[SITES-40704] Add suggestion data validation using shared Joi schemas

src/accessibility/utils/data-processing.js

@@ -20,6 +20,7 @@ import {
 import { isoCalendarWeek } from '@adobe/spacecat-shared-utils';
 import { getObjectFromKey, getObjectKeysUsingPrefix } from '../../utils/s3-utils.js';
 import { extractMainDomainName } from '../../support/utils.js';
+import { warnOnInvalidSuggestionData } from '../../utils/data-access.js';
 import {
   createReportOpportunitySuggestionInstance,
   createInDepthReportOpportunity,
@@ -652,6 +653,7 @@ export async function createOrUpdateDeviceSpecificSuggestion(
       // Update only the suggestionValue field to avoid ElectroDB timestamp conflicts
       const newData = { ...currentData, suggestionValue: suggestions[0].data.suggestionValue };
 
+      warnOnInvalidSuggestionData(newData, opportunity.getType(), log);
       existingSuggestion.setData(newData);
       await existingSuggestion.save();
 

src/accessibility/utils/generate-individual-opportunities.js

@@ -21,6 +21,7 @@ import { createAccessibilityAssistiveOpportunity, createAccessibilityColorContra
 import {
   syncSuggestions,
   keepSameDataFunction,
+  warnOnInvalidSuggestionData,
 } from '../../utils/data-access.js';
 import {
   successCriteriaLinks, accessibilityOpportunitiesMap, URL_SOURCE_SEPARATOR, issueTypesForCodeFix,
@@ -1106,6 +1107,7 @@ export async function handleAccessibilityRemediationGuidance(message, context) {
         };
 
         // Update the suggestion
+        warnOnInvalidSuggestionData(updatedSuggestionData, opportunity.getType(), log);
         targetSuggestion.setData(updatedSuggestionData);
         processingPromises.push({
           promise: targetSuggestion.save(),

src/backlinks/handler.js

@@ -21,7 +21,7 @@ import { AuditBuilder } from '../common/audit-builder.js';
 import calculateKpiMetrics from './kpi-metrics.js';
 import { convertToOpportunity } from '../common/opportunity.js';
 import { createOpportunityData } from './opportunity-data-mapper.js';
-import { syncSuggestionsWithPublishDetection } from '../utils/data-access.js';
+import { syncSuggestionsWithPublishDetection, warnOnInvalidSuggestionData } from '../utils/data-access.js';
 import { filterByAuditScope, extractPathPrefix } from '../internal-links/subpath-filter.js';
 import {
   filterBrokenSuggestedUrls,
@@ -420,11 +420,13 @@ export const generateSuggestionData = async (context) => {
         return;
       }
 
-      suggestion.setData({
+      const updatedData = {
         ...suggestion.getData(),
         urlsSuggested,
         aiRationale: `The suggested URL is chosen based on top search results for closely matching keywords from the broken URL. Keywords used: "${keywords}".`,
-      });
+      };
+      warnOnInvalidSuggestionData(updatedData, opportunity.getType(), log);
+      suggestion.setData(updatedData);
 
       await suggestion.save();
       resolvedByBrightData.add(brokenLink.suggestionId);

src/broken-links-guidance/guidance-handler.js

@@ -13,6 +13,7 @@
 import { badRequest, notFound, ok } from '@adobe/spacecat-shared-http-utils';
 import { isValidUrl } from '@adobe/spacecat-shared-utils';
 import { filterBrokenSuggestedUrls } from '../utils/url-utils.js';
+import { warnOnInvalidSuggestionData } from '../utils/data-access.js';
 
 export default async function handler(message, context) {
   const { log, dataAccess } = context;
@@ -103,11 +104,13 @@ export default async function handler(message, context) {
       aiRationale = '';
     }
 
-    suggestion.setData({
+    const updatedData = {
       ...suggestion.getData(),
       urlsSuggested: filteredSuggestedUrls,
       aiRationale,
-    });
+    };
+    warnOnInvalidSuggestionData(updatedData, opportunity.getType(), log);
+    suggestion.setData(updatedData);
 
     return suggestion.save();
   }));

src/experimentation-opportunities/guidance-high-organic-low-ctr-handler.js

@@ -13,6 +13,7 @@
 import { notFound, ok } from '@adobe/spacecat-shared-http-utils';
 import { Suggestion as SuggestionModel } from '@adobe/spacecat-shared-data-access';
 import { convertToOpportunityEntity } from './opportunity-data-mapper.js';
+import { warnOnInvalidSuggestionData } from '../utils/data-access.js';
 /**
  * Checks if any suggestions in the array were manually modified (updatedBy !== 'system')
  * @param {Array} suggestions - Array of suggestion objects
@@ -96,6 +97,7 @@ export default async function handler(message, context) {
     },
   };
 
