feat: Add _vision_sidecar plugin - #1841
Merged
Merged
Conversation
Drop the duplicate plugin implementation and source mutation workflow so the sidecar can live in its owning model-config and vision tool modules.
Add a strict per-preset sidecar slot, Main-first routing, one-call multi-image analysis, parallel-worker image resolution, and inline model settings with focused regression coverage.
3clyp50
force-pushed
the
add_vision_sidecar
branch
from
August 25, 2026 17:28
5a3de84 to
2ab8644
Compare
Reuse the stock public vision_load prompt and remove the sidecar-specific schema and query argument. Keep delegated analysis instructions in a private framework prompt, preserve the parent request in parallel workers, and retain one-call multi-image batching.
This file contains hidden or bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
Sign up for free
to join this conversation on GitHub.
Already have an account?
Sign in to comment
2 participants
Add this suggestion to a batch that can be applied as a single commit.This suggestion is invalid because no changes were made to the code.Suggestions cannot be applied while the pull request is closed.Suggestions cannot be applied while viewing a subset of changes.Only one suggestion per line can be applied in a batch.Add this suggestion to a batch that can be applied as a single commit.Applying suggestions on deleted lines is not supported.You must change the existing code in this line in order to create a valid suggestion.Outdated suggestions cannot be applied.This suggestion has been applied or marked resolved.Suggestions cannot be applied from pending reviews.Suggestions cannot be applied on multi-line comments.Suggestions cannot be applied while the pull request is queued to merge.Suggestion cannot be applied right now. Please check back later.
Plugin: Vision Sidecar
vision_loadto accept paths given as string.vision_loadwith aquery(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)