fix: three more measured false positives, all reported the same day v0.1.2 shipped

- extractChangelogTop truncated PEP 440 pre-release versions (0.5.0a2 -> 0.5.0),
  so VERSION-CHANGELOG disagreed with VERSION-TAG over a version everything
  already agreed on. Reported by llm-ingestion-okf with a repro.
- BADGE-STATIC-CLAIM treated a bare `status` badge as a run claim, same as
  tests/build/CI. A self-declared maturity label asserts no run, same class
  as version/licence/platform. Reported by llm-ingestion-pipeline-security.
- BOILERPLATE flagged FIXME when a scanner's own docs named the TODO/FIXME
  convention rather than an instance of it. Reported by config-audit.

92 tests green, up from 86.

Co-Authored-By: Claude Sonnet 5 <noreply@anthropic.com>
Claude-Session: https://claude.ai/code/session_01Uwwfdmrfnp7FuGQ4z25RKH
This commit is contained in:
Kjell Tore Guttormsen 2026-08-03 22:10:17 +02:00
commit 5eba10acdd
7 changed files with 110 additions and 7 deletions

View file

@ -427,7 +427,12 @@ export function checkVersionConsistency({ pluginVersion, readmeBadge, changelogT
// A static image asserting "tests: 642 passing" is a claim dressed as evidence.
// Version, licence and platform badges assert no run, so they are fine static.
const CLAIM_BADGE = /(tests?|build|ci|coverage|passing|status)/i;
// Bare `status` used to be in this list and caught a self-declared maturity
// badge ("status: alpha") as if it were a run claim — reported by
// llm-ingestion-pipeline-security. `build`/`ci`/`passing` already catch the
// run-asserting compounds ("build status", "CI status"), so dropping the bare
// word loses no real detection.
const CLAIM_BADGE = /(tests?|build|ci|coverage|passing)/i;
export function checkBadges({ readme }) {
const findings = [];
@ -453,6 +458,7 @@ export function checkBadges({ readme }) {
// Template text that was never filled in. A visible unfinished template costs
// more trust than the missing document would have.
const FIXME_RE = /FIXME/;
const BOILERPLATE = [
/your-project-name/i,
/\byour-org\b/i,
@ -460,16 +466,24 @@ const BOILERPLATE = [
/<your[- ][a-z]+>/i,
/TODO:\s*(fill|replace|update)/i,
/example@example\.(com|org)/i,
/FIXME/,
FIXME_RE,
];
// "TODO/FIXME" named together names the convention, not a live instance of
// one — reported by config-audit: a scanner whose job is finding these
// markers names its own detection target in its own docs, unquoted. A lone
// FIXME is still caught; only the paired reference is exempt.
const NAMES_THE_CONVENTION = /\bTODO\s*\/\s*FIXME\b|\bFIXME\s*\/\s*TODO\b/i;
export function checkBoilerplate({ files }) {
const findings = [];
for (const [path, text] of Object.entries(files ?? {})) {
// Same discipline as the link check: code spans and fenced blocks are where
// a document ABOUT placeholders keeps its examples.
stripCode(text).split('\n').forEach((line, i) => {
const namesTheConvention = NAMES_THE_CONVENTION.test(line);
for (const re of BOILERPLATE) {
if (re === FIXME_RE && namesTheConvention) continue;
if (re.test(line)) {
findings.push({
level: 'WARN',
@ -788,7 +802,13 @@ export function extractBadgeVersion(readmeText) {
// design — it is not a claim that anything shipped.
export function extractChangelogTop(changelogText) {
for (const line of String(changelogText || '').split('\n')) {
const m = /^##\s*\[?v?(\d+\.\d+\.\d+)\]?/.exec(line.trim());
// The suffix class stops at `]`, whitespace or end of string, so a
// pre-release token (PEP 440 `a2`, semver `-beta.1`) is kept without
// reaching into a trailing `] — DATE`. Reported by llm-ingestion-okf:
// truncating this to X.Y.Z made VERSION-CHANGELOG disagree with
// VERSION-TAG, which compares the untruncated tag and does not have
// this problem — a repo on a pre-release could never reach 0 ERROR.
const m = /^##\s*\[?v?(\d+\.\d+\.\d+[0-9A-Za-z.+-]*)\]?/.exec(line.trim());
if (m) return m[1];
}
return null;