+  warnOnInvalidSuggestionData(suggestionData.data, opportunity.getType(), log);
   await Suggestion.create(suggestionData);
 
   return ok();

src/image-alt-text/opportunityHandler.js

@@ -18,6 +18,7 @@ import {
   CPC, PENALTY_PER_IMAGE, RUM_INTERVAL, ALT_TEXT_GUIDANCE_TYPE, ALT_TEXT_OBSERVATION,
   MYSTIQUE_BATCH_SIZE,
 } from './constants.js';
+import { warnOnInvalidSuggestionData } from '../utils/data-access.js';
 
 const AUDIT_TYPE = AuditModel.AUDIT_TYPES.ALT_TEXT;
 
@@ -53,6 +54,8 @@ export async function syncAltTextSuggestions({ opportunity, newSuggestionDTOs, l
 
   // Add new suggestions to oppty
   if (isNonEmptyArray(suggestionsToAdd)) {
+    const opportunityType = opportunity.getType?.();
+    suggestionsToAdd.forEach((s) => warnOnInvalidSuggestionData(s.data, opportunityType, log));
     const updateResult = await opportunity.addSuggestions(suggestionsToAdd);
 
     if (isNonEmptyArray(updateResult.errorItems)) {
@@ -251,6 +254,8 @@ export async function addAltTextSuggestions({ opportunity, newSuggestionDTOs, lo
     return;
   }
 
+  const opportunityType = opportunity.getType?.();
+  newSuggestionDTOs.forEach((s) => warnOnInvalidSuggestionData(s.data, opportunityType, log));
   const updateResult = await opportunity.addSuggestions(newSuggestionDTOs);
 
   if (isNonEmptyArray(updateResult.errorItems)) {

src/internal-links/handler.js

@@ -39,6 +39,7 @@ import {
 import { createAuditLogger } from '../common/context-logger.js';
 import BrightDataClient from '../support/bright-data-client.js';
 import { sleep } from '../support/utils.js';
+import { warnOnInvalidSuggestionData } from '../utils/data-access.js';
 
 const { AUDIT_STEP_DESTINATIONS } = Audit;
 const INTERVAL = 30; // days
@@ -573,11 +574,13 @@ export const opportunityAndSuggestionsStep = async (context) => {
         return;
       }
 
-      suggestion.setData({
+      const updatedData = {
         ...suggestion.getData(),
         urlsSuggested,
         aiRationale: `The suggested URL is chosen based on top search results for closely matching keywords from the broken URL. Keywords used: "${keywords}".`,
-      });
+      };
+      warnOnInvalidSuggestionData(updatedData, opportunity.getType(), log);
+      suggestion.setData(updatedData);
 
       await suggestion.save();
       resolvedByBrightData.add(brokenLink.suggestionId);

src/metatags-guidance/guidance-handler.js

@@ -11,6 +11,7 @@
  */
 
 import { badRequest, notFound, ok } from '@adobe/spacecat-shared-http-utils';
+import { warnOnInvalidSuggestionData } from '../utils/data-access.js';
 
 export default async function handler(message, context) {
   const { log, dataAccess } = context;
@@ -75,11 +76,13 @@ export default async function handler(message, context) {
       );
     }
 
-    suggestion.setData({
+    const updatedData = {
       ...suggestion.getData(),
       aiSuggestion: aiSuggestion || '',
       aiRationale: aiRationale || '',
-    });
+    };
+    warnOnInvalidSuggestionData(updatedData, opportunity.getType(), log);
+    suggestion.setData(updatedData);
 
     return suggestion.save();
   }));

src/no-cta-above-the-fold/guidance-handler.js

@@ -15,6 +15,7 @@ import {
   mapToSuggestion,
 } from './guidance-opportunity-mapper.js';
 import { createPaidLogger } from '../paid/paid-log.js';
+import { warnOnInvalidSuggestionData } from '../utils/data-access.js';
 
 const GUIDANCE_TYPE = 'no-cta-above-the-fold';
 
@@ -87,6 +88,7 @@ export default async function handler(message, context) {
     guidanceParsed,
   );
 
