couldbeme/dsh-write-gate

插件 ⭐ 0 MIT coding

面向AI编码代理的提交写入门控:两级预执行策略(确定性守卫+LLM评审),并附带可测量的收据。DeepSeek Harness插件,引擎无关的核心。

catalog 简介:Commitment write-gate for AI coding agents: two-tier pre-execution policy (deterministic guard + LLM judge) with measured receipts. DeepSeek Harness plugin, engine-agnostic core.

安装

Semantics: `kinds`/`tools` are scope filters; `paths`/`commands` are structural evidence. A non-semantic commitment with scope but no evidence fires on every in-scope action; a non-semantic commitment with neither is rejected at load as unenforceable. Command regexes are case-insensitive by default. One foot-gun to know: command patterns execute inside the synchronous guard, so a catastrophically backtracking regex can stall the tool pipeline — commitments are operator-authored (trusted), but keep patterns simple. Full example: [`commitments.example.yaml`](commitments.example.yaml) (itself under test).

## Mounting

The package declares the ecosystem convention (`dsh.bundle.patch` → [`cordis.patch.yml`](cordis.patch.yml)) and mounts with:

couldbeme/dsh-write-gate 加入你的 DSH 配置(web profile)即可启用。

README

展开完整 README 收起

README 内容为空。