Plugins

Show the image a read_image call returned, inline in the tool row it belongs to

General file previewer for DeepSeek Harness: after an agent turn produces files, the produced-files row expands vertically and one click opens a right-side panel that renders markdown (official MarkdownText), syntax-highlighted code, csv/tsv tables, text,

Turn a paper into an academic talk for DeepSeek Harness (dsh) — 论文转 PPT / 组会汇报 / 会议报告 / 答辩 / 开题. Reads the real full text, budgets the slot per venue, and builds the deck around the figures with the speaker notes written as the script. Drives dsh-ai4schol

DSH Web UI 插件：每轮结束时汇总本轮所有文件修改差异

dsh plugin that turns the iterate skill into an autonomous closed-loop harness: plan -> parallel review xN -> atomic fixes -> validate -> loop -> auto-stop, plus a dry-run pure-review mode with multi-round convergence and a meta-review that audits the rep

Installation safety gate for DSH plugins: antivirus-style scan of install scripts, permissions, secrets and network callbacks on local directories or npm tarballs, returning a BLOCK/WARN/PASS verdict before "dsh plugin add".

Verifies that Cordis-managed runtime resources return to baseline after isolated plugin teardown, with deterministic cleanup receipts.

System-level desktop notifications: turn-completion and workflow-end banners, plus a modal alert when an approval is needed (macOS osascript / Linux notify-send).

Native Windows system notification (Notification Center toast) when a task completes: goal completion or agent turn end.

Ambient fullscreen status grid for DeepSeek Harness sessions with token/rate graphs, plus ntfy push and alarm notifications when a turn ends, errors, or waits for approval.

Two-way Feishu (Lark) chat bridge for DeepSeek Harness over the official WebSocket long connection: messages route to the bound workspace's latest session and replies return automatically; bot credentials and workspace routing are configurable from the settings page.

Event-sourced cross-session work ledger: register, track and settle tasks with full audit history, kanban export, and a board digest injected into every model turn.

Document workshop skill pack: four pure-prompt Agent Skills that turn a codebase into READMEs, PR descriptions, changelogs and code reviews, installed into dsh via a dsh.bundle plugin row.

Human-in-the-loop tools (`human_task` / `human_task_ready_check`): pause the agent until the user performs a real-world action or returns an observation (GUI operation, game testing, visual verification, hardware checks), gated by session consent and an AFK presence check, returning a structured JSON result via a web task dialog.

Turn any SVG logo into a motion video inside DSH: an `animate_svg` tool renders a transparent 30fps assembly animation (parts fly in, or the whole mark settles) and synthesizes an MP4 with ffmpeg.

Turns markdown into a WeChat Official Account (微信公众号) draft: inlines every CSS rule onto its element because the editor discards `<style>` blocks and class names, uploads each local image through WeChat's own endpoint so it is not filtered out, and creates the draft; it never broadcasts.

LLM-driven remember/forget memory: after each turn a model decides what to keep (MemoryDirector), injects relevant memories before each step, dedups, and persists cross-session.

Automatically starts a fresh Web session near the context limit with the last complete turn, and adds an editable additive whale-maid persona with on-demand reload.

Clippy ha vuelto, y esta vez sí que puede ayudar. Una mascota asistente de oficina que reacciona al estado real del agente, salta cuando el turno se completa, y abre un clásico diálogo de «operación ilegal» cuando un turno falla.

Presupuestos de cierre seguro por turno para pasos, llamadas a herramientas y tokens de proveedor en DeepSeek Harness

Lectura del saldo de la cartera de DeepSeek en el pie de la barra lateral: icono de tarjeta + importe, coloreado según el estado, actualizado al final del turno y al hacer clic

Proveedor de búsqueda respaldado por la API de Brave Search para la interfaz de capacidad web de DeepSeek Harness (ctx.web). Cada búsqueda es una solicitud HTTP, sin consumir un turno del modelo.

Puerta de revisión de código con IA local: revisa un diff de espacio de trabajo/rama/commit mediante el ocr.js gestionado, devolviendo hallazgos estructurados con estadísticas de tokens; el modo de puerta falla si hay hallazgos.