플러그인

DSH용 모델 스위치: 모든 OpenAI 호환 엔드포인트를 지정 가능하며, 엄선된 무료/저가 DeepSeek 프로바이더 프리셋과 무료 티어가 속도 제한에 걸릴 때 자동 폴백 제공

프롬프트, 도구 인자, 결과 텍스트, 원본 세션 ID를 저장하지 않고 도구 결과와 세션 이벤트에 대한 해시 체인 JSONL 영수증을 로컬에 추가로 기록합니다.

SVG 패스와 키프레임 명세를 자체 완결형 Lottie JSON 애니메이션 파일로 컴파일

텍스트/JSON/CSV/Markdown에 대한 구조화된 비교와 통합 diff를 제공합니다.

실시간 미리보기와 함께 사용자 및 내장 시스템 프롬프트 섹션을 편집

컴포저용 마이크 음성 입력: 브라우저 Web Speech API 실시간 전사, 중복 제거/자동 이어쓰기, 스마트 문장 부호, 언어 및 자동 전송 설정

Web 컴포저에서 임의의 로컬 파일 업로드, 대기 중 카드 표시, 설정에서 저장된 파일 관리

Turn another computer into a remote Agent teammate: the worker runs its own DSH and a full Agent loop locally, so dispatched tasks keep running when the link drops and its model credentials never leave that machine. The hub dispatches through 8 remote_* tools, receives only a handoff summary plus an artifact manifest, and pulls finished products on demand — intermediate artifacts stay on the worker. Pairing-code onboarding, direct or relay transport for NAT, Web panel on both sides.

Reusable Agent Team presets for DeepSeek Harness: a Settings page stores named Teams — a captain with its own prompt and tool allow-list, plus members carrying their own provider/model route, reasoning effort, prompt and tools — and a composer control applies one Team to the current Session, installing the captain prompt and registering the spawn_team_member, get_team_preset and update_team_preset tools.

Hold-to-talk dictation in the composer that ships no recognizer of its own and reuses the speech service the official voice-input bundle already mounts - long-press the input box with mouse or touch, release to write the transcript into the draft, slide up to cancel, and it never sends.

Mounts external skill directories (Claude Code, Codex, ZCode) into DSH as read-only skill providers: frontmatter field mapping, name slug normalization and hot reload.

Automated data masking tool based on national standards, automatically identifying sensitive fields like ID cards and phone numbers.

Data lineage tracking tool, mapping the full lifecycle of data to meet source legality requirements.

Quantitative data quality scoring based on GB/T 36344-2018, providing auditable quality reports for data asset capitalization.

A daily journal the agent keeps: the journal_record tool appends dated todos and memories, with optional detail and tags, to one JSON file per day under the DSH home; the right sidebar draws those files as a month calendar marked per day by open todos, finished todos or memories, with checkable todos and the selected day's entries below; and the duty sentence it adds to the system prompt is editable from the calendar itself.

Preview conversation context and selectively keep, summarize, or omit exchange groups before applying persistent compaction through Harness session services.

A plugin to completely delete sessions and clean up the associated files in the .dsh/sessions directory.

Reads each third-party endpoint's own model listing and keeps llm-pi-ai's per-model reasoningEfforts in sync, so the composer offers the thinking levels a model actually has.

Brings the WorkBuddy, Trae and Qoder desktop logins on this machine into DeepSeek Harness as OpenAI-compatible local endpoints, with an account pool, automatic account switching when WorkBuddy is rate limited, and a settings panel.

Global and per-session prompt templates in a right-side panel — insert into the draft or send now, edit, promote session templates to global, with SQLite persistence via the built-in node:sqlite.

Code workbench in the right sidebar: a workspace file tree and a multi-tab Monaco editor with syntax highlighting and version-guarded saving, Tab completion from DeepSeek fill-in-the-middle, per-save checkpoints with rollback, codebase search (plus a codebase_search tool for the agent), and reference chips that insert a selection into the chat as an @path mention.

Input prediction for the DSH composer: your next prompt suggested as ghost text after each turn, accepted with Tab. (autocomplete / input prediction / prompt suggestion)