feat(v2): complete n8n workflow template (36 nodes) covering full V2 pipeline + shadow branch

- 14 new Code node drivers implementing the pipeline stages: normalize
  candidates, build context SQL, merge context + hash, decide AI need,
  prepare AI prompt, validate AI response, AI-disabled fallback, reuse
  cached classification, compute score, select top 10, prepare memory/
  envio records, build message/digest, compare legacy x V2, debug panel.
- Consolidated the two context queries (followups/tasks) into a single
  UNION ALL query tagged by tipo, and added a "Merge - Unir Shadow"
  synchronization node before comparing legacy x V2: n8n does not
  guarantee relative execution order between sibling branches that only
  share an early common ancestor, so cross-branch data was only safe to
  read by name once a real Merge node forced both to complete first.
- Reordered score calculation before the memory upsert (score is needed
  in the persisted row) and turned both Data Table writes into
  side-effect branches that fan out from the main path instead of
  gating it, so the Data Table node's own output shape never needs to
  carry the full pipeline state forward.
- Fixed a duplicate-identifier bug in the build script: score.js's
  require('./cooldown') survived inlining and collided with
  cooldown.js's own computeCooldown function in the same Code node
  scope. build-workflow.js now strips inter-module requires when
  inlining, and a new test syntax-checks every generated jsCode string
  plus asserts no leftover require() calls.

Co-Authored-By: Claude Sonnet 5 <noreply@anthropic.com>

n8n/nodes/compare-legacy-v2.node.js

@@ -0,0 +1,33 @@
+// Este node roda depois de "Merge - Unir Shadow" (append: Code - Montar Digest Coordenacao +
+// MySQL - Legado Top 10 (Shadow)), que existe so para GARANTIR que os dois ja executaram --
+// os dados continuam sendo lidos por nome, nao pelo item mesclado, para nao depender de ordem.
+const digestData = $('Code - Montar Digest Coordenacao').first().json; // { mensagem, selected, excluded, dateStr, digest, changedBlocked }
+const legacyRows = $('MySQL - Legado Top 10 (Shadow)').all().map((item) => item.json);
+
+const legacyIds = legacyRows.map((row) => Number(row.id));
+const v2Ids = digestData.selected.map((item) => Number(item.ticket.id));
+
+const added = v2Ids.filter((id) => !legacyIds.includes(id));
+const removed = legacyIds.filter((id) => !v2Ids.includes(id));
+
+const addedReasons = added.map((id) => {
+  const item = digestData.selected.find((s) => Number(s.ticket.id) === id);
+  return { id, motivo: item ? `${item.aiClassification.classification} - ${item.aiClassification.reason}` : 'desconhecido' };
+});
+const removedReasons = removed.map((id) => {
+  const excludedItem = digestData.excluded.find((e) => Number(e.ticket.id) === id);
+  return { id, motivo: excludedItem ? (excludedItem.exclusionReason || excludedItem.aiClassification.classification) : 'nao estava nos candidatos V2' };
+});
+
+return [{
+  json: {
+    run_at: Date.now(),
+    legacy_ids: JSON.stringify(legacyIds),
+    v2_ids: JSON.stringify(v2Ids),
+    added: JSON.stringify(added),
+    removed: JSON.stringify(removed),
+    summary: JSON.stringify({ addedReasons, removedReasons }),
+    mensagem: digestData.mensagem,
+    digest: digestData.digest,
+  },
+}];