fix(#2128): address review — migrate 9 mis-allowlisted sites, harden scanner + guards

Correctness review of the Phase 4 guard found the allowlist over-broad and the
scanner/guards evadable. Fixed all findings:

- Migrate 9 sites that were wrongly sanctioned: their regex is the PURE canonical
  token (`\d+[A-Z]?(?:\.\d+)*`, no variant), byte-identical to already-migrated
  siblings. The old justification argued against swapping to the extractPhaseToken()
  FUNCTION (behavior-risky) — but the guard only wants the same regex built from
  the SOURCE string (byte-equal, zero risk). Coverage is now 32 migrated / 5
  sanctioned, not the overstated 23 / 14 (audit.cts x3, uat.cts, init.cts x4,
  roadmap-upgrade.cts). Each conversion proven byte-equal (.source + .flags).
- Harden the drift detector: also catch the `[0-9]`-in-place-of-`\d` variant;
  document the accepted limits (cross-line split, semantic restructuring —
  covered by the identity guard + review, not a text scan).
- Sanction robustness: a `phase-id-owner:` marker now counts only inside a `//`
  comment (a bare substring in a string no longer suppresses a real flag), and
  the preceding-line window skips blank lines (an auto-formatter's blank line no
  longer reactivates the flag).
- roadmap-parser.cts:462 comment: corrected — that regex carries no /i flag, so
  its [A-Za-z] class does real case work (matches state.cts:1409's rationale).
- Identity guard: surface require failures instead of silently skipping, and
  floor coverage at >75% of consumer modules (inspects 156/157).

Co-Authored-By: Claude Opus 4.8 <noreply@anthropic.com>
This commit is contained in:
Tom Boucher
2026-07-10 09:14:15 -04:00
parent dfad3a7510
commit e2eaa5b046
7 changed files with 67 additions and 36 deletions

View File

@@ -20,6 +20,9 @@ const { planningDir } = planningWorkspace;
// eslint-disable-next-line @typescript-eslint/no-require-imports
import frontmatter = require('./frontmatter.cjs');
const { extractFrontmatter } = frontmatter;
// eslint-disable-next-line @typescript-eslint/no-require-imports
import phaseIdMod = require('./phase-id.cjs');
const { PHASE_NUMBER_TOKEN_SOURCE } = phaseIdMod;
import { requireSafePath, sanitizeForDisplay } from './security.cjs';
// ─── Types ────────────────────────────────────────────────────────────────────
@@ -482,8 +485,7 @@ function scanUatGaps(planDir: string): UatGapItem[] {
for (const dir of dirs) {
const phaseDir = path.join(phasesDir, dir);
// phase-id-owner: cosmetic phase label derived from a dir name for JSON output; the single-segment capture is not equivalent to extractPhaseToken dash-continuation semantics, so not a behavior-preserving drop-in.
const phaseMatch = dir.match(/^(\d+[A-Z]?(?:\.\d+)*)/i);
const phaseMatch = dir.match(new RegExp(`^(${PHASE_NUMBER_TOKEN_SOURCE})`, 'i'));
const phaseNum = phaseMatch ? phaseMatch[1] : dir;
let files: string[];
@@ -553,8 +555,7 @@ function scanVerificationGaps(planDir: string): VerificationGapItem[] {
for (const dir of dirs) {
const phaseDir = path.join(phasesDir, dir);
// phase-id-owner: cosmetic phase label derived from a dir name for JSON output; the single-segment capture is not equivalent to extractPhaseToken dash-continuation semantics, so not a behavior-preserving drop-in.
const phaseMatch = dir.match(/^(\d+[A-Z]?(?:\.\d+)*)/i);
const phaseMatch = dir.match(new RegExp(`^(${PHASE_NUMBER_TOKEN_SOURCE})`, 'i'));
const phaseNum = phaseMatch ? phaseMatch[1] : dir;
let files: string[];
@@ -616,8 +617,7 @@ function scanContextQuestions(planDir: string): ContextQuestionItem[] {
for (const dir of dirs) {
const phaseDir = path.join(phasesDir, dir);
// phase-id-owner: cosmetic phase label derived from a dir name for JSON output; the single-segment capture is not equivalent to extractPhaseToken dash-continuation semantics, so not a behavior-preserving drop-in.
const phaseMatch = dir.match(/^(\d+[A-Z]?(?:\.\d+)*)/i);
const phaseMatch = dir.match(new RegExp(`^(${PHASE_NUMBER_TOKEN_SOURCE})`, 'i'));
const phaseNum = phaseMatch ? phaseMatch[1] : dir;
let files: string[];

