Skip to content

chore(bots): regenerate registry (186 agents) for app#1280 #46

New issue

Have a question about this project? Sign up for a free GitHub account to open an issue and contact its maintainers and the community.

Sign up for GitHub

By clicking “Sign up for GitHub”, you agree to our terms of service and privacy statement. We’ll occasionally send you account related emails.

Already on GitHub? Sign in to your account

Merged
cport1 merged 1 commit into from
Sep 24, 2026
Merged

chore(bots): regenerate registry (186 agents) for app#1280 #46

Show file tree
Hide file tree
Changes from all commits
Commits
Show all changes
1 commit
Select commit
File filter

Filter by extension

Filter by extension
Conversations
Failed to load comments.
Loading
Jump to
Jump to file
Failed to load files.
Loading
Diff view
Diff view
23 changes: 22 additions & 1 deletion packages/webdecoy/src/bots/bots.test.ts
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -20,6 +20,27 @@ describe('matchUserAgent', () => {
expect(claude?.category).toBe('training_crawler');
});

it('keeps AI search and user-triggered fetchers out of training', () => {
// Every Anthropic UA carries an @anthropic.com contact, so a bare
// "anthropic" training pattern once caught all of them.
const user = matchUserAgent(
'Mozilla/5.0 AppleWebKit/537.36 (KHTML, like Gecko; compatible; Claude-User/1.0; +Claude-User@anthropic.com)',
);
expect(user?.id).toBe('claude-user');
expect(user?.category).toBe('ai_agent');

const search = matchUserAgent(
'Mozilla/5.0 AppleWebKit/537.36 (KHTML, like Gecko; compatible; PerplexityBot/1.0; +https://perplexity.ai/perplexitybot)',
);
expect(search?.category).toBe('ai_search_crawler');

const mistral = matchUserAgent(
'Mozilla/5.0 AppleWebKit/537.36 (KHTML, like Gecko; compatible; MistralAI-User/1.0; +https://docs.mistral.ai/robots)',
);
expect(mistral?.id).toBe('mistralai-user');
expect(mistral?.category).toBe('ai_assistant');
});

it('is case-insensitive, because User-Agent casing is not a contract', () => {
expect(matchUserAgent('GPTBOT/1.1')?.id).toBe('gptbot');
expect(matchUserAgent('gptbot/1.1')?.id).toBe('gptbot');
Expand Down Expand Up @@ -60,7 +81,7 @@ describe('matchUserAgent', () => {

describe('registry integrity', () => {
it('carries the full generated table', () => {
expect(BOT_REGISTRY.length).toBe(182);
expect(BOT_REGISTRY.length).toBe(186);
expect(BOT_CATEGORIES).toContain('training_crawler');
expect(BOT_CATEGORIES).toContain('search_crawler');
});
Expand Down
60 changes: 48 additions & 12 deletions packages/webdecoy/src/bots/parity-vectors.generated.json
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -84,13 +84,13 @@
"matched": true
},
{
"userAgent": "anthropic",
"userAgent": "anthropic-ai",
"id": "anthropic",
"category": "training_crawler",
"matched": true
},
{
"userAgent": "Mozilla/5.0 (compatible; anthropic/1.0; +http://example.com/bot)",
"userAgent": "Mozilla/5.0 (compatible; anthropic-ai/1.0; +http://example.com/bot)",
"id": "anthropic",
"category": "training_crawler",
"matched": true
Expand Down Expand Up @@ -372,15 +372,15 @@
"matched": true
},
{
"userAgent": "chatgpt",
"id": "chatgpt-user",
"category": "ai_assistant",
"userAgent": "claude-searchbot",
"id": "claude-searchbot",
"category": "ai_search_crawler",
"matched": true
},
{
"userAgent": "Mozilla/5.0 (compatible; chatgpt/1.0; +http://example.com/bot)",
"id": "chatgpt-user",
"category": "ai_assistant",
"userAgent": "Mozilla/5.0 (compatible; claude-searchbot/1.0; +http://example.com/bot)",
"id": "claude-searchbot",
"category": "ai_search_crawler",
"matched": true
},
{
Expand Down Expand Up @@ -1223,6 +1223,18 @@
"category": "training_crawler",
"matched": true
},
{
"userAgent": "meta-externalfetcher",
"id": "meta-externalfetcher",
"category": "ai_assistant",
"matched": true
},
{
"userAgent": "Mozilla/5.0 (compatible; meta-externalfetcher/1.0; +http://example.com/bot)",
"id": "meta-externalfetcher",
"category": "ai_assistant",
"matched": true
},
{
"userAgent": "metaphor",
"id": "metaphor",
Expand Down Expand Up @@ -1260,13 +1272,25 @@
"matched": true
},
{
"userAgent": "mistral",
"userAgent": "mistralai-user",
"id": "mistralai-user",
"category": "ai_assistant",
"matched": true
},
{
"userAgent": "Mozilla/5.0 (compatible; mistralai-user/1.0; +http://example.com/bot)",
"id": "mistralai-user",
"category": "ai_assistant",
"matched": true
},
{
"userAgent": "mistralbot",
"id": "mistral",
"category": "training_crawler",
"matched": true
},
{
"userAgent": "Mozilla/5.0 (compatible; mistral/1.0; +http://example.com/bot)",
"userAgent": "Mozilla/5.0 (compatible; mistralbot/1.0; +http://example.com/bot)",
"id": "mistral",
"category": "training_crawler",
"matched": true
Expand Down Expand Up @@ -1523,16 +1547,28 @@
"category": "generic_scraper",
"matched": true
},
{
"userAgent": "perplexity-user",
"id": "perplexity-user",
"category": "ai_assistant",
"matched": true
},
{
"userAgent": "Mozilla/5.0 (compatible; perplexity-user/1.0; +http://example.com/bot)",
"id": "perplexity-user",
"category": "ai_assistant",
"matched": true
},
{
"userAgent": "perplexitybot",
"id": "perplexitybot",
"category": "training_crawler",
"category": "ai_search_crawler",
"matched": true
},
{
"userAgent": "Mozilla/5.0 (compatible; perplexitybot/1.0; +http://example.com/bot)",
"id": "perplexitybot",
"category": "training_crawler",
"category": "ai_search_crawler",
"matched": true
},
{
Expand Down
14 changes: 9 additions & 5 deletions packages/webdecoy/src/bots/registry.generated.ts
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -11,7 +11,7 @@
* agents share User-Agent substrings, so sorting this array changes how real
* traffic is classified.
*
* 182 agents across 15 categories.
* 186 agents across 15 categories.
*/

