@adobe/spacecat-shared-data-access 3.44.0 → 3.45.0

package/CHANGELOG.md

@@ -1,3 +1,10 @@
+## [@adobe/spacecat-shared-data-access-v3.45.0](https://github.com/adobe/spacecat-shared/compare/@adobe/spacecat-shared-data-access-v3.44.0...@adobe/spacecat-shared-data-access-v3.45.0) (2026-04-04)
+
+### Features
+
+* Manage a custom list of audit target URLs ([#1484](https://github.com/adobe/spacecat-shared/issues/1484)) ([06c54d8](https://github.com/adobe/spacecat-shared/commit/06c54d89ea2488f6951cc96b9458521ac9d26706))
+* update suggestion data schemas for some of the opportunities ([#1466](https://github.com/adobe/spacecat-shared/issues/1466)) ([a09e968](https://github.com/adobe/spacecat-shared/commit/a09e968bba9235813451b65defe7d133a8956711))
+
 ## [@adobe/spacecat-shared-data-access-v3.44.0](https://github.com/adobe/spacecat-shared/compare/@adobe/spacecat-shared-data-access-v3.43.0...@adobe/spacecat-shared-data-access-v3.44.0) (2026-04-02)
 
 ### Features

package/package.json

@@ -1,6 +1,6 @@
 {
   "name": "@adobe/spacecat-shared-data-access",
-  "version": "3.44.0",
+  "version": "3.45.0",
   "description": "Shared modules of the Spacecat Services - Data Access",
   "type": "module",
   "engines": {

package/src/models/site/config.js

@@ -400,6 +400,11 @@ export const configSchema = Joi.object({
   contentAiConfig: Joi.object({
     index: Joi.string().optional(),
   }).optional(),
+  auditTargetURLs: Joi.object({
+    manual: Joi.array().items(Joi.object({
+      url: Joi.string().uri().required(),
+    })).optional().default([]),
+  }).options({ stripUnknown: true }).optional(),
   handlers: Joi.object().pattern(Joi.string(), Joi.object({
     mentions: Joi.object().pattern(Joi.string(), Joi.array().items(Joi.string())),
     excludedURLs: Joi.array().items(Joi.string()),
@@ -510,6 +515,60 @@ export const Config = (data = {}) => {
   self.getEdgeOptimizeConfig = () => state?.edgeOptimizeConfig;
   self.getOnboardConfig = () => state?.onboardConfig;
   self.getCommerceLlmoConfig = () => state?.commerceLlmoConfig;
+  const AUDIT_TARGET_SOURCES = ['manual'];
+  const auditTargetEntrySchema = Joi.object({
+    url: Joi.string().uri().required(),
+  });
+
+  const validateAuditTargetSource = (source) => {
+    if (!AUDIT_TARGET_SOURCES.includes(source)) {
+      throw new Error(`Invalid audit target source: "${source}". Must be one of: ${AUDIT_TARGET_SOURCES.join(', ')}`);
+    }
+  };
+
+  self.getAuditTargetURLsConfig = () => state?.auditTargetURLs;
+
+  self.getAuditTargetURLs = () => {
+    const targets = state?.auditTargetURLs;
+    if (!targets) return [];
+    return AUDIT_TARGET_SOURCES.flatMap(
+      (source) => (targets[source] || []).map((entry) => ({ ...entry, source })),
+    );
+  };
+
+  self.getAuditTargetURLsBySource = (source) => {
+    validateAuditTargetSource(source);
+    return state?.auditTargetURLs?.[source] || [];
+  };
+
+  self.updateAuditTargetURLs = (source, urls) => {
+    validateAuditTargetSource(source);
+    Joi.assert(urls, Joi.array().items(auditTargetEntrySchema), 'Invalid audit target URLs');
+    state.auditTargetURLs = state.auditTargetURLs || {};
+    state.auditTargetURLs[source] = urls;
+  };
+
+  self.addAuditTargetURL = (source, urlObj) => {
+    validateAuditTargetSource(source);
+    Joi.assert(urlObj, auditTargetEntrySchema, 'Invalid audit target URL');
+
+    state.auditTargetURLs = state.auditTargetURLs || {};
+    state.auditTargetURLs[source] = state.auditTargetURLs[source] || [];
+    const allUrls = AUDIT_TARGET_SOURCES.flatMap(
+      (s) => (state.auditTargetURLs[s] || []).map((e) => e.url),
+    );
+    if (!allUrls.includes(urlObj.url)) {
+      state.auditTargetURLs[source].push(urlObj);
+    }
+  };
+
+  self.removeAuditTargetURL = (source, url) => {
+    validateAuditTargetSource(source);
+    if (!state.auditTargetURLs?.[source]) return;
+    state.auditTargetURLs[source] = state.auditTargetURLs[source]
+      .filter((t) => t.url !== url);
+  };
+
   self.updateSlackConfig = (channel, workspace, invitedUserCount) => {
     state.slack = {
       channel,
@@ -864,4 +923,5 @@ Config.toDynamoItem = (config) => ({
   edgeOptimizeConfig: config.getEdgeOptimizeConfig(),
   onboardConfig: config.getOnboardConfig?.(),
   commerceLlmoConfig: config.getCommerceLlmoConfig?.(),
+  auditTargetURLs: config.getAuditTargetURLsConfig?.(),
 });

