플러그인

중단된 DSH Web 요청을 자동으로 재개합니다: 네트워크 오류, 타임아웃, 호스트 크래시 후 대기 중이던 「继续」(계속)를 전송하며, 오류 분류, 적응형 백오프, 템플릿화된 계속 문구, 브라우저 알림을 지원합니다.

DSH 대화 글을 세션 내 Excalidraw 다이어그램으로 변환합니다. diagram_create 초안, 편집/자동 저장, PNG/SVG/.excalidraw 내보내기, diagram_read 재읽기를 지원합니다. 0.6은 대형 3단계 트리용 편집 개요와 색인을 추가합니다.

DeepSeek Harness용 동시성 가드 및 모니터: 동시 모델 요청이 한도에 도달했을 때의 FIFO 큐, 오류 종류 분류가 포함된 일일 영구 통계, 그리고 버려진 스트림에 대한 중단 감지.

강화된 비전 툴박스: 단일 OpenAI 호환 엔드포인트로 구동되는 14개의 픽셀 레벨 비전 툴(describe, ground, detect, crop, pixel-diff, OCR, long-screenshot OCR, vectorize, colors, cutout, screenshot, present, materialize, html-screenshot), 깔끔한 [图片: path] 브리지 마커, 콘텐츠 안전 분류 및 속도 제한 자동 재시도.

MACD, RSI, 이동평균, 거래량 등 기술적 신호를 융합해 상승 사후 확률을 산출하는 베이지안 주가 예측 플러그인. 다중 기간 비교, 추세 상태 분류, A주와 미국 주식 포지션 리스크 지표 제공.

DeepSeek Harness용 프로젝트별 메모리입니다. 각 workspace의 세션 첫 단계에서 PROJECT.md, DECISIONS.md, SESSIONS.md를 자동 생성하고 디스크에서 다시 읽으며 변경되거나 압축으로 빠졌을 때만 재주입합니다. memory_checkpoint로 분류 저장하고 작업했지만 기록이 없으면 턴 끝에 제한적으로 알립니다. memory_read는 실시간 로그와 아카이브를 읽고, memory_search는 의존성 없는 BM25로 검색합니다. 로그는 200개 제한이며 초과분은 SESSIONS-archive.md로 옮겨 컨텍스트에 넣지 않지만 열람·검색·항목별 복원이 가능합니다. 설정은 workspace/경로 필터, 세 파일 및 아카이브 읽기 전용 보기·새로고침, workspace별 JSON 내보내기/가져오기, 2단계 삭제, AGENTS.md 지침 블록 수정·제거, PROJECT.md 오래됨 알림을 지원합니다. 상태 칩은 동기화를 보여 주고 클릭 시 파일을 만듭니다. 의존성·벡터 저장소·임베딩·모델 호출 없음.

Verifiable issue-to-PR delivery chain: an 11-stage pipeline (analysis, search, code understanding, hypothesis, planning, implementation, patch ledger, tests, review, failure classification, PR build) with 4 human review gates, GitHub/GitLab/CodeArts credential connections, a 5-page workbench and a draggable AI assistant panel.

DSH 설정 내비게이션을 정리합니다. 접을 수 있는 그룹 행 아래에 서드파티 플러그인 항목을 묶고, 북마크 스타일 사용자 지정 그룹, 접기 토글, 자동 분류(마켓 태그 → 이름 규칙 → 사용자의 AI 모델)를 제공합니다.

적응형 모델 라우팅: 요청별 복잡도 분류와 자동 프로바이더 라우팅

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.

DSH agent tools for local Ollama System One decision models: classify, answer yes/no, and score against a rubric in one batched request.

Hands secrets and PII to the agent without them entering its context, with checksum-validated extraction and masked content classification.

Sorts every loaded skill into one or more user-owned workspaces in a right-sidebar tab: each workspace is its own category list plus where every skill sits, categories are created, renamed, reordered and deleted in place, and skills are dragged or picked between them. A first run can let the profile model build the first classification, or place skills into categories the user built first; clicking a row copies its /skill-name and hovering unfolds the description the skill ships.

Lightweight crash-recovery for dsh: after a restart, it detects sessions whose last turn was killed mid-flight and re-injects a continuation prompt that first demands the agent verify real-world state before acting, so side-effecting operations are not blindly repeated. It only reacts to the genuine crash marker (turn/end reason 'interrupted', synthesized on cold read by session repair), so it never misfires on user cancels, rate limits or model errors - which is why it needs no error classification, backoff or configuration UI. Unlike general-purpose auto-continue plugins, it also covers the case where a subagent was interrupted mid-run: the parent turn has already ended normally while it waits, so a naive check sees nothing to resume and the whole subagent tree dies silently; this plugin detects the interrupted child and wakes the parent instead. Single host file, zero external dependencies, seven config constants.

Grouped skill picker for the composer. A button beside the input box opens a panel that browses every installed skill by scene (research, office, data, writing, media, dev), with auto-classification for new skills, Chinese annotations, search and drill-down; picking one inserts the /skill-name gesture.

Zero-UI-overhead DeepSeek Harness plugin that automatically classifies conversation intents and names sessions with clean emoji prefixes (optimize, fix, feature, explore, etc.).

Replaces the chat model picker with a collapsible provider-grouped list (640x720 max) that shows each model name, provider name, provider ID and exact model ID, plus a manually managed uncommon list and a separate favorites list. Classification is user-driven only: no usage tracking and no auto-sorting. Search covers model name, model ID, provider name, provider ID and account notes.

Connects TypeSafe/Jev, Cloudflare/Clef, Nace/Drex, self-hosted Laya, and custom decision providers through one interface for agent and plugin classification, filtering, scoring, and image-object localization with structured results.

session_health for DeepSeek Harness — health intelligence (outcome classification, tool-health signals, prompt heuristics, context pressure, A–F grade) computed in-process from the session store, plus a standalone CLI over the same engine.

Auto-adjust model reasoning effort per task (off/low/high/max): task classification, \[effort=...] markers, in-turn error escalation, DeepSeek peak-pricing-period capping with countdown notices, and manual-selection priority.

Apple on-device Vision tools for text-only dsh models: local OCR (zh-Hans + 30 langs), image classification, face detection, document layout, and a combined describe — 100% offline, no API key, tall-screenshot slicing.

Cross-border commerce: HS codes, customs invoices, mainland reachability. HS/HTS code lookup and classification, commercial invoices, live exchange rates, IBAN and EAN/UPC checks, amount-in-English for documents, and whether your site is actually reachabl

Chemical safety intelligence through the hosted MSDS Chain MCP endpoint: 23 tools for compatibility and mixing order, GHS hazards, PPE, storage, waste disposal, exposure limits, transport classification, multi-region regulatory compliance, SDS lookup and version diffs, and signed audit reports, each answer citing the supplier SDS and revision date it is grounded in.