feat: add template sync validation to prevent consumer repo sync failures

.github/scripts/__tests__/issue_scope_parser.test.js

@@ -709,3 +709,69 @@ test('handles nested bullets', () => {
     ].join('\n')
   );
 });
+
+test('preserves code blocks but does not add checkboxes inside them', () => {
+  const issue = [
+    '## Tasks',
+    '- Implement the feature',
+    '- Add documentation',
+    '',
+    '```python',
+    'def example():',
+    '    # Code example with bullet that should NOT get checkbox',
+    '    tasks = ["- item one", "- item two"]',
+    '```',
+    '',
+    '## Acceptance Criteria',
+    '- Feature works correctly',
+  ].join('\n');
+
+  const result = extractScopeTasksAcceptanceSections(issue);
+
+  // Real tasks should get checkboxes
+  assert.ok(result.includes('- [ ] Implement the feature'));
+  assert.ok(result.includes('- [ ] Add documentation'));
+  assert.ok(result.includes('- [ ] Feature works correctly'));
+
+  // Code block should be preserved but items inside should NOT have checkboxes
+  assert.ok(result.includes('```python'));
+  assert.ok(result.includes('def example():'));
+  // The bullet inside the code should NOT have [ ] added
+  assert.ok(!result.includes('- [ ] item one'));
+});
+
+test('handles multiple code blocks - preserves content without adding checkboxes', () => {
+  const issue = [
+    '## Tasks',
+    '- Real task one',
+    '',
+    '```yaml',
+    'tasks:',
+    '  - YAML example task',
+    '```',
+    '',
+    '- Real task two',
+    '',
+    '~~~markdown',
+    '- Markdown example in tilde fence',
+    '~~~',
+    '',
+    '## Acceptance Criteria',
+    '- Done',
+  ].join('\n');
+
+  const result = extractScopeTasksAcceptanceSections(issue);
+
+  // Real tasks outside code blocks get checkboxes
+  assert.ok(result.includes('- [ ] Real task one'));
+  assert.ok(result.includes('- [ ] Real task two'));
+  assert.ok(result.includes('- [ ] Done'));
+
+  // Code blocks are preserved
+  assert.ok(result.includes('```yaml'));
+  assert.ok(result.includes('~~~markdown'));
+
+  // But items inside code blocks do NOT get checkboxes added
+  assert.ok(result.includes('  - YAML example task'));  // preserved as-is
+  assert.ok(!result.includes('- [ ] YAML example task'));  // no checkbox added
+});

.github/scripts/issue_scope_parser.js

@@ -3,6 +3,13 @@
 const normalizeNewlines = (value) => String(value || '').replace(/\r\n/g, '\n');
 const stripBlockquotePrefixes = (value) =>
   String(value || '').replace(/^[ \t]*>+[ \t]?/gm, '');
+
+/**
+ * Check if a line is a code fence delimiter (``` or ~~~).
+ * Used to track code block boundaries when processing content.
+ */
+const isCodeFenceLine = (line) => /^(`{3,}|~{3,})/.test(line.trim());
+
 const LIST_ITEM_REGEX = /^(\s*)([-*+]|\d+[.)])\s+(.*)$/;
 
 const SECTION_DEFS = [
@@ -84,7 +91,20 @@ function normaliseChecklist(content) {
 
   const lines = raw.split('\n');
   let mutated = false;
+  let insideCodeBlock = false;
+
   const updated = lines.map((line) => {
+    // Track code fence boundaries - don't add checkboxes inside code blocks
+    if (isCodeFenceLine(line)) {
+      insideCodeBlock = !insideCodeBlock;
+      return line;
+    }
+
+    // Skip checkbox normalization for lines inside code blocks
+    if (insideCodeBlock) {
+      return line;
+    }
+
     const match = line.match(LIST_ITEM_REGEX);
     if (!match) {
       return line;
@@ -155,6 +175,7 @@ function isExplicitHeadingLine(rawLine) {
 function extractListBlocks(lines) {
   const blocks = [];
   let current = [];
+  let insideCodeBlock = false;
 
   const flush = () => {
     if (current.length) {
@@ -167,6 +188,24 @@ function extractListBlocks(lines) {
   };
 
