dsh-auto-approver
Auto-approval agent for DSH permission requests: rule layer (denyAlways/allowlist) plus Hermes Pro semantic adjudication with quick-fail retries, fail-closed to human when Hermes is unavailable, rejection feedback returned to the requesting session, and approve tasks enqueued into the task queue with a shared busy mutex.
DSH 权限请求自动审批代理：规则层（黑名单/白名单）+ Hermes Pro 语义裁决（快速失败重试），Hermes 不可用时 fail-closed 转人工；拒绝原因回传发起会话；审批任务入队并与消费端共用忙锁串行化。
How to install
dsh plugin add github:nicecx/dsh-auto-approver About
dsh-auto-approver **Configurable auto-approval for DeepSeek Harness.** Intercepts approval/request (and optionally ask_user_question) and answers by policy — rule layer, an optional **Hermes Pro semantic verdict**, or the human. Every decision is audit-logged. Why DeepSeek Harness asks for approval before privileged operations (file writes, command execution, danger-full-access, …). In a trusted, autonomous setup — or for a known-safe subset of tools — those prompts are pure noise. This host plugin intercepts every approval request **before** the relay/UI push and settles it, with a full audit…
Recommendation signals
Meta
- License
- MIT
- Language
- JavaScript
- GitHub stars
- 0
- mo. downloads
- –
- Last push
- 2026-08-31
- Created
- 2026-08-31
Links
Basic safety check
- Findings
- curated 收录但无 npm 包/安装命令
- Sources
- curated:awesome-dsh-plugin.com, curated:awesome-dsh-plugin/awesome-dsh-plugin
- Topics
- approval, deepseek-harness, dsh-plugin
Related plugins
langfuse
langfuse/langfuse
🪢 Open source agent evals & observability: Trace, evaluate, and improve LLM applications with one open platform.
claude-code-templates
davila7/claude-code-templates
CLI tool for configuring and monitoring Claude Code
semiotic
nteract/semiotic
React data visualization library for streaming, networks, and AI-assisted development
dsh-desktop
dataelement/dsh-desktop
DSHDesktop：DeepSeek Harness Desktop / DeepSeek Harness 桌面版