View file

@ -28,6 +28,7 @@ import {
classifyRepo,
levelOf,
parseRepoNameFromRemote,
extractChangelogTop,
} from './repo-standard-check.mjs';
const REGISTER = {
@ -490,6 +491,22 @@ test('a released version with no matching tag is an ERROR', () => {
assert.equal(f.some((x) => x.level === 'ERROR' && x.code === 'VERSION-TAG'), true);
});
// Reported by llm-ingestion-okf (coord, 2026-08-03): a PEP 440 pre-release
// (`0.5.0a2`) matches the manifest and the tag exactly, but the CHANGELOG
// extractor truncated it to `0.5.0` — the only way to reach 0 ERROR would have
// been to announce a release that never happened.
test('extractChangelogTop keeps a PEP 440 pre-release suffix, not just X.Y.Z', () => {
assert.equal(extractChangelogTop('## [0.5.0a2] - 2026-07-31'), '0.5.0a2');
assert.equal(extractChangelogTop('## [0.1.1] — 2026-08-03'), '0.1.1');
});
test('a PEP 440 pre-release version agrees with its own CHANGELOG heading', () => {
const f = checkVersionConsistency({
pluginVersion: '0.5.0a2', readmeBadge: '0.5.0a2', changelogTop: extractChangelogTop('## [0.5.0a2] - 2026-07-31'), tags: ['v0.5.0a2'],
});
assert.equal(f.some((x) => x.level === 'ERROR'), false);
});
// -------------------------------------------------------- required headings
test('required headings are per class — Non-goals is required, not optional', () => {
@ -530,6 +547,22 @@ test('a build badge that links to a real run is fine', () => {
assert.equal(checkBadges({ readme }).filter((f) => f.level !== 'OK').length, 0);
});
// Reported by llm-ingestion-pipeline-security (coord, 2026-08-03): a bare
// `status` badge is a self-declared maturity label ("alpha", "experimental"),
// the same class as version/licence/platform, which already assert no run —
// not a run claim like "build status" or "CI status".
test('a static maturity-status badge asserts no run, unlike build/CI status', () => {
const f = checkBadges({ readme: '![Status](https://img.shields.io/badge/status-alpha-orange)' });
assert.equal(f.some((x) => x.code === 'BADGE-STATIC-CLAIM'), false);
});
test('a build- or CI-status badge is still caught — only bare "status" was too wide', () => {
const build = checkBadges({ readme: '![Build Status](https://img.shields.io/badge/build-passing-green)' });
assert.equal(build.some((x) => x.code === 'BADGE-STATIC-CLAIM'), true);
const ci = checkBadges({ readme: '![CI Status](https://img.shields.io/badge/ci-passing-green)' });
assert.equal(ci.some((x) => x.code === 'BADGE-STATIC-CLAIM'), true);
});
// -------------------------------------------------------------- boilerplate
test('unfinished template text is a finding', () => {
@ -540,6 +573,27 @@ test('unfinished template text is a finding', () => {
assert.equal(g.some((x) => x.code === 'BOILERPLATE'), true);
});
test('a lone FIXME with no TODO alongside is still caught', () => {
const f = checkBoilerplate({ files: { 'NOTES.md': 'FIXME: handle the null case here.' } });
assert.equal(f.some((x) => x.level === 'WARN'), true);
});
// Reported by config-audit (coord, 2026-08-03): a scanner whose JOB is to find
// TODO/FIXME markers in OTHER repos names its own detection target in its own
// docs — prose and a table row, neither wrapped in backticks. "TODO/FIXME"
// named together is the convention itself, not a forgotten instance of one.
test('"TODO/FIXME" named together as the convention is not a live marker', () => {
const listItem = checkBoilerplate({
files: { 'agents/scanner-agent.md': "- Flag TODO/FIXME markers that haven't been addressed" },
});
assert.equal(listItem.some((x) => x.level === 'WARN'), false);
const tableRow = checkBoilerplate({
files: { 'knowledge/anti-patterns.md': '| 5 | TODO/FIXME comments in CLAUDE.md | CA-CML-005 | low |' },
});
assert.equal(tableRow.some((x) => x.level === 'WARN'), false);
});
test('ordinary prose is not boilerplate', () => {
const f = checkBoilerplate({ files: { 'README.md': 'This project solves a real problem.' } });
assert.equal(f.filter((x) => x.level !== 'OK').length, 0);