   for (const line of lines) {
+    // Track code fence boundaries
+    if (isCodeFenceLine(line)) {
+      insideCodeBlock = !insideCodeBlock;
+      // Include code fence lines in current block if we're building one
+      if (current.length) {
+        current.push(line);
+      }
+      continue;
+    }
+
+    // Lines inside code blocks are treated as continuation (don't break the block)
+    if (insideCodeBlock) {
+      if (current.length) {
+        current.push(line);
+      }
+      continue;
+    }
+
     if (LIST_ITEM_REGEX.test(line)) {
       current.push(line);
       continue;
@@ -190,6 +229,7 @@ function extractListBlocksWithOffsets(lines) {
   let blockStart = null;
   let blockEnd = null;
   let offset = 0;
+  let insideCodeBlock = false;
 
   const flush = () => {
     if (!current.length) {
@@ -205,6 +245,27 @@ function extractListBlocksWithOffsets(lines) {
   };
 
   for (const line of lines) {
+    // Track code fence boundaries
+    if (isCodeFenceLine(line)) {
+      insideCodeBlock = !insideCodeBlock;
+      if (current.length) {
+        current.push(line);
+        blockEnd = offset + line.length;
+      }
+      offset += line.length + 1;
+      continue;
+    }
+
+    // Lines inside code blocks continue the current block
+    if (insideCodeBlock) {
+      if (current.length) {
+        current.push(line);
+        blockEnd = offset + line.length;
+      }
+      offset += line.length + 1;
+      continue;
+    }
+
     const isList = LIST_ITEM_REGEX.test(line);
     if (isList) {
       if (!current.length) {
@@ -377,23 +438,33 @@ function collectSections(source) {
   const lines = segment.split('\n');
   const listBlocks = extractListBlocksWithOffsets(lines);
   let offset = 0;
+  let insideCodeBlock = false;
   for (const line of lines) {
-    const matchedLabel = extractHeadingLabel(line);
-    if (matchedLabel) {
-      const title = matchedLabel.toLowerCase();
-      if (aliasLookup[title]) {
-        const section = aliasLookup[title];
-        headings.push({
-          title: section.key,
-          label: section.label,
-          index: offset,
-          length: line.length,
-          matchedLabel,
-        });
-      }
+    // Track code fence boundaries - skip heading detection inside code blocks
+    if (isCodeFenceLine(line)) {
+      insideCodeBlock = !insideCodeBlock;
+      offset += line.length + 1;
+      continue;
     }
-    if (isExplicitHeadingLine(line)) {
-      allHeadings.push({ index: offset, length: line.length });
+
+    if (!insideCodeBlock) {
+      const matchedLabel = extractHeadingLabel(line);
+      if (matchedLabel) {
+        const title = matchedLabel.toLowerCase();
+        if (aliasLookup[title]) {
+          const section = aliasLookup[title];
+          headings.push({
+            title: section.key,
+            label: section.label,
+            index: offset,
+            length: line.length,
+            matchedLabel,
+          });
+        }
+      }
+      if (isExplicitHeadingLine(line)) {
+        allHeadings.push({ index: offset, length: line.length });
+      }
     }
     offset += line.length + 1;
   }

.github/workflows/validate-template-sync.yml

@@ -0,0 +1,38 @@
+name: Validate Template Sync
+
+on:
+  pull_request:
+    paths:
+      - '.github/scripts/**/*.js'
+      - 'templates/consumer-repo/.github/scripts/**/*.js'
+  push:
+    branches: [main]
+    paths:
+      - '.github/scripts/**/*.js'
+      - 'templates/consumer-repo/.github/scripts/**/*.js'
+
+jobs:
+  validate:
+    runs-on: ubuntu-latest
+    steps:
+      - uses: actions/checkout@v4
+
+      - name: Set up Python
+        uses: actions/setup-python@v5
+        with:
+          python-version: '3.11'
+
+      - name: Validate template sync
+        run: |
+          python scripts/validate_template_sync.py
+          if [ $? -ne 0 ]; then
+            echo ""
+            echo "❌ FAILED: Template files are out of sync!"
+            echo ""
+            echo "To fix this error:"
+            echo "  1. Run: ./scripts/sync_templates.sh"
+            echo "  2. Commit the changes to templates/consumer-repo/"
+            echo "  3. Push to your branch"
+            echo ""
+            exit 1
+          fi

docs/CONTRIBUTING.md

@@ -75,8 +75,27 @@ Before submitting changes, run the validation scripts:
 
