Plugins

Custo de API por sessão e diário, orçamento com % de uso, saldo oficial, dashboard de histórico e sincronização de preços oficiais com um clique, incluindo tarifação de horário de pico/fora de pico.

DeepSeek Harness control center for official balance monitoring, per-session costs and tokens, third-party token totals, completion alerts, official recharge, flexible layouts, and agent-assisted session controls.

Pause and resume tasks automatically during user-defined time windows to avoid peak-hour API costs; includes account balance display and 10-minute granularity spend bar chart.

🐋 Caderno da Baleia — o relatório anual do seu Agent: gera relatórios diários/semanais/mensais/anuais a partir do log de eventos da sessão, em qualquer intervalo, somente leitura sem reescrever nada.

Self-contained DeepSeek Harness (DSH) plugin for Provider/Auth login, model switching, image fallback, token/cost analytics, and same-port Web restart. Useful? A star helps.

Saldo da conta DeepSeek e custo da sessão na dock do composer, com preços oficiais obtidos automaticamente e suporte a horários de pico/fora de pico.

Auditoria de injeção de contexto: custos em tokens de cadeias de instruções / catálogos de skills / schemas de ferramentas, com detecção de duplicatas e conflitos.

Roteador de modelos e otimizador de custos para o DeepSeek Harness: respostas rápidas via flash para perguntas simples, fallback automático em caso de falha e painel em tempo real de tokens/cache/custo.

Um painel flutuante à direita e o comando /context para o DeepSeek Harness — um gráfico de rosca ao vivo do uso de tokens de contexto, alocação e custo estimado.

Vision for text-only DeepSeek via Doubao Web by default (zero-cost, no API key — drives your logged-in Chrome through a Windows CDP bridge), with Antigravity IDE quota (flash/pro) or Gemini fallback; auto detail escalation, vision evidence memory with compaction rehydration, content-hash cache, and a bilingual client panel.

OpenCode Go usage bar in the composer dock: rolling/weekly/monthly quota rings, DSH-session token & cost stats priced with live official rates, per-model and current-session scope breakdowns with live per-session updates, one-click API key copy.

Tema claro Solarized, layout compacto, cápsulas recolhíveis para think/cadeia de ferramentas, e dashboards de saldo, custo de sessão e uso para a web UI do DSH.

dsh client bundle: a sidebar usage & cost dashboard — token stats, peak/off-peak aware per-model pricing, membership ladder, achievements and a daily heatmap.

DeepSeek account balance and session cost under the composer, with a live peak/off-peak pricing badge (Beijing time), a countdown to the next pricing switch, hover price tables, and usage advice.

Per-model token usage and cost estimation with DeepSeek account balance, shown in a Settings panel tab.

Chip de carteira multiprovedor: saldo oficial da DeepSeek, custo e tokens por sessão, totais de tokens de terceiros, atalho de recarga e alertas de saldo baixo.

Dashboard de tokens, custo e saldo abaixo do composer: indicador ao vivo, além de gráficos SVG sem dependências para uso por turno, custo estimado e saldo da conta DeepSeek.

Exports metadata-only DSH turn, model, tool, approval, retry, and error events to Tuning Engines for governed traces, policy evaluation, cost analysis, and Work Session review, with a disk-backed retry queue.

Cross-platform Computer Use for DeepSeek Harness: virtual-mouse human-like operation (screen_observe + computer_click + type + key + scroll + drag, 11 tools), AX-tree zero-vision-cost mode with free GLM-4V-Flash vision fallback, safety guards (snapshot TTL / app whitelist / dangerous-action approval / password-box protection).

A configurable 17-segment session status bar for the dsh composer dock with live TPS, per-model cost estimation, and a usage & cost dialog.

Usage and cost statistics with peak/off-peak pricing after the 2026-08-17 rate change, a floating summary panel, per-session breakdowns, and a day/week/month/year/all usage heatmap.

Um plugin do DeepSeek Harness para rastreamento de tokens em tempo real e estimativa de custo de sessão altamente precisa, com suporte a precificação dinâmica de horário de pico/fora de pico.

Optimize a raw instruction into a professional prompt through the harness llm service — four-section (Role / Task / Context / Format) or a headerless plain-text style. Context-aware by default: the recent conversation is injected as background and may enrich the ## Context section. Long outputs resume from the truncation point with auto-expanded budgets; validated results are cached (identical requests cost zero model calls); a unified call budget bounds worst-case cost. Composer ✨ one-click optimize, undo, cancel and a token-cost hint; prompt_optimize tool (optimize + iterate), auto-optimize hook, auto-detected zh/en role document.

Export sessions to Markdown/JSON for review, replay, and per-session cost summaries.