chore: import upstream snapshot with attribution
CI / Migrate Dev DB (push) Has been skipped
CI / Detect Version (push) Has been cancelled
CI / Migrate DB (push) Has been cancelled
CI / Build Dev ECR (./docker/app.Dockerfile, ECR_APP) (push) Has been cancelled
CI / Build Dev ECR (./docker/db.Dockerfile, ECR_MIGRATIONS) (push) Has been cancelled
CI / Build Dev ECR (./docker/pii.Dockerfile, ECR_PII) (push) Has been cancelled
CI / Build Dev ECR (./docker/realtime.Dockerfile, ECR_REALTIME) (push) Has been cancelled
CI / Deploy Trigger.dev (Dev) (push) Has been cancelled
CI / Build AMD64 (./docker/app.Dockerfile, ECR_APP, ghcr.io/simstudioai/simstudio) (push) Has been cancelled
CI / Build AMD64 (./docker/db.Dockerfile, ECR_MIGRATIONS, ghcr.io/simstudioai/migrations) (push) Has been cancelled
CI / Build AMD64 (./docker/pii.Dockerfile, ECR_PII, ghcr.io/simstudioai/pii) (push) Has been cancelled
CI / Build AMD64 (./docker/realtime.Dockerfile, ECR_REALTIME, ghcr.io/simstudioai/realtime) (push) Has been cancelled
CI / Build ARM64 (GHCR Only) (./docker/app.Dockerfile, ghcr.io/simstudioai/simstudio) (push) Has been cancelled
CI / Build ARM64 (GHCR Only) (./docker/db.Dockerfile, ghcr.io/simstudioai/migrations) (push) Has been cancelled
CI / Build ARM64 (GHCR Only) (./docker/pii.Dockerfile, ghcr.io/simstudioai/pii) (push) Has been cancelled
CI / Build ARM64 (GHCR Only) (./docker/realtime.Dockerfile, ghcr.io/simstudioai/realtime) (push) Has been cancelled
CI / Create GHCR Manifests (ghcr.io/simstudioai/migrations) (push) Has been cancelled
CI / Create GHCR Manifests (ghcr.io/simstudioai/pii) (push) Has been cancelled
CI / Create GHCR Manifests (ghcr.io/simstudioai/realtime) (push) Has been cancelled
CI / Create GHCR Manifests (ghcr.io/simstudioai/simstudio) (push) Has been cancelled
CI / Check Docs Changes (push) Has been cancelled
CI / Process Docs (push) Has been cancelled
CI / Create GitHub Release (push) Has been cancelled
CI / Test and Build (push) Has been cancelled
Publish CLI Package / publish-npm (push) Has been cancelled
Publish Python SDK / publish-pypi (push) Has been cancelled
Publish TypeScript SDK / publish-npm (push) Has been cancelled

This commit is contained in:
wehub-resource-sync
2026-07-13 13:20:55 +08:00
commit d25d482dc2
13754 changed files with 4996608 additions and 0 deletions
@@ -0,0 +1,67 @@
/**
* @vitest-environment node
*/
import { describe, expect, it } from 'vitest'
import { companyInfoEnrichment } from '@/enrichments/company-info/company-info'
import type { EnrichmentProvider } from '@/enrichments/types'
function provider(id: string): EnrichmentProvider {
const p = companyInfoEnrichment.providers.find((x) => x.id === id)
if (!p) throw new Error(`Provider ${id} not found in company-info cascade`)
return p
}
const domainInput = { domain: 'https://www.acme.com/about' }
describe('company-info enrichment cascade', () => {
it('chains the company-info providers in waterfall order', () => {
expect(companyInfoEnrichment.providers.map((p) => p.id)).toEqual([
'hunter',
'pdl',
'datagma',
'leadmagic',
])
})
describe('hunter', () => {
const p = provider('hunter')
it('normalizes the domain and maps size/description', () => {
expect(p.toolId).toBe('hunter_companies_find')
expect(p.buildParams(domainInput)).toEqual({ domain: 'acme.com' })
expect(p.buildParams({ domain: '' })).toBeNull()
expect(p.mapOutput({ size: '11-50', description: 'Payments' })).toEqual({
employeeCount: '11-50',
description: 'Payments',
})
expect(p.mapOutput({})).toEqual({})
})
})
describe('datagma', () => {
const p = provider('datagma')
it('passes the normalized domain as data and maps companySize/shortDescription', () => {
expect(p.toolId).toBe('datagma_enrich_company')
expect(p.buildParams(domainInput)).toEqual({ data: 'acme.com' })
expect(p.buildParams({ domain: '' })).toBeNull()