package/src/models/site/index.d.ts

@@ -99,6 +99,20 @@ export interface LlmoCustomerIntent {
   value: string;
 }
 
+export type AuditTargetSource = 'manual';
+
+export interface AuditTargetEntry {
+  url: string;
+}
+
+export interface AuditTargetEntryWithSource extends AuditTargetEntry {
+  source: AuditTargetSource;
+}
+
+export interface AuditTargetURLs {
+  manual?: AuditTargetEntry[];
+}
+
 export interface SiteConfig {
   state: {
     slack?: {
@@ -107,6 +121,7 @@ export interface SiteConfig {
       invitedUserCount?: number;
     };
     imports?: ImportConfig[];
+    auditTargetURLs?: AuditTargetURLs;
     handlers?: Record<string, {
       mentions?: Record<string, string[]>;
       excludedURLs?: string[];
@@ -205,6 +220,11 @@ export interface SiteConfig {
   removeLlmoTag(tag: string): void;
   getOnboardConfig(): { lastProfile?: string; lastStartTime?: number; forcedOverride?: boolean; history?: Array<{ profile?: string; startTime?: number }> } | undefined;
   updateOnboardConfig(onboardConfig: { lastProfile?: string; lastStartTime?: number; forcedOverride?: boolean }, options?: { maxHistory?: number }): void;
+  getAuditTargetURLs(): AuditTargetEntryWithSource[];
+  getAuditTargetURLsBySource(source: AuditTargetSource): AuditTargetEntry[];
+  updateAuditTargetURLs(source: AuditTargetSource, urls: AuditTargetEntry[]): void;
+  addAuditTargetURL(source: AuditTargetSource, urlObj: AuditTargetEntry): void;
+  removeAuditTargetURL(source: AuditTargetSource, url: string): void;
 }
 
 export interface Site extends BaseModel {

package/src/models/suggestion/suggestion.data-schemas.js

@@ -26,6 +26,17 @@
 import Joi from 'joi';
 import { OPPORTUNITY_TYPES } from '@adobe/spacecat-shared-utils';
 