/**
Expand Down Expand Up @@ -78,7 +78,7 @@ export const BOT_REGISTRY: readonly BotAgent[] = [
{ id: "reflectionbot", name: "Reflectionbot", category: "training_crawler", organization: "Reflection AI", baseScore: 70, respectsRobots: true, uaPatterns: ["reflectionbot"] },
{ id: "gptbot", name: "GPTBot", category: "training_crawler", organization: "OpenAI", baseScore: 85, respectsRobots: true, uaPatterns: ["gptbot"] },
{ id: "claudebot", name: "ClaudeBot", category: "training_crawler", organization: "Anthropic", baseScore: 85, respectsRobots: true, uaPatterns: ["claudebot"] },
{ id: "anthropic", name: "Anthropic", category: "training_crawler", organization: "Anthropic", baseScore: 85, respectsRobots: true, uaPatterns: ["anthropic"] },
{ id: "anthropic", name: "Anthropic", category: "training_crawler", organization: "Anthropic", baseScore: 85, respectsRobots: true, uaPatterns: ["anthropic-ai"] },
{ id: "claude-web", name: "Claude-Web", category: "training_crawler", organization: "Anthropic", baseScore: 85, respectsRobots: true, uaPatterns: ["claude-web"] },
{ id: "ccbot", name: "CCBot", category: "training_crawler", organization: "Common Crawl", baseScore: 80, respectsRobots: true, uaPatterns: ["ccbot"] },
{ id: "google-extended", name: "Google-Extended", category: "training_crawler", organization: "Google", baseScore: 80, respectsRobots: true, uaPatterns: ["google-extended"] },
Expand All @@ -87,10 +87,9 @@ export const BOT_REGISTRY: readonly BotAgent[] = [
{ id: "facebookbot", name: "FacebookBot", category: "training_crawler", organization: "Meta", baseScore: 70, respectsRobots: true, uaPatterns: ["facebookbot"] },
{ id: "meta-externalagent", name: "Meta-ExternalAgent", category: "training_crawler", organization: "Meta", baseScore: 75, respectsRobots: true, uaPatterns: ["meta-externalagent"] },
{ id: "cohere-ai", name: "Cohere", category: "training_crawler", organization: "Cohere", baseScore: 80, respectsRobots: true, uaPatterns: ["cohere-ai", "cohere"] },
{ id: "perplexitybot", name: "PerplexityBot", category: "training_crawler", organization: "Perplexity AI", baseScore: 80, respectsRobots: true, uaPatterns: ["perplexitybot"] },
{ id: "applebot-extended", name: "Applebot-Extended", category: "training_crawler", organization: "Apple", baseScore: 75, respectsRobots: true, uaPatterns: ["applebot-extended"] },
{ id: "youbot", name: "YouBot", category: "training_crawler", organization: "You.com", baseScore: 75, respectsRobots: true, uaPatterns: ["youbot"] },
{ id: "mistral", name: "MistralBot", category: "training_crawler", organization: "Mistral AI", baseScore: 80, respectsRobots: true, uaPatterns: ["mistral"] },
{ id: "mistral", name: "MistralBot", category: "training_crawler", organization: "Mistral AI", baseScore: 80, respectsRobots: true, uaPatterns: ["mistralbot"] },
{ id: "gemini", name: "Gemini", category: "training_crawler", organization: "Google", baseScore: 80, respectsRobots: true, uaPatterns: ["gemini"] },
{ id: "ai2bot", name: "AI2Bot", category: "training_crawler", organization: "Allen Institute for AI", baseScore: 75, respectsRobots: true, uaPatterns: ["ai2bot"] },
{ id: "deepseek", name: "DeepSeek", category: "training_crawler", organization: "DeepSeek", baseScore: 80, respectsRobots: true, uaPatterns: ["deepseek"] },
Expand All @@ -107,6 +106,8 @@ export const BOT_REGISTRY: readonly BotAgent[] = [
