Plugins

Guardrails de escrita de romances: 20 ferramentas novel_* impõem consistência do livro-razão de fatos, portas de fase e capítulo, auditoria automática com métricas determinísticas e revisões apenas de proposta; um workbench do painel direito cobre leitura, reprodução TTS, polimento, revisão, verificações de continuidade e redação em lote, e um mecanismo de desvio executa etapas internas fora da conversa principal.

Melhoria de prompt com um clique no compositor — reescreve o rascunho num prompt estruturado (função e objetivo, passos executáveis, formato de saída, critérios de aceitação, casos limite) com pré-visualização antes/depois, reposição no campo e desfazer. Nunca altera a intenção, nunca inventa requisitos.

Dobra as linhas de Think e chamadas de ferramenta em uma pílula de resumo flutuante com contagens de falha em vermelho, para uma visualização de chat mais limpa e amigável a redatores.

Executa pipelines AItelier do DSH sobre MCP: 39 ferramentas (22 de leitura, 17 de escrita) para gerar, executar, inspecionar, editar, exportar e importar pipelines SkillFlow multi-etapa. As etapas executam no AItelier em vez da sessão DSH e são consultadas por run_id, pausam em checkpoints impostos pelo motor respondidos com answer_checkpoint, e deixam rastros por etapa e saídas de etapa para ler depois; add_provider / map_model / edit_role apontam um papel individual para um endpoint local ou mais barato. Agrupa uma habilidade aitelier-pipelines.

Análise de execução de sessões: etapas, chamadas de ferramentas, falhas, ações repetidas, uso de tokens e sinais de verificação, apresentados como relatórios em texto/Markdown/JSON.

Estado de trabalho entre sessões explícito para DeepSeek Harness: objetivos, decisões e próximos passos capturados automaticamente a partir de eventos do host ou por meio de uma ferramenta work_state visível para o modelo, inspecionável com /checkpoint.

Adiciona uma aba Reading ao cliente web DSH que mostra etapas do processo e raciocínio ao vivo na ordem de origem, recolhe turnos bem-sucedidos à resposta final e mantém intactas as abas originais, o compositor e as ferramentas.

Adiciona um separador Graph que apresenta a execução de uma sessão como um DAG interativo de turnos, passos de LLM, ferramentas, skills, subagentes, alterações de código e testes, com estado ao vivo, agregação de novas tentativas, caminho crítico e ligação à trajetória.

Plugin de imposição do protocolo de memória: faz a ponte com o servidor MCP opencode-memory, força memory_weave antes das chamadas de ferramenta, ingere automaticamente as interações e injeta contexto de memória nas etapas do agente.

Model-autonomous context compaction for DeepSeek Harness: a mind_map tool surveys the agent context surface (stable seq ids, roles, token weights, clear-boundary markers, the clear-mind playbook), a clear_mind tool replaces a chosen conversation-history span with a model-written checkpoint through the native compaction transaction, call and result pairs self-collapse into one-line tombstones, and a proactive reminder nudges the model when the context grows long or a turn runs too many steps.

A GitHub-connected visual git manager for DeepSeek Harness: guided GitHub-Flow steps, commit graph with PR/CI badges, one-click GitHub login, PR and issue management, and structured git tools for the agent. Renamed from gitcompass in 2.0.0.

Adds a sidebar tab that folds a session into user turns (input, tool steps, output) with one-click jump back into the conversation.

Always-on ADHD-friendly output shaping: one system-prompt section makes replies action-first with numbered steps and concrete time estimates; adhd_on / adhd_off / adhd_status tools persist the mode across restarts.

Session manager panel under Settings → Plugins: list all sessions with title, cwd, agent preset, updated time, turns and steps, expand a row to view message history, delete non-running sessions, and export a session as JSON or Markdown via a browser Blob URL.

Feishu/Lark channel that drives DeepSeek Harness agents from chats: streaming rich cards with live thinking and tool steps, per-turn cost metering at DeepSeek peak/off-peak rates, one-tap approval cards, model-gated image intake, and QR onboarding without a public endpoint.

Publishes a project plan the agent writes: ordered steps in a panel docked to the right of the frame, and the framework graph as an auto-laid-out diagram in its own centre tab, downloadable as SVG or PNG. Charts are rebuilt from the session log, so they survive restart and resume.

Backend de telemetria que exporta turnos, etapas do modelo e chamadas de ferramentas para o yiTrace

A newspaper-style front page for a session you left running, as a Conversation View tab beside Chat and Trajectory: a per-turn timeline (duration, steps, tools, tokens, outcome), file churn counted per file, where the wall clock went and how much of it was the model rather than tools, which single turn ate the spend, failures nobody retried quoted with their failing command, and a context-pressure gauge measured against the routed model's own declared capacity. The briefing is folded from the durable session log and never generated by a model, so it costs no tokens, cannot hallucinate, and is byte-identical for the same log and clock; it appends nothing to the session and reaches no model, and it reports a pending approval without ever answering it. Pages are offered only when they have content, and the tab refreshes itself on turn settle and on a two-speed poll backed by a metadata-only tail probe.

Windows-native computer use for DeepSeek Harness: two tools drive and read any desktop app. One batch call runs find, click, type, key, read, wait and screenshot steps in a single engine pass, so a task whose steps are known up front costs one model round trip; reading returns window text rather than an image, and input and capture prefer UI Automation patterns, Win32 messages and offscreen PrintWindow so the user's focus and pointer stay untouched.

Notification sounds for dsh-tui: distinct tones for conversation done / user question, focused vs unfocused terminal, 9 selectable sound groups, master volume 0-150% in 5% steps, settings section, zh/en

Plan-and-execute orchestration over ReactLoopAgent — turns a goal into reviewable steps with a web UI plan card.

Code management panel for the DSH web UI that handles everyday Git in five steps: ① env check auto-detects git/gh/ssh and one-click installs missing tools (gh mirror download sources speed up installs, Windows included) with check-update; ② SSH ed25519 key generation / connection tests plus one-click 443 config to bypass blocked port 22, with the Gitee personal token configured here; ③ repo status, side-by-side diffs, stage/commit, branch switching, history with revert/cherry-pick, one-click repo creation and push, auto-ignoring >100MB files; ④ lists all repos of your account for one-click clone; ⑤ five-step npm publish wizard. GitHub / Gitee dual-platform, with the UI switching between 中文 and English live.

Periodic prompt injection for the DeepSeek Harness Web GUI: every N model invocations (conversation turns and tool-call steps both count) the plugin injects a user-configured prompt as a model-visible user message; the first injection happens at conversat

First-run health check for DeepSeek Harness: verifies Node/pnpm/dsh toolchain, home, profile, API key (names only, never values), workspace writability and npm registry, then prints actionable next steps — CLI plus an agent-callable quickstart tool, dsh-firstrun/v1 reports, zero runtime deps.