Eigma

Use this when you need the wiki's table of contents to plan where a page belongs, or to browse the structure before an edit. With NO argument it returns the categories with their page titles + one-line summaries (or, for a large wiki, a tiered overview of top-level categories). Pass a category_path to drill INTO that category and see its subcategories + pages, then call again with a deeper path to go further down the tree. Reuse a category and a page title EXACTLY as shown. Concept lookup in a large wiki is eigma_search_wiki; a page's full body comes from eigma_read_page. A repeat call with the same arguments returns the same data.

Use this when you want to target what the user should review: which pages they have not read, not been quizzed on, or are forgetting (answered wrong or decayed), in the active volume or a chapter. Returns three buckets of specific pages (to_read / to_test / fading, each with its title + category), plus mean-state and counts. Read-only. Page content itself comes from eigma_read_page.

Use this when you need one existing Eigma page's FULL body: before integrating an update into it, or to answer a question grounded in it. Pass a title (and category if known) for ONE page; pass a category_path with NO title to read a whole chapter at once (before reorganizing it). Returns the body, summary, tags, and the page's quizzes as {id, prompt}; a miss means treat the concept as new. Reuse the returned page id when a later edit targets this page, and a quiz's id to remove or replace that exact quiz via eigma_suggest_edits (edit_quizzes). It reads only the user's Eigma wiki, not the web; keyword lookup across the wiki is eigma_search_wiki.

Use this once before eigma_save_notes, with ALL your drafted pages: it returns, per draft, the existing pages it may duplicate (title + category + summary) plus the wiki's chapter list, so you update the right page instead of creating a near-copy. Read-only, and only for the pre-save check - to answer a question about the wiki or look a concept up, use eigma_search_wiki or eigma_browse_wiki.

Use this when the user asks to save, file, keep, note, or remember THIS conversation (or part of it) into their Eigma wiki. It drafts the pages worth keeping and saves them to the user's Eigma review inbox in this one call, then ends the request. Only durable, learn-worthy knowledge becomes pages (skip look-up trivia, logistics, and small talk), so a conversation with nothing worth keeping yields no draft and nothing saved. Editing pages that ALREADY exist is eigma_suggest_edits' job. Give every page a fitting category_path: an existing chapter when one fits, and a new chapter when the concept belongs to none of them rather than forcing it into an unrelated one. To get that right, call eigma_resolve_pages FIRST, once, with every page you drafted: it returns, per draft, the existing pages it may duplicate and the wiki's real chapters. Reuse a returned page's title AND category_path exactly to update it, and for any page you update call eigma_read_page on it FIRST: saving REPLACES that page's body, so body_md must carry BOTH what the page already says AND what this conversation adds - every sentence you leave out is deleted from the user's wiki, and an update body written from the conversation alone destroys the page. Do not browse the whole wiki for this. Pass nodes (one object per page) plus the top-level conversation block. Every page object needs ALL of: title (the concept's plain canonical name as a 1-3 word noun phrase, with NO appended source or qualifier, so it matches and updates any existing page on that concept), category_path (the CHAPTER the page lives under, never the page's own title; normally ONE level, 2 only if unusually specific; reuse a fitting existing chapter over inventing a near-duplicate, and create a new chapter when none of them fits), body_md (a STRUCTURED page: a lead paragraph then ## sections; write math as LaTeX in $...$/$$...$$; ONLY if the chat used outside sources, add [^N] footnotes and one ## References section, each definition written as "[^N]: label" carrying the source's REAL link (a bare source name with no URL becomes a dead, unclickable reference)), summary (ONE short line), links (related concept titles, including exact existing-page titles, to connect the graph), and quizzes (1-3, REQUIRED, each an understanding-testing selection question {kind,prompt,options,answer}; no option may run more than half again as long as the shortest, reached by making each wrong option a MORE substantial claim, never by shortening the right one). Draft every page in FULL now: whatever you send is EXACTLY what lands in the user's review inbox, so a missing field saves an incomplete page. The body_md MAY also include a mermaid diagram and/or ONE self-contained animation widget (all JS/CSS inline, no external network); most pages need neither. This call SAVES the pages into the user's Eigma review inbox and returns a receipt listing what it saved as NEW or as an UPDATE; show that receipt to the user, then end your turn - unless the receipt itself says pages did not fit, in which case call this again with exactly those remaining pages first. This is the only call that WRITES (eigma_resolve_pages before it only looks things up). Saving the same pages twice is harmless (the server ignores a duplicate), so if the user asks again, simply call this again.

Use this when you need to find existing Eigma pages by concept or keywords, anywhere in the wiki (matches title, summary, category): to locate the page to update, or the page(s) that answer a question. Returns matching page titles + categories + one-line summaries, not full bodies. A page's full text comes from eigma_read_page; an identical repeated search returns the same results.

Use this when the user asks to organize, verify, cite, add sources, merge, dedupe, move, rename, delete, restructure, refine, or add quizzes to pages that ALREADY exist in their Eigma wiki. This is the ONE tool for every edit to the existing wiki; new pages from the current conversation come from eigma_save_notes instead. It writes: this one call queues the changes into the user's Eigma review inbox, and nothing touches the wiki until the user accepts each change there. Call it ONCE per request and relay the receipt it returns. Put every change from this request into ONE call with ONE ops array; each op is an object {kind, ...} where kind is move, merge, delete, rename, update_page, edit_quizzes, or add_page. Reference each page by its EXACT title + category_path (verbatim from eigma_browse_wiki or eigma_read_page); an id is valid only when it came from reading that page. A verify, cite, or add-sources request is an update_page op whose body_md carries the corrected page with inline [^n] citations and a ## References section (each definition written as "[^N]: label" carrying the source's REAL link (a bare source name with no URL becomes a dead, unclickable reference)): draft it and send it here rather than answering in prose. If nothing needs changing, propose nothing. A refine op MAY add a mermaid or svg diagram or ONE self-contained ```animation widget (inline CSS/JS, no external network) to a body_md; most pages need neither.

Use this when the user asks for an EXISTING Eigma page in another language. Translate that page's body (and its summary if it has one) into the target language and send it here. The page's TITLE and its quiz questions are NOT translated and must be left alone. The result goes to the user's Eigma inbox for them to confirm; it does not change the page itself. Pass page exactly as the title appears in the wiki.