Plugin record
Einskyle/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.
What it declares
- Kind
- bundle
- Package
- dsh-llm-vision-bridge
- Version
- 0.1.2
- Profile / bundle
- Unknown
- License
- MIT
Permission hints
Declarations or static clues from the public source—not runtime permission proof.
Compatibility context
- DSH declaration
- Unknown
- Node declaration
- Unknown
- Runtime tested
- Not tested
- Source reference
- 5a8e31788f4b2b11c4d2122ed5f138235d9ae55e
Evidence
- Observed
- 2026-08-14T00:00:00.000Z
- Runtime result
- Public metadata and declared DSH package fields were read at a fixed source commit. No runtime test was performed.
- Evidence URLs
- Open evidence · Open evidence · Open evidence
Install notes
Review the source, license, dependencies, and permissions before you run anything. A branch URL is not a pinned reference.
No fixed command is available. Open the source repository for install instructions.
Copy disabled: this record has no verified fixed reference.
Related Stacks
No complete Stack currently references this record.
Community feedback
Have you used this plugin?
Share a rating and practical context. Every submission is reviewed before it can be published or included in an aggregate.