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

@@ -1161,8 +1161,8 @@ function cmdInitMilestoneOp(cwd: string, raw: boolean): void {
const roadmapPath = path.join(planningDir(cwd), 'ROADMAP.md');
const roadmapRaw = fs.readFileSync(roadmapPath, 'utf-8');
const currentSection = 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*:`, '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+(${PHASE_NUMBER_TOKEN_SOURCE})(?:\\s*\\([^)\\n]{0,200}\\))?\\s*:`, 'gi');
let m: RegExpExecArray | null;
while ((m = phasePattern.exec(currentSection)) !== null) {
if (/^999(?:\.|$)/.test(m[1])) continue;
@@ -1325,8 +1325,8 @@ function cmdInitManager(cwd: string, raw: boolean): void {
_checkboxStates.set(_cbMatch[2], _cbMatch[1].toLowerCase() === 'x');
}
// #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 phases: Record<string, unknown>[] = [];
let match: RegExpExecArray | null;
@@ -1688,8 +1688,8 @@ function cmdInitProgress(cwd: string, raw: boolean): void {
fs.readFileSync(path.join(planningDir(cwd), 'ROADMAP.md'), 'utf-8'),
cwd,
);
// #1729: `(?:\s*\([^)\n]*\))?` tolerates a pre-colon ( ) tag (literal mirror of OPTIONAL_PHASE_TAG_SOURCE).
const headingPattern = 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 headingPattern = new RegExp(`#{2,4}\\s*Phase\\s+(${PHASE_NUMBER_TOKEN_SOURCE})(?:\\s*\\([^)\\n]{0,200}\\))?\\s*:\\s*([^\\n]+)`, 'gi');
let hm: RegExpExecArray | null;
while ((hm = headingPattern.exec(roadmapContent)) !== null) {
roadmapPhaseNums.add(hm[1]);