Plugins

Guardarraíles de escritura de novelas: 20 herramientas novel_* aplican la coherencia del libro de hechos, las puertas de fase y capítulo, la auditoría automática con métricas deterministas y revisiones de propuesta únicamente; un banco de trabajo del panel derecho cubre lectura, reproducción TTS, pulido, corrección, comprobaciones de continuidad y redacción por lotes, y un motor de derivación ejecuta pasos internos fuera de la conversación principal.

Mejora de prompt con un clic en el compositor: reescribe el borrador en un prompt estructurado (rol y objetivo, pasos ejecutables, formato de salida, criterios de aceptación, casos límite) con vista previa antes/después, reinserción y deshacer. Nunca cambia la intención ni inventa requisitos.

Plega las filas de Think y de llamadas a herramientas en una píldora resumen flotante con recuento de fallos en rojo, para una vista de chat más limpia y amigable para redactores.

Ejecuta pipelines de AItelier desde DSH sobre MCP: 39 herramientas (22 de lectura, 17 de escritura) para generar, ejecutar, inspeccionar, editar, exportar e importar pipelines SkillFlow multi-paso. Los pasos se ejecutan en AItelier en lugar de en la sesión DSH y se sondean por run_id, pausan en checkpoints impuestos por el motor respondidos con answer_checkpoint, y dejan rastros por paso y salidas de paso para leer después; add_provider / map_model / edit_role apuntan un rol individual a un endpoint local o más barato. Agrupa una habilidad aitelier-pipelines.

Analítica de ejecución de sesión: pasos, llamadas a herramientas, fallos, acciones repetidas, uso de tokens y señales de verificación, presentados como informes en texto/Markdown/JSON.

Estado de trabajo entre sesiones explícito para DeepSeek Harness: objetivos, decisiones y siguientes pasos capturados automáticamente desde eventos del host o mediante una herramienta work_state visible para el modelo, inspeccionable con /checkpoint.

Añade una pestaña Reading al cliente web DSH que muestra los pasos del proceso y el razonamiento en vivo en orden de origen, colapsa los turnos exitosos a la respuesta final y mantiene intactas las pestañas, el compositor y las herramientas originales.

Añade una pestaña Graph que representa la ejecución de una sesión como un DAG interactivo de turnos, pasos de LLM, herramientas, Skills, subagentes, cambios de código y pruebas, con estado en vivo, agregación de reintentos, ruta crítica y vínculo con la trayectoria.

Plugin de aplicación obligatoria del protocolo de memoria: conecta el servidor MCP opencode-memory, fuerza memory_weave antes de las llamadas a herramientas, ingiere automáticamente los turnos e inyecta contexto de memoria en los pasos del 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 telemetría que exporta turnos, pasos del modelo y llamadas a herramientas a 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.