플러그인

한 컴퓨터의 세션 간에 데스크별 티켓을 주고받습니다. 세션 제목 앞에 번호를 붙여 소속 데스크를 표시하고 티켓은 데스크 하나를 지정합니다. 해당 데스크에서 작업을 시작한 첫 세션이 티켓을 가져가므로 주소는 세션이 아닌 데스크이며, 잠시 들른 세션에는 전달되지 않습니다.

Prompt optimizer for the composer: a button in the tool row rewrites your draft through a model channel you already configured, streaming into a panel that floats above the composer without taking up layout. Your draft changes only when you click Accept — and Accept is refused while the answer is still streaming, so a half-finished reply can never be written back. It asks first when the draft carries @ references or attachments, which a whole-draft replace would flatten into plain text. No global keyboard shortcuts, and no API key ever reaches the browser: the host half makes the call.

A project-scoped memory plugin for DSH. Knowledge authoring and the plugin's own prompts are open to editing, so users can redesign the library structure and how the model is driven without changing a line of code. By default the library is built on one core idea: a project document you design yourself (a handoff by default) is the project entity; the plugin detects which project a session belongs to, binds captured knowledge to that project, and promotes what generalizes into theme and global layers. The most natural logic there is does the pre-filtering of knowledge, with controllable compression and archiving of context.

Model attribution panel for the dsh web chat — local, zero-network structural fingerprinting (template token leaks, glitch canaries, tokenizer usage-vector matching) that scores which of 29 AI vendors a session's responses most resemble, with a per-claim evidence ledger and a 12-probe active battery.

DSH Web 화학 작업대입니다. Ketcher 캔버스에 구조를 그리고 빌드 다운로드 스크립트를 통해 브라우저에서 로컬 렌더링합니다(백엔드 불필요). 현재 분자를 모델 호출 없이 RDKit으로 계산: 분자식·분자량·정확 질량·logP·TPSA·수소결합 공여체/수용체·고리 수·Fsp3·입체중심·Lipinski/Veber 항목별 검사·QED·PAINS/BRENK 경고·Murcko 골격, SMARTS 검색, 유사도, 형식 변환, 표준화, 일괄 정리. 역합성 탭은 기본 Retro* 등 교체 가능한 백엔드와 JSON 입출력 프로세스로 통신하며 미설치 시 경로를 지어내지 않고 누락을 알립니다. 계산은 별도 pip 설치가 필요한 저장소의 Python 패키지(rdkit)가 수행합니다.

DeepSeek Harness용 온디맨드 skill 도구입니다. skill_search / skill_load / skill_ref로 단계형 라이브러리를 검색하고 필요할 때만 본문을 불러와 라이브러리 전체를 세션 카탈로그나 매 턴 컨텍스트에 상주시키지 않습니다. 대화의 Skills 탭은 전체 세션을 다시 읽어 실제 로드된 skill과 턴을 나열합니다. 의존성은 없으며 기록은 클라이언트에서만 렌더링되어 모델 컨텍스트에 들어가지 않습니다.

Security-audit facts AI coding agents cannot compute, plus a verdict gate: euthyna history attributes deleted lines to commits and flags those from security fixes (--origins finds the first introducer), euthyna coverage reports which changed symbols no test ever invoked, and euthyna gate checks each finding against six gates, downgrading any without evidence to an observation.

승인 카드에 Explain 버튼을 추가합니다. 모델을 한 번 호출해 대기 중 작업을 정확히 세 줄로 설명합니다: 작업 내용, 읽기·쓰기·변경·실행할 파일 또는 시스템 상태, 위험·주의·안전 판정과 한 문장 근거. command 필드만 읽어 빈칸이던 write/edit 호출 세부 사항도 렌더링합니다.

셸 호출의 파일 시스템 권한을 명령 이름이 아니라 경로와 능력별로 허용합니다. 명령줄에서 필요한 읽기·쓰기·생성·삭제·실행 효과를 분석하고, 능력이 부족하면 일괄 거부 대신 승인 카드를 띄웁니다. 동일 규칙을 macOS Seatbelt 프로필로 컴파일해 프로세스·자식·인자에 드러나지 않은 코드에도 적용합니다. 대화의 Approvals 탭에서 감사 로그와 각 호출에 응답한 규칙·자동 검토자·사람을 확인합니다.

DeepSeek Harness 플러그인 작성자용 업그레이드 스킬입니다. 호출자의 peer 버전대를 판별해 해당 closed corridor 카드로 안내하는 인덱스를 제공합니다(0.1.3-alpha.1→0.1.5-rc.1은 구간 A+B, 0.1.5-rc.2→0.1.6-alpha.2는 구간 C). 의존성 없는 경계 스캐너도 스킬 번들과 npx CLI로 제공합니다.

DeepSeek Harness의 워크스페이스별 MCP 범위 지정 — 세션이 열린 디렉터리를 기준으로 어떤 MCP 서버를 볼 수 있는지 결정합니다.

DeepSeek Harness 세션 활동을 자체 호스팅 cc-monitor 서버로 보고하면, 서버가 Claude Code와 DSH 세션을 하나의 웹 대시보드에 색상 코드 상태 카드로 표시하고 세션에 주의가 필요할 때 브라우저와 Android 앱에 알림을 보냅니다.

