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 +1,196 @@
import { z } from 'zod'
import { AWS_REGION_PATTERN, toolJsonResponseSchema } from '@/lib/api/contracts/tools/media/shared'
import { defineRouteContract } from '@/lib/api/contracts/types'
import { FileInputSchema, RawFileInputSchema } from '@/lib/uploads/utils/file-schemas'
const textractQuerySchema = z.object({
Text: z.string().min(1),
Alias: z.string().optional(),
Pages: z.array(z.string()).optional(),
})
export const textractParseBodySchema = z
.object({
accessKeyId: z.string().min(1, 'AWS Access Key ID is required'),
secretAccessKey: z.string().min(1, 'AWS Secret Access Key is required'),
region: z
.string()
.min(1, 'AWS region is required')
.regex(
AWS_REGION_PATTERN,
'AWS region must be a valid AWS region (e.g., us-east-1, eu-west-2, us-gov-west-1)'
),
processingMode: z.enum(['sync', 'async']).optional().default('sync'),
filePath: z.string().optional(),
file: RawFileInputSchema.optional(),
s3Uri: z.string().optional(),
featureTypes: z
.array(z.enum(['TABLES', 'FORMS', 'QUERIES', 'SIGNATURES', 'LAYOUT']))
.optional(),
queries: z.array(textractQuerySchema).optional(),
})
.superRefine((data, ctx) => {
if (data.processingMode === 'async' && !data.s3Uri) {
ctx.addIssue({
code: 'custom',
message: 'S3 URI is required for multi-page processing (s3://bucket/key)',
path: ['s3Uri'],
})
}
if (data.processingMode !== 'async' && !data.file && !data.filePath) {
ctx.addIssue({
code: 'custom',
message: 'File input is required for single-page processing',
path: ['filePath'],
})
}
})
export const textractAnalyzeExpenseBodySchema = z
.object({
accessKeyId: z.string().min(1, 'AWS Access Key ID is required'),
secretAccessKey: z.string().min(1, 'AWS Secret Access Key is required'),
region: z
.string()
.min(1, 'AWS region is required')
.regex(
AWS_REGION_PATTERN,
'AWS region must be a valid AWS region (e.g., us-east-1, eu-west-2, us-gov-west-1)'
),
processingMode: z.enum(['sync', 'async']).optional().default('sync'),
filePath: z.string().optional(),
file: RawFileInputSchema.optional(),
s3Uri: z.string().optional(),
})
.superRefine((data, ctx) => {
if (data.processingMode === 'async' && !data.s3Uri) {
ctx.addIssue({
code: 'custom',
message: 'S3 URI is required for multi-page processing (s3://bucket/key)',
path: ['s3Uri'],
})
}
if (data.processingMode !== 'async' && !data.file && !data.filePath) {
ctx.addIssue({
code: 'custom',
message: 'Document input is required for single-page processing',
path: ['filePath'],
})
}
})
export const textractAnalyzeIdBodySchema = z
.object({
accessKeyId: z.string().min(1, 'AWS Access Key ID is required'),
secretAccessKey: z.string().min(1, 'AWS Secret Access Key is required'),
region: z
.string()
.min(1, 'AWS region is required')
.regex(
AWS_REGION_PATTERN,
'AWS region must be a valid AWS region (e.g., us-east-1, eu-west-2, us-gov-west-1)'
),
filePath: z.string().optional(),
file: RawFileInputSchema.optional(),
filePathBack: z.string().optional(),
fileBack: RawFileInputSchema.optional(),
})
.superRefine((data, ctx) => {
if (!data.file && !data.filePath) {
ctx.addIssue({
code: 'custom',
message: 'Identity document is required',
path: ['filePath'],
})
}
})
export const reductoParseBodySchema = z.object({
apiKey: z.string().min(1, 'API key is required'),
filePath: z.string().optional(),
file: RawFileInputSchema.optional(),
pages: z.array(z.number()).optional(),
tableOutputFormat: z.enum(['html', 'md']).optional(),
})
export const pulseParseBodySchema = z.object({
apiKey: z.string().min(1, 'API key is required'),
filePath: z.string().optional(),
file: RawFileInputSchema.optional(),
pages: z.string().optional(),
extractFigure: z.boolean().optional(),
figureDescription: z.boolean().optional(),
returnHtml: z.boolean().optional(),
chunking: z.string().optional(),
chunkSize: z.number().optional(),
})
export const extendParseBodySchema = z.object({
apiKey: z.string().min(1, 'API key is required'),
filePath: z.string().optional(),
file: RawFileInputSchema.optional(),
outputFormat: z.enum(['markdown', 'spatial']).optional(),
chunking: z.enum(['page', 'document', 'section']).optional(),
engine: z.enum(['parse_performance', 'parse_light']).optional(),
})
export const mistralParseBodySchema = z.object({
apiKey: z.string().min(1, 'API key is required'),
filePath: z.string().min(1, 'File path is required').optional(),
fileData: FileInputSchema.optional(),
file: FileInputSchema.optional(),
resultType: z.string().optional(),
pages: z.array(z.number()).optional(),
includeImageBase64: z.boolean().optional(),
imageLimit: z.number().optional(),
imageMinSize: z.number().optional(),
})
export const textractParseContract = defineRouteContract({
method: 'POST',
path: '/api/tools/textract/parse',
body: textractParseBodySchema,
response: { mode: 'json', schema: toolJsonResponseSchema },
})
export const textractAnalyzeExpenseContract = defineRouteContract({
method: 'POST',
path: '/api/tools/textract/analyze-expense',
body: textractAnalyzeExpenseBodySchema,
response: { mode: 'json', schema: toolJsonResponseSchema },
})
export const textractAnalyzeIdContract = defineRouteContract({
method: 'POST',
path: '/api/tools/textract/analyze-id',
body: textractAnalyzeIdBodySchema,
response: { mode: 'json', schema: toolJsonResponseSchema },
})
export const reductoParseContract = defineRouteContract({
method: 'POST',
path: '/api/tools/reducto/parse',
body: reductoParseBodySchema,
response: { mode: 'json', schema: toolJsonResponseSchema },
})
export const pulseParseContract = defineRouteContract({
method: 'POST',
path: '/api/tools/pulse/parse',
body: pulseParseBodySchema,
response: { mode: 'json', schema: toolJsonResponseSchema },
})
export const extendParseContract = defineRouteContract({
method: 'POST',
path: '/api/tools/extend/parse',
body: extendParseBodySchema,
response: { mode: 'json', schema: toolJsonResponseSchema },
})
export const mistralParseContract = defineRouteContract({
method: 'POST',
path: '/api/tools/mistral/parse',
body: mistralParseBodySchema,
response: { mode: 'json', schema: toolJsonResponseSchema },
})