Plugins

Painel de uso da DeepSeek API para DSH Web: estatísticas diárias de acertos/falhas de cache e tokens de saída a partir de logs de sessão, estimativas de custo por modelo, account balance, tendências de 7 dias e um resumo de uso do composer.

Aviso amarelo de uma linha para um erro de cache de prompt após a reconstrução do cache; mostra tokens de entrada sem cache cobrados novamente, tokens atingidos no cache e TTFT.

Rastreamento de custo de tokens por modelo, com precificação configurável de acerto/erro de cache, saída e janela de pico, barra de custo de sessão em tempo real e sinalizações de modelos não configurados

Pílula de estatísticas retrátil no estilo iOS abaixo do compositor: custo da sessão, saldo da conta DeepSeek, taxa de acerto de cache e uso de tokens em um painel translúcido

Token usage dashboard in the DSH settings page: nine metric cards (total, today, yesterday, peak day, longest session, active-day streak, active days, sessions, subagent tokens), a GitHub-style daily/weekly/cumulative heatmap, and an activity insight list, aggregated locally from session logs and projection caches, keeping token history after a session is deleted.

Session-affinity routing for LLM gateways: injects the session ID into every request sent to NewApi-style gateways so the gateway can pin requests per session and raise prompt-cache hits; takes over the official pi-ai routing on install and restores it on uninstall.

Live token cost for every chat in the DSH Web UI: the chat, its subagents and the whole session tree, priced from a bundled models.dev snapshot of seven providers and 139 priced models, with cache read and write rates wherever the provider publishes them and DeepSeek from its own peak and off-peak table. Every finished answer carries its own price in the transcript, and a chat that is not currently open is priced from the log instead of disappearing. Spend is costed per interval from an append-only JSONL ledger in the project folder, so logged work keeps the tariff it was billed at. On top of it: budget-aware work plans packed against a money limit, routing scenarios that show which models are worth connecting, a generated plan document in English, Chinese or Russian, and a warning when spend belongs to no plan unit.

Folds streaming reasoning and tool calls into collapsed step bars and collapses each finished turn into a single summary bar; step bars show native tool icons, filenames, edited line counts, and failure counts, finished turns restore duration, first-token time, token usage, generation speed, and cache hit metrics from recorded Session events, and preferences persist on the Host. Changes browser presentation only. Requires DSH 0.1.5-alpha.1.

Settings section that reports token usage: totals for input, output, cache read, cache write, reasoning and call count, with breakdowns by model, day, month and project plus a per-day trend chart for the last 30 days; history is rebuilt once on a worker thread and then kept current from live session events.

Scans the whole C drive and classifies every large folder into A/B/C/D/E/P (safe cache / relocatable / junction-movable / abandoned software / config-memory redline / personal files), then deletes, moves, or redirects on demand — with strong redline protection, dry-run preview and undo. Unknown software decided by LLM fallback + human confirmation.

What's up - a zero-maintenance status board for your sessions. Scans every conversation on the host, extracts a goal + one-line status per session (multi-provider LLM, fingerprint-cached), surfaces half-done, unanswered and recent work in a sidebar panel, and jumps you back into any session with one click.

Local token usage and cost dashboard for DeepSeek Harness: four-segment token breakdown (miss/cache-hit/cache-write/output), cache savings estimate against the miss/hit price gap, per-session drill-down with context-growth curves and anomaly flags, global filters with shareable URLs, monthly budget progress with month-end projection, and day/month aggregate fast-path queries (O(days)) with incremental rescan.

Draggable ring gauge showing live model output speed (tok/s) with an expandable per-step detail panel (exact speed, TTFT, cache-hit rate, cache read/write, reasoning and input tokens, model, cumulative tokens).

MUV variable table editor for DeepSeek Harness: a tree view of the variables being tracked, a macro test panel for random, pick and roll, a dice shortcut bar and pick-cache management. Companion plugin for dsh-muv-engine.

Shows official DeepSeek API cash balance and private DSH-local request, token, cache, daily, and per-model usage charts.

DeepSeek account-wide usage & balance panel from the official platform API (api/v0/usage/by_api_key): cache hit/miss & output tokens, cost, 24h–90d ranges, persistent platform token, and a model-visible `deepseek_usage_query` tool.

A right-side session stats panel showing average cache-hit rate, session cost, runtime, request count, cumulative tokens and account balance.

Gerenciador de arquivos para DSH Web: lista sessões arquivadas na página de Configurações e as exclui de verdade, incluindo seu log, marcador de arquivo e cache de projeção.

Monitoramento do saldo da conta DeepSeek e do custo dos modelos com preços oficiais de ponta/fora de ponta, cobrança de tokens em três níveis (cache miss, cache hit, saída), detalhamentos por modelo e por sessão, uma barra de resumo no compositor com detalhes ao passar o mouse, exportação em CSV e um painel de configurações.

Adaptive Reversible Context (ARC) para o DeepSeek Harness — governança de contexto ciente de provedor e de cache, com recuperação reversível.

Visibilidade de contexto estilo Codex para DeepSeek Harness: ocupação ao vivo da janela de contexto, detalhamento de composição, taxa de acerto do KV-cache e mapa de calor de uso estilo GitHub de 53 semanas

Visão como plugin para modelos somente texto no DSH, com interação nativa para compreensão e geração de imagens, automação de GUI, memória de evidências em camadas e cache.

Um porte enxuto do Headroom: comprime a saída de ferramentas e corta até 20% do contexto, sem afetar o cache de contexto do modelo nem o desempenho do agente.

Protege o cache persistido de projeção de sessão: degradação JSON por linha, para que uma unidade de projeção problemática (por exemplo, um plugin de terceiros que armazena um Map) nunca mais trave títulos de sessão ou o cache inteiro, além de uma autocorreção na inicialização que preenche títulos ausentes.