Plugins
Navegue, filtre e instale plugins do DeepSeek-Harness.
5 plugins encontrados
dsh-smart-compact
hoyyang/dsh-smart-compact
Gestão automática de contexto ao estilo Codex para DeepSeek Harness: rollover sem perdas e sem chamadas a modelos de resumo, âncoras de passagem de tarefa, notas de trabalho que sobrevivem à compactação e recuperação literal de janelas arquivadas. Notas obsoletas geram um aviso explícito em vez de serem apresentadas como atuais. Inclui botão de um clique e comando /smart-compact, rollover automático em três níveis e limpeza obrigatória das âncoras; funciona sem configuração.
dsh-context-rollover
athif23/dsh-context-rollover
Pacote de rotação da janela de contexto orientada pelo modelo para o DeepSeek Harness: contexto de trabalho novo, notas duráveis gerenciadas pelo modelo, uma pequena cauda recente literal e recuperação direcionada do histórico — sem sumarização.
dsh-rollover
zyxql-ala/dsh-rollover
Context rollover: auto-saves a handoff before the context window fills and re-injects it once in the next session segment. Two tools and a settings panel.
dsh-todos-diy
huningsong/dsh-todos-diy
Work todo reminders in a sidebar panel with four stage tabs (not started, in progress, overdue, done) plus separate recurring and paused filters, priority derived from the end time in real time, pinning that survives overdue, and enable/disable for recurring tasks. Recurrence covers workdays (following China's statutory holidays and make-up workdays), selected weekdays, monthly dates with month-end rollover, and 5-field cron; one-off tasks default to start and end reminders (start optional, end required); meetings can disable the end reminder. Alerts appear in a page overlay with optional browser notifications, snooze and quiet hours. Twelve agent tools; weekly/monthly reports, natural-language quick add, and cross-view search; data is a single local JSON file with completed tasks archived per quarter.
dsh-notes-context
sqzw-x/dsh-notes-context
Notes-backed context compression for DeepSeek Harness: replaces LLM-summarized compaction with a model-written persistent notebook plus recoverable raw history, so the rollover boundary itself costs zero model calls.