Import a book by file path (.txt or .epub) or raw text, split it into chapters and size-bounded chunks, and register it for chunked reading. EPUB chapter boundaries (spine order) are preserved.

List all imported books with chunk counts and last-read position.

List all chunks (chapter/part breakdown) of a book, without their text.

Read the text of one chunk. Pass chunkId to read a specific chunk, or omit it to continue from the book's last-read position (its nextId). Reading a chunk updates reading progress.

Search all chunks of a book for a substring (case-insensitive) and return matching chunks with context snippets.

Get the last-read chunk id for a book.

Manually set the last-read chunk id for a book (e.g. to jump or re-read).

Read the accumulated discussion notes for a book, used to restore context cheaply between sessions.

Append a timestamped note entry (clues, reasoning, thoughts) for a book.

Add an annotation anchored to a quoted passage within a chunk. author should be 'human' or 'claude'. If the other author already has an overlapping annotation on the same quote, a shared card pairing both notes is created automatically.

List annotations for a book, optionally filtered to one chunk.

List shared cards: passages where both human and claude have left overlapping annotations.