expect(p.mapOutput({ companySize: '11-50', shortDescription: 'Payments' })).toEqual({
employeeCount: '11-50',
description: 'Payments',
})
expect(p.mapOutput({})).toEqual({})
})
})
describe('leadmagic', () => {
const p = provider('leadmagic')
it('searches by domain and prefers the headcount range', () => {
expect(p.toolId).toBe('leadmagic_company_search')
expect(p.buildParams(domainInput)).toEqual({ company_domain: 'acme.com' })
expect(p.buildParams({ domain: '' })).toBeNull()
expect(
p.mapOutput({ employeeRange: '11-50', employeeCount: 42, description: 'Pay' })
).toEqual({ employeeCount: '11-50', description: 'Pay' })
expect(p.mapOutput({ employeeCount: 42 })).toEqual({ employeeCount: '42' })
expect(p.mapOutput({})).toEqual({})
})
})
})
@@ -0,0 +1,94 @@
import { filterUndefined } from '@sim/utils/object'
import { Building2 } from 'lucide-react'
import { normalizeDomain, str, toolProvider } from '@/enrichments/providers'
import type { EnrichmentConfig } from '@/enrichments/types'
/**
* Company Info enrichment. Looks up a company by domain, trying Hunter first
* (free) then People Data Labs, then Datagma and LeadMagic as fallbacks. Outputs
* are limited to the fields the providers reliably return — employee count and
* description — so the result stays consistent regardless of which provider fills
* the cell. `employeeCount` is a string so Hunter's range bucket (e.g. `"11-50"`),
* PDL's exact count, and LeadMagic's range all map onto the same column.
*/
export const companyInfoEnrichment: EnrichmentConfig = {
id: 'company-info',
name: 'Company Info',
description: "Look up a company's size and description from its domain.",
icon: Building2,
inputs: [{ id: 'domain', name: 'Company domain', type: 'string', required: true }],
outputs: [
{ id: 'employeeCount', name: 'employee count', type: 'string' },
{ id: 'description', name: 'description', type: 'string' },
],
providers: [
toolProvider({
id: 'hunter',
label: 'Hunter',
toolId: 'hunter_companies_find',
buildParams: (inputs) => {
const domain = normalizeDomain(inputs.domain)
if (!domain) return null
return { domain }
},
mapOutput: (output) => {
return filterUndefined({
employeeCount: str(output.size) || undefined,
description: str(output.description) || undefined,
})
},
}),
toolProvider({
id: 'pdl',
label: 'People Data Labs',
toolId: 'pdl_company_enrich',
buildParams: (inputs) => {
const website = normalizeDomain(inputs.domain)
if (!website) return null
// `required` makes PDL 404 (free) when neither field we extract is
// present, instead of charging a credit for a match we'd discard.
return { website, required: 'employee_count OR summary' }
},
mapOutput: (output) => {
const company = output.company as Record<string, unknown> | undefined
return filterUndefined({
employeeCount: str(company?.employee_count) || undefined,
description: str(company?.summary) || undefined,
})
},
}),
toolProvider({
id: 'datagma',
label: 'Datagma',
toolId: 'datagma_enrich_company',
buildParams: (inputs) => {
const data = normalizeDomain(inputs.domain)
if (!data) return null
return { data }
},
mapOutput: (output) => {
return filterUndefined({
employeeCount: str(output.companySize) || undefined,
description: str(output.shortDescription) || undefined,
})
},
}),
toolProvider({
id: 'leadmagic',
label: 'LeadMagic',
toolId: 'leadmagic_company_search',
buildParams: (inputs) => {
const companyDomain = normalizeDomain(inputs.domain)
if (!companyDomain) return null
return { company_domain: companyDomain }
},
mapOutput: (output) => {
// Prefer the headcount range to match Hunter's bucket style; fall back to the exact count.
return filterUndefined({
employeeCount: str(output.employeeRange) || str(output.employeeCount) || undefined,
description: str(output.description) || undefined,
})
},
}),
],
}
@@ -0,0 +1 @@
export { companyInfoEnrichment } from './company-info'