Plugin

Modifica le sezioni del system prompt utente e integrate con anteprima live

Condividi qualsiasi estratto di una conversazione

Coda di task cross-sessione con note di passaggio di consegne: sessioni e subagent inseriscono, prendono in carico, completano e annullano task su una coda condivisa basata su file, lasciando un riepilogo di consegna per chi prende in carico successivamente

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

Comprimi con un clic ogni sezione espansa (righe Think, schede degli strumenti) con una pillola di conteggio live e una scorciatoia personalizzabile

Pillola di statistiche in stile iOS, comprimibile, sotto il composer: costo della sessione, saldo dell'account DeepSeek, tasso di cache-hit e utilizzo dei token in un pannello smerigliato

Composer Plus for DeepSeek Harness (dsh): git Changes panel, ↑/↓ input history, Shift+Tab /plan, one-click Continue, queue drag-and-drop, deeplinks, Auto Review allow-for-chat, notifications, 11 UI languages, auto-update

Markdown Studio：在 DSH 原生右侧文件预览与对话消息中渲染 Mermaid 图表、KaTeX 公式、GFM 表格、任务列表、脚注及代码高亮。渲染引擎随包内置，完全离线可用。 / Native DSH right-sidebar Markdown preview with Mermaid diagrams, KaTeX math, GFM tables and syntax highlighting — fully offline.

DSH (DeepSeek Harness) plugin: per-provider (account) proxy routing with a named proxy pool -?route each LLM account through its own SOCKS5/HTTP(S) proxy via DSH's bundled undici, configurable live from the DSH settings page.

DeepSeek Harness LLM adapter for Qoder CN subscriptions, built on the official @qodercn-ai/qodercn-agent-sdk. Reuses the local qoderclicn login, and exposes a fully configurable settings page (per-model context window, session pool, timeouts, model deny l

DeepSeek Harness approval guardian: a reviewer model decides permission requests before they reach you, with a System One decision-API backend (TypeSafe Jev, SiliconFlow, self-hosted Laya), a configurable low-confidence policy and an allow-rule whitelist.

Three-tier deny/ask/auto gate for the computer-use (cua-driver) tool family: each tool category gets one segmented control in Settings, and an allow list or deny list overrides the tiers per tool name.

Reads and writes a self-hosted Bitwarden/Vaultwarden vault from any session: nine bitwarden_* tools, real-time WebSocket sync with a polling fallback, and a settings panel with readonly, ask and auto write modes.

Connects one existing DSH session to QQ through OneBot/NapCat without starting a new session, and uses a fail-closed whitelist plus @-mention, nickname and configurable-probability wake rules to decide which messages reach the model.

Notifies you about 11 configurable DSH agent events (task completion, questions, denied approvals, background subagents/goals/jobs, team tasks, context compaction, triggered schedules, plugin startup and permission changes) as browser Web Notifications through a bundled service worker, falling back to Windows toast or Linux D-Bus, with three silence levels and click-to-open.

Connects a DSH Host to Slack and Feishu using your own bot applications.

Synchronizes DeepSeek Harness third-party plugin lists through S3-compatible storage with diff preview, local snapshots, rollback, and optional LLM provider configuration sync.

Correct-encoding command runner and mojibake recovery: encoding_run spawns a child process and decodes its raw output bytes (UTF-8/UTF-16LE/GBK auto-detected or forced), and encoding_decode recovers garbled text back to correct Unicode.

9router-backed web search + fetch providers for DeepSeek Harness (ctx.web). Wires the native web_search/web_fetch tools to 9router's /v1/search and /v1/web/fetch endpoints.

Bridges DSH to a local MemVault store: core memory blocks injected into the system prompt, finished turns extracted through MemVault's own pipeline, and a panel to browse, trace, review and replay what was stored.

Reasoning-effort gear presets for third-party models: 16 vendor/model presets with per-mode custom wire values, written into dsh-llm-pi-ai with pre-write validation and per-rule rejection; per-model switching between OpenAI Chat Completions, OpenAI Responses and Anthropic Messages with automatic route regrouping; plus a composer Optimize button and a settings section that rewrite the input text with a model you pick.

Adds subscription OAuth and provider Plan API-key logins through Pi adapters, using a DSH-owned credential store.

DeepSeek account wallet balance and the current peak or off-peak billing period, in a fixed status region at the sidebar foot, with a manual refresh and an official top-up link.

Desktop-only token statistics, provider quotas, custom quota queries, optional WorkBuddy credits and an advanced model selector.