Build the prose-vs-Workflow bake-off machinery for /trekreview Phase 5-6 and
run a 1-run/arm smoke to de-risk before the full measurement (operator posture:
build + smoke, then pause for go/no-go on the full >=3-runs/arm run).
New:
- lib/review/fidelity-diff.mjs (+ tests) — the PRIMARY metric: parse two
review.md (or two structured arm outputs) and compare verdict + jaccard over
(file,line,rule_key)-IDs + per-finding severity/rule_key. Reuses jaccard +
frontmatter + NW1 findings-schema + finding-id. fidelityDiffStructured avoids
rendering review.md per run.
- scripts/trekreview-armB.workflow.mjs — Arm B: Phase 5-6 as a Workflow
(parallel([conformance, correctness]) schema-forced -> JS dedup-by-triplet ->
agent(review-coordinator) verdict schema). Path-based input via args (reviewers
carry Read). Inlines dedup + the 12-key rule_key enum (scripts have no imports).
- tests/fixtures/bakeoff/ — committable fixture: real diff of b149538 (NW1) +
brief reconstructed from plan S9. Both arms review the same pinned input.
- docs/T2-bakeoff-results.md — smoke results + verdict + go/no-go recommendation.
Smoke result: SMOKE PASS. Arm B runs the full pipeline (3 agents) with ZERO
classifier interference; fidelity EQUIVALENT to Arm A at the verdict level
(both ALLOW; jaccard 1.0). Caveat: the clean TDD'd fixture yielded ~0 findings,
so finding-SET fidelity was not stressed (only verdict fidelity proven). A
reviewer-level divergence appeared (Arm B raised 1 raw finding, coordinator
filtered it; Arm A raised 0) — to be quantified in the full run on a
richer-finding-surface fixture. NOT the T2 §5 POSITIVE/NEGATIVE verdict.
Suite 647 -> 662 (660 pass / 2 skip / 0 fail; +15 fidelity-diff). claude plugin
validate clean (known root-CLAUDE.md warning only). Plan: docs/W1-narrow-wins-plan.md S10.
Co-Authored-By: Claude Opus 4.8 (1M context) <noreply@anthropic.com>
Claude-Session: https://claude.ai/code/session_01LqBYc8Ltrk7LipyJmGxXiB
165 lines
6.7 KiB
JavaScript
165 lines
6.7 KiB
JavaScript
import { test } from 'node:test';
|
|
import { strict as assert } from 'node:assert';
|
|
import { readFileSync } from 'node:fs';
|
|
import { join, dirname } from 'node:path';
|
|
import { fileURLToPath } from 'node:url';
|
|
import {
|
|
parseReviewArtifact,
|
|
fidelityDiff,
|
|
fidelityDiffStructured,
|
|
normalizeArmOutput,
|
|
} from '../../lib/review/fidelity-diff.mjs';
|
|
import { computeFindingId } from '../../lib/parsers/finding-id.mjs';
|
|
|
|
const HERE = dirname(fileURLToPath(import.meta.url));
|
|
const ROOT = join(HERE, '..', '..');
|
|
|
|
function fixture(name) {
|
|
return readFileSync(join(ROOT, 'tests/fixtures/trekreview', name), 'utf-8');
|
|
}
|
|
|
|
const RUN_A = fixture('review-run-A.md');
|
|
const RUN_B = fixture('review-run-B.md');
|
|
|
|
// ---- parseReviewArtifact ----------------------------------------------------
|
|
|
|
test('parseReviewArtifact — extracts verdict + finding IDs from frontmatter', () => {
