Plugins

Anexos de imagem nativos para DeepSeek somente texto na Web GUI: imagens coladas ou arrastadas aparecem como miniaturas na sessão e, antes do envio, o host as lê com a API de visão gratuita Zhipu GLM-4V-Flash (cadeia de fallback glm-4v-flash) e substitui pela descrição, permitindo que o DeepSeek responda sobre a imagem enquanto o original permanece no histórico.

Kit de visão para DeepSeek apenas texto: ferramenta `vision` invocável pelo modelo, adaptadores wrapper para deepseek/opencode-go (v4 flash/pro), cota do Antigravity IDE (default, flash/pro) / qualquer VLM compatível com OpenAI / Gemini / canais locais do Ollama, memória de evidências com reidratação por compactação, cache de hash de conteúdo e um painel de cliente bilíngue.

Ferramenta `vision` invocável pelo modelo para o DeepSeek Harness: descreve e faz OCR de arquivos de imagem chamando diretamente a API de visão Zhipu GLM gratuita (cadeia de fallback glm-4v-flash), sem precisar de CLI externo.

Tell your deepseek-v4.1-flash: "shut up! Stop looping!"

DeepSeek Harness plugin: auto-route image-bearing requests to deepseek-v4-flash-vision-exp, then fall back to the original model.

Composer stats strip for the DSH Web UI: official CNY pricing with auto-synced peak/off-peak tiers, per-model accounting, live timers, subagent-tree merging, DeepSeek account balance, budget alerts, and streaming cost estimation.

Mostra o saldo da API DeepSeek e os custos de uso local do DSH Flash e Pro.

Toast nativo do Windows e piscar da barra de tarefas para tarefa concluída, aprovação e ask_user_question; Win10/11, instalação via npm `dsh plugin --profile web add dsh-notify-win`.

Plugin experimental APEX para o DeepSeek Harness: inicialização ancorada no Minimal, ferramentas Standard sob demanda, estado persistente de tarefas e pesquisa direcionada com o V4 Flash.

Ferramenta image_describe (识图) voltada ao modelo sobre a API compatível com OpenAI do DashScope (qwen3.7-flash), além de uma ponte de colagem: em sessões somente texto, imagens coladas se convertem automaticamente em caminhos de arquivo no envio e são renderizadas de volta na transcrição, para nunca esbarrarem na admissão de imagens. Traga sua própria DASHSCOPE_API_KEY; endpoint/modelo/orçamentos configuráveis, cliente HTTP à prova de redirecionamento e funciona em todos os agent presets.

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.

Shows a reminder card in the bottom-right corner of the DSH web GUI whenever the agent is waiting for your answer, and adds a desktop notification plus a flashing tab title when you are on another tab or window.

Maintained fork of feibi-mochi/deepseek-harness-control-center, which has not been updated since 2026-09-09. Pricing follows the official model pool instead of a hardcoded model prefix, so DeepSeek V4.1 Flash (`deepseek-flash`) is billed and shows its peak/off-peak clock, and the official price page is parsed structurally so a renamed or retired model no longer stops price sync. Adds an English interface beside the original Chinese. Otherwise the same plugin: balance, per-session cost and token breakdown, a 24-hour peak/off-peak clock, Z.ai plan quota, and a local usage ledger, following the host light/dark theme.

Quick Control panel for DSH Web: a docked or floating shortcut panel whose switches other plugins register through the quickControl service. Includes a theme and skin switcher plus fine-grained NO_PROXY proxy controls, and works with dock-base or standalone.

Sets the DeepSeek flash model's reasoning effort per step — thinking off for short cheap prompts, low for a plain request, high for engineering work — and raises it only on repeated tool failures. The model itself never changes; effort max is opt-in.

Quick-notes floating panel for dsh web: timestamped entries, clock, alarms with flashing reminder, API prices & balances, day/week/month/year grouping.

DeepSeek Harness 自动审批门控：Flash 模型预判写入/命令是否不可回补，安全自动批准、危险转人工（fail-safe），最小人工介入，含人工审查 UI

Reads AI replies aloud as they stream, with voiced waiting phrases while the model thinks. Edge TTS built in, any OpenAI-compatible cloud engine supported.

Vision bridge for text-only DeepSeek models: transcribes attached images with deepseek-v4-flash-vision-exp before they reach deepseek-v4-pro, with no third-party dependencies.

Twelve curated palettes, eight accent colours, a contrast slider and font/scale overrides for the DSH web UI, with an inlined first-paint script that prevents theme flash.

Auto-switch the DeepSeek route to the vision model on demand: flash main session switches (A), pro keeps deep reasoning and delegates image reading to a vision subagent (B), subagents always switch, with fatal-failure fallback. No manual model switching.

DeepSeek balance and per-session cost in the DSH web composer dock, with official peak/off-peak pricing (peak hours Mon-Fri BJT 9-12 / 14-18, weekends off-peak) and built-in deepseek-v4-flash-vision-exp vision model rates billed at flash price (images billed as tokens, max 384 tokens each).

DSH provider preset for the Memorax DeepSeek V4 Flash gateway

Self-contained vocabulary flashcards for DeepSeek Harness web sessions