Plugins

A batch workbench and six-step wizard for the PDL engine: group raw well files by well, merge them into delivery tables, and export GeoEast-ready load packages, with run records and reference libraries.

DSH 插件开发测试工作台：写插件时装上就能用。生成脚手架、七层检查、沙箱四阶段测试。装不上的原因（inject 写错、output schema 不合法）会直接告诉你在哪一层。

ZenTao workbench for DSH: load a ZenTao browse-page URL into a panel, multi-select bugs, tasks and stories, and hand them to the current or a new session with description, recent comments, screenshots as real image attachments and other files saved locally; when the agent is done it writes comments and status transitions (resolve, close, activate, start, finish and so on) back into ZenTao, one item or a batch, from the panel or through five registered agent tools (bug write-back verified end to end, task and story forms share the same code path).

LeetCode practice bench in the DSH sidebar: live problem bank fetched from leetcode.cn, Java editor with completion and one-tap submit, plus copy-to-chat AI coaching.

Automatically discovers the local Magpie gateway to sync chat models, enables Codex and Gemini image generation, and configures image sources for eligible workbenches.

Runs N serial speedtest rounds in one unchanged environment from the plugin detail page, then reports per-round tables with median, min, max and MAD, and keeps each batch as an archive that can be renamed or deleted.

Disk, CPU/memory/GPU, listening-port and token-usage cards with a full-page zoom; runs as a workbench module or standalone. The port card works on Windows only and the GPU card needs nvidia-smi.

Paper libraries and literature management tools with nested collections, PDF imports, local metadata, reading, translation queues and optional ink annotations. An extension of GGboya/dsh-paper-reader 1.6.1 that reuses its default data directory (~/.dsh-paper-reader/data), so back up the library before migrating and enable only one of the two in a profile, because tool names and routes clash. Needs Harness 0.2.2-rc.1 and Node 24.9 or later; the ink annotations use tldraw, which needs a tldraw license key that you obtain and enter yourself.

Project workbench for DSH: groups sessions by project (workspace) in a panel with project cards and session lists, applies a project's default preset, model and reasoning effort to new sessions, scopes memory per project on request, previews AGENTS.md/CLAUDE.md read-only, and groups the sidebar by project at startup.

Runs a complete HR workbench inside DSH — a 3D office, recruiting pipeline (resume, interview, written test, score), employee roster, files, attendance, performance, training and analytics — with the site’s AI assistant answering through the model DSH already runs.

SSH workbench for launching remote agent CLIs with durable sessions, terminal, file editing, Git worktrees and local port forwarding. It drives the local OpenSSH client (macOS/Linux; remote Linux with GNU coreutils, tmux optional) to run commands, edit files and forward ports on any host from ~/.ssh/config, with host-key checking defaulting to accept-new; the last 512K characters of each terminal's output are saved under ~/.dsh/remote-agent/terminals. It uses the same package name and mount id as zbzbhs/dsh-remote-agent, so the two collide if installed together.

Godot game development workbench for DeepSeek Harness. Windows only, preview release: plans a game (GDD, tasks, acceptance checks), changes project files through controlled read/write tools, diagnoses the project and runs it for evidence. Runtime and import checks launch your configured Godot as a normal process with your permissions (the AppContainer sandbox applies only in the restrictedProduction option); the official Godot 4 standard build can be downloaded on request after confirmation (SHA-256 checked), creating a project registers it in Godot's project list, and the selected project context is sent to your configured model.

Track, branch, compare and reproduce local CSV classification and regression experiments through DSH tools backed by MLflow; requires a separately installed Python backend. By default training runs as detached local worker processes that keep running after DSH exits (executionMode dsh stops them with DSH); running your own Python preprocessing or estimator code needs allowCustomCode, which is off by default; the plugin makes no network requests.

Manage iterative text annotation through DSH tools with rule versions, stale-result isolation, human review preservation and traceable exports; requires a separately installed Python backend.

Postman-style HTTP workbench in the Harness Web GUI: collections and environments with {{var}} substitution, a request builder covering method, params, headers, body and auth, a response inspector, cURL import and export, and a CDN origin probe that fetches the same URL twice so a deleted file can be told apart from an edge cache. It also exposes an http_request_desktop agent tool that shares the panel send path, so a request debugged in the panel can be replayed by the agent. Zero runtime dependencies; state lives in $DSH_HOME/postman-desktop/store.json.

Runs a four-task, 150-point model intelligence benchmark inside DeepSeek Harness (Qin 60, Pompeii 45, Pelican 22.5, Candy 22.5): each selected model × reasoning-effort pair executes every task in its own isolated subagent session, Qin and Pelican are graded by the selected judge model against rubrics, Pompeii and Candy programmatically, and batches keep scores, artifacts and cost. Adds a 0–1000 real-world performance score per model × effort computed from local session logs across seven dimensions (output speed, first-token latency, reasoning speed, tool cadence, tool latency, tool success rate, cache hit), with baseline deltas and controlled speed runs, plus a sidebar page with ranking, performance, history and settings views. Each batch spends real tokens of the candidate and judge models, and candidate subagents get file and bash tools inside an isolated run directory.

Visualizes Finesse 3 KatScript in the conversation and adds a drag-and-drop optical bench designer that generates the Finesse model. It scans every user and assistant message for KatScript or a Finesse Python cell and renders them in the background with the first Python interpreter that can import finesse (Finesse 3, NumPy and Matplotlib required; interpreter overridable with FINESSE_VIZ_PYTHON), keeping the code and figures under ~/.dsh/finesse-vis.

DeepSeek Harness plugin: AI research toolkit — model release radar, model benchmark & community report, and AI news digest (4 tools + 3 skills).

Bridges the official IAR C-SPY MCP server into DeepSeek Harness: build .ewp projects, start simulator or hardware debug sessions, and read variables, registers, memory, the call stack and target output from the conversation. Windows only, and it needs an IAR Embedded Workbench installation. Setup needs Python 3.10+, Git and network access to GitHub and PyPI.

AI-assisted research workbench with editable step workflows, on-demand skill binding, a live execution graph and in-project document review (needs a local Python with python-docx, python-pptx, openpyxl and PyMuPDF), while keeping existing projects on their original configurations. Requires DSH 0.2.2 or later.

Write, illustrate and hand off WeChat and short-video content from one workbench, with per-image versions and draft push.

A local mirrored A/B benchmark for context compression, not another compressor. It runs one fixed read-only scenario twice with the same model and temperature — compression off, then on — and reports input tokens, turns, tool-call success, fact coverage, answer similarity and a per-line diff, with JSON, a self-contained SVG and raw warnings. 18 node --test tests, zero dependencies. The first measured run: 63,029 → 6,927 locally estimated input tokens (−89.0%), 3 → 3 turns, facts 3/3 → 3/3, answer similarity 1.00 on one sample.

Amazon product research workbench for DeepSeek Harness: category, brand and follow-seller collectors driven through the local Edge browser, a product library with unified filters, an FBA/FBM/self-operated profit calculator, blue-ocean category scoring with candidate picks, trademark lookup, supplier image search and Excel export. Proprietary software: it installs and starts without a license, but every data call returns 403 until the author issues a device-bound license key. Needs Edge started with --remote-debugging-port=9222 and signed in to Amazon; starts a local backend on port 3088. The separate 智赢 collector browser extension is optional and adds size, weight, trademark and monthly-sales fields.

dsh-插件｜一个专业的医院感染病例分析工作台