@ontosdk/next 1.5.6 → 1.5.7
This diff represents the content of publicly available package versions that have been released to one of the supported registries. The information contained in this diff is provided for informational purposes only and reflects changes between package versions as they appear in their respective public registries.
- package/dist/middleware.js +2 -2
- package/dist/middleware.js.map +1 -1
- package/dist/middleware.mjs +2 -2
- package/dist/middleware.mjs.map +1 -1
- package/package.json +1 -1
- package/src/middleware.ts +8 -2
- package/dist/OntoHead.d.mts +0 -27
- package/dist/OntoHead.d.ts +0 -27
- package/dist/OntoProvider.d.mts +0 -52
- package/dist/OntoProvider.d.ts +0 -52
- package/dist/cli.d.mts +0 -1
- package/dist/cli.d.ts +0 -1
- package/dist/config.d.mts +0 -80
- package/dist/config.d.ts +0 -80
- package/dist/index.d.mts +0 -25
- package/dist/index.d.ts +0 -25
- package/dist/middleware.d.mts +0 -29
- package/dist/middleware.d.ts +0 -29
- package/dist/schemas.d.mts +0 -72
- package/dist/schemas.d.ts +0 -72
package/dist/middleware.js
CHANGED
|
@@ -1,4 +1,4 @@
|
|
|
1
|
-
"use strict";var h=Object.defineProperty;var C=Object.getOwnPropertyDescriptor;var T=Object.getOwnPropertyNames;var G=Object.prototype.hasOwnProperty;var _=(t,e)=>{for(var n in e)h(t,n,{get:e[n],enumerable:!0})},$=(t,e,n,o)=>{if(e&&typeof e=="object"||typeof e=="function")for(let a of T(e))!G.call(t,a)&&a!==n&&h(t,a,{get:()=>e[a],enumerable:!(o=C(e,a))||o.enumerable});return t};var
|
|
1
|
+
"use strict";var h=Object.defineProperty;var C=Object.getOwnPropertyDescriptor;var T=Object.getOwnPropertyNames;var G=Object.prototype.hasOwnProperty;var _=(t,e)=>{for(var n in e)h(t,n,{get:e[n],enumerable:!0})},$=(t,e,n,o)=>{if(e&&typeof e=="object"||typeof e=="function")for(let a of T(e))!G.call(t,a)&&a!==n&&h(t,a,{get:()=>e[a],enumerable:!(o=C(e,a))||o.enumerable});return t};var I=t=>$(h({},"__esModule",{value:!0}),t);var U={};_(U,{AI_BOT_USER_AGENTS:()=>y,matchBot:()=>c,ontoMiddleware:()=>b});module.exports=I(U);var p=require("next/server");var u=[{name:"GPTBot",company:"OpenAI",addedAt:"2025-01-01"},{name:"ChatGPT-User",company:"OpenAI",addedAt:"2025-01-01"},{name:"OAI-SearchBot",company:"OpenAI",addedAt:"2025-01-01"},{name:"ChatGPT",company:"OpenAI",addedAt:"2025-03-25"},{name:"OpenAI",company:"OpenAI",addedAt:"2025-03-25"},{name:"GPT",company:"OpenAI",addedAt:"2025-03-25"},{name:"Google-CloudVertexBot",company:"Google",addedAt:"2025-01-01"},{name:"Google-Extended",company:"Google",addedAt:"2025-01-01"},{name:"GoogleOther",company:"Google",addedAt:"2025-01-01"},{name:"ClaudeBot",company:"Anthropic",addedAt:"2025-01-01"},{name:"Claude-User",company:"Anthropic",addedAt:"2025-01-01"},{name:"claude-fetch",company:"Anthropic",addedAt:"2025-03-25"},{name:"AnthropicFetch",company:"Anthropic",addedAt:"2025-03-25"},{name:"Claude-Fetch",company:"Anthropic",addedAt:"2025-03-25"},{name:"anthropic-ai",company:"Anthropic",addedAt:"2025-01-01"},{name:"Claude",company:"Anthropic",addedAt:"2025-03-25"},{name:"Anthropic",company:"Anthropic",addedAt:"2025-03-25"},{name:"PerplexityBot",company:"Perplexity",addedAt:"2025-01-01"},{name:"Perplexity-User",company:"Perplexity",addedAt:"2025-01-01"},{name:"Perplexity",company:"Perplexity",addedAt:"2025-03-25"},{name:"Meta-ExternalAgent",company:"Meta",addedAt:"2025-01-01"},{name:"Meta-ExternalFetcher",company:"Meta",addedAt:"2025-01-01"},{name:"facebookexternalhit",company:"Meta",addedAt:"2025-03-25"},{name:"FacebookBot",company:"Meta",addedAt:"2025-01-01"},{name:"MistralBot",company:"Mistral",addedAt:"2025-03-25"},{name:"Mistral",company:"Mistral",addedAt:"2025-03-25"},{name:"Amazonbot",company:"Amazon",addedAt:"2025-03-25"},{name:"AI2Bot",company:"Allen Institute",addedAt:"2025-03-25"},{name:"DuckAssistBot",company:"DuckDuckGo",addedAt:"2025-03-25"},{name:"Diffbot",company:"Diffbot",addedAt:"2025-03-25"},{name:"CCBot",company:"Common Crawl",addedAt:"2025-01-01"},{name:"Bytespider",company:"ByteDance",addedAt:"2025-01-01"},{name:"Applebot-Extended",company:"Apple",addedAt:"2025-01-01"},{name:"YouBot",company:"You.com",addedAt:"2025-01-01"},{name:"python-requests",company:"Generic Bot",addedAt:"2025-03-25"},{name:"python-httpx",company:"Generic Bot",addedAt:"2025-03-25"},{name:"httpx",company:"Generic Bot",addedAt:"2025-03-25"},{name:"axios",company:"Generic Bot",addedAt:"2025-03-25"},{name:"node-fetch",company:"Generic Bot",addedAt:"2025-03-25"},{name:"Go-http-client",company:"Generic Bot",addedAt:"2025-03-25"},{name:"Wget",company:"Generic Bot",addedAt:"2025-03-25"},{name:"Curl",company:"Generic Bot",addedAt:"2025-03-25"}],y=P();function P(){return u.map(t=>t.name)}function c(t){if(!t)return;let e=t.toLowerCase(),n=u.filter(o=>e.includes(o.name.toLowerCase()));if(n.length!==0)return n.length===1?n[0]:n.reduce((o,a)=>a.name.length>o.name.length?a:o)}function g(t){let e=[];if(e.push(`# ${t.name}`),e.push(""),e.push(`> ${t.summary}`),e.push(""),t.routes&&t.routes.length>0){e.push("## Key Routes"),e.push("");for(let n of t.routes){let o=`${t.baseUrl}${n.path}`;e.push(`- [${n.path}](${o}): ${n.description}`)}e.push("")}if(t.externalLinks&&t.externalLinks.length>0){e.push("## Resources"),e.push("");for(let n of t.externalLinks)n.description?e.push(`- [${n.title}](${n.url}): ${n.description}`):e.push(`- [${n.title}](${n.url})`);e.push("")}if(t.sections&&t.sections.length>0)for(let n of t.sections)e.push(`## ${n.heading}`),e.push(""),e.push(n.content),e.push("");return e.join(`
|
|
2
2
|
`).trim()+`
|
|
3
|
-
`}async function
|
|
3
|
+
`}async function b(t,e){let n=t.headers.get("user-agent"),o=t.nextUrl.clone(),a=c(n),x=t.headers.get("accept")||"",l=t.nextUrl.searchParams.has("onto"),f=!!a,O=x.includes("text/markdown")||l;if(f||O){if(o.pathname.startsWith("/_next"))return p.NextResponse.next();if(o.pathname==="/llms.txt")try{if(e){let i=g(e),m=new p.NextResponse(i,{headers:{"Content-Type":"text/plain; charset=utf-8","Cache-Control":"public, max-age=3600, s-maxage=3600, stale-while-revalidate=86400"}});return a&&m.headers.set("X-Onto-Bot",`${a.name} (${a.company})`),m.headers.set("X-Onto-Trace",n||"no-ua"),m}}catch(i){console.error("[Onto] Failed to generate llms.txt:",i)}if(o.pathname.includes("."))return p.NextResponse.next();let r=o.pathname;(r==="/"||r==="")&&(r="/index"),r.endsWith("/")&&r!=="/"&&(r=r.slice(0,-1));let A=process.env.ONTO_API_KEY,B=process.env.ONTO_DASHBOARD_URL||"https://app.buildonto.dev";A&&fetch(`${B}/api/track`,{method:"POST",headers:{"x-onto-key":A,"Content-Type":"application/json"},body:JSON.stringify({route:o.pathname,userAgent:n,bot:a?.name,company:a?.company})}).catch(()=>{}),o.pathname=`/.onto${r}.md`;let d=p.NextResponse.rewrite(o);return d.headers.set("Content-Type","text/markdown; charset=utf-8"),d.headers.set("Cache-Control","public, max-age=3600, s-maxage=3600, stale-while-revalidate=86400"),d.headers.set("Vary","User-Agent, Accept"),d.headers.set("X-Onto-Trace",n||"no-ua"),a&&(d.headers.set("X-Onto-Bot",`${a.name} (${a.company})`),d.headers.set("X-Onto-Matched","true")),l&&d.headers.set("X-Onto-Debug","true"),d}let s=p.NextResponse.next();return s.headers.set("Vary","User-Agent, Accept"),s.headers.set("X-Onto-Trace",n||"no-ua"),a?(s.headers.set("X-Onto-Matched-Bot",a.name),s.headers.set("X-Onto-Identified","true")):s.headers.set("X-Onto-Identified","false"),s}0&&(module.exports={AI_BOT_USER_AGENTS,matchBot,ontoMiddleware});
|
|
4
4
|
//# sourceMappingURL=middleware.js.map
|
package/dist/middleware.js.map
CHANGED
|
@@ -1 +1 @@
|
|
|
1
|
-
{"version":3,"sources":["../src/middleware.ts","../src/bots.ts","../src/config.ts"],"sourcesContent":["import { NextRequest, NextResponse } from 'next/server';\r\nimport { matchBot } from './bots';\r\nimport { generateLlmsTxt, OntoConfig } from './config';\r\n\r\nexport async function ontoMiddleware(request: any, config?: OntoConfig) {\r\n const userAgent = request.headers.get('user-agent');\r\n const url = request.nextUrl.clone();\r\n const matched = matchBot(userAgent);\r\n\r\n const accept = request.headers.get('accept') || '';\r\n const hasDebugParam = request.nextUrl.searchParams.has('onto');\r\n\r\n const isAiBot = !!matched;\r\n const isMarkdownRequested = accept.includes('text/markdown') || hasDebugParam;\r\n\r\n // Common logic for bot/markdown negotiation\r\n if (isAiBot || isMarkdownRequested) {\r\n // Ignore internal next.js requests\r\n if (url.pathname.startsWith('/_next')) {\r\n return NextResponse.next();\r\n }\r\n\r\n // --- llms.txt Auto-Discovery ---\r\n if (url.pathname === '/llms.txt') {\r\n try {\r\n if (config) {\r\n const llmsTxtContent = generateLlmsTxt(config);\r\n const response = new NextResponse(llmsTxtContent, {\r\n headers: {\r\n 'Content-Type': 'text/plain; charset=utf-8',\r\n 'Cache-Control': 'public, max-age=3600, s-maxage=3600, stale-while-revalidate=86400',\r\n }\r\n });\r\n if (matched) response.headers.set('X-Onto-Bot', `${matched.name} (${matched.company})`);\r\n response.headers.set('X-Onto-Trace', userAgent || 'no-ua');\r\n return response;\r\n }\r\n } catch (error) {\r\n console.error('[Onto] Failed to generate llms.txt:', error);\r\n }\r\n }\r\n\r\n // Skip other static assets with dots\r\n if (url.pathname.includes('.')) {\r\n return NextResponse.next();\r\n }\r\n\r\n // Determine the corresponding payload path\r\n let payloadPath = url.pathname;\r\n if (payloadPath === '/' || payloadPath === '') payloadPath = '/index';\r\n if (payloadPath.endsWith('/') && payloadPath !== '/') payloadPath = payloadPath.slice(0, -1);\r\n\r\n // --- Onto Control Plane Integration (Premium) ---\r\n const ONTO_API_KEY = process.env.ONTO_API_KEY;\r\n const DASHBOARD_URL = process.env.ONTO_DASHBOARD_URL || 'https://app.buildonto.dev';\r\n\r\n if (ONTO_API_KEY) {\r\n // Logic for tracking and injection ... (fire-and-forget tracking)\r\n fetch(`${DASHBOARD_URL}/api/track`, {\r\n method: 'POST',\r\n headers: { 'x-onto-key': ONTO_API_KEY, 'Content-Type': 'application/json' },\r\n body: JSON.stringify({ route: url.pathname, userAgent, bot: matched?.name, company: matched?.company })\r\n }).catch(() => {});\r\n }\r\n\r\n // Rewrite to semantic payload\r\n url.pathname = `/.onto${payloadPath}.md`;\r\n const response = NextResponse.rewrite(url);\r\n \r\n // Apply headers\r\n response.headers.set('Content-Type', 'text/markdown; charset=utf-8');\r\n response.headers.set('Cache-Control', 'public, max-age=3600, s-maxage=3600, stale-while-revalidate=86400');\r\n response.headers.set('Vary', 'User-Agent, Accept');\r\n response.headers.set('X-Onto-Trace', userAgent || 'no-ua');\r\n \r\n if (matched) {\r\n response.headers.set('X-Onto-Bot', `${matched.name} (${matched.company})`);\r\n response.headers.set('X-Onto-Matched', 'true');\r\n }\r\n \r\n if (hasDebugParam) response.headers.set('X-Onto-Debug', 'true');\r\n\r\n return response;\r\n }\r\n\r\n // Default response for non-bots\r\n const response = NextResponse.next();\r\n \r\n // Crucial: Tell Vercel/Edge to vary the cache by User-Agent \r\n // This ensures bots get the rewrite and humans get the HTML\r\n response.headers.set('Vary', 'User-Agent, Accept');\r\n response.headers.set('X-Onto-Trace', userAgent || 'no-ua');\r\n \r\n return response;\r\n}\r\n\r\n// Re-export the bot registry for consumers who want to extend or inspect it\r\nexport { AI_BOT_USER_AGENTS, matchBot } from './bots';\r\nexport type { AiBot } from './bots';\r\n\r\n\r\n","/**\n * Comprehensive registry of AI bot user-agent strings.\n * The middleware uses this list to detect AI crawlers and serve optimized markdown.\n */\n\nexport interface AiBot {\n /** The user-agent substring to match against */\n name: string;\n /** The company operating this bot */\n company: string;\n /** ISO date when this bot was added or last verified */\n addedAt?: string;\n}\n\n/**\n * Structured registry of all known AI bots, grouped by company.\n * Useful for analytics and the Control Plane dashboard.