voyage/lib/util/test-census.mjs
Kjell Tore Guttormsen 440594f1b2 feat(eval): SKAL-1·4b offline gold-scored output eval
Scores committed agent-run fixtures against the golden corpus at
(file, rule_key) granularity, building on the deterministic coordinator
contract (4a). Offline: committed reviewer payloads, no live agent spawn,
no LLM, no network (the LLM-in-the-loop grading is the separate 4c tier).

- lib/review/gold-scorer.mjs: scoreFindings (precision/recall/f1 at
  (file,rule_key) granularity, line+severity ignored) + scoreVerdict; pure,
  with documented vacuous-set conventions.
- tests/fixtures/bakeoff-rich/runs/run-perfect.json: committed run that
  reproduces all 5 seeded gold findings through runContract.
- tests/lib/gold-eval.test.mjs: the scoring RUN (precision/recall/f1 = 1.0,
  verdict == expected_verdict BLOCK, nothing suppressed/skipped).
- lib/util/test-census.mjs: third census category (goldEval) — a scoring run
  is neither behavior coverage nor a doc-pin; honest-count invariant now 3-way.
- docs/eval-corpus/README.md: 4b moved from Future hardening to implemented.

Suite 809 -> 822 (820/0/2). gold-scorer covers TP+FP+FN+degenerate paths.

Co-Authored-By: Claude Opus 4.8 (1M context) <noreply@anthropic.com>
Claude-Session: https://claude.ai/code/session_01BJQYC5vpkJWxndS55vQQZ6
2026-06-30 09:00:33 +02:00

62 lines
2.7 KiB
JavaScript

// lib/util/test-census.mjs
// Census of the test suite: split top-level test() declarations into three
// honest categories:
// - "behavior" — ordinary behavior coverage (the default bucket).
// - "docPins" — doc-consistency pins (string/existence assertions that pin
// documentation against a source-of-truth).
// - "goldEval" — the offline gold-scored output eval scoring RUN (SKAL-1·4b):
// neither behavior nor prose-pin, but a run that scores a
// committed agent-run fixture against the golden corpus.
// Makes the cited test count honest — a prose-pin is not the same coverage as a
// behavior test, and a scoring run is a third thing again, so a single
// conflated total oversells behavior coverage.
// Devil's-advocate audit §Top changes #8 (S19); third bucket added in SKAL-1·4b.
//
// Metric: top-level `test(` declarations (static, deterministic, in-process).
// This is distinct from node:test's runtime total, which additionally counts
// subtests; the runtime total is therefore ≥ this declaration count.
import { readFileSync, readdirSync } from 'node:fs';
import { join } from 'node:path';
// Files whose tests are documentation pins, not behavior coverage. Kept as a
// regex (not a single filename) so a future split-out (e.g. prose-pins.test.mjs)
// is bucketed correctly without editing this module.
export const PIN_FILE_RE = /(doc-consistency|prose-pins)\.test\.mjs$/;
// Files whose tests are the offline gold-scored output eval scoring run
// (SKAL-1·4b). Kept as a regex (not a single filename) so a future split-out
// is bucketed correctly without editing this module.
export const GOLD_EVAL_FILE_RE = /gold-eval\.test\.mjs$/;
function walk(dir) {
const out = [];
for (const e of readdirSync(dir, { withFileTypes: true })) {
const p = join(dir, e.name);
if (e.isDirectory()) out.push(...walk(p));
else if (e.isFile() && e.name.endsWith('.test.mjs')) out.push(p);
}
return out;
}
function countTests(file) {
return (readFileSync(file, 'utf-8').match(/^\s*test\(/gm) || []).length;
}
// Returns { behavior, docPins, goldEval, total, byFile } for all *.test.mjs
// under testsRoot. behavior + docPins + goldEval === total by construction.
export function censusTests(testsRoot) {
const files = walk(testsRoot).sort();
const byFile = {};
let behavior = 0;
let docPins = 0;
let goldEval = 0;
for (const f of files) {
const n = countTests(f);
byFile[f] = n;
if (PIN_FILE_RE.test(f)) docPins += n;
else if (GOLD_EVAL_FILE_RE.test(f)) goldEval += n;
else behavior += n;
}
return { behavior, docPins, goldEval, total: behavior + docPins + goldEval, byFile };
}