feat(tests): integrate SmartAi/DualAgentOrchestrator into extraction tests and add JSON self-validation

test/test.invoices.nanonets.ts

@@ -13,7 +13,7 @@ import { execSync } from 'child_process';
 import * as os from 'os';
 import { ensureNanonetsOcr, ensureMiniCpm, isContainerRunning } from './helpers/docker.js';
 import { SmartAi } from '@push.rocks/smartai';
-import { DualAgentOrchestrator } from '@push.rocks/smartagent';
+import { DualAgentOrchestrator, JsonValidatorTool } from '@push.rocks/smartagent';
 
 const NANONETS_URL = 'http://localhost:8000/v1';
 const NANONETS_MODEL = 'nanonets/Nanonets-OCR2-3B';
@@ -76,11 +76,11 @@ Page numbers should be wrapped in brackets. Ex: <page_number>14</page_number>.`;
 const JSON_EXTRACTION_PROMPT = `Extract key fields from the invoice. Return ONLY valid JSON.
 
 WHERE TO FIND DATA:
-- invoice_number, invoice_date, vendor_name: Look in the HEADER section at the TOP of PAGE 1 (near "Invoice no.", "Invoice date:", "Rechnungsnummer")
+- invoice_number, invoice_date, vendor_name: Look in the HEADER section at the TOP of PAGE 1 (near "Invoice no.", "Invoice date:", "Rechnungsnummer"). Use common sense. Btw. an invoice number might start on INV* .
 - net_amount, vat_amount, total_amount: Look in the SUMMARY section at the BOTTOM (look for "Total", "Amount due", "Gesamtbetrag")
 
 RULES:
-1. invoice_number: Extract ONLY the value (e.g., "R0015632540"), NOT the label "Invoice no."
+1. Use common sense.
 2. invoice_date: Convert to YYYY-MM-DD format (e.g., "14/04/2022" → "2022-04-14")
 3. vendor_name: The company issuing the invoice
 4. currency: EUR, USD, or GBP
@@ -643,18 +643,27 @@ tap.test('Stage 2: Setup Ollama + GPT-OSS 20B', async () => {
     guardianPolicyPrompt: `
       JSON EXTRACTION POLICY:
       - APPROVE all JSON extraction tasks
+      - APPROVE all json.validate tool calls
       - This is a read-only operation - no file system or network access needed
       - The task is to extract structured data from document text
     `,
     driverSystemMessage: `You are a precise JSON extraction assistant. Your only job is to extract invoice data from documents.
 
 CRITICAL RULES:
-1. Output ONLY valid JSON - no markdown, no explanations, no thinking
-2. Use the exact format requested
-3. If you cannot find a value, use empty string "" or 0 for numbers
+1. Output valid JSON with the exact format requested
+2. If you cannot find a value, use empty string "" or 0 for numbers
+3. IMPORTANT: Before completing, validate your JSON using the json.validate tool:
+
+<tool_call>
+  <tool>json</tool>
+  <action>validate</action>
+  <params>{"jsonString": "YOUR_JSON", "requiredFields": ["invoice_number", "invoice_date", "vendor_name", "currency", "net_amount", "vat_amount", "total_amount"]}</params>
+</tool_call>
+
+4. Only complete after validation passes
 
 When done, wrap your JSON in <task_complete></task_complete> tags.`,
-    maxIterations: 3,
+    maxIterations: 5,
     // Enable streaming for real-time progress visibility
     onToken: (token, source) => {
       if (source === 'driver') {
@@ -663,7 +672,9 @@ When done, wrap your JSON in <task_complete></task_complete> tags.`,
     },
   });
 
-  // No tools needed for JSON extraction
+  // Register JsonValidatorTool for self-validation
+  orchestrator.registerTool(new JsonValidatorTool());
+
   console.log('  [SmartAgent] Starting orchestrator...');
   await orchestrator.start();
   console.log('  [SmartAgent] Ready for extraction');