Bundle
dsh-read-image-jpeg-fallback
DSH profile plugin: converts read_image PNG/WebP attachments to opaque sRGB JPEG so LM Studio's openai-completions endpoint accepts them
wuyiwuaa1-ship-it
Browse
279 results
Bundle
dsh-model-auto-hot-switch
Automatic per-task model hot-switching for DeepSeek Harness (dsh): image-aware tasks route to the vision model automatically, every other task keeps your default model. Zero extra tokens, no context disturbance.
SHUJILAI
Bundle
dsh-llm-capabilities
DSH plugin: auto-detect and configure model capabilities (reasoningEfforts + input modalities) for llm-pi-ai. Successor to dsh-reasoning-efforts.
bamboostrip
Bundle
dsh-awesome-model-setting
DeepSeek Harness web plugin: a Model Capabilities settings page for declaring model input modalities, context window, output cap and image budgets without hand-editing settings.yaml.
Kazusa1085
Bundle
dsh-vision-toggle
DSH 模型视觉开关：设置页「模型视觉」行，为 llm-pi-ai 自定义路由下手写声明的模型切换 input 视觉模态（settings.mutate 官方通道，热生效）。
123twtd
Bundle
dsh-image-router
DeepSeek Harness plugin: analyse images out of band with a vision model — pasted images are digested into text before admission and a describe_image tool covers image paths, all without ever changing the session's model.
zhiwuli0228
Bundle
dsh-image-base64
DeepSeek Harness plugin: transcodes images to a base64-safe format (PNG) before a vision request, fixing gateways like LM Studio that reject non-PNG/JPEG/GIF data URLs with "'url' field must be a base64 encoded image."
pureexe
Bundle
dsh-file-upload
Upload button + drag-and-drop files into DSH conversation as local paths; uploaded-file management (list/info/delete/@path) and clipboard path reading (zero-copy, no size limit)
666emmm
Bundle
um-dsh-azimg
Give DeepSeek Harness agents eyes: local image analysis via vision models — um_analyze_img tool + model-capability recognition + hot-switch settings UI
UnforgetMemory
Bundle
dsh-document-evidence
Project PDF library with background indexing and cited page highlights for DeepSeek Harness Web
Anduin9527
Bundle
taishan-vision
泰山识图 Taishan Vision - 让 DeepSeek Harness 纯文本模型也能识图:GLM 视觉识别 + 所选模型推理(静态插件包,重启永久生效;由鲸晴 JingQing v1.1.8 魔改)
iguanren
Bundle
dsh-vision-patch
Per-model and per-route image-input (vision) checkboxes on the Models page's custom-provider cards, writing through the llm-pi-ai settings namespace.
ryasrk
Bundle
vision-exp-tile
为 deepseek-v4-flash-vision-exp 量身定制的大图智能识图插件：整图预检 → 本地 OCR+像素网格（文字）+ 兴趣点按比例切块（最长边 800）→ 汇总；保留全图 800x800 网格切块模式。不代为统计/不显示 token 与费用，实际计费以 DeepSeek 官方 API 平台账单为准。v0.4.3：仓库元数据修复 / 计费表述诚实化 / 新增隐私与数据说明 / 过期临时产物清理。
Nicholaskin
Bundle
dsh-plugin-screenshot-ask
DSH 截图提问插件：输入框相机按钮或 Ctrl+Shift+A → 自动最小化窗口 → 原生全屏框选浮层（确认/取消按钮）→ 选区直接作为图片附件进入当前会话输入框，全程不落盘。Screenshot-to-ask for DeepSeek Harness: the window hides, a native region overlay covers every monitor, and the crop lands in the composer as an image attachment.
sky1ine139
Bundle
@goodandready/dsh-vision-bridge
Flagship multimodal vision hub for DeepSeek Harness: ~40 tools, PDF drag-and-drop, LaTeX formulas, complex tables, QR codes, UI flow diagrams, and multi-model consensus.
GooDAnDReaDY