Build a toy vision-language bridge: summarize patch brightness into a deterministic coarse description before language generation.
Required APIdef describe_image(patch_means):
return 'dark' | 'mixed' | 'bright'Think through the mechanism first if you want the extra reasoning step. It never blocks the editor.
describe_image([0.9, 0.8])high visual evidence maps to a bright description
describe_image([0.1, 0.2])low visual evidence maps to a dark description
2 hidden edge tests run after the visible contract passes.
Run Tests to see the contract verdicts here.