Plugins

Two-way WeChat bridge for DeepSeek Harness via the iLink protocol: bind your personal WeChat with a QR scan and chat with a local DSH agent from the chat box (text, images, voice-to-text, files); a web settings panel handles binding/start/stop/status, project-session binding continues the conversation on desktop, proactive wechat_notify pushes include throttling, and the pure-Node daemon runs on Windows/macOS/Linux.

Native tools for an Obsidian wiki vault: wiki_query, wiki_write, wiki_rename, wiki_scaffold, wiki_archive, and wiki_lint cover BM25 search with link-graph context, bookkeeping writes with sha256 source tracking, vault-wide renames, mode scaffolds, source archiving, and health checks — with cross-process locks and optional git auto-commit.

Import Codex-style sprite-sheet pets and render them as a floating shell.overlay with a pet library, interactions, and agent-state linkage.

Secure remote access for the official Web UI: authenticated LAN/tunnel gateway with QR + HMAC one-time pairing, per-device sessions and revocation, mDNS discovery, and a fork_session tool.

IM channel bridge: WeChat (ilinkai) / QQ / Feishu with proactive push — wake the channel bot from scheduled tasks and deliver AI replies to your phone.

DeepSeek Harness 微信网关适配插件：复用 DeepSeekAdapter + 流式 think 标签转译

DSH web client plugin: open a session directly from the URL (?session=<id>).

Session deep links, full session export (markdown/JSON), approved cross-session messaging with pairing, and team roster, rotation and recovery tools for multi-session work.

dsh-ecolink DSH 适配层:直读本地记忆池、pre-step 注入(打分+预算+会话去重)、#记忆名 过滤,打通网页端记忆生态

Fills missing context window, max tokens, thinking levels, and image input on custom DSH models from models.dev, and lists unmatched models for manual edits.

Runs one-time and RFC 5545 recurring Agent tasks in fresh DSH sessions, with visual schedule editing and session-linked history.

OpenCode Go subscription chat for DSH with per-model Completions, Responses, or Anthropic protocol selection, model discovery, context, vision and thinking metadata, effort defaults, and usage meters.

Switch the language of the agent's thinking/reasoning process (chain-of-thought): 简体中文, English, Русский, Français, Deutsch, Español, 日本語, 한국어 and more, or auto-follow the system locale. Adds a Settings → General row, a system-prompt instruction (per-prompt assembly, applies to new sessions), and the /thinking-language command.

A web Settings "Loop engine" switch that swaps the agent loop driving every dsh session among five engines — the built-in in-process loop plus hosted Claude Code, Codex, Pi, and Kimi Code — with zero changes to the harness; each hosted engine keeps its thinking and tool calls in the durable session transcript, takes over commands, skills, and the agent preset, and runs sandboxed through the dsh subprocess seam.

Requires DSH 0.1.6-alpha.2. Annotate completed assistant replies, submit multiple drafts with official composer text and attachments as one Session message, navigate linked model replies, and use Settings to hide selected reasoning or tool details without changing stored events.

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

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.

A desktop pet plugin for DeepSeek Harness (DSH): import Codex-style sprite-sheet pets and render them in the DSH Web GUI as a floating shell.overlay, with a pet library, interactions, and Agent-state linkage. / DSH 桌面宠物插件：导入精灵图序列帧宠物并在 Web GUI 悬浮渲染。

Side web-preview panel: local static hosting, Markdown/code/image preview, one-click run of non-static projects (Cargo/npm/Go/Python) with live logs, drag files into the chat (saved to the workspace), element mark & annotate, workspace file search on 404, and link-click takeover into the side panel.

Circuit breaker for idle agent turns: watches agent/assistant-stream and cancels a turn that produces only reasoning — no text and no tool call — after 45s, after 80000 reasoning characters, or on a degenerate repetition pattern (exact repeat unit, sentence-template repeat, sparse repeat, or 6-gram density). On trip it injects a continue instruction that requires the next action to be a tool call, and ships 11 regression cases plus per-gate tuning.

Adds an edit action to finalized assistant replies in DeepSeek Harness, letting you rewrite the reply text or reasoning chain; the edit is saved as a surface replacement.

FriendliAI serverless LLM adapter for DeepSeek Harness — OpenAI-compatible chat completions with dynamic model discovery and reasoning support

Reasoning-wait thinking indicator for the DeepSeek Harness web composer