couldbeme/dsh-write-gate

couldbeme★ 1TypeScript最后同步: 2026-08-20

在 GitHub 打开

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.

README 摘要

dsh-write-gate A commitment write-gate for DeepSeek Harness: the operator authors constraints ("never force-push to a shared branch", "stay read-only on the production database"), and the gate enforces them before a tool call executes. Structural violations are caught deterministically; semantic drift is judged by a model against the operator's own wording. Every block is recorded to a contradictions log that explains which commitment fired and why. Engine-agnostic core ( dsh-write-gate/core , zero harness imports) with a dsh adapter; a Claude Code adapter over the same core is planned. A live model inside the real dsh app, told to force-push, after the gate denied the call: "The force push to the main branch was blocked by the repository's 'no-force-push' policy." That turn ran fully local, zero API keys; reproduction and session-log receipts in docs/E2E-HEADLESS.md . How it enforces: two tiers in two slots Tier Mechanism dsh slot Why this slot 1: deterministic path globs, command regexes, scope filters ctx.tools.guard() (monotonic) no listener ordering can turn a guard denial back into permission 2: semantic LLM judge over the commitment statement tools/pre-execute waterfall (pre…

在 GitHub 查看完整 README →
Agent/智能体agent-safetyai-agentsdeepseek-harnessdsh-pluginguardrailsagent

分类