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/merge-context-hash.node.js

@@ -0,0 +1,28 @@
+// @requires context.js hash.js
+const candidatosBase = $('Code - Normalizar Candidatos Base').all().map((item) => item.json);
+const contextRows = $input.all().map((item) => item.json);
+
+function groupBy(rows, key) {
+  const map = {};
+  for (const row of rows) {
+    const k = String(row[key]);
+    if (!map[k]) map[k] = [];
+    map[k].push(row);
+  }
+  return map;
+}
+
+const followupRows = contextRows.filter((row) => row.tipo === 'followup');
+const taskRows = contextRows.filter((row) => row.tipo === 'task');
+
+const followupsByTicket = groupBy(followupRows, 'tickets_id');
+const tasksByTicket = groupBy(taskRows, 'tickets_id');
+
+return candidatosBase.map((base) => {
+  const idKey = String(base.id);
+  const followups = (followupsByTicket[idKey] || []).map((f) => ({ id: f.id, date: f.date, texto: f.texto }));
+  const tasks = (tasksByTicket[idKey] || []).map((t) => ({ id: t.id, date: t.date, status: t.status, texto: t.texto }));
+  const ticket = normalizeTicket(base, { followups, tasks });
+  const contextHash = buildContextFingerprint(ticket);
+  return { json: { ticket, contextHash } };
+});