|
|
const a = parseReviewArtifact(RUN_A);
|
|
assert.equal(a.verdict, 'WARN');
|
|
assert.ok(Array.isArray(a.findingIds));
|
|
assert.equal(a.findingIds.length, 5);
|
|
for (const id of a.findingIds) assert.match(id, /^[0-9a-f]{40}$/);
|
|
});
|
|
|
|
test('parseReviewArtifact — extracts per-finding details from trailing JSON', () => {
|
|
const a = parseReviewArtifact(RUN_A);
|
|
assert.ok(Array.isArray(a.details));
|
|
assert.equal(a.details.length, 5);
|
|
const blocker = a.details.find((d) => d.severity === 'BLOCKER');
|
|
assert.ok(blocker);
|
|
// fixtures use the key "rule"; real reviewer output uses "rule_key" — both accepted
|
|
assert.equal(blocker.rule_key, 'UNIMPLEMENTED_CRITERION');
|
|
assert.equal(blocker.file, 'lib/handlers/login.mjs');
|
|
assert.equal(blocker.line, 23);
|
|
});
|
|
|
|
test('parseReviewArtifact — tolerates a missing trailing JSON block (details = [])', () => {
|
|
const noJson = '---\ntype: trekreview\nverdict: ALLOW\nfindings: []\n---\n\n# Review\n\nNo findings.\n';
|
|
const r = parseReviewArtifact(noJson);
|
|
assert.equal(r.verdict, 'ALLOW');
|
|
assert.deepEqual(r.findingIds, []);
|
|
assert.deepEqual(r.details, []);
|
|
});
|
|
|
|
// ---- fidelityDiff -----------------------------------------------------------
|
|
|
|
test('fidelityDiff — identical artifact is fully equivalent (jaccard 1.0)', () => {
|
|
const d = fidelityDiff(RUN_A, RUN_A);
|
|
assert.equal(d.verdictMatch, true);
|
|
assert.equal(d.jaccard, 1);
|
|
assert.equal(d.equivalent, true);
|
|
assert.equal(d.severityMismatches.length, 0);
|
|
assert.equal(d.ruleKeyMismatches.length, 0);
|
|
});
|
|
|
|
test('fidelityDiff — A vs B (A ⊂ B): same verdict, jaccard 5/6, equivalent at default tolerance', () => {
|
|
const d = fidelityDiff(RUN_A, RUN_B);
|
|
assert.equal(d.verdictMatch, true);
|
|
assert.ok(Math.abs(d.jaccard - 5 / 6) < 1e-9, `jaccard=${d.jaccard}`);
|
|
assert.equal(d.equivalent, true); // default jaccardTolerance 0.7
|
|
});
|
|
|
|
test('fidelityDiff — divergent verdict makes it non-equivalent even at jaccard 1.0', () => {
|
|
const a = parseReviewArtifact(RUN_A);
|
|
const flipped = RUN_A.replace('verdict: WARN', 'verdict: BLOCK');
|
|
const d = fidelityDiff(RUN_A, flipped);
|
|
assert.equal(d.verdictMatch, false);
|
|
assert.equal(d.jaccard, 1);
|
|
assert.equal(d.equivalent, false);
|
|
void a;
|
|
});
|
|
|
|
test('fidelityDiff — tolerance gate: jaccard below tolerance is non-equivalent', () => {
|
|
const dLoose = fidelityDiff(RUN_A, RUN_B, { jaccardTolerance: 0.7 });
|
|
const dStrict = fidelityDiff(RUN_A, RUN_B, { jaccardTolerance: 0.95 });
|
|
assert.equal(dLoose.equivalent, true);
|
|
assert.equal(dStrict.equivalent, false);
|
|
});
|
|
|
|
test('fidelityDiff — flags severity mismatch on a shared finding ID', () => {
|
|
// Flip the BLOCKER severity in B's trailing JSON for the shared login.mjs finding.
