152 results
Vision for text-only DeepSeek Harness agents: delegate image reading to a one-shot subagent on a configurable vision route (MiniMax / Kimi / any OpenAI-compatible provider), keeping image bytes and the vision model's context out of the main session.
DSH multimodal input plugin: route file attachments (images, video, audio, text) through per-preset model chains and feed the results to the session model as prompt tokens. Adds a Multimodal settings page.
mm-vision (通感编码器) for DeepSeek Harness — give any text-only LLM the ability to see images via structured spatial text encoding. Registers the mm_vision tool.
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。
Private multimodal integration suite for DeepSeek Harness
Adaptive image routing for DeepSeek Harness: pass images directly to native multimodal models and transcribe them only for text-only models.
dsh-eye-vision: give text-only DeepSeek Harness models eyes — image understanding via any OpenAI-compatible multimodal API. Fork of dsh-free-vision with custom-provider fixes and an allowed-directories whitelist.
MindsEye: model-driven vision tools, structured evidence, and exact cache for DeepSeek Harness
Multimodal plugin for DeepSeek Harness: understand images and generate images through configurable OpenAI-compatible or DashScope endpoints.
DeepSeek Harness plugin: the Models+ settings page — a fully plugin-owned model/provider UI with per-model extension fields (reasoning efforts, input modalities, compat flags) and models.dev metadata prefill
给 DSH agent 装一双眼睛：调用在线 VLM（多供应商、OpenAI 兼容）分析本地图片、URL 与会话上传的附件；勾选的模型特色能力会实时注入系统提示
DeepSeek Harness Web plugin: per-model input-modality selector on the Models settings page for third-party (pi-ai) providers
Mobile UI fixes for the DeepSeek Harness web profile: a restart row, input-modality switches, a narrow-screen drawer and settings tabs, a full-width model menu, a stuck-request network chip, a scrollable question region, a throttled reaction to streaming message storms, a guarded subagent-catalog refresh, click-to-open lineage chips, a narrow-header collector sheet, and a throttled session-list render under background streaming load.
DSH-native video understanding with configurable multimodal providers
DeepSeek Harness plugin: bridge image-bearing messages to a user-configured OpenAI-compatible vision endpoint when the active text model cannot see images
Agnes 全模态插件 for DeepSeek Harness：看图（agnes_vision）、生图/图生图（agnes_image）、视觉桥（带图消息可发送并自动交给 Agnes 视觉分析）。密钥经 DSH 凭据服务读取，不写入代码。
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.
A vision bridge for text-only DeepSeek Harness models: registers an `analyze_image` tool that answers questions about images via ANY OpenAI-compatible vision/multimodal endpoint (SiliconFlow, DashScope, Zhipu, OpenRouter, Ollama, ...).
DeepSeek Harness 视觉理解插件：把用户消息与工具结果中的图片翻译成文字描述，交给纯文本任务模型（如 DeepSeek）。
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
DSH plugin: when a provider's model sync returns only ids, automatically fill display name, context window, max output tokens, reasoning efforts, and input modalities from the models.dev catalog (cached, TTL-refreshed), and surface a settings page with toggles, refresh, and a fill report.
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.
TokenLab provider bundle for DeepSeek Harness with native Responses, Messages and Chat routing plus full multimodal and async tools.
DeepSeek Harness plugin: route an agent request to a vision model (deepseek-v4-flash-vision-exp) when the user message contains an image, and keep the original model otherwise.