fix(start-work): add CHECKED_CHECKBOX_PATTERN for plan progress tracking (#3066)

Plan progress now correctly counts checked checkboxes when determining
current task vs completed tasks.

TDD verified. tsc clean.

Closes #3066

src/features/boulder-state/storage.ts

@@ -196,8 +196,25 @@ export function findPrometheusPlans(directory: string): string[] {
   }
 }
 
+const TODO_HEADING_PATTERN = /^##\s+TODOs\b/i
+const FINAL_VERIFICATION_HEADING_PATTERN = /^##\s+Final Verification Wave\b/i
+const SECOND_LEVEL_HEADING_PATTERN = /^##\s+/
+const UNCHECKED_CHECKBOX_PATTERN = /^(\s*)[-*]\s*\[\s*\]\s*(.+)$/
+const CHECKED_CHECKBOX_PATTERN = /^(\s*)[-*]\s*\[[xX]\]\s*(.+)$/
+const TODO_TASK_PATTERN = /^\d+\.\s+/
+const FINAL_WAVE_TASK_PATTERN = /^F\d+\.\s+/i
+
+type ProgressSection = "todo" | "final-wave" | "other"
+
 /**
  * Parse a plan file and count checkbox progress.
+ *
+ * Only top-level (zero-indent) checkboxes under `## TODOs` and
+ * `## Final Verification Wave` sections are counted. The checkbox
+ * body must carry a valid task label (`N.` for TODOs, `FN.` for
+ * Final Verification Wave). Nested acceptance-criteria checkboxes
+ * and checkboxes in other sections are intentionally ignored so
+ * that progress tracking stays aligned with `readCurrentTopLevelTask`.
  */
 export function getPlanProgress(planPath: string): PlanProgress {
   if (!existsSync(planPath)) {
@@ -206,13 +223,47 @@ export function getPlanProgress(planPath: string): PlanProgress {
 
   try {
     const content = readFileSync(planPath, "utf-8")
-    
-    // Match markdown checkboxes: - [ ] or - [x] or - [X]
-    const uncheckedMatches = content.match(/^\s*[-*]\s*\[\s*\]/gm) || []
-    const checkedMatches = content.match(/^\s*[-*]\s*\[[xX]\]/gm) || []
+    const lines = content.split(/\r?\n/)
+    let section: ProgressSection = "other"
+    let total = 0
+    let completed = 0
 
-    const total = uncheckedMatches.length + checkedMatches.length
-    const completed = checkedMatches.length
+    for (const line of lines) {
+      if (SECOND_LEVEL_HEADING_PATTERN.test(line)) {
+        section = TODO_HEADING_PATTERN.test(line)
+          ? "todo"
+          : FINAL_VERIFICATION_HEADING_PATTERN.test(line)
+            ? "final-wave"
+            : "other"
+        continue
+      }
+
+      if (section !== "todo" && section !== "final-wave") {
+        continue
+      }
+
+      const checkedMatch = line.match(CHECKED_CHECKBOX_PATTERN)
+      const uncheckedMatch = checkedMatch ? null : line.match(UNCHECKED_CHECKBOX_PATTERN)
+      const match = checkedMatch ?? uncheckedMatch
+      if (!match) {
+        continue
+      }
+
+      if (match[1].length > 0) {
+        continue
+      }
+
+      const taskBody = match[2].trim()
+      const labelPattern = section === "todo" ? TODO_TASK_PATTERN : FINAL_WAVE_TASK_PATTERN
+      if (!labelPattern.test(taskBody)) {
+        continue
+      }
+
+      total++
+      if (checkedMatch) {
+        completed++
+      }
+    }
 
     return {
       total,