Плагины

Режим Auto для DeepSeek Harness (dsh): пункт Auto в селекторе Permissions, в котором на запросы подтверждения отвечает политика OpenGuardrails вместо человека — плюс полноценный движок защиты OGR под капотом. Без изменений ядра.

База долговременной памяти для ИИОН (AGI): многоагентный пространственно-временной граф памяти, самоэволюционирующий маховик знаний, самопознание и проверяемые ограждающие механизмы доверия.

Agent security guardrail: intercepts and audits every tool call, requiring human confirmation on sensitive operations.

Внедряйте правила по необходимости, не тратя впустую контекст. Порт opencode-stream-rules для DSH.

DeepSeek Harness (dsh) approval answerer backed by the agent-governance sidecar — every approval/request is decided by the deny-by-default gate, L0–L4 rules and the organizational audit chain.

Commitment write-gate: operator-authored rules enforced before a tool call runs — a deterministic guard tier plus an LLM-judge tier, fail-closed by default, every block written to a contradictions log.

Self-protection guardrails for the DeepSeek Harness: protected-path interception, backup-before-destroy, CLI self-recovery commands, and strict sandbox defaulting

Configurable per-turn budgets for supported file mutations, limiting distinct files, mutation calls, and UTF-8 payload bytes before tool execution.

Deterministic Runtime Execution Governance & Security Circuit-Breaker for DSH Agents

Honesty guardrails on the tool pipeline: blocks a coding agent from weakening tests, swallowing errors, stubbing type checks, or deleting tests through the shell — nine deterministic hooks, each backed by a planted-failure test proving the guard can fail.

Taints the agent when tool results carry untrusted content, gates the privileged calls that follow, and refuses credentials passed to network-capable tools in every mode.

Pre-execution guardrail: vetoes dangerous shell commands and blocks secret/credential leaks before they run.