Plugins

DSH Web GUI paperclip button: a 📎 button in the composer opens a file picker (drag & drop supported) and inserts file contents into the textarea.

Lets text-only models handle pasted chat images, with a native vision experience, batch image viewing, and a built-in OpenAI-compatible analyze_image tool; vision-capable models are unaffected.

Floating card showing your real position P&L (今日盈亏), Shanghai Composite Index, and intraday chart, auto-synced from the Tonghuashun investment-ledger — no manual watchlist setup.

Bridges DeepSeek Harness lifecycle status, errors, and approval requests to a locally running OpenPets desktop companion.

Unified image generation router for DeepSeek Harness (DSH): auto-discovers image models from any OpenAI-compatible endpoint, provides draw_image and draw_list_sources tools, supports SenseNova, StepFun, Agnes, Qwen, Flux, SD, Imagen and more.

Renders pasted/uploaded images inline in the DSH Web chat and gives text-only models vision: the model-invokable visual_review tool calls any OpenAI-compatible multimodal API first, falling back to a local Qwen3-VL worker.

Vision MCP and DSH bundle for text-only DeepSeek: analyze_image, analyze_clipboard, compare_images and vision_status tools, a visual settings page, free GLM-4.6V-Flash by default, result caching and rate-limit tolerance; keys stay out of logs.

Give agents access to files on the machine where the browser runs: user authorizes a local directory via File System Access, tool calls relay over the plugin's own WebSocket; read-only compat mode for mobile/insecure contexts.

Learning Mode agent preset: a coding agent that teaches while coding — concrete scenario-grounded explanations, Socratic guidance, and TODO(你) practice blanks, modeled on Claude Code's Learning output style; installable via dsh plugin add (dsh-learning-mode on npm).

Tracks the agent's state as Yogācāra mental factors over a durable seed store, and feeds it back into the prompt as first-person inclination.

Permanent composer-dock balance card: real-time DeepSeek API account balance with 5-minute auto-refresh, a manual refresh button, and low-balance color warnings.

Drag & drop or click to attach any non-image file (PDF/Word/Excel/ZIP/text) into the composer: in the desktop shell it resolves the real Finder path instantly; otherwise it uploads to the workspace and inserts the path.

DSH plugin: edit the system prompt (deployment persona) from the Settings page, with live preview.

Writes local JSONL summaries of per-turn tool counts and coarse verification signals without storing prompts, tool arguments, or result text.

Fail-closed Feishu (Lark) channel bridge: chat with a bot, get dsh agent turns back — with opt-in human-in-the-loop tool approval (Allow/Deny cards before every bash call, fail-closed timeout). Official-Python-SDK-only integration (exact-pinned); deny-by-default allowlist, webhook signature/timestamp/replay verification, per-chat sticky sessions; daily latest-SDK compatibility canary; bilingual docs.

Per-workspace completion ringtones plus attention sounds for approval, question, plan-review, goal-blocked, and task-failure events, with built-in synth, voice (TTS), and custom audio.

Agent plugin for major harnesses — DeepSeek Harness (DSH), OpenCode, Pi and Codex: define custom AI agent roles with per-role prompts, models, skills, permissions, memory and multi-agent orchestration.

Captures the agent's own self-reported mistakes into a categorised lesson library that is re-injected into the system prompt every turn (each captured draft is confirmed or edited by the user before it is recorded), and adds two conversation-header panels for editing the cross-conversation global prompt and a per-session prompt.

Markdown rendering for DeepSeek Harness sent user messages: every message bubble renders lists, code, tables, quotes and inline formatting through the host's own Markdown pipeline, while queues, previews and the composer keep their plain projection.

Third-party model settings for DeepSeek Harness: pick a provider and a model in the composer menu, gate a model's thinking level with one switch on the official Models page card, and configure per-route request headers.

Ollama Cloud provider for DeepSeek Harness that configures the route on install, publishes each model's own thinking levels for the composer effort control, and shows account usage with an API-key field in the Models page and sidebar.

Codex-style appearance for the DSH Web interface: window edge hairlines and shadows, sidebar colours and row alignment, a model picker with a reasoning-effort power rail, composer and right-panel geometry, a full-page settings-modal pass, a Trajectory view exit, and a settings card for theme, accent, background, foreground, fonts, sidebar translucency and contrast.

Edit any user turn in DeepSeek Harness and re-run it: an inline editor on the message row rolls the conversation back to just before that turn through the official surface-replace contract, then re-prompts the agent with the revised text. The append-only