explain refinements: no opt-out row, one committed field (owner 2026-09-27)

Two follow-up rulings on the explain tool:

1. No 'I don't know' row — not needed in free recall. If he doesn't
   know, he says so in his own words; his text is the only answer
   channel. Dock: text mode is rowless again (the composer IS the
   surface); doctrine and the shared prompt chunk updated; the format
   branch and card revert to quiz-only dontKnow.

2. explanation + correctAnswer collapse into ONE field — the separate
   explanation was quiz remnant (MC needs the why outside its options;
   a free-text commitment carries its own reasoning). Schema is now
   {question, correctAnswer, details?}; the reveal shows the single
   committed answer; no explanation snapshots anywhere on the explain
   path.

1047/1047 tests, typecheck/lint/build green.

src/agent/prompts/shared/20-question-tools.md

@@ -4,9 +4,8 @@ Two instruments. The quiz tool (its exact name depends on the quizzing mechanic
 
 ### Quiz checks — shared doctrine
 
-- `explanation` (required) says why the correct answer is correct. It comes BEFORE `correctAnswer` in the call by design: reason it out first, then commit to the answer the reasoning supports.
-- An "I don't know" choice is always available to the learner — never author your own opt-out. A dontKnow result is a genuine gap, not a wrong answer.
-- Answers may carry a free-text `note` — read it; it says what he was thinking.
+- Multiple choice carries a separate `explanation` (why the correct option is correct, written BEFORE `correctAnswer`: reason it out first, then commit). Free recall has ONE field — `correctAnswer`, the committed answer with its reasoning inside.
+- Option-style answers may carry a free-text `note` — read it; it says what he was thinking.
 - ONE question per turn: ask, then end your turn — his answer determines the next.
 
 ### `ask_user_question`

src/agent/tools.ts

@@ -113,12 +113,11 @@ const QUIZ_OPTION_CRAFT =
  *  the teach variant appends the nodeId tagging paragraph. */
 const EXPLAIN_DOCTRINE =
 	"Ask the learner to EXPLAIN something in his own words — a graded check with NO options: he types a free-text " +
-	"answer. Unlike ask_user_question (no right answer), explain always has one. THE COMMITMENT RULE: write " +
-	"explanation (your reasoning) first, then correctAnswer — the FULL correct answer, committed before he ever sees " +
-	"the question. When his answer returns, grade it strictly against your committed answer in your reply: never " +
+	"answer. Unlike ask_user_question (no right answer), explain always has one. THE COMMITMENT RULE: write correctAnswer — the FULL " +
+	"correct answer in your own words, reasoning included — committed before he ever sees the question. When his answer returns, grade it strictly against your committed answer in your reply: never " +
 	"revise the commitment after seeing his words, and never mark a wrong answer right to be kind — a near-miss is " +
-	"partial understanding; name exactly what he got and what he missed. He sees the committed answer and the " +
-	"explanation on submit. An 'I don't know' choice is always available to him — a genuine gap, not a wrong answer. " +
+	"partial understanding; name exactly what he got and what he missed. He sees the committed answer on submit. If he genuinely doesn't know, he says so in his own words — that is a genuine " +
+	"gap, not a wrong answer. " +
 	"ONE question per turn: call a single explain, then end your turn — his answer determines the next.";
 
 export const probeQuizTool: AgentTool<typeof probeQuizInputSchema> = {

src/core/question-core.ts

@@ -224,26 +224,22 @@ export const probeQuizInputSchema = quizInputBase;
 // correct answer BEFORE posing (the commitment rides the persisted call
 // args, is revealed to the learner on submit, and is restated in the answer
 // result the model grades against; the client never grades free text).
-// Mechanics doctrine lives in the TOOL DESCRIPTIONS (owner ruling
-// 2026-09-27: pi-native — doctrine travels with the armed tool), not in
-// the system prompt.
+// ONE committed answer, reasoning included (owner ruling 2026-09-27: the
+// separate explanation field was quiz remnant — collapsed away).
+// Mechanics doctrine lives in the TOOL DESCRIPTIONS (pi-native ruling),
+// not in the system prompt.
 
 export const explainInputBase = Type.Object({
 	question: Type.String({
 		description:
 			"The single question to ask. ONE question per turn: ask, then end your turn — the answer determines the next.",
 	}),
-	explanation: Type.String({
-		description:
-			"REQUIRED. Explanation revealed AFTER the learner answers (shown however he did). It is written BEFORE " +
-			"correctAnswer by design: reason it out first, then commit to the answer the reasoning supports.",
-	}),
 	correctAnswer: Type.String({
 		description:
-			"REQUIRED. The full correct answer in your own words — COMMITTED before the learner ever sees the question. " +
-			"The commitment is immutable: when his answer returns, grade it strictly against this text — never revise the " +
-			"commitment after seeing his words, and never mark a wrong answer right to be kind. Both this and the explanation " +
-			"are shown to him on submit; your next reply grades the nuance of what he wrote.",
+			"REQUIRED. The full correct answer in your own words, reasoning included — COMMITTED before the learner " +
+			"ever sees the question. The commitment is immutable: when his answer returns, grade it strictly against this " +
+			"text — never revise the commitment after seeing his words, and never mark a wrong answer right to be kind. " +
+			"It is shown to him on submit; your next reply grades the nuance of what he wrote.",
 	}),
 	details: Type.Optional(
 		Type.String({ description: "Optional extra context or instructions shown under the question." }),
@@ -338,6 +334,7 @@ export interface QuestionData {
 	correctIndices?: number[];
 	// explain only. NEVER send to the client before answering:
 	committedAnswer?: string;
+	// quiz only (the MC "why"). NEVER send to the client before answering:
 	explanation?: string;
 	createdAt: string;
 }
@@ -356,7 +353,7 @@ export interface QuestionAnswerData {
 	correct?: boolean; // quiz only
 	correctIndices?: number[]; // quiz only (rendering)
 	committed?: string; // explain only (rendering): the model's committed answer
-	explanation?: string; // quiz/explain only (rendering)
+	explanation?: string; // quiz only (rendering)
 	dismissed?: boolean;
 	answeredAt: string;
 }
@@ -595,9 +592,8 @@ export function buildAnswer(qd: QuestionData, req: AnswerRequest): QuestionAnswe
 	}
 	if (qd.kind === "explain") {
 		// No client grading — the model grades in its reply, against the
-		// commitment. Snapshots ride along for the reveal + rendering.
+		// commitment. The commitment snapshots for the reveal + rendering.
 		base.committed = qd.committedAnswer;
-		base.explanation = qd.explanation;
 	}
 	return base;
 }
@@ -627,13 +623,9 @@ export function formatAnswerMessage(ad: QuestionAnswerData): string {
 		}
 		lines.push(`Correct: ${correctStr}`);
 	} else if (ad.kind === "explain") {
-		if (ad.dontKnow) {
-			lines.push(
-				`The learner selected "I don't know" — they did NOT attempt an answer (a genuine knowledge gap, not a wrong guess).`,
-			);
-		} else {
-			lines.push(`The learner answered: ${ad.text ?? "(no answer)"}`);
-		}
+		// No opt-out row on explain (owner ruling 2026-09-27): if he doesn't
+		// know, he says so in his own words — his text is all there is.
+		lines.push(`The learner answered: ${ad.text ?? "(no answer)"}`);
 		if (ad.committed) {
 			lines.push(`Your committed correct answer (immutable — grade against it, never revise it): ${ad.committed}`);
 		}