feat(voyage): S10 part B — NW2 full bake-off (rich fixture) → verdict POSITIVE

Run the full T2 §5 prose-vs-Workflow /trekreview bake-off (operator GO,
choice "a"): 3 runs/arm on a rich-finding JWT-auth fixture, resolving the
smoke's 0-finding limitation.

Deliverables:
- tests/fixtures/bakeoff-rich/ — JWT-auth brief + diff with 5 seeded blatant,
  brief-traceable issues (varied severity/rule_key, one dual-flaggable).
- scripts/bakeoff-armA-merge.mjs — Arm A (prose) validate (NW1) + triplet-dedup,
  matching Arm B's dedup exactly.
- scripts/bakeoff-fidelity.mjs — cross-arm + within-arm + granularity-ladder
  fidelity analysis over the structured arm outputs.
- docs/T2-bakeoff-results.md §Full run — the T2 §5 verdict.

Result (3 runs/arm, both arms ran the coordinator):
- Verdict fidelity EQUIVALENT — all 6 runs BLOCK, cross-arm verdict-match 1.0.
- Finding-set: substrate is fidelity-neutral. Cross-arm jaccard 0.41 (triplet)
  → 0.71 (file,rule_key) → 1.0 (file); cross-arm ≈ within-arm at every
  granularity. Issue coverage 5/5 in 6/6 runs. Low triplet jaccard is
  line-citation noise shared by both arms, not a substrate effect.
- Token +4.4% (Arm B vs A; <=+15%). Classifier interference 0 at 9-agent
  concurrency. JSON-robustness: Arm B schema-forced; Arm A 6/6 valid via NW1.
- VERDICT POSITIVE → S11 proceeds with opt-in --workflow flag.

Caveat (per plan posture): strict triplet-jaccard>=0.7 flag is 0/9, a
metric-calibration artifact (both arms sub-0.7 against themselves), not a
regression. Residual: F4 auto/bypass explicit-mode check (mode not settable
in-session).

Suite green (662/660 pass, 2 skip); plugin validate clean (modulo the
pre-existing root-CLAUDE.md warning). No production code changed.

Co-Authored-By: Claude Opus 4.8 (1M context) <noreply@anthropic.com>
Claude-Session: https://claude.ai/code/session_01LqBYc8Ltrk7LipyJmGxXiB
This commit is contained in:
Kjell Tore Guttormsen 2026-06-18 15:44:24 +02:00
commit f7c8aa45ab
6 changed files with 537 additions and 4 deletions

