@kevinrabun/judges 3.126.0 → 3.126.2

package/dist/commands/llm-benchmark.js

@@ -148,13 +148,15 @@ export function parseLlmRuleIds(response) {
     const validPrefixes = getValidRulePrefixes();
     const pattern = /\b([A-Z][A-Z0-9]+)-(\d{1,3})\b/g;
     const found = new Set();
-    // Split response into paragraphs/sections and skip sections that explicitly
-    // declare zero findings — rule IDs mentioned in "zero findings" rationale
-    // are explanatory references, not actual detections.
-    const sections = response.split(/\n{2,}/);
-    const zeroFindingsPattern = /\*?\*?(?:ZERO|zero|0|no)\s+findings?\*?\*?|(?:findings?|issues?)[\s:]*\*?\*?(?:none|0|zero)\*?\*?|no\s+(?:issues?|findings?|problems?|concerns?)\s+(?:found|detected|identified|reported)/i;
+    // Split response into judge sections (separated by --- dividers or ## headers)
+    // and skip entire sections that declare zero/no findings. This prevents rule
+    // IDs mentioned in rationale text or findings tables of "clean" judge sections
+    // from being counted as detections.
+    const sections = response.split(/(?:^|\n)---\s*\n|(?=^## )/m);
+    const zeroFindingsPattern = /\*?\*?(?:ZERO|zero|0|no)\s+findings?\*?\*?|(?:findings?|issues?)[\s:]*\*?\*?(?:none|0|zero)\*?\*?|no\s+(?:issues?|findings?|problems?|concerns?)\s+(?:found|detected|identified|reported)|report(?:ing)?\s+zero|Score\s*[|:]\s*\*?\*?100\s*\/?\s*100\*?\*?/i;
     for (const section of sections) {
-        // If this section explicitly declares zero/no findings, skip rule ID extraction
+        // If this section explicitly declares zero/no findings or a perfect score,
+        // skip rule ID extraction — any rule IDs are explanatory references
         if (zeroFindingsPattern.test(section))
             continue;
         let match;
@@ -165,13 +167,17 @@ export function parseLlmRuleIds(response) {
             }
         }
     }
-    // Secondary pass on full text: extract known prefixes from compound IDs like DEPS-TYPO-001
-    // These are almost always in findings tables, not rationale
-    const compoundPattern = /\b([A-Z][A-Z0-9]+)-[A-Z][A-Z0-9]+-(\d{1,3})\b/g;
-    let match;
-    while ((match = compoundPattern.exec(response)) !== null) {
-        if (validPrefixes.has(match[1])) {
-            found.add(`${match[1]}-${match[2]}`);
+    // Secondary pass: extract compound IDs like DEPS-TYPO-001 from sections
+    // that did NOT declare zero findings (reuse the filtered sections)
+    for (const section of sections) {
+        if (zeroFindingsPattern.test(section))
+            continue;
+        const compoundPattern = /\b([A-Z][A-Z0-9]+)-[A-Z][A-Z0-9]+-(\d{1,3})\b/g;
+        let match;
+        while ((match = compoundPattern.exec(section)) !== null) {
+            if (validPrefixes.has(match[1])) {
+                found.add(`${match[1]}-${match[2]}`);
+            }
         }
     }
     return [...found];

package/package.json

@@ -1,6 +1,6 @@
 {
   "name": "@kevinrabun/judges",
-  "version": "3.126.0",
+  "version": "3.126.2",
   "description": "45 specialized judges that evaluate AI-generated code for security, cost, and quality.",
   "mcpName": "io.github.KevinRabun/judges",
   "type": "module",

package/server.json

@@ -16,12 +16,12 @@
       "mimeType": "image/png"
     }
   ],
-  "version": "3.126.0",
+  "version": "3.126.2",
   "packages": [
     {
       "registryType": "npm",
       "identifier": "@kevinrabun/judges",
-      "version": "3.126.0",
+      "version": "3.126.2",
       "transport": {
         "type": "stdio"
       }