+  warnOnInvalidSuggestionData(suggestionData.data, opportunity.getType(), log);
   await Suggestion.create(suggestionData);
   paidLog.createdSuggestion(opportunity.getId(), siteId, url, auditId);
 

src/paid-cookie-consent/guidance-handler.js

@@ -13,6 +13,7 @@ import { ok, notFound } from '@adobe/spacecat-shared-http-utils';
 import { mapToPaidOpportunity, mapToPaidSuggestion, isLowSeverityGuidanceBody } from './guidance-opportunity-mapper.js';
 import { getAuditData } from './audit-data-provider.js';
 import { createPaidLogger } from '../paid/paid-log.js';
+import { warnOnInvalidSuggestionData } from '../utils/data-access.js';
 
 const GUIDANCE_TYPE = 'paid-cookie-consent';
 
@@ -67,6 +68,7 @@ export default async function handler(message, context) {
     url,
     guidanceParsed,
   );
+  warnOnInvalidSuggestionData(suggestionData.data, opportunity.getType(), log);
   await Suggestion.create(suggestionData);
   paidLog.createdSuggestion(opportunity.getId(), siteId, url, auditId);
 

src/paid-keyword-optimizer/guidance-handler.js

@@ -16,6 +16,7 @@ import {
   isLowSeverityGuidanceBody,
 } from './guidance-opportunity-mapper.js';
 import { createPaidLogger } from '../paid/paid-log.js';
+import { warnOnInvalidSuggestionData } from '../utils/data-access.js';
 
 const GUIDANCE_TYPE = 'ad-intent-mismatch';
 
@@ -70,6 +71,7 @@ export default async function handler(message, context) {
     opportunity.getId(),
     message,
   );
+  warnOnInvalidSuggestionData(suggestionData.data, opportunity.getType(), log);
   await Suggestion.create(suggestionData);
   paidLog.createdSuggestion(opportunity.getId(), siteId, url, auditId);
 

src/paid-traffic-analysis/guidance-handler.js

@@ -14,6 +14,7 @@ import { randomUUID } from 'crypto';
 import { Suggestion as SuggestionModel } from '@adobe/spacecat-shared-data-access';
 import { DATA_SOURCES } from '../common/constants.js';
 import { createPaidLogger } from '../paid/paid-log.js';
+import { warnOnInvalidSuggestionData } from '../utils/data-access.js';
 
 const GUIDANCE_TYPE = 'guidance:traffic-analysis';
 const TRAFFIC_OPP_TYPE = 'paid-traffic';
@@ -129,10 +130,13 @@ export default async function handler(message, context) {
       ? SuggestionModel.STATUSES.PENDING_VALIDATION
       : SuggestionModel.STATUSES.NEW;
 
-    await Promise.all(suggestions.map((s) => Suggestion.create({
-      ...s,
-      status,
-    })));
+    await Promise.all(suggestions.map((s) => {
+      warnOnInvalidSuggestionData(s.data, opportunity.getType(), log);
+      return Suggestion.create({
+        ...s,
+        status,
+      });
+    }));
   }
 
   // Only after successful opportunity and suggestions creation, ignore previous ones

src/prerender/guidance-handler.js

@@ -12,6 +12,7 @@
 
 import { badRequest, notFound, ok } from '@adobe/spacecat-shared-http-utils';
 import { isPaidLLMOCustomer } from './utils/utils.js';
+import { warnOnInvalidSuggestionData } from '../utils/data-access.js';
 
 const LOG_PREFIX = 'Prerender -';
 
@@ -192,6 +193,7 @@ export default async function handler(message, context) {
         valuable: isValuable,
       };
 
+      warnOnInvalidSuggestionData(updatedData, opportunity.getType(), log);
       existing.setData(updatedData);
       suggestionsToSave.push(existing);
     });

src/readability/opportunities/guidance-handler.js

@@ -11,6 +11,7 @@
  */
 
 import { ok, notFound } from '@adobe/spacecat-shared-http-utils';
+import { warnOnInvalidSuggestionData } from '../../utils/data-access.js';
 
 /**
  * Enriches suggestion data with fileds required for auto-optimize.
@@ -181,6 +182,7 @@ export default async function handler(message, context) {
           // Enrich with auto-optimize data only after validating improvedText
           const enrichedData = enrichSuggestionDataForAutoOptimize(updatedData);
 
+          warnOnInvalidSuggestionData(enrichedData, readabilityOpportunity.getType(), log);
           await matchingSuggestion.setData(enrichedData);
           await matchingSuggestion.save();
 

src/structured-data/guidance-handler.js

@@ -11,6 +11,7 @@
  */
 
 import { badRequest, notFound, ok } from '@adobe/spacecat-shared-http-utils';
+import { warnOnInvalidSuggestionData } from '../utils/data-access.js';
 
 export default async function handler(message, context) {
   const { log, dataAccess } = context;
@@ -53,7 +54,7 @@ export default async function handler(message, context) {
     return notFound('Suggestion not found');
   }
 