+/**
+ * Custom Joi validator that accepts malformed HTTP/HTTPS URLs and relative paths
+ * while rejecting dangerous URI schemes (javascript:, data:, blob:, etc.).
+ * Used for BROKEN_INTERNAL_LINKS where crawled content may contain malformed URLs.
+ */
+const relaxedUrl = Joi.string().min(1).custom((value, helpers) => (
+  /^(https?:\/\/|\/)/i.test(value) ? value : helpers.error('string.uriScheme')
+), 'relaxed URL').messages({
+  'string.uriScheme': '{{#label}} must start with http://, https://, or /',
+});
+
 /**
  * Data schemas configuration per opportunity type.
  *
@@ -85,6 +96,8 @@ export const DATA_SCHEMAS = {
       ).required(),
       jiraLink: Joi.string().uri().allow(null).optional(),
       aggregationKey: Joi.string().optional(),
+      patchContent: Joi.string().optional(),
+      isCodeChangeAvailable: Joi.boolean().optional(),
     }).unknown(true),
     projections: {
       minimal: {
@@ -113,6 +126,8 @@ export const DATA_SCHEMAS = {
       ).required(),
       jiraLink: Joi.string().uri().allow(null).optional(),
       aggregationKey: Joi.string().optional(),
+      patchContent: Joi.string().optional(),
+      isCodeChangeAvailable: Joi.boolean().optional(),
     }).unknown(true),
     projections: {
       minimal: {
@@ -123,10 +138,14 @@ export const DATA_SCHEMAS = {
       },
     },
   },
+  // CWV has two implicit data shapes:
+  // 1. Page-level (type='url'): url and issues are present
+  // 2. Group-type (type='group'): url is absent, issues may be populated later via update
+  // Both shapes share the same schema; url and issues are optional to support both.
   [OPPORTUNITY_TYPES.CWV]: {
     schema: Joi.object({
       type: Joi.string().required(),
-      url: Joi.string().uri().required(),
+      url: Joi.string().uri().optional(),
       pageviews: Joi.number().optional(),
       organic: Joi.number().optional(),
       metrics: Joi.array().items(
@@ -144,7 +163,7 @@ export const DATA_SCHEMAS = {
           organic: Joi.number().optional(),
         }).unknown(true),
       ).required(),
-      issues: Joi.array().items(Joi.object()).required(),
+      issues: Joi.array().items(Joi.object()).optional().default([]),
       jiraLink: Joi.string().uri().allow(null).optional(),
       aggregationKey: Joi.string().allow(null).optional(),
     }).unknown(true),
@@ -163,6 +182,7 @@ export const DATA_SCHEMAS = {
         Joi.object({
           isAppropriate: Joi.boolean().optional(),
           isDecorative: Joi.boolean().optional(),
+          hasAltAttribute: Joi.boolean().optional(),
           xpath: Joi.string().optional(),
           altText: Joi.string().optional(),
           imageUrl: Joi.string().uri().optional(),
@@ -376,12 +396,16 @@ export const DATA_SCHEMAS = {
   [OPPORTUNITY_TYPES.BROKEN_INTERNAL_LINKS]: {
     schema: Joi.object({
       // Support both naming conventions (snake_case and camelCase)
-      url_from: Joi.string().uri().optional(),
-      urlFrom: Joi.string().uri().optional(),
-      url_to: Joi.string().uri().optional(),
-      urlTo: Joi.string().uri().optional(),
+      // URL fields use relaxedUrl instead of Joi.string().uri() because
+      // internal-links sometimes keeps URL values as-is, including malformed URLs.
+      // Unlike BROKEN_BACKLINKS, these accept malformed http/https/relative URLs
+      // but reject dangerous schemes (javascript:, data:, blob:, etc.).
+      url_from: relaxedUrl.optional(),
+      urlFrom: relaxedUrl.optional(),
+      url_to: relaxedUrl.optional(),
+      urlTo: relaxedUrl.optional(),
       title: Joi.string().optional(),
-      urlsSuggested: Joi.array().items(Joi.string().uri()).optional(),
+      urlsSuggested: Joi.array().items(relaxedUrl).optional(),
       aiRationale: Joi.string().optional(),
       trafficDomain: Joi.number().optional(),
       priority: Joi.string().optional(),