@intellectif/lk-core 1.3.0 → 1.5.0

package/dist/ai-check.js

@@ -1,5 +1,5 @@
-import { D as checkAiCoaching, E as aiCoachingRequest, L as checkAiExplanation, M as aiExplanationRequest, P as aiHintRequest, R as checkAiHint, c as aiDraftsRequest, h as checkAiCritique, i as checkAiWritingFeedback, l as checkAiDrafts, m as aiCritiqueRequest, r as aiWritingFeedbackRequest } from "./ai-writing-CCBjTOM3.js";
-import { o as gradeReadAloud } from "./scoring-BZqUkuDF.js";
+import { A as checkAiCoaching, B as checkAiExplanation, F as aiExplanationRequest, L as aiHintRequest, V as checkAiHint, _ as aiCritiqueRequest, a as checkAiGrading, d as aiDraftsRequest, f as checkAiDrafts, i as aiGradingRequest, k as aiCoachingRequest, n as checkAiWritingFeedback, t as aiWritingFeedbackRequest, v as checkAiCritique } from "./ai-writing-D8PdhJJz.js";
+import { o as gradeReadAloud } from "./scoring-BKNNTz-s.js";
 //#region src/ai-check/cases.ts
 /**
 * The items the cases are built from. Small, ordinary language-course content
@@ -13,7 +13,13 @@ import { o as gradeReadAloud } from "./scoring-BZqUkuDF.js";
 * - a passage with more than one blank, so a hint can be about the wrong one;
 * - a short essay whose mistakes a model must quote exactly as the learner
 *   wrote them — straight apostrophes a model likes to curl, a mistake made
-*   twice — so a correction of words nobody wrote is caught.
+*   twice — so a correction of words nobody wrote is caught;
+* - questions in item groups: a reading passage that prints a question's
+*   answer, which a hint must point to without quoting, and a run of blanks
+*   whose instructions only the group states;
+* - essays to grade on a rubric of three criteria, two judged on levels and
+*   one on a score, so a grade that drops a criterion or leaves a scale is
+*   caught.
 */
 const capital = {
 	schemaVersion: "1.0",
@@ -94,6 +100,86 @@ const listening = {
 	title: "Listen and type",
 	transcript: "The train leaves at half past nine."
 };
+/**
+* A reading group: a passage, a question it answers word for word, and a
+* summary of it. The question's answer is printed in the passage, so a hint
+* that quotes the passage where it answers is refused.
+*/
+const TIDES = "Along most coasts the tide comes in twice a day. It is pulled by the moon: as the Earth turns, the ocean nearest the moon bulges towards it, and so does the ocean on the far side. The highest tides, called spring tides, come when the sun and the moon line up.";
+const springTides = {
+	schemaVersion: "1.0",
+	type: "multiple-choice",
+	id: "ai-check-tides",
+	title: "Spring tides",
+	question: "When do the highest tides come?",
+	mode: "single",
+	scoringStrategy: "all-or-nothing",
+	options: [
+		{
+			id: "line-up",
+			text: "When the sun and the moon line up",
+			isCorrect: true
+		},
+		{
+			id: "full-moon",
+			text: "Only at full moon",
+			isCorrect: false
+		},
+		{
+			id: "winter",
+			text: "In winter",
+			isCorrect: false
+		}
+	]
+};
+const tidesSummary = {
+	schemaVersion: "1.0",
+	type: "written-response",
+	id: "ai-check-tides-summary",
+	title: "Summary",
+	prompt: "Summarise the text in one or two sentences.",
+	minWords: 10,
+	maxWords: 60,
+	languageTarget: "en-B1"
+};
+const tides = {
+	schemaVersion: "1.0",
+	type: "item-group",
+	id: "ai-check-tides-group",
+	title: "Part 2 — Reading",
+	stimulus: {
+		id: "ai-check-tides-text",
+		kind: "text",
+		title: "Tides",
+		body: TIDES
+	},
+	items: [springTides, tidesSummary]
+};
+/** A part whose questions share instructions the questions themselves never state. */
+const formation = {
+	schemaVersion: "1.0",
+	type: "fill-in-the-blanks",
+	id: "ai-check-formation",
+	title: "Word formation",
+	passage: "She smiled {{a}} when she heard the news. (HAPPY)",
+	blanks: [{
+		id: "a",
+		acceptedAnswers: ["happily"]
+	}],
+	scoringStrategy: "all-or-nothing"
+};
+const formationPart = {
+	schemaVersion: "1.0",
+	type: "item-group",
+	id: "ai-check-formation-part",
+	title: "Part 1 — Word formation",
+	stimulus: {
+		id: "ai-check-formation-instructions",
+		kind: "text",
+		body: "Use the word in capitals at the end of each sentence to form a word that fits the gap."
