Plugins

Windows desktop automation for DeepSeek Harness: accessibility-first observe/act loop with 30 standard tools (element/coordinate targets, auto/a11y/event strategy routing), superseded-observations and no-replay safety semantics, persistent kill switch, RuntimeId/rect-drift stale protection, chat cards and a floating panel (live ops, frame wall, env auto-detect settings), tiled vision describe for low-res models, JSONL audit trail and a pid allowlist. Requires Windows 10+ and Python 3.9+ with uiautomation and pillow (installable from the settings page).

Cost panel for DeepSeek Harness: meters every request from session events, prices it against a built-in catalog of 136 models across 16 providers, and shows the current model, account balance, session, today and month spend plus a monthly budget bar next to the composer. Bilingual zh/en.

Read-only Odoo tools over JSON-RPC: server info, model field introspection, and a restricted search_read limited to an allow list of models whose domain field names may not contain dots, so related-record traversal is not possible. A draft-create tool is registered only when allowWrite is enabled, and is limited to sale.order and project.task with the draft state enforced by the plugin.

Grok Build provider using the official CLI browser login, with dynamic account-visible models, streaming reasoning and tools, plus quota and model-capability settings.

Displays CodexRadar model capability benchmarks in a Settings page and shows the selected session model's DeepSWE score beside the composer.

Register models, assist with portraits, and select the Agent model from a secret-free catalog for DeepSeek Harness.

A document preview / edit / management plugin for DeepSeek Harness. It provides a VSCode-style "Document Center" workbench inside the DSH Web GUI: a file tree on the left, click-to-preview, editable code & Markdown with Ctrl/Cmd+S save; and exposes three document tools (doc_read / doc_edit / doc_create) to agents, letting models read and write workspace documents through natural language.

DSH 模型检测：对任意 pi-ai 提供方，拉取其线上最新模型清单，并用 models.dev 自动富化正确模态/容量/推理后写入该提供方

A pixel companion living in the chat area: hatches from an egg into one of three sprites or an LLM-drawn custom one from a text description, platform-jumps over message bubbles on its own, WASD controllable, chats in character through the models you already configured, and carries a nurture system (mood/power/health, levels, shop) driven by real token usage.

Local-memory lifecycle for the official Hindsight plugin on DSH desktop: one-click start/stop of the hindsight-embed daemon, auto-start on boot, stop on exit, hides the uv.exe console window, and installs the vault/models to another drive.

World-model research toolkit: inspect frames, name 3D / pixel / latent routes, score pred vs GT, and RSI skills / wm.yaml.

Model-facing `generate_image` tool for text-only models: the model asks for a picture in natural language, Gemini draws it via the Antigravity CLI, the image is saved to a configurable output directory, and the tool returns the file paths for the model to use in its work.

OpenCode Zen free models provider for dsh

DeepSeek Harness plugin: import models with capabilities from an OpenAI-compatible /v1/models listing (gateway capability extensions) and edit per-model capabilities (thinking, vision) on its settings page

Composer-attached images are transcribed to text by an OpenAI-compatible vision model before reaching text-only DeepSeek models.

Side-by-side model comparison for the DeepSeek Harness Web UI: send one prompt to 2–4 models in sibling sessions forked from the current one, watch the answers stream in columns (tabs on phones) with latency, time to first token, tokens, and cost, then co

Personal dsh preferences: a tunable companion to the official compaction engine (threshold, retention, summarization model/reasoning, turn-end compaction), llama.cpp model import for the Models page, and tab/notification helpers (status-light favicon, bro

Drive DSH from anything that speaks HTTP: 47 routes (REST + SSE) for workspaces, sessions (create/prompt, live SSE generation, history, stats, todos, cancel, ask-user Q&A), models and the global default model, providers, agent presets, settings namespaces, skills, and workspace files including resumable chunked upload — plus an OpenAI-compatible /chat/completions, a built-in OpenAPI 3.0 spec and an interactive request page. It only injects the host webServer and tools, so it rides on the DSH webserver (default prefix /api/v1) or its own port with optional API-key auth, and it ships a skill that teaches the DSH agent to call the API.

Bitmap-frame context compression plugin for DeepSeek Harness: renders discarded conversation history into pixel-font PNG frames for vision-capable models.

DeepSeek Harness (dsh) plugin: live NVIDIA GPU monitor in the web rightbar. NVML-first on Linux (nvidia-smi fallback). NVIDIA only! Not AMD/Intel/macOS. Multi-GPU util/VRAM/power/temp, processes, sparklines. Installable dsh.bundle.

Replaces the built-in llm-pi-ai and llm-deepseek adapters, the model selector and the Models settings page with self-maintained versions, tracks upstream @earendil-works/pi-ai through a safe-zone download with a one-click enable toggle, and adds provider quota and balance lookups plus a provider management page.

Task monitor plus remote chat for DeepSeek Harness. Read sessions, background jobs, subagents, goal rounds, workflows and pending approvals from a phone-friendly page, and talk to any session from it: streamed replies, tool-call progress, stop at any time, switch sessions and models. Also ships a GUI sidebar panel.

Same-origin in mechanism with the two loudest lines in context compression. The code-skeleton gate follows the skeletonization approach of Headroom (Apache-2.0), whose published headline is 20% fewer tokens for coding agents and 60–95% fewer tokens for JSON, same answers. The estimator channel follows TokenPilot (arXiv:2606.17016), which reports up to 60% lower cost for long-session agents. Both figures are theirs, quoted as-is; this plugin ships no benchmark of its own and claims no reduction of its own. What it adds for DeepSeek Harness: choose a compression profile, set the Auto Compact trigger level and toggle code-skeleton compression from one settings section, with exact DeepSeek V4 tokenizer measurement, same-revision count verification, and fail-open behaviour that keeps the original tool results on unsupported models.

Dense translucent-glass Universal Palette for DeepSeek Harness Web — federates Commands, Models, Sessions and Conversation Hits with deterministic ranking and verified public-contract interoperability.