\n */\nexport const AI_BOTS: AiBot[] = [\n // OpenAI\n { name: 'GPTBot', company: 'OpenAI', addedAt: '2025-01-01' },\n { name: 'ChatGPT-User', company: 'OpenAI', addedAt: '2025-01-01' },\n { name: 'OAI-SearchBot', company: 'OpenAI', addedAt: '2025-01-01' },\n { name: 'ChatGPT', company: 'OpenAI', addedAt: '2025-03-25' },\n { name: 'OpenAI', company: 'OpenAI', addedAt: '2025-03-25' },\n { name: 'GPT', company: 'OpenAI', addedAt: '2025-03-25' },\n\n // Google (SEO Safety: Googlebot proper is EXCLUDED)\n { name: 'Google-CloudVertexBot', company: 'Google', addedAt: '2025-01-01' },\n { name: 'Google-Extended', company: 'Google', addedAt: '2025-01-01' },\n { name: 'GoogleOther', company: 'Google', addedAt: '2025-01-01' },\n\n // Anthropic\n { name: 'ClaudeBot', company: 'Anthropic', addedAt: '2025-01-01' },\n { name: 'Claude-User', company: 'Anthropic', addedAt: '2025-01-01' },\n { name: 'claude-fetch', company: 'Anthropic', addedAt: '2025-03-25' },\n { name: 'AnthropicFetch', company: 'Anthropic', addedAt: '2025-03-25' },\n { name: 'Claude-Fetch', company: 'Anthropic', addedAt: '2025-03-25' },\n { name: 'anthropic-ai', company: 'Anthropic', addedAt: '2025-01-01' },\n { name: 'Claude', company: 'Anthropic', addedAt: '2025-03-25' },\n { name: 'Anthropic', company: 'Anthropic', addedAt: '2025-03-25' },\n\n // Perplexity\n { name: 'PerplexityBot', company: 'Perplexity', addedAt: '2025-01-01' },\n { name: 'Perplexity-User', company: 'Perplexity', addedAt: '2025-01-01' },\n { name: 'Perplexity', company: 'Perplexity', addedAt: '2025-03-25' },\n\n // Meta\n { name: 'Meta-ExternalAgent', company: 'Meta', addedAt: '2025-01-01' },\n { name: 'Meta-ExternalFetcher', company: 'Meta', addedAt: '2025-01-01' },\n { name: 'facebookexternalhit', company: 'Meta', addedAt: '2025-03-25' },\n { name: 'FacebookBot', company: 'Meta', addedAt: '2025-01-01' },\n\n // Mistral\n { name: 'MistralBot', company: 'Mistral', addedAt: '2025-03-25' },\n { name: 'Mistral', company: 'Mistral', addedAt: '2025-03-25' },\n\n // Amazon\n { name: 'Amazonbot', company: 'Amazon', addedAt: '2025-03-25' },\n\n // Others\n { name: 'AI2Bot', company: 'Allen Institute', addedAt: '2025-03-25' },\n { name: 'DuckAssistBot', company: 'DuckDuckGo', addedAt: '2025-03-25' },\n { name: 'Diffbot', company: 'Diffbot', addedAt: '2025-03-25' },\n { name: 'CCBot', company: 'Common Crawl', addedAt: '2025-01-01' },\n { name: 'Bytespider', company: 'ByteDance', addedAt: '2025-01-01' },\n { name: 'Applebot-Extended', company: 'Apple', addedAt: '2025-01-01' },\n { name: 'YouBot', company: 'You.com', addedAt: '2025-01-01' },\n\n // Generic AI / Scraping Libraries (Last Resort)\n { name: 'python-requests', company: 'Generic Bot', addedAt: '2025-03-25' },\n { name: 'python-httpx', company: 'Generic Bot', addedAt: '2025-03-25' },\n { name: 'httpx', company: 'Generic Bot', addedAt: '2025-03-25' },\n { name: 'axios', company: 'Generic Bot', addedAt: '2025-03-25' },\n { name: 'node-fetch', company: 'Generic Bot', addedAt: '2025-03-25' },\n { name: 'Go-http-client', company: 'Generic Bot', addedAt: '2025-03-25' },\n { name: 'Wget', company: 'Generic Bot', addedAt: '2025-03-25' },\n { name: 'Curl', company: 'Generic Bot', addedAt: '2025-03-25' },\n];\n\n/**\n * Flat list of user-agent substrings for fast matching in the middleware.\n */\nexport const AI_BOT_USER_AGENTS: string[] = AI_BOT_USER_AGENTS_CACHE();\n\nfunction AI_BOT_USER_AGENTS_CACHE() {\n return AI_BOTS.map(bot => bot.name);\n}\n\n/**\n * Given a raw user-agent string, returns the matched AiBot entry or undefined.\n * Uses a \"Longest Match\" strategy to ensure maximum specificity.\n * Comparison is case-insensitive.\n */\nexport function matchBot(userAgent: string | null): AiBot | undefined {\n if (!userAgent) return undefined;\n const lowerUA = userAgent.toLowerCase();\n \n // Find all matches\n const matches = AI_BOTS.filter(bot => \n lowerUA.includes(bot.name.toLowerCase())\n );\n\n if (matches.length === 0) return undefined;\n if (matches.length === 1) return matches[0];\n\n // Pick the longest match for maximum specificity (e.g. 'ChatGPT-User' vs 'GPT')\n return matches.reduce((longest, current) => \n current.name.length > longest.name.length ? current : longest\n );\n}\n","/**\r\n * Configuration schema for onto.config.ts\r\n * Used to dynamically generate llms.txt and other AI discovery files\r\n */\r\n\r\nexport type PageType = 'scoring' | 'about' | 'default';\r\n\r\nexport interface OntoRoute {\r\n /**\r\n * The URL path (e.g., '/docs', '/api/reference')\r\n */\r\n path: string;\r\n /**\r\n * Description of what this route contains\r\n */\r\n description: string;\r\n /**\r\n * Optional: Page type for automatic JSON-LD schema injection\r\n * - 'scoring': Injects Methodology schema with AIO scoring weights (40/35/25)\r\n * - 'about': Injects Organization/AboutPage schema\r\n * - 'default': No automatic schema injection\r\n */\r\n pageType?: PageType;\r\n}\r\n\r\nexport interface OntoConfig {\r\n /**\r\n * The name of your project or site (required)\r\n * Used as the H1 heading in llms.txt\r\n */\r\n name: string;\r\n\r\n /**\r\n * A short summary of your project (required)\r\n * Displayed as a blockquote in llms.txt\r\n * Should contain key information necessary for understanding the rest of the file\r\n */\r\n summary: string;\r\n\r\n /**\r\n * The base URL of your site (e.g., 'https://example.com')\r\n */\r\n baseUrl: string;\r\n\r\n /**\r\n * Optional: Additional sections to include in llms.txt\r\n * Each section can contain any markdown content\r\n */\r\n sections?: {\r\n heading: string;\r\n content: string;\r\n }[];\r\n\r\n /**\r\n * Key routes that AI agents should know about\r\n * These will be formatted as a markdown list in llms.txt\r\n */\r\n routes?: OntoRoute[];\r\n\r\n /**\r\n * Optional: Links to external resources (documentation, API references, etc.)\r\n */\r\n externalLinks?: {\r\n title: string;\r\n url: string;\r\n description?: string;\r\n }[];\r\n\r\n /**\r\n * Optional: Organization information for JSON-LD schemas\r\n */\r\n organization?: {\r\n name: string;\r\n description?: string;\r\n url?: string;\r\n logo?: string;\r\n foundingDate?: string;\r\n };\r\n}\r\n\r\n/**\r\n * Generate llms.txt content from OntoConfig\r\n * Follows the llms.txt specification:\r\n * - H1 with project name\r\n * - Blockquote with summary\r\n * - Additional markdown sections\r\n */\r\nexport function generateLlmsTxt(config: OntoConfig): string {\r\n const lines: string[] = [];\r\n\r\n // H1: Project name (required)\r\n lines.push(`# ${config.name}`);\r\n lines.push('');\r\n\r\n // Blockquote: Summary (required)\r\n lines.push(`> ${config.summary}`);\r\n lines.push('');\r\n\r\n // Key Routes section (if provided)\r\n if (config.routes && config.routes.length > 0) {\r\n lines.push('## Key Routes');\r\n lines.push('');\r\n for (const route of config.routes) {\r\n const fullUrl = `${config.baseUrl}${route.path}`;\r\n lines.push(`- [${route.path}](${fullUrl}): ${route.description}`);\r\n }\r\n lines.push('');\r\n }\r\n\r\n // External Links section (if provided)\r\n if (config.externalLinks && config.externalLinks.length > 0) {\r\n lines.push('## Resources');\r\n lines.push('');\r\n for (const link of config.externalLinks) {\r\n if (link.description) {\r\n lines.push(`- [${link.title}](${link.url}): ${link.description}`);\r\n } else {\r\n lines.push(`- [${link.title}](${link.url})`);\r\n }\r\n }\r\n lines.push('');\r\n }\r\n\r\n // Custom sections (if provided)\r\n if (config.sections && config.sections.length > 0) {\r\n for (const section of config.sections) {\r\n lines.push(`## ${section.heading}`);\r\n lines.push('');\r\n lines.push(section.content);\r\n lines.push('');\r\n }\r\n }\r\n\r\n return lines.join('\\n').trim() + '\\n';\r\n}\r\n"],"mappings":"yaAAA,IAAAA,EAAA,GAAAC,EAAAD,EAAA,wBAAAE,EAAA,aAAAC,EAAA,mBAAAC,IAAA,eAAAC,EAAAL,GAAA,IAAAM,EAA0C,uBCkBnC,IAAMC,EAAmB,CAE5B,CAAE,KAAM,SAAqB,QAAS,SAAY,QAAS,YAAa,EACxE,CAAE,KAAM,eAAoB,QAAS,SAAY,QAAS,YAAa,EACvE,CAAE,KAAM,gBAAoB,QAAS,SAAY,QAAS,YAAa,EACvE,CAAE,KAAM,UAAoB,QAAS,SAAY,QAAS,YAAa,EACvE,CAAE,KAAM,SAAoB,QAAS,SAAY,QAAS,YAAa,EACvE,CAAE,KAAM,MAAoB,QAAS,SAAY,QAAS,YAAa,EAGvE,CAAE,KAAM,wBAA2B,QAAS,SAAU,QAAS,YAAa,EAC5E,CAAE,KAAM,kBAA2B,QAAS,SAAU,QAAS,YAAa,EAC5E,CAAE,KAAM,cAA2B,QAAS,SAAU,QAAS,YAAa,EAG5E,CAAE,KAAM,YAAmB,QAAS,YAAa,QAAS,YAAa,EACvE,CAAE,KAAM,cAAkB,QAAS,YAAa,QAAS,YAAa,EACtE,CAAE,KAAM,eAAkB,QAAS,YAAa,QAAS,YAAa,EACtE,CAAE,KAAM,iBAAkB,QAAS,YAAa,QAAS,YAAa,EACtE,CAAE,KAAM,eAAkB,QAAS,YAAa,QAAS,YAAa,EACtE,CAAE,KAAM,eAAkB,QAAS,YAAa,QAAS,YAAa,EACtE,CAAE,KAAM,SAAkB,QAAS,YAAa,QAAS,YAAa,EACtE,CAAE,KAAM,YAAkB,QAAS,YAAa,QAAS,YAAa,EAGtE,CAAE,KAAM,gBAAmB,QAAS,aAAc,QAAS,YAAa,EACxE,CAAE,KAAM,kBAAmB,QAAS,aAAc,QAAS,YAAa,EACxE,CAAE,KAAM,aAAmB,QAAS,aAAc,QAAS,YAAa,EAGxE,CAAE,KAAM,qBAAwB,QAAS,OAAQ,QAAS,YAAa,EACvE,CAAE,KAAM,uBAAwB,QAAS,OAAQ,QAAS,YAAa,EACvE,CAAE,KAAM,sBAAwB,QAAS,OAAQ,QAAS,YAAa,EACvE,CAAE,KAAM,cAAwB,QAAS,OAAQ,QAAS,YAAa,EAGvE,CAAE,KAAM,aAAc,QAAS,UAAW,QAAS,YAAa,EAChE,CAAE,KAAM,UAAc,QAAS,UAAW,QAAS,YAAa,EAGhE,CAAE,KAAM,YAAa,QAAS,SAAU,QAAS,YAAa,EAG9D,CAAE,KAAM,SAAiB,QAAS,kBAAmB,QAAS,YAAa,EAC3E,CAAE,KAAM,gBAAiB,QAAS,aAAc,QAAS,YAAa,EACtE,CAAE,KAAM,UAAiB,QAAS,UAAe,QAAS,YAAa,EACvE,CAAE,KAAM,QAAiB,QAAS,eAAgB,QAAS,YAAa,EACxE,CAAE,KAAM,aAAiB,QAAS,YAAgB,QAAS,YAAa,EACxE,CAAE,KAAM,oBAAqB,QAAS,QAAY,QAAS,YAAa,EACxE,CAAE,KAAM,SAAiB,QAAS,UAAgB,QAAS,YAAa,EAGxE,CAAE,KAAM,kBAAoB,QAAS,cAAe,QAAS,YAAa,EAC1E,CAAE,KAAM,eAAoB,QAAS,cAAe,QAAS,YAAa,EAC1E,CAAE,KAAM,QAAoB,QAAS,cAAe,QAAS,YAAa,EAC1E,CAAE,KAAM,QAAoB,QAAS,cAAe,QAAS,YAAa,EAC1E,CAAE,KAAM,aAAoB,QAAS,cAAe,QAAS,YAAa,EAC1E,CAAE,KAAM,iBAAoB,QAAS,cAAe,QAAS,YAAa,EAC1E,CAAE,KAAM,OAAoB,QAAS,cAAe,QAAS,YAAa,EAC1E,CAAE,KAAM,OAAoB,QAAS,cAAe,QAAS,YAAa,CAC9E,EAKaC,EAA+BC,EAAyB,EAErE,SAASA,GAA2B,CAChC,OAAOF,EAAQ,IAAIG,GAAOA,EAAI,IAAI,CACtC,CAOO,SAASC,EAASC,EAA6C,CAClE,GAAI,CAACA,EAAW,OAChB,IAAMC,EAAUD,EAAU,YAAY,EAGhCE,EAAUP,EAAQ,OAAOG,GAC3BG,EAAQ,SAASH,EAAI,KAAK,YAAY,CAAC,CAC3C,EAEA,GAAII,EAAQ,SAAW,EACvB,OAAIA,EAAQ,SAAW,EAAUA,EAAQ,CAAC,EAGnCA,EAAQ,OAAO,CAACC,EAASC,IAC5BA,EAAQ,KAAK,OAASD,EAAQ,KAAK,OAASC,EAAUD,CAC1D,CACJ,CCvBO,SAASE,EAAgBC,EAA4B,CAC1D,IAAMC,EAAkB,CAAC,EAWzB,GARAA,EAAM,KAAK,KAAKD,EAAO,IAAI,EAAE,EAC7BC,EAAM,KAAK,EAAE,EAGbA,EAAM,KAAK,KAAKD,EAAO,OAAO,EAAE,EAChCC,EAAM,KAAK,EAAE,EAGTD,EAAO,QAAUA,EAAO,OAAO,OAAS,EAAG,CAC7CC,EAAM,KAAK,eAAe,EAC1BA,EAAM,KAAK,EAAE,EACb,QAAWC,KAASF,EAAO,OAAQ,CACjC,IAAMG,EAAU,GAAGH,EAAO,OAAO,GAAGE,EAAM,IAAI,GAC9CD,EAAM,KAAK,MAAMC,EAAM,IAAI,KAAKC,CAAO,MAAMD,EAAM,WAAW,EAAE,CAClE,CACAD,EAAM,KAAK,EAAE,CACf,CAGA,GAAID,EAAO,eAAiBA,EAAO,cAAc,OAAS,EAAG,CAC3DC,EAAM,KAAK,cAAc,EACzBA,EAAM,KAAK,EAAE,EACb,QAAWG,KAAQJ,EAAO,cACpBI,EAAK,YACPH,EAAM,KAAK,MAAMG,EAAK,KAAK,KAAKA,EAAK,GAAG,MAAMA,EAAK,WAAW,EAAE,EAEhEH,EAAM,KAAK,MAAMG,EAAK,KAAK,KAAKA,EAAK,GAAG,GAAG,EAG/CH,EAAM,KAAK,EAAE,CACf,CAGA,GAAID,EAAO,UAAYA,EAAO,SAAS,OAAS,EAC9C,QAAWK,KAAWL,EAAO,SAC3BC,EAAM,KAAK,MAAMI,EAAQ,OAAO,EAAE,EAClCJ,EAAM,KAAK,EAAE,EACbA,EAAM,KAAKI,EAAQ,OAAO,EAC1BJ,EAAM,KAAK,EAAE,EAIjB,OAAOA,EAAM,KAAK;AAAA,CAAI,EAAE,KAAK,EAAI;AAAA,CACnC,CFlIA,eAAsBK,EAAeC,EAAcC,EAAqB,CACpE,IAAMC,EAAYF,EAAQ,QAAQ,IAAI,YAAY,EAC5CG,EAAMH,EAAQ,QAAQ,MAAM,EAC5BI,EAAUC,EAASH,CAAS,EAE5BI,EAASN,EAAQ,QAAQ,IAAI,QAAQ,GAAK,GAC1CO,EAAgBP,EAAQ,QAAQ,aAAa,IAAI,MAAM,EAEvDQ,EAAU,CAAC,CAACJ,EACZK,EAAsBH,EAAO,SAAS,eAAe,GAAKC,EAGhE,GAAIC,GAAWC,EAAqB,CAEhC,GAAIN,EAAI,SAAS,WAAW,QAAQ,EAChC,OAAO,eAAa,KAAK,EAI7B,GAAIA,EAAI,WAAa,YACjB,GAAI,CACA,GAAIF,EAAQ,CACR,IAAMS,EAAiBC,EAAgBV,CAAM,EACvCW,EAAW,IAAI,eAAaF,EAAgB,CAC9C,QAAS,CACL,eAAgB,4BAChB,gBAAiB,mEACrB,CACJ,CAAC,EACD,OAAIN,GAASQ,EAAS,QAAQ,IAAI,aAAc,GAAGR,EAAQ,IAAI,KAAKA,EAAQ,OAAO,GAAG,EACtFQ,EAAS,QAAQ,IAAI,eAAgBV,GAAa,OAAO,EAClDU,CACX,CACJ,OAASC,EAAO,CACZ,QAAQ,MAAM,sCAAuCA,CAAK,CAC9D,CAIJ,GAAIV,EAAI,SAAS,SAAS,GAAG,EACzB,OAAO,eAAa,KAAK,EAI7B,IAAIW,EAAcX,EAAI,UAClBW,IAAgB,KAAOA,IAAgB,MAAIA,EAAc,UACzDA,EAAY,SAAS,GAAG,GAAKA,IAAgB,MAAKA,EAAcA,EAAY,MAAM,EAAG,EAAE,GAG3F,IAAMC,EAAe,QAAQ,IAAI,aAC3BC,EAAgB,QAAQ,IAAI,oBAAsB,4BAEpDD,GAEA,MAAM,GAAGC,CAAa,aAAc,CAChC,OAAQ,OACR,QAAS,CAAE,aAAcD,EAAc,eAAgB,kBAAmB,EAC1E,KAAM,KAAK,UAAU,CAAE,MAAOZ,EAAI,SAAU,UAAAD,EAAW,IAAKE,GAAS,KAAM,QAASA,GAAS,OAAQ,CAAC,CAC1G,CAAC,EAAE,MAAM,IAAM,CAAC,CAAC,EAIrBD,EAAI,SAAW,SAASW,CAAW,MACnC,IAAMF,EAAW,eAAa,QAAQT,CAAG,EAGzC,OAAAS,EAAS,QAAQ,IAAI,eAAgB,8BAA8B,EACnEA,EAAS,QAAQ,IAAI,gBAAiB,mEAAmE,EACzGA,EAAS,QAAQ,IAAI,OAAQ,oBAAoB,EACjDA,EAAS,QAAQ,IAAI,eAAgBV,GAAa,OAAO,EAErDE,IACAQ,EAAS,QAAQ,IAAI,aAAc,GAAGR,EAAQ,IAAI,KAAKA,EAAQ,OAAO,GAAG,EACzEQ,EAAS,QAAQ,IAAI,iBAAkB,MAAM,GAG7CL,GAAeK,EAAS,QAAQ,IAAI,eAAgB,MAAM,EAEvDA,CACX,CAGA,IAAMA,EAAW,eAAa,KAAK,EAInC,OAAAA,EAAS,QAAQ,IAAI,OAAQ,oBAAoB,EACjDA,EAAS,QAAQ,IAAI,eAAgBV,GAAa,OAAO,EAElDU,CACX","names":["middleware_exports","__export","AI_BOT_USER_AGENTS","matchBot","ontoMiddleware","__toCommonJS","import_server","AI_BOTS","AI_BOT_USER_AGENTS","AI_BOT_USER_AGENTS_CACHE","bot","matchBot","userAgent","lowerUA","matches","longest","current","generateLlmsTxt","config","lines","route","fullUrl","link","section","ontoMiddleware","request","config","userAgent","url","matched","matchBot","accept","hasDebugParam","isAiBot","isMarkdownRequested","llmsTxtContent","generateLlmsTxt","response","error","payloadPath","ONTO_API_KEY","DASHBOARD_URL"]}
|
|
1
|
+
