9 results
Read-only security & compliance toolkit for DeepSeek Harness: prompt-injection detection (rule engine with a pluggable model classifier), Chinese-PII and structured-JSON redaction, and a local configuration security audit that emits redacted, reproducible, self-checksummed risk reports.
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.
Automode for DeepSeek Harness: a fourth permission preset that runs on full access with an LLM classifier as the only gate before every tool call
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
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.
Automatic model routing for DeepSeek Harness: a virtual `smart` model classifies every request by difficulty (hard / normal / easy) and by vision need, then delegates to the models you already configured in Settings → Models. 内置智能路由：三级难度 + 视觉自动路由，模型从「设置-模型」已配置模型中选取，虚拟 smart 模型零配置接入。
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.
Read-only security & compliance toolkit for DeepSeek Harness: prompt-injection detection (rule engine with a pluggable model classifier), Chinese-PII redaction, and a local configuration security audit that emits redacted, reproducible risk reports.