free-recall explain tool: the quizzing-mechanic switch (owner 2026-09-27)

Sycophancy mitigation as a structural commitment: the model writes its
full correctAnswer (plus explanation, in that order) BEFORE the learner
sees the question; the commitment rides the persisted call args, is
revealed on submit, and grades his free text in the model's next reply —
the client never grades free recall.

- tools.explain setting (segmented 'Quizzing — Multiple choice | Free
  recall' in Agent settings' Tools group): free arms explain and drops
  quiz for BOTH agents (prober variant carries no nodeId, same pattern
  as the probe quiz); mechanics keys never pass filterEnabledTools —
  quiz stays unwritable (the 2026-09-19 wedge ruling stands)
- doctrine lives pi-natively in the tool descriptions (owner ruling —
  no conditional system-prompt chunks): explain carries the commitment
  rule; the MC option-building craft moved out of the prompt into the
  quiz description; shared/20-question-tools.md slims to the
  quiz-agnostic core
- display seams: parseExplainInput (LaTeX-debris restoration included),
  dock text-mode with an 'I don't know' row (kbd row 0), AnsweredCard
  reveal (The answer / Why, no verdict chips), [Explain answer] format
- phases/plan seams recognize both quizzing tools' nodeId tags; explain
  answers deliberately feed no ledger evidence (no client grading to
  key on — a future ruling can parse the model's grade)

1049/1049 tests, typecheck/lint/build green.

tests/plan-tree.test.ts

@@ -405,3 +405,47 @@ describe("derivePlanStatuses (the map tracks position, not completion)", () => {
 		assert.equal(derivedNodeStatus(later, "c"), "upcoming");
 	});
 });
+
+// ─── the explain mechanic derives position identically (owner 2026-09-27) ──
+
+describe("derivePlanStatuses: tagged explain calls move the map like quiz calls", () => {
+	const tree: PlanTree = {
+		nodes: [
+			{ id: "a", title: "A" },
+			{ id: "b", title: "B" },
+		],
+		edges: [{ from: "a", to: "b" }],
+		version: 1,
+	};
+	const explainPart = (nodeId: string | undefined) => ({
+		type: "tool-explain",
+		state: "output-available",
+		input: nodeId === undefined ? {} : { nodeId },
+	});
+	type Part = { type: string; state: string; input: unknown; output?: unknown };
+	const msg = (...parts: Part[]) => ({ parts });
+
+	it("a tagged explain call is the current position; earlier ones are visited", () => {
+		const st = derivePlanStatuses(tree, [
+			msg(explainPart("a")),
+			msg(explainPart("b")),
+		]);
+		assert.equal(st.current, "b");
+		assert.deepEqual([...st.visited], ["a"]);
+	});
+
+	it("untagged explain calls move nothing", () => {
+		const st = derivePlanStatuses(tree, [msg(explainPart(undefined))]);
+		assert.equal(st.current, null);
+		assert.equal(st.visited.size, 0);
+	});
+
+	it("mixed mechanics (an old quiz record, then an explain) still derive one run", () => {
+		const st = derivePlanStatuses(tree, [
+			msg({ type: "tool-quiz", state: "output-available", input: { nodeId: "a" } }),
+			msg(explainPart("b")),
+		]);
+		assert.equal(st.current, "b");
+		assert.deepEqual([...st.visited], ["a"]);
+	});
+});