{"version":3,"sources":["../src/middleware.ts","../src/bots.ts","../src/config.ts"],"sourcesContent":["import { NextRequest, NextResponse } from 'next/server';\r\nimport { matchBot } from './bots';\r\nimport { generateLlmsTxt, OntoConfig } from './config';\r\n\r\nexport async function ontoMiddleware(request: any, config?: OntoConfig) {\r\n const userAgent = request.headers.get('user-agent');\r\n const url = request.nextUrl.clone();\r\n const matched = matchBot(userAgent);\r\n\r\n const accept = request.headers.get('accept') || '';\r\n const hasDebugParam = request.nextUrl.searchParams.has('onto');\r\n\r\n const isAiBot = !!matched;\r\n const isMarkdownRequested = accept.includes('text/markdown') || hasDebugParam;\r\n\r\n // Common logic for bot/markdown negotiation\r\n if (isAiBot || isMarkdownRequested) {\r\n // Ignore internal next.js requests\r\n if (url.pathname.startsWith('/_next')) {\r\n return NextResponse.next();\r\n }\r\n\r\n // --- llms.txt Auto-Discovery ---\r\n if (url.pathname === '/llms.txt') {\r\n try {\r\n if (config) {\r\n const llmsTxtContent = generateLlmsTxt(config);\r\n const response = new NextResponse(llmsTxtContent, {\r\n headers: {\r\n 'Content-Type': 'text/plain; charset=utf-8',\r\n 'Cache-Control': 'public, max-age=3600, s-maxage=3600, stale-while-revalidate=86400',\r\n }\r\n });\r\n if (matched) response.headers.set('X-Onto-Bot', `${matched.name} (${matched.company})`);\r\n response.headers.set('X-Onto-Trace', userAgent || 'no-ua');\r\n return response;\r\n }\r\n } catch (error) {\r\n console.error('[Onto] Failed to generate llms.txt:', error);\r\n }\r\n }\r\n\r\n // Skip other static assets with dots\r\n if (url.pathname.includes('.')) {\r\n return NextResponse.next();\r\n }\r\n\r\n // Determine the corresponding payload path\r\n let payloadPath = url.pathname;\r\n if (payloadPath === '/' || payloadPath === '') payloadPath = '/index';\r\n if (payloadPath.endsWith('/') && payloadPath !== '/') payloadPath = payloadPath.slice(0, -1);\r\n\r\n // --- Onto Control Plane Integration (Premium) ---\r\n const ONTO_API_KEY = process.env.ONTO_API_KEY;\r\n const DASHBOARD_URL = process.env.ONTO_DASHBOARD_URL || 'https://app.buildonto.dev';\r\n\r\n if (ONTO_API_KEY) {\r\n // Logic for tracking and injection ... (fire-and-forget tracking)\r\n fetch(`${DASHBOARD_URL}/api/track`, {\r\n method: 'POST',\r\n headers: { 'x-onto-key': ONTO_API_KEY, 'Content-Type': 'application/json' },\r\n body: JSON.stringify({ route: url.pathname, userAgent, bot: matched?.name, company: matched?.company })\r\n }).catch(() => {});\r\n }\r\n\r\n // Rewrite to semantic payload\r\n url.pathname = `/.onto${payloadPath}.md`;\r\n const response = NextResponse.rewrite(url);\r\n \r\n // Apply headers\r\n response.headers.set('Content-Type', 'text/markdown; charset=utf-8');\r\n response.headers.set('Cache-Control', 'public, max-age=3600, s-maxage=3600, stale-while-revalidate=86400');\r\n response.headers.set('Vary', 'User-Agent, Accept');\r\n response.headers.set('X-Onto-Trace', userAgent || 'no-ua');\r\n \r\n if (matched) {\r\n response.headers.set('X-Onto-Bot', `${matched.name} (${matched.company})`);\r\n response.headers.set('X-Onto-Matched', 'true');\r\n }\r\n \r\n if (hasDebugParam) response.headers.set('X-Onto-Debug', 'true');\r\n\r\n return response;\r\n }\r\n\r\n // Default response for non-bots\r\n const response = NextResponse.next();\r\n \r\n // Add identify headers to EVERY response for clinical debugging\r\n response.headers.set('Vary', 'User-Agent, Accept');\r\n response.headers.set('X-Onto-Trace', userAgent || 'no-ua');\r\n \r\n if (matched) {\r\n response.headers.set('X-Onto-Matched-Bot', matched.name);\r\n response.headers.set('X-Onto-Identified', 'true');\r\n } else {\r\n response.headers.set('X-Onto-Identified', 'false');\r\n }\r\n \r\n return response;\r\n}\r\n\r\n// Re-export the bot registry for consumers who want to extend or inspect it\r\nexport { AI_BOT_USER_AGENTS, matchBot } from './bots';\r\nexport type { AiBot } from './bots';\r\n\r\n\r\n","/**\n * Comprehensive registry of AI bot user-agent strings.\n * The middleware uses this list to detect AI crawlers and serve optimized markdown.\n */\n\nexport interface AiBot {\n /** The user-agent substring to match against */\n name: string;\n /** The company operating this bot */\n company: string;\n /** ISO date when this bot was added or last verified */\n addedAt?: string;\n}\n\n/**\n * Structured registry of all known AI bots, grouped by company.\n * Useful for analytics and the Control Plane dashboard.\n */\nexport const AI_BOTS: AiBot[] = [\n // OpenAI\n { name: 'GPTBot', company: 'OpenAI', addedAt: '2025-01-01' },\n { name: 'ChatGPT-User', company: 'OpenAI', addedAt: '2025-01-01' },\n { name: 'OAI-SearchBot', company: 'OpenAI', addedAt: '2025-01-01' },\n { name: 'ChatGPT', company: 'OpenAI', addedAt: '2025-03-25' },\n { name: 'OpenAI', company: 'OpenAI', addedAt: '2025-03-25' },\n { name: 'GPT', company: 'OpenAI', addedAt: '2025-03-25' },\n\n // Google (SEO Safety: Googlebot proper is EXCLUDED)\n { name: 'Google-CloudVertexBot', company: 'Google', addedAt: '2025-01-01' },\n { name: 'Google-Extended', company: 'Google', addedAt: '2025-01-01' },\n { name: 'GoogleOther', company: 'Google', addedAt: '2025-01-01' },\n\n // Anthropic\n { name: 'ClaudeBot', company: 'Anthropic', addedAt: '2025-01-01' },\n { name: 'Claude-User', company: 'Anthropic', addedAt: '2025-01-01' },\n { name: 'claude-fetch', company: 'Anthropic', addedAt: '2025-03-25' },\n { name: 'AnthropicFetch', company: 'Anthropic', addedAt: '2025-03-25' },\n { name: 'Claude-Fetch', company: 'Anthropic', addedAt: '2025-03-25' },\n { name: 'anthropic-ai', company: 'Anthropic', addedAt: '2025-01-01' },\n { name: 'Claude', company: 'Anthropic', addedAt: '2025-03-25' },\n { name: 'Anthropic', company: 'Anthropic', addedAt: '2025-03-25' },\n\n // Perplexity\n { name: 'PerplexityBot', company: 'Perplexity', addedAt: '2025-01-01' },\n { name: 'Perplexity-User', company: 'Perplexity', addedAt: '2025-01-01' },\n { name: 'Perplexity', company: 'Perplexity', addedAt: '2025-03-25' },\n\n // Meta\n { name: 'Meta-ExternalAgent', company: 'Meta', addedAt: '2025-01-01' },\n { name: 'Meta-ExternalFetcher', company: 'Meta', addedAt: '2025-01-01' },\n { name: 'facebookexternalhit', company: 'Meta', addedAt: '2025-03-25' },\n { name: 'FacebookBot', company: 'Meta', addedAt: '2025-01-01' },\n\n // Mistral\n { name: 'MistralBot', company: 'Mistral', addedAt: '2025-03-25' },\n { name: 'Mistral', company: 'Mistral', addedAt: '2025-03-25' },\n\n // Amazon\n { name: 'Amazonbot', company: 'Amazon', addedAt: '2025-03-25' },\n\n // Others\n { name: 'AI2Bot', company: 'Allen Institute', addedAt: '2025-03-25' },\n { name: 'DuckAssistBot', company: 'DuckDuckGo', addedAt: '2025-03-25' },\n { name: 'Diffbot', company: 'Diffbot', addedAt: '2025-03-25' },\n { name: 'CCBot', company: 'Common Crawl', addedAt: '2025-01-01' },\n { name: 'Bytespider', company: 'ByteDance', addedAt: '2025-01-01' },\n { name: 'Applebot-Extended', company: 'Apple', addedAt: '2025-01-01' },\n { name: 'YouBot', company: 'You.com', addedAt: '2025-01-01' },\n\n // Generic AI / Scraping Libraries (Last Resort)\n { name: 'python-requests', company: 'Generic Bot', addedAt: '2025-03-25' },\n { name: 'python-httpx', company: 'Generic Bot', addedAt: '2025-03-25' },\n { name: 'httpx', company: 'Generic Bot', addedAt: '2025-03-25' },\n { name: 'axios', company: 'Generic Bot', addedAt: '2025-03-25' },\n { name: 'node-fetch', company: 'Generic Bot', addedAt: '2025-03-25' },\n { name: 'Go-http-client', company: 'Generic Bot', addedAt: '2025-03-25' },\n { name: 'Wget', company: 'Generic Bot', addedAt: '2025-03-25' },\n { name: 'Curl', company: 'Generic Bot', addedAt: '2025-03-25' },\n];\n\n/**\n * Flat list of user-agent substrings for fast matching in the middleware.\n */\nexport const AI_BOT_USER_AGENTS: string[] = AI_BOT_USER_AGENTS_CACHE();\n\nfunction AI_BOT_USER_AGENTS_CACHE() {\n return AI_BOTS.map(bot => bot.name);\n}\n\n/**\n * Given a raw user-agent string, returns the matched AiBot entry or undefined.\n * Uses a \"Longest Match\" strategy to ensure maximum specificity.\n * Comparison is case-insensitive.\n */\nexport function matchBot(userAgent: string | null): AiBot | undefined {\n if (!userAgent) return undefined;\n const lowerUA = userAgent.toLowerCase();\n \n // Find all matches\n const matches = AI_BOTS.filter(bot => \n lowerUA.includes(bot.name.toLowerCase())\n );\n\n if (matches.length === 0) return undefined;\n if (matches.length === 1) return matches[0];\n\n // Pick the longest match for maximum specificity (e.g. 'ChatGPT-User' vs 'GPT')\n return matches.reduce((longest, current) => \n current.name.length > longest.name.length ? current : longest\n );\n}\n","/**\r\n * Configuration schema for onto.config.ts\r\n * Used to dynamically generate llms.txt and other AI discovery files\r\n */\r\n\r\nexport type PageType = 'scoring' | 'about' | 'default';\r\n\r\nexport interface OntoRoute {\r\n /**\r\n * The URL path (e.g., '/docs', '/api/reference')\r\n */\r\n path: string;\r\n /**\r\n * Description of what this route contains\r\n */\r\n description: string;\r\n /**\r\n * Optional: Page type for automatic JSON-LD schema injection\r\n * - 'scoring': Injects Methodology schema with AIO scoring weights (40/35/25)\r\n * - 'about': Injects Organization/AboutPage schema\r\n * - 'default': No automatic schema injection\r\n */\r\n pageType?: PageType;\r\n}\r\n\r\nexport interface OntoConfig {\r\n /**\r\n * The name of your project or site (required)\r\n * Used as the H1 heading in llms.txt\r\n */\r\n name: string;\r\n\r\n /**\r\n * A short summary of your project (required)\r\n * Displayed as a blockquote in llms.txt\r\n * Should contain key information necessary for understanding the rest of the file\r\n */\r\n summary: string;\r\n\r\n /**\r\n * The base URL of your site (e.g., 'https://example.com')\r\n */\r\n baseUrl: string;\r\n\r\n /**\r\n * Optional: Additional sections to include in llms.txt\r\n * Each section can contain any markdown content\r\n */\r\n sections?: {\r\n heading: string;\r\n content: string;\r\n }[];\r\n\r\n /**\r\n * Key routes that AI agents should know about\r\n * These will be formatted as a markdown list in llms.txt\r\n */\r\n routes?: OntoRoute[];\r\n\r\n /**\r\n * Optional: Links to external resources (documentation, API references, etc.)\r\n */\r\n externalLinks?: {\r\n title: string;\r\n url: string;\r\n description?: string;\r\n }[];\r\n\r\n /**\r\n * Optional: Organization information for JSON-LD schemas\r\n */\r\n organization?: {\r\n name: string;\r\n description?: string;\r\n url?: string;\r\n logo?: string;\r\n foundingDate?: string;\r\n };\r\n}\r\n\r\n/**\r\n * Generate llms.txt content from OntoConfig\r\n * Follows the llms.txt specification:\r\n * - H1 with project name\r\n * - Blockquote with summary\r\n * - Additional markdown sections\r\n */\r\nexport function generateLlmsTxt(config: OntoConfig): string {\r\n const lines: string[] = [];\r\n\r\n // H1: Project name (required)\r\n lines.push(`# ${config.name}`);\r\n lines.push('');\r\n\r\n // Blockquote: Summary (required)\r\n lines.push(`> ${config.summary}`);\r\n lines.push('');\r\n\r\n // Key Routes section (if provided)\r\n if (config.routes && config.routes.length > 0) {\r\n lines.push('## Key Routes');\r\n lines.push('');\r\n for (const route of config.routes) {\r\n const fullUrl = `${config.baseUrl}${route.path}`;\r\n lines.push(`- [${route.path}](${fullUrl}): ${route.description}`);\r\n }\r\n lines.push('');\r\n }\r\n\r\n // External Links section (if provided)\r\n if (config.externalLinks && config.externalLinks.length > 0) {\r\n lines.push('## Resources');\r\n lines.push('');\r\n for (const link of config.externalLinks) {\r\n if (link.description) {\r\n lines.push(`- [${link.title}](${link.url}): ${link.description}`);\r\n } else {\r\n lines.push(`- [${link.title}](${link.url})`);\r\n }\r\n }\r\n lines.push('');\r\n }\r\n\r\n // Custom sections (if provided)\r\n if (config.sections && config.sections.length > 0) {\r\n for (const section of config.sections) {\r\n lines.push(`## ${section.heading}`);\r\n lines.push('');\r\n lines.push(section.content);\r\n lines.push('');\r\n }\r\n }\r\n\r\n return lines.join('\\n').trim() + '\\n';\r\n}\r\n"],"mappings":"yaAAA,IAAAA,EAAA,GAAAC,EAAAD,EAAA,wBAAAE,EAAA,aAAAC,EAAA,mBAAAC,IAAA,eAAAC,EAAAL,GAAA,IAAAM,EAA0C,uBCkBnC,IAAMC,EAAmB,CAE5B,CAAE,KAAM,SAAqB,QAAS,SAAY,QAAS,YAAa,EACxE,CAAE,KAAM,eAAoB,QAAS,SAAY,QAAS,YAAa,EACvE,CAAE,KAAM,gBAAoB,QAAS,SAAY,QAAS,YAAa,EACvE,CAAE,KAAM,UAAoB,QAAS,SAAY,QAAS,YAAa,EACvE,CAAE,KAAM,SAAoB,QAAS,SAAY,QAAS,YAAa,EACvE,CAAE,KAAM,MAAoB,QAAS,SAAY,QAAS,YAAa,EAGvE,CAAE,KAAM,wBAA2B,QAAS,SAAU,QAAS,YAAa,EAC5E,CAAE,KAAM,kBAA2B,QAAS,SAAU,QAAS,YAAa,EAC5E,CAAE,KAAM,cAA2B,QAAS,SAAU,QAAS,YAAa,EAG5E,CAAE,KAAM,YAAmB,QAAS,YAAa,QAAS,YAAa,EACvE,CAAE,KAAM,cAAkB,QAAS,YAAa,QAAS,YAAa,EACtE,CAAE,KAAM,eAAkB,QAAS,YAAa,QAAS,YAAa,EACtE,CAAE,KAAM,iBAAkB,QAAS,YAAa,QAAS,YAAa,EACtE,CAAE,KAAM,eAAkB,QAAS,YAAa,QAAS,YAAa,EACtE,CAAE,KAAM,eAAkB,QAAS,YAAa,QAAS,YAAa,EACtE,CAAE,KAAM,SAAkB,QAAS,YAAa,QAAS,YAAa,EACtE,CAAE,KAAM,YAAkB,QAAS,YAAa,QAAS,YAAa,EAGtE,CAAE,KAAM,gBAAmB,QAAS,aAAc,QAAS,YAAa,EACxE,CAAE,KAAM,kBAAmB,QAAS,aAAc,QAAS,YAAa,EACxE,CAAE,KAAM,aAAmB,QAAS,aAAc,QAAS,YAAa,EAGxE,CAAE,KAAM,qBAAwB,QAAS,OAAQ,QAAS,YAAa,EACvE,CAAE,KAAM,uBAAwB,QAAS,OAAQ,QAAS,YAAa,EACvE,CAAE,KAAM,sBAAwB,QAAS,OAAQ,QAAS,YAAa,EACvE,CAAE,KAAM,cAAwB,QAAS,OAAQ,QAAS,YAAa,EAGvE,CAAE,KAAM,aAAc,QAAS,UAAW,QAAS,YAAa,EAChE,CAAE,KAAM,UAAc,QAAS,UAAW,QAAS,YAAa,EAGhE,CAAE,KAAM,YAAa,QAAS,SAAU,QAAS,YAAa,EAG9D,CAAE,KAAM,SAAiB,QAAS,kBAAmB,QAAS,YAAa,EAC3E,CAAE,KAAM,gBAAiB,QAAS,aAAc,QAAS,YAAa,EACtE,CAAE,KAAM,UAAiB,QAAS,UAAe,QAAS,YAAa,EACvE,CAAE,KAAM,QAAiB,QAAS,eAAgB,QAAS,YAAa,EACxE,CAAE,KAAM,aAAiB,QAAS,YAAgB,QAAS,YAAa,EACxE,CAAE,KAAM,oBAAqB,QAAS,QAAY,QAAS,YAAa,EACxE,CAAE,KAAM,SAAiB,QAAS,UAAgB,QAAS,YAAa,EAGxE,CAAE,KAAM,kBAAoB,QAAS,cAAe,QAAS,YAAa,EAC1E,CAAE,KAAM,eAAoB,QAAS,cAAe,QAAS,YAAa,EAC1E,CAAE,KAAM,QAAoB,QAAS,cAAe,QAAS,YAAa,EAC1E,CAAE,KAAM,QAAoB,QAAS,cAAe,QAAS,YAAa,EAC1E,CAAE,KAAM,aAAoB,QAAS,cAAe,QAAS,YAAa,EAC1E,CAAE,KAAM,iBAAoB,QAAS,cAAe,QAAS,YAAa,EAC1E,CAAE,KAAM,OAAoB,QAAS,cAAe,QAAS,YAAa,EAC1E,CAAE,KAAM,OAAoB,QAAS,cAAe,QAAS,YAAa,CAC9E,EAKaC,EAA+BC,EAAyB,EAErE,SAASA,GAA2B,CAChC,OAAOF,EAAQ,IAAIG,GAAOA,EAAI,IAAI,CACtC,CAOO,SAASC,EAASC,EAA6C,CAClE,GAAI,CAACA,EAAW,OAChB,IAAMC,EAAUD,EAAU,YAAY,EAGhCE,EAAUP,EAAQ,OAAOG,GAC3BG,EAAQ,SAASH,EAAI,KAAK,YAAY,CAAC,CAC3C,EAEA,GAAII,EAAQ,SAAW,EACvB,OAAIA,EAAQ,SAAW,EAAUA,EAAQ,CAAC,EAGnCA,EAAQ,OAAO,CAACC,EAASC,IAC5BA,EAAQ,KAAK,OAASD,EAAQ,KAAK,OAASC,EAAUD,CAC1D,CACJ,CCvBO,SAASE,EAAgBC,EAA4B,CAC1D,IAAMC,EAAkB,CAAC,EAWzB,GARAA,EAAM,KAAK,KAAKD,EAAO,IAAI,EAAE,EAC7BC,EAAM,KAAK,EAAE,EAGbA,EAAM,KAAK,KAAKD,EAAO,OAAO,EAAE,EAChCC,EAAM,KAAK,EAAE,EAGTD,EAAO,QAAUA,EAAO,OAAO,OAAS,EAAG,CAC7CC,EAAM,KAAK,eAAe,EAC1BA,EAAM,KAAK,EAAE,EACb,QAAWC,KAASF,EAAO,OAAQ,CACjC,IAAMG,EAAU,GAAGH,EAAO,OAAO,GAAGE,EAAM,IAAI,GAC9CD,EAAM,KAAK,MAAMC,EAAM,IAAI,KAAKC,CAAO,MAAMD,EAAM,WAAW,EAAE,CAClE,CACAD,EAAM,KAAK,EAAE,CACf,CAGA,GAAID,EAAO,eAAiBA,EAAO,cAAc,OAAS,EAAG,CAC3DC,EAAM,KAAK,cAAc,EACzBA,EAAM,KAAK,EAAE,EACb,QAAWG,KAAQJ,EAAO,cACpBI,EAAK,YACPH,EAAM,KAAK,MAAMG,EAAK,KAAK,KAAKA,EAAK,GAAG,MAAMA,EAAK,WAAW,EAAE,EAEhEH,EAAM,KAAK,MAAMG,EAAK,KAAK,KAAKA,EAAK,GAAG,GAAG,EAG/CH,EAAM,KAAK,EAAE,CACf,CAGA,GAAID,EAAO,UAAYA,EAAO,SAAS,OAAS,EAC9C,QAAWK,KAAWL,EAAO,SAC3BC,EAAM,KAAK,MAAMI,EAAQ,OAAO,EAAE,EAClCJ,EAAM,KAAK,EAAE,EACbA,EAAM,KAAKI,EAAQ,OAAO,EAC1BJ,EAAM,KAAK,EAAE,EAIjB,OAAOA,EAAM,KAAK;AAAA,CAAI,EAAE,KAAK,EAAI;AAAA,CACnC,CFlIA,eAAsBK,EAAeC,EAAcC,EAAqB,CACpE,IAAMC,EAAYF,EAAQ,QAAQ,IAAI,YAAY,EAC5CG,EAAMH,EAAQ,QAAQ,MAAM,EAC5BI,EAAUC,EAASH,CAAS,EAE5BI,EAASN,EAAQ,QAAQ,IAAI,QAAQ,GAAK,GAC1CO,EAAgBP,EAAQ,QAAQ,aAAa,IAAI,MAAM,EAEvDQ,EAAU,CAAC,CAACJ,EACZK,EAAsBH,EAAO,SAAS,eAAe,GAAKC,EAGhE,GAAIC,GAAWC,EAAqB,CAEhC,GAAIN,EAAI,SAAS,WAAW,QAAQ,EAChC,OAAO,eAAa,KAAK,EAI7B,GAAIA,EAAI,WAAa,YACjB,GAAI,CACA,GAAIF,EAAQ,CACR,IAAMS,EAAiBC,EAAgBV,CAAM,EACvCW,EAAW,IAAI,eAAaF,EAAgB,CAC9C,QAAS,CACL,eAAgB,4BAChB,gBAAiB,mEACrB,CACJ,CAAC,EACD,OAAIN,GAASQ,EAAS,QAAQ,IAAI,aAAc,GAAGR,EAAQ,IAAI,KAAKA,EAAQ,OAAO,GAAG,EACtFQ,EAAS,QAAQ,IAAI,eAAgBV,GAAa,OAAO,EAClDU,CACX,CACJ,OAASC,EAAO,CACZ,QAAQ,MAAM,sCAAuCA,CAAK,CAC9D,CAIJ,GAAIV,EAAI,SAAS,SAAS,GAAG,EACzB,OAAO,eAAa,KAAK,EAI7B,IAAIW,EAAcX,EAAI,UAClBW,IAAgB,KAAOA,IAAgB,MAAIA,EAAc,UACzDA,EAAY,SAAS,GAAG,GAAKA,IAAgB,MAAKA,EAAcA,EAAY,MAAM,EAAG,EAAE,GAG3F,IAAMC,EAAe,QAAQ,IAAI,aAC3BC,EAAgB,QAAQ,IAAI,oBAAsB,4BAEpDD,GAEA,MAAM,GAAGC,CAAa,aAAc,CAChC,OAAQ,OACR,QAAS,CAAE,aAAcD,EAAc,eAAgB,kBAAmB,EAC1E,KAAM,KAAK,UAAU,CAAE,MAAOZ,EAAI,SAAU,UAAAD,EAAW,IAAKE,GAAS,KAAM,QAASA,GAAS,OAAQ,CAAC,CAC1G,CAAC,EAAE,MAAM,IAAM,CAAC,CAAC,EAIrBD,EAAI,SAAW,SAASW,CAAW,MACnC,IAAMF,EAAW,eAAa,QAAQT,CAAG,EAGzC,OAAAS,EAAS,QAAQ,IAAI,eAAgB,8BAA8B,EACnEA,EAAS,QAAQ,IAAI,gBAAiB,mEAAmE,EACzGA,EAAS,QAAQ,IAAI,OAAQ,oBAAoB,EACjDA,EAAS,QAAQ,IAAI,eAAgBV,GAAa,OAAO,EAErDE,IACAQ,EAAS,QAAQ,IAAI,aAAc,GAAGR,EAAQ,IAAI,KAAKA,EAAQ,OAAO,GAAG,EACzEQ,EAAS,QAAQ,IAAI,iBAAkB,MAAM,GAG7CL,GAAeK,EAAS,QAAQ,IAAI,eAAgB,MAAM,EAEvDA,CACX,CAGA,IAAMA,EAAW,eAAa,KAAK,EAGnC,OAAAA,EAAS,QAAQ,IAAI,OAAQ,oBAAoB,EACjDA,EAAS,QAAQ,IAAI,eAAgBV,GAAa,OAAO,EAErDE,GACAQ,EAAS,QAAQ,IAAI,qBAAsBR,EAAQ,IAAI,EACvDQ,EAAS,QAAQ,IAAI,oBAAqB,MAAM,GAEhDA,EAAS,QAAQ,IAAI,oBAAqB,OAAO,EAG9CA,CACX","names":["middleware_exports","__export","AI_BOT_USER_AGENTS","matchBot","ontoMiddleware","__toCommonJS","import_server","AI_BOTS","AI_BOT_USER_AGENTS","AI_BOT_USER_AGENTS_CACHE","bot","matchBot","userAgent","lowerUA","matches","longest","current","generateLlmsTxt","config","lines","route","fullUrl","link","section","ontoMiddleware","request","config","userAgent","url","matched","matchBot","accept","hasDebugParam","isAiBot","isMarkdownRequested","llmsTxtContent","generateLlmsTxt","response","error","payloadPath","ONTO_API_KEY","DASHBOARD_URL"]}
|
package/dist/middleware.mjs
CHANGED
|
@@ -1,4 +1,4 @@
|
|
|
1
|
-
import{NextResponse as
|
|
1
|
+
import{NextResponse as p}from"next/server";var A=[{name:"GPTBot",company:"OpenAI",addedAt:"2025-01-01"},{name:"ChatGPT-User",company:"OpenAI",addedAt:"2025-01-01"},{name:"OAI-SearchBot",company:"OpenAI",addedAt:"2025-01-01"},{name:"ChatGPT",company:"OpenAI",addedAt:"2025-03-25"},{name:"OpenAI",company:"OpenAI",addedAt:"2025-03-25"},{name:"GPT",company:"OpenAI",addedAt:"2025-03-25"},{name:"Google-CloudVertexBot",company:"Google",addedAt:"2025-01-01"},{name:"Google-Extended",company:"Google",addedAt:"2025-01-01"},{name:"GoogleOther",company:"Google",addedAt:"2025-01-01"},{name:"ClaudeBot",company:"Anthropic",addedAt:"2025-01-01"},{name:"Claude-User",company:"Anthropic",addedAt:"2025-01-01"},{name:"claude-fetch",company:"Anthropic",addedAt:"2025-03-25"},{name:"AnthropicFetch",company:"Anthropic",addedAt:"2025-03-25"},{name:"Claude-Fetch",company:"Anthropic",addedAt:"2025-03-25"},{name:"anthropic-ai",company:"Anthropic",addedAt:"2025-01-01"},{name:"Claude",company:"Anthropic",addedAt:"2025-03-25"},{name:"Anthropic",company:"Anthropic",addedAt:"2025-03-25"},{name:"PerplexityBot",company:"Perplexity",addedAt:"2025-01-01"},{name:"Perplexity-User",company:"Perplexity",addedAt:"2025-01-01"},{name:"Perplexity",company:"Perplexity",addedAt:"2025-03-25"},{name:"Meta-ExternalAgent",company:"Meta",addedAt:"2025-01-01"},{name:"Meta-ExternalFetcher",company:"Meta",addedAt:"2025-01-01"},{name:"facebookexternalhit",company:"Meta",addedAt:"2025-03-25"},{name:"FacebookBot",company:"Meta",addedAt:"2025-01-01"},{name:"MistralBot",company:"Mistral",addedAt:"2025-03-25"},{name:"Mistral",company:"Mistral",addedAt:"2025-03-25"},{name:"Amazonbot",company:"Amazon",addedAt:"2025-03-25"},{name:"AI2Bot",company:"Allen Institute",addedAt:"2025-03-25"},{name:"DuckAssistBot",company:"DuckDuckGo",addedAt:"2025-03-25"},{name:"Diffbot",company:"Diffbot",addedAt:"2025-03-25"},{name:"CCBot",company:"Common Crawl",addedAt:"2025-01-01"},{name:"Bytespider",company:"ByteDance",addedAt:"2025-01-01"},{name:"Applebot-Extended",company:"Apple",addedAt:"2025-01-01"},{name:"YouBot",company:"You.com",addedAt:"2025-01-01"},{name:"python-requests",company:"Generic Bot",addedAt:"2025-03-25"},{name:"python-httpx",company:"Generic Bot",addedAt:"2025-03-25"},{name:"httpx",company:"Generic Bot",addedAt:"2025-03-25"},{name:"axios",company:"Generic Bot",addedAt:"2025-03-25"},{name:"node-fetch",company:"Generic Bot",addedAt:"2025-03-25"},{name:"Go-http-client",company:"Generic Bot",addedAt:"2025-03-25"},{name:"Wget",company:"Generic Bot",addedAt:"2025-03-25"},{name:"Curl",company:"Generic Bot",addedAt:"2025-03-25"}],O=B();function B(){return A.map(n=>n.name)}function m(n){if(!n)return;let t=n.toLowerCase(),e=A.filter(a=>t.includes(a.name.toLowerCase()));if(e.length!==0)return e.length===1?e[0]:e.reduce((a,o)=>o.name.length>a.name.length?o:a)}function u(n){let t=[];if(t.push(`# ${n.name}`),t.push(""),t.push(`> ${n.summary}`),t.push(""),n.routes&&n.routes.length>0){t.push("## Key Routes"),t.push("");for(let e of n.routes){let a=`${n.baseUrl}${e.path}`;t.push(`- [${e.path}](${a}): ${e.description}`)}t.push("")}if(n.externalLinks&&n.externalLinks.length>0){t.push("## Resources"),t.push("");for(let e of n.externalLinks)e.description?t.push(`- [${e.title}](${e.url}): ${e.description}`):t.push(`- [${e.title}](${e.url})`);t.push("")}if(n.sections&&n.sections.length>0)for(let e of n.sections)t.push(`## ${e.heading}`),t.push(""),t.push(e.content),t.push("");return t.join(`
|
|
2
2
|
`).trim()+`
|
|
3
|
-
`}async function
|
|
3
|
+
`}async function b(n,t){let e=n.headers.get("user-agent"),a=n.nextUrl.clone(),o=m(e),y=n.headers.get("accept")||"",h=n.nextUrl.searchParams.has("onto"),g=!!o,x=y.includes("text/markdown")||h;if(g||x){if(a.pathname.startsWith("/_next"))return p.next();if(a.pathname==="/llms.txt")try{if(t){let c=u(t),i=new p(c,{headers:{"Content-Type":"text/plain; charset=utf-8","Cache-Control":"public, max-age=3600, s-maxage=3600, stale-while-revalidate=86400"}});return o&&i.headers.set("X-Onto-Bot",`${o.name} (${o.company})`),i.headers.set("X-Onto-Trace",e||"no-ua"),i}}catch(c){console.error("[Onto] Failed to generate llms.txt:",c)}if(a.pathname.includes("."))return p.next();let r=a.pathname;(r==="/"||r==="")&&(r="/index"),r.endsWith("/")&&r!=="/"&&(r=r.slice(0,-1));let l=process.env.ONTO_API_KEY,f=process.env.ONTO_DASHBOARD_URL||"https://app.buildonto.dev";l&&fetch(`${f}/api/track`,{method:"POST",headers:{"x-onto-key":l,"Content-Type":"application/json"},body:JSON.stringify({route:a.pathname,userAgent:e,bot:o?.name,company:o?.company})}).catch(()=>{}),a.pathname=`/.onto${r}.md`;let d=p.rewrite(a);return d.headers.set("Content-Type","text/markdown; charset=utf-8"),d.headers.set("Cache-Control","public, max-age=3600, s-maxage=3600, stale-while-revalidate=86400"),d.headers.set("Vary","User-Agent, Accept"),d.headers.set("X-Onto-Trace",e||"no-ua"),o&&(d.headers.set("X-Onto-Bot",`${o.name} (${o.company})`),d.headers.set("X-Onto-Matched","true")),h&&d.headers.set("X-Onto-Debug","true"),d}let s=p.next();return s.headers.set("Vary","User-Agent, Accept"),s.headers.set("X-Onto-Trace",e||"no-ua"),o?(s.headers.set("X-Onto-Matched-Bot",o.name),s.headers.set("X-Onto-Identified","true")):s.headers.set("X-Onto-Identified","false"),s}export{O as AI_BOT_USER_AGENTS,m as matchBot,b as ontoMiddleware};
|
|
4
4
|
//# sourceMappingURL=middleware.mjs.map
|
package/dist/middleware.mjs.map
CHANGED
|
@@ -1 +1 @@
|
|
|
1
|
-
{"version":3,"sources":["../src/middleware.ts","../src/bots.ts","../src/config.ts"],"sourcesContent":["import { NextRequest, NextResponse } from 'next/server';\r\nimport { matchBot } from './bots';\r\nimport { generateLlmsTxt, OntoConfig } from './config';\r\n\r\nexport async function ontoMiddleware(request: any, config?: OntoConfig) {\r\n const userAgent = request.headers.get('user-agent');\r\n const url = request.nextUrl.clone();\r\n const matched = matchBot(userAgent);\r\n\r\n const accept = request.headers.get('accept') || '';\r\n const hasDebugParam = request.nextUrl.searchParams.has('onto');\r\n\r\n const isAiBot = !!matched;\r\n const isMarkdownRequested = accept.includes('text/markdown') || hasDebugParam;\r\n\r\n // Common logic for bot/markdown negotiation\r\n if (isAiBot || isMarkdownRequested) {\r\n // Ignore internal next.js requests\r\n if (url.pathname.startsWith('/_next')) {\r\n return NextResponse.next();\r\n }\r\n\r\n // --- llms.txt Auto-Discovery ---\r\n if (url.pathname === '/llms.txt') {\r\n try {\r\n if (config) {\r\n const llmsTxtContent = generateLlmsTxt(config);\r\n const response = new NextResponse(llmsTxtContent, {\r\n headers: {\r\n 'Content-Type': 'text/plain; charset=utf-8',\r\n 'Cache-Control': 'public, max-age=3600, s-maxage=3600, stale-while-revalidate=86400',\r\n }\r\n });\r\n if (matched) response.headers.set('X-Onto-Bot', `${matched.name} (${matched.company})`);\r\n response.headers.set('X-Onto-Trace', userAgent || 'no-ua');\r\n return response;\r\n }\r\n } catch (error) {\r\n console.error('[Onto] Failed to generate llms.txt:', error);\r\n }\r\n }\r\n\r\n // Skip other static assets with dots\r\n if (url.pathname.includes('.')) {\r\n return NextResponse.next();\r\n }\r\n\r\n // Determine the corresponding payload path\r\n let payloadPath = url.pathname;\r\n if (payloadPath === '/' || payloadPath === '') payloadPath = '/index';\r\n if (payloadPath.endsWith('/') && payloadPath !== '/') payloadPath = payloadPath.slice(0, -1);\r\n\r\n // --- Onto Control Plane Integration (Premium) ---\r\n const ONTO_API_KEY = process.env.ONTO_API_KEY;\r\n const DASHBOARD_URL = process.env.ONTO_DASHBOARD_URL || 'https://app.buildonto.dev';\r\n\r\n if (ONTO_API_KEY) {\r\n // Logic for tracking and injection ... (fire-and-forget tracking)\r\n fetch(`${DASHBOARD_URL}/api/track`, {\r\n method: 'POST',\r\n headers: { 'x-onto-key': ONTO_API_KEY, 'Content-Type': 'application/json' },\r\n body: JSON.stringify({ route: url.pathname, userAgent, bot: matched?.name, company: matched?.company })\r\n }).catch(() => {});\r\n }\r\n\r\n // Rewrite to semantic payload\r\n url.pathname = `/.onto${payloadPath}.md`;\r\n const response = NextResponse.rewrite(url);\r\n \r\n // Apply headers\r\n response.headers.set('Content-Type', 'text/markdown; charset=utf-8');\r\n response.headers.set('Cache-Control', 'public, max-age=3600, s-maxage=3600, stale-while-revalidate=86400');\r\n response.headers.set('Vary', 'User-Agent, Accept');\r\n response.headers.set('X-Onto-Trace', userAgent || 'no-ua');\r\n \r\n if (matched) {\r\n response.headers.set('X-Onto-Bot', `${matched.name} (${matched.company})`);\r\n response.headers.set('X-Onto-Matched', 'true');\r\n }\r\n \r\n if (hasDebugParam) response.headers.set('X-Onto-Debug', 'true');\r\n\r\n return response;\r\n }\r\n\r\n // Default response for non-bots\r\n const response = NextResponse.next();\r\n \r\n // Crucial: Tell Vercel/Edge to vary the cache by User-Agent \r\n // This ensures bots get the rewrite and humans get the HTML\r\n response.headers.set('Vary', 'User-Agent, Accept');\r\n response.headers.set('X-Onto-Trace', userAgent || 'no-ua');\r\n \r\n return response;\r\n}\r\n\r\n// Re-export the bot registry for consumers who want to extend or inspect it\r\nexport { AI_BOT_USER_AGENTS, matchBot } from './bots';\r\nexport type { AiBot } from './bots';\r\n\r\n\r\n","/**\n * Comprehensive registry of AI bot user-agent strings.\n * The middleware uses this list to detect AI crawlers and serve optimized markdown.\n */\n\nexport interface AiBot {\n /** The user-agent substring to match against */\n name: string;\n /** The company operating this bot */\n company: string;\n /** ISO date when this bot was added or last verified */\n addedAt?: string;\n}\n\n/**\n * Structured registry of all known AI bots, grouped by company.\n * Useful for analytics and the Control Plane dashboard.