컴포저용 중국 대응 음성 입력입니다. 로컬 Python 브리지가 필요합니다 (pip install dashscope websockets, bridge/voice-bridge.py 실행) — 플러그인만으로는 작동하지 않습니다. 브라우저 마이크가 16kHz PCM을 브리지로 스트리밍하고, Alibaba Cloud DashScope ASR(paraformer-realtime-v2)를 실행합니다. 중간 결과가 커서 위치의 초안을 채우며, 무음 시 자동 정지, 선택적 자동 전송을 지원합니다.

전송 상자 옆의 녹색 interrupt button: 실행 중인 에이전트를 조용히 중지하고 진행 상황을 요약한 후 새 요구 사항을 묻습니다. interrupt prompt는 사용자 정의 가능.

DeepSeek Harness(DSH) 플러그인: 설정 → 일반 아래의 "사고 언어" 선택기로, 시스템 프롬프트 섹션을 통해 모델이 어떤 언어로 추론(사고 사슬)할지 지정. 추가 호출 없음, 지연 없음, 12개 언어 지원

Recursive delegation for dsh agent trees: a preset plus Host limits bound what each subagent may do, subagents work in separate _agents/ workspaces, and the parent decides which results to integrate.

Keeps a DeepSeek Harness run going on its own: continues a turn that ended abnormally, and continues a turn logged as completed while the model tool call was emitted as plain text instead, which leaves the agent silently idle. Revives a model request that stops streaming. A wait on an approval or on a question is logged and notified, never answered.

Union web search for DSH (consolidated successor of DDDMUC/dsh-free-search, which it credits): 28 engines across three tiers — keyless free (Bing/DuckDuckGo/AnySearch/SearXNG multi-instance union, plus Exa/Tavily/Keenable/Firecrawl/Parallel keyless modes), paid-with-key (Zhihu/Perplexity/Serply/DeepSeek official/You.com/Baidu/Kimi/Aliyun/Doubao/Zhipu/Bocha/Metaso), and model built-in search (OpenAI/Gemini/Claude/Grok, explicit opt-in only) — with auto smart routing, per-engine enable/disable & fallback priority, parallel top-3 merge, multi_search, failure-aware fallback, a toggle to block the system built-in search, time filtering, platform search, web_fetch and a web settings UI. Experimental free advance_fetch: whole-page GFM-Markdown or CSS-selector/fields structured extraction with no API key and no per-call billing; fetch identity configurable (custom User-Agent, Referer, per-domain cookies attached only on domain match, never leaked across cross-domain redirects). Hosts 0.1.0-rc.2 through 0.2.1-rc.2 (17-tag exact engines.dsh enum; the rc.2 search-provider takeover goes through volatile config pinning after capability probing, never version branches). Paid engines need your own API keys (optional; free engines work keyless). npm: @drscrewdriver/dsh-union-search and bare dsh-union-search.

One settings page for every MCP server on your machine. It reads the real config file of 17 other AI tools (Claude Desktop, Claude Code, Cursor, VS Code, Windsurf, OpenCode, Trae, Trae CN, Qoder, Gemini CLI, Qwen, Zed, Roo Code, Copilot CLI, Kiro, CodeBuddy, Continue) plus DeepSeek Harness itself, groups servers by the file that declares them, probes each one over JSON-RPC to see whether it starts and which tools it exposes, and gives every server a switch that mounts or unmounts it in DeepSeek Harness without editing the other tools' own files.

Read-only assessment of whether a Dameng DM8 database can be recovered and to which point (LSN or time), across 16 recovery scenarios, with an HTML report. Needs Java 8+ and a Dameng JDBC driver jar (DmJdbcDriver8.jar) that you provide yourself.

Adds job-role prompts to the DSH composer: type - at the start of the input to pick a role, which becomes a reference chip in the draft and is then injected as a system prompt section on every turn of that conversation, so the instruction keeps applying without showing up in the transcript. Roles are added and edited on a Settings page and stored in ~/.dsh/dsh-role-prompts.md.

Predicts your next message after each completed turn and shows it as ghost text in the composer: press → to accept, or keep typing and finish it word by word with Ctrl+→, Esc to dismiss. The prediction model follows the session by default or can be picked in the settings card, which also has an on/off switch and a speed test.

Keeps quotes out of the message body: quoting any passage from an assistant turn opens an editable quote tray above the composer, the quotes are injected into the next turn as system-prompt context (attributed with source and time), and an expandable quote row under that turn shows exactly which quotes were used. Quotes persist across page reloads and are claimed per turn; the host and client halves hand-shake on version and report a compatibility verdict.

Publishes whichever model the profile has selected in chat or on the Models page as an OpenAI-compatible HTTP endpoint: /v1/models, /v1/chat/completions (streaming SSE and non-streaming), /health. A request may name any routable model; one that omits `model` gets the current chat selection, so switching model in chat switches the endpoint. Switched on, it can also lend the model the Harness tools switched on individually, run those calls through the Harness tool runtime and feed results back up to a round limit. The listener is the plugin's own, so 127.0.0.1, 0.0.0.0 and a NAT-forwarded port all behave the same with no change to the request path. Settings cover bind address, port, API key with a generator, fallback provider and model, reasoning effort, CORS origin and timeout.