Showing the last saved plugin snapshot.
← Leaderboard / Models / Plugin
shenhuanageshei/@dsh-external/dsh-vision-bridge
“DeepSeek Harness vision bridge.”
Star rank
#13653declared plugin rank
In Models
#1635category rank
Stars
0GitHub repository
Forks
0GitHub repository
Watchers
0GitHub subscribers
TL;DR
DeepSeek Harness vision bridge: session screenshots route by model capability. Image-capable models receive attachments inline; text-only models see the standard placeholder, and the bridge reads the image through a vision-language model — on demand via the vision_bridge_read tool or automatically via agent/pre-step context injection. : ; VLM (tool/auto )。
30 days of GitHub stars
+0 stars
+0% observed change
Oct 14Oct 28Nov 12