View file

@ -0,0 +1,101 @@
// scripts/bakeoff-armA-merge.mjs
// NW2 bake-off — Arm A (prose path) merge step.
//
// Arm A is the CURRENT /trekreview Phase 56 substrate: main spawns the two
// reviewers FOREGROUND (Agent tool), each emits a trailing fenced ```json block
// of findings (the prose contract), and main hand-validates + dedups before
// spawning the coordinator. This script is that hand-validate + dedup, made
// reproducible:
//
// for each reviewer raw-output file:
// validateReviewerOutput() (NW1 — extract last json fence, parse, schema-check)
// collect findings from VALID reviewers
// triplet-dedup by (file,line,rule_key) [SAME logic as Arm B's dedupByTriplet,
// so the two arms dedup identically —
// triplet-only, no jaccard pass-2]
// → emit { merged, validation, raw_finding_count, deduped_count }
//
// The merged findings are then handed to the review-coordinator (spawned by main),
// mirroring Arm B's coordinatorPrompt input. JSON-robustness metric = the
// `validation` report (parse/schema failures + which codes).
//
// Usage:
// node scripts/bakeoff-armA-merge.mjs [--json] <reviewerA.txt> <reviewerB.txt> ...
// → stdout: merged findings JSON (or full report with --json). Exit 0 always
// (validation failures are reported in-band, not as a nonzero exit).
import { readFileSync, existsSync } from 'node:fs';
import { validateReviewerOutput } from '../lib/review/findings-schema.mjs';
// Triplet dedup — byte-for-byte the same key + first-wins policy as
// scripts/trekreview-armB.workflow.mjs `dedupByTriplet`, so neither arm gets a
// dedup advantage. Triplet-only (file,line,rule_key); NO jaccard pass-2.
export function dedupByTriplet(findings) {
const seen = new Map();
for (const f of findings) {
const key = `${f.file} ${f.line} ${f.rule_key}`;
if (!seen.has(key)) seen.set(key, f);
}
return [...seen.values()];
}
/**
* Merge an array of reviewer raw-output texts into the coordinator's input.
* @param {Array<{label?: string, text: string}>} reviewerOutputs
* @returns {{ merged, validation, raw_finding_count, deduped_count }}
*/
export function mergeArmA(reviewerOutputs) {
const validation = [];
const allFindings = [];
for (const { label, text } of reviewerOutputs) {
const r = validateReviewerOutput(text);
validation.push({
label: label || null,
valid: r.valid,
finding_count: Array.isArray(r.parsed?.findings) ? r.parsed.findings.length : 0,
error_codes: (r.errors || []).map((e) => e.code),
warning_codes: (r.warnings || []).map((w) => w.code),
});
// Mirror Phase 5: only VALID reviewer output flows to the coordinator.
if (r.valid && Array.isArray(r.parsed?.findings)) {
allFindings.push(...r.parsed.findings);
}
}
const merged = dedupByTriplet(allFindings);
return {
merged,
validation,
raw_finding_count: allFindings.length,
deduped_count: merged.length,
};
}
// ---- CLI shim ----------------------------------------------------------------
if (import.meta.url === `file://${process.argv[1]}`) {
const argv = process.argv.slice(2);
const asJson = argv.includes('--json');
const files = argv.filter((a) => !a.startsWith('--'));
if (files.length === 0) {
process.stderr.write('Usage: bakeoff-armA-merge.mjs [--json] <reviewer-output> ...\n');
process.exit(2);
}
const outputs = files.map((f) => {
if (!existsSync(f)) {
process.stderr.write(`bakeoff-armA-merge: file not found: ${f}\n`);
process.exit(2);
}
return { label: f, text: readFileSync(f, 'utf-8') };
});
const result = mergeArmA(outputs);
if (asJson) {
process.stdout.write(JSON.stringify(result, null, 2) + '\n');
} else {
process.stdout.write(JSON.stringify(result.merged, null, 2) + '\n');
process.stderr.write(
`arm-A merge: ${result.raw_finding_count} raw → ${result.deduped_count} deduped; ` +
`validation ${result.validation.map((v) => `${v.label}:${v.valid ? 'OK' : v.error_codes.join('/')}`).join(' ')}\n`,
);
}
process.exit(0);
}

