Plugins

LongCat-2.0 LLM adapter: 1M context, binary thinking mode, tool calling, and streaming over the OpenAI-compatible endpoint.

Android client implementation for DeepSeek Harness: bridges local dsh web to the OneBox app with QR scan-to-pair and an end-to-end encrypted cloud relay tunnel.

Stages exact DSH tool calls without dispatch, presents complete canonical arguments in a durable Batch Review Inbox, invalidates approvals after edits or restarts, and commits only a matching SHA-256 digest plus single-use nonce through the normal DSH tool pipeline.

Speaks agent replies in the DeepSeek Harness web UI through a provider fallback chain (OpenAI, ElevenLabs, Google, Azure, Groq, Deepgram, OpenRouter, Edge, Piper, eSpeak), so a failing or rate-limited provider falls through to the next instead of going silent.

Read-only GitHub access for agents, wrapping several tools. Inside the tool it automatically probes and selects whichever GitHub access method works locally, and tries network proxies on its own. That cuts down the network and parsing problems an agent may hit when accessing GitHub, and the overhead of it repeatedly trying different approaches.

Desktop and webhook alerts on macOS, Linux and Windows when an agent finishes a turn, errors, or waits for approval — zero-dependency native notifications (osascript / notify-send / PowerShell toast) plus a Slack-compatible webhook, with a configurable minimum turn duration.

Ship a project to Cloudflare and publish your plugin to npm — the first deploy needs no cloud account, and credentials never reach the model.

File-change monitor and code editor for the DSH Web UI. Agent edits appear beside your conversation as real-time line-by-line diffs, with a syntax-highlighted editor, one-click revert, change history, workspace switcher, and per-session isolation.

Read the config your harness actually booted, and validate an overlay before you apply it. A Blueprint tab for the DSH web client.

Automatic Flash/Pro routing for DeepSeek Harness subagent calls: light tasks run on a cheap model (e.g. V4 Flash), heavy tasks stay on the strong model — with per-call overrides and /delegate session modes.

Remote-SSH-style workspaces: turn an SSH host and a remote directory into a native DSH workspace; the agent operates the remote filesystem directly via 12 rw_* tools (SFTP/exec), with workspace-confined paths and known_hosts verification.

Kubernetes ops for the agent: get resources with structured JSON output, describe, logs, exec, apply/delete (user-confirmed) and port-forward.

Bot Mode for DeepSeek Harness: a roster of named bots with avatars, personas and per-bot chats, each backed by one durable continuable subagent session that keeps memory across turns.

More agent presets for DSH, derived from other coding agents such as Qwen Code and iFlow.

Project documentation scaffolding skill: question-driven setup of project standards, AI-collaboration workflows, and memory discipline across DSH, Reasonix, Claude Code, and Codex.

Self-learning loop for dsh: record lessons, draft and promote skills, periodic curator review that corrects, consolidates, and retires skills.

Fruit price tracking skill: collect and query global wholesale fruit prices with RMB/kg conversion.

Global news monitoring skill: track world events and analyze impact across industries, currencies and commodities.

Fridge manager skill: recognize ingredient photos and recommend recipes, with inventory and shopping reminders.

Tracking assistant skill: monitor product prices, celebrity news and custom metrics with change alerts and scheduled pushes.

Fishing assistant skill: spot analysis, fish activity and bait/lure recommendations from water photos and weather data.

Token usage and cost metering for dsh: per-session and aggregate statistics with configurable pricing and reports.

Security and governance for dsh: rule-based tool denial, full tool-call audit trail, and governance reports.