Dsh Approval Llm
Letter2025/dsh-approval-llm · skills
Model-based permission approval (approve-for-me) for DeepSeek Harness: an approval/request answerer backed by a separate reviewer model.
★ 8GitHub stars
0Forks
2026-09-08Last updated
TypeScriptLanguage
MITLicense
Key features
- Model-based permission approval (approve-for-me) for DeepSeek Harness.
- ALLOW / DENY / ESCALATE map 11 onto the dsh outcome vocabulary (allowed-once / rejected / delegate).
- Prompt isolationthe reviewer prompt is assembled by this plugin from its own config
- ESCALATE and model failures never fabricate a rejection — they hand the request to the next answerer (the human UI), and a deployment with no human answerer fails closed (unavailable), exactly like Codex's fail-closed guardian.
- The mode gate makes the modes exclusive.
Requirements
- No dedicated log-only audit event.
- Model decisions are visible in the main chain as user/message notices (durable and replayable), and the built-in approval/asked + approval/decided pair records the ask/outcome.
Install command
dsh plugin --profile web add github:Letter2025/dsh-approval-llm