Second-model AI auto-review for DeepSeek Harness approval requests: a read-only reviewer subagent returns structured allow/deny verdicts with reasons, fail-closed by default, fully auditable from the session log (approval/asked -> autoReview/verdict -> approval/decided).
Claude Code-style declarative permission rules for DeepSeek Harness: ordered allow/deny/ask rules with tool-name, argument (glob/regex), and workspace-path matching on the tools/pre-execute waterfall, session-log audit, and HMR reload.
Prompt-injection, jailbreak, and secret-leak defense for DeepSeek Harness: Aho-Corasick detection with allow/ask/block interception and sanitized audit events
PII masking middleware for DeepSeek Harness: anonymize names, phones, emails, ID cards, bank cards, keys, and addresses to placeholders before they reach the model, restore them at the display layer, keep the restore table only in memory and a controlled storage domain, never log plaintext, and expose /mask and the mask_test tool
模式匹配自动注入 steering rules，不占系统上下文 - Inject rules when needed, without wasting context. Similar to oh-my-pi's "Time-traveling stream rules", but with a very simple and compact code implementation.
多文件夹 workspace：让 DSH（DeepSeek Harness）的 Agent 不只能读写主目录，还能同时读写你添加的其他文件夹。Multi-folder workspace for DeepSeek Harness: let the agent read and write several folders at once, not just the primary one.
Enforce strict checks as dsh harness policy: repeated-failure intervention, a glob-protected critical-path gate that blocks with diagnostics, and an automatic post-write check.