|
|
const sharedId = '763d174e6c519fafbadcba5d1706708479e36e61';
|
|
const tampered = RUN_B.replace(
|
|
`"id": "${sharedId}", "severity": "BLOCKER"`,
|
|
`"id": "${sharedId}", "severity": "MINOR"`,
|
|
);
|
|
const d = fidelityDiff(RUN_A, tampered);
|
|
assert.ok(d.severityMismatches.some((m) => m.id === sharedId),
|
|
`expected a severity mismatch for ${sharedId}; got ${JSON.stringify(d.severityMismatches)}`);
|
|
assert.equal(d.equivalent, false);
|
|
});
|
|
|
|
test('fidelityDiff — exposes finding counts for both arms', () => {
|
|
const d = fidelityDiff(RUN_A, RUN_B);
|
|
assert.equal(d.countA, 5);
|
|
assert.equal(d.countB, 6);
|
|
});
|
|
|
|
// ---- structured arm-output path (the bake-off comparison) -------------------
|
|
|
|
const ARM = (verdict, findings) => ({ verdict, findings });
|
|
const F = (severity, rule_key, file, line) => ({ severity, rule_key, file, line });
|
|
|
|
test('normalizeArmOutput — recomputes canonical IDs from the (file,line,rule_key) triplet', () => {
|
|
const arm = ARM('WARN', [F('BLOCKER', 'SECURITY_INJECTION', 'lib/exec.mjs', 23)]);
|
|
const n = normalizeArmOutput(arm);
|
|
assert.equal(n.verdict, 'WARN');
|
|
assert.equal(n.findingIds.length, 1);
|
|
assert.equal(n.findingIds[0], computeFindingId('lib/exec.mjs', 23, 'SECURITY_INJECTION'));
|
|
});
|
|
|
|
test('normalizeArmOutput — drops findings missing file/rule_key from the ID set', () => {
|
|
const arm = ARM('WARN', [F('MAJOR', 'MISSING_TEST', '', 0), { severity: 'MINOR', line: 5 }]);
|
|
const n = normalizeArmOutput(arm);
|
|
assert.equal(n.findingIds.length, 0);
|
|
assert.equal(n.details.length, 2); // still recorded, just not ID-keyed
|
|
});
|
|
|
|
test('fidelityDiffStructured — identical arms are equivalent (jaccard 1.0)', () => {
|
|
const findings = [
|
|
F('BLOCKER', 'UNIMPLEMENTED_CRITERION', 'a.mjs', 1),
|
|
F('MAJOR', 'MISSING_TEST', 'b.mjs', 0),
|
|
];
|
|
const d = fidelityDiffStructured(ARM('BLOCK', findings), ARM('BLOCK', findings));
|
|
assert.equal(d.equivalent, true);
|
|
assert.equal(d.jaccard, 1);
|
|
assert.equal(d.verdictMatch, true);
|
|
});
|
|
|
|
test('fidelityDiffStructured — divergent verdict fails even with identical findings', () => {
|
|
const findings = [F('BLOCKER', 'UNIMPLEMENTED_CRITERION', 'a.mjs', 1)];
|
|
const d = fidelityDiffStructured(ARM('BLOCK', findings), ARM('WARN', findings));
|
|
assert.equal(d.verdictMatch, false);
|
|
assert.equal(d.equivalent, false);
|
|
});
|
|
|
|
test('fidelityDiffStructured — extra finding in Arm B lowers jaccard', () => {
|
|
const a = ARM('WARN', [F('MAJOR', 'MISSING_TEST', 'a.mjs', 10)]);
|
|
const b = ARM('WARN', [
|
|
F('MAJOR', 'MISSING_TEST', 'a.mjs', 10),
|
|
F('MINOR', 'PLACEHOLDER_IN_CODE', 'b.mjs', 14),
|
|
]);
|
|
const d = fidelityDiffStructured(a, b);
|
|
assert.ok(Math.abs(d.jaccard - 1 / 2) < 1e-9, `jaccard=${d.jaccard}`);
|
|
assert.equal(d.countA, 1);
|
|
assert.equal(d.countB, 2);
|
|
});
|
|
|
|
test('fidelityDiffStructured — same triplet, different severity → severity mismatch', () => {
|
|
const a = ARM('BLOCK', [F('BLOCKER', 'UNIMPLEMENTED_CRITERION', 'a.mjs', 1)]);
|
|
const b = ARM('BLOCK', [F('MAJOR', 'UNIMPLEMENTED_CRITERION', 'a.mjs', 1)]);
|
|
const d = fidelityDiffStructured(a, b);
|
|
assert.equal(d.jaccard, 1); // same triplet → same ID
|
|
assert.equal(d.severityMismatches.length, 1);
|
|
assert.equal(d.equivalent, false);
|
|
});
|