Plugins

Mini-jogo de tempo de espera com grade de Schulte dinâmica: clique em 1..N em ordem em uma grade estática ou uma roda roleta girando enquanto o modelo pensa.

Front-end Pi TUI (framework de terminal com renderização diferencial): markdown em streaming, recolhimento do raciocínio, cartões de ferramentas, comandos slash, sobreposições de aprovação/pergunta e armazenamento de sessão dsh compartilhado

Plugin do DeepSeek Harness: alternância de modo de raciocínio por requisição (enable_thinking) para modelos da família Qwen3 em endpoints compatíveis com OpenAI

Moves reasoning that a provider leaks into the visible text channel back into the reasoning channel, and emits a text block when a whole turn of answer text lands only in the reasoning channel. Catches three shapes: `<thinking>`-tagged text, text that continues a reasoning tail which ended mid-token, and an answer-only reasoning turn that stops. Healthy streams pass through unchanged, block order is preserved, and each of the four rules can be switched off in one JSON config.

Qwen mode for DSH: manages local GenieX and Alibaba Cloud QwenCloud providers, normalizes thinking and sampling, detects model capabilities, and shows per-turn latency and decode speed. Its bundle patch replaces the permission plugin's preset table with reply-only, read-only, workspace-write and danger-full-access (the last two as in stock), so any custom presets are overridden.

Connect a locally installed agy CLI to DeepSeek Harness 0.2.2-rc.1, with separate thinking levels, quota display, and Harness-owned tools. Community fork of dannndouglas/dsh-antigravity-acp, beta, verified on Windows x64 only. Needs the agy CLI signed in with your own Google account; installing makes new chats default to Agy models (messages go through agy to Google), switches web search to the agy provider and replaces the built-in compaction. Do not enable it alongside other forks that register the agy-local-acp provider.

The row that is running expands itself and folds back when it settles. A running turn keeps its whole procedure in one height-capped window that scrolls itself; a finished turn merges into the built-in finished header, leaving only the final answer. It works by driving the official disclosure rows rather than drawing its own panel, leaves rows you opened by hand alone, and restores the official settings on uninstall.

Delivers one required user-role runtime context that makes the agent reason in Simplified Chinese and keep a whale-loli in-thinking persona (calls itself 本鱼, lazy-arrogant tone) in both reasoning and the final reply, while proper nouns, identifiers, paths, commands, URLs and error text stay verbatim; persona, extra proper nouns and context order are configurable. Enabled by default for every agent in the profile, subagents included.

Imports chats captured from chat.deepseek.com by the repo's companion Edge extension (loaded unpacked in Edge) into DeepSeek Harness as new sessions; thinking is saved as a sidecar thinking.md, and trimmed, branched or very long chats also get the full transcript.md.

Per-turn reasoning-effort routing that keeps the current provider/model: judges each user message (retry or correction, explicit intent, length, code blocks, errors, task scope) and sets reasoningEffort to a level the model actually declares, so Magpie and other OpenAI-compatible models work too. Ships a composer chip with an auto/manual switch and per-session decision history.

Replaces the composer model picker with a model + thinking-effort picker and an Auto level; Auto scores each turn by how far the conversation has drifted from the main objective and by repeated failures (one extra small judge call per turn), picks the effort from that score, and labels every finished turn with the effort it sent.

Turns scattered thinking notes into a growing constellation of themes, claims, relations and open questions, plus a written synthesis of the argument.

Injects a Chinese-thinking reminder around the system prompt and the per-step runtime snapshot, so the agent reasons in Simplified Chinese instead of drifting back to English as the transcript grows.

Replaces the composer Effort switch with a Claude Desktop-style five-level slider (Low/Medium/High/Max/Ultracode): a pill opens a popover above the composer, dragging snaps with a spring and writes once, and Ultracode maps to the model's maximum reasoning effort. Ships the Ultracode WebGL2 energy grid, a per-session Ultracode mode, and passes modifier-click through to the shipped level list.

Provedor SAP AI Core com OAuth compartilhado, cinco opções de modelos Qwen, orçamentos de raciocínio, streaming e chamadas de ferramentas; validado no cn40.

[LLM] Permite que o DSH sincronize as modalidades de entrada e o nível de raciocínio a partir do upstream do magpie.

Plugin para DeepSeek Harness: instrui cada agente a escrever seu raciocínio privado em chinês simplificado.

Slider do composer inspirado no Claude Desktop para ajustar esforço de raciocínio do modelo por clique, arraste ou teclado.

Bundle Windows x64 que inclui o runtime ACP oficial do Antigravity. Delega tarefas de texto de execução única com autenticação, modelo e nível de pensamento selecionáveis. Usa host peers para Harness >=0.2.1-rc.3 <0.2.2-0, incluindo RCs posteriores do 0.2.1 e a versão estável 0.2.1.

O histórico do composer restaura todo o estado de entrada: conteúdo, anexos de imagem/arquivo, referências @ e comandos slash, além do modelo, esforço de raciocínio, permissão e preset de agente usados.

Menu de três pontos no cabeçalho da sessão: baixar o log, alternar a transcrição de cada chat entre Normal e Verbose e definir o que Verbose expande (blocos de raciocínio, chamadas de ferramentas, saída do terminal).

Provedor de modelos Cohere para DSH: usa wire compatível com OpenAI por padrão e a via nativa Cohere v2 para citações/RAG/orçamento de raciocínio. Adaptador direto, sem proxy.

UI monocromática tranquila para DSH com detalhes lavanda, animações de início e troca, workspace de pensamento, skills com escopo e conexões locais opcionais de voz e pet.