Plugins

Agent billing and usage observability for dsh web: session-log direct-scan recording (zstd, per-event timestamps, watermark + lastSeq double dedup), multi-account rate profiles per provider and model, per-window live badge reading the window session id via React fiber, full glassmorphism dashboard with 14-day sparkline, budget alerts, relay-station balance queries and a 332-model official price library.

Immersive read-only reading panel for DSH — the model delivers pre-formatted Markdown to a native right-sidebar tab via `reading_pad_send`, with three low-blue-light themes and 30em measure typography; also browse manuscript chapters read-only.

Balance badge that follows the active model provider: official readings for DeepSeek, Qwen Token Plan and Aliyun BSS, plus Moonshot and OpenRouter endpoints not yet key-verified.

Fleet console for DeepSeek Harness: one local dsh page manages many remote dsh machines — live idle/running status, in-place switching without new tabs, keep-alive iframes, cross-device session reading, one-click refresh/restart, and a controller/managed role split.

A calmer reading view for DeepSeek Harness with auto-collapsing process, a minimap-style message navigation rail, in-page search, unified failure cards, and generative MCP Apps (SEP-1865) in sandboxed iframes.

A draggable tarot card back in the corner of the DeepSeek Harness UI. Click to draw, right-click for the four spreads, full 78-card deck with bilingual meanings. Readings use only the cards actually drawn.

DeepSeek Harness plugin: GitHub repository/issue search, repo and issue details, and file reading tools (github_search / github_get). Anonymous by default; an optional read-only fine-grained token unlocks code search and raises the rate limit.

A phone shell for the web GUI - the sidebar becomes an overlay drawer that closes when a session is tapped, the settings sheet goes full-screen single column, and the transcript is retuned for phone reading.

Per-profile settings overlay for DeepSeek Harness: global settings.yaml stays the baseline while each profile overrides any namespace through its own profiles/<name>/settings.patch.yml — object sections merge recursively, scalars and arrays replace wholesale, and !unset masks an inherited value. The overlay is transparent to existing plugins (they keep reading ctx.settings unchanged), writes land in the profile overlay only, and official schema validation, revision semantics, expectedRevision conflicts, watchers and events are untouched. Ships a settings command family (get/set/unset/mask/unmask/promote/demote/migrate/diff/layers) plus a Profile Settings section in the web Settings panel over a loopback RPC channel.

WeChat Reading (WeRead) multi-target export for DeepSeek Harness via the official Skills API gateway: browse your bookshelf, export highlights & thoughts to flomo, a local Markdown file, or Notion, optionally reworked by a configurable LLM prompt.

Private local file attachments for DeepSeek Harness with native images and bounded document reading.

Upload, leitura, OCR e renderização de arquivos arbitrários vinculados ao workspace, para o DeepSeek Harness.

Plugin de sumário da conversa para o DeepSeek Harness: um painel lateral e uma cortina de largura total como duas visões do mesmo sumário; três escopos de busca (títulos, texto completo e outras sessões); várias formas de saltar (um cabeçalho, o cabeçalho de um turno, o fim de uma seção); um sumário completo ou um modo de leitura somente de perguntas, alternáveis a qualquer momento; posição de leitura memorizada por sessão; e interface em chinês/inglês com um cartão de configuração do plugin.

Upload, leitura, OCR e renderização de arquivos arbitrários vinculados ao workspace para DeepSeek Harness.

Bloqueia que agentes leiam ou gravem arquivos sensíveis (.env, credenciais, material de chave), mascara valores com forma de segredo vazados nos resultados de ferramentas, mantém um diário de auditoria e expõe ferramentas seguras de inspeção sg_* que nunca imprimem valores brutos.

Dá ao agente sua própria caixa de entrada de e-mail via AgentMail — onze ferramentas para enviar, ler e rotular mensagens, além de e-mails recebidos entregues em uma sessão do harness por thread, com portão de aprovação e lista de destinatários permitidos em tudo que sai.

Cross-session long-term memory: captures durable facts from each turn, auto-associates them by shared entity and tag, and recalls with BM25 plus spreading activation over the link graph.

Local TXT reader in a right-sidebar tab plus a spoiler-safe AI reading companion: the model only sees what you have already read — the current chapter, the tail of the previous chapter, and a per-book background file it grows as you go. Excerpts, thoughts and the companion replies become structured Markdown notes exportable to Obsidian; raw text unlocks only for a book you mark as finished.

Paper library and reading workbench: arXiv search, a local plain-file library (metadata / PDF / extracted full text), and three-level reading notes (overview / understanding / critique) kept as markdown beside the PDFs; seven model tools plus a web panel.

A dsh-better-sidebar reading view for .pptx decks: slides in deck order, bullet levels, speaker notes and inline pictures. Ceilings on archive size, per-part inflated bytes and slide count keep a deck from freezing the tab.

A dsh-better-sidebar reading view for .docx files: headings from the style map, paragraphs, lists, real table cells, inline pictures and header notes. Ceilings on archive size, per-part inflated bytes and rendered blocks keep a document from freezing the tab.

Speaker button beside the composer microphone — one click scrolls to the start of your newest question, marks it with a blinking caret and reads from there through the newest agent reply (dsh-tts, browser voice as fallback); press-and-drag-right picks any other reading start position on the page, press-and-drag-up opens a vertical mixer for in-page media volume and system output volume.

Conversation outline panel for the DSH web surface: user questions as root nodes (index, time, tool count and text volume per turn) with the Markdown headings of assistant replies hanging beneath them, plus level slider, search scope, bookmarks, copy and export as Markdown, section jump, keyboard navigation, a right-edge density rail and per-session reading-position memory. Read-only UI: it never touches prompts, tool results or provider traffic, and writes nothing outside its own localStorage keys.

Windows-native computer use for DeepSeek Harness: two tools drive and read any desktop app. One batch call runs find, click, type, key, read, wait and screenshot steps in a single engine pass, so a task whose steps are known up front costs one model round trip; reading returns window text rather than an image, and input and capture prefer UI Automation patterns, Win32 messages and offscreen PrintWindow so the user's focus and pointer stay untouched.