diff --git a/test/helpers/llm-judge.ts b/test/helpers/llm-judge.ts
index 5647cb31..af19cd34 100644
--- a/test/helpers/llm-judge.ts
+++ b/test/helpers/llm-judge.ts
@@ -236,16 +236,22 @@ export async function judgeRecommendation(askUserText: string): Promise<Recommen
   const present = !!recLine;
   const recBody = recLine?.[1]?.trim() ?? '';
 
-  // commits: reject obvious hedging language. The format-spec self-check
-  // requires the recommendation to name ONE choice; "either", "depending on",
-  // "if X then" all signal the model bailed on the commitment.
-  const commits = present && !/\b(either|depends? on|depending|if .+ then|or maybe|whichever)\b/i.test(recBody);
-
   // has_because: literal "because" token in the body, per the format spec.
   const becauseMatch = recBody.match(/\bbecause\s+(.+?)$/i);
   const has_because = !!becauseMatch;
   const reason_text = becauseMatch?.[1]?.trim() ?? '';
 
+  // commits: reject hedging language only in the CHOICE portion (before the
+  // "because" token). The because-clause itself is the reason and routinely
+  // contains technical phrases like "the plan doesn't yet depend on Redis"
+  // that aren't hedging at all. Looking only at the choice keeps the check
+  // focused: "Either A or B because..." → flagged; "A because depends on X" →
+  // accepted.
+  const choicePortion = becauseMatch
+    ? recBody.slice(0, recBody.toLowerCase().indexOf('because')).trim()
+    : recBody;
+  const commits = present && !/\b(either|depends? on|depending|if .+ then|or maybe|whichever)\b/i.test(choicePortion);
+
   // If the because-clause is absent, the substance score is implicitly 1.
   // Skip the LLM call — there is nothing to grade.
   if (!present || !has_because || !reason_text) {
diff --git a/test/skill-e2e-plan-format.test.ts b/test/skill-e2e-plan-format.test.ts
index 4038afa3..f1db699d 100644
--- a/test/skill-e2e-plan-format.test.ts
+++ b/test/skill-e2e-plan-format.test.ts
@@ -41,7 +41,11 @@ const evalCollector = createEvalCollector('e2e-plan-format');
 // — the canonical form per generate-ask-user-format.ts is just
 // `Recommendation: <choice> because <reason>`, where <choice> is the bare
 // option label. judgeRecommendation.present covers the canonical shape.
-const COMPLETENESS_RE = /Completeness:\s*\d{1,2}\/10/;
+// COMPLETENESS regex matches both legacy bare form (`Completeness: 10/10`) and
+// the canonical option-prefixed form (`Completeness: A=10/10, B=7/10`) per
+// scripts/resolvers/preamble/generate-ask-user-format.ts. The optional
+// `[A-Z]=` prefix tolerates either shape; both are acceptable spec output.
+const COMPLETENESS_RE = /Completeness:\s*(?:[A-Z]=)?\d{1,2}\/10/;
 const KIND_NOTE_RE = /options differ in kind/i;
 
 // v1.7.0.0 Pros/Cons format tokens. Tests are additive: existing