플러그인

Render and iterate on Blender scenes from DSH: 16 tools for scene specs, previews, visual review and delivery renders, with immutable revisions and an approval gate.

Same-origin in mechanism with the two loudest lines in context compression. The code-skeleton gate follows the skeletonization approach of Headroom (Apache-2.0), whose published headline is 20% fewer tokens for coding agents and 60–95% fewer tokens for JSON, same answers. The estimator channel follows TokenPilot (arXiv:2606.17016), which reports up to 60% lower cost for long-session agents. Both figures are theirs, quoted as-is; this plugin ships no benchmark of its own and claims no reduction of its own. What it adds for DeepSeek Harness: choose a compression profile, set the Auto Compact trigger level and toggle code-skeleton compression from one settings section, with exact DeepSeek V4 tokenizer measurement, same-revision count verification, and fail-open behaviour that keeps the original tool results on unsupported models.

An editable diagram canvas in the DSH sidebar plus two agent tools (diagram_read, diagram_apply) that read and edit the workspace in place, using native .drawio files: the canvas opens and saves them losslessly — cells it does not understand are preserved byte-for-byte — and a file-fingerprint revision powers optimistic locking against concurrent edits.

DeepSeek Harness plugin: auto-route image-bearing requests to deepseek-v4-flash-vision-exp, then fall back to the original model.

Desktop computer-use for DSH: captures the Windows screen into the agent vision channel and drives mouse/keyboard through a Codex-style overlay with Esc abort; auto-detects Windows native or WSL hosts.

Windows computer use forked from computer-user: 13 computer_* tools that read the screen and drive the mouse and keyboard. Image-capable routes get the screenshot as a real image with an exact image-to-screen mapping, so no external OCR; elements return as UI Automation refs so a click lands on the exact control rectangle; Ctrl+Alt+Esc stops every call.

Model picker for the DSH web composer that replaces the model seat: a search-first popup whose left column indexes the suppliers and scrolls the grouped list, with a favorites group pinned at the top, image icons separating native from bridged vision input, and a reasoning-effort panel opened from the right zone of the trigger.

Evidence-first attention supervision for DeepSeek Harness with C0–C3 policy, deduplicated Inbox alerts, quiet hours, and redacted outcome records.

Provisions the kimi-webbridge bridge daemon (auto-install with SHA-256 verification, auto-start) and registers a 25-action skill that drives the user's real browser through the local bridge.

OpenAI-completions-compatible adapter for custom gateways (vLLM / LM Studio / self-hosted proxies): always role:"system", thinking driven by the model config, Qwen-style response split, and vision-model image input (single / multiple).

Transparent multimodal routing for text-only models: every image in every model call is fully transcribed (verbatim OCR, data, uncertainty zones, injection-hardened) by your own multimodal understander, with focused re-look via vision_relook and automatic retry on image-related failures. No bundled endpoints, no borrowed logins.

Free vision OCR with adaptive tile recognition for long documents and Markdown/Word/PNG/Excel export.

Per-profile settings overlay for DeepSeek Harness: global settings.yaml stays the baseline while each profile overrides any namespace through its own profiles/<name>/settings.patch.yml — object sections merge recursively, scalars and arrays replace wholesale, and !unset masks an inherited value. The overlay is transparent to existing plugins (they keep reading ctx.settings unchanged), writes land in the profile overlay only, and official schema validation, revision semantics, expectedRevision conflicts, watchers and events are untouched. Ships a settings command family (get/set/unset/mask/unmask/promote/demote/migrate/diff/layers) plus a Profile Settings section in the web Settings panel over a loopback RPC channel.

DeepSeek Harness vision plugin: 8 analysis modes (describe, OCR, chart data, UI review, object detection, compare, code-gen, debug), any OpenAI- or Anthropic-compatible vision API, with a built-in free vision model and automatic rate-limit failover.

Screen capture and external vision recognition: take_screenshot, list_windows, analyze_image and view_image tools with a configurable GPT vision channel (gpt-5.5 / gpt-5.6-sol / gpt-5.6-terra), API key via the credentials service, and a settings card; view_image shows the screenshot in the Web UI while the model context keeps text only.

텍스트 전용 모델에서 dsh-tool-vision으로 브리지된 붙여넣기 이미지에 대한 채팅 내 인라인 이미지 미리보기 (클릭하면 확대, 이전 메시지에도 미리보기 적용).

DeepSeek Harness용 계층형 모델 라우팅: think/build 모델 계층, 비전 위임(비전 모델은 이미지만 설명하고 작업 모델이 실행), 이미지 생성, 고영향 가드.

장시간 실행되는 서비스(개발 서버, watcher, 목 API)를 턴·세션·DSH 재시작을 넘어 유지하는 분리형 브로커 감독. Service 사이드바 탭(better-sidebar 확장 API로 등록)과 service_start/stop/restart/list/logs 모델 도구를 제공합니다.

Design Studio 탭: 디자인 브리프가 라이브 미리보기, 요소 피커, 비전 리뷰가 있는 디자인 에이전트 채팅, 아이덴티티 프리셋, zip 내보내기를 갖춘 html/css/js 목업이 됩니다.

DeepSeek Harness(DSH) web 플러그인: 파일을 컴포저에 붙여넣어 받은 편지함에 저장하고 썸네일을 표시합니다. 텍스트는 read_inbox로 읽고, 이미지 이해는 자체 비전 스킬(번들 image-reader + ARK_API_KEY)이 필요합니다.

DSH 이중 모델 라우팅 플러그인: 주 대화는 DeepSeek에 두고, 이미지 작업은 명시적으로 설정한 비전 모델로 자동 분배한 뒤 분석 결과를 DeepSeek에 돌려주어 계속합니다.

DeepSeek Harness 플러그인: 이미지 입력을 선언하는 `deepseek-vision` 라우트로, 무료 Zhipu GLM 비전 모델을 통해 붙여넣은 이미지를 전사한 뒤 DeepSeek 어댑터로 위임합니다.

DeepSeek Harness 비트리 플러그인: 이미지를 Qwen-VL(DashScope) 경로로 ctx.llm을 통해 라우팅하고 텍스트를 반환하여 텍스트 전용 코딩 모델에 시각을 부여

DeepSeek Harness settings-pro 플러그인: IM 브리지(Telegram/WeChat), DeepSeek 사용량, 재시작 간 메모리, 데스크톱 펫 및 비전 브리지