플러그인

Safe, audited SQLite/PostgreSQL/MySQL access for dsh agents: schema introspection, enforced read-only queries, a write approval gate, and a durable JSONL SQL audit trail.

SMS forwarding webhook for DeepSeek Harness. Phone apps (SMS Forwarder, Tasker, or any HTTP POST) push messages to a local HTTP endpoint; the plugin stores them as JSONL and exposes sms_recent / sms_search tools so the agent can read SMS verification codes during tasks. Auto-extracts the first 4-8 digit OTP from each message, supports keyword filtering, and works over LAN or Tailscale.

삭제되거나 손상된 dsh 세션(session.jsonl.zstd)과 메모리(memory.db)를 원시 디스크에서 복구하고, 재개에 실패하는 재구성된 세션을 웹 UI의 /session-repair 명령으로 수리합니다.

도구 파이프라인 실행 시 보안 게이트: egress 허용 목록 밖 호스트를 지정한 호출을 거부하고, 결과에서 자격 증명을 렌더링된 내용이 아니라 정규 값 단계에서 마스킹하며, 모든 판단을 JSONL 감사 로그에 추가합니다. 기본은 모니터 전용 모드.

세션 라이프사이클 CLI: 내보내기(md/json/jsonl), 아카이브/복원, 휴지통, 검색, 통계. 기본적으로 읽기 전용이며 엔진이 무언가를 삭제하는 일은 없습니다.

테스트용 어시스턴트 메시지를 생성/수정/주입하고, session.jsonl(.zstd) 세션 로그를 새 세션으로 가져오기/복구합니다.

DeepSeek Harness용 런타임 로그 패널: 설정에 실시간 SSE 로그 뷰 제공, 날짜/크기 기준으로 순환되는 JSONL 파일도 함께 관리

Agent 行为守护桌宠：跨 agent 监控可疑外传（加密打包直传对象存储 / DNS 外泄线索 / 敏感密钥被读），发现即告警，明确确认后按「一次一个」终止目标 agent；事件写入只追加 guard-events.jsonl，并通过 DSH host 工具 + MCP(stdio) 供其它 agent 查询

dsh 插件：本地蒸馏器——扫描全部历史会话，挖出「用户纠错 → agent 改对」片段，脱敏后蒸馏成微调数据对（JSONL）、技能草稿与 AGENTS.md 规则补丁，带人工审核队列

Turns DSH permissions into 9 selectable presets (3 sandbox modes x 4 approval tiers), with rule plus LLM risk classification across four risk levels, password-gated approval for high-risk operations, and a JSONL audit log.

Drop-in web_search provider that follows the session's routed model: a runtime-editable priority chain with three wire dialects (Anthropic web search, OpenRouter online, Zhipu bigmodel), per-route endpoints and credentials, a Settings UI panel, local JSONL call audit, and built-in official fallback.

Mine local DSH session logs (JSONL) into personal usage & impact receipts: Markdown day/week/month reports plus a self-contained HTML receipt, cross-referenced with local git log — zero-network, privacy-first.

Local tool-call failsafe for DSH: blocks a fixed list of high-risk shell patterns and credential-file reads before execution, with a per-session hash-linked JSONL audit log, and an optional external Gateway for centralized policy.

Local JSONL run traces for DeepSeek Harness sessions

Agent governance suite: policy-based tool gating (allow/deny/ask with wildcards and priorities), a structured JSONL audit trail, and per-agent token quotas against the host token meter, with state under $DSH_HOME/gov.

Persistent model tool-call trace recorder: every tool call is durably written to a JSONL file that survives restarts, queryable via a structured call_trace tool and a callTraceHistory service, with size rotation and an optional floating canvas UI add-on.