/** * Multimodal message assembly for `Task(images=[...])`. * * Port of `praisonaiagents/agents/agents.py::get_multimodal_message`: a local * file is inlined as a `data:` URI, anything else is passed through as a remote * image URL, and the text prompt leads the content list. * * One documented gap: Python's `.mp4` branch decodes the video with OpenCV and * appends one frame per second. There is no equivalent decoder in this package, * so a local video contributes a text note naming the file instead of silently * producing an unusable `data:video/...` URI. Pass extracted frames as images * to get the Python behaviour. */ /** One part of an OpenAI-style multimodal message. */ export type MessageContentPart = { type: 'text'; text: string; } | { type: 'image_url'; image_url: { url: string; }; }; /** The filesystem calls this module needs; injectable so tests need no disk. */ export interface ImageFileSystem { existsSync(p: string): boolean; readFileSync(p: string): Buffer; } /** The note used in place of Python's OpenCV frame extraction. */ export declare function videoNote(file: string): string; /** * Build the message content for `text` plus `images`. * * With no images this is a single text part, which is what makes the option * observable: the same prompt with `images` gains one `image_url` part per * entry. */ export declare function buildMultimodalContent(text: string, images: readonly string[], fileSystem?: ImageFileSystem): MessageContentPart[];