-  suggestion.setData({
+  const updatedData = {
     ...suggestion.getData(),
     errors: (remediations || []).map((remediation) => (
       {
@@ -62,7 +63,9 @@ export default async function handler(message, context) {
         errorTitle: remediation.error_title,
         fix: remediation.corrected_markup,
       })),
-  });
+  };
+  warnOnInvalidSuggestionData(updatedData, opportunity.getType(), log);
+  suggestion.setData(updatedData);
   await suggestion.save();
   return ok();
 }

src/utils/data-access.js

@@ -31,6 +31,22 @@ export const AUTHOR_ONLY_OPPORTUNITY_TYPES = [
   'security-permissions',
 ];
 
+/**
+ * Validates suggestion data against the Joi schema for the given opportunity type.
+ * Logs a warning if validation fails but does not block the operation.
+ *
+ * @param {Object} data - Suggestion data to validate.
+ * @param {string} opportunityType - The opportunity type from OPPORTUNITY_TYPES enum.
+ * @param {Object} log - Logger object.
+ */
+export function warnOnInvalidSuggestionData(data, opportunityType, log) {
+  try {
+    SuggestionDataAccess.validateData(data, opportunityType);
+  } catch (error) {
+    log.warn(`Suggestion data validation warning [${opportunityType}]: ${error.message}`);
+  }
+}
+
 /**
  * Safely stringify an object for logging, truncating large arrays to prevent
  * exceeding JavaScript's maximum string length.
@@ -351,6 +367,8 @@ export async function syncSuggestions({
 
   log.debug(`Existing suggestions = ${existingSuggestions.length}: ${safeStringify(existingSuggestions)}`);
 
+  const opportunityType = opportunity.getType?.();
+
   // Update existing suggestions - O(N) with Map lookup
   await Promise.all(
     existingSuggestions
@@ -361,7 +379,9 @@ export async function syncSuggestions({
       .map((existing) => {
         const existingKey = buildKey(existing.getData());
         const newDataItem = newDataByKey.get(existingKey);
-        existing.setData(mergeDataFunction(existing.getData(), newDataItem));
+        const mergedData = mergeDataFunction(existing.getData(), newDataItem);
+        warnOnInvalidSuggestionData(mergedData, opportunityType, log);
+        existing.setData(mergedData);
 
         // Use the merge status function to determine if status should change
         const newStatus = mergeStatusFunction(existing, newDataItem, context);
@@ -387,6 +407,10 @@ export async function syncSuggestions({
         status: requiresValidation ? SuggestionDataAccess.STATUSES.PENDING_VALIDATION
           : SuggestionDataAccess.STATUSES.NEW,
       };
+    })
+    .map((suggestion) => {
+      warnOnInvalidSuggestionData(suggestion.data, opportunityType, log);
+      return suggestion;
     });
 
   // Add new suggestions if any

src/vulnerabilities-code-fix/handler.js

@@ -14,6 +14,7 @@ import { badRequest, notFound, ok } from '@adobe/spacecat-shared-http-utils';
 import { Audit } from '@adobe/spacecat-shared-data-access';
 import { isNonEmptyArray } from '@adobe/spacecat-shared-utils';
 import { getObjectFromKey } from '../utils/s3-utils.js';
+import { warnOnInvalidSuggestionData } from '../utils/data-access.js';
 
 const AUDIT_TYPE = Audit.AUDIT_TYPES.SECURITY_VULNERABILITIES;
 
@@ -191,11 +192,13 @@ export default async function handler(message, context) {
       return;
     }
 
-    suggestion.setData({
+    const updatedData = {
       ...suggestion.getData(),
       patchContent: reportData.diff,
       isCodeChangeAvailable: true,
-    });
+    };
+    warnOnInvalidSuggestionData(updatedData, AUDIT_TYPE, log);
+    suggestion.setData(updatedData);
 
     suggestion.save();
   }));

test/audits/accessibility/data-processing.test.js

@@ -5529,6 +5529,7 @@ describe('data-processing utility functions', () => {
       mockOpportunity = {
         getSuggestions: sandbox.stub().resolves([mockExistingSuggestion]),
         addSuggestions: sandbox.stub().resolves({ id: 'new-sugg' }),
+        getType: () => 'accessibility',
       };
     });