+	},
+	items: [formation]
+};
 const weekend = {
 	schemaVersion: "1.0",
 	type: "written-response",
@@ -121,6 +207,117 @@ const weekend = {
 		}
 	] }
 };
+/**
+* The weekend task set as an exam question: graded on three criteria, two on
+* levels and one on a score. Three, so a prompt that names only the ones it
+* expects drops one; two scales, so a grade must keep to each.
+*/
+const weekendExam = {
+	schemaVersion: "1.0",
+	type: "written-response",
+	id: "ai-check-writing-exam",
+	title: "Your weekend",
+	prompt: "Write a few sentences about what you did last weekend.",
+	minWords: 15,
+	maxWords: 120,
+	languageTarget: "en-A2",
+	rubric: { criteria: [
+		{
+			name: "Task",
+			description: "Says what the learner did last weekend, in order",
+			weight: 1,
+			levels: [
+				{
+					label: "Not met",
+					description: "Not about last weekend"
+				},
+				{
+					label: "Partly met",
+					description: "About the weekend, but thin or out of order"
+				},
+				{
+					label: "Met",
+					description: "Says what they did, in order"
+				}
+			]
+		},
+		{
+			name: "Grammar",
+			description: "Past tenses, articles, agreement",
+			weight: 2,
+			levels: [
+				{
+					label: "Limited",
+					description: "Errors in most sentences, some blocking meaning"
+				},
+				{
+					label: "Basic",
+					description: "Frequent errors in past tenses and articles"
+				},
+				{
+					label: "Good",
+					description: "Some errors, none that blocks meaning"
+				},
+				{
+					label: "Very good",
+					description: "Past tenses, articles and agreement almost always right"
+				}
+			]
+		},
+		{
+			name: "Vocabulary",
+			description: "Everyday words, used correctly",
+			weight: 1
+		}
+	] }
+};
+/** The tides summary set as an exam question, graded against its group's passage. */
+const tidesSummaryExam = {
+	schemaVersion: "1.0",
+	type: "written-response",
+	id: "ai-check-tides-summary-exam",
+	title: "Summary",
+	prompt: "Summarise the text in one or two sentences.",
+	minWords: 10,
+	maxWords: 60,
+	languageTarget: "en-B1",
+	rubric: { criteria: [{
+		name: "Content",
+		description: "What the text says, and nothing it does not",
+		weight: 2,
+		levels: [
+			{
+				label: "Wrong",
+				description: "Misstates what the text says"
+			},
+			{
+				label: "Partly right",
+				description: "Gets one of its points wrong, or leaves it out"
+			},
+			{
+				label: "Right",
+				description: "States its points as the text does"
+			}
+		]
+	}, {
+		name: "Language",
+		description: "Clear sentences, in the learner's own words",
+		weight: 1
+	}] }
+};
+const tidesExam = {
+	schemaVersion: "1.0",
+	type: "item-group",
+	id: "ai-check-tides-exam",
+	title: "Part 2 — Reading",
+	stimulus: {
+		id: "ai-check-tides-exam-text",
+		kind: "text",
+		title: "Tides",
+		body: TIDES
+	},
+	items: [springTides, tidesSummaryExam]
+};
 const weather = {
 	schemaVersion: "1.0",
 	type: "read-aloud",
@@ -363,10 +560,11 @@ const READ_ALOUD_SETTINGS = {
 	}] }
 };
 /** Builds a case, failing loudly rather than shipping a case with no request. */
-function explanationCase(id, about, data, response) {
+function explanationCase(id, about, data, response, group) {
 	const request = aiExplanationRequest({
 		data,
-		response
+		response,
+		...group ? { group } : {}
 	});
 	if (request === null) throw new Error(`ai-check: no explanation request for "${id}"`);
 	return {
@@ -376,11 +574,12 @@ function explanationCase(id, about, data, response) {
 		request
 	};
 }
-function hintCase(id, about, data, response, previousHints = []) {
+function hintCase(id, about, data, response, previousHints = [], group) {
 	const request = aiHintRequest({
 		data,
 		response,
-		previousHints
+		previousHints,
+		...group ? { group } : {}
 	});
 	if (request === null) throw new Error(`ai-check: no hint request for "${id}"`);
 	return {
@@ -390,11 +589,12 @@ function hintCase(id, about, data, response, previousHints = []) {
 		request
 	};
 }
-function writingCase(id, about, text, previousFeedback = [], learnerLocale) {
+function writingCase(id, about, text, previousFeedback = [], learnerLocale, task = { data: weekend }) {
 	const request = aiWritingFeedbackRequest({
-		data: weekend,
+		data: task.data,
 		response: drafted(text),
 		previousFeedback,
+		...task.group ? { group: task.group } : {},
