Plugins

Feishu bridge for DeepSeek Harness (derived from dsh-im-bridge): WebSocket long connection, approval cards, group @-mention-only replies, streaming card updates, /stop command.

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

Browser operation by accessibility refs: navigate, snapshot the page as a ref tree, act on elements, and wait for conditions; the origin policy follows the session approval stance and is enforced by request interception.

Database tools for agents: list/query/exec/schema/stats/health across SQLite/MySQL/PostgreSQL, with lexer-grade read-only protection, row caps, CSV/JSON query output and an approval-gated write path.

Docker tools for agents: ps/images/logs/inspect/exec/manage/health with JSON output, env-configurable CLI path, approval-gated exec and zero runtime dependencies.

Ask-before-act approval for every edit and every bash command: a red/green line diff before a file is touched, a description+command panel before a command runs — approve once or reject, each gate with its own master switch in Settings → General.

Gives an agent its own email inbox through AgentMail — eleven tools for sending, reading and labelling mail, plus inbound mail delivered into one harness session per email thread, with an approval gate and recipient allowlist on everything outbound.

Cross-platform Computer Use for DeepSeek Harness: virtual-mouse human-like operation (screen_observe + computer_click + type + key + scroll + drag, 11 tools), AX-tree zero-vision-cost mode with free GLM-4V-Flash vision fallback, safety guards (snapshot TTL / app whitelist / dangerous-action approval / password-box protection).

DSH审批汉化 — approval dialogs translated to Chinese before they render: DeepSeek-powered, host-side, nothing for React to revert.

A hands-off safety net: directories the agent deletes go to a trash folder first and symlinks are never followed, with zero approvals.

Take control of your tmux panes: list/send-keys/capture, run long jobs in a pane with watch mode, and approval-gated destructive commands.

Manual approval mode ("Manual Mode" / "Ask Mode").

IM webhook and local notifications on turn completion, errors, or approval (Feishu/WeCom/DingTalk/Slack/Discord/custom).