fix(#2128): bound the phase-tag clause to {0,200} — kill quadratic ReDoS

The canonical OPTIONAL_PHASE_TAG_SOURCE tag clause `(?:\s*\([^)\n]*\))?` (and its
inlined literal mirrors across 11 modules) had an UNBOUNDED body, making the
optional-group + /g header scan quadratic on adversarial ROADMAP.md/STATE.md — a
long run of `(` after a header ran ~18.8s at 1.7MB. Bound the body to {0,200} in
the constant AND every mirror in lockstep (the #1729 "both forms change together"
contract), so the scan is linear: the same 1.7MB input now resolves in ~9ms
(measured), while real tags (a handful of chars) still match and a 201-char tag
is rejected. Added a #2128 boundary regression to the #1729 suite.

Pre-existing (byte-identical before/after the Phase 4 migrations); folded in at
maintainer direction rather than deferred.

Co-Authored-By: Claude Opus 4.8 <noreply@anthropic.com>
This commit is contained in:
Tom Boucher
2026-07-10 09:31:17 -04:00
parent a1de52d71b
commit c1cd43a39f
12 changed files with 56 additions and 41 deletions

View File

@@ -1081,8 +1081,8 @@ function checkMilestonePrefixMismatches(
}
for (const section of sections) {
const content = roadmapContent.slice(section.start, section.end);
// #1729: `(?:\s*\([^)\n]*\))?` tolerates a pre-colon ( ) tag (literal mirror of OPTIONAL_PHASE_TAG_SOURCE).
const phaseRx = /#{2,4}\s*(?:\[[^\]]+\]\s*)?Phase\s+([\w][\w.-]*)(?:\s*\([^)\n]*\))?\s*:/gi;
// #1729: `(?:\s*\([^)\n]{0,200}\))?` tolerates a pre-colon ( ) tag (literal mirror of OPTIONAL_PHASE_TAG_SOURCE).
const phaseRx = /#{2,4}\s*(?:\[[^\]]+\]\s*)?Phase\s+([\w][\w.-]*)(?:\s*\([^)\n]{0,200}\))?\s*:/gi;
let pm: RegExpExecArray | null;
while ((pm = phaseRx.exec(content)) !== null) {
const phaseId = pm[1];
@@ -1812,8 +1812,8 @@ function cmdValidateHealth(
if (isMarkedComplete) {
const roadmapRaw = fs.readFileSync(roadmapPath, 'utf-8');
const scopedContent = extractCurrentMilestone(roadmapRaw, cwd);
// #1729: `(?:\s*\([^)\n]*\))?` tolerates a pre-colon ( ) tag (literal mirror of OPTIONAL_PHASE_TAG_SOURCE).
const phasePattern = new RegExp(`#{2,4}\\s*Phase\\s+(${PHASE_NUMBER_TOKEN_SOURCE})(?:\\s*\\([^)\\n]*\\))?\\s*:\\s*([^\\n]+)`, 'gi');
// #1729: `(?:\s*\([^)\n]{0,200}\))?` tolerates a pre-colon ( ) tag (literal mirror of OPTIONAL_PHASE_TAG_SOURCE).
const phasePattern = new RegExp(`#{2,4}\\s*Phase\\s+(${PHASE_NUMBER_TOKEN_SOURCE})(?:\\s*\\([^)\\n]{0,200}\\))?\\s*:\\s*([^\\n]+)`, 'gi');
const unstarted: string[] = [];
let pm: RegExpExecArray | null;
// Non-hoisted: load-order matters (circular dep guard)