Plugins

Poste de travail de bureau auto-modifiable pour DeepSeek Harness : une réplique complète de dsh web avec un mode édition dans lequel l'agent modifie le poste de travail (couches de patch, plugins, UI) avec rechargement à chaud.

Le gestionnaire de plugins `dsh pm` : recherche multi-source (liste awesome + GitHub + npm), installation/suppression/mise à jour par profil, et un audit doctor des manifestes, des patchs de bundle et de la dérive de version.

Convertit le Markdown en une page HTML autonome et complète : un outil `md_html_render` qui fonctionne en profil headless, plus un tiroir web pour parcourir, prévisualiser, éditer et exporter des fichiers `.md` locaux ; les deux partagent le même moteur de rendu, sans dépendance à l'exécution.

Audit en lecture seule de l'hygiène des identifiants d'une flotte d'agents : permissions des fichiers d'identifiants, identifiants intégrés dans les remotes git (masqués dans la sortie), et comptage des jetons de fournisseur en clair ; sans dépendance et déterministe.

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

SenseNova connect family bundle for the Harness Web UI: Token Plan credit panel (per-pool quota windows, per-model consumption, self-renewing console token) plus optional provider registration that brings SenseNova models into DSH conversation, with host-

Coding-learn floating panel: edits and runs Python/JavaScript/TypeScript/PowerShell with exit code and timing, grades JSON course lessons with progress export, keeps Markdown notes and snippet library, and sends code plus a question into the current conversation for the main model to answer.

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.

Realtime model usage panel: tokens, cost, requests, trend and composition, with editable pricing.

MCP server manager for DeepSeek Harness: add, edit, enable and test stdio / Streamable HTTP MCP servers from the Web settings page and from agent tools, connected and disconnected at runtime without restarting DSH

cc-switch-style global prompt for DeepSeek Harness (dsh 0.1.5): one user-editable block injected into the system prompt of every conversation, mirrored into each session project's AGENTS.md, and naming the harness's user-global AGENTS.md by absolute path

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.

Legal knowledge-base workbench: hybrid keyword/statistical/vector retrieval over local statute .doc/.docx corpora, faceted filtering, charge-name and civil-cause trees, a document editor, and four AI tools (citation check, contract review, AI analysis, AI drafting).

In-place prompt editing in the web chat: cleanly forks session history at the edited turn, preserves image and file attachments, and auto-archives the superseded branch.

Audit DSH skills automatically: a host-layer tools/post-execute plugin that ships both the skill body and the audit engine, runs the engine after skill files change (write/edit/shell) or after a bulk restore/backup (any tool invoked with mode: restore|bac

Shared infrastructure for data assetization plugins: business rules loader, file format adapter, report generator, path validator, audit logger Also known as @deepseek-ai/dsh-data-asset-shared.

Approval-free writes into whitelisted directories — wraps the filesystem fence for write/edit tools and auto-answers bash sandbox escalations that touch whitelisted paths, with a settings GUI.

Personal-experience memory for DSH: turns solved tasks into sourced problem cases with condition-scoped claims, recalls them into new tasks via hidden pre-step injection, and makes corrections/deletes cascade to future recall.

Brings the Codex (ChatGPT Plus/Pro) subscription already signed in on this machine into DSH. It (1) shows the 5-hour and weekly windows with their reset times and the remaining reset credits in a sidebar panel, with one-click reset that consumes a credit; (2) registers the subscription route in llm-pi-ai (openai-codex) when the quota is read, so the Codex models appear in the model picker; (3) refreshes the OAuth access token before expiry and writes it back atomically, so no key has to be replaced by hand; and (4) adds a codex tool that delegates a task to the local Codex agent. No API key has to be entered.

Shows the active model's usage and remaining balance in the session header: OpenCode Go plan usage (rolling, weekly, monthly) with the selected model's monthly cap, Command Code 5-hour and weekly window usage with remaining credits, and DeepSeek account balance.

Session change-review for DeepSeek Harness: tracks write/edit tool calls and renders VS Code-style side-by-side diffs via diff2html, auto-following the theme, with subagent aggregation and one-click revert.

Contract check for DeepSeek Harness plugins: statically verifies that registered tools' output.render() returns ContentBlock[], and warns when a session event type falls outside the kernel vocabulary. Warn-only. 契约体检插件（不检测恶意）。

Standalone DSH plugin for PPT authoring, template selection, validation and editable PPTX export

DeepSeek balance and per-session token usage in the session header, with a three-level balance alert and editable thresholds, one-click top-up links, a segmented token bar with cache-hit statistics, and a visibility-aware poller.