플러그인

DSH용 설정 기반 개발 작업 오케스트레이션: 작업/게이트웨이/휴먼 노드의 그래프 워크플로와 단계별 지속성을 제공하며, 에디터 내 AI 어시스턴트가 실시간 검증과 함께 대화를 통해 워크플로를 구성합니다. 문서는 노드에 일반 첨부 파일로 전달되며(선언 불필요), 파일은 작업 작업 공간에 배치되고 ${inputs.附件}는 줄바꿈으로 결합된 절대 경로를 제공하므로 노드는 자체 프롬프트로 이를 파싱합니다.

외형 아래에 테마 조정 패널을 추가해 액센트, 배경, 전경, 대비, 그라디언트를 사용자 지정하고 테마 토큰 오버라이드를 통해 실시간으로 적용합니다.

분리된 Git worktree에서 3개 또는 5개의 코딩 에이전트 후보를 실행하고, 프로젝트 명령으로 패치를 검증하며, 통과한 후보만 순위 매기고 승격 전에 별도 승인을 요구합니다.

DeepSeek Harness Web UI에 20개 로케일(번체자 중국어 HK/TW, 일본어, 한국어, 프랑스어, 독일어, 스페인어, 포르투갈어, 이탈리아어, 러시아어, 우크라이나어, 폴란드어, 네덜란드어, 터키어, 아랍어, 힌디어, 인도네시아어, 베트남어, 태국어, 스웨덴어) 추가. 정성껏 다듬은 번역, 런타임 폴백, 마켓 및 서드파티 텍스트의 자동 번역 제공.

X/Twitter 검색을 위한 x_search 도구를 DeepSeek Harness에 추가합니다. 별도의 SuperGrok OAuth 계정으로 인증하므로 세션 공급자 할당량을 소모하지 않습니다.

로컬 이미지, 음성, 음악 및 SFX 생성과 전사. 고정 ID 기능: 캐릭터, 동물, 객체 및 배우 음성을 한 번 정의하면 이후 모든 호출에서 재사용됩니다. 퇴화된 출력(거의 평평한 이미지, 무음 오디오)은 성공으로 반환되지 않고 거부되며, 생성된 줄은 텍스트로 다시 읽을 수 있어 끝을 삼킨 클론이 드러납니다. 엔진은 유휴 시 언로드되며, 이미지 생성과 전사는 로컬 Vulkan 백엔드 대신 OpenAI 호환 API를 가리키도록 설정할 수 있습니다.

DSH의 파일 읽기, 이미지 조회, 코드 편집을 WakaTime에서 추적하며, AI가 추가 및 삭제한 정확한 줄 수도 포함합니다. DSH가 응답하는 동안에도 활동 추적을 계속 실행하고, 파일 간 업데이트를 일괄 처리하며, 병렬 DSH 프로세스 간 프로젝트별 보고 한도를 조정합니다. wakatime-cli를 자동으로 설치 및 업데이트합니다.

GPT가 의존성 DAG를 계획하고, DeepSeek worker가 적응형 병렬성으로 작업을 실행하며, 선택적 GPT reviewer가 증분 Git diff를 감사하고 수정 라운드를 이끈다.

TaskPlane의 DSH 포트입니다. 의존성 순서에 따른 웨이브를 병렬 git-worktree 레인에서 실행하고, 작업 패킷, 모델 간 검토, 충돌 복구를 제공합니다.

Markdown 노트용 이중 지식 그래프 RAG(half-life 메모리 감쇠): 전제 조건 + 유사도 그래프(P/S-Agent 트래버설), 단락 청킹, n-gram/embedding 하이브리드 검색, 명시적 가중치 피드백 루프 — Cordis 네이티브 플러그인, npm으로 @eqman00003/knowlp-rag 설치 가능.

Connects DeepSeek Harness to QQ over OneBot 11/12, Satori, Milky or the official QQ bot API, with a separate session per group or private chat and nine built-in tools: group management, chat history with image understanding, web search, page fetching, reverse image search and image generation. Optional proactive chatter reads recent messages on an interval and decides whether to join in, with the judging and speaking stages able to use different models. Models, proxy and allowlists are configured in the DSH settings page. First run requires an owner (auth.owners): with it empty the plugin drives no sessions at all (deny by default, so installing it does not expose the bot); once set, private chats and groups work immediately, guests only reach the guest tool allowlist while qqbot and qqconfig stay owner-only.

Runtime plugin firewall for sessions started through its launcher (the DSH Desktop app cannot be injected and is not covered): filesystem, network and subprocess calls plugins make are attributed to the plugin that made them and judged against what that plugin declares, so a plugin doing its declared job stays silent and leaving it is recorded. Attribution is best-effort, not a guarantee - uncovered calls fall back to host, never to another plugin. Also adds a pre-install health card (capability surface, red-line combinations, PASS/WARN/BLOCK), boundary judging, opt-in pre-execution blocking with a credential-exfil rule, update diff with a trial install in an isolated child process, SARIF/CSV audit export, and multi-source aggregation. Local-only storage, no telemetry; the optional webhook is off by default.

