Plugins

DeepSeek Harness 原生视觉 Bundle：粘贴或拖入图片，通过托管的 deepseek-vision-mcp 调用 OpenAI 兼容视觉模型。

Digimon-style raising game: hatch an egg that feeds on real work (turns, tool calls, errors) and evolves along four branching lines shaped by how you work; zero tokens, invisible to the model.

Popup guardian for session logs: opens with the Web UI on a configurable reminder interval (10 min-3 h), with one-click incremental backup of every session.jsonl(.zstd) under ~/.dsh/sessions in raw or readable chat-log format.

Native tavern management panel for DeepSeek Harness: multiple character cards, multiple worldbooks, switchable presets.

Toggle switches for the plugin inventory: enable/disable any plugin live from Settings → Plugins → Plugin list without restarting, with groups/filters, bulk toggle, undo, and backup.

Open plugin marketplace: live GitHub dsh-plugin topic search with per-repo package.json verification (dsh.bundle/dsh.client manifest badges and a verified-only filter), npm-first installs with same-source anti-squatting checks, update detection, and five agent tools for headless use.

Password-gated public access for the DSH Web GUI through quick or named Cloudflare Tunnels, with HTTP/WebSocket proxying and an in-app directory picker.

Vets third-party plugins before you trust them: static scan for malicious patterns (exfiltration, credential access, obfuscation, persistence) and over-privileged path use, transitive-dependency coverage, official-package hash baseline for supply-chain tamper detection, and an optional plugin-tool call gate.

Settings -> Plugins switchboard: every loaded plugin card shows its package description and runtime phase, with fuzzy search and start/stop toggles that never rewrite config files.

Unified LLM request/response inspector: reasoning-effort tuning, external-think export, traffic & bundle analysis.

Wraps Python virtual environment management commands: reduces the network and permission problems agents hit when managing environments through terminal commands, works across operating systems, and routes installs automatically through mirrors and local proxies. The tools are strictly confined by the granted read/write permissions.

Connects dsh to Weixin, with arbitrary file sending support.

Feishu (Lark) bridge for DeepSeek Harness: one-command install, streaming progress cards with a tool panel, ask/approval button cards, attachments, and proactive feishu_send pushes.

Multi-channel IM bridge for DeepSeek Harness: route WeChat (ClawBot/iLink), QQ, and Feishu (Lark) chat messages to a DSH agent and relay its replies back, with per-channel sessions and reply dedup.

Registers a SpecWorkflow skill pack for requirement clarification, implementation specs, execution, delivery review, repair planning, bug diagnosis, and source-backed research.

Kimi-Code-style swarm: batch-parallel subagent dispatch with adaptive scheduling, a /swarm command, and in-chat live progress rows.

Engineering workflow agent preset for dsh: five gated phases (requirements clarification, plan approval, TDD, parallel subagents, verified finishing) with six workflow skills adapted from obra/superpowers.

OMX-style workflow skills for DeepSeek Harness: deep-interview, ralplan, ralph, autopilot, team, code-review and 19 more, rewritten on native DSH tools, without vision skills.

Voice tools: free edge-tts neural speech synthesis, OpenAI-compatible ASR transcription, voice list, batch voice preview and health self-check.

Full-duplex voice mode for the Web UI: tap-to-toggle or hold-to-talk dictation (send key or `Ctrl`) with a live caption, host-side SenseVoice ASR via sherpa-onnx, sentence-by-sentence spoken replies, and speaking interrupts playback and the running turn (true barge-in). No API key.

Free voice closed loop for the Web UI: browser SpeechRecognition mic input with live interim results plus read-aloud speaker buttons and auto-read for assistant replies, zero configuration and no API key.

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.

Fully-local image understanding & OCR via macOS Vision Framework: `ocr_image` (text, table layout + coordinates) and `view_image` (scene, faces, QR) — paste multiple images into the web input box or pass path/URL/base64; images never leave your Mac.

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.