Files
simstudioai--sim/apps/sim/tools/firecrawl/map.ts
T
wehub-resource-sync d25d482dc2
Publish CLI Package / publish-npm (push) Waiting to run
Publish Python SDK / publish-pypi (push) Waiting to run
Publish TypeScript SDK / publish-npm (push) Waiting to run
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
chore: import upstream snapshot with attribution
2026-07-13 13:20:55 +08:00

150 lines
4.1 KiB
TypeScript

import type { MapParams, MapResponse } from '@/tools/firecrawl/types'
import type { ToolConfig } from '@/tools/types'
export const mapTool: ToolConfig<MapParams, MapResponse> = {
id: 'firecrawl_map',
name: 'Firecrawl Map',
description:
'Get a complete list of URLs from any website quickly and reliably. Useful for discovering all pages on a site without crawling them.',
version: '1.0.0',
params: {
url: {
type: 'string',
required: true,
visibility: 'user-or-llm',
description: 'The base URL to map and discover links from (e.g., "https://example.com")',
},
search: {
type: 'string',
required: false,
visibility: 'user-or-llm',
description: 'Filter results by relevance to a search term (e.g., "blog")',
},
sitemap: {
type: 'string',
required: false,
visibility: 'user-only',
description: 'Controls sitemap usage: "skip", "include" (default), or "only"',
},
includeSubdomains: {
type: 'boolean',
required: false,
visibility: 'user-only',
description: 'Whether to include URLs from subdomains (default: true)',
},
ignoreQueryParameters: {
type: 'boolean',
required: false,
visibility: 'user-only',
description: 'Exclude URLs containing query strings (default: true)',
},
limit: {
type: 'number',
required: false,
visibility: 'user-or-llm',
description:
'Maximum number of links to return (e.g., 100, 1000, 5000). Max: 100,000, default: 5,000',
},
timeout: {
type: 'number',
required: false,
visibility: 'user-only',
description: 'Request timeout in milliseconds',
},
location: {
type: 'json',
required: false,
visibility: 'hidden',
description: 'Geographic context for proxying (country, languages)',
},
apiKey: {
type: 'string',
required: true,
visibility: 'user-only',
description: 'Firecrawl API key',
},
},
hosting: {
envKeyPrefix: 'FIRECRAWL_API_KEY',
apiKeyParam: 'apiKey',
byokProviderId: 'firecrawl',
pricing: {
type: 'custom',
getCost: (_params, output) => {
if (output.creditsUsed == null) {
throw new Error('Firecrawl response missing creditsUsed field')
}
const creditsUsed = Number(output.creditsUsed)
if (Number.isNaN(creditsUsed)) {
throw new Error('Firecrawl response returned a non-numeric creditsUsed field')
}
return {
cost: creditsUsed * 0.001,
metadata: { creditsUsed },
}
},
},
rateLimit: {
mode: 'per_request',
requestsPerMinute: 100,
},
},
request: {
method: 'POST',
url: 'https://api.firecrawl.dev/v2/map',
headers: (params) => ({
'Content-Type': 'application/json',
Authorization: `Bearer ${params.apiKey}`,
}),
body: (params) => {
const body: Record<string, any> = {
url: params.url,
}
if (params.search) body.search = params.search
if (params.sitemap) body.sitemap = params.sitemap
if (typeof params.includeSubdomains === 'boolean')
body.includeSubdomains = params.includeSubdomains
if (typeof params.ignoreQueryParameters === 'boolean')
body.ignoreQueryParameters = params.ignoreQueryParameters
if (params.limit) body.limit = Number(params.limit)
if (params.timeout) body.timeout = Number(params.timeout)
if (params.location) body.location = params.location
return body
},
},
transformResponse: async (response: Response) => {
const data = await response.json()
return {
success: data.success,
output: {
success: data.success,
links: data.links || [],
creditsUsed: 1,
},
}
},
outputs: {
success: {
type: 'boolean',
description: 'Whether the mapping operation was successful',
},
links: {
type: 'array',
description: 'Array of discovered URLs from the website',
items: {
type: 'string',
},
},
},
}