fix(kb): fix race condition in stuck document retry during sync

The stuck document retry at the end of each sync was querying for all
documents with processingStatus 'pending' or 'failed'. This included
documents added in the CURRENT sync that were still processing
asynchronously, causing duplicate concurrent processing attempts.

The race between the original (correct) processing and the retry
(which reads the raw title from DB as filename) produced
nondeterministic failures — some documents would succeed while
others would fail with "Unsupported file type: <meeting title>".

Fixes:
- Filter stuck doc query by uploadedAt < syncStartedAt to exclude
  documents from the current sync
- Pass mimeType through to parseHttpFile and use existing
  getExtensionFromMimeType utility as fallback when filename has
  no extension (e.g. Fireflies meeting titles)
- Apply same mimeType fallback in parseDataURI for consistency

Author: waleedlatif1

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

@@ -7,7 +7,7 @@ import { parseBuffer, parseFile } from '@/lib/file-parsers'
 import type { FileParseMetadata } from '@/lib/file-parsers/types'
 import { retryWithExponentialBackoff } from '@/lib/knowledge/documents/utils'
 import { StorageService } from '@/lib/uploads'
-import { isInternalFileUrl } from '@/lib/uploads/utils/file-utils'
+import { getExtensionFromMimeType, isInternalFileUrl } from '@/lib/uