Plugin

Vision toolkit for text-only DeepSeek: model-invokable `vision` tool, wrapper adapters for deepseek/opencode-go (v4 flash/pro), Antigravity IDE quota (default, flash/pro) / any OpenAI-compatible VLM / Gemini / local Ollama channels, evidence memory with compaction rehydration, content-hash cache, and a bilingual client panel.

China A-share financial data MCP server for the harness: 11 fin_data__* tools (quotes/K-lines/financials/calendar/special-data/announcements/EDB/reconcile/funds/indices) over THS free official REST (primary) + AKShare (fallback) + Wind (exclusive domains), with observable degradation, context-budget compression (result-side -72.2% measured), and an offline 10-year market-data lake; BYOK.

Local toolbox for the DSH web GUI: 35 pure-client tools (text, encoding, hashing, extraction, conversion, reference tables) in a sidebar view, plus the /toolbox command and config-driven agent tool exposure.

Zero-dependency MCP client bridge that connects stdio and HTTP MCP servers and registers their tools as mcp_<server>_<tool> for the agent.

Conversation history recall for DSH: three-layer (literal/fuzzy/semantic) retrieval over every past session's original text, fully local & offline — AI never forgets what you told it. One-command install via `dsh.bundle.patch`, semantic layer runs in a worker thread.

Turns local markdown and text documents into a queryable knowledge base with hybrid semantic and keyword search, citation verification, and source injection.

Human-readable Markdown memory for DeepSeek Harness: user-level (~/.deepseek-harness/MEMORY.md) + workspace-level memory injected every turn, auto daily-log writing with distillation, bridges existing WorkBuddy/CodeBuddy memory dirs, memory_note / memory_note_user / memory_read tools with built-in dedup, and a bilingual settings page. Plain-text storage, no database.

Deterministic context compaction: prunes conversation atoms in reference-graph topological order with no LLM calls during compaction, and keeps pruned atoms recallable by marker.

Adds a Settings Usage dashboard for DeepSeek API balance, official token and cost analysis, trends, context warnings, and live API activity.

**DeepSeek Chat (chat.deepseek.com) same-style attachments**: paperclip upload button, 240×64 DS-style file cards with official colored doc icons (PDF/DOCX/XLSX/PPT/IMG extracted from the DS frontend bundle), drag-and-drop, text extraction (PDF/DOCX/XLSX/TXT) injected into the message, and real attachment cards rendered in the transcript (custom user renderer) with the model reading full content.

Workspace file tree for the Web UI: multi-tab preview (text/DOCX/PDF/Markdown/CSV/images), inline Markdown editing, a Git changes panel, and file operations (rename/delete/copy/move/create) via context menu.

Right-side prompt toolbox panel with 24 built-in deep templates plus user-defined ones, accessible via the /prompt slash trigger and a context-aware floating suggestion card; one-click inserts the selected prompt into the composer.

Trasmissione asincrona del contesto, riassunta da un LLM, tra le sessioni DSH e le Agent Team Room autorizzate, con snapshot istantanei e riepiloghi programmati

Montaggio incrementale dei file con deduplicazione delle letture: gli intervalli di righe montati non vengono mai reinviati al modello, le modifiche su disco invalidano e rimontano, con una scheda File montati e il conteggio del risparmio di token

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

Note vocali in ingresso, risposte parlate in uscita: detta audio che diventa messaggi utente (trascrizione), fai leggere ad alta voce le risposte dall'agente (sintesi vocale), local-first sotto ~/.dsh/voice

Crea pacchetti di knowledge base verificabili (SQLite FTS5) da md/txt/docx/pdf con recupero deterministico e lettura del testo originale

Local knowledge base RAG for DeepSeek Harness -- index project files and search for relevant context

Writing tools that remove AI-sounding patterns and match your personal voice. 8 deterministic tools scan text, build a style fingerprint from your samples, and return rewrite briefs.

DeepSeek Harness (dsh) plugin for @tabilo/ai-code-review: registers the ai_code_review tool (review | context) that reuses the Node.js engine to collect diffs, run tests/coverage, do impact analysis, and feed pack skills to the model.

Youdao-style word-selection translation for the DSH web GUI. Select text anywhere, click the floating button, get a translation from the harness's own LLM — no API keys, no third-party endpoints. 有道风格划词翻译：DSH Web GUI 里划选文本即现悬浮「译」按钮，点击由 harness 自带大模型翻译，无需

A searchable, sortable model picker for the DeepSeek Harness Web UI — provider groups, favorites, models.dev prices, context windows, live per-task token cost and a local-model filter. One-command install: dsh plugin add dsh-model-garden.

DSH 智能上下文压缩插件 —— 在有限窗口内管理认知资源，让 Agent 记住真正重要的信息。 Smart context compression for DSH — managing cognitive resources within limited windows, so your Agent remembers what truly matters.

Xiaomi MiMo text-to-speech controls for DeepSeek Harness Web assistant messages