Plugins

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.

Barra lateral derecha de turnos de ocultación automática estilo Codex: mostrar/ocultar con edge-peek, tooltip por turno, búsqueda dentro de la barra, y ventana desplazable de 30 turnos para sesiones largas.

Guardián cooperativo de tiempo de espera para ask_user_question: las preguntas perdidas o sin responder se resuelven como un ASK_TIMEOUT estructurado en lugar de dejar el turno colgado para siempre.

Memoria de traspaso autogestionada por directorio de trabajo y rama de git: registra los turnos, los condensa en Markdown conciso, e inyecta el resultado en sesiones futuras desde ~/.agent/agent-handoff, compatible byte a byte con pi-handoff.

Convierte las sesiones de DeepSeek Harness en informes diarios, semanales, de traspaso y artículos, con exportación HTML verificable y un recibo que vuelve a comprobar el archivo guardado.

Uso del modelo por turno y coste de sesión con reconocimiento de repeticiones (replay) para DeepSeek Harness

Notificaciones push de Bark al iPhone: eventos de finalización de turno, espera de entrada y aprobación enviados desde el host de DSH.

Readable transcript export for DeepSeek Harness: turn any Session into a Markdown / HTML / ZIP transcript with reasoning blocks, tool calls and results, images and usage — from the Session header or the /export-md command.

Personal dsh preferences: a tunable companion to the official compaction engine (threshold, retention, summarization model/reasoning, turn-end compaction), llama.cpp model import for the Models page, and tab/notification helpers (status-light favicon, bro

Turn a dsh session into a shareable, redacted idea and deliver it to DeepHub friends. Built on DeepSeek Harness.

Conversation task-completion reminder for DeepSeek Harness (Web UI and DSH Desktop): a Windows system toast (Web Notification) on every stop — task complete, the agent waiting for your answer (ask_user_question pending), or an error stop (any failed turn

Resumes turns interrupted by a DSH host restart: hooks agent activation (once a session is live), reads the crash-repair turn/end, and sends a continuation that requires verifying real-world state first rather than assuming a side effect succeeded or failed. Permanent failures (AUTH, QUOTA, context overflow) are skipped, with a cross-restart budget, adaptive backoff and a minimal-context payload.

Markdown visual enhancement and session workbench for DSH Web Composer: live syntax presentation with caret-row source reveal, deterministic local completions and diagnostics; long pastes fold into persistent chips with inline context or file-mode delivery (@path across 50+ extensions) plus sidebar LLM rewrites (stop, preview diff, undo/redo); real-time context map with token gauge, composition breakdown, per-turn growth chart with anchor lines, in-place /compact, and turn forking.

Meeting rooms for DSH sessions: joining a room grants the right to convene and the duty to attend, and a session belongs to at most one room. Convening forks each participant in with its own completed-turn context and with its tools stripped, a moderator that carries no context chooses the speakers, and every turn is appended to disk as it is spoken. After adjournment each participant receives its own minutes as a user turn and resumes work.

On-demand skill tools for DeepSeek Harness: registers skill_search / skill_load / skill_ref so the model searches a staged skill library first and loads a skill body only when it needs it, keeping the library out of the resident session catalog and out of every turn's context; adds a Skills tab to the conversation view ring that reads back the whole session and lists which skills were actually loaded, and in which turn. Zero dependencies, and the records render client-side only, never entering the model's context.

Audio cues for DeepSeek Harness: a short synthesized sound when an agent needs confirmation, finishes a turn or a background job, or fails, with five sound packs, per-event toggles and volume, and do-not-disturb rules stored in the host settings document.

Turn-rail settings for the DSH Web conversation locator: tick thickness, rail side, a curved length gradient anchored on the hovered tick, and a plain-text hover preview with adjustable line count, font size, and width.

Adds an Explain button to the approval card: one model call returns exactly three lines reading the pending operation, covering what it does, which files or system state it reads, writes, modifies or executes, and a risky/attention/safe verdict with a one-sentence justification. It also renders the detail area for `write` and `edit` calls, which the shipped renderer leaves blank because it only reads a `command` field.

Email notifications for DSH with an away-mode switch: mails you when a turn ends, a tool waits for approval, or the assistant asks a question. Title and body are editable templates.

Turns a dsh session into a redacted idea and delivers it end-to-end encrypted to friends on DeepHub; received ideas land as new sessions.

Workspace checkpoints per tool call: records every file mutation inside the workspace (excluding .git and node_modules by default), including changes made by shell commands rather than by write/edit, and stores the previous content of each changed path in a content-addressed store kept outside the workspace. Restores have two modes — undo one record, or return to a point in time — with a line-level diff preview, a dry run by default, and a rescue record written before every restore so the restore itself can be undone.

Mounts the mcptoon MCP gateway as one stdio server, so the agent discovers the tools of every MCP server you have configured through mcptoon's compressed view instead of full JSON schemas on each turn. Ships a doctor CLI that checks the mcptoon executable resolves and prints the exact command/args override when it does not.

Cross-session experience memory for DSH. Lessons are evidence-graded, injected when the turn is about the same thing, and shown just before an action only when the record declares which call it applies to. A rule that holds whatever the turn is about — "always answer in Chinese" — can be marked **standing** and is then carried every turn: measured on 24 isolated real-model turns, a standing rule is followed 6/6 against 0/18 for the controls (empty store, same record unmarked, unrelated standing record). A guess still cannot become always-on: a standing record needs a verified passage like any other. What nobody looks up is retired, reversibly. Five tools, seven slash commands, zero runtime dependencies.

A dsh-better-sidebar tab that renders a session brief — a todo board read from the `todos` projection plus a deliverables section listing the files written this turn — and hides the official todo panel above the composer while it is mounted.