vercel.internal._gw_images_collect

(internal) Collect a turn into the endpoint's two inputs: text blocks trimmed into `parts` (blanks dropped), image blocks into `files` — how this endpoint does image editing / variations (image-model protocol v4) — at every position. The other media kinds have no representation and are rejected.

Reference version

Signature

function vercel.internal._gw_images_collect(
blocks: ai.content.Block[],
parts: string[],
preview: bool = …
) -> void throws baml.errors.InvalidArgument | baml.errors.Io | baml.errors.Timeout | ai.errors.InvalidRequest | ai.errors.NetworkFailure | ai.errors.PreviewUnsupported

(internal) Collect a turn into the endpoint's two inputs: text blocks trimmed into parts (blanks dropped), image blocks into files — how this endpoint does image editing / variations (image-model protocol v4) — at every position. The other media kinds have no representation and are rejected.

Source:<builtin>/vercel/ns_internal/images.bamlbytes 64127277