DeepSeek Agent
插件市场Agent 与自动化dsh-auto-review
DEEPSEEK HARNESS PLUGIN

dsh-auto-review

Second-model AI auto-review for DeepSeek Harness approval requests: a read-only reviewer subagent returns structured allow/deny verdicts with reasons, fail-closed by default, fully auditable from the session log (approval/asked -> autoReview/verdict -> approval/decided).

插件介绍

Second-model AI auto-review for DeepSeek Harness approval requests: a read-only reviewer subagent returns structured allow/deny verdicts with reasons, fail-closed by default, fully auditable from the session log (approval/asked -> autoReview/verdict -> approval/decided).

ai-safetyapprovalauto-reviewcordisdeepseekdeepseek-harnessdshdsh-pluginllmsandboxsecond-modelsubagent

项目详情摘要

🤖 dsh-auto-review Second-model AI approval for DeepSeek Harness — a read-only reviewer subagent decides allow/deny on the approval chain, fail-closed by default.** When an action crosses the sandbox boundary, a second model reads the evidence and returns a verdict with a reason — so humans approve nothing while nothing unsafe slips through.* **Official repository.** This is the only official repository of dsh-auto-review, maintained by PerryLink. Same-name repositories under other accounts are not affiliated. English · 简体中文 · Español · Português · हिन्दी Compatibility Surface | Status | Harness | DeepSeek Harness `dsh-v0.1.5-rc.2` (GitHub tag, verified 2026-09-11). Dual-line npm support: dev pins and runtime deps `0.1.5-rc.2`, peers `>=0.1.2-rc.1 =0.1.5-alpha.1 =24.0.0` | Platforms | All (host answerer; optional Web review panel via the session-projection capability) | Model | Any (the reviewer inherits the session agent's route; `reviewerModel` overrides) | What you get `dsh-auto-review` puts a second model on the `approval/request` answerer chain: 1. **Official seam** — an answerer that claims only the requests it owns (`ai` policy) and delegates everything else via `next()`; the human approval flow is never short-circuited. 2. **Read-only reviewer subagent** — a one-shot fork with a `read`/`glob`/`grep` tool allow-list returns a structured verdict `{ decision, reason, riskLevel }`. Reviewer asks are recognized by identity and delegated; `maxDepth` + the allow-list keep the reviewer non-delegating. 3. **Fail closed** — reviewer crash, timeout, or schema mismatch resolves through `fallbackPolicy` (default `rejected`); a deny verdict feeds its reason back to the calling model. 4. **Config-driven routing** — per-tool policies (`ai`/`human`/`never`) plus regex risk rules,

摘自项目公开 README,可能随上游仓库更新。

安装方法

建议先在测试 Profile 中安装,并检查权限、安装脚本和依赖。

npx -p @deepseek-ai/dsh dsh plugin --profile web add github:PerryLink/dsh-auto-review

使用前检查

  • 确认项目符合 DSH bundle 规范,而不只是相关仓库。
  • 阅读许可证和安装脚本,检查网络、文件及执行权限。
  • 备份配置,并确保插件能够安全卸载或回滚。