Connector only, it renders nothing itself: subscribes to DeepSeek Harness session events and folds them into a 12-phase work state (planning / thinking / executing-tool / streaming / waiting-input / voice / awaiting-approval / complete / error / paused / idle / heartbeat), then POSTs each phase to a desktop-pet backend at http://127.0.0.1:8000/api/plugin/dsh/ingest. It holds no window. No API key or token is needed. Requires the Mao Live2D pet application to be separately installed and running (that is a Windows Electron app with its own PowerShell 7 / Python 3.10+ / Node 18+ prerequisites); without it this plugin has nothing to push to.

Android development toolchain inside DeepSeek Harness: 23 android_* tools that find the SDK, create and manage AVDs, start and stop emulators, scaffold a Kotlin/Compose project, build and run it with Gradle, then install, launch, screenshot, tail logcat and drive the UI. A settings page holds the SDK, emulator, API-level, build and output parameters.

A long-form Chinese novel workbench inside DeepSeek Harness: read, edit and annotate the manuscript in place; AI reports problems with ready-to-adopt revision drafts, and the text changes only when you accept. A ledger for characters, facts and foreshadowing plus a world map keep a long novel consistent, and AI can continue, expand or rewrite chapters.

Runs a Douyin subagent that browses videos and reads comments in valley hours and reports back, with dy_* tools for publishing and replying (comments sent from the already-logged-in page with its own request signature, no IM ticket), a daily quota timer, and a settings panel under Settings → Douyin: master switch, auto mode, valley windows, rounds per day and report depth. Windows-oriented; needs the separate douyin-mcp binary (yunsur/douyin-mcp releases, path set via dy_config mcpExe) and an Edge/Chromium login; replying needs a logged-in browser on a CDP port; publishing needs extra credentials most accounts lack.

Continues work across coding agents inside DeepSeek Harness: six sessionflow_* tools query a local session index built by sessionFlow to find past work, show where the current project left off, and hand the goal, files and open items to the next agent. Requires the separate sessionFlow core, installed from its GitHub repo. Everything stays local — no cloud, no telemetry.

Model-linked AI personas and desktop pet for DSH, with shared world lore, separate editable memories, task animations, usage statistics, optional AI diaries and idle-time diary consolidation. The native pet window is Windows x64 only; sleep consolidation spends tokens in the background. Before installing or updating, close the visible desktop pet and notification bubble by choosing Close All (全部关闭) in the context menu; otherwise, files in use may cause installation to fail.

Requires the ZCode CLI installed and signed in. Relays the ZCode CLI agent into DeepSeek Harness as a model provider. A resident app-server session streams each turn, and the model catalogue is read from the CLI at runtime, so context windows, image support and provider routes follow the installed CLI and account. Stable 0.5.1 declares DSH compatibility through engines.dsh; ZCode CLI 3.16.3 is the documented reference version. Tool permission requests are denied by default; unknown approval or permission methods are always denied, and full-auto requires an explicit opt-in. DSH approval UI does not mediate this separately spawned app-server process, and the policy is not an OS sandbox.

Model settings panel for DeepSeek Harness: set the default model for new sessions, plus separate provider/model/reasoning-effort overrides for subagents and goal rounds, with live reload.

Separate font slots for content, code and terminal text, plus an interface font, an interface-size stepper and an inline-code size stepper, with line-height and letter-spacing controls. Typography only — it never touches colour.

Shows JeV-selected task plans, progress updates and stage summaries in DSH chat, with native translation or lightweight summaries. Requires a JeV key; the Jev service is called externally and may bill. and hierarchical serial/parallel task flows.

Predicts your next message after each turn and shows it as gray ghost text in the composer: Tab takes the whole line, Alt+Right takes one word at a time, Enter takes it and sends, Esc dismisses, and Alt+R asks the model again without repeating the old one. Typing a few characters completes from prompts already sent in the session, Up in an empty composer recalls the last one, and a plugin-page form sets the provider, model, reasoning effort, per-key toggles and generation limits.

A no-limit Texas holdem table where you are the only human. Eight seats: you plus seven LLM agents written on AI-founder personas (Altman, Dario Amodei, Musk, Liang Wenfeng, Jensen Huang, Lei Jun, Zhang Yiming). Each agent bets through the currently selected host model and falls back to its own heuristic style when no model is available; every agent only ever sees its own hole cards, because the prompt is built from that seat alone. A hand ends by revealing the winner hole cards, with a flip animation replayed on every community card, and a rail keeps a live action-and-table-talk timeline. LAN mode (off by default, single-machine play is unaffected) lets another install on the same network join this very table: the host shows a six-digit room code, UDP broadcast discovers nearby tables, and a joiner randomly takes over one bot seat, with the seat handed back to its character on leave or after twenty seconds of silence. The room code is never put on the wire and every snapshot is generated for one viewer seat, so nobody, not even the host, can read another player hole cards. Fork of BubblePtr/dsh-holdem (MIT), credited in the README and in the UI.