vision 117

DeepSeek Harness 视觉桥：自动发现你已配置的多模态模型，给纯文本主模型装上 vision 工具，识别结果以纯文本返回。零配置，一条命令安装。

GLM 视觉模型插件：注册 glm-vision 供应商路由（glm-4.6v 系列，image+text 输入声明）并提供 glm_vision 工具，让 DeepSeek 等文本主模型直接调用智谱视觉模型看图。

MindsEye: model-driven vision tools, structured evidence, and exact cache for DeepSeek Harness

Per-model vision (image input) toggle for DeepSeek Harness (dsh): list every configured model and flip a switch to enable/disable image support without hand-editing settings.yaml. 为 DeepSeek Harness 提供按模型的「支持图片」开关：无需手改 settings.yaml。

Bridges images into text for DeepSeek Harness: when the session's selected model cannot see images, a configured vision model describes them and the descriptions enter the durable session history as folded context rows — your message stays untouched.

VisionForge: vision understanding + image generation for DeepSeek Harness (DSH)

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

DSH 静默视觉增强：主模型照常选择，图片自动交给固定视觉模型后以隐藏上下文返回主模型。

Capability-aware vision for DeepSeek Harness: native image input for multimodal models, with an isolated one-shot vision-route fallback for text-only models.

DSH plugin: auto-detect and configure model capabilities (reasoningEfforts + capacities) for llm-pi-ai. Vision (input) is managed by the official UI. Successor to dsh-reasoning-efforts.

Gives a text-only LLM vision capability

MiniMax CLI bridge for DeepSeek Harness (dsh): mmx-backed web search fallback and transparent image understanding, with first-run onboarding and a settings card.

明眸 VisionBridge - 自研视觉桥：瞎子模型收图时自动调用视觉模型识别，把识别文字喂回主模型，无感、可配置、升级不丢

Display companion for dsh-vision-router: keep Auto Vision routing, and put a square picture button on each original model row. Does nothing unless dsh-vision-router is installed.

DeepSeek Harness 视觉能力全家桶：vision_understand 工具（OpenAI 兼容视觉 API，默认免费智谱 GLM-4.6V-Flash，限流自动降级 GLM-4V）+ 粘贴/拖拽/按钮三入口识图

Bridge Apple's on-device Vision framework (macOS) into DeepSeek Harness: OCR, image classification, face detection, and document layout as local dsh tools. No network, no API key, no daemon.

DeepSeek Harness plugin: local text-to-image with a canvas-style GUI, inpainting, DeepSeek vision review, OpenAI-compatible API option, and a Python Stable Diffusion worker (diffusers/MPS).

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。

Fully-local OCR CLI for text-only LLMs: PaddleOCR-VL first-tier engine with tesseract fallback, dsh plugin included

Give text-only DeepSeek-V4-Pro real vision with zero new dependencies and DeepSeek-only routing: images are described by deepseek-v4-flash-vision-exp (your existing DEEPSEEK_API_KEY), then the text is handed to V4-Pro.

DSH 桌面自动化插件：无障碍树优先的观察-动作回路，30 个标准电脑控制工具（元素/坐标双目标、auto/a11y/event 策略），写后作废/禁重放/持久急停等安全语义，对话卡片+悬浮面板+环境自检设置页，分块识图，JSONL 审计与 pid 白名单。默认关闭。

A vision bridge profile bundle for DeepSeek Harness (dsh): gives non-vision models image-reading capability by delegating transcription to a vision-capable model, with GUI paste admission and a web settings page for vision model selection.

模型能力管理：为手写模型设置图片输入与推理强度、线路系统消息角色（可一键继承目录模型的精确能力）。

DeepSeek Harness plugin: a configurable provider route that transcribes pasted images via free Zhipu GLM vision models before delegating to a text-only adapter.

macOS desktop control for DeepSeek Harness: agent operates non-browser apps (CapCut/PS/WPS/native clients) like a human — see screen, move mouse, type text. 14 tools + vision closed-loop (see/locate/click/verify).

Vision bundle + plugin for DeepSeek Harness: the describe_image tool reads local images and asks any configured multimodal route, with zero core changes

Give DeepSeek (text-only) models vision in Claude Code, Codex, and Agent Plugins clients: describe images via any OpenAI-compatible vision endpoint.

Let text-only models see images in DeepSeek Harness: intercepts the llm/stream waterfall and transparently substitutes each image with a vision model's description.

DSH Web 插件：调用智谱 GLM 视觉模型分析图片（analyze_image 工具 + 插件设置卡片）。

DeepSeek Harness plugin: a vision worker over Cloudflare Workers AI (@cf/moonshotai/kimi-k2.6) that routes image requests from text-only callers, returns a versioned righthand.vision.v1 envelope, and supports follow-up questions.

DSH plugin: read images through a user-configured vision-capable model when the main model route cannot accept image input

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.

为 DSH 非视觉模型提供基于 DeepSeek V4 Flash Vision Exp 的会话图片分析工具

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

Local OCR for DeepSeek Harness: read text out of images with Apple Vision on macOS — no network, no API key, nothing to install. Falls back to tesseract elsewhere.

让纯文本会话模型也能读取用户上传的图片——包装原生 deepseek-official 适配器：声明图片输入能力放行附件，把图片交给视觉模型转成文字，再委托给纯文本 DeepSeek。

Automatic tier-based model routing for DeepSeek Harness: a virtual `smart` model classifies each request by difficulty (hard / normal / easy) and by vision need, then delegates it to the models you already configured. 三级难度 + 视觉自动路由，虚拟 smart 模型零配置接入。

Project PDF library with background indexing and cited page highlights for DeepSeek Harness Web

Third-party provider reasoning-effort AND input-modality settings for DeepSeek Harness: thinking levels and image-input support declared per model, auto-adapted from a model knowledge base + wire-protocol inference, edited right inside the official Models

dsh web 插件：自动配置模型思考档位与能力，并按 provider+model 记住最后选择的思考档位

Model tags, reasoning capabilities, image routing, and vision proxy support for DeepSeek Harness

Meta package: one-command installation of useful community plugins for DeepSeek Harness — upload button, document reader, vision (image reading via DeepSeek's built-in multimodal model), plugin manager, and desktop launcher.

DSH-Plugin for DeepSeek-Harness: fully-local image understanding & OCR powered by macOS Vision Framework

DSH desktop agent: a native-vision decision loop that drives the host desktop through the Cua Driver tools. DSH 桌面 Agent 子插件。

Local image understanding for the DeepSeek Harness: OCR, table-layout detection, and semantic description of textless images via macOS Vision, fully on-device (images never leave your Mac). 本地化识图，图片不出本机。

Vision tools (analyze_image, locate_element) for DeepSeek Harness: local ollama, DSH subagent (qwen-vl etc), or OpenAI-compatible HTTP endpoints

DSH 视觉桥插件：自动区分多模态/文本模型。多模态模型直接看图；文本模型通过可配置的多模态端点（baseUrl + apiKey + model）代看，支持粘贴图片、read_image 工具、请求时图片转证据。

Capability metadata for hand-declared gateway models, resolved at runtime by bare model name (context window, output cap, reasoning levels, vision) — matched against the official DeepSeek route's catalog, the installed pi-ai catalog, opencode and models.d

DSH 视觉桥接插件：让无视觉能力的主模型看图（会话收图 + 自动转文字 + view_image 工具）

把长文本渲染成图片发送来压缩 LLM 输入 token（DeepSeek 视觉模型、每图 384 token 封顶）— text-as-image token compression for DeepSeek Harness