practice: slim the tool schemas — the modelSolution IS the reveal

Owner round (2026-10-05): the problem pose only really needs statement,
mode, target, modelSolution; conclude needs no reveal field.

- problemInputObject drops decisionPoints, expectedWrongMoves, strategy,
  rationale. Halves the pose payload (the GLM incident's failing args
  were 3.3KB — a direct weak-model hardening).
- concludeInputObject drops solutionReveal: the reveal is the
  modelSolution committed at pose time, shown verbatim at conclude.
- Doctrine pass (00-base mechanics, 10-doctrine V.4/V.5): the commitment
  is the solution alone; the reveal instruction points at it.

Fixtures slimmed to the new shapes (flow, agents, heal). ConcludeCard's
render of legacy solutionReveal input stays until the card redesign
lands (Slice C).

tests/practice-agents.test.ts

@@ -76,16 +76,11 @@ const PROBLEM_INPUT = {
 	mode: "recall",
 	target: ["parity-sum"],
 	modelSolution: "Pair them; each pair is even.",
-	decisionPoints: ["pairing move"],
-	expectedWrongMoves: [{ move: "induction", resolution: "pairing is direct" }],
-	strategy: "near-twin surfaces",
-	rationale: "weakest target, undemonstrated recall",
 } as const;
 
 const CONCLUDE_INPUT = {
 	outcome: "solved",
 	verdict: "Clean — the pairing came unaided.",
-	solutionReveal: "Pair them; each pair is even.",
 	rung: null,
 	missClass: null,
 	retest: false,