Kjell Tore Guttormsen
8bea3a224a
Ny data/domain-taxonomy.json (tracket via gitignore-negasjon; generert registry/rapporter forblir ignorert) konsoliderer de 4 divergerende taksonomiene: (a) sitemap-prefikser, (b) discover INCLUDE/EXCLUDE, (c) category->skill, (d) getFilePriority. lib/taxonomy.mjs laster + kompilerer. Refaktor: poll-sitemaps, discover-new-urls, report-changes LESER taksonomien (ingen embeddede kopier). Kriterium grep TARGET_PREFIXES=[ == 0 oppfylt. Konsolideringsfunn: - category-skill-map.json stale i 4 entries (copilot-extensibility, monitoring-observability, performance-scalability, prompt-engineering -> sa engineering; disk sier advisor/governance/security/advisor). DISK er kanon. Map-en er ukonsumert av kode (kun README) -> flagget, ikke rort. - discover fikk poll-paritet (12 -> 18 sitemap-prefikser). - skill utledes na fra kanonisk category_skill -> ingen divergens (invariant-test). Adferdsbevarende: 0 mismatch old vs ny prioritetslogikk pa 51 endrede filer; discover sine hardkodede skill-verdier matchet allerede disk. Tester: validate 239, kb-update 49 (+7 taksonomi), kb-eval 13 - alle gronne. Co-Authored-By: Claude Opus 4.8 (1M context) <noreply@anthropic.com> Claude-Session: https://claude.ai/code/session_01REiKFhP4w6xGXXqWKpPCJJ
95 lines
4.5 KiB
JSON
95 lines
4.5 KiB
JSON
{
|
|
"version": 1,
|
|
"description": "Single source of truth (lag 0) for 'in-domain' classification. Consolidates four previously-divergent taxonomies into one: (a) poll-sitemaps TARGET_PREFIXES, (b) discover-new-urls INCLUDE/EXCLUDE, (c) category->skill ownership, (d) report-changes getFilePriority. Scripts READ this file; they no longer embed their own copies.",
|
|
"provenance": {
|
|
"category_skill": "PHYSICAL DISK is canonical (skills/<skill>/references/<category>/). category-skill-map.json drifted on 4 entries (copilot-extensibility, monitoring-observability, performance-scalability, prompt-engineering) and is no longer consumed by code.",
|
|
"sitemap_prefixes": "poll-sitemaps superset (18). discover-new-urls previously had only 12 — now reads this list for poll parity.",
|
|
"notes": "dotnet_en-us_ deliberately excluded: 75 sitemaps, only ~12 matches — not worth weekly polling."
|
|
},
|
|
"sitemap_prefixes": [
|
|
"azure_en-us_",
|
|
"microsoft-copilot-studio_en-us_",
|
|
"security_en-us_",
|
|
"fabric_en-us_",
|
|
"power-platform_en-us_",
|
|
"ai_en-us_",
|
|
"copilot_en-us_",
|
|
"compliance_en-us_",
|
|
"agent-framework_en-us_",
|
|
"semantic-kernel_en-us_",
|
|
"entra_en-us_",
|
|
"purview_en-us_",
|
|
"microsoftteams_en-us_",
|
|
"sharepoint_en-us_",
|
|
"microsoft-365_en-us_",
|
|
"training_en-us_",
|
|
"cloud-computing_en-us_",
|
|
"privacy_en-us_"
|
|
],
|
|
"category_skill": {
|
|
"agent-orchestration": "ms-ai-engineering",
|
|
"ai-security-engineering": "ms-ai-security",
|
|
"api-management": "ms-ai-engineering",
|
|
"architecture": "ms-ai-advisor",
|
|
"azure-ai-services": "ms-ai-engineering",
|
|
"bcdr": "ms-ai-infrastructure",
|
|
"copilot-extensibility": "ms-ai-advisor",
|
|
"cost-optimization": "ms-ai-security",
|
|
"data-engineering": "ms-ai-engineering",
|
|
"development": "ms-ai-advisor",
|
|
"hybrid-edge": "ms-ai-infrastructure",
|
|
"mlops-genaiops": "ms-ai-engineering",
|
|
"monitoring-observability": "ms-ai-governance",
|
|
"multi-modal": "ms-ai-engineering",
|
|
"norwegian-public-sector-governance": "ms-ai-governance",
|
|
"performance-scalability": "ms-ai-security",
|
|
"platforms": "ms-ai-advisor",
|
|
"prompt-engineering": "ms-ai-advisor",
|
|
"rag-architecture": "ms-ai-engineering",
|
|
"responsible-ai": "ms-ai-governance",
|
|
"security-scoring": "ms-ai-security"
|
|
},
|
|
"relevance": {
|
|
"include": [
|
|
{ "pattern": "/azure/ai-foundry/", "category": "azure-ai-services" },
|
|
{ "pattern": "/azure/ai-services/", "category": "azure-ai-services" },
|
|
{ "pattern": "/azure/machine-learning/", "category": "mlops-genaiops" },
|
|
{ "pattern": "/azure/search/", "category": "rag-architecture" },
|
|
{ "pattern": "/azure/api-management/", "category": "api-management" },
|
|
{ "pattern": "/azure/azure-monitor/", "category": "monitoring-observability" },
|
|
{ "pattern": "/azure/well-architected/", "category": "architecture" },
|
|
{ "pattern": "/microsoft-copilot-studio/", "category": "copilot-extensibility" },
|
|
{ "pattern": "/copilot/microsoft-365/", "category": "copilot-extensibility" },
|
|
{ "pattern": "/microsoft-365-copilot/", "category": "copilot-extensibility" },
|
|
{ "pattern": "/security/(?:ai|benchmark|engineering)/", "category": "ai-security-engineering" },
|
|
{ "pattern": "/azure/defender-for-cloud/", "category": "ai-security-engineering" },
|
|
{ "pattern": "/purview/", "category": "responsible-ai" },
|
|
{ "pattern": "/semantic-kernel/", "category": "agent-orchestration" },
|
|
{ "pattern": "/agent-framework/", "category": "agent-orchestration" },
|
|
{ "pattern": "/fabric/(?:data-engineering|data-science|real-time-intelligence)/", "category": "data-engineering" },
|
|
{ "pattern": "/azure/cosmos-db/", "category": "data-engineering" },
|
|
{ "pattern": "/azure/databricks/", "category": "data-engineering" },
|
|
{ "pattern": "/entra/(?:identity|agent)/", "category": "ai-security-engineering" }
|
|
],
|
|
"exclude": [
|
|
"/training/",
|
|
"/credentials/",
|
|
"/legal/",
|
|
"/previous-versions/",
|
|
"/archive/",
|
|
"/samples/",
|
|
"/release-notes?/",
|
|
"/whats-new",
|
|
"/changelog",
|
|
"/migrate/"
|
|
]
|
|
},
|
|
"priority": {
|
|
"rules": [
|
|
{ "match": "cost|pricing|pris", "priority": "critical" },
|
|
{ "match": "responsible-ai|governance|ai-security-(?:engineering|scoring)", "priority": "high" },
|
|
{ "match": "platforms|copilot|azure-ai-services|agent-orchestration|rag|mlops|prompt-engineering|monitoring|performance", "priority": "medium" }
|
|
],
|
|
"default": "low"
|
|
}
|
|
}
|