Plugin

Adds a summonable domain-expert roster that runs as subagents while the parent session keeps the task and final answer.

12 tested engineering skills (git commit, code review, test-first, plugin dev, debugging, changelog, PR review, task breakdown, and more): every SKILL.md passes a format validator aligned with the official skill rules plus an isolated load smoke test.

Create a one-click Windows desktop shortcut from the Settings page: a .cmd launcher + desktop icon for DeepSeek Harness or any local server, auto-opens the browser, with taskbar pin hints.

Pause / resume / cancel the in-flight conversation task from the composer area: forced pause interrupts immediately and remembers the interrupted tool, safe pause lands after the tool or reasoning finishes, resume asks for confirmation, and the default pause granularity is configurable in the settings.

Espone le capacità dell'agente DeepSeek Harness come server MCP, così un client MCP esterno (ad es. Hermes) può guidare Harness nell'esecuzione di task di programmazione. Hermes = cervello, Harness = braccia

Un orchestratore di task multi-provider compatibile con Symphony e dashboard per DeepSeek Harness

Un plugin meta-agente nativo del modello per DeepSeek Harness: il modello sintetizza a runtime flussi di lavoro specifici per il task a partire da cinque pattern di workflow agentici (concatenazione di prompt, worker paralleli, router, supervisore, ciclo di valutazione) e coordina strumenti e subagent

Approvazioni con ambito di turno "Consenti per questo task": consente automaticamente le escalation `danger-full-access` corrispondenti solo per il task corrente, poi scadono

Suonerie di completamento per workspace più suoni di attenzione per eventi di approvazione, domanda, revisione del piano, obiettivo bloccato e fallimento del task, con sintesi integrata, voce (TTS) e audio personalizzato

Aggiunge artefatti di specifica, skill, comandi, implementazione guidata da obiettivi e contesto sull'avanzamento dei task

Task programmati tramite impostazioni che vengono eseguiti a orario o durante le ore di minor traffico di DeepSeek, con pianificazioni una tantum e giornaliere supportate da uno stato del task durevole

Memoria cross-sessione con ambito di progetto: snapshot di PROJECT.md iniettato nel primo messaggio utente, uno strumento memory_remember e auto-riflessione dopo i task ReAct; ogni progetto mantiene il proprio file di memoria

Pre-flight plugin-library check for DSH agents: task-type requests trigger a Top-K hint of suitable plugins with use_when/not_for capability declarations, making plugin usage predictable instead of opportunistic.

Native Windows toast + taskbar flash for task done / approval / ask_user_question; Win10/11, npm install `dsh plugin --profile web add dsh-notify-win`.

DeepSeekHarness任务完成时进行消息推送提醒（微信+Windows通知）

Local-model (Ollama) integration for DeepSeek Harness: discover, pull, remove, and inspect local models, route requests to them by task type or keyword with automatic fallback to the cloud, and get a one-shot status overview via /ollama.

DSH web GUI plugin: an "Archived Tasks" settings page that lists archived sessions and supports restore or permanent delete

Composable working, reasoning, and quality controls for DeepSeek Harness Web.

Machine-level cron jobs for DeepSeek Harness: configure scheduled tasks in the Web settings page; the host fires internally-driven agent requests into a dedicated session, hands-off.

Real-time stage, ETA & cost dashboard for headless dsh tasks: turns the black-box session event stream into a live multi-task grid (cordis plugin + standalone local dashboard, no API calls).

System-native notifications when a task finishes or needs your confirmation: Windows toast, macOS osascript, and Linux notify-send.

WeChat automation for DSH: push task progress to WeChat, listen for messages with keyword auto-reply, and a WeChat ↔ DSH two-way bridge controllable from the settings page, built on wxauto4.

Git worktree Session Targets with isolated task sessions, Ready for Review, reversible Local Preview, human-confirmed delivery, environment retention and recovery, and same-session iteration.

Per-task isolated git worktrees with a full create/sync/finish lifecycle: task names auto-derive branches, merge targets are double-checked, and batch cleanup is built in — zero manual git operations.