Lingard Vocab

Attaches generated or supplied images to existing Lingard cards. This tool does not generate images from prompt alone: pass actual imageBase64, dataUri, or imageUrl. PNG, JPEG, WebP, and SVG inputs are converted to WebP and uploaded as private custom card images; an image the card already has is replaced. An imageUrl is downloaded from that address. Pass commit=true to write.

Commits a previously previewed or freshly supplied Lingard vocabulary change. For AI-generated new cards, include all applicable useful fields except image by default: title, translate, pos, pron/ipa, syns, and examples with translations. For German/Romance nouns, include the dictionary article in title/word when needed, e.g. der Hund, die Reise, das Haus. Example text and example translation must highlight the target word/translated word with {}. form is not part of speech; use it only for the current inflected-form category, otherwise omit/null it. Do not write word+translation-only cards unless allowIncompleteCards=true was explicitly requested by the user. This is the tool that corrects existing cards: mergeMode:"overwrite_non_empty" replaces values that are already filled in and clearFields:["form"] clears a wrong grammatical form, so the user is asked to approve it. To only add new cards or fill empty fields, use lingard_add_words_to_collection or lingard_fill_missing_card_fields.

Rewrites only the translation line of examples that already exist on Lingard cards; the example sentence, its {} highlights and its audio/typing markers are left exactly as they are. Use this when the user wants to change, add, or remove example translations — including leaving them empty, which is a supported card state, not an error. Read the current examples first with lingard_get_vocab_collection includeExamples:true, then send one `translations` entry per example, in order. Pass commit=true to write; without it the call returns the resulting examples as a preview.

Adds cards to an existing Lingard collection, deduplicating by normalized word title. Pass commit=true to write. Only collections with writable="full" accept new cards: curated Lingard collections are read-only and the unfiled bucket takes no new cards — create a collection with lingard_create_vocab_collection instead. By default every AI-generated card must include all applicable useful fields except image: title, translate, pos, pron/ipa, syns, and examples with translations. For German/Romance nouns, include the dictionary article in title/word when needed, e.g. der Hund, die Reise, das Haus. Example text and example translation must highlight the target word/translated word with {}. form is not part of speech; use it only for the current inflected-form category, otherwise omit/null it. Do not add word+translation-only cards unless the user explicitly requests sparse cards and allowIncompleteCards=true. It only adds: a word already in the collection gets its empty fields filled (mergeMode "fill_missing", the default) or is left alone ("add_only"); a value that is already filled in is never changed or cleared — use lingard_commit_vocab_changes for that.

Creates a Lingard vocabulary collection, optionally with initial cards. Pass commit=true to write. By default every AI-generated card must include all applicable useful fields except image: title, translate, pos, pron/ipa, syns, and examples with translations. For German/Romance nouns, include the dictionary article in title/word when needed, e.g. der Hund, die Reise, das Haus. Example text and example translation must highlight the target word/translated word with {}. form is not part of speech; use it only for the current inflected-form category, otherwise omit/null it. Do not create word+translation-only cards unless the user explicitly requests sparse cards and allowIncompleteCards=true.

Fills empty fields on existing Lingard cards. It never overwrites or clears a field that already has a value; to correct one — e.g. clear an incorrect grammatical form with clearFields:["form"] — use lingard_commit_vocab_changes. Works on the user's own collections and on the "Words not in a collection" bucket; curated Lingard collections are read-only because their content comes from the Lingard catalog. Pass commit=true to write.

Call this first whenever the user asks for their current Lingard learning context, English profile, vocabulary totals, saved collections, collection titles, card counts, or missing-field stats. Reads live Lingard Firestore data; do not answer from memory or generic Lingard history. Every collection reports `source`: "user" (made by the user), "catalog" (a curated Lingard collection — read-only, its words come from the Lingard catalog) and "unfiled" (the bucket of cards saved while reading, which belong to no collection). Never tell the user a collection is missing or that the account looks wrong just because they only recognise some of the titles.

Puts collections and sources on pause or takes them off it, for one language — e.g. "study only my Travel collection this week", "pause the news words", "resume everything". action: "pause" or "resume" the listed ones; "only" — resume the listed ones and pause every other collection and source of the language; "resume_all" — take every pause off (lists ignored). Name collections by uuid or exact title and sources by bookKey or exact title, as lingard_get_learning_pauses returns them. A paused item gives the automatic «Now learning» sessions no words and is not counted in goals or reminders; opening it in the app still studies it. Pass commit=true to write; without it the call returns a preview of the changes and the resulting state.

Use this after search, or when the user gives a Lingard resource URI such as lingard://learning-context/en. Fetches the full live Lingard JSON record from Firestore.

Returns live Lingard cards in a collection that are missing requested fields such as translation, POS, pronunciation, examples, or image. Use before filling missing fields. A curated Lingard collection always reports zero gaps: its words come from the Lingard catalog and are not the user's to fill.

Lists, for one language, the user's collections and sources (books, the news) and which of them are on pause. A collection or source on pause gives the automatic «Now learning» sessions no words — no new words and no reviews — and is not counted in the day's goals or reminders; opening it in the app still studies it as usual. Use this when the user asks what is paused or which collections they are studying, and before lingard_set_learning_pauses to get exact uuids, bookKeys and titles.

Returns live cards from one Lingard vocabulary collection by UUID or title, including curated Lingard collections and the "Words not in a collection" bucket of cards saved while reading. Use this when the user asks what words/cards are in a specific Lingard collection. Pass includeExamples:true to also read each card's example sentences and their translations — required before editing them.

Returns live Lingard profile level, topic, collection context, and existing words so the calling AI can suggest level-appropriate new cards without duplicates.

Previews a Lingard vocabulary collection/card change without writing to Firestore. For AI-generated new cards, include all applicable useful fields except image by default: title, translate, pos, pron/ipa, syns, and examples with translations. For German/Romance nouns, include the dictionary article in title/word when needed, e.g. der Hund, die Reise, das Haus. Example text and example translation must highlight the target word/translated word with {}. form is not part of speech; use it only for the current inflected-form category, otherwise omit/null it.

Use this when the user asks about their Lingard vocabulary, learning context, English profile, totals, collection titles, saved words, flashcards, or missing vocabulary fields. Returns live Lingard Firestore results; do not use generic memory or personal context instead.