Plugins

Caixa de ferramentas local para a interface Web DSH: 35 ferramentas puramente cliente (texto, codificação, hashing, extração, conversão, tabelas de referência) numa vista lateral, mais o comando /toolbox e a exposição de ferramentas do agente controlada por configuração.

Adiciona os níveis de raciocínio de models.dev aos modelos DeepSeek Harness de terceiros não configurados.

Plugin DSH: converte documentos Word, PPT, Excel, PDF, EPUB, CSV etc. para Markdown no formato GitHub, usando @firecrawl/anydoc

Leve as skills e a configuração do OpenCode para o DeepSeek Harness

Envie imagens e arquivos locais para seu host de imagens usando a configuração já existente do PicGo (PicGo Cloud, GitHub, S3, COS, Qiniu ou qualquer plugin de upload instalado), por meio de uma ferramenta `picgo_upload` e do comando `/picgo`.

Database access for DeepSeek Harness through the DBHub MCP server: configure MySQL, MariaDB, PostgreSQL, SQLite and SQL Server connections per workspace and environment, then let the agent configure, list, query and search SQLite objects through four fixed tools. Passwords and full connection strings are entered in the settings UI and never accepted as tool arguments, so the model only sees metadata such as mysql://host:3306/db; each environment can be read-only (the model may enable it but not clear it) or reached through a manual SSH tunnel. Every call runs its own short-lived dbhub process and dbhub installs itself when missing.

Screen-sense mode for the dsh-pet desktop pet: captures the primary display every 30 seconds, compares an 8x8 average hash of each frame, and sends the screenshot to the session model when the frame changed (and again after the idle interval even if unchanged) so the pet comments in one short bubble line. Adds /fish, /fish_look and /fish_screen commands, a status and control HTTP pair, and a change threshold plus an idle repeat interval that can be tuned in the plugin config. Windows only (PowerShell WinForms).

Model channel auto-enricher for DeepSeek Harness: eliminates manually configuring contextWindow, maxTokens, \[text, image] multimodal input, and {low, high, max} reasoning effort tiers model by model after adding a provider channel, with live auto-enrichment on save, a Settings UI page, and timestamped backups.

MCP server and skill management for DeepSeek Harness: a sidebar panel and a plugin-page config section with search, status lights, per-row switches, expandable details, and an add-server form following Codex mcp_servers fields.

Automated data masking tool based on national standards, automatically identifying sensitive fields like ID cards and phone numbers.

Data lineage tracking tool, mapping the full lifecycle of data to meet source legality requirements.

Quantitative data quality scoring based on GB/T 36344-2018, providing auditable quality reports for data asset capitalization.

Tidy the model list of DeepSeek Harness: hide any model from the selector, rename models and channels while keeping the provider billing rate, and arrange both with arrows. Search, per-provider batch toggles, back to top, one-click restore. Display only — no provider configuration is rewritten.

A configurable Liquid Glass theme for DeepSeek Harness with translucent surfaces, wallpaper, desktop transparency, window blur, custom cursors, click ripples, and per-side conversation contrast controls.

Let Agents directly control independent local DSH instances with zero intrusion—no plugins or components required on the target. Isolated environments enable autonomous configuration and testing, while Agents with different models and personalities can chat, role-play, or form nested control chains. Supports conversational setup, user-like operations, incremental reading, saved references, and remote session/workspace search.

Emite sons e notificações quando uma tarefa termina ou aguarda aprovação ou resposta. Os sons podem ser configurados em Settings com estilos sintetizados ou arquivo de áudio próprio; há sons de gato Hachimi por diversão. Um patch opcional para Windows adiciona número na barra de tarefas, piscadas e notificações nativas.

Model failover and turn keep-alive for DeepSeek Harness: a request that fails with a model error before any visible output falls through the models of the configured provider groups (then the next provider) until one streams; transient failures retry with backoff under a liveness watchdog, a dead turn self-resumes with templated 「继续」 wake-ups, and an optional full-auto mode auto-answers permission, question and plan approvals with every decision appended to an AUTO-MODE.md audit log.

Cotas diárias de envio e horários silenciosos para caixas de agentes: as mensagens são contadas em grupos nomeados com limite diário, o início do novo dia é configurável e, no período silencioso, o núcleo retém mensagens online em vez de entregá-las.

Prompt optimizer for the composer: a button in the tool row rewrites your draft through a model channel you already configured, streaming into a panel that floats above the composer without taking up layout. Your draft changes only when you click Accept — and Accept is refused while the answer is still streaming, so a half-finished reply can never be written back. It asks first when the draft carries @ references or attachments, which a whole-draft replace would flatten into plain text. No global keyboard shortcuts, and no API key ever reaches the browser: the host half makes the call.

Registers the eight official GSAP AI skills in DeepSeek Harness; the skill bodies ship inside the plugin, so it works after installing and restarting with no configuration, account or API key.

Notifies you about 11 configurable DSH agent events (task completion, questions, denied approvals, background subagents/goals/jobs, team tasks, context compaction, triggered schedules, plugin startup and permission changes) as browser Web Notifications through a bundled service worker, falling back to Windows toast or Linux D-Bus, with three silence levels and click-to-open.

Pesquisa na Web com fontes para DeepSeek Harness via gateways compatíveis com OpenRouter: `web_search` usa o mesmo endpoint e chave dos modelos de chat, retorna fontes citáveis e pode ser configurado em Plugins.

Exposes the models already configured in DeepSeek Harness through an OpenAI-compatible gateway, so other local projects can call them with any standard OpenAI client. Multiple provider candidates share one named group with ordered, balanced or random dispatch; upstream failures before any output switch to the next candidate transparently, and rate-limited requests are retried after the provider's backoff. Per-candidate call statistics (attempts, answers, failures, token/TTFT totals) appear as badges in the settings page, and daily aggregates persist to a local file with a 30-day heatmap and trend view. Until you create a key in the UI, the endpoint accepts calls from anyone who can reach it; keys (stored as SHA-256 hashes) then turn authentication on, and the endpoint stays locked even after the last key is revoked. Exposing the optional LAN listener without a key leaves the port open to the whole network. Runs on DSH 0.1.2-rc.1 through 0.1.7-alpha.1 and later.

Gere skills (SKILL.md) e servidores MCP nas definições DSH, globalmente ou por projeto; as alterações são aplicadas de imediato.