View File

@@ -1181,8 +1181,7 @@ function cmdInitMilestoneOp(cwd: string, raw: boolean): void {
const entries = fs.readdirSync(phasesDir, { withFileTypes: true });
for (const e of entries) {
if (!e.isDirectory()) continue;
// phase-id-owner: dir-name phase-token parse; extractPhaseToken dash-separated sub-phase semantics differ, so a token-source swap would risk remapping phase<->directory matches. Kept local.
const m = stripProjectCodePrefix(e.name).match(/^(\d+[A-Z]?(?:\.\d+)*)/);
const m = stripProjectCodePrefix(e.name).match(new RegExp(`^(${PHASE_NUMBER_TOKEN_SOURCE})`));
if (!m) continue;
diskPhaseDirs.set(canonicalizePhase(m[1]), e.name);
}
@@ -1715,17 +1714,14 @@ function cmdInitProgress(cwd: string, raw: boolean): void {
.map((e) => e.name)
.filter(isDirInMilestone)
.sort((a, b) => {
// phase-id-owner: dir-name phase-token parse; extractPhaseToken dash-separated sub-phase semantics differ, so a token-source swap would risk remapping phase<->directory matches. Kept local.
const pa = a.match(/^(\d+[A-Z]?(?:\.\d+)*)/i);
// phase-id-owner: dir-name phase-token parse; extractPhaseToken dash-separated sub-phase semantics differ, so a token-source swap would risk remapping phase<->directory matches. Kept local.
const pb = b.match(/^(\d+[A-Z]?(?:\.\d+)*)/i);
const pa = a.match(new RegExp(`^(${PHASE_NUMBER_TOKEN_SOURCE})`, 'i'));
const pb = b.match(new RegExp(`^(${PHASE_NUMBER_TOKEN_SOURCE})`, 'i'));
if (!pa || !pb) return a.localeCompare(b);
return parseInt(pa[1], 10) - parseInt(pb[1], 10);
});
for (const dir of dirs) {
// phase-id-owner: dir-name phase-token parse; extractPhaseToken dash-separated sub-phase semantics differ, so a token-source swap would risk remapping phase<->directory matches. Kept local.
const dirMatch = dir.match(/^(\d+[A-Z]?(?:\.\d+)*)-?(.*)/i);
const dirMatch = dir.match(new RegExp(`^(${PHASE_NUMBER_TOKEN_SOURCE})-?(.*)`, 'i'));
const phaseNumber = dirMatch ? dirMatch[1] : dir;
const phaseName = dirMatch && dirMatch[2] ? dirMatch[2] : null;
seenPhaseNums.add(phaseNumber.replace(/^0+/, '') || '0');

View File

@@ -459,7 +459,7 @@ function getMilestonePhaseFilter(cwd: string, versionOverride?: string | null, p
// the milestone as a bogus "46-6" id.
const numericRe = roadmapUsesHyphenedIds
? /^0*(\d+(?:-\d{2,})*[A-Za-z]?(?:\.\d+)*)/
// phase-id-owner: [A-Za-z] case-variant token (identical under /i); kept literal, not source-byte-equal to the canonical PHASE_NUMBER_TOKEN_SOURCE.
// phase-id-owner: the [A-Za-z] letter class does real case handling here — this regex carries NO /i flag; kept literal, not source-byte-equal to the canonical PHASE_NUMBER_TOKEN_SOURCE.
: /^0*(\d+[A-Za-z]?(?:\.\d+)*)/;
function isDirInMilestone(dirName: string): boolean {

View File

@@ -175,8 +175,7 @@ function extractPhaseNumFromDir(dirName: string): string | null {
const stripped = stripProjectCodePrefix(dirName);
// Matches: digits + optional letter + optional decimal suffix, followed by '-' or end.
// e.g. "02.1-hotfix" → "02.1", "01-setup" → "01"
// phase-id-owner: strips a leading phase number from a dir name; extractPhaseToken returns the project-code-prefixed token, so it is not a behavior-preserving drop-in.
const m = stripped.match(/^(\d+[A-Z]?(?:\.\d+)*)(?:-|$)/i);
const m = stripped.match(new RegExp(`^(${PHASE_NUMBER_TOKEN_SOURCE})(?:-|$)`, 'i'));
return m ? m[1] : null;
}

View File

@@ -29,6 +29,9 @@ const { planningDir } = planningWorkspace;
// eslint-disable-next-line @typescript-eslint/no-require-imports
import frontmatter = require('./frontmatter.cjs');
const { extractFrontmatter } = frontmatter;
// eslint-disable-next-line @typescript-eslint/no-require-imports
import phaseIdMod = require('./phase-id.cjs');
const { PHASE_NUMBER_TOKEN_SOURCE } = phaseIdMod;
import { requireSafePath, sanitizeForDisplay } from './security.cjs';
// ─── Types ────────────────────────────────────────────────────────────────────
@@ -82,8 +85,7 @@ function cmdAuditUat(cwd: string, raw: boolean): void {
.sort();
for (const dir of dirs) {
// phase-id-owner: display phase field derived from a dir name (same family as the audit.cts sites); not equivalent to extractPhaseToken for dash-form dirs.
const phaseMatch = dir.match(/^(\d+[A-Z]?(?:\.\d+)*)/i);
const phaseMatch = dir.match(new RegExp(`^(${PHASE_NUMBER_TOKEN_SOURCE})`, 'i'));
const phaseNum = phaseMatch ? phaseMatch[1] : dir;
const phaseDir = path.join(phasesDir, dir);
const files = fs.readdirSync(phaseDir);