import type { RegulatoryFindingQuery } from '../../domain/regulatory-rag'; import { REGULATORY_FINDING_QUERY_SCHEMA_VERSION } from '../../domain/regulatory-rag'; import type { UnifiedResultProjection } from '../../domain/unified-result'; import catalog from './catalog.json'; import { publicSecurityTopics } from './public-security-topics'; const publicTools: Record = { 'cis-cat': 'CIS-CAT / CIS Benchmarks', maester: 'Maester', pingcastle: 'PingCastle', 'purple-knight': 'Semperis Purple Knight' }; const publicRuleIds: Record = { maester: catalog.maesterIds, pingcastle: catalog.pingcastleIds }; /** * Builds an embedding query only from catalog-owned identifiers and fixed public * concepts. Raw finding prose is inspected locally for topic recognition and is * never copied into the returned query. */ export function buildRegulatoryFindingQuery(finding: UnifiedResultProjection): RegulatoryFindingQuery | undefined { if (finding.sourceKind !== 'scanner-finding') return undefined; const toolId = finding.sourceTool?.trim().toLowerCase() ?? ''; const publicTool = publicTools[toolId]; const publicRuleId = recognizedRuleId(toolId, finding.sourceRuleId); const evidence = [finding.title, finding.description, finding.recommendation].filter(Boolean).join('\n').slice(0, 20_000); const topics = publicSecurityTopics(evidence); if (!publicRuleId && !topics.length) return undefined; const specificity = publicRuleId ? 'rule' : 'topic'; const query = [ 'Retrieve regulatory controls whose normative requirements directly address this security finding.', publicTool && `Public assessment tool: ${publicTool}.`, publicRuleId && `Public rule ID: ${publicRuleId}.`, topics.length && `Public technical topics: ${topics.join('; ')}.`, 'Prefer controls with direct requirement text over merely related guidance. Do not infer customer scope, assets, configuration values, or compliance status.' ].filter(Boolean).join(' '); return { schemaVersion: REGULATORY_FINDING_QUERY_SCHEMA_VERSION, query, specificity, ...(publicTool ? { publicTool } : {}), ...(publicRuleId ? { publicRuleId } : {}), publicTopics: topics }; } function recognizedRuleId(toolId: string, value: string | undefined): string | undefined { const candidate = value?.trim(); if (!candidate) return undefined; return publicRuleIds[toolId]?.find(id => id.toLowerCase() === candidate.toLowerCase()); }