tools: the standard argument heal — every registry, both seams

The whitehead incident (2026-10-09): glm-5.3 emitted quiz type with
quotes baked in ('"predict"') — rejected ten times, byte-identical
retries, the lesson never started — and correctAnswer with the JSON
key-value colon glued on ([':parmenides']). Third GLM wobble incident,
and each prior heal was wired only where its incident landed; this one
landed precisely where the practice heal never reached.

Layer 1 — healEncodedArguments moves to core/argument-heal (the display
seam needs it too — the tool-parts law) with withArgumentHeal +
healToolRecord (agent/tools/heal) wired at EVERY registry: prober,
teacher, practice, bareQuestionTools (it had no prepareArguments at
all), demo-builder, and submit-agent (composing after
healStringifiedArrays; the auditor's extraTools wrapped).

Layer 2 — stripModelValueDebris (core/value-debris): leading/trailing
colons, quotes, backticks, whitespace strip at the MEMBERSHIP seams —
coerceCorrectAnswer (boundary check + display + grading in one),
normalizeQuizType (persisted wobbled records keep their role),
resolveTargetId (copy-syntax on targets).

Layer 3 — schema description hygiene: the quiz type and practice
mode/outcome/rung/missClass values now read as bare words — the quoted
JSON-key style invited quote-copying.

Display mirror — parseQuizInput heals the raw record on read, so a
boundary-healed quiz whose record keeps raw args renders instead of
becoming an invisible pending quiz (learner lockout).

Pins: tests/tool-heal.test.ts (the incident shapes end-to-end through
pi-ai validation, the wiring, the strips, the mirror). The stringy-
options pins flip to boundary-parity per tool-parts' own law; the
chat-flow garbage pin keeps its honest-reject intent with an unhealable
shape. 1471 tests, typecheck, lint green.

tests/chat-flow.test.ts

@@ -689,20 +689,20 @@ describe("teacher chat flow (scripted model)", () => {
 		assert.deepEqual(pending?.input, QUIZ_INPUT);
 	});
 
-	it("a structurally invalid quiz (the live double-encoded options string) never reaches the dock and retries clean", async () => {
-		// The exact live modal-realism crash shape: GLM occasionally serializes
-		// a nested array as a JSON STRING inside the arguments. The structural
-		// layer (JSON Schema: options must be array) rejects the call at the
-		// boundary — it must surface as tool-input-error, never as a pending
-		// question, and the model's retry must become the pending quiz.
+	it("structurally invalid quiz input (unhealable garbage) never reaches the dock and retries clean", async () => {
+		// The two-tier world (owner, 2026-10-09 — the universal argument
+		// heal): a JSON-ENCODED stand-in for the schema shape (the live
+		// string-options habit) now heals at EVERY registry — see
+		// tests/tool-heal.test.ts for that pin — so the structural reject
+		// this test holds is the OTHER tier: garbage no mechanical rule
+		// could rescue (not JSON, not an array) rejects honestly at the
+		// boundary — tool-input-error, never a pending question — and the
+		// model's clean retry becomes the pending quiz.
 		const STRINGY_QUIZ_INPUT = {
 			question: "Lewis's indexical analysis of 'actual' — which is it?",
 			type: "check",
 			nodeId: "indexicals",
-			options: JSON.stringify([
-				{ label: "Like 'I'", value: "indexical" },
-			{ label: "Like a title", value: "unique" },
-			]), // ← the bug: a string, not an array
+			options: "definitely not a JSON array — denim all the way down", // ← unhealable garbage
 			correctAnswer: "indexical",
 			explanation: "Indexical: every world is actual to its own inhabitants.",
 		};