tbenandClaude Opus 5.5
bea656ade8
Bots can now show a concept as a visual: create_graphic (with update_graphic, read_graphic and list_graphics, on every run, no computer needed) stores one HTML document in bot_graphics, per user like the conversation, and the chat renders its [graphic:ID] ref as an inline card sized to fit, with a large view and a page of its own (no rail). Graphic HTML is treated as hostile: it is only served at /graphics/<id> with a CSP sandbox allowing scripts under an origin of its own and no network, loading only the vendored Chart.js and Mermaid from /graphics-lib/. The document carries the app's theme vars and scrollbars, reports its height to the thread, and a frame that navigates away is closed. Co-Authored-By: Claude Opus 5.5 <[email protected]>
17 lines
549 B
TypeScript
17 lines
549 B
TypeScript
/**
|
|
* What the graphic tools of one run work with: the bot, the user it works
|
|
* for and the place, and a callback that puts a graphic on its message.
|
|
*/
|
|
export type GraphicToolContext = {
|
|
bot_id: number | string;
|
|
user_id: number | string;
|
|
session_id?: number | string | null;
|
|
workspace_id?: number | string | null;
|
|
job_id?: number | string | null;
|
|
/**
|
|
* Called with a graphic's ref when the run makes or changes it, so its
|
|
* message always shows it.
|
|
*/
|
|
onGraphic?: (params: { ref: string }) => void;
|
|
};
|