feat: Add _vision_sidecar plugin

[GreifMax]

Plugin: Vision Sidecar

1. Changes vision_load to accept paths given as string.
2. Allows to configure a dedicated Vision Model for non vision-capable Main Models (like GLM/DeepSeek). When set up, the Main Model will call vision_load with a query (like: "verify that the two top right buttons are horizontally aligned") and the Vision Model will respond with specific information about the image.

Note

This version has been updated after discovering instabilities related to parallel vision_load calls. Now the Main may execute up to 4 vision_load calls, which call the API in parallel (like call_subordinate)

• GitHub reference: https://github.com/GreifMax/a0-vision-sidecar