\n */\nexport const AI_BOTS: AiBot[] = [\n // OpenAI\n { name: 'GPTBot', company: 'OpenAI', addedAt: '2025-01-01' },\n { name: 'ChatGPT-User', company: 'OpenAI', addedAt: '2025-01-01' },\n { name: 'OAI-SearchBot', company: 'OpenAI', addedAt: '2025-01-01' },\n { name: 'ChatGPT', company: 'OpenAI', addedAt: '2025-03-25' },\n { name: 'OpenAI', company: 'OpenAI', addedAt: '2025-03-25' },\n { name: 'GPT', company: 'OpenAI', addedAt: '2025-03-25' },\n\n // Google (SEO Safety: Googlebot proper is EXCLUDED)\n { name: 'Google-CloudVertexBot', company: 'Google', addedAt: '2025-01-01' },\n { name: 'Google-Extended', company: 'Google', addedAt: '2025-01-01' },\n { name: 'GoogleOther', company: 'Google', addedAt: '2025-01-01' },\n\n // Anthropic\n { name: 'ClaudeBot', company: 'Anthropic', addedAt: '2025-01-01' },\n { name: 'Claude-User', company: 'Anthropic', addedAt: '2025-01-01' },\n { name: 'claude-fetch', company: 'Anthropic', addedAt: '2025-03-25' },\n { name: 'AnthropicFetch', company: 'Anthropic', addedAt: '2025-03-25' },\n { name: 'Claude-Fetch', company: 'Anthropic', addedAt: '2025-03-25' },\n { name: 'anthropic-ai', company: 'Anthropic', addedAt: '2025-01-01' },\n { name: 'Claude', company: 'Anthropic', addedAt: '2025-03-25' },\n { name: 'Anthropic', company: 'Anthropic', addedAt: '2025-03-25' },\n\n // Perplexity\n { name: 'PerplexityBot', company: 'Perplexity', addedAt: '2025-01-01' },\n { name: 'Perplexity-User', company: 'Perplexity', addedAt: '2025-01-01' },\n { name: 'Perplexity', company: 'Perplexity', addedAt: '2025-03-25' },\n\n // Meta\n { name: 'Meta-ExternalAgent', company: 'Meta', addedAt: '2025-01-01' },\n { name: 'Meta-ExternalFetcher', company: 'Meta', addedAt: '2025-01-01' },\n { name: 'facebookexternalhit', company: 'Meta', addedAt: '2025-03-25' },\n { name: 'FacebookBot', company: 'Meta', addedAt: '2025-01-01' },\n\n // Mistral\n { name: 'MistralBot', company: 'Mistral', addedAt: '2025-03-25' },\n { name: 'Mistral', company: 'Mistral', addedAt: '2025-03-25' },\n\n // Amazon\n { name: 'Amazonbot', company: 'Amazon', addedAt: '2025-03-25' },\n\n // Others\n { name: 'AI2Bot', company: 'Allen Institute', addedAt: '2025-03-25' },\n { name: 'DuckAssistBot', company: 'DuckDuckGo', addedAt: '2025-03-25' },\n { name: 'Diffbot', company: 'Diffbot', addedAt: '2025-03-25' },\n { name: 'CCBot', company: 'Common Crawl', addedAt: '2025-01-01' },\n { name: 'Bytespider', company: 'ByteDance', addedAt: '2025-01-01' },\n { name: 'Applebot-Extended', company: 'Apple', addedAt: '2025-01-01' },\n { name: 'YouBot', company: 'You.com', addedAt: '2025-01-01' },\n\n // Generic AI / Scraping Libraries (Last Resort)\n { name: 'python-requests', company: 'Generic Bot', addedAt: '2025-03-25' },\n { name: 'python-httpx', company: 'Generic Bot', addedAt: '2025-03-25' },\n { name: 'httpx', company: 'Generic Bot', addedAt: '2025-03-25' },\n { name: 'axios', company: 'Generic Bot', addedAt: '2025-03-25' },\n { name: 'node-fetch', company: 'Generic Bot', addedAt: '2025-03-25' },\n { name: 'Go-http-client', company: 'Generic Bot', addedAt: '2025-03-25' },\n { name: 'Wget', company: 'Generic Bot', addedAt: '2025-03-25' },\n { name: 'Curl', company: 'Generic Bot', addedAt: '2025-03-25' },\n];\n\n/**\n * Flat list of user-agent substrings for fast matching in the middleware.\n */\nexport const AI_BOT_USER_AGENTS: string[] = AI_BOT_USER_AGENTS_CACHE();\n\nfunction AI_BOT_USER_AGENTS_CACHE() {\n return AI_BOTS.map(bot => bot.name);\n}\n\n/**\n * Given a raw user-agent string, returns the matched AiBot entry or undefined.\n * Uses a \"Longest Match\" strategy to ensure maximum specificity.\n * Comparison is case-insensitive.\n */\nexport function matchBot(userAgent: string | null): AiBot | undefined {\n if (!userAgent) return undefined;\n const lowerUA = userAgent.toLowerCase();\n \n // Find all matches\n const matches = AI_BOTS.filter(bot => \n lowerUA.includes(bot.name.toLowerCase())\n );\n\n if (matches.length === 0) return undefined;\n if (matches.length === 1) return matches[0];\n\n // Pick the longest match for maximum specificity (e.g. 'ChatGPT-User' vs 'GPT')\n return matches.reduce((longest, current) => \n current.name.length > longest.name.length ? current : longest\n );\n}\n","/**\r\n * Configuration schema for onto.config.ts\r\n * Used to dynamically generate llms.txt and other AI discovery files\r\n */\r\n\r\nexport type PageType = 'scoring' | 'about' | 'default';\r\n\r\nexport interface OntoRoute {\r\n /**\r\n * The URL path (e.g., '/docs', '/api/reference')\r\n */\r\n path: string;\r\n /**\r\n * Description of what this route contains\r\n */\r\n description: string;\r\n /**\r\n * Optional: Page type for automatic JSON-LD schema injection\r\n * - 'scoring': Injects Methodology schema with AIO scoring weights (40/35/25)\r\n * - 'about': Injects Organization/AboutPage schema\r\n * - 'default': No automatic schema injection\r\n */\r\n pageType?: PageType;\r\n}\r\n\r\nexport interface OntoConfig {\r\n /**\r\n * The name of your project or site (required)\r\n * Used as the H1 heading in llms.txt\r\n */\r\n name: string;\r\n\r\n /**\r\n * A short summary of your project (required)\r\n * Displayed as a blockquote in llms.txt\r\n * Should contain key information necessary for understanding the rest of the file\r\n */\r\n summary: string;\r\n\r\n /**\r\n * The base URL of your site (e.g., 'https://example.com')\r\n */\r\n baseUrl: string;\r\n\r\n /**\r\n * Optional: Additional sections to include in llms.txt\r\n * Each section can contain any markdown content\r\n */\r\n sections?: {\r\n heading: string;\r\n content: string;\r\n }[];\r\n\r\n /**\r\n * Key routes that AI agents should know about\r\n * These will be formatted as a markdown list in llms.txt\r\n */\r\n routes?: OntoRoute[];\r\n\r\n /**\r\n * Optional: Links to external resources (documentation, API references, etc.)\r\n */\r\n externalLinks?: {\r\n title: string;\r\n url: string;\r\n description?: string;\r\n }[];\r\n\r\n /**\r\n * Optional: Organization information for JSON-LD schemas\r\n */\r\n organization?: {\r\n name: string;\r\n description?: string;\r\n url?: string;\r\n logo?: string;\r\n foundingDate?: string;\r\n };\r\n}\r\n\r\n/**\r\n * Generate llms.txt content from OntoConfig\r\n * Follows the llms.txt specification:\r\n * - H1 with project name\r\n * - Blockquote with summary\r\n * - Additional markdown sections\r\n */\r\nexport function generateLlmsTxt(config: OntoConfig): string {\r\n const lines: string[] = [];\r\n\r\n // H1: Project name (required)\r\n lines.push(`# ${config.name}`);\r\n lines.push('');\r\n\r\n // Blockquote: Summary (required)\r\n lines.push(`> ${config.summary}`);\r\n lines.push('');\r\n\r\n // Key Routes section (if provided)\r\n if (config.routes && config.routes.length > 0) {\r\n lines.push('## Key Routes');\r\n lines.push('');\r\n for (const route of config.routes) {\r\n const fullUrl = `${config.baseUrl}${route.path}`;\r\n lines.push(`- [${route.path}](${fullUrl}): ${route.description}`);\r\n }\r\n lines.push('');\r\n }\r\n\r\n // External Links section (if provided)\r\n if (config.externalLinks && config.externalLinks.length > 0) {\r\n lines.push('## Resources');\r\n lines.push('');\r\n for (const link of config.externalLinks) {\r\n if (link.description) {\r\n lines.push(`- [${link.title}](${link.url}): ${link.description}`);\r\n } else {\r\n lines.push(`- [${link.title}](${link.url})`);\r\n }\r\n }\r\n lines.push('');\r\n }\r\n\r\n // Custom sections (if provided)\r\n if (config.sections && config.sections.length > 0) {\r\n for (const section of config.sections) {\r\n lines.push(`## ${section.heading}`);\r\n lines.push('');\r\n lines.push(section.content);\r\n lines.push('');\r\n }\r\n }\r\n\r\n return lines.join('\\n').trim() + '\\n';\r\n}\r\n"],"mappings":"AAAA,OAAsB,gBAAAA,MAAoB,cCkBnC,IAAMC,EAAmB,CAE5B,CAAE,KAAM,SAAqB,QAAS,SAAY,QAAS,YAAa,EACxE,CAAE,KAAM,eAAoB,QAAS,SAAY,QAAS,YAAa,EACvE,CAAE,KAAM,gBAAoB,QAAS,SAAY,QAAS,YAAa,EACvE,CAAE,KAAM,UAAoB,QAAS,SAAY,QAAS,YAAa,EACvE,CAAE,KAAM,SAAoB,QAAS,SAAY,QAAS,YAAa,EACvE,CAAE,KAAM,MAAoB,QAAS,SAAY,QAAS,YAAa,EAGvE,CAAE,KAAM,wBAA2B,QAAS,SAAU,QAAS,YAAa,EAC5E,CAAE,KAAM,kBAA2B,QAAS,SAAU,QAAS,YAAa,EAC5E,CAAE,KAAM,cAA2B,QAAS,SAAU,QAAS,YAAa,EAG5E,CAAE,KAAM,YAAmB,QAAS,YAAa,QAAS,YAAa,EACvE,CAAE,KAAM,cAAkB,QAAS,YAAa,QAAS,YAAa,EACtE,CAAE,KAAM,eAAkB,QAAS,YAAa,QAAS,YAAa,EACtE,CAAE,KAAM,iBAAkB,QAAS,YAAa,QAAS,YAAa,EACtE,CAAE,KAAM,eAAkB,QAAS,YAAa,QAAS,YAAa,EACtE,CAAE,KAAM,eAAkB,QAAS,YAAa,QAAS,YAAa,EACtE,CAAE,KAAM,SAAkB,QAAS,YAAa,QAAS,YAAa,EACtE,CAAE,KAAM,YAAkB,QAAS,YAAa,QAAS,YAAa,EAGtE,CAAE,KAAM,gBAAmB,QAAS,aAAc,QAAS,YAAa,EACxE,CAAE,KAAM,kBAAmB,QAAS,aAAc,QAAS,YAAa,EACxE,CAAE,KAAM,aAAmB,QAAS,aAAc,QAAS,YAAa,EAGxE,CAAE,KAAM,qBAAwB,QAAS,OAAQ,QAAS,YAAa,EACvE,CAAE,KAAM,uBAAwB,QAAS,OAAQ,QAAS,YAAa,EACvE,CAAE,KAAM,sBAAwB,QAAS,OAAQ,QAAS,YAAa,EACvE,CAAE,KAAM,cAAwB,QAAS,OAAQ,QAAS,YAAa,EAGvE,CAAE,KAAM,aAAc,QAAS,UAAW,QAAS,YAAa,EAChE,CAAE,KAAM,UAAc,QAAS,UAAW,QAAS,YAAa,EAGhE,CAAE,KAAM,YAAa,QAAS,SAAU,QAAS,YAAa,EAG9D,CAAE,KAAM,SAAiB,QAAS,kBAAmB,QAAS,YAAa,EAC3E,CAAE,KAAM,gBAAiB,QAAS,aAAc,QAAS,YAAa,EACtE,CAAE,KAAM,UAAiB,QAAS,UAAe,QAAS,YAAa,EACvE,CAAE,KAAM,QAAiB,QAAS,eAAgB,QAAS,YAAa,EACxE,CAAE,KAAM,aAAiB,QAAS,YAAgB,QAAS,YAAa,EACxE,CAAE,KAAM,oBAAqB,QAAS,QAAY,QAAS,YAAa,EACxE,CAAE,KAAM,SAAiB,QAAS,UAAgB,QAAS,YAAa,EAGxE,CAAE,KAAM,kBAAoB,QAAS,cAAe,QAAS,YAAa,EAC1E,CAAE,KAAM,eAAoB,QAAS,cAAe,QAAS,YAAa,EAC1E,CAAE,KAAM,QAAoB,QAAS,cAAe,QAAS,YAAa,EAC1E,CAAE,KAAM,QAAoB,QAAS,cAAe,QAAS,YAAa,EAC1E,CAAE,KAAM,aAAoB,QAAS,cAAe,QAAS,YAAa,EAC1E,CAAE,KAAM,iBAAoB,QAAS,cAAe,QAAS,YAAa,EAC1E,CAAE,KAAM,OAAoB,QAAS,cAAe,QAAS,YAAa,EAC1E,CAAE,KAAM,OAAoB,QAAS,cAAe,QAAS,YAAa,CAC9E,EAKaC,EAA+BC,EAAyB,EAErE,SAASA,GAA2B,CAChC,OAAOF,EAAQ,IAAIG,GAAOA,EAAI,IAAI,CACtC,CAOO,SAASC,EAASC,EAA6C,CAClE,GAAI,CAACA,EAAW,OAChB,IAAMC,EAAUD,EAAU,YAAY,EAGhCE,EAAUP,EAAQ,OAAOG,GAC3BG,EAAQ,SAASH,EAAI,KAAK,YAAY,CAAC,CAC3C,EAEA,GAAII,EAAQ,SAAW,EACvB,OAAIA,EAAQ,SAAW,EAAUA,EAAQ,CAAC,EAGnCA,EAAQ,OAAO,CAACC,EAASC,IAC5BA,EAAQ,KAAK,OAASD,EAAQ,KAAK,OAASC,EAAUD,CAC1D,CACJ,CCvBO,SAASE,EAAgBC,EAA4B,CAC1D,IAAMC,EAAkB,CAAC,EAWzB,GARAA,EAAM,KAAK,KAAKD,EAAO,IAAI,EAAE,EAC7BC,EAAM,KAAK,EAAE,EAGbA,EAAM,KAAK,KAAKD,EAAO,OAAO,EAAE,EAChCC,EAAM,KAAK,EAAE,EAGTD,EAAO,QAAUA,EAAO,OAAO,OAAS,EAAG,CAC7CC,EAAM,KAAK,eAAe,EAC1BA,EAAM,KAAK,EAAE,EACb,QAAWC,KAASF,EAAO,OAAQ,CACjC,IAAMG,EAAU,GAAGH,EAAO,OAAO,GAAGE,EAAM,IAAI,GAC9CD,EAAM,KAAK,MAAMC,EAAM,IAAI,KAAKC,CAAO,MAAMD,EAAM,WAAW,EAAE,CAClE,CACAD,EAAM,KAAK,EAAE,CACf,CAGA,GAAID,EAAO,eAAiBA,EAAO,cAAc,OAAS,EAAG,CAC3DC,EAAM,KAAK,cAAc,EACzBA,EAAM,KAAK,EAAE,EACb,QAAWG,KAAQJ,EAAO,cACpBI,EAAK,YACPH,EAAM,KAAK,MAAMG,EAAK,KAAK,KAAKA,EAAK,GAAG,MAAMA,EAAK,WAAW,EAAE,EAEhEH,EAAM,KAAK,MAAMG,EAAK,KAAK,KAAKA,EAAK,GAAG,GAAG,EAG/CH,EAAM,KAAK,EAAE,CACf,CAGA,GAAID,EAAO,UAAYA,EAAO,SAAS,OAAS,EAC9C,QAAWK,KAAWL,EAAO,SAC3BC,EAAM,KAAK,MAAMI,EAAQ,OAAO,EAAE,EAClCJ,EAAM,KAAK,EAAE,EACbA,EAAM,KAAKI,EAAQ,OAAO,EAC1BJ,EAAM,KAAK,EAAE,EAIjB,OAAOA,EAAM,KAAK;AAAA,CAAI,EAAE,KAAK,EAAI;AAAA,CACnC,CFlIA,eAAsBK,EAAeC,EAAcC,EAAqB,CACpE,IAAMC,EAAYF,EAAQ,QAAQ,IAAI,YAAY,EAC5CG,EAAMH,EAAQ,QAAQ,MAAM,EAC5BI,EAAUC,EAASH,CAAS,EAE5BI,EAASN,EAAQ,QAAQ,IAAI,QAAQ,GAAK,GAC1CO,EAAgBP,EAAQ,QAAQ,aAAa,IAAI,MAAM,EAEvDQ,EAAU,CAAC,CAACJ,EACZK,EAAsBH,EAAO,SAAS,eAAe,GAAKC,EAGhE,GAAIC,GAAWC,EAAqB,CAEhC,GAAIN,EAAI,SAAS,WAAW,QAAQ,EAChC,OAAOO,EAAa,KAAK,EAI7B,GAAIP,EAAI,WAAa,YACjB,GAAI,CACA,GAAIF,EAAQ,CACR,IAAMU,EAAiBC,EAAgBX,CAAM,EACvCY,EAAW,IAAIH,EAAaC,EAAgB,CAC9C,QAAS,CACL,eAAgB,4BAChB,gBAAiB,mEACrB,CACJ,CAAC,EACD,OAAIP,GAASS,EAAS,QAAQ,IAAI,aAAc,GAAGT,EAAQ,IAAI,KAAKA,EAAQ,OAAO,GAAG,EACtFS,EAAS,QAAQ,IAAI,eAAgBX,GAAa,OAAO,EAClDW,CACX,CACJ,OAASC,EAAO,CACZ,QAAQ,MAAM,sCAAuCA,CAAK,CAC9D,CAIJ,GAAIX,EAAI,SAAS,SAAS,GAAG,EACzB,OAAOO,EAAa,KAAK,EAI7B,IAAIK,EAAcZ,EAAI,UAClBY,IAAgB,KAAOA,IAAgB,MAAIA,EAAc,UACzDA,EAAY,SAAS,GAAG,GAAKA,IAAgB,MAAKA,EAAcA,EAAY,MAAM,EAAG,EAAE,GAG3F,IAAMC,EAAe,QAAQ,IAAI,aAC3BC,EAAgB,QAAQ,IAAI,oBAAsB,4BAEpDD,GAEA,MAAM,GAAGC,CAAa,aAAc,CAChC,OAAQ,OACR,QAAS,CAAE,aAAcD,EAAc,eAAgB,kBAAmB,EAC1E,KAAM,KAAK,UAAU,CAAE,MAAOb,EAAI,SAAU,UAAAD,EAAW,IAAKE,GAAS,KAAM,QAASA,GAAS,OAAQ,CAAC,CAC1G,CAAC,EAAE,MAAM,IAAM,CAAC,CAAC,EAIrBD,EAAI,SAAW,SAASY,CAAW,MACnC,IAAMF,EAAWH,EAAa,QAAQP,CAAG,EAGzC,OAAAU,EAAS,QAAQ,IAAI,eAAgB,8BAA8B,EACnEA,EAAS,QAAQ,IAAI,gBAAiB,mEAAmE,EACzGA,EAAS,QAAQ,IAAI,OAAQ,oBAAoB,EACjDA,EAAS,QAAQ,IAAI,eAAgBX,GAAa,OAAO,EAErDE,IACAS,EAAS,QAAQ,IAAI,aAAc,GAAGT,EAAQ,IAAI,KAAKA,EAAQ,OAAO,GAAG,EACzES,EAAS,QAAQ,IAAI,iBAAkB,MAAM,GAG7CN,GAAeM,EAAS,QAAQ,IAAI,eAAgB,MAAM,EAEvDA,CACX,CAGA,IAAMA,EAAWH,EAAa,KAAK,EAInC,OAAAG,EAAS,QAAQ,IAAI,OAAQ,oBAAoB,EACjDA,EAAS,QAAQ,IAAI,eAAgBX,GAAa,OAAO,EAElDW,CACX","names":["NextResponse","AI_BOTS","AI_BOT_USER_AGENTS","AI_BOT_USER_AGENTS_CACHE","bot","matchBot","userAgent","lowerUA","matches","longest","current","generateLlmsTxt","config","lines","route","fullUrl","link","section","ontoMiddleware","request","config","userAgent","url","matched","matchBot","accept","hasDebugParam","isAiBot","isMarkdownRequested","NextResponse","llmsTxtContent","generateLlmsTxt","response","error","payloadPath","ONTO_API_KEY","DASHBOARD_URL"]}
|
|
1
|
+
