Files
Jyotisha/frontend/tests/rectification-convergence-budget.test.ts
T

118 lines
4.0 KiB
TypeScript

import assert from "node:assert/strict";
import test from "node:test";
import { EFFECTIVE_ANSWER_SAFETY_CAP } from "../src/lib/birth-time-dynamic-stop-policy.ts";
import { DEFAULT_MAX_DISCRIMINATION_ROUNDS } from "../src/lib/rectification-agentic/core/types.ts";
import { decideRectification } from "../src/lib/rectification-agentic/core/rectification-decision.ts";
import { RECTIFICATION_POLICY } from "../src/lib/rectification-policy.ts";
import type { CandidateDiscriminatorProbe } from "../src/lib/rectification-agentic/core/candidate-contrast-packet.ts";
const PROBE: CandidateDiscriminatorProbe = {
probeId: "probe-1",
candidateSetVersion: "set-1",
question: "这件事更接近哪一种情况?",
expectedOutcomes: [
{
outcomeId: "yes",
supportsCandidateIds: ["05:00"],
conflictsCandidateIds: ["05:06", "05:07"],
},
{
outcomeId: "no",
supportsCandidateIds: ["05:06", "05:07"],
conflictsCandidateIds: ["05:00"],
},
],
candidateSplitHash: "05:00|05:06|05:07",
informationGain: 0.5,
sourceFeatures: [{ technique: "test", calculationResultId: null }],
domain: "career",
year: 2020,
semanticKey: "career.2020.test",
};
const BASE_INPUT = {
methodCoverageAll: true,
trainingGateOpen: true,
candidateScores: [
{ time: "05:00", score: 34 },
{ time: "05:06", score: 33 },
{ time: "05:07", score: 33 },
],
discriminatorProbe: PROBE,
holdoutValidation: "unavailable" as const,
};
function decideWithBudget(budget: {
inferenceRounds?: number;
effectiveAnswerCount?: number;
plateauRounds?: number;
}) {
return decideRectification({ ...BASE_INPUT, ...budget });
}
test("every persisted discrimination budget terminates before asking another probe", () => {
for (const budget of [
{ inferenceRounds: DEFAULT_MAX_DISCRIMINATION_ROUNDS },
{ effectiveAnswerCount: EFFECTIVE_ANSWER_SAFETY_CAP },
{ plateauRounds: RECTIFICATION_POLICY.maxPlateauRounds },
]) {
const decision = decideWithBudget(budget);
assert.equal(decision.nextAction, "complete_with_range");
assert.equal(decision.sessionOutcome, "completed_with_range");
assert.notEqual(decision.nextAction, "ask_candidate_discriminator");
}
});
test("repeated declined or unsure answers reach the existing plateau terminal", () => {
const decision = decideWithBudget({
inferenceRounds: 0,
effectiveAnswerCount: RECTIFICATION_POLICY.maxPlateauRounds,
plateauRounds: RECTIFICATION_POLICY.maxPlateauRounds,
});
assert.equal(decision.nextAction, "complete_with_range");
assert.equal(decision.sessionOutcome, "completed_with_range");
});
test("exhausted discrimination still delivers the credible candidate range", () => {
const decision = decideWithBudget({
inferenceRounds: DEFAULT_MAX_DISCRIMINATION_ROUNDS,
effectiveAnswerCount: 0,
plateauRounds: 0,
});
assert.equal(decision.resultStatus, "completed_with_range");
assert.equal(decision.sessionOutcome, "completed_with_range");
assert.equal(decision.canOfferRange, true);
assert.equal(decision.canAdopt, true);
assert.deepEqual(decision.credibleRange, ["05:00", "05:07"]);
});
test("additional score evidence never widens the credible range", () => {
const before = decideRectification({
...BASE_INPUT,
candidateScores: [
{ time: "05:00", score: 34 },
{ time: "05:06", score: 33 },
{ time: "05:07", score: 33 },
],
inferenceRounds: DEFAULT_MAX_DISCRIMINATION_ROUNDS,
});
const after = decideRectification({
...BASE_INPUT,
candidateScores: [
{ time: "05:00", score: 42 },
{ time: "05:06", score: 33 },
{ time: "05:07", score: 33 },
],
inferenceRounds: DEFAULT_MAX_DISCRIMINATION_ROUNDS,
});
const width = (range: readonly [string, string] | null) => {
assert.ok(range);
const toMinutes = (time: string) => Number(time.slice(0, 2)) * 60 + Number(time.slice(3, 5));
return toMinutes(range[1]) - toMinutes(range[0]);
};
assert.ok(width(after.credibleRange) <= width(before.credibleRange));
});