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 +1,68 @@
import type {
BrightDataCancelSnapshotParams,
BrightDataCancelSnapshotResponse,
} from '@/tools/brightdata/types'
import type { ToolConfig } from '@/tools/types'
export const brightDataCancelSnapshotTool: ToolConfig<
BrightDataCancelSnapshotParams,
BrightDataCancelSnapshotResponse
> = {
id: 'brightdata_cancel_snapshot',
name: 'Bright Data Cancel Snapshot',
description:
'Cancel an active Bright Data scraping job using its snapshot ID. Terminates data collection in progress.',
version: '1.0.0',
params: {
apiKey: {
type: 'string',
required: true,
visibility: 'user-only',
description: 'Bright Data API token',
},
snapshotId: {
type: 'string',
required: true,
visibility: 'user-or-llm',
description: 'The snapshot ID of the collection to cancel (e.g., "s_m4x7enmven8djfqak")',
},
},
request: {
method: 'POST',
url: (params) =>
`https://api.brightdata.com/datasets/v3/snapshot/${params.snapshotId?.trim()}/cancel`,
headers: (params) => ({
Authorization: `Bearer ${params.apiKey}`,
}),
},
transformResponse: async (response: Response, params) => {
if (!response.ok) {
const errorText = await response.text()
throw new Error(errorText || `Cancel snapshot failed with status ${response.status}`)
}
await response.json().catch(() => null)
return {
success: true,
output: {
snapshotId: params?.snapshotId ?? null,
cancelled: true,
},
}
},
outputs: {
snapshotId: {
type: 'string',
description: 'The snapshot ID that was cancelled',
optional: true,
},
cancelled: {
type: 'boolean',
description: 'Whether the cancellation was successful',
},
},
}
+250
View File
@@ -0,0 +1,250 @@
import { createLogger } from '@sim/logger'
import { toError } from '@sim/utils/errors'
import { sleep } from '@sim/utils/helpers'
import { DEFAULT_EXECUTION_TIMEOUT_MS } from '@/lib/core/execution-limits'
import type { BrightDataDiscoverParams, BrightDataDiscoverResponse } from '@/tools/brightdata/types'
import type { ToolConfig } from '@/tools/types'
const logger = createLogger('tools:brightdata:discover')
const POLL_INTERVAL_MS = 3000
const MAX_POLL_TIME_MS = DEFAULT_EXECUTION_TIMEOUT_MS
export const brightDataDiscoverTool: ToolConfig<
BrightDataDiscoverParams,
BrightDataDiscoverResponse
> = {
id: 'brightdata_discover',
name: 'Bright Data Discover',
description:
'AI-powered web discovery that finds and ranks results by intent. Returns up to 20 results with optional cleaned page content for RAG and verification.',
version: '1.0.0',
params: {
apiKey: {
type: 'string',
required: true,
visibility: 'user-only',
description: 'Bright Data API token',
},
query: {
type: 'string',
required: true,
visibility: 'user-or-llm',
description: 'The search query (e.g., "competitor pricing changes enterprise plan")',
},
numResults: {
type: 'number',
required: false,
visibility: 'user-or-llm',
description: 'Number of results to return (1-20). Defaults to 10',
},
mode: {
type: 'string',
required: false,
visibility: 'user-or-llm',
description:
'Search depth and ranking mode: "standard" (balanced), "deep" (exhaustive, broader search), "fast" (optimized for speed), or "zeroRanking" (raw volume without AI filtering). Defaults to "standard"',
},
intent: {
type: 'string',
required: false,
visibility: 'user-or-llm',
description:
'Describes what the agent is trying to accomplish, used to rank results by relevance (e.g., "find official pricing pages and change notes")',
},
includeContent: {
type: 'boolean',
required: false,
visibility: 'user-or-llm',
description: 'Whether to include cleaned page content in results',
},
format: {
type: 'string',
required: false,
visibility: 'user-or-llm',
description: 'Response format: "json" or "md". Defaults to "json"',
},
language: {
type: 'string',
required: false,
visibility: 'user-or-llm',
description: 'Search language code (e.g., "en", "es", "fr"). Defaults to "en"',
},
country: {
type: 'string',
required: false,
visibility: 'user-or-llm',
description: 'Two-letter ISO country code for localized results (e.g., "us", "gb")',
},
},
request: {
method: 'POST',
url: 'https://api.brightdata.com/discover',
headers: (params) => ({
'Content-Type': 'application/json',
Authorization: `Bearer ${params.apiKey}`,
}),
body: (params) => {
const body: Record<string, unknown> = {
query: params.query,
}
if (params.numResults) body.num_results = params.numResults
if (params.mode) body.mode = params.mode
if (params.intent) body.intent = params.intent
if (params.includeContent != null) body.include_content = params.includeContent
if (params.format) body.format = params.format
if (params.language) body.language = params.language
if (params.country) body.country = params.country
return body
},
},
transformResponse: async (response: Response, params) => {
if (!response.ok) {
const errorText = await response.text()
throw new Error(errorText || `Discover request failed with status ${response.status}`)
}
const data = await response.json()
return {
success: true,
output: {
results: [],
query: params?.query ?? null,
totalResults: 0,
taskId: data.task_id ?? null,
},
}
},
postProcess: async (result, params) => {
if (!result.success) return result
const taskId = result.output.taskId
if (!taskId) {
return {
...result,
success: false,
error: 'Discover API did not return a task_id. Cannot poll for results.',
}
}
logger.info(`Bright Data Discover task ${taskId} created, polling for results...`)
let elapsedTime = 0
while (elapsedTime < MAX_POLL_TIME_MS) {
try {
const pollResponse = await fetch(
`https://api.brightdata.com/discover?task_id=${encodeURIComponent(taskId)}`,
{
method: 'GET',
headers: {
Authorization: `Bearer ${params.apiKey}`,
},
}
)
if (!pollResponse.ok) {
return {
...result,
success: false,
error: `Failed to poll discover results: ${pollResponse.statusText}`,
}
}
const data = await pollResponse.json()
logger.info(`Bright Data Discover task ${taskId} status: ${data.status}`)
if (data.status === 'done') {
const items = Array.isArray(data.results) ? data.results : []
const results = items.map((item: Record<string, unknown>) => ({
url: (item.link as string) ?? (item.url as string) ?? null,
title: (item.title as string) ?? null,
description: (item.description as string) ?? (item.snippet as string) ?? null,
relevanceScore: (item.relevance_score as number) ?? null,
content: (item.content as string) ?? null,
}))
return {
success: true,
output: {
results,
query: params.query ?? null,
totalResults: results.length,
},
}
}
if (data.status === 'failed' || data.status === 'error') {
return {
...result,
success: false,
error: `Discover task failed: ${data.error ?? 'Unknown error'}`,
}
}
await sleep(POLL_INTERVAL_MS)
elapsedTime += POLL_INTERVAL_MS
} catch (error) {
logger.error('Error polling for discover task:', {
message: toError(error).message,
taskId,
})
return {
...result,
success: false,
error: `Error polling for discover task: ${toError(error).message}`,
}
}
}
logger.warn(
`Discover task ${taskId} did not complete within the maximum polling time (${MAX_POLL_TIME_MS / 1000}s)`
)
return {
...result,
success: false,
error: `Discover task ${taskId} timed out after ${MAX_POLL_TIME_MS / 1000}s. Check status manually.`,
}
},
outputs: {
results: {
type: 'array',
description: 'Array of discovered web results ranked by intent relevance',
items: {
type: 'object',
description: 'A discovered result',
properties: {
url: { type: 'string', description: 'URL of the discovered page', optional: true },
title: { type: 'string', description: 'Page title', optional: true },
description: {
type: 'string',
description: 'Page description or snippet',
optional: true,
},
relevanceScore: {
type: 'number',
description: 'AI-calculated relevance score for intent-based ranking',
optional: true,
},
content: {
type: 'string',
description:
'Cleaned page content in the requested format (when includeContent is true)',
optional: true,
},
},
},
},
query: { type: 'string', description: 'The search query that was executed', optional: true },
totalResults: { type: 'number', description: 'Total number of results returned' },
},
}
@@ -0,0 +1,116 @@
import type {
BrightDataDownloadSnapshotParams,
BrightDataDownloadSnapshotResponse,
} from '@/tools/brightdata/types'
import type { ToolConfig } from '@/tools/types'
export const brightDataDownloadSnapshotTool: ToolConfig<
BrightDataDownloadSnapshotParams,
BrightDataDownloadSnapshotResponse
> = {
id: 'brightdata_download_snapshot',
name: 'Bright Data Download Snapshot',
description:
'Download the results of a completed Bright Data scraping job using its snapshot ID. The snapshot must have ready status.',
version: '1.0.0',
params: {
apiKey: {
type: 'string',
required: true,
visibility: 'user-only',
description: 'Bright Data API token',
},
snapshotId: {
type: 'string',
required: true,
visibility: 'user-or-llm',
description:
'The snapshot ID returned when the collection was triggered (e.g., "s_m4x7enmven8djfqak")',
},
format: {
type: 'string',
required: false,
visibility: 'user-or-llm',
description: 'Output format: "json", "ndjson", "jsonl", or "csv". Defaults to "json"',
},
compress: {
type: 'boolean',
required: false,
visibility: 'user-or-llm',
description: 'Whether to compress the results',
},
},
request: {
method: 'GET',
url: (params) => {
const queryParams = new URLSearchParams()
if (params.format) queryParams.set('format', params.format)
if (params.compress) queryParams.set('compress', 'true')
const qs = queryParams.toString()
return `https://api.brightdata.com/datasets/v3/snapshot/${params.snapshotId?.trim()}${qs ? `?${qs}` : ''}`
},
headers: (params) => ({
Authorization: `Bearer ${params.apiKey}`,
}),
},
transformResponse: async (response: Response, params) => {
if (response.status === 409) {
throw new Error(
'Snapshot is not ready for download. Check the snapshot status first and wait until it is "ready".'
)
}
if (!response.ok) {
const errorText = await response.text()
throw new Error(errorText || `Snapshot download failed with status ${response.status}`)
}
const contentType = response.headers.get('content-type') || ''
let data: Array<Record<string, unknown>>
if (contentType.includes('application/json')) {
const parsed = await response.json()
data = Array.isArray(parsed) ? parsed : [parsed]
} else {
const text = await response.text()
try {
const parsed = JSON.parse(text)
data = Array.isArray(parsed) ? parsed : [parsed]
} catch {
data = [{ raw: text }]
}
}
return {
success: true,
output: {
data,
format: contentType,
snapshotId: params?.snapshotId ?? null,
},
}
},
outputs: {
data: {
type: 'array',
description: 'Array of scraped result records',
items: {
type: 'json',
description: 'A scraped record with dataset-specific fields',
},
},
format: {
type: 'string',
description: 'The content type of the downloaded data',
},
snapshotId: {
type: 'string',
description: 'The snapshot ID that was downloaded',
optional: true,
},
},
}
+19
View File
@@ -0,0 +1,19 @@
import { brightDataCancelSnapshotTool } from '@/tools/brightdata/cancel_snapshot'
import { brightDataDiscoverTool } from '@/tools/brightdata/discover'
import { brightDataDownloadSnapshotTool } from '@/tools/brightdata/download_snapshot'
import { brightDataScrapeDatasetTool } from '@/tools/brightdata/scrape_dataset'
import { brightDataScrapeUrlTool } from '@/tools/brightdata/scrape_url'
import { brightDataSerpSearchTool } from '@/tools/brightdata/serp_search'
import { brightDataSnapshotStatusTool } from '@/tools/brightdata/snapshot_status'
import { brightDataSyncScrapeTool } from '@/tools/brightdata/sync_scrape'
export {
brightDataCancelSnapshotTool,
brightDataDiscoverTool,
brightDataDownloadSnapshotTool,
brightDataScrapeDatasetTool,
brightDataScrapeUrlTool,
brightDataSerpSearchTool,
brightDataSnapshotStatusTool,
brightDataSyncScrapeTool,
}
+104
View File
@@ -0,0 +1,104 @@
import type {
BrightDataScrapeDatasetParams,
BrightDataScrapeDatasetResponse,
} from '@/tools/brightdata/types'
import type { ToolConfig } from '@/tools/types'
export const brightDataScrapeDatasetTool: ToolConfig<
BrightDataScrapeDatasetParams,
BrightDataScrapeDatasetResponse
> = {
id: 'brightdata_scrape_dataset',
name: 'Bright Data Scrape Dataset',
description:
'Trigger a Bright Data pre-built scraper to extract structured data from URLs. Supports 660+ scrapers for platforms like Amazon, LinkedIn, Instagram, and more.',
version: '1.0.0',
params: {
apiKey: {
type: 'string',
required: true,
visibility: 'user-only',
description: 'Bright Data API token',
},
datasetId: {
type: 'string',
required: true,
visibility: 'user-or-llm',
description:
'Dataset scraper ID from your Bright Data dashboard (e.g., "gd_l1viktl72bvl7bjuj0")',
},
urls: {
type: 'string',
required: true,
visibility: 'user-or-llm',
description:
'JSON array of URL objects to scrape (e.g., [{"url": "https://example.com/product"}])',
},
format: {
type: 'string',
required: false,
visibility: 'user-or-llm',
description: 'Output format: "json" or "csv". Defaults to "json"',
},
includeErrors: {
type: 'boolean',
required: false,
visibility: 'user-or-llm',
description: 'Whether to include a per-input error report in the results',
},
},
request: {
method: 'POST',
url: (params) => {
const queryParams = new URLSearchParams()
queryParams.set('dataset_id', params.datasetId.trim())
queryParams.set('format', params.format || 'json')
if (params.includeErrors) queryParams.set('include_errors', 'true')
return `https://api.brightdata.com/datasets/v3/trigger?${queryParams.toString()}`
},
headers: (params) => ({
'Content-Type': 'application/json',
Authorization: `Bearer ${params.apiKey}`,
}),
body: (params) => {
if (typeof params.urls === 'string') {
try {
return JSON.parse(params.urls)
} catch {
return [{ url: params.urls }]
}
}
return params.urls
},
},
transformResponse: async (response: Response) => {
if (!response.ok) {
const errorText = await response.text()
throw new Error(errorText || `Dataset trigger failed with status ${response.status}`)
}
const data = await response.json()
return {
success: true,
output: {
snapshotId: data.snapshot_id ?? data.snapshotId ?? '',
status: data.status ?? 'triggered',
},
}
},
outputs: {
snapshotId: {
type: 'string',
description: 'The snapshot ID to retrieve results later',
},
status: {
type: 'string',
description: 'Status of the scraping job (e.g., "triggered", "running")',
},
},
}
+111
View File
@@ -0,0 +1,111 @@
import type {
BrightDataScrapeUrlParams,
BrightDataScrapeUrlResponse,
} from '@/tools/brightdata/types'
import type { ToolConfig } from '@/tools/types'
export const brightDataScrapeUrlTool: ToolConfig<
BrightDataScrapeUrlParams,
BrightDataScrapeUrlResponse
> = {
id: 'brightdata_scrape_url',
name: 'Bright Data Scrape URL',
description:
'Fetch content from any URL using Bright Data Web Unlocker. Bypasses anti-bot protections, CAPTCHAs, and IP blocks automatically.',
version: '1.0.0',
params: {
apiKey: {
type: 'string',
required: true,
visibility: 'user-only',
description: 'Bright Data API token',
},
zone: {
type: 'string',
required: true,
visibility: 'user-or-llm',
description: 'Web Unlocker zone name from your Bright Data dashboard (e.g., "web_unlocker1")',
},
url: {
type: 'string',
required: true,
visibility: 'user-or-llm',
description: 'The URL to scrape (e.g., "https://example.com/page")',
},
format: {
type: 'string',
required: false,
visibility: 'user-or-llm',
description:
'Response format: "raw" for HTML or "json" for parsed content. Defaults to "raw"',
},
country: {
type: 'string',
required: false,
visibility: 'user-or-llm',
description: 'Two-letter country code for geo-targeting (e.g., "us", "gb")',
},
dataFormat: {
type: 'string',
required: false,
visibility: 'user-or-llm',
description:
'Convert the response to "markdown" instead of raw HTML, useful for feeding page content to an LLM. Omit for the default HTML/JSON response',
},
},
request: {
method: 'POST',
url: 'https://api.brightdata.com/request',
headers: (params) => ({
'Content-Type': 'application/json',
Authorization: `Bearer ${params.apiKey}`,
}),
body: (params) => {
const body: Record<string, unknown> = {
zone: params.zone,
url: params.url,
format: params.format || 'raw',
}
if (params.country) body.country = params.country
if (params.dataFormat) body.data_format = params.dataFormat
return body
},
},
transformResponse: async (response: Response, params) => {
const contentType = response.headers.get('content-type') || ''
if (!response.ok) {
const errorText = await response.text()
throw new Error(errorText || `Request failed with status ${response.status}`)
}
let content: string
if (contentType.includes('application/json')) {
const data = await response.json()
content = typeof data === 'string' ? data : JSON.stringify(data)
} else {
content = await response.text()
}
return {
success: true,
output: {
content,
url: params?.url ?? null,
statusCode: response.status,
},
}
},
outputs: {
content: {
type: 'string',
description: 'The scraped page content (HTML or JSON depending on format)',
},
url: { type: 'string', description: 'The URL that was scraped', optional: true },
statusCode: { type: 'number', description: 'HTTP status code of the response', optional: true },
},
}
+219
View File
@@ -0,0 +1,219 @@
import type {
BrightDataSerpSearchParams,
BrightDataSerpSearchResponse,
} from '@/tools/brightdata/types'
import type { ToolConfig } from '@/tools/types'
const SEARCH_ENGINE_CONFIG: Record<
string,
{ url: string; queryKey: string; numKey: string; langKey: string; countryKey: string }
> = {
google: {
url: 'https://www.google.com/search',
queryKey: 'q',
numKey: 'num',
langKey: 'hl',
countryKey: 'gl',
},
bing: {
url: 'https://www.bing.com/search',
queryKey: 'q',
numKey: 'count',
langKey: 'setLang',
countryKey: 'cc',
},
duckduckgo: {
url: 'https://duckduckgo.com/',
queryKey: 'q',
numKey: '',
langKey: '',
countryKey: '',
},
yandex: {
url: 'https://yandex.com/search/',
queryKey: 'text',
numKey: 'numdoc',
langKey: 'lang',
countryKey: '',
},
} as const
export const brightDataSerpSearchTool: ToolConfig<
BrightDataSerpSearchParams,
BrightDataSerpSearchResponse
> = {
id: 'brightdata_serp_search',
name: 'Bright Data SERP Search',
description:
'Search Google, Bing, DuckDuckGo, or Yandex and get structured search results using Bright Data SERP API.',
version: '1.0.0',
params: {
apiKey: {
type: 'string',
required: true,
visibility: 'user-only',
description: 'Bright Data API token',
},
zone: {
type: 'string',
required: true,
visibility: 'user-or-llm',
description: 'SERP API zone name from your Bright Data dashboard (e.g., "serp_api1")',
},
query: {
type: 'string',
required: true,
visibility: 'user-or-llm',
description: 'The search query (e.g., "best project management tools")',
},
searchEngine: {
type: 'string',
required: false,
visibility: 'user-or-llm',
description:
'Search engine to use: "google", "bing", "duckduckgo", or "yandex". Defaults to "google"',
},
country: {
type: 'string',
required: false,
visibility: 'user-or-llm',
description: 'Two-letter country code for localized results (e.g., "us", "gb")',
},
language: {
type: 'string',
required: false,
visibility: 'user-or-llm',
description: 'Two-letter language code (e.g., "en", "es")',
},
numResults: {
type: 'number',
required: false,
visibility: 'user-or-llm',
description: 'Number of results to return (e.g., 10, 20). Defaults to 10',
},
},
request: {
method: 'POST',
url: 'https://api.brightdata.com/request',
headers: (params) => ({
'Content-Type': 'application/json',
Authorization: `Bearer ${params.apiKey}`,
}),
body: (params) => {
const engine = params.searchEngine || 'google'
const config = SEARCH_ENGINE_CONFIG[engine] || SEARCH_ENGINE_CONFIG.google
const searchParams = new URLSearchParams()
searchParams.set(config.queryKey, params.query)
if (params.numResults && config.numKey) {
searchParams.set(config.numKey, String(params.numResults))
}
if (params.language && config.langKey) {
searchParams.set(config.langKey, params.language)
}
if (params.country && config.countryKey) {
searchParams.set(config.countryKey, params.country)
}
searchParams.set('brd_json', '1')
const body: Record<string, unknown> = {
zone: params.zone,
url: `${config.url}?${searchParams.toString()}`,
format: 'raw',
}
if (params.country) body.country = params.country
return body
},
},
transformResponse: async (response: Response, params) => {
if (!response.ok) {
const errorText = await response.text()
throw new Error(errorText || `SERP request failed with status ${response.status}`)
}
const contentType = response.headers.get('content-type') || ''
let results: Array<{
title: string | null
url: string | null
description: string | null
rank: number | null
}> = []
let data: Record<string, unknown> | null = null
if (contentType.includes('application/json')) {
data = await response.json()
if (Array.isArray(data?.organic)) {
results = data.organic.map((item: Record<string, unknown>, index: number) => ({
title: (item.title as string) ?? null,
url: (item.link as string) ?? (item.url as string) ?? null,
description: (item.description as string) ?? (item.snippet as string) ?? null,
rank: index + 1,
}))
} else if (Array.isArray(data)) {
results = data.map((item: Record<string, unknown>, index: number) => ({
title: (item.title as string) ?? null,
url: (item.link as string) ?? (item.url as string) ?? null,
description: (item.description as string) ?? (item.snippet as string) ?? null,
rank: index + 1,
}))
}
} else {
const text = await response.text()
results = [
{
title: 'Raw SERP Response',
url: null,
description: text.slice(0, 500),
rank: 1,
},
]
}
return {
success: true,
output: {
results,
query:
((data?.general as Record<string, unknown> | undefined)?.query as string) ??
params?.query ??
null,
searchEngine:
((data?.general as Record<string, unknown> | undefined)?.search_engine as string) ??
params?.searchEngine ??
null,
},
}
},
outputs: {
results: {
type: 'array',
description: 'Array of search results',
items: {
type: 'object',
description: 'A search result entry',
properties: {
title: { type: 'string', description: 'Title of the search result', optional: true },
url: { type: 'string', description: 'URL of the search result', optional: true },
description: {
type: 'string',
description: 'Snippet or description of the result',
optional: true,
},
rank: { type: 'number', description: 'Position in search results', optional: true },
},
},
},
query: { type: 'string', description: 'The search query that was executed', optional: true },
searchEngine: {
type: 'string',
description: 'The search engine that was used',
optional: true,
},
},
}
@@ -0,0 +1,74 @@
import type {
BrightDataSnapshotStatusParams,
BrightDataSnapshotStatusResponse,
} from '@/tools/brightdata/types'
import type { ToolConfig } from '@/tools/types'
export const brightDataSnapshotStatusTool: ToolConfig<
BrightDataSnapshotStatusParams,
BrightDataSnapshotStatusResponse
> = {
id: 'brightdata_snapshot_status',
name: 'Bright Data Snapshot Status',
description:
'Check the progress of an async Bright Data scraping job. Returns status: starting, running, ready, or failed.',
version: '1.0.0',
params: {
apiKey: {
type: 'string',
required: true,
visibility: 'user-only',
description: 'Bright Data API token',
},
snapshotId: {
type: 'string',
required: true,
visibility: 'user-or-llm',
description:
'The snapshot ID returned when the collection was triggered (e.g., "s_m4x7enmven8djfqak")',
},
},
request: {
method: 'GET',
url: (params) => `https://api.brightdata.com/datasets/v3/progress/${params.snapshotId?.trim()}`,
headers: (params) => ({
Authorization: `Bearer ${params.apiKey}`,
}),
},
transformResponse: async (response: Response) => {
if (!response.ok) {
const errorText = await response.text()
throw new Error(errorText || `Snapshot status check failed with status ${response.status}`)
}
const data = await response.json()
return {
success: true,
output: {
snapshotId: data.snapshot_id ?? null,
datasetId: data.dataset_id ?? null,
status: data.status ?? 'unknown',
},
}
},
outputs: {
snapshotId: {
type: 'string',
description: 'The snapshot ID that was queried',
},
datasetId: {
type: 'string',
description: 'The dataset ID associated with this snapshot',
optional: true,
},
status: {
type: 'string',
description: 'Current status of the snapshot: "starting", "running", "ready", or "failed"',
},
},
}
+131
View File
@@ -0,0 +1,131 @@
import type {
BrightDataSyncScrapeParams,
BrightDataSyncScrapeResponse,
} from '@/tools/brightdata/types'
import type { ToolConfig } from '@/tools/types'
export const brightDataSyncScrapeTool: ToolConfig<
BrightDataSyncScrapeParams,
BrightDataSyncScrapeResponse
> = {
id: 'brightdata_sync_scrape',
name: 'Bright Data Sync Scrape',
description:
'Scrape URLs synchronously using a Bright Data pre-built scraper and get structured results directly. Supports up to 20 URLs with a 1-minute timeout.',
version: '1.0.0',
params: {
apiKey: {
type: 'string',
required: true,
visibility: 'user-only',
description: 'Bright Data API token',
},
datasetId: {
type: 'string',
required: true,
visibility: 'user-or-llm',
description:
'Dataset scraper ID from your Bright Data dashboard (e.g., "gd_l1viktl72bvl7bjuj0")',
},
urls: {
type: 'string',
required: true,
visibility: 'user-or-llm',
description:
'JSON array of URL objects to scrape, up to 20 (e.g., [{"url": "https://example.com/product"}])',
},
format: {
type: 'string',
required: false,
visibility: 'user-or-llm',
description: 'Output format: "json", "ndjson", or "csv". Defaults to "json"',
},
includeErrors: {
type: 'boolean',
required: false,
visibility: 'user-or-llm',
description: 'Whether to include error reports in results',
},
},
request: {
method: 'POST',
url: (params) => {
const queryParams = new URLSearchParams()
queryParams.set('dataset_id', params.datasetId.trim())
queryParams.set('format', params.format || 'json')
if (params.includeErrors) queryParams.set('include_errors', 'true')
return `https://api.brightdata.com/datasets/v3/scrape?${queryParams.toString()}`
},
headers: (params) => ({
'Content-Type': 'application/json',
Authorization: `Bearer ${params.apiKey}`,
}),
body: (params) => {
if (typeof params.urls === 'string') {
try {
const parsed = JSON.parse(params.urls)
return { input: Array.isArray(parsed) ? parsed : [parsed] }
} catch {
return { input: [{ url: params.urls }] }
}
}
return { input: params.urls }
},
},
transformResponse: async (response: Response) => {
if (!response.ok) {
const errorText = await response.text()
throw new Error(errorText || `Sync scrape failed with status ${response.status}`)
}
if (response.status === 202) {
const data = await response.json()
return {
success: true,
output: {
data: [],
snapshotId: data.snapshot_id ?? null,
isAsync: true,
},
}
}
const data = await response.json()
const results = Array.isArray(data) ? data : [data]
return {
success: true,
output: {
data: results,
snapshotId: null,
isAsync: false,
},
}
},
outputs: {
data: {
type: 'array',
description:
'Array of scraped result objects with fields specific to the dataset scraper used',
items: {
type: 'json',
description: 'A scraped record with dataset-specific fields',
},
},
snapshotId: {
type: 'string',
description:
'Snapshot ID returned if the request exceeded the 1-minute timeout and switched to async processing',
optional: true,
},
isAsync: {
type: 'boolean',
description:
'Whether the request fell back to async mode (true means use snapshot ID to retrieve results)',
},
},
}
+149
View File
@@ -0,0 +1,149 @@
import type { ToolResponse } from '@/tools/types'
export interface BrightDataScrapeUrlParams {
apiKey: string
zone: string
url: string
format?: string
country?: string
dataFormat?: string
}
export interface BrightDataScrapeUrlResponse extends ToolResponse {
output: {
content: string
url: string | null
statusCode: number | null
}
}
export interface BrightDataSerpSearchParams {
apiKey: string
zone: string
query: string
searchEngine?: string
country?: string
language?: string
numResults?: number
}
export interface BrightDataSerpSearchResponse extends ToolResponse {
output: {
results: Array<{
title: string | null
url: string | null
description: string | null
rank: number | null
}>
query: string | null
searchEngine: string | null
}
}
export interface BrightDataScrapeDatasetParams {
apiKey: string
datasetId: string
urls: string
format?: string
includeErrors?: boolean
}
export interface BrightDataScrapeDatasetResponse extends ToolResponse {
output: {
snapshotId: string
status: string
}
}
export interface BrightDataSyncScrapeParams {
apiKey: string
datasetId: string
urls: string
format?: string
includeErrors?: boolean
}
export interface BrightDataSyncScrapeResponse extends ToolResponse {
output: {
data: Array<Record<string, unknown>>
snapshotId: string | null
isAsync: boolean
}
}
export interface BrightDataSnapshotStatusParams {
apiKey: string
snapshotId: string
}
export interface BrightDataSnapshotStatusResponse extends ToolResponse {
output: {
snapshotId: string | null
datasetId: string | null
status: string
}
}
export interface BrightDataDownloadSnapshotParams {
apiKey: string
snapshotId: string
format?: string
compress?: boolean
}
export interface BrightDataDownloadSnapshotResponse extends ToolResponse {
output: {
data: Array<Record<string, unknown>>
format: string
snapshotId: string | null
}
}
export interface BrightDataCancelSnapshotParams {
apiKey: string
snapshotId: string
}
export interface BrightDataCancelSnapshotResponse extends ToolResponse {
output: {
snapshotId: string | null
cancelled: boolean
}
}
export interface BrightDataDiscoverParams {
apiKey: string
query: string
numResults?: number
mode?: string
intent?: string
includeContent?: boolean
format?: string
language?: string
country?: string
}
export interface BrightDataDiscoverResponse extends ToolResponse {
output: {
results: Array<{
url: string | null
title: string | null
description: string | null
relevanceScore: number | null
content: string | null
}>
query: string | null
totalResults: number
taskId?: string | null
}
}
export type BrightDataResponse =
| BrightDataScrapeUrlResponse
| BrightDataSerpSearchResponse
| BrightDataScrapeDatasetResponse
| BrightDataSyncScrapeResponse
| BrightDataSnapshotStatusResponse
| BrightDataDownloadSnapshotResponse
| BrightDataCancelSnapshotResponse
| BrightDataDiscoverResponse