{"version":3,"sources":["../src/middleware.ts","../src/bots.ts","../src/config.ts"],"sourcesContent":["import { NextRequest, NextResponse } from 'next/server';\r\nimport { matchBot } from './bots';\r\nimport { generateLlmsTxt, OntoConfig } from './config';\r\n\r\nexport async function ontoMiddleware(request: any, config?: OntoConfig) {\r\n const userAgent = request.headers.get('user-agent');\r\n const url = request.nextUrl.clone();\r\n const matched = matchBot(userAgent);\r\n\r\n const accept = request.headers.get('accept') || '';\r\n const hasDebugParam = request.nextUrl.searchParams.has('onto');\r\n\r\n const isAiBot = !!matched;\r\n const isMarkdownRequested = accept.includes('text/markdown') || hasDebugParam;\r\n\r\n // Common logic for bot/markdown negotiation\r\n if (isAiBot || isMarkdownRequested) {\r\n // Ignore internal next.js requests\r\n if (url.pathname.startsWith('/_next')) {\r\n return NextResponse.next();\r\n }\r\n\r\n // --- llms.txt Auto-Discovery ---\r\n if (url.pathname === '/llms.txt') {\r\n try {\r\n if (config) {\r\n const llmsTxtContent = generateLlmsTxt(config);\r\n const response = new NextResponse(llmsTxtContent, {\r\n headers: {\r\n 'Content-Type': 'text/plain; charset=utf-8',\r\n 'Cache-Control': 'public, max-age=3600, s-maxage=3600, stale-while-revalidate=86400',\r\n }\r\n });\r\n if (matched) response.headers.set('X-Onto-Bot', `${matched.name} (${matched.company})`);\r\n response.headers.set('X-Onto-Trace', userAgent || 'no-ua');\r\n return response;\r\n }\r\n } catch (error) {\r\n console.error('[Onto] Failed to generate llms.txt:', error);\r\n }\r\n }\r\n\r\n // Skip other static assets with dots\r\n if (url.pathname.includes('.')) {\r\n return NextResponse.next();\r\n }\r\n\r\n // Determine the corresponding payload path\r\n let payloadPath = url.pathname;\r\n if (payloadPath === '/' || payloadPath === '') payloadPath = '/index';\r\n if (payloadPath.endsWith('/') && payloadPath !== '/') payloadPath = payloadPath.slice(0, -1);\r\n\r\n // --- Onto Control Plane Integration (Premium) ---\r\n const ONTO_API_KEY = process.env.ONTO_API_KEY;\r\n const DASHBOARD_URL = process.env.ONTO_DASHBOARD_URL || 'https://app.buildonto.dev';\r\n\r\n if (ONTO_API_KEY) {\r\n // Logic for tracking and injection ... (fire-and-forget tracking)\r\n fetch(`${DASHBOARD_URL}/api/track`, {\r\n method: 'POST',\r\n headers: { 'x-onto-key': ONTO_API_KEY, 'Content-Type': 'application/json' },\r\n body: JSON.stringify({ route: url.pathname, userAgent, bot: matched?.name, company: matched?.company })\r\n }).catch(() => {});\r\n }\r\n\r\n // Rewrite to semantic payload\r\n url.pathname = `/.onto${payloadPath}.md`;\r\n const response = NextResponse.rewrite(url);\r\n \r\n // Apply headers\r\n response.headers.set('Content-Type', 'text/markdown; charset=utf-8');\r\n response.headers.set('Cache-Control', 'public, max-age=3600, s-maxage=3600, stale-while-revalidate=86400');\r\n response.headers.set('Vary', 'User-Agent, Accept');\r\n response.headers.set('X-Onto-Trace', userAgent || 'no-ua');\r\n \r\n if (matched) {\r\n response.headers.set('X-Onto-Bot', `${matched.name} (${matched.company})`);\r\n response.headers.set('X-Onto-Matched', 'true');\r\n }\r\n \r\n if (hasDebugParam) response.headers.set('X-Onto-Debug', 'true');\r\n\r\n return response;\r\n }\r\n\r\n // Default response for non-bots\r\n const response = NextResponse.next();\r\n \r\n // Add identify headers to EVERY response for clinical debugging\r\n response.headers.set('Vary', 'User-Agent, Accept');\r\n response.headers.set('X-Onto-Trace', userAgent || 'no-ua');\r\n \r\n if (matched) {\r\n response.headers.set('X-Onto-Matched-Bot', matched.name);\r\n response.headers.set('X-Onto-Identified', 'true');\r\n } else {\r\n response.headers.set('X-Onto-Identified', 'false');\r\n }\r\n \r\n return response;\r\n}\r\n\r\n// Re-export the bot registry for consumers who want to extend or inspect it\r\nexport { AI_BOT_USER_AGENTS, matchBot } from './bots';\r\nexport type { AiBot } from './bots';\r\n\r\n\r\n","/**\n * Comprehensive registry of AI bot user-agent strings.\n * The middleware uses this list to detect AI crawlers and serve optimized markdown.\n */\n\nexport interface AiBot {\n /** The user-agent substring to match against */\n name: string;\n /** The company operating this bot */\n company: string;\n /** ISO date when this bot was added or last verified */\n addedAt?: string;\n}\n\n/**\n * Structured registry of all known AI bots, grouped by company.\n * Useful for analytics and the Control Plane dashboard.\n */\nexport const AI_BOTS: AiBot[] = [\n // OpenAI\n { name: 'GPTBot', company: 'OpenAI', addedAt: '2025-01-01' },\n { name: 'ChatGPT-User', company: 'OpenAI', addedAt: '2025-01-01' },\n { name: 'OAI-SearchBot', company: 'OpenAI', addedAt: '2025-01-01' },\n { name: 'ChatGPT', company: 'OpenAI', addedAt: '2025-03-25' },\n { name: 'OpenAI', company: 'OpenAI', addedAt: '2025-03-25' },\n { name: 'GPT', company: 'OpenAI', addedAt: '2025-03-25' },\n\n // Google (SEO Safety: Googlebot proper is EXCLUDED)\n { name: 'Google-CloudVertexBot', company: 'Google', addedAt: '2025-01-01' },\n { name: 'Google-Extended', company: 'Google', addedAt: '2025-01-01' },\n { name: 'GoogleOther', company: 'Google', addedAt: '2025-01-01' },\n\n // Anthropic\n { name: 'ClaudeBot', company: 'Anthropic', addedAt: '2025-01-01' },\n { name: 'Claude-User', company: 'Anthropic', addedAt: '2025-01-01' },\n { name: 'claude-fetch', company: 'Anthropic', addedAt: '2025-03-25' },\n { name: 'AnthropicFetch', company: 'Anthropic', addedAt: '2025-03-25' },\n { name: 'Claude-Fetch', company: 'Anthropic', addedAt: '2025-03-25' },\n { name: 'anthropic-ai', company: 'Anthropic', addedAt: '2025-01-01' },\n { name: 'Claude', company: 'Anthropic', addedAt: '2025-03-25' },\n { name: 'Anthropic', company: 'Anthropic', addedAt: '2025-03-25' },\n\n // Perplexity\n { name: 'PerplexityBot', company: 'Perplexity', addedAt: '2025-01-01' },\n { name: 'Perplexity-User', company: 'Perplexity', addedAt: '2025-01-01' },\n { name: 'Perplexity', company: 'Perplexity', addedAt: '2025-03-25' },\n\n // Meta\n { name: 'Meta-ExternalAgent', company: 'Meta', addedAt: '2025-01-01' },\n { name: 'Meta-ExternalFetcher', company: 'Meta', addedAt: '2025-01-01' },\n { name: 'facebookexternalhit', company: 'Meta', addedAt: '2025-03-25' },\n { name: 'FacebookBot', company: 'Meta', addedAt: '2025-01-01' },\n\n // Mistral\n { name: 'MistralBot', company: 'Mistral', addedAt: '2025-03-25' },\n { name: 'Mistral', company: 'Mistral', addedAt: '2025-03-25' },\n\n // Amazon\n { name: 'Amazonbot', company: 'Amazon', addedAt: '2025-03-25' },\n\n // Others\n { name: 'AI2Bot', company: 'Allen Institute', addedAt: '2025-03-25' },\n { name: 'DuckAssistBot', company: 'DuckDuckGo', addedAt: '2025-03-25' },\n { name: 'Diffbot', company: 'Diffbot', addedAt: '2025-03-25' },\n { name: 'CCBot', company: 'Common Crawl', addedAt: '2025-01-01' },\n { name: 'Bytespider', company: 'ByteDance', addedAt: '2025-01-01' },\n { name: 'Applebot-Extended', company: 'Apple', addedAt: '2025-01-01' },\n { name: 'YouBot', company: 'You.com', addedAt: '2025-01-01' },\n\n // Generic AI / Scraping Libraries (Last Resort)\n { name: 'python-requests', company: 'Generic Bot', addedAt: '2025-03-25' },\n { name: 'python-httpx', company: 'Generic Bot', addedAt: '2025-03-25' },\n { name: 'httpx', company: 'Generic Bot', addedAt: '2025-03-25' },\n { name: 'axios', company: 'Generic Bot', addedAt: '2025-03-25' },\n { name: 'node-fetch', company: 'Generic Bot', addedAt: '2025-03-25' },\n { name: 'Go-http-client', company: 'Generic Bot', addedAt: '2025-03-25' },\n { name: 'Wget', company: 'Generic Bot', addedAt: '2025-03-25' },\n { name: 'Curl', company: 'Generic Bot', addedAt: '2025-03-25' },\n];\n\n/**\n * Flat list of user-agent substrings for fast matching in the middleware.\n */\nexport const AI_BOT_USER_AGENTS: string[] = AI_BOT_USER_AGENTS_CACHE();\n\nfunction AI_BOT_USER_AGENTS_CACHE() {\n return AI_BOTS.map(bot => bot.name);\n}\n\n/**\n * Given a raw user-agent string, returns the matched AiBot entry or undefined.\n * Uses a \"Longest Match\" strategy to ensure maximum specificity.\n * Comparison is case-insensitive.\n */\nexport function matchBot(userAgent: string | null): AiBot | undefined {\n if (!userAgent) return undefined;\n const lowerUA = userAgent.toLowerCase();\n \n // Find all matches\n const matches = AI_BOTS.filter(bot => \n lowerUA.includes(bot.name.toLowerCase())\n );\n\n if (matches.length === 0) return undefined;\n if (matches.length === 1) return matches[0];\n\n // Pick the longest match for maximum specificity (e.g. 'ChatGPT-User' vs 'GPT')\n return matches.reduce((longest, current) => \n current.name.length > longest.name.length ? current : longest\n );\n}\n","/**\r\n * Configuration schema for onto.config.ts\r\n * Used to dynamically generate llms.txt and other AI discovery files\r\n */\r\n\r\nexport type PageType = 'scoring' | 'about' | 'default';\r\n\r\nexport interface OntoRoute {\r\n /**\r\n * The URL path (e.g., '/docs', '/api/reference')\r\n */\r\n path: string;\r\n /**\r\n * Description of what this route contains\r\n */\r\n description: string;\r\n /**\r\n * Optional: Page type for automatic JSON-LD schema injection\r\n * - 'scoring': Injects Methodology schema with AIO scoring weights (40/35/25)\r\n * - 'about': Injects Organization/AboutPage schema\r\n * - 'default': No automatic schema injection\r\n */\r\n pageType?: PageType;\r\n}\r\n\r\nexport interface OntoConfig {\r\n /**\r\n * The name of your project or site (required)\r\n * Used as the H1 heading in llms.txt\r\n */\r\n name: string;\r\n\r\n /**\r\n * A short summary of your project (required)\r\n * Displayed as a blockquote in llms.txt\r\n * Should contain key information necessary for understanding the rest of the file\r\n */\r\n summary: string;\r\n\r\n /**\r\n * The base URL of your site (e.g., 'https://example.com')\r\n */\r\n baseUrl: string;\r\n\r\n /**\r\n * Optional: Additional sections to include in llms.txt\r\n * Each section can contain any markdown content\r\n */\r\n sections?: {\r\n heading: string;\r\n content: string;\r\n }[];\r\n\r\n /**\r\n * Key routes that AI agents should know about\r\n * These will be formatted as a markdown list in llms.txt\r\n */\r\n routes?: OntoRoute[];\r\n\r\n /**\r\n * Optional: Links to external resources (documentation, API references, etc.)\r\n */\r\n externalLinks?: {\r\n title: string;\r\n url: string;\r\n description?: string;\r\n }[];\r\n\r\n /**\r\n * Optional: Organization information for JSON-LD schemas\r\n */\r\n organization?: {\r\n name: string;\r\n description?: string;\r\n url?: string;\r\n logo?: string;\r\n foundingDate?: string;\r\n };\r\n}\r\n\r\n/**\r\n * Generate llms.txt content from OntoConfig\r\n * Follows the llms.txt specification:\r\n * - H1 with project name\r\n * - Blockquote with summary\r\n * - Additional markdown sections\r\n */\r\nexport function generateLlmsTxt(config: OntoConfig): string {\r\n const lines: string[] = [];\r\n\r\n // H1: Project name (required)\r\n lines.push(`# ${config.name}`);\r\n lines.push('');\r\n\r\n // Blockquote: Summary (required)\r\n lines.push(`> ${config.summary}`);\r\n lines.push('');\r\n\r\n // Key Routes section (if provided)\r\n if (config.routes && config.routes.length > 0) {\r\n lines.push('## Key Routes');\r\n lines.push('');\r\n for (const route of config.routes) {\r\n const fullUrl = `${config.baseUrl}${route.path}`;\r\n lines.push(`- [${route.path}](${fullUrl}): ${route.description}`);\r\n }\r\n lines.push('');\r\n }\r\n\r\n // External Links section (if provided)\r\n if (config.externalLinks && config.externalLinks.length > 0) {\r\n lines.push('## Resources');\r\n lines.push('');\r\n for (const link of config.externalLinks) {\r\n if (link.description) {\r\n lines.push(`- [${link.title}](${link.url}): ${link.description}`);\r\n } else {\r\n lines.push(`- [${link.title}](${link.url})`);\r\n }\r\n }\r\n lines.push('');\r\n }\r\n\r\n // Custom sections (if provided)\r\n if (config.sections && config.sections.length > 0) {\r\n for (const section of config.sections) {\r\n lines.push(`## ${section.heading}`);\r\n lines.push('');\r\n lines.push(section.content);\r\n lines.push('');\r\n }\r\n }\r\n\r\n return