Plugin

Aggiunge generation_fork e generation_run per copiare un preset dell'agente ed eseguire un'attività in una nuova sessione.

Plugin schema colori per Web UI: cambia e mantieni i temi dalle Impostazioni, con 8 preset open source integrati e temi personalizzati.

Preset agente in modalità codifica DeepSeek Harness adattato a Windows con shell PowerShell 7 persistente.

Gestore di plugin nel web per DeepSeek Harness: elenco plugin categorizzato, bundle predefiniti con cambio con un clic, importazione/esportazione e rollback automatico in caso di errore, e marketplace dei plugin con installazione con un clic.

Pagina Skill Manager nel pannello impostazioni DSH: esplora skill di sistema / utente / workspace / predefinite, espandi una skill per visualizzarne l'albero dei file, visualizza e modifica file, importa skill da uno zip ed esportale o eliminale (le skill di sistema sono in sola lettura).

Gestore assistente in stile Hana per DSH: gestione visiva dei preset (schede, personalità yuan, ritaglio avatar) più uno stack completo di memoria Hana (riepiloghi progressivi, compilazione a livelli, archivio di fatti SQLite, memoria profonda).

Scorciatoie da tastiera per le sessioni nella GUI web di DSH: passa da una sessione all'altra come schede del browser (Alt+1-9 posizionali, slot fissati, precedente/successiva, nuova/archivia/rinomina), cambio di modello da tastiera con Alt+M, invio alternativo, passaggio del focus con Esc e Alt+W per chiudere o ripristinare un'area di lavoro dsh-split-screen — tutto rimappabile con preset Windows/macOS. Verificato su DSH 0.1.1 e 0.1.5.

Override per chiamata di modello, provider, persona e toolFilter per la delega ai subagent, con riferimenti @preset: e ID composti provider/modello

Scanner locale limitato e privacy-safe per metadati di Codex, Claude Code, WorkBuddy e CodeBuddy: aggrega atomicamente evidenze chiave e consiglia deterministicamente preset DSH integrati e capacità opzionali — senza conservazione del contenuto, accesso di rete o mutazione dei preset.

只填 Key 的服务商预设：50 家渠道为 DSH 一键写入官方 llm-pi-ai 路由与凭据（插件），并可写入腾讯 WorkBuddy、OpenCode（Key 走其 auth.json）与 cc-switch 的配置（CLI）；核心为纯 JS，可被更多应用的外壳复用。

Drive DSH from anything that speaks HTTP: 47 routes (REST + SSE) for workspaces, sessions (create/prompt, live SSE generation, history, stats, todos, cancel, ask-user Q&A), models and the global default model, providers, agent presets, settings namespaces, skills, and workspace files including resumable chunked upload — plus an OpenAI-compatible /chat/completions, a built-in OpenAPI 3.0 spec and an interactive request page. It only injects the host webServer and tools, so it rides on the DSH webserver (default prefix /api/v1) or its own port with optional API-key auth, and it ships a skill that teaches the DSH agent to call the API.

Replaces the reasoning-effort dropdown with a draggable snapping slider, and draws 13 canvas effects across five style families (thrust, fluid, fantasy, tech, texture) with three tiers that unlock as the effort level rises. Custom mode combines 10 particle forms with 8 flow trajectories; 9 accent presets and a hex picker recolor every effect, and optional key sounds cover two voice clips, a synthesized duck squeak, a mechanical click and a local audio file.

Drive your local DSH from WeChat: a self-hosted iLink bridge over a persistent ACP session (context lives in DSH and is resumable), phone conversations grouped into the desktop workspace, with image recognition, file messages (Excel/Word/PDF, parsed by the agent itself) and voice transcripts. Access defaults to strict (only registered devices are served); the phone channel's permission preset is wide by design - see the README security section before sharing the bot.

Multi-provider LLM API balances under the chat input, with presets for DeepSeek, OpenRouter and SiliconFlow.

Compaction fallback for compaction-basic: when its LLM summary throws, comes back empty or cannot fit the window, the span is compiled deterministically with a seq pointer on every line (vendored dsh-compaction-instant compiler). Adds recall and search tools, /recall and /context commands, an idle trigger at 45% of the window and an on-disk span archive. The engine mounts as one row in the agent preset (docs/dsh-integration.md).

A DeepSeek Harness bundle of the 25 promoted mattpocock/skills with a native agent preset, an invocation-aware skill provider, and a light grilling-to-implement bootstrap.

Custom modes and custom prompts for DeepSeek Harness (dsh): edit a mode's system prompt on the settings page (it takes effect on the next model step), choose its base mode, switch plugins row by row, and keep several assistants side by side.

Agent preset plugin for DeepSeek Harness that triages every request, delegates implementation to an expert, and schedules parallel work through a dependency-DAG taskboard and a file-based message bus before an independent review gate. Ships with only 11 core experts out of the box; more expert teams (Agency agents EN/ZH, classic collections) are one-click downloads from the settings page over dual GitHub/CDN channels with sha256 verification.

Alibaba Bailian (DashScope) model catalog preset + auto-adapter for DeepSeek Harness — reasoning effort levels, thinking budgets, context windows, auto-adaptation of existing Bailian routes, a configurable context ceiling

Compares existing DSH sessions or runs controlled A/B trials between agent presets, showing aligned timelines, paired metric deltas, explicit success checks, and exportable reports.

Adobe Lightroom Classic as native dsh tools through the lightroom-py MCP server: read the catalog, apply develop settings and presets, export JPEG/TIFF/PSD/DNG, and write ratings, labels, keywords and IPTC — 15 tools driving the Lightroom Classic installed on the local machine, no cloud round-trip; the Python package is on PyPI and the Lightroom plugin installs with one command.

Infinite canvas for sessions, with regions bound to workspaces and agent presets, pinned session cards, sticky notes and alignment guides.

Expert market for DeepSeek Harness: WorkBuddy expert/expert-team system ported onto native agent presets, 425-expert catalog installed on demand, capability subtraction, and team delegation tools.

An approval-gated OME engineering delivery preset with session-isolated lifecycle evidence.