@nanmicoder/dsh-auto-mode
Sandbox-first automatic permission policy for DeepSeek Harness
8 results
Sandbox-first automatic permission policy for DeepSeek Harness
CC-style auto mode for DeepSeek Harness: deterministic deny/allow rules + pre-execute gate + model-agnostic two-stage classifier. Two-state (allow/reject) classifier since 0.8.0. TypeScript rewrite merging dsh-auto-mode v0.4.1 with Nuo-cl/dsh-auto-mode native integration.
Hybrid model router for DeepSeek Harness: declarative rules, user-configurable cost control (cost-first / quality-first / balanced), optional LLM task classifier, and failure fallback chains.
Auto model selection for DeepSeek Harness: routes each turn to V4 Flash or V4 Pro through a classifier call
DSH plugin: auto mode that routes permission-gated tool calls through an LLM review before approving, blocking, or asking for confirmation.
Autonomous (auto) mode permission classifier for DeepSeek Harness: a Claude-Code-auto-mode-like classifier over tools/pre-execute and approval/request, a selectable 'auto' permission preset, LLM semantic judge, git checkpointing, agent discipline guidance, and a web control page in Settings → Plugins.
DSH 插件:按任务复杂度在 deepseek-v4-flash 与 deepseek-v4-pro 之间自动路由(只升不降)
自动模式 Auto Mode: an AI pre-judgment layer for DeepSeek Harness — a flash-model router that picks the best agent preset (standard/code/minimal/cordis) for each new session and lets the user confirm before execution.