practice slice 3B — the practice agents: partitioner, generator, grader

src/agent/subagents/practice.ts: createPracticeAgents(deps) with the
ExtractionModels mirror (per-stage engine overrides + engineFor +
providerKeyMissing + refuseIfStagesUnready, all three roles strong-tier).
Generator doctrine = the owner's problem-engineering framework verbatim
(minus Sources) + Part III wiring section per the green-lit amendments
(FULL SET input with minimal-use doctrine; degradation never in
meta-commentary). Partitioner: true-partition doctrine, validate via
chainCoverage + exactly-once + unknown-ids, error-back retries through
runSubmitAgent's new validate hook (ToolInputError → error tool result).
Generator: echo law (chains set === target). Grader: verdict union +
nonempty feedback (schema-enforced). renderChains/renderPropositions/
renderParams/renderPreviousProblems. BACKGROUND_MODEL_ROLES extended with
the practice trio (settings override symmetry). runSubmitAgent gains the
validate seam (null = accept). 16-test faux-engine suite incl. retry
paths, refusal gates, neverSubmitted.

tests/zero-keys.test.tsx

@@ -122,7 +122,16 @@ describe("the dictation keyless seam (owner dictation trio)", () => {
 const catalog = (strongProvider: string | null, ...keyedProviders: string[]): ModelCatalogResponse => ({
 	models: [],
 	defaults: null,
-	rolePins: { researcher: null, demoBuilder: null, visualMaker: null, extractor: null, auditor: null },
+	rolePins: {
+		researcher: null,
+		demoBuilder: null,
+		visualMaker: null,
+		extractor: null,
+		auditor: null,
+		partitioner: null,
+		problemGenerator: null,
+		grader: null,
+	},
 	slots: {
 		strong: strongProvider
 			? { model: { provider: strongProvider, id: `${strongProvider}/model` }, thinkingLevel: "low" }