Plugins

Security-audit facts AI coding agents cannot compute, plus a verdict gate: euthyna history attributes deleted lines to commits and flags those from security fixes (--origins finds the first introducer), euthyna coverage reports which changed symbols no test ever invoked, and euthyna gate checks each finding against six gates, downgrading any without evidence to an observation.

TypeSafe Jev (modelo de decisão System One) para o DeepSeek Harness, de ponta a ponta: jev_decision (choice/score/noul, paralelo, respostas tipadas + confiança), um cartão em Settings > Plugins para a API key e chaves de liga/desliga, visualizações inline de ferramenta mostrando cada decisão na conversa (resposta, confiança, latência, custo), um auto-guard (checagens determinísticas + de risco/loop do Jev), um dashboard local /jev e um benchmark de verificação online (96,3% em 27 perguntas rotuladas, mediana ~283 ms no jev-latest, 2026-09-21). Honesto por design: só API real, sem fallback simulado.

Ren'Py galgame production workbench: a host-side project service (write gateway plus git snapshots, a dialogue/scene dialect parser, derived progress, human-only review stamps, pinned-SDK validation and playtest, local publish) behind one seam, driven by an embedded web panel and agent tools.

Long-form novel writing plugin: each book is a git repository of frontmatter files, with 39 DSH domain tools and a web writing UI. Deep import drafts candidates, AI adoption into canonical assets requires DSH approval, and deterministic continuity checks ship with a report-only benchmark. Independent open source (MIT), not an official DeepSeek product; requires Node >= 24.11.0 and currently targets DSH 0.1.2-rc.1.

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.

One MCP tool instead of every schema you own — a lazy capability broker that cuts resident tool context by a measured 94.4%. Search, inspect, enable and call MCP servers and skills on demand.

Compares existing DSH sessions or runs controlled A/B trials between agent presets, showing aligned timelines, paired metric deltas, explicit success checks, and exportable reports.

Fullscreen business-app framework for DeepSeek Harness Web with a dark-sidebar workbench bundling a database connectivity tester and SQL query panel, a two-level knowledge base (bill and accounting) with local search and Word document ingestion, metadata environment comparison with alter-SQL generation, a data dictionary, agent log-search report demos, a system test-case runner, Evernote-style notes, developer utilities, and mini-games.

Image generation workbench and agent tool for DSH: one tool (ark9_generate_image) paints text-to-image and image-to-image via any OpenAI-compatible API. Channels are entirely user-configured - no bundled endpoint, you bring your own baseURL, key and model name (manual input supported). Agent-initiated generations are approval-gated by default: requests queue in the floating panel and nothing bills until you approve; approval is non-blocking (the agent replies "awaiting your approval" immediately, and results, denials or timeouts are injected back so the agent reports them in the next turn). Floating glass workbench with five tabs (Generate / Approvals / Prompts / History / About), aspect-ratio grid with quality-budget + 16px-alignment sizing, transparent background, batch up to 10 images as aggregated sub-tasks, prompt library with custom JSON sources fetched through a host proxy, persistent generation logs with one-click retry, multi-channel aggregation with per-channel model fetching, bilingual UI (zh/en), stroke-SVG icon set, config import/export. Registers as a Better Sidebar tab when dsh-better-sidebar is installed; stacks above the dsh-cua FAB when both are present.

A terminal workbench for dsh with streaming chat, tool execution, session management, provider management, and image input.

Conversation-level multi-agent workbench for editable task planning, real child-session observation, plan-versus-runtime comparison, and evidence-backed recovery previews; tested with DSH 0.1.1-rc.2.

Verifiable issue-to-PR delivery chain: an 11-stage pipeline (analysis, search, code understanding, hypothesis, planning, implementation, patch ledger, tests, review, failure classification, PR build) with 4 human review gates, GitHub/GitLab/CodeArts credential connections, a 5-page workbench and a draggable AI assistant panel.

A living memory workbench for DeepSeek Harness: watch the Hindsight bank grow (7-day curve, recall heat, timeline) and manage knowledge pages and background tasks, with the local daemon auto-started by the plugin.

A permanent DSH plugin that bundles a developer workbench, an in-session conversation tree, and a plugin manager: build and run an LVAL project, browse its code, and keep per-program version snapshots with rollback; edit, retry, or branch any message in place, with message micro-versions; a feature manager plus a global-plugin library whose entries each carry an enable tier; cross-dialogue memory, one-shot temporary chats, and model collaboration; five network-permission tiers, mixed-model routing, a security audit, and browser control through a companion extension.

Piano performance plugin: ask the agent to play a piece and it renders on a Canvas2D grand piano with real Salamander Grand samples, an immersive stage, and an interactive 88-key keyboard.

AI-driven source-code security scanning workbench: 5 model tools (start/finding/status/report/list) plus a /hawkeye web UI and JSON/Markdown/HTML vulnerability reports; zero-dependency Cordis plugin, installable as agent preset or npm package.

Experience validation layer for DSH: zero-token collection of tool-failure/retry/search signals, AI refinement into verified skill books (three-layer verification), looked up at task start. Ships 10 trial skills and benchmark data (complex-task success 100% vs 60% bare).

Adds quick installation and switching for workbench templates in DSH Desktop.

Enterprise workbench for DSH: manage AI employees, knowledge bases, skills, MCP servers and DSH plugins from a running session.

Bancada Git no estilo Codex: alterações com escopo do workspace, diff, stage, commit, operações de branch protegidas, histórico em grafo, fetch, pull fast-forward e push para upstream por meio de APIs oficiais de plugin.

Um sistema de acoplamento com qualidade de bancada para os plugins web do DeepSeek Harness

Uma bancada de trabalho de projetos e IA estilo desktop para DeepSeek Harness

Suíte de escritório confiável para trabalho governamental/empresarial da Beijing Caizhi Technology (深知可信智能): três habilidades — consultoria confiável (Q&A de políticas/regulamentos com marcadores de citação + HTML de procedência), busca confiável (recuperação de políticas/padrões autoritativos com HTML rastreável + Markdown limpo) e redação de documentos oficiais (minuta/reescrita/Word/entrega com timbre); todas as interfaces passam pelo MCP do ambiente confiável dknowc (auth Bearer), os produtos chegam ao espaço de trabalho da sessão e a configuração de chave persiste para sessões futuras; publicado no npm como dknowc-dsh.

Bancada de trabalho de desktop autoeditável para o DeepSeek Harness: uma réplica completa do dsh web com um modo de edição em que o agente modifica a própria bancada (camadas de patch, plugins, UI) com hot reload