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/prepare-ai-prompt.node.js

@@ -0,0 +1,57 @@
+// @requires context.js
+const VALID_CLASSIFICATIONS = [
+  'ACTIONABLE_NOW', 'UNASSIGNED_ACTIONABLE', 'WAITING_REQUESTER', 'WAITING_VENDOR',
+  'WAITING_APPROVAL', 'SCHEDULED', 'DEPENDENCY_BLOCKED', 'NEEDS_COORDINATION',
+  'PROJECT_LONG_TERM', 'DUPLICATE_OR_OBSOLETE', 'INSUFFICIENT_CONTEXT',
+];
+
+const systemPrompt = [
+  'Voce e um analisador operacional de chamados de TI (GLPI). Voce NAO e um atendente e NAO conversa com o usuario.',
+  'Use SOMENTE as informacoes fornecidas abaixo sobre o chamado. Nunca invente fatos.',
+  'Distinga evidencia (o que esta escrito no chamado) de inferencia (sua conclusao).',
+  'SLA vencido sozinho NAO e evidencia de que existe uma acao executavel agora.',
+  'Idade do chamado sozinha NAO e evidencia de acionabilidade.',
+  'Identifique: existe acao executavel hoje? quem pode executar? existe bloqueio? quem segura o bloqueio? qual a proxima acao concreta? existe data conhecida para revisao? existe evidencia nos apontamentos que justifique a conclusao?',
+  'Se a informacao for insuficiente para decidir com confianca, use a classificacao INSUFFICIENT_CONTEXT e confidence baixo -- nao invente uma acao.',
+  `Responda em JSON estrito com os campos: classification (uma de: ${VALID_CLASSIFICATIONS.join(', ')}), actionable_today (boolean), confidence (0 a 1), blocker_type, waiting_for, next_action (curto, poucas palavras, sem paragrafo), suggested_action_type, business_risk (low|medium|high), reason (uma frase), evidence (lista curta de evidencias textuais encontradas).`,
+].join('\n');
+
+return $input.all().map((item) => {
+  const data = item.json;
+  const userPrompt = buildAiContextText(data.ticket, data.config.aiMaxContextChars);
+
+  const requestBody = {
+    model: data.config.aiModel,
+    temperature: 0.1,
+    response_format: {
+      type: 'json_schema',
+      json_schema: {
+        name: 'ticket_classification',
+        strict: true,
+        schema: {
+          type: 'object',
+          additionalProperties: false,
+          properties: {
+            classification: { type: 'string', enum: VALID_CLASSIFICATIONS },
+            actionable_today: { type: 'boolean' },
+            confidence: { type: 'number' },
+            blocker_type: { type: ['string', 'null'] },
+            waiting_for: { type: ['string', 'null'] },
+            next_action: { type: 'string' },
+            suggested_action_type: { type: 'string' },
+            business_risk: { type: 'string' },
+            reason: { type: 'string' },
+            evidence: { type: 'array', items: { type: 'string' } },
+          },
+          required: ['classification', 'actionable_today', 'confidence', 'blocker_type', 'waiting_for', 'next_action', 'suggested_action_type', 'business_risk', 'reason', 'evidence'],
+        },
+      },
+    },
+    messages: [
+      { role: 'system', content: systemPrompt },
+      { role: 'user', content: userPrompt },
+    ],
+  };
+
+  return { json: { ...data, requestBody } };
+});