Plugin

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

Scacchi automatici: umano contro AI, oppure AI contro AI.

Generazione automatica di unit test: un comando /testgen e uno strumento generate_tests che creano l'impalcatura, eseguono e correggono i test finché non passano (generatori LLM + template offline; vitest/jest/mocha/node:test).

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

Operazioni ADB su dispositivi e banco di prova per DSH: scoperta dei dispositivi, logcat strutturato (streaming in background), installazione apk, pull/push di file e snapshot delle prestazioni con dumpsys

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

Shell desktop nella tray di Windows per DSH: installa automaticamente l'exe dalle GitHub Releases, crea un collegamento sul desktop e aggiunge uno strumento desktop_launch per avviarlo dalla chat

Allows deepseek harness to think dynamically like human,automatically judge the difficulty of tasks with suitable thinking chain.

Filesystem permissions for shell calls, granted per path and capability rather than per command name. The command line is parsed for the read, write, create, delete and execute effects it needs, a capability it lacks raises the approval card instead of a flat refusal, and the same rules are compiled into the macOS Seatbelt profile the process, its children and the code its arguments never showed all run under. An Approvals tab in the conversation reads the audit log back and shows which rule, automatic reviewer or person answered each call.

Back up your DSH profile configuration to a private GitHub Gist on a schedule, with merged restore.

Prompt-polish template injector for DSH: click ✨ in the composer to inject a "polish my prompt" template (current draft auto-embedded), no send, no network, no model — the main agent rewrites with full context. Replaces narrative-prompt-polish (2026-09-14 migration).

Model-callable compact_agents tool that force-compacts context in every live session (main session, ordinary sub-agents and AgentTeams members alike), queues busy targets and compacts them when the turn ends, reports the shadowed node count and estimated tokens per target, and ships a browser form for the trigger ratio, retained ratio, controlled-phase output budget, auto-continue budget and an end-of-turn pre-compaction ratio that compacts near the trigger line once a turn ends, so a reply no longer opens with a wait for the summarizer.

Automatically highlights key points, definitions, warnings, and questions in completed assistant answers using one separate model call.

GLM Mode agent preset for zhipuai/glm-5.3-flash: PTC/Code Mode tool presentation, a reasoning loop guard and a tool spin guard (live-incident driven), and GLM-specific auto-compaction at 75%/22%.

Manage VPS servers over SSH key login: 21 zero-token /vps- commands (status queries, recipe installs with a plan and /vps-yes confirmation, reboot that waits for the machine to come back), an in-conversation terminal (xterm.js over ssh -tt) for interactive programs, 5 agent tools with risk-tiered confirmation, file backup with automatic restore and a firewall/SSH safety net, 29 built-in recipes, and a settings page for adding machines.

Review-first batch automation for DeepSeek Harness: three reviewed samples, a full preview, one approval, then a safe apply across many files.

Per-reply read-aloud with a multi-provider settings page — MiniMax or any OpenAI-compatible /audio/speech endpoint, with voice, emotion, speed and model selection plus an auto-read toggle.

Per-project memory for DeepSeek Harness. Three Markdown files per workspace — PROJECT.md, DECISIONS.md and SESSIONS.md — are auto-created on the first step of any session in that workspace, re-read from disk and re-injected only when they change (and re-injected if compaction dropped them), and written back by classification through a memory_checkpoint tool, with a bounded end-of-turn nudge when a turn did work but recorded nothing. memory_read and memory_search read the live log and the archive, the latter over a zero-dependency BM25 index. The session log is capped at 200 entries with the overflow moved to SESSIONS-archive.md — never injected, but visible, readable and searchable, and restorable one entry at a time. Settings page: a workspace list with a path filter, read-only tabs for the three memory files plus the archive, reload, export/import of one workspace's memory as a JSON bundle, a two-step clear, a panel that rewrites or removes the AGENTS.md instruction block, and a PROJECT.md staleness reminder. A composer status chip shows that workspace's sync state and creates the files on click. Zero dependencies — no vector store, no embeddings, and no model calls.

Same-origin in mechanism with the two loudest lines in context compression. The code-skeleton gate follows the skeletonization approach of Headroom (Apache-2.0), whose published headline is 20% fewer tokens for coding agents and 60–95% fewer tokens for JSON, same answers. The estimator channel follows TokenPilot (arXiv:2606.17016), which reports up to 60% lower cost for long-session agents. Both figures are theirs, quoted as-is; this plugin ships no benchmark of its own and claims no reduction of its own. What it adds for DeepSeek Harness: choose a compression profile, set the Auto Compact trigger level and toggle code-skeleton compression from one settings section, with exact DeepSeek V4 tokenizer measurement, same-revision count verification, and fail-open behaviour that keeps the original tool results on unsupported models.

Customize the interface font, size, weight, color and layout from the settings page, Word-style and WYSIWYG, auto-saved. Ships two bundled open-source fonts (STIX2Text, Latin Modern Mono Light) plus an author-recommended typography, and stores settings under ~/.dsh.

Team knowledge base for offline knowledge sharing (FDE box scenario): browse, full-text search and refinement entry points; raw material is queued automatically and distilled into wiki pages by a serial bot session (Karpathy LLM Wiki pattern: immutable raw, two-step refinement, log stream, monthly lint).

Git worktree-aware workspace browser for DeepSeek Harness: project sections, repository-grouped worktrees, and automatic workspace synchronization.

Adapt ERP: learn your ERP through the browser and build private local knowledge in DeepSeek Harness

FDE toolbox bundle: installing this one plugin pulls in a curated set of common dsh plugins (git server, WebDAV mount, knowledge base, scheduled tasks, auto-resume, UI tweaks, auto-retrospection, file manager, smart titles, task board, plugin market, context trimmer, IM bridge, sidebar enhancements), with a panel showing install status and one-click gap-filling.