 		...learnerLocale !== void 0 ? { learnerLocale } : {}
 	});
 	if (request === null) throw new Error(`ai-check: no writing feedback request for "${id}"`);
@@ -405,6 +605,21 @@ function writingCase(id, about, text, previousFeedback = [], learnerLocale) {
 		request
 	};
 }
+function gradingCase(id, about, text, extra = {}) {
+	const built = aiGradingRequest({
+		data: extra.data ?? weekendExam,
+		response: drafted(text),
+		...extra.group ? { group: extra.group } : {},
+		...extra.learnerLocale !== void 0 ? { learnerLocale: extra.learnerLocale } : {}
+	});
+	if (!built.ok) throw new Error(`ai-check: no grading request for "${id}": ${built.problem}`);
+	return {
+		id,
+		feature: "grading",
+		about,
+		request: built.request
+	};
+}
 function coachingCase(id, about, marks, learnerLocale) {
 	const assessment = marks.assessment ?? forecast(true);
 	const grade = gradeReadAloud(weather, {
@@ -441,8 +656,9 @@ function coachingCase(id, about, marks, learnerLocale) {
 /**
 * The cases {@link runAiCheck} runs: every type the SDK explains, answered
 * right, wrong and — where a type can be — partly right; every type it hints
-* for, before an answer and after a wrong one; and drafts of an essay, with
-* mistakes, without, and revised.
+* for, before an answer and after a wrong one; drafts of an essay, with
+* mistakes, without, and revised; and essays to grade, on the task, with
+* mistakes to quote, off the task, and against a passage.
 *
 * They are ordinary calls. What makes them a test is that the SDK knows the
 * answer to each, so it can check what your model writes about it.
@@ -477,6 +693,7 @@ function aiCheckCases() {
 		})),
 		explanationCase("dictation-near", "Typed the sentence with two words wrong", listening, wrote("The train leaves at half past five")),
 		explanationCase("dictation-correct", "Typed the sentence correctly", listening, wrote("The train leaves at half past nine.")),
+		explanationCase("mc-reading-wrong", "Chose 'Only at full moon', on a question about its group's passage", springTides, chose(["full-moon"]), tides),
 		hintCase("mc-hint-1", "Has not answered yet", capital, chose([])),
 		hintCase("mc-hint-2", "Asked again after choosing Seville", capital, chose(["seville"]), ["Think about where the government sits."]),
 		hintCase("fib-hint-1", "Both blanks empty", introduction, typed({})),
@@ -486,10 +703,16 @@ function aiCheckCases() {
 		}), ["Look again at the first blank."]),
 		hintCase("gap-hint-1", "Neither gap chosen, in Spanish", landscape, picked({})),
 		hintCase("gap-hint-2", "Asked again with the first gap wrong", landscape, picked({ g1: "campo" }), ["Piensa en la forma del terreno."]),
+		hintCase("mc-reading-hint", "Has not answered a question whose answer its group's passage prints", springTides, chose([]), [], tides),
+		hintCase("fib-formation-hint", "A word-formation blank, under the instructions its group gives", formation, typed({}), [], formationPart),
 		writingCase("writing-mistakes", "A first draft with tense, article and agreement mistakes", "Last weekend I go to the market and buyed a apple. My friends was there too, so we don't go home early. Then I go to the cinema."),
 		writingCase("writing-clean", "A first draft with no mistakes to correct", "Last weekend I went to the market and bought an apple. My friends were there too, so we stayed until the evening. Then we went to the cinema."),
 		writingCase("writing-revised", "A second draft that fixed some mistakes", "Last weekend I went to the market and bought a apple. My friends was there too, so we didn't go home early.", ["Check your past tenses: \"go\" and \"buyed\" should be past forms."]),
 		writingCase("writing-feedback-in-spanish", "A first draft, with feedback asked for in Spanish", "Last weekend I visit my grandmother. She cook a big lunch and we eat together in the garden.", [], "es"),
+		writingCase("writing-summary", "A summary of its group's passage that gets the spring tides wrong", "The tide comes in twice a day because the moon pulls the ocean. The highest tides come only at full moon.", [], void 0, {
+			data: tidesSummary,
+			group: tides
+		}),
 		coachingCase("coaching-slips", "A reading with a mispronounced \"th\" and a word left out", { assessment: forecast(true) }),