lines.join('\\n').trim() + '\\n';\r\n}\r\n"],"mappings":"AAAA,OAAsB,gBAAAA,MAAoB,cCkBnC,IAAMC,EAAmB,CAE5B,CAAE,KAAM,SAAqB,QAAS,SAAY,QAAS,YAAa,EACxE,CAAE,KAAM,eAAoB,QAAS,SAAY,QAAS,YAAa,EACvE,CAAE,KAAM,gBAAoB,QAAS,SAAY,QAAS,YAAa,EACvE,CAAE,KAAM,UAAoB,QAAS,SAAY,QAAS,YAAa,EACvE,CAAE,KAAM,SAAoB,QAAS,SAAY,QAAS,YAAa,EACvE,CAAE,KAAM,MAAoB,QAAS,SAAY,QAAS,YAAa,EAGvE,CAAE,KAAM,wBAA2B,QAAS,SAAU,QAAS,YAAa,EAC5E,CAAE,KAAM,kBAA2B,QAAS,SAAU,QAAS,YAAa,EAC5E,CAAE,KAAM,cAA2B,QAAS,SAAU,QAAS,YAAa,EAG5E,CAAE,KAAM,YAAmB,QAAS,YAAa,QAAS,YAAa,EACvE,CAAE,KAAM,cAAkB,QAAS,YAAa,QAAS,YAAa,EACtE,CAAE,KAAM,eAAkB,QAAS,YAAa,QAAS,YAAa,EACtE,CAAE,KAAM,iBAAkB,QAAS,YAAa,QAAS,YAAa,EACtE,CAAE,KAAM,eAAkB,QAAS,YAAa,QAAS,YAAa,EACtE,CAAE,KAAM,eAAkB,QAAS,YAAa,QAAS,YAAa,EACtE,CAAE,KAAM,SAAkB,QAAS,YAAa,QAAS,YAAa,EACtE,CAAE,KAAM,YAAkB,QAAS,YAAa,QAAS,YAAa,EAGtE,CAAE,KAAM,gBAAmB,QAAS,aAAc,QAAS,YAAa,EACxE,CAAE,KAAM,kBAAmB,QAAS,aAAc,QAAS,YAAa,EACxE,CAAE,KAAM,aAAmB,QAAS,aAAc,QAAS,YAAa,EAGxE,CAAE,KAAM,qBAAwB,QAAS,OAAQ,QAAS,YAAa,EACvE,CAAE,KAAM,uBAAwB,QAAS,OAAQ,QAAS,YAAa,EACvE,CAAE,KAAM,sBAAwB,QAAS,OAAQ,QAAS,YAAa,EACvE,CAAE,KAAM,cAAwB,QAAS,OAAQ,QAAS,YAAa,EAGvE,CAAE,KAAM,aAAc,QAAS,UAAW,QAAS,YAAa,EAChE,CAAE,KAAM,UAAc,QAAS,UAAW,QAAS,YAAa,EAGhE,CAAE,KAAM,YAAa,QAAS,SAAU,QAAS,YAAa,EAG9D,CAAE,KAAM,SAAiB,QAAS,kBAAmB,QAAS,YAAa,EAC3E,CAAE,KAAM,gBAAiB,QAAS,aAAc,QAAS,YAAa,EACtE,CAAE,KAAM,UAAiB,QAAS,UAAe,QAAS,YAAa,EACvE,CAAE,KAAM,QAAiB,QAAS,eAAgB,QAAS,YAAa,EACxE,CAAE,KAAM,aAAiB,QAAS,YAAgB,QAAS,YAAa,EACxE,CAAE,KAAM,oBAAqB,QAAS,QAAY,QAAS,YAAa,EACxE,CAAE,KAAM,SAAiB,QAAS,UAAgB,QAAS,YAAa,EAGxE,CAAE,KAAM,kBAAoB,QAAS,cAAe,QAAS,YAAa,EAC1E,CAAE,KAAM,eAAoB,QAAS,cAAe,QAAS,YAAa,EAC1E,CAAE,KAAM,QAAoB,QAAS,cAAe,QAAS,YAAa,EAC1E,CAAE,KAAM,QAAoB,QAAS,cAAe,QAAS,YAAa,EAC1E,CAAE,KAAM,aAAoB,QAAS,cAAe,QAAS,YAAa,EAC1E,CAAE,KAAM,iBAAoB,QAAS,cAAe,QAAS,YAAa,EAC1E,CAAE,KAAM,OAAoB,QAAS,cAAe,QAAS,YAAa,EAC1E,CAAE,KAAM,OAAoB,QAAS,cAAe,QAAS,YAAa,CAC9E,EAKaC,EAA+BC,EAAyB,EAErE,SAASA,GAA2B,CAChC,OAAOF,EAAQ,IAAIG,GAAOA,EAAI,IAAI,CACtC,CAOO,SAASC,EAASC,EAA6C,CAClE,GAAI,CAACA,EAAW,OAChB,IAAMC,EAAUD,EAAU,YAAY,EAGhCE,EAAUP,EAAQ,OAAOG,GAC3BG,EAAQ,SAASH,EAAI,KAAK,YAAY,CAAC,CAC3C,EAEA,GAAII,EAAQ,SAAW,EACvB,OAAIA,EAAQ,SAAW,EAAUA,EAAQ,CAAC,EAGnCA,EAAQ,OAAO,CAACC,EAASC,IAC5BA,EAAQ,KAAK,OAASD,EAAQ,KAAK,OAASC,EAAUD,CAC1D,CACJ,CCvBO,SAASE,EAAgBC,EAA4B,CAC1D,IAAMC,EAAkB,CAAC,EAWzB,GARAA,EAAM,KAAK,KAAKD,EAAO,IAAI,EAAE,EAC7BC,EAAM,KAAK,EAAE,EAGbA,EAAM,KAAK,KAAKD,EAAO,OAAO,EAAE,EAChCC,EAAM,KAAK,EAAE,EAGTD,EAAO,QAAUA,EAAO,OAAO,OAAS,EAAG,CAC7CC,EAAM,KAAK,eAAe,EAC1BA,EAAM,KAAK,EAAE,EACb,QAAWC,KAASF,EAAO,OAAQ,CACjC,IAAMG,EAAU,GAAGH,EAAO,OAAO,GAAGE,EAAM,IAAI,GAC9CD,EAAM,KAAK,MAAMC,EAAM,IAAI,KAAKC,CAAO,MAAMD,EAAM,WAAW,EAAE,CAClE,CACAD,EAAM,KAAK,EAAE,CACf,CAGA,GAAID,EAAO,eAAiBA,EAAO,cAAc,OAAS,EAAG,CAC3DC,EAAM,KAAK,cAAc,EACzBA,EAAM,KAAK,EAAE,EACb,QAAWG,KAAQJ,EAAO,cACpBI,EAAK,YACPH,EAAM,KAAK,MAAMG,EAAK,KAAK,KAAKA,EAAK,GAAG,MAAMA,EAAK,WAAW,EAAE,EAEhEH,EAAM,KAAK,MAAMG,EAAK,KAAK,KAAKA,EAAK,GAAG,GAAG,EAG/CH,EAAM,KAAK,EAAE,CACf,CAGA,GAAID,EAAO,UAAYA,EAAO,SAAS,OAAS,EAC9C,QAAWK,KAAWL,EAAO,SAC3BC,EAAM,KAAK,MAAMI,EAAQ,OAAO,EAAE,EAClCJ,EAAM,KAAK,EAAE,EACbA,EAAM,KAAKI,EAAQ,OAAO,EAC1BJ,EAAM,KAAK,EAAE,EAIjB,OAAOA,EAAM,KAAK;AAAA,CAAI,EAAE,KAAK,EAAI;AAAA,CACnC,CFlIA,eAAsBK,EAAeC,EAAcC,EAAqB,CACpE,IAAMC,EAAYF,EAAQ,QAAQ,IAAI,YAAY,EAC5CG,EAAMH,EAAQ,QAAQ,MAAM,EAC5BI,EAAUC,EAASH,CAAS,EAE5BI,EAASN,EAAQ,QAAQ,IAAI,QAAQ,GAAK,GAC1CO,EAAgBP,EAAQ,QAAQ,aAAa,IAAI,MAAM,EAEvDQ,EAAU,CAAC,CAACJ,EACZK,EAAsBH,EAAO,SAAS,eAAe,GAAKC,EAGhE,GAAIC,GAAWC,EAAqB,CAEhC,GAAIN,EAAI,SAAS,WAAW,QAAQ,EAChC,OAAOO,EAAa,KAAK,EAI7B,GAAIP,EAAI,WAAa,YACjB,GAAI,CACA,GAAIF,EAAQ,CACR,IAAMU,EAAiBC,EAAgBX,CAAM,EACvCY,EAAW,IAAIH,EAAaC,EAAgB,CAC9C,QAAS,CACL,eAAgB,4BAChB,gBAAiB,mEACrB,CACJ,CAAC,EACD,OAAIP,GAASS,EAAS,QAAQ,IAAI,aAAc,GAAGT,EAAQ,IAAI,KAAKA,EAAQ,OAAO,GAAG,EACtFS,EAAS,QAAQ,IAAI,eAAgBX,GAAa,OAAO,EAClDW,CACX,CACJ,OAASC,EAAO,CACZ,QAAQ,MAAM,sCAAuCA,CAAK,CAC9D,CAIJ,GAAIX,EAAI,SAAS,SAAS,GAAG,EACzB,OAAOO,EAAa,KAAK,EAI7B,IAAIK,EAAcZ,EAAI,UAClBY,IAAgB,KAAOA,IAAgB,MAAIA,EAAc,UACzDA,EAAY,SAAS,GAAG,GAAKA,IAAgB,MAAKA,EAAcA,EAAY,MAAM,EAAG,EAAE,GAG3F,IAAMC,EAAe,QAAQ,IAAI,aAC3BC,EAAgB,QAAQ,IAAI,oBAAsB,4BAEpDD,GAEA,MAAM,GAAGC,CAAa,aAAc,CAChC,OAAQ,OACR,QAAS,CAAE,aAAcD,EAAc,eAAgB,kBAAmB,EAC1E,KAAM,KAAK,UAAU,CAAE,MAAOb,EAAI,SAAU,UAAAD,EAAW,IAAKE,GAAS,KAAM,QAASA,GAAS,OAAQ,CAAC,CAC1G,CAAC,EAAE,MAAM,IAAM,CAAC,CAAC,EAIrBD,EAAI,SAAW,SAASY,CAAW,MACnC,IAAMF,EAAWH,EAAa,QAAQP,CAAG,EAGzC,OAAAU,EAAS,QAAQ,IAAI,eAAgB,8BAA8B,EACnEA,EAAS,QAAQ,IAAI,gBAAiB,mEAAmE,EACzGA,EAAS,QAAQ,IAAI,OAAQ,oBAAoB,EACjDA,EAAS,QAAQ,IAAI,eAAgBX,GAAa,OAAO,EAErDE,IACAS,EAAS,QAAQ,IAAI,aAAc,GAAGT,EAAQ,IAAI,KAAKA,EAAQ,OAAO,GAAG,EACzES,EAAS,QAAQ,IAAI,iBAAkB,MAAM,GAG7CN,GAAeM,EAAS,QAAQ,IAAI,eAAgB,MAAM,EAEvDA,CACX,CAGA,IAAMA,EAAWH,EAAa,KAAK,EAGnC,OAAAG,EAAS,QAAQ,IAAI,OAAQ,oBAAoB,EACjDA,EAAS,QAAQ,IAAI,eAAgBX,GAAa,OAAO,EAErDE,GACAS,EAAS,QAAQ,IAAI,qBAAsBT,EAAQ,IAAI,EACvDS,EAAS,QAAQ,IAAI,oBAAqB,MAAM,GAEhDA,EAAS,QAAQ,IAAI,oBAAqB,OAAO,EAG9CA,CACX","names":["NextResponse","AI_BOTS","AI_BOT_USER_AGENTS","AI_BOT_USER_AGENTS_CACHE","bot","matchBot","userAgent","lowerUA","matches","longest","current","generateLlmsTxt","config","lines","route","fullUrl","link","section","ontoMiddleware","request","config","userAgent","url","matched","matchBot","accept","hasDebugParam","isAiBot","isMarkdownRequested","NextResponse","llmsTxtContent","generateLlmsTxt","response","error","payloadPath","ONTO_API_KEY","DASHBOARD_URL"]}
|
package/package.json
CHANGED
package/src/middleware.ts
CHANGED
|
@@ -86,11 +86,17 @@ export async function ontoMiddleware(request: any, config?: OntoConfig) {
|
|
|
86
86
|
// Default response for non-bots
|
|
87
87
|
const response = NextResponse.next();
|
|
88
88
|
|
|
89
|
-
//
|
|
90
|
-
// This ensures bots get the rewrite and humans get the HTML
|
|
89
|
+
// Add identify headers to EVERY response for clinical debugging
|
|
91
90
|
response.headers.set('Vary', 'User-Agent, Accept');
|
|
92
91
|
response.headers.set('X-Onto-Trace', userAgent || 'no-ua');
|
|
93
92
|
|
|
93
|
+
if (matched) {
|
|
94
|
+
response.headers.set('X-Onto-Matched-Bot', matched.name);
|
|
95
|
+
response.headers.set('X-Onto-Identified', 'true');
|
|
96
|
+
} else {
|
|
97
|
+
response.headers.set('X-Onto-Identified', 'false');
|
|
98
|
+
}
|
|
99
|
+
|
|
94
100
|
return response;
|
|
95
101
|
}
|
|
96
102
|
|
package/dist/OntoHead.d.mts
DELETED
|
@@ -1,27 +0,0 @@
|
|
|
1
|
-
import * as react_jsx_runtime from 'react/jsx-runtime';
|
|
2
|
-
|
|
3
|
-
/**
|
|
4
|
-
* OntoHead — Auto-Discovery component for AI agents.
|
|
5
|
-
*
|
|
6
|
-
* Injects `<link rel="alternate">` tags into the page `<head>` so AI crawlers
|
|
7
|
-
* can discover the optimized markdown endpoint for the current route.
|
|
8
|
-
*
|
|
9
|
-
* Usage in a Next.js App Router layout:
|
|
10
|
-
* ```tsx
|
|
11
|
-
* import { OntoHead } from '@ontosdk/next/components';
|
|
12
|
-
*
|
|
13
|
-
* export default function RootLayout({ children }) {
|
|
14
|
-
* return (
|
|
15
|
-
* <html>
|
|
16
|
-
* <head>
|
|
17
|
-
* <OntoHead />
|
|
18
|
-
* </head>
|
|
19
|
-
* <body>{children}</body>
|
|
20
|
-
* </html>
|
|
21
|
-
* );
|
|
22
|
-
* }
|
|
23
|
-
* ```
|
|
24
|
-
*/
|
|
25
|
-
declare function OntoHead(): react_jsx_runtime.JSX.Element;
|
|
26
|
-
|
|
27
|
-
export { OntoHead };
|
package/dist/OntoHead.d.ts
DELETED
|
@@ -1,27 +0,0 @@
|
|
|
1
|
-
import * as react_jsx_runtime from 'react/jsx-runtime';
|
|
2
|
-
|
|
3
|
-
/**
|
|
4
|
-
* OntoHead — Auto-Discovery component for AI agents.
|
|
5
|
-
*
|
|
6
|
-
* Injects `<link rel="alternate">` tags into the page `<head>` so AI crawlers
|
|
7
|
-
* can discover the optimized markdown endpoint for the current route.
|
|
8
|
-
*
|
|
9
|
-
* Usage in a Next.js App Router layout:
|
|
10
|
-
* ```tsx
|
|
11
|
-
* import { OntoHead } from '@ontosdk/next/components';
|
|
12
|
-
*
|
|
13
|
-
* export default function RootLayout({ children }) {
|
|
14
|
-
* return (
|
|
15
|
-
* <html>
|
|
16
|
-
* <head>
|
|
17
|
-
* <OntoHead />
|
|
18
|
-
* </head>
|
|
19
|
-
* <body>{children}</body>
|
|
20
|
-
* </html>
|
|
21
|
-
* );
|
|
22
|
-
* }
|
|
23
|
-
* ```
|
|
24
|
-
*/
|
|
25
|
-
declare function OntoHead(): react_jsx_runtime.JSX.Element;
|
|
26
|
-
|
|
27
|
-
export { OntoHead };
|
package/dist/OntoProvider.d.mts
DELETED
|
@@ -1,52 +0,0 @@
|
|
|
1
|
-
import * as react_jsx_runtime from 'react/jsx-runtime';
|
|
2
|
-
import { ReactNode } from 'react';
|
|
3
|
-
import { OntoConfig } from './config.mjs';
|
|
4
|
-
|
|
5
|
-
interface OntoProviderProps {
|
|
6
|
-
/**
|
|
7
|
-
* The base URL of your site (e.g., 'https://example.com')
|
|
8
|
-
* Used to construct the full href for the AI discovery link tag.
|
|
9
|
-
*/
|
|
10
|
-
baseUrl: string;
|
|
11
|
-
/**
|
|
12
|
-
* Child components to render
|
|
13
|
-
*/
|
|
14
|
-
children: ReactNode;
|
|
15
|
-
/**
|
|
16
|
-
* Optional: Onto configuration for automatic JSON-LD schema injection
|
|
17
|
-
* If provided, the provider will automatically inject JSON-LD schemas
|
|
18
|
-
* based on the page type configuration
|
|
19
|
-
*/
|
|
20
|
-
config?: OntoConfig;
|
|
21
|
-
}
|
|
22
|
-
/**
|
|
23
|
-
* OntoProvider — Automatic AI Discovery Provider
|
|
24
|
-
*
|
|
25
|
-
* Wraps your application and automatically injects:
|
|
26
|
-
* 1. `<link rel="alternate">` tags for AI discovery
|
|
27
|
-
* 2. JSON-LD structured data schemas based on page type
|
|
28
|
-
*
|
|
29
|
-
* With config, automatically generates JSON-LD schemas:
|
|
30
|
-
* - 'scoring' pages get Methodology schema with AIO weights (40/35/25)
|
|
31
|
-
* - 'about' pages get Organization/AboutPage schema
|
|
32
|
-
*
|
|
33
|
-
* Usage in a Next.js App Router layout:
|
|
34
|
-
* ```tsx
|
|
35
|
-
* import { OntoProvider } from '@ontosdk/next/provider';
|
|
36
|
-
* import config from '../onto.config';
|
|
37
|
-
*
|
|
38
|
-
* export default function RootLayout({ children }) {
|
|
39
|
-
* return (
|
|
40
|
-
* <OntoProvider baseUrl="https://example.com" config={config}>
|
|
41
|
-
* <html>
|
|
42
|
-
* <head />
|
|
43
|
-
* <body>{children}</body>
|
|
44
|
-
* </html>
|
|
45
|
-
* </OntoProvider>
|
|
46
|
-
* );
|
|
47
|
-
* }
|
|
48
|
-
* ```
|
|
49
|
-
*/
|
|
50
|
-
declare function OntoProvider({ baseUrl, children, config }: OntoProviderProps): react_jsx_runtime.JSX.Element;
|
|
51
|
-
|
|
52
|
-
export { OntoProvider, type OntoProviderProps };
|
package/dist/OntoProvider.d.ts
DELETED
|
@@ -1,52 +0,0 @@
|
|
|
1
|
-
import * as react_jsx_runtime from 'react/jsx-runtime';
|
|
2
|
-
import { ReactNode } from 'react';
|
|
3
|
-
import { OntoConfig } from './config.js';
|
|
4
|
-
|
|
5
|
-
interface OntoProviderProps {
|
|
6
|
-
/**
|
|
7
|
-
* The base URL of your site (e.g., 'https://example.com')
|
|
8
|
-
* Used to construct the full href for the AI discovery link tag.
|
|
9
|
-
*/
|
|
10
|
-
baseUrl: string;
|
|
11
|
-
/**
|
|
12
|
-
* Child components to render
|
|
13
|
-
*/
|
|
14
|
-
children: ReactNode;
|
|
15
|
-
/**
|
|
16
|
-
* Optional: Onto configuration for automatic JSON-LD schema injection
|
|
17
|
-
* If provided, the provider will automatically inject JSON-LD schemas
|
|
18
|
-
* based on the page type configuration
|
|
19
|
-
*/
|
|
20
|
-
config?: OntoConfig;
|
|
21
|
-
}
|
|
22
|
-
/**
|
|
23
|
-
* OntoProvider — Automatic AI Discovery Provider
|
|
24
|
-
*
|
|
25
|
-
* Wraps your application and automatically injects:
|
|
26
|
-
* 1. `<link rel="alternate">` tags for AI discovery
|
|
27
|
-
* 2. JSON-LD structured data schemas based on page type
|
|
28
|
-
*
|
|
29
|
-
* With config, automatically generates JSON-LD schemas:
|
|
30
|
-
* - 'scoring' pages get Methodology schema with AIO weights (40/35/25)
|
|
31
|
-
* - 'about' pages get Organization/AboutPage schema
|
|
32
|
-
*
|
|
33
|
-
* Usage in a Next.js App Router layout:
|
|
34
|
-
* ```tsx
|
|
35
|
-
* import { OntoProvider } from '@ontosdk/next/provider';
|
|
36
|
-
* import config from '../onto.config';
|
|
37
|
-
*
|
|
38
|
-
* export default function RootLayout({ children }) {
|
|
39
|
-
* return (
|
|
40
|
-
* <OntoProvider baseUrl="https://example.com" config={config}>
|
|
41
|
-
* <html>
|
|
42
|
-
* <head />
|
|
43
|
-
* <body>{children}</body>
|
|
44
|
-
* </html>
|
|
45
|
-
* </OntoProvider>
|
|
46
|
-
* );
|
|
47
|
-
* }
|
|
48
|
-
* ```
|
|
49
|
-
*/
|
|
50
|
-
declare function OntoProvider({ baseUrl, children, config }: OntoProviderProps): react_jsx_runtime.JSX.Element;
|
|
51
|
-
|
|
52
|
-
export { OntoProvider, type OntoProviderProps };
|
package/dist/cli.d.mts
DELETED
|
@@ -1 +0,0 @@
|
|
|
1
|
-
#!/usr/bin/env node
|
package/dist/cli.d.ts
DELETED
|
@@ -1 +0,0 @@
|
|
|
1
|
-
#!/usr/bin/env node
|
package/dist/config.d.mts
DELETED
|
@@ -1,80 +0,0 @@
|
|
|
1
|
-
/**
|
|
2
|
-
* Configuration schema for onto.config.ts
|
|
3
|
-
* Used to dynamically generate llms.txt and other AI discovery files
|
|
4
|
-
*/
|
|
5
|
-
type PageType = 'scoring' | 'about' | 'default';
|
|
6
|
-
interface OntoRoute {
|
|
7
|
-
/**
|
|
8
|
-
* The URL path (e.g., '/docs', '/api/reference')
|
|
9
|
-
*/
|
|
10
|
-
path: string;
|
|
11
|
-
/**
|
|
12
|
-
* Description of what this route contains
|
|
13
|
-
*/
|
|
14
|
-
description: string;
|
|
15
|
-
/**
|
|
16
|
-
* Optional: Page type for automatic JSON-LD schema injection
|
|
17
|
-
* - 'scoring': Injects Methodology schema with AIO scoring weights (40/35/25)
|
|
18
|
-
* - 'about': Injects Organization/AboutPage schema
|
|
19
|
-
* - 'default': No automatic schema injection
|
|
20
|
-
*/
|
|
21
|
-
pageType?: PageType;
|
|
22
|
-
}
|
|
23
|
-
interface OntoConfig {
|
|
24
|
-
/**
|
|
25
|
-
* The name of your project or site (required)
|
|
26
|
-
* Used as the H1 heading in llms.txt
|
|
27
|
-
*/
|
|
28
|
-
name: string;
|
|
29
|
-
/**
|
|
30
|
-
* A short summary of your project (required)
|
|
31
|
-
* Displayed as a blockquote in llms.txt
|
|
32
|
-
* Should contain key information necessary for understanding the rest of the file
|
|
33
|
-
*/
|
|
34
|
-
summary: string;
|
|
35
|
-
/**
|
|
36
|
-
* The base URL of your site (e.g., 'https://example.com')
|
|
37
|
-
*/
|
|
38
|
-
baseUrl: string;
|
|
39
|
-
/**
|
|
40
|
-
* Optional: Additional sections to include in llms.txt
|
|
41
|
-
* Each section can contain any markdown content
|
|
42
|
-
*/
|
|
43
|
-
sections?: {
|
|
44
|
-
heading: string;
|
|
45
|
-
content: string;
|
|
46
|
-
}[];
|
|
47
|
-
/**
|
|
48
|
-
* Key routes that AI agents should know about
|
|
49
|
-
* These will be formatted as a markdown list in llms.txt
|
|
50
|
-
*/
|
|
51
|
-
routes?: OntoRoute[];
|
|
52
|
-
/**
|
|
53
|
-
* Optional: Links to external resources (documentation, API references, etc.)
|
|
54
|
-
*/
|
|
55
|
-
externalLinks?: {
|
|
56
|
-
title: string;
|
|
57
|
-
url: string;
|
|
58
|
-
description?: string;
|
|
59
|
-
}[];
|
|
60
|
-
/**
|
|
61
|
-
* Optional: Organization information for JSON-LD schemas
|
|
62
|
-
*/
|
|
63
|
-
organization?: {
|
|
64
|
-
name: string;
|
|
65
|
-
description?: string;
|
|
66
|
-
url?: string;
|
|
67
|
-
logo?: string;
|
|
68
|
-
foundingDate?: string;
|
|
69
|
-
};
|
|
70
|
-
}
|
|
71
|
-
/**
|
|
72
|
-
* Generate llms.txt content from OntoConfig
|
|
73
|
-
* Follows the llms.txt specification:
|
|
74
|
-
* - H1 with project name
|
|
75
|
-
* - Blockquote with summary
|
|
76
|
-
* - Additional markdown sections
|
|
77
|
-
*/
|
|
78
|
-
declare function generateLlmsTxt(config: OntoConfig): string;
|
|
79
|
-
|
|
80
|
-
export { type OntoConfig, type OntoRoute, type PageType, generateLlmsTxt };
|
package/dist/config.d.ts
DELETED
|
@@ -1,80 +0,0 @@
|
|
|
1
|
-
/**
|
|
2
|
-
* Configuration schema for onto.config.ts
|
|
3
|
-
* Used to dynamically generate llms.txt and other AI discovery files
|
|
4
|
-
*/
|
|
5
|
-
type PageType = 'scoring' | 'about' | 'default';
|
|
6
|
-
interface OntoRoute {
|
|
7
|
-
/**
|
|
8
|
-
* The URL path (e.g., '/docs', '/api/reference')
|
|
9
|
-
*/
|
|
10
|
-
path: string;
|
|
11
|
-
/**
|
|
12
|
-
* Description of what this route contains
|
|
13
|
-
*/
|
|
14
|
-
description: string;
|
|
15
|
-
/**
|
|
16
|
-
* Optional: Page type for automatic JSON-LD schema injection
|
|
17
|
-
* - 'scoring': Injects Methodology schema with AIO scoring weights (40/35/25)
|
|
18
|
-
* - 'about': Injects Organization/AboutPage schema
|
|
19
|
-
* - 'default': No automatic schema injection
|
|
20
|
-
*/
|
|
21
|
-
pageType?: PageType;
|
|
22
|
-
}
|
|
23
|
-
interface OntoConfig {
|
|
24
|
-
/**
|
|
25
|
-
* The name of your project or site (required)
|
|
26
|
-
* Used as the H1 heading in llms.txt
|
|
27
|
-
*/
|
|
28
|
-
name: string;
|
|
29
|
-
/**
|
|
30
|
-
* A short summary of your project (required)
|
|
31
|
-
* Displayed as a blockquote in llms.txt
|
|
32
|
-
* Should contain key information necessary for understanding the rest of the file
|
|
33
|
-
*/
|
|
34
|
-
summary: string;
|
|
35
|
-
/**
|
|
36
|
-
* The base URL of your site (e.g., 'https://example.com')
|
|
37
|
-
*/
|
|
38
|
-
baseUrl: string;
|
|
39
|
-
/**
|
|
40
|
-
* Optional: Additional sections to include in llms.txt
|
|
41
|
-
* Each section can contain any markdown content
|
|
42
|
-
*/
|
|
43
|
-
sections?: {
|
|
44
|
-
heading: string;
|
|
45
|
-
content: string;
|
|
46
|
-
}[];
|
|
47
|
-
/**
|
|
48
|
-
* Key routes that AI agents should know about
|
|
49
|
-
* These will be formatted as a markdown list in llms.txt
|
|
50
|
-
*/
|
|
51
|
-
routes?: OntoRoute[];
|
|
52
|
-
/**
|
|
53
|
-
* Optional: Links to external resources (documentation, API references, etc.)
|
|
54
|
-
*/
|
|
55
|
-
externalLinks?: {
|
|
56
|
-
title: string;
|
|
57
|
-
url: string;
|
|
58
|
-
description?: string;
|
|
59
|
-
}[];
|
|
60
|
-
/**
|
|
61
|
-
* Optional: Organization information for JSON-LD schemas
|
|
62
|
-
*/
|
|
63
|
-
organization?: {
|
|
64
|
-
name: string;
|
|
65
|
-
description?: string;
|
|
66
|
-
url?: string;
|
|
67
|
-
logo?: string;
|
|
68
|
-
foundingDate?: string;
|
|
69
|
-
};
|
|
70
|
-
}
|
|
71
|
-
/**
|
|
72
|
-
* Generate llms.txt content from OntoConfig
|
|
73
|
-
* Follows the llms.txt specification:
|
|
74
|
-
* - H1 with project name
|
|
75
|
-
* - Blockquote with summary
|
|
76
|
-
* - Additional markdown sections
|
|
77
|
-
*/
|
|
78
|
-
declare function generateLlmsTxt(config: OntoConfig): string;
|
|
79
|
-
|
|
80
|
-
export { type OntoConfig, type OntoRoute, type PageType, generateLlmsTxt };
|
package/dist/index.d.mts
DELETED
|
@@ -1,25 +0,0 @@
|
|
|
1
|
-
export { OntoConfig, OntoConfig as OntoConfigType, OntoRoute, OntoRoute as OntoRouteType, PageType, generateLlmsTxt } from './config.mjs';
|
|
2
|
-
export { AIOMethodologySchema, AboutPageSchema, OrganizationSchema, generateAIOMethodologySchema, generateAboutPageSchema, generateOrganizationSchema, generateSchemaForPageType, serializeSchema } from './schemas.mjs';
|
|
3
|
-
|
|
4
|
-
interface ExtractionResult {
|
|
5
|
-
markdown: string;
|
|
6
|
-
metadata: {
|
|
7
|
-
title: string;
|
|
8
|
-
description: string;
|
|
9
|
-
jsonLd: any[];
|
|
10
|
-
};
|
|
11
|
-
stats: {
|
|
12
|
-
originalHtmlSize: number;
|
|
13
|
-
markdownSize: number;
|
|
14
|
-
tokenReductionRatio: number;
|
|
15
|
-
};
|
|
16
|
-
}
|
|
17
|
-
/**
|
|
18
|
-
* Extracts pure semantic markdown and metadata from rendered Next.js HTML strings.
|
|
19
|
-
* @param html The raw HTML string.
|
|
20
|
-
* @param sourceUrl (Optional) the URL this was generated from, to attach as metadata.
|
|
21
|
-
* @returns {ExtractionResult} The extracted payload.
|
|
22
|
-
*/
|
|
23
|
-
declare function extractContent(html: string, sourceUrl?: string): ExtractionResult;
|
|
24
|
-
|
|
25
|
-
export { extractContent };
|
package/dist/index.d.ts
DELETED
|
@@ -1,25 +0,0 @@
|
|
|
1
|
-
export { OntoConfig, OntoConfig as OntoConfigType, OntoRoute, OntoRoute as OntoRouteType, PageType, generateLlmsTxt } from './config.js';
|
|
2
|
-
export { AIOMethodologySchema, AboutPageSchema, OrganizationSchema, generateAIOMethodologySchema, generateAboutPageSchema, generateOrganizationSchema, generateSchemaForPageType, serializeSchema } from './schemas.js';
|
|
3
|
-
|
|
4
|
-
interface ExtractionResult {
|
|
5
|
-
markdown: string;
|
|
6
|
-
metadata: {
|
|
7
|
-
title: string;
|
|
8
|
-
description: string;
|
|
9
|
-
jsonLd: any[];
|
|
10
|
-
};
|
|
11
|
-
stats: {
|
|
12
|
-
originalHtmlSize: number;
|
|
13
|
-
markdownSize: number;
|
|
14
|
-
tokenReductionRatio: number;
|
|
15
|
-
};
|
|
16
|
-
}
|
|
17
|
-
/**
|
|
18
|
-
* Extracts pure semantic markdown and metadata from rendered Next.js HTML strings.
|
|
19
|
-
* @param html The raw HTML string.
|
|
20
|
-
* @param sourceUrl (Optional) the URL this was generated from, to attach as metadata.
|
|
21
|
-
* @returns {ExtractionResult} The extracted payload.
|
|
22
|
-
*/
|
|
23
|
-
declare function extractContent(html: string, sourceUrl?: string): ExtractionResult;
|
|
24
|
-
|
|
25
|
-
export { extractContent };
|
package/dist/middleware.d.mts
DELETED
|
@@ -1,29 +0,0 @@
|
|
|
1
|
-
import { NextResponse } from 'next/server';
|
|
2
|
-
import { OntoConfig } from './config.mjs';
|
|
3
|
-
|
|
4
|
-
/**
|
|
5
|
-
* Comprehensive registry of AI bot user-agent strings.
|
|
6
|
-
* The middleware uses this list to detect AI crawlers and serve optimized markdown.
|
|
7
|
-
*/
|
|
8
|
-
interface AiBot {
|
|
9
|
-
/** The user-agent substring to match against */
|
|
10
|
-
name: string;
|
|
11
|
-
/** The company operating this bot */
|
|
12
|
-
company: string;
|
|
13
|
-
/** ISO date when this bot was added or last verified */
|
|
14
|
-
addedAt?: string;
|
|
15
|
-
}
|
|
16
|
-
/**
|
|
17
|
-
* Flat list of user-agent substrings for fast matching in the middleware.
|
|
18
|
-
*/
|
|
19
|
-
declare const AI_BOT_USER_AGENTS: string[];
|
|
20
|
-
/**
|
|
21
|
-
* Given a raw user-agent string, returns the matched AiBot entry or undefined.
|
|
22
|
-
* Uses a "Longest Match" strategy to ensure maximum specificity.
|
|
23
|
-
* Comparison is case-insensitive.
|
|
24
|
-
*/
|
|
25
|
-
declare function matchBot(userAgent: string | null): AiBot | undefined;
|
|
26
|
-
|
|
27
|
-
declare function ontoMiddleware(request: any, config?: OntoConfig): Promise<NextResponse<unknown>>;
|
|
28
|
-
|
|
29
|
-
export { AI_BOT_USER_AGENTS, type AiBot, matchBot, ontoMiddleware };
|
package/dist/middleware.d.ts
DELETED
|
@@ -1,29 +0,0 @@
|
|
|
1
|
-
import { NextResponse } from 'next/server';
|
|
2
|
-
import { OntoConfig } from './config.js';
|
|
3
|
-
|
|
4
|
-
/**
|
|
5
|
-
* Comprehensive registry of AI bot user-agent strings.
|
|
6
|
-
* The middleware uses this list to detect AI crawlers and serve optimized markdown.
|
|
7
|
-
*/
|
|
8
|
-
interface AiBot {
|
|
9
|
-
/** The user-agent substring to match against */
|
|
10
|
-
name: string;
|
|
11
|
-
/** The company operating this bot */
|
|
12
|
-
company: string;
|
|
13
|
-
/** ISO date when this bot was added or last verified */
|
|
14
|
-
addedAt?: string;
|
|
15
|
-
}
|
|
16
|
-
/**
|
|
17
|
-
* Flat list of user-agent substrings for fast matching in the middleware.
|
|
18
|
-
*/
|
|
19
|
-
declare const AI_BOT_USER_AGENTS: string[];
|
|
20
|
-
/**
|
|
21
|
-
* Given a raw user-agent string, returns the matched AiBot entry or undefined.
|
|
22
|
-
* Uses a "Longest Match" strategy to ensure maximum specificity.
|
|
23
|
-
* Comparison is case-insensitive.
|
|
24
|
-
*/
|
|
25
|
-
declare function matchBot(userAgent: string | null): AiBot | undefined;
|
|
26
|
-
|
|
27
|
-
declare function ontoMiddleware(request: any, config?: OntoConfig): Promise<NextResponse<unknown>>;
|
|
28
|
-
|
|
29
|
-
export { AI_BOT_USER_AGENTS, type AiBot, matchBot, ontoMiddleware };
|
package/dist/schemas.d.mts
DELETED
|
@@ -1,72 +0,0 @@
|
|
|
1
|
-
import { OntoConfig } from './config.mjs';
|
|
2
|
-
|
|
3
|
-
/**
|
|
4
|
-
* JSON-LD Schema generators for automatic structured data injection
|
|
5
|
-
* Follows Schema.org standards for AI-friendly metadata
|
|
6
|
-
*/
|
|
7
|
-
|
|
8
|
-
/**
|
|
9
|
-
* Standard AIO (AI Optimization) scoring methodology
|
|
10
|
-
* Based on the Onto scoring algorithm:
|
|
11
|
-
* - React Tax (Efficiency): 40% (Step 1)
|
|
12
|
-
* - Semantic Richness: 35% (Step 2)
|
|
13
|
-
* - Content Negotiation: 25% (Step 3)
|
|
14
|
-
*/
|
|
15
|
-
interface AIOMethodologySchema {
|
|
16
|
-
'@context': 'https://schema.org';
|
|
17
|
-
'@type': 'HowTo';
|
|
18
|
-
name: string;
|
|
19
|
-
description: string;
|
|
20
|
-
step: Array<{
|
|
21
|
-
'@type': 'HowToStep';
|
|
22
|
-
name: string;
|
|
23
|
-
text: string;
|
|
24
|
-
position: number;
|
|
25
|
-
}>;
|
|
26
|
-
}
|
|
27
|
-
/**
|
|
28
|
-
* Generate AIO Scoring Methodology JSON-LD schema
|
|
29
|
-
* This explains to AI agents how the scoring system works
|
|
30
|
-
*/
|
|
31
|
-
declare function generateAIOMethodologySchema(config: OntoConfig, pageUrl: string): AIOMethodologySchema;
|
|
32
|
-
/**
|
|
33
|
-
* Organization schema for About pages
|
|
34
|
-
*/
|
|
35
|
-
interface OrganizationSchema {
|
|
36
|
-
'@context': 'https://schema.org';
|
|
37
|
-
'@type': 'Organization';
|
|
38
|
-
name: string;
|
|
39
|
-
url?: string;
|
|
40
|
-
description?: string;
|
|
41
|
-
logo?: string;
|
|
42
|
-
foundingDate?: string;
|
|
43
|
-
}
|
|
44
|
-
/**
|
|
45
|
-
* Generate Organization JSON-LD schema for About pages
|
|
46
|
-
*/
|
|
47
|
-
declare function generateOrganizationSchema(config: OntoConfig, pageUrl: string): OrganizationSchema | null;
|
|
48
|
-
/**
|
|
49
|
-
* AboutPage schema combining Organization and WebPage
|
|
50
|
-
*/
|
|
51
|
-
interface AboutPageSchema {
|
|
52
|
-
'@context': 'https://schema.org';
|
|
53
|
-
'@type': 'AboutPage';
|
|
54
|
-
name: string;
|
|
55
|
-
url: string;
|
|
56
|
-
description?: string;
|
|
57
|
-
mainEntity?: OrganizationSchema;
|
|
58
|
-
}
|
|
59
|
-
/**
|
|
60
|
-
* Generate AboutPage JSON-LD schema
|
|
61
|
-
*/
|
|
62
|
-
declare function generateAboutPageSchema(config: OntoConfig, pageUrl: string): AboutPageSchema;
|
|
63
|
-
/**
|
|
64
|
-
* Determine which schema to generate based on page type
|
|
65
|
-
*/
|
|
66
|
-
declare function generateSchemaForPageType(pageType: 'scoring' | 'about' | 'default', config: OntoConfig, pageUrl: string): any | null;
|
|
67
|
-
/**
|
|
68
|
-
* Serialize schema to JSON-LD script tag content
|
|
69
|
-
*/
|
|
70
|
-
declare function serializeSchema(schema: any | null): string | null;
|
|
71
|
-
|
|
72
|
-
export { type AIOMethodologySchema, type AboutPageSchema, type OrganizationSchema, generateAIOMethodologySchema, generateAboutPageSchema, generateOrganizationSchema, generateSchemaForPageType, serializeSchema };
|
package/dist/schemas.d.ts
DELETED
|
@@ -1,72 +0,0 @@
|
|
|
1
|
-
import { OntoConfig } from './config.js';
|
|
2
|
-
|
|
3
|
-
/**
|
|
4
|
-
* JSON-LD Schema generators for automatic structured data injection
|
|
5
|
-
* Follows Schema.org standards for AI-friendly metadata
|
|
6
|
-
*/
|
|
7
|
-
|
|
8
|
-
/**
|
|
9
|
-
* Standard AIO (AI Optimization) scoring methodology
|
|
10
|
-
* Based on the Onto scoring algorithm:
|
|
11
|
-
* - React Tax (Efficiency): 40% (Step 1)
|
|
12
|
-
* - Semantic Richness: 35% (Step 2)
|
|
13
|
-
* - Content Negotiation: 25% (Step 3)
|
|
14
|
-
*/
|
|
15
|
-
interface AIOMethodologySchema {
|
|
16
|
-
'@context': 'https://schema.org';
|
|
17
|
-
'@type': 'HowTo';
|
|
18
|
-
name: string;
|
|
19
|
-
description: string;
|
|
20
|
-
step: Array<{
|
|
21
|
-
'@type': 'HowToStep';
|
|
22
|
-
name: string;
|
|
23
|
-
text: string;
|
|
24
|
-
position: number;
|
|
25
|
-
}>;
|
|
26
|
-
}
|
|
27
|
-
/**
|
|
28
|
-
* Generate AIO Scoring Methodology JSON-LD schema
|
|
29
|
-
* This explains to AI agents how the scoring system works
|
|
30
|
-
*/
|
|
31
|
-
declare function generateAIOMethodologySchema(config: OntoConfig, pageUrl: string): AIOMethodologySchema;
|
|
32
|
-
/**
|
|
33
|
-
* Organization schema for About pages
|
|
34
|
-
*/
|
|
35
|
-
interface OrganizationSchema {
|
|
36
|
-
'@context': 'https://schema.org';
|
|
37
|
-
'@type': 'Organization';
|
|
38
|
-
name: string;
|
|
39
|
-
url?: string;
|
|
40
|
-
description?: string;
|
|
41
|
-
logo?: string;
|
|
42
|
-
foundingDate?: string;
|
|
43
|
-
}
|
|
44
|
-
/**
|
|
45
|
-
* Generate Organization JSON-LD schema for About pages
|
|
46
|
-
*/
|
|
47
|
-
declare function generateOrganizationSchema(config: OntoConfig, pageUrl: string): OrganizationSchema | null;
|
|
48
|
-
/**
|
|
49
|
-
* AboutPage schema combining Organization and WebPage
|
|
50
|
-
*/
|
|
51
|
-
interface AboutPageSchema {
|
|
52
|
-
'@context': 'https://schema.org';
|
|
53
|
-
'@type': 'AboutPage';
|
|
54
|
-
name: string;
|
|
55
|
-
url: string;
|
|
56
|
-
description?: string;
|
|
57
|
-
mainEntity?: OrganizationSchema;
|
|
58
|
-
}
|
|
59
|
-
/**
|
|
60
|
-
* Generate AboutPage JSON-LD schema
|
|
61
|
-
*/
|
|
62
|
-
declare function generateAboutPageSchema(config: OntoConfig, pageUrl: string): AboutPageSchema;
|
|
63
|
-
/**
|
|
64
|
-
* Determine which schema to generate based on page type
|
|
65
|
-
*/
|
|
66
|
-
declare function generateSchemaForPageType(pageType: 'scoring' | 'about' | 'default', config: OntoConfig, pageUrl: string): any | null;
|
|
67
|
-
/**
|
|
68
|
-
* Serialize schema to JSON-LD script tag content
|
|
69
|
-
*/
|
|
70
|
-
declare function serializeSchema(schema: any | null): string | null;
|
|
71
|
-
|
|
72
|
-
export { type AIOMethodologySchema, type AboutPageSchema, type OrganizationSchema, generateAIOMethodologySchema, generateAboutPageSchema, generateOrganizationSchema, generateSchemaForPageType, serializeSchema };
|