valent-pipeline 0.19.59 → 0.19.60

package/package.json

@@ -1,6 +1,6 @@
 {
   "name": "valent-pipeline",
-  "version": "0.19.59",
+  "version": "0.19.60",
   "description": "v3 multi-agent AI pipeline for software development lifecycle",
   "type": "module",
   "bin": {

package/src/commands/crosscheck.js

@@ -12,7 +12,7 @@ import { join } from 'path';
 import { randomBytes } from 'crypto';
 import { crosscheckVerdict, formatCrosscheck } from '../lib/crosscheck.js';
 import { extractFencedBlock } from '../lib/handoff.js';
-import { evidenceDir, latestPins, resolveRoot, utcCompact, latestAssert, authenticateBaseline } from '../lib/evidence.js';
+import { evidenceDir, latestPins, resolveRoot, utcCompact, latestAssert, assertPassedCountsForLabel, authenticateBaseline } from '../lib/evidence.js';
 
 const GATE_ARTIFACTS = {
   judge: 'judge-decision.md',
@@ -67,6 +67,11 @@ export async function crosscheckCmd(options) {
   // verify — the bare "newest assert" let a later red/acceptance assert shadow the qa-b green one.
   const expect = options.expect === 'red' ? 'red' : 'green';
   const got = latestAssert(evDir, { label: options.label || null, expect });
+  // Multi-suite label-multiplexing (2026-06-25): passed-counts of every green assert UNDER THE GATE'S
+  // LABEL, so the crosscheck can tell a real sibling-suite count (a run JUDGE legitimately counted)
+  // from a fabricated testsPassed. Gated on a label being bound — the unbound/legacy recount stays
+  // strict (it must not tolerate a count from an unrelated label). Single-run stories are unaffected.
+  const siblingPassedCounts = options.label ? assertPassedCountsForLabel(evDir, { label: options.label, expect }) : [];
   // Baseline authentication feeds the preExistingExcluded rule (review pass-3 #5).
   let baselineAuth = null;
   const baselineCandidates = [join(evDir, 'baseline.json'), join(root, '.valent-pipeline', 'evidence-baseline.json')];
@@ -89,6 +94,7 @@ export async function crosscheckCmd(options) {
     baselineAuth,
     assertRequired: options.requireAssert === true,
     expectedLabel: options.label || null,
+    siblingPassedCounts,
   });
   if (malformedInputs.length) {
     result.mismatches.push(...malformedInputs);

package/src/lib/crosscheck.js

@@ -35,7 +35,7 @@ const OPEN_STATUSES = new Set(['open', 'fix-in-progress']);
  * @returns {{ok:boolean, skipped:boolean, mismatches:Array<{field:string, claimed:*, actual:*}>,
  *            warnings:string[], recounted:object}}
  */
-export function crosscheckVerdict({ reported = null, bugsBlock = null, assertVerdict = null, pin = null, diskVerdict = null, baselineAuth = null, assertRequired = false, expectedLabel = null }) {
+export function crosscheckVerdict({ reported = null, bugsBlock = null, assertVerdict = null, pin = null, diskVerdict = null, baselineAuth = null, assertRequired = false, expectedLabel = null, siblingPassedCounts = [] }) {
   const mismatches = [];
   const warnings = [];
   const recounted = {};
@@ -87,6 +87,18 @@ export function crosscheckVerdict({ reported = null, bugsBlock = null, assertVer
       warnings.push(`${field}: self-reported ${reported[field]} but artifacts show ${actual} — under-report (safe direction: under-stating passes cannot sneak a ship), reconciled to the recount`);
       return;
     }
+    // Multi-suite label-multiplexing (2026-06-25): when several DISTINCT green suites run under ONE
+    // label at one gate (e.g. acceptance + server-project, case sets the record-time auto-namespace
+    // did not split), the label-bound recount picks the LATEST assert, which may not be the suite
+    // JUDGE counted. A testsPassed OVER-claim that EXACTLY equals some OTHER green same-label
+    // assert's passed count is a real machine recount of a sibling run JUDGE counted — not padded
+    // green — so reconcile with a warning. A value matching NO real same-label assert stays a hard
+    // mismatch (the fabrication case the crosscheck exists to catch). Strictly safer than binding
+    // the recount to the run JUDGE *cites* (which would let the gate choose its own recount source).
+    if (field === 'testsPassed' && numeric && reported[field] > actual && Array.isArray(siblingPassedCounts) && siblingPassedCounts.includes(reported[field])) {
+      warnings.push(`testsPassed: self-reported ${reported[field]} but the label-bound assert shows ${actual} — matches a sibling green run under the same label (multi-suite label-multiplexing); reconciled to a real recount, not a fabrication`);
+      return;
+    }
     mismatches.push({ field, claimed: reported[field], actual });
   };