Plugin

Competenza di sceneggiatura cinese in formato lungo: due blocchi di input (contesto + bibbia dei personaggi) che alimentano un motore di valori causali, una revisione anti-sapore-IA e un registro di continuità; funziona su Codex / Claude Code / dsh / zcode.

Importa la cronologia chat di claude-code / codex / reasonix / zcode nelle sessioni dsh: associazione allo spazio di lavoro, chiamate agli strumenti preservate, protezione per sessioni troppo grandi, ripristino della compattazione zcode.

Scansiona oltre 20 agenti AI su questa macchina (Codex, Claude Code, cc-switch, Hermes, opencode, Gemini, Grok, Kimi, CodeBuddy, Trae, OpenClaw, Qoder, WorkBuddy, Zcode, Cursor, Windsurf, Cline, Roo Code, Qwen Code, ...) e sincronizza, gestisce e aggiunge con un clic i loro server MCP e skill in DSH — globale o per workspace.

Memoria di progetto persistente in stile ZCode con un gestore impostazioni completo, iniezione index-first e strumenti di memoria dell'agente.

Continua il lavoro di Codex, Claude Code, Cursor, Grok, Pi e ZCode in DeepSeek Harness.

Quota del piano Command Code nella barra laterale di DSH sopra le impostazioni: finestre a 5 ore, settimanale e mensile come percentuali usate con conto alla rovescia al reset, un comando /quota e una CLI senza dipendenze. Legge la chiave dalla tua rotta provider, quindi non serve configurazione né altri plugin.

Esegue un dibattito tesi-antitesi-sigillo il cui verdetto è calcolato da codici di uscita reali dei comandi e conteggi dei casi, mai dalla prosa dell'agente.

Bridge locale multi-piano per DeepSeek Harness: usa i tuoi abbonamenti esistenti a ChatGPT Codex, Claude, ZCode (GLM) e Qwen tramite un solo proxy di loopback, con una scheda di stato nella pagina delle impostazioni e provisioning in un clic. Nessuna modifica al core di dsh.

Gestore di competenze DSH: sfoglia, abilita/disabilita, importa da Codex/Claude Code/ZCode/WorkBuddy/QCoderWork, scoperta automatica delle competenze con supporto ai link simbolici.

DeepSeek Harness plugin for model smart configuration & capability adaptation, ported from ZCode

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.

Token usage statistics panel for DeepSeek Harness: usage trends, model breakdown and activity heatmap, hand-written SVG, zero chart libraries.

ZCode CLI app-server relay for DeepSeek Harness, with GLM streaming, image input and session reuse using an existing Start Plan login; requires the ZCode client.

Structured git tools for DeepSeek Harness agents: status, diff, log, branch, commit and stash. Output is pinned with ten `git -c` overrides so a user pager, colour or quotepath setting cannot reshape what the agent reads; every invocation is an argv array, so no shell ever parses an argument; and the mutating actions go through the harness approval service, refusing rather than proceeding when no approval service is mounted.

Multi-instance ComfyUI orchestration: probes every configured ComfyUI endpoint for its GPU, free VRAM and queue depth, then dispatches a generation job to the idlest eligible instance. Ships three tools (comfyui_farm_status, comfyui_farm_pick, comfyui_farm_run). An instance is eligible only if it is reachable, has at least the requested free VRAM, and its queue is no deeper than the configured ceiling; eligible instances are ranked by free VRAM minus queue depth times a weight, so an idle shallow queue wins over a busy large one. Zero runtime dependencies. Optional retry on probe failure, because a single timeout across an SSH tunnel is not proof that an instance is down.

Long-term memory for DeepSeek Harness, read-only as of 0.1.0: a scribe_recall tool that reads a plain-markdown memory room, path rules that refuse directory traversal, Unicode smuggling and NTFS alternate data streams, and a bounded index whose truncation is always reported rather than silent.

Rapid-refill circuit breaker for DeepSeek Harness automatic compaction. It refuses a compaction that would be futile — the context refilled within fewer than N tool turns M times in a row, which the unbounded step-pressure trigger cannot detect — and instead of burning a summarization call on every step it reports the situation with advice, usually that a single read or tool output was too large. Shows state and re-arms through /compaction-breaker, and injects one prompt section so the model relays it to the user. Covers host-plane sessions through its profile bundle; ordinary sessions need one row replaced inside an agent preset.

Make the model believe it is inside the Z.ai Code (Zhipu ZCode) agent environment: replaces the harness identity opener and injects a ZCode rules skeleton with a dynamic project section. 让模型认为自己处于智谱 ZCode Agent 环境。