Plugins

fal.ai native image generation for DSH: a FAL_KEY settings card that follows DSH's language (zh/en, English default) plus Agent tools (fal_generate_image async / fal_edit_image / fal_get_image_task / fal_list_image_models) that call queue.fal.run directly

Escalation-only LLM reviewer: reviews sandbox escapes only, keeps the sandbox, fails closed.

中瑞世联工作台 / CRWU audit workbench for DeepSeek Harness: pick a pending audit report, dispatch one AI audit subagent, watch and stop/restart it, auto-upload deliverables to Aliyun OSS.

树形任务流：把多步任务组织成目标→任务→子任务三级树，节点完成时由 AI 提交结果，插件随即把该节点的执行过程从上下文里折叠掉，只留下结果。

Watches Feishu (Lark) conversations with your own user identity and forwards new messages as prompts into a chosen DeepSeek Harness session: per-monitor sender filters, @bot-mention bypass and keyword allow/block lists, auto-created pinned target sessions, and cursor-based polling that re-reads messages after a failed delivery.

Model relay station for DeepSeek Harness (模型中转站): serve any registered DSH LLM provider (e.g. @tnnevol/dsh-codebuddy) over an OpenAI-compatible /v1 API, so other projects can call those models with a standard OpenAI client.

DeepSeek Harness (dsh) host adapter for anysearch: thin Cordis bundle — hooks layer only, all business logic stays in the anysearch server over 127.0.0.1 HTTP IPC

dsh plugin: unattended approval gate — subagent/scheduled/cron approval requests get a bounded answer window, then settle with a fail-closed default instead of hanging forever (per origin or per session)

Converts Mermaid flowcharts into GB/T 1526-1989 (ISO 5807) compliant SVG through one model-facing tool, with optional A4/A3 pagination.

DeepSeek Harness (dsh) plugin: an ambient pill under the composer showing whether your selected DeepSeek or z.ai plan is billed at peak or off-peak (half-price) rates right now, with a click-to-open schedule panel. PS: No human touched this code

Harness-neutral Traditional Chinese enforcer + offline converter (skill, DSH bundle, CLI). One script axis either way + Cantonese/Japanese-only filters. Converts both ways; optional wording preference. Also: an LLM output guard, cp950/GBK console scan.

Beyond the built-in @: line ranges (@src/a.ts:12-40), skills, plugins and any git repo — with the token cost of each reference shown before you send.

Theme studio for the DeepSeek Harness web GUI: eight switchable preset styles, accent and panel-translucency fine-tuning, host-side wallpapers painted on the first frame, and a one-click fix when the wallpaper-engine glass tint greys out light styles.

Legal training workbench: three-pane academic UI that reads the "Minglü" (lawagent preset) learning profile (case dossiers, flashcards, wrong-answer book, notes) and sends instructions into a Minglü session with one click.

A newspaper-style front page for a session you left running, as a Conversation View tab beside Chat and Trajectory: a per-turn timeline (duration, steps, tools, tokens, outcome), file churn counted per file, where the wall clock went and how much of it was the model rather than tools, which single turn ate the spend, failures nobody retried quoted with their failing command, and a context-pressure gauge measured against the routed model's own declared capacity. The briefing is folded from the durable session log and never generated by a model, so it costs no tokens, cannot hallucinate, and is byte-identical for the same log and clock; it appends nothing to the session and reaches no model, and it reports a pending approval without ever answering it. Pages are offered only when they have content, and the tab refreshes itself on turn settle and on a two-speed poll backed by a metadata-only tail probe.

Paper library and reading workbench: arXiv search, a local plain-file library (metadata / PDF / extracted full text), and three-level reading notes (overview / understanding / critique) kept as markdown beside the PDFs; seven model tools plus a web panel.

Matrix digital rain: drapes the chat window in the classic green character rain — cascading columns with incandescent white heads and green tails, streaming the tokens the agent is generating into the rain in real time; opacity, speed, density, font size and colors are all adjustable, and rain intensity follows agent activity.

Gemini provider for DeepSeek Harness on Google Cloud Vertex AI, with Application Default Credentials, streaming, and thought-signature replay across tool calls.

DSH 本机代码包依赖图谱（开发工具）：把已安装的 @deepseek-ai/* 包与第三方插件的依赖、挂载关系画成区-组-包三层交互图，支持聚焦、拖拽布局与中英切换。零运行时依赖，内置 cytoscape，断网可用。

LESSONS.md (AI mistake notebook) visualizer panel for DeepSeek Harness Web UI — browse, search and review your AI mistake notebook entries by level and recurrence.

Model relay station for DeepSeek Harness (模型中转站): serve any registered DSH LLM provider (e.g. @tnnevol/dsh-codebuddy) over an OpenAI-compatible /v1 API, so other projects can call those models with a standard OpenAI client.

DeepSeek Harness (dsh) plugin that connects Sber GigaChat models: a built-in local OAuth proxy (client-credentials -> OpenAI-compatible endpoint, upstream serialization, legacy tool-calling translation) plus automatic provider-route bootstrap, so GigaChat