Pine 457304e619 feat(vision): add the model-facing recognition consumer ...

Registers the recognize_image tool and a bundled image-recognition skill,
and hooks agent/pre-step to deterministically inject the skill body when a
step input carries an image (content block or image path/URL), so the model
recognizes the image before continuing the task.

Co-Authored-By: Claude <noreply@anthropic.com>

2026-08-14 10:57:38 +08:00

..

image-recognition

feat(vision): add the image-recognition capability seam

2026-08-14 10:55:57 +08:00

image-recognition-http

feat(vision): add the configurable HTTP vision provider

2026-08-14 10:56:10 +08:00

tool-image-recognition

feat(vision): add the model-facing recognition consumer

2026-08-14 10:57:38 +08:00