 # Comprehensive check (30-120 seconds)
 ./scripts/check_branch.sh
+
+# Template sync validation (if you modified .github/scripts/)
+python scripts/validate_template_sync.py
 ```
 
+### ⚠️ CRITICAL: Template Sync Guard
+
+**If you modify any file in `.github/scripts/`, you MUST also update the template:**
+
+```bash
+# After editing .github/scripts/*.js, run:
+./scripts/sync_templates.sh
+
+# Verify sync:
+python scripts/validate_template_sync.py
+```
+
+**Why?** Consumer repos get workflow updates via `templates/consumer-repo/`. If you only update `.github/scripts/` but not the template, your changes won't sync to consumer repos and no sync PRs will be created.
+
+The CI will fail if templates are out of sync with source files.
+
 ## Code Style
 
 ### Python

scripts/langchain/capability_check.py

@@ -177,7 +177,7 @@ def _is_multi_action_task(task: str) -> bool:
         return True
     if any(sep in lowered for sep in (" and ", " + ", " & ", " then ", "; ")):
         return True
-    return bool("," in task or "/" in task or re.search(r"\s\+\s", lowered))
+    return bool("," in task or " / " in task or re.search(r"\s\+\s", lowered))
 
 
 def _requires_admin_access(task: str) -> bool:

scripts/langchain/issue_optimizer.py

@@ -470,7 +470,7 @@ def _is_large_task(task: str) -> bool:
         return True
     if any(sep in lowered for sep in (" and ", " + ", " & ", " then ", "; ")):
         return True
-    return bool(re.search(r"\s\+\s", lowered) or ", " in task or "/" in task)
+    return bool(re.search(r"\s\+\s", lowered) or ", " in task or " / " in task)
 
 
 def _detect_task_splitting(tasks: list[str], *, use_llm: bool = False) -> list[dict[str, Any]]:

scripts/langchain/task_decomposer.py

@@ -167,8 +167,10 @@ def _split_task_parts(task: str) -> list[str]:
         parts = [part.strip() for part in task.split(";") if part.strip()]
     elif ", " in task:
         parts = [part.strip() for part in task.split(",") if part.strip()]
-    elif " / " in task or "/" in task:
-        parts = [part.strip() for part in re.split(r"\s*/\s*", task) if part.strip()]
+    elif " / " in task:
+        # Only split on spaced slashes to avoid splitting compound words
+        # like "additions/removals" or paths like "src/utils"
+        parts = [part.strip() for part in task.split(" / ") if part.strip()]
     else:
         parts = [task]
     return [part for part in parts if part]

scripts/sync_templates.sh

@@ -0,0 +1,34 @@
+#!/bin/bash
+# Sync source scripts to template directory
+set -e
+
+SOURCE_DIR=".github/scripts"
+TEMPLATE_DIR="templates/consumer-repo/.github/scripts"
+
+echo "🔄 Syncing scripts to template directory..."
+
+# Get list of files to sync (exclude tests)
+FILES=$(find "$SOURCE_DIR" -name "*.js" -type f \
+    | grep -v "__tests__" \
+    | grep -v ".test.js" \
+    | sed "s|^$SOURCE_DIR/||")
+
+synced=0
+for file in $FILES; do
+    source_file="$SOURCE_DIR/$file"
+    template_file="$TEMPLATE_DIR/$file"
+
+    if [ -f "$template_file" ]; then
+        if ! cmp -s "$source_file" "$template_file"; then
+            echo "  ✓ Syncing $file"
+            cp "$source_file" "$template_file"
+            ((synced++))
+        fi
+    fi
+done
+
+if [ $synced -eq 0 ]; then
+    echo "✅ All files already in sync"
+else
+    echo "✅ Synced $synced file(s)"
+fi