image-understanding 13

DeepSeek brain + automatic image transcription for DeepSeek Harness: a deepseek-vision provider route that transcribes attached images to text before delegating to the text-only DeepSeek adapter. Official deepseek-v4-flash-vision-exp by default (a pure-te

Eyes for text-only DeepSeek on DeepSeek Harness: image understanding via Doubao Web by default (zero cost, no API key), Antigravity IDE quota (flash/pro), Gemini API, or Cockpit proxy — model-invokable vision tool, wrapper adapters, evidence memory, and a

On-demand vision for text-only DSH sessions: images become markers, and a vision_describe tool sends only image + question to an OpenAI-compatible vision model

Codex-backed web search, image generation, and image understanding tools for the DeepSeek Harness.

Eyes for text-only DeepSeek on DeepSeek Harness: image understanding via Antigravity IDE quota (default, flash/pro), OpenAI-compatible VLM endpoints, Gemini API, or local Ollama — model-invokable vision tool, wrapper adapters for deepseek/opencode-go, evi

Adaptive image routing for DeepSeek Harness: pass images directly to native multimodal models and transcribe them only for text-only models.

Lightweight, route-preserving vision link for DSH: a configured vision model sees while the selected text model stays in control.

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

Multimodal plugin for DeepSeek Harness: understand images and generate images through configurable OpenAI-compatible or DashScope endpoints.

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。

Lets a text-only agent call a multimodal model mid-task: the vision tool sends one image file to Qwen, Kimi, OpenAI, Claude, Gemini or a self-hosted endpoint and returns structured evidence — summary, verbatim OCR, layout, entities, and what the model cou

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.

Local-first vision for text-only DeepSeek Harness agents: route image understanding to a local OpenAI-compatible vision model, return structured JSON evidence (summary / OCR / layout / semantics / visual / uncertainty).