Table of contents (3 levels): topic areas -> schede (with page ranges, exercise counts, completion checkmark) -> sections (the printed index entries inside each scheda, with book page and kind grammar/vocabulary).

Full content of one book page (OCR markdown). Look it up by PDF page or by printed book page.

List exercises (brief). Filters: scheda number, topic substring (e.g. 'passato prossimo'), exercise type, section title substring (e.g. 'imperfetto'), progress status.

Full exercise: instruction, content (markdown + structured items), metadata, source page, and the history of submitted solutions.

Full-text search over all pages and exercises (Italian). Returns matches with a context snippet and references.

Record a solution attempt for an exercise. The server only stores data: grading (is_correct/score/feedback) is whatever the caller provides; leave them out to record an ungraded submission.

Progress rollup per scheda (or the whole book): exercise counts by status, attempts, last activity, and the completion checkmark (is_complete = every exercise of the scheda is completed).