页面加载中
dsh-llm-vision-bridge
Native LLM-provider vision bridge: images pasted in the chat are described by a vision model (Qwen3-VL via pi-ai/llama.cpp) and the text description is fed to text-only DeepSeek for the reply — image admission, routing and compaction all run through harness-native mechanisms, with an LRU description cache and 503 retry.
PromptHub provides the directory and install command only. Plugin code comes from the author's GitHub or npm source; review it locally before installing.
dsh plugin --profile web add dsh-llm-vision-bridgeThese labels describe capabilities publicly declared by the plugin; actual behavior depends on the author's source and host configuration.
A DSH Plugin runs with your local permissions and may access files, shells, networks, or credentials. Listing and static metadata are not a security guarantee from PromptHub; review the source first.