dsh-autovision
by — · Junkrat9527/dsh-autovision
★ 0 Stars
⑂ 0 Forks
Original language: English
About
Vision for text-only dsh models: paste an image and a configured multimodal model transcribes it to text automatically — transparent twin routing, an agent-callable read-image tool, no built-in keys or relay.
Similar plugins
Transparent multimodal routing for text-only models: every image in every model call is fully transcribed (verbatim OCR, data, uncertainty zones, injection-hardened) by your own multimodal understande
★ 0
dsh plugin --profile web add dsh-mmrouteConfigurable image recognition for text-only DSH models: image messages are first transcribed by an OpenAI-compatible vision model (Base URL, model ID and API key set in a Settings section) and then p
★ 0
dsh plugin --profile web add @lp181818/dsh-vision-pluginGive text-only models vision: a describe_image tool that delegates images to a vision model from your dsh model list over the harness's own LLM runtime.
★ 0
dsh plugin --profile web add dsh-easyvisionVision for any DSH route: paste images in the Web composer with intent-aware auto-analysis, delegate workspace image reads to a Kimi/MiniMax vision subagent, and materialize pasted originals for editi
★ 0
dsh plugin --profile web add dsh-vision-subagentVision provider route that transcribes attached images to text through a configurable model (15+ OpenAI-compatible and Anthropic vendors) while DeepSeek keeps answering.
★ 0
dsh plugin --profile web add dsh-vision-recognizerAuto-discovery vision bridge for text-only DeepSeek Harness agents: automatically finds an image-capable model from your configured providers and returns picture descriptions as plain text via a visio
★ 0
dsh plugin --profile web add dsh-auto-vision