fix(boulder): support both structured and simple plan formats in getPlanProgress

Structured plans (with ## TODOs section) use strict numbered-label
parsing. Simple plans (without sections) fall back to regex checkbox
counting. This fixes 9 test failures from the #3066 merge.

src/features/boulder-state/storage.ts

@@ -224,6 +224,24 @@ export function getPlanProgress(planPath: string): PlanProgress {
   try {
     const content = readFileSync(planPath, "utf-8")
     const lines = content.split(/\r?\n/)
+
+    // Check if the plan has structured sections (## TODOs / ## Final Verification Wave)
+    const hasStructuredSections = lines.some((line) => TODO_HEADING_PATTERN.test(line))
+
+    if (hasStructuredSections) {
+      // Structured plan: only count top-level checkboxes with numbered labels
+      // under ## TODOs and ## Final Verification Wave sections
+      return getStructuredPlanProgress(lines)
+    }
+
+    // Simple plan: count all top-level checkboxes anywhere
+    return getSimplePlanProgress(content)
+  } catch {
+    return { total: 0, completed: 0, isComplete: true }
+  }
+}
+
+function getStructuredPlanProgress(lines: string[]): PlanProgress {
   let section: ProgressSection = "other"
   let total = 0
   let completed = 0
@@ -270,8 +288,19 @@ export function getPlanProgress(planPath: string): PlanProgress {
     completed,
     isComplete: total > 0 && completed === total,
   }
-  } catch {
+}
-    return { total: 0, completed: 0, isComplete: true }
+
+function getSimplePlanProgress(content: string): PlanProgress {
+  const uncheckedMatches = content.match(/^\s*[-*]\s*\[\s*\]/gm) || []
+  const checkedMatches = content.match(/^\s*[-*]\s*\[[xX]\]/gm) || []
+
+  const total = uncheckedMatches.length + checkedMatches.length
+  const completed = checkedMatches.length
+
+  return {
+    total,
+    completed,
+    isComplete: total > 0 && completed === total,
   }
 }