Unified static-image generation router for DeepSeek Harness: one image_generate tool with standard parameters, config-driven engine routing (OpenAI Images, Zhipu CogView, and any compatible endpoint) with health-aware fallback, durable workspace attachments, per-session quota accounting, and a Plugins settings panel
DeepSeek Harness all-in-one: no model switching — regular DeepSeek auto-routes to vision & image gen. Multi-backend: Gemini + any OpenAI-compatible (GPT-4o, Qwen-VL, GLM-4V, gpt-image, DALL-E, Flux, OpenRouter). gemini_vision/gemini_generate_image/gemini_optimize_image with vision self-check. Better than modlens.
给 DeepSeek Harness 纯文本模型加视觉：采用codex风格聊天框拖图自动分流给用户配置的视觉模型转文字，v4 不切换模型即可识图。 Vision for text-only DSH models: routes chat-box images to a user-configured vision model and returns text descriptions, deepseek-v4-pro reads images without switching.