View file

@ -0,0 +1,123 @@
// scripts/bakeoff-fidelity.mjs
// NW2 bake-off — fidelity analysis across ≥3 runs/arm (S10 part B).
//
// Consumes the per-run structured arm outputs ({verdict, findings:[...]}) and
// computes the T2 §5 fidelity picture:
//
// - CROSS-ARM (PRIMARY): every (Ai, Bj) pair via fidelityDiffStructured
// (lib/review/fidelity-diff.mjs) → median jaccard, verdict-match rate,
// equivalence rate, severity/rule_key mismatch tallies.
// - WITHIN-ARM (context): each arm's own run-to-run variance (Ai vs Aj),
// so cross-arm divergence can be read against each arm's intrinsic noise.
// - Distributions: per-arm verdicts + finding counts.
//
// Pure analysis over JSON the live runs produced — no LLM, deterministic.
//
// Usage:
// node scripts/bakeoff-fidelity.mjs --armA a1.json a2.json a3.json \
// --armB b1.json b2.json b3.json [--json]
// Each *.json is a structured arm result: {"verdict": "...", "findings": [...]}.
import { readFileSync } from 'node:fs';
import { fidelityDiffStructured } from '../lib/review/fidelity-diff.mjs';
function median(nums) {
if (nums.length === 0) return null;
const s = [...nums].sort((a, b) => a - b);
const mid = Math.floor(s.length / 2);
return s.length % 2 ? s[mid] : (s[mid - 1] + s[mid]) / 2;
}
function round(n, d = 4) {
return n === null ? null : Number(n.toFixed(d));
}
function pairwise(arms, label) {
const out = [];
for (let i = 0; i < arms.length; i++) {
for (let j = i + 1; j < arms.length; j++) {
const d = fidelityDiffStructured(arms[i].result, arms[j].result);
out.push({ pair: `${label}${i + 1}×${label}${j + 1}`, jaccard: round(d.jaccard), verdictMatch: d.verdictMatch, equivalent: d.equivalent });
}
}
return out;
}
/**
* @param {Array<{name, result:{verdict,findings}}>} armA
* @param {Array<{name, result:{verdict,findings}}>} armB
*/
export function analyze(armA, armB) {
// Cross-arm — the substrate comparison.
const cross = [];
for (let i = 0; i < armA.length; i++) {
for (let j = 0; j < armB.length; j++) {
const d = fidelityDiffStructured(armA[i].result, armB[j].result);
cross.push({
pair: `A${i + 1}×B${j + 1}`,
verdictA: d.verdictA, verdictB: d.verdictB, verdictMatch: d.verdictMatch,
jaccard: round(d.jaccard), countA: d.countA, countB: d.countB,
severityMismatches: d.severityMismatches.length,
ruleKeyMismatches: d.ruleKeyMismatches.length,
equivalent: d.equivalent,
});
}
}
const crossJ = cross.map((c) => c.jaccard);
const summary = {
runs: { armA: armA.length, armB: armB.length },
cross_arm: {
median_jaccard: round(median(crossJ)),
min_jaccard: round(Math.min(...crossJ)),
max_jaccard: round(Math.max(...crossJ)),
verdict_match_rate: round(cross.filter((c) => c.verdictMatch).length / cross.length, 3),
equivalent_rate: round(cross.filter((c) => c.equivalent).length / cross.length, 3),
severity_mismatch_pairs: cross.filter((c) => c.severityMismatches > 0).length,
rulekey_mismatch_pairs: cross.filter((c) => c.ruleKeyMismatches > 0).length,
},
within_arm_A: pairwise(armA, 'A'),
within_arm_B: pairwise(armB, 'B'),
distributions: {
armA_verdicts: armA.map((a) => a.result.verdict),
armB_verdicts: armB.map((b) => b.result.verdict),
armA_counts: armA.map((a) => (a.result.findings || []).length),
armB_counts: armB.map((b) => (b.result.findings || []).length),
},
};
return { summary, cross };
}
// ---- CLI shim ----------------------------------------------------------------
if (import.meta.url === `file://${process.argv[1]}`) {
const argv = process.argv.slice(2);
const asJson = argv.includes('--json');
function collect(flag) {
const i = argv.indexOf(flag);
if (i === -1) return [];
const files = [];
for (let k = i + 1; k < argv.length && !argv[k].startsWith('--'); k++) files.push(argv[k]);
return files.map((f) => ({ name: f, result: JSON.parse(readFileSync(f, 'utf-8')) }));
}
const armA = collect('--armA');
const armB = collect('--armB');
if (armA.length === 0 || armB.length === 0) {
process.stderr.write('Usage: bakeoff-fidelity.mjs --armA a*.json --armB b*.json [--json]\n');
process.exit(2);
}
const { summary, cross } = analyze(armA, armB);
if (asJson) {
process.stdout.write(JSON.stringify({ summary, cross }, null, 2) + '\n');
} else {
const x = summary.cross_arm;
process.stdout.write('NW2 bake-off fidelity (cross-arm = PRIMARY)\n');
process.stdout.write(` runs: A=${summary.runs.armA} B=${summary.runs.armB}\n`);
process.stdout.write(` median jaccard: ${x.median_jaccard} (min ${x.min_jaccard}, max ${x.max_jaccard})\n`);
process.stdout.write(` verdict-match rate: ${x.verdict_match_rate}\n`);
process.stdout.write(` equivalent rate: ${x.equivalent_rate}\n`);
process.stdout.write(` severity-mismatch pairs: ${x.severity_mismatch_pairs}; rule_key-mismatch pairs: ${x.rulekey_mismatch_pairs}\n`);
process.stdout.write(` armA verdicts: ${summary.distributions.armA_verdicts.join(',')} | counts ${summary.distributions.armA_counts.join(',')}\n`);
process.stdout.write(` armB verdicts: ${summary.distributions.armB_verdicts.join(',')} | counts ${summary.distributions.armB_counts.join(',')}\n`);
}
process.exit(0);
}