fix(knowledge): case-insensitive scheme checks for fileUrl

Boundary schema accepted uppercase schemes (e.g. HTTPS://, DATA:) via the
case-insensitive http regex, but the processor's case-sensitive
startsWith('data:') / startsWith('http') / startsWith('https://') checks
rejected them with a confusing "Unsupported fileUrl scheme" error.
Aligns processor checks to the schema using case-insensitive regex per
RFC 3986 §3.1.

Co-Authored-By: Claude Opus 4.7 <noreply@anthropic.com>

Author: waleedlatif1

apps/sim/lib/api/contracts/knowledge/shared.ts

@@ -34,7 +34,7 @@ export const knowledgeDocumentFileUrlSchema = z
   .string()
   .min(1, 'File URL is required')
   .refine(
-    (value) => value.startsWith('data:') || /^https?:\/\//i.test(value),
+    (value) => /^data:/i.test(value) || /^https?:\/\//i.test(value),
     'File URL must be a data: URI or an http(s):// URL'
   )
 

apps/sim/lib/knowledge/documents/document-processor.ts

@@ -315,7 +315,7 @@ async function handleFileForOCR(
   userId?: string,
   workspaceId?: string | null
 ) {
-  const isExternalHttps = fileUrl.startsWith('https://') && !isInternalFileUrl(fileUrl)
+  const isExternalHttps = /^https:\/\//i.test(fileUrl) && !isInternalFileUrl(fileUrl)
 
   if (isExternalHttps) {
     if (mimeType === 'application/pdf') {
@@ -385,14 +385,14 @@ async function downloadFileWithTimeout(fileUrl: string): Promise<Buffer> {
 }
 
 async function downloadFileForBase64(fileUrl: string): Promise<Buffer> {
-  if (fileUrl.startsWith('data:')) {
+  if (/^data:/i.test(fileUrl)) {
     const [, base64Data] = fileUrl.split(',')
     if (!base64Data) {
       throw new Error('Invalid data URI format')
     }
     return Buffer.from(base64Data, 'base64')
   }
-  if (fileUrl.startsWith('http')) {
+  if (/^https?:\/\//i.test(fileUrl)) {
     return downloadFileWithTimeout(fileUrl)
   }
   throw new Error('Unsupported fileUrl scheme: only data: URIs and http(s):// URLs are allowed')
@@ -782,9 +782,9 @@ async function parseWithFileParser(fileUrl: string, filename: string, mimeType:
     let content: string
     let metadata: FileParseMetadata = {}
 
-    if (fileUrl.startsWith('data:')) {
+    if (/^data:/i.test(fileUrl)) {
       content = await parseDataURI(fileUrl, filename, mimeType)
-    } else if (fileUrl.startsWith('http')) {
+    } else if (/^https?:\/\//i.test(fileUrl)) {
       const result = await parseHttpFile(fileUrl, filename, mimeType)
       content = result.content
       metadata = result.metadata || {}