Plugins

Beta: a project supervisor for DeepSeek Harness — standing rules plus a Web panel (three switches, dispatch modes) that splits a goal into parallel teammate dialogs, checks engineering baselines, interviews new-project requirements and protects beginners. The standing rules come from the repo kit installer, an optional separate step.

Connects a ComfyUI server to the agent through five draw_* tools (status, workflows, models, generate, reverse) and a sidebar panel. It ships no workflows and assumes nothing about your models: every API-format JSON you drop into the workflow directory is inspected to find where prompt, negative, width, height, steps, cfg, seed and LoRA live, and a sidecar file can override what was detected. LoRA injection splices into any graph. All paths are configuration, editable from the panel and saved to a settings file, so it works against a remote or already-running ComfyUI. Headless auto-start and idle shutdown are opt-in and off by default.

Production pack for ComfyUI inside DeepSeek Harness: submit API-format workflows to a local or remote server, batch-generate and fetch outputs, and diagnose bad images with measured parameter ranges and a failure-mode decision tree (black frames, duplicated subjects, color fringes, OOM).

Memory that outlives the session, kept as plain daily log files: one markdown file per day plus a generated index the agent greps instead of re-reading. Registers the annals skill, injects the write-it-down rules into the system prompt, and exposes three tools — annals_init builds the log directory, the index generator and a separate Git repository in one call; annals_query full-text searches past entries and returns them with file and line anchors; annals_links resolves which entry cites which. Reminds the agent once per turn when it changed files but wrote no log that day, and once more when the log was updated but the index was not. Adds a settings page for the six switches.

Adds a connection-test panel under Settings -> Models: reads the deployment's model catalog and probes each configured model with one minimal chat round-trip (a short "ping" with a small output cap) through the Host LLM service, verifying connectivity with a real request. Each row reports success/failure with the harness failure code (NO_ADAPTER, MISSING_CREDENTIAL, AUTH, RATE_LIMIT, TIMEOUT, ...) plus first-token/total latency; single-model and concurrent test-all (3) are supported. Credentials are resolved inside the Host process and never reach the browser; probes are independent per model behind a same-origin-fenced route with a body-size cap. Pure JS, no build step, MIT.

Rates how hard the current message is and shows the cheapest model and reasoning effort that still fits, above the composer, before you send.

Orihime golden-hour skin for DeepSeek Harness: a two-layer illustrated backdrop with a sidebar workshop for composition and sharpness, amber message bubbles and a cream letter-paper composer.

Per-model API price table with Peak and Off-Peak rates in USD or CNY, the DeepSeek account balance and live session spend under the composer, an all-time total, a collapsible source URL and check date per model, and optional per-model Peak schedules.

Native Anki workspace backed by one real headless Anki collection: browse, edit, add and review notes, suspend cards, import and export APKG, and sync with AnkiWeb, with the same collection exposed to the anki AI tool. No Anki desktop app, AnkiConnect or Qt is started. Windows x64 only; the matching headless Anki core, CPython and all Python runtime dependencies are bundled, so no separate Anki or Python installation is required.

Adds an Optimize button to the composer that rewrites a one-line idea into a structured product brief: a positioning sentence, 3–6 key features, visual references and design tokens; it sits beside your original text in a compare dialog where you can accept it into the input, generate another version, or cancel and keep the draft untouched. No settings page and no API keys — it calls the model channel you already configured.

Transforms DSH into a dual-column Codex workspace with an integrated Activity Bar, unified topbar, avatar quick access, session history navigation.

DeepSeek Harness's own fast mode: a few configs that set how fast a task runs — bound where thinking settles, bound the process narration, bound the steps per task — faster delivery without touching the model or its thinking strength. Measured over 10 task families and 30 complete units: the default reaches 0.72x total time, 0.74x output tokens and 0.71x steps; moving the "write it once" reminder from step 4 to step 2 gives debugfix 0.535x, ledger 0.506x, migrate 0.751x, and 0.625x pooled over 13 pairs with 0.614x output tokens (migrate alone 0.509x with 0.528x output at step 3). Hidden tests passed in every pair. Short 1-5 step repairs and data reshaping do not pay for the reminder, so try it once per task shape.

Bridges a OneBot QQ bot into DSH: the owner's direct messages open a session on the same home, answers go back to QQ, and files named with \[SEND_FILE: path] are delivered. Needs a OneBot v11 implementation with a forward WebSocket (such as NapCat) and ownerId set in the config, otherwise every message is ignored. The home it shares with the main session is provided by the separately installed dsh-wakeup plugin. It also runs an unauthenticated local status endpoint on 127.0.0.1:3002 with open CORS that returns the owner QQ number, the login QR code and recent log lines (including the first 60 characters of incoming messages).

A work assistant for WeChat: it records what you tell it into a SQLite task ledger, ranks items by urgency, reminds you on schedule, extracts people and their relations from your notes, and hands tasks to separate assistant sessions. Ships its own WeChat bot channel (scan to log in; private chat only) and a full-page dashboard.

Review AI-generated Word, PowerPoint, PDF and HTML in the official preview: box problems, edit the text in place, and hand the notes to the agent. PDF and images are annotate-only; editing relies on the Harness bundled LibreOffice kit and Python.

Cross-session memory for DeepSeek Harness: a three-tier store (behavior notes, deep details, session archive) plus a 600-character core card injected every step, work/companion/learning state lines, multi-person and multi-group records with visibility partitions, session-scoped suppression or deletion of memory fragments, summaries and fact candidates that can route to a separate model, and backup plus self-check tools. Data is plain text under the home directory, and entries can carry images and audio stored by content hash.

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.

Edit and regenerate: adds an edit action to user message bubbles, regenerating from that message with images and files carried over and the original model inherited.

Import your own fonts, set three sizes and six weight stops, and pick a separate palette for body, chat and hint text — an Aqua glass theme for DeepSeek Harness 0.2.1-rc.3, with adjustable blur and frost, a fluid or image/video wallpaper, per-region text tuning, and a switch that restores the stock UI. Continues the Aqua theme by WYH66666666 (DSH-Transparent-UI-Plugin v1.3.0); do not install alongside the upstream.

General Agentics distribution bundle for DeepSeek Harness (DSH): one install brings the General Agentics white-label brand, curated plugins, bundled skills, and MCP pre-configuration. Built on DeepSeek Harness (DSH).

Generate images and frontend HTML demos through a real ChatGPT Pro web session, saved locally with a design gallery panel in DeepSeek Harness.

模型故障转移队列：P1 限额/限流/不可用时自动切到队列下一个模型继续，全部图形界面配置 | Model fallback queue for DeepSeek Harness: auto-switch to the next model when the current one hits quota or rate limits

Two buttons beside the chat input: one rewrites the draft with the current directory in view, the other inserts a role template from 85 curated entries generated from the bundled `agents/` role library, which the settings card can extend with your own `.md` role files.

Multi-agent Chinese debate simulator with eight debaters, live two-column discussion and draft notes, judges and scoreboard, single-side clocks, per-round ZIP archives, a training side with a configurable end condition (win-rate threshold or fixed rounds), and a Word prep package.