{ id: "sofyabot", name: "SofyaBot", category: "ai_search_crawler", organization: "Sofya", baseScore: 65, respectsRobots: true, uaPatterns: ["sofyabot"] },
{ id: "xai-searchbot", name: "xAI-SearchBot", category: "ai_search_crawler", organization: "xAI", baseScore: 70, respectsRobots: true, uaPatterns: ["xai-searchbot"] },
{ id: "linkupbot", name: "LinkupBot", category: "ai_search_crawler", organization: "Linkup", baseScore: 65, respectsRobots: true, uaPatterns: ["linkupbot"] },
{ id: "perplexitybot", name: "PerplexityBot", category: "ai_search_crawler", organization: "Perplexity AI", baseScore: 80, respectsRobots: true, uaPatterns: ["perplexitybot"] },
{ id: "claude-searchbot", name: "Claude-SearchBot", category: "ai_search_crawler", organization: "Anthropic", baseScore: 75, respectsRobots: true, uaPatterns: ["claude-searchbot"] },
{ id: "oai-searchbot", name: "OAI-SearchBot", category: "ai_search_crawler", organization: "OpenAI", baseScore: 80, respectsRobots: true, uaPatterns: ["oai-searchbot"] },
{ id: "searchgpt", name: "SearchGPT", category: "ai_search_crawler", organization: "OpenAI", baseScore: 75, respectsRobots: true, uaPatterns: ["searchgpt"] },
{ id: "phind", name: "Phind", category: "ai_search_crawler", organization: "Phind", baseScore: 70, respectsRobots: true, uaPatterns: ["phind"] },
Expand Down Expand Up @@ -252,7 +253,10 @@ export const BOT_REGISTRY: readonly BotAgent[] = [
{ id: "apify", name: "Apify", category: "commercial_scraper", organization: "Apify", baseScore: 65, respectsRobots: true, uaPatterns: ["apify"] },
{ id: "crawlbase", name: "Crawlbase", category: "commercial_scraper", organization: "Crawlbase", baseScore: 65, respectsRobots: true, uaPatterns: ["crawlbase"] },
{ id: "webscrapingapi", name: "WebScrapingAPI", category: "commercial_scraper", organization: "WebScrapingAPI", baseScore: 65, respectsRobots: true, uaPatterns: ["webscrapingapi"] },
{ id: "chatgpt-user", name: "ChatGPT-User", category: "ai_assistant", organization: "OpenAI", baseScore: 85, respectsRobots: true, uaPatterns: ["chatgpt-user", "chatgpt"] },
{ id: "chatgpt-user", name: "ChatGPT-User", category: "ai_assistant", organization: "OpenAI", baseScore: 85, respectsRobots: true, uaPatterns: ["chatgpt-user"] },
{ id: "perplexity-user", name: "Perplexity-User", category: "ai_assistant", organization: "Perplexity AI", baseScore: 75, respectsRobots: false, uaPatterns: ["perplexity-user"] },
{ id: "mistralai-user", name: "MistralAI-User", category: "ai_assistant", organization: "Mistral AI", baseScore: 75, respectsRobots: true, uaPatterns: ["mistralai-user"] },
{ id: "meta-externalfetcher", name: "Meta-ExternalFetcher", category: "ai_assistant", organization: "Meta", baseScore: 70, respectsRobots: false, uaPatterns: ["meta-externalfetcher"] },
{ id: "gemini-deep-research", name: "Gemini-Deep-Research", category: "ai_assistant", organization: "Google", baseScore: 65, respectsRobots: true, uaPatterns: ["gemini-deep-research"] },
{ id: "copilot", name: "Microsoft Copilot", category: "ai_assistant", organization: "Microsoft", baseScore: 65, respectsRobots: true, uaPatterns: ["copilot"] },
{ id: "cortana", name: "Cortana", category: "ai_assistant", organization: "Microsoft", baseScore: 60, respectsRobots: true, uaPatterns: ["cortana"] },
Expand Down
Loading