DeepSeek Harness 플러그인 — 741 페이지

DeepSeek Harness client plugin: paste a screenshot, draw on it in an overlay (pen, arrow, rectangle, ellipse, text), and file the annotated PNG into the conversation as a normal attachment.

Image auto-describe provider for the DeepSeek Harness apiproxy admission seam: transcribes pasted images through configurable vision routes (Qwen first, GLM fallback) so text-only session models still receive image prompts.

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."

Give text-only models eyes: an analyze_image tool for DeepSeek Harness, backed by free Chinese vision APIs (GLM-4V-Flash / Qwen-VL) or any OpenAI-compatible vision endpoint. 给纯文本模型装上眼睛。

让文本模型（如 DeepSeek）也能正常粘贴并发送图片：图片落盘到工作区，消息转成仅模型可见的路径文本，由模型调用视觉/MCP 工具识别。

Let image-incapable LLM models receive image messages in DeepSeek Harness (dsh): replace image blocks with text placeholders + local paths, then describe via a vision script (qwen)

DSH 图片理解桥接插件:挂 agent/pre-step,把消息中的图片块经视觉模型(默认智谱 GLM-4V-Flash 免费档)转成文字描述,让纯文本模型(DeepSeek)也能看图

Paginated image viewer for DeepSeek Harness: open a set of images in one pageable viewer, zoom and pan each image independently, reorder them by dragging the filmstrip, and browse the session workspace from inside the panel.

Codex-style generated-image gallery and lightbox for DeepSeek Harness

Recover a DSH visual-model session when an upstream gateway rejects a request for carrying too many images: offload the oldest image occurrences to text placeholders and retry the step.

Giving text models eyes to see in DeepSeek Harness.

Caps the longest side of images sent to chosen providers or models in DeepSeek Harness, with its own Settings tab

DeepSeek Harness plugin: Qwen-Image 文生图 / 参考图编辑，把官方提示词契约的 wh_ratio 做成一等参数；后端 local（本插件自带受管运行时）/ comfyui / api，默认 auto

Convert model-bound images to JPEG/PNG/WebP for LM Studio compatibility

DeepSeek Harness plugin: generate images via Aliyun Bailian Qwen-Image (bl CLI). Adds a generate_image tool that returns images as conversation attachments.

DeepSeek Harness plugin: image generation through a configurable, provider-agnostic backend. It mounts the bundled stdio MCP server behind an NDJSON bridge, exposing mcp__image_generation__image_generate and mcp__image_generation__image_config_status, and registers the bundled image-generation skill.

Image generation tool and settings page for DeepSeek Harness, talking to any OpenAI-compatible /images/generations endpoint.

DSH 生图插件：在设置中配置多个生图供应商/模型，并在对话中通过 image_generate 调用当前选中的模型。

DeepSeek Harness Cordis plugin for Responses API image_generation: durable attachments and inline conversation rendering.

Session image payload governor for DeepSeek Harness: audit which images a session still ships, pick the ones to keep, and move the rest out of the model context.

DeepSeek Harness plugin: trims the oldest images from outgoing chat requests and, when the provider rejects the image count with HTTP 400, parses the limit from the error and retries with fewer images. · DSH 插件：裁剪即将发出请求中的历史图片，并在上游因图片数量返回 400 时解析该上限并按更少的图片重试。

让文本模型（如 DeepSeek）在 DSH 里直接收发图片：图片落盘工作区、模型可见面自动替换为 mmx（MiniMax VLM）识别结果，用户侧照常显示缩略图。

Inlines each image block only in the request where it first appears, then swaps it for the harness's own placeholder text on every later request. On by default for every provider; each provider can be switched off or limited to specific models from the plugin page.

DeepSeek Harness Web GUI 输入框 📎 选图按钮:通过系统文件选择器添加参考图,绕开拖拽环境问题,复用官方附件管线(缩略图/上限校验/随消息上传)。Image-picker button for the conversation composer.