dsh-human-intent

Human intent verification and cryptographic action authorization for AI agents. AI can propose an action. Only a human can authorize it. 适合需要对智能体高风险操作进行严格人类授权和审计的场景。

Agent collaboration

Package: dsh-human-intent
Compatibility: Unverified
Harness peer range: >=0.1.1-rc.0
Version: 0.1.0
License: MIT
Last updated: Sep 16, 2026

Install

$npx -p @deepseek-ai/dsh dsh plugin --profile web add github:guhanfei-ai/dsh-human-intent

README

Read the full README ↗

Configuration

Option	Default	Meaning
`enabled`	`true`	Enforce human intent for protected tools.
`protectedTools`	`[]`	Tool names / dot-globs requiring authorization.
`rules`	`[]`	`{ tool, risk }` rules combining protection and risk level.
`rpID`	`localhost`	WebAuthn relying-party ID.
`allowedOrigins`	`http://localhost:
`	WebAuthn origin allowlist.
`requestTtlMs`	`120000`	Human decision window.
`dataDir`	(memory)	Directory for `credentials.json` + `audit.jsonl`.