 		coachingCase("coaching-clean", "A reading the engine marked correct throughout", { assessment: forecast(false) }),
 		coachingCase("coaching-from-grade", "The same slips, from a stored grade: marks without sounds", { fromGradeOnly: true }),
@@ -558,7 +781,15 @@ function aiCheckCases() {
 			locale: "en",
 			instructions: "Focus on what Maria and her grandmother buy.",
 			settings: { "read-aloud": READ_ALOUD_SETTINGS }
-		})
+		}),
+		gradingCase("grading-on-task", "An essay that does the task, with one slip in its tenses", "Last weekend I went to the market with my sister and we bought some apples. In the afternoon we watched a film at home, and on Sunday I visit my grandmother."),
+		gradingCase("grading-mistakes", "An essay with tense, article and agreement mistakes, each to quote as written", "Last weekend I go to the market and buyed a apple. My friends was there too, so we don't go home early. Then I go to the cinema."),
+		gradingCase("grading-off-task", "An essay about something other than last weekend", "My favourite food is pizza. I like it with cheese and tomato, and I eat it every Friday with my family at a small restaurant near our house."),
+		gradingCase("grading-summary", "A summary graded against its group's passage, getting the spring tides wrong", "The tide comes in twice a day because the moon pulls the ocean. The highest tides come only at full moon.", {
+			data: tidesSummaryExam,
+			group: tidesExam
+		}),
+		gradingCase("grading-in-spanish", "The essay with mistakes, with comments asked for in Spanish", "Last weekend I go to the market and buyed a apple. My friends was there too, so we don't go home early. Then I go to the cinema.", { learnerLocale: "es" })
 	];
 }
 //#endregion
@@ -587,6 +818,7 @@ function aiCheckCases() {
 *   pronunciationCoaching: (request) => callMyModel(COACHING_PROMPT, request),
 *   critique: (request) => callMyModel(CRITIQUE_PROMPT, request),
 *   drafts: (request) => callMyModel(DRAFTS_PROMPT, request),
+*   grading: (request) => callMyModel(GRADING_PROMPT, request),
 * });
 * console.log(formatAiCheckReport(report));
 * if (report.refused > 0 || report.errors > 0) {
@@ -599,18 +831,27 @@ function aiCheckCases() {
 * to take most seriously — that prompt gives answers away. Next come
 * `misquotes-answer` on a writing case — that prompt corrects words the learner
 * never wrote — and `contradicts-marks` on a coaching case: that prompt coaches
-* words the engine heard as right, or sounds it never reported.
+* words the engine heard as right, or sounds it never reported. On a grading
+* case, `misses-criteria` and `out-of-scale` mean a grade nobody can use: one
+* that leaves a criterion out grades a different task, and one off a
+* criterion's scale grades on a scale the author did not write.
+*
+* A grading case the SDK accepts is a reply of the right shape, not a right
+* grade: whether a model grades as your teachers do is what a calibration
+* measures (`calibrationReport`), on your own responses.
 */
-const REFUSALS = [
-	"malformed",
-	"empty",
-	"too-long",
-	"contradicts-grade",
-	"reveals-answer",
-	"misquotes-answer",
-	"contradicts-marks",
-	"contradicts-item"
-];
+const REFUSALS = Object.keys({
+	malformed: true,
+	empty: true,
+	"too-long": true,
+	"contradicts-grade": true,
+	"reveals-answer": true,
+	"misquotes-answer": true,
+	"contradicts-marks": true,
+	"contradicts-item": true,
+	"misses-criteria": true,
+	"out-of-scale": true
+});
 /** The port a case is for. */
 function portFor(ports, one) {
 	switch (one.request.feature) {
@@ -619,6 +860,7 @@ function portFor(ports, one) {
 		case "pronunciation-coaching": return ports.pronunciationCoaching;
 		case "item-critique": return ports.critique;
 		case "draft-generation": return ports.drafts;
+		case "grading": return ports.grading;
 		default: return ports.writingFeedback;
 	}
 }
@@ -641,6 +883,15 @@ async function runCase(ports, one) {
 		};
 	}
 	const ms = now() - started;
+	if (one.request.feature === "grading") {
+		const checked = checkAiGrading(raw, one.request);
+		return checked.ok ? {
+			case: one,
+			ok: true,
+			grading: checked.judgement,
+			ms
+		} : refused(one, raw, checked.refusal, ms);
+	}
 	if (one.request.feature === "draft-generation") {
 		let next = 0;
 		const checked = checkAiDrafts(raw, one.request, { newId: () => {