Files
simstudioai--sim/apps/sim/app/api/tools/extend/parse/route.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

190 lines
5.6 KiB
TypeScript

import { createLogger } from '@sim/logger'
import { getErrorMessage } from '@sim/utils/errors'
import { type NextRequest, NextResponse } from 'next/server'
import { extendParseContract } from '@/lib/api/contracts/tools/media/document-parse'
import { getValidationErrorMessage, parseRequest } from '@/lib/api/server'
import { checkInternalAuth } from '@/lib/auth/hybrid'
import {
secureFetchWithPinnedIP,
validateUrlWithDNS,
} from '@/lib/core/security/input-validation.server'
import { generateRequestId } from '@/lib/core/utils/request'
import { withRouteHandler } from '@/lib/core/utils/with-route-handler'
import { isInternalFileUrl } from '@/lib/uploads/utils/file-utils'
import { resolveFileInputToUrl } from '@/lib/uploads/utils/file-utils.server'
export const dynamic = 'force-dynamic'
const logger = createLogger('ExtendParseAPI')
export const POST = withRouteHandler(async (request: NextRequest) => {
const requestId = generateRequestId()
try {
const authResult = await checkInternalAuth(request, { requireWorkflowId: false })
if (!authResult.success || !authResult.userId) {
logger.warn(`[${requestId}] Unauthorized Extend parse attempt`, {
error: authResult.error || 'Missing userId',
})
return NextResponse.json(
{
success: false,
error: authResult.error || 'Unauthorized',
},
{ status: 401 }
)
}
const userId = authResult.userId
const parsed = await parseRequest(
extendParseContract,
request,
{},
{
validationErrorResponse: (error) => {
logger.warn(`[${requestId}] Invalid request data`, { errors: error.issues })
return NextResponse.json(
{
success: false,
error: getValidationErrorMessage(error, 'Invalid request data'),
details: error.issues,
},
{ status: 400 }
)
},
}
)
if (!parsed.success) return parsed.response
const validatedData = parsed.data.body
logger.info(`[${requestId}] Extend parse request`, {
fileName: validatedData.file?.name,
filePath: validatedData.filePath,
isWorkspaceFile: validatedData.filePath ? isInternalFileUrl(validatedData.filePath) : false,
userId,
})
const resolution = await resolveFileInputToUrl({
file: validatedData.file,
filePath: validatedData.filePath,
userId,
requestId,
logger,
})
if (resolution.error) {
return NextResponse.json(
{ success: false, error: resolution.error.message },
{ status: resolution.error.status }
)
}
const fileUrl = resolution.fileUrl
if (!fileUrl) {
return NextResponse.json({ success: false, error: 'File input is required' }, { status: 400 })
}
const extendBody: Record<string, unknown> = {
file: { fileUrl },
}
const config: Record<string, unknown> = {}
if (validatedData.outputFormat) {
config.target = validatedData.outputFormat
}
if (validatedData.chunking) {
config.chunkingStrategy = { type: validatedData.chunking }
}
if (validatedData.engine) {
config.engine = validatedData.engine
}
if (Object.keys(config).length > 0) {
extendBody.config = config
}
const extendEndpoint = 'https://api.extend.ai/parse'
const extendValidation = await validateUrlWithDNS(extendEndpoint, 'Extend API URL')
if (!extendValidation.isValid) {
logger.error(`[${requestId}] Extend API URL validation failed`, {
error: extendValidation.error,
})
return NextResponse.json(
{
success: false,
error: 'Failed to reach Extend API',
},
{ status: 502 }
)
}
const extendResponse = await secureFetchWithPinnedIP(
extendEndpoint,
extendValidation.resolvedIP!,
{
method: 'POST',
headers: {
'Content-Type': 'application/json',
Accept: 'application/json',
Authorization: `Bearer ${validatedData.apiKey}`,
'x-extend-api-version': '2025-04-21',
},
body: JSON.stringify(extendBody),
}
)
if (!extendResponse.ok) {
const errorText = await extendResponse.text()
logger.error(`[${requestId}] Extend API error:`, errorText)
let clientError = `Extend API error: ${extendResponse.statusText || extendResponse.status}`
try {
const parsedError = JSON.parse(errorText)
if (parsedError?.message || parsedError?.error) {
clientError = (parsedError.message ?? parsedError.error) as string
}
} catch {
// errorText is not JSON; keep generic message
}
return NextResponse.json(
{
success: false,
error: clientError,
},
{ status: extendResponse.status }
)
}
const extendData = (await extendResponse.json()) as Record<string, unknown>
logger.info(`[${requestId}] Extend parse successful`)
return NextResponse.json({
success: true,
output: {
id: extendData.id ?? null,
status: extendData.status ?? 'PROCESSED',
chunks: extendData.chunks ?? [],
blocks: extendData.blocks ?? [],
pageCount: extendData.pageCount ?? extendData.page_count ?? null,
creditsUsed: extendData.creditsUsed ?? extendData.credits_used ?? null,
},
})
} catch (error) {
logger.error(`[${requestId}] Error in Extend parse:`, error)
return NextResponse.json(
{
success: false,
error: getErrorMessage(error, 'Internal server error'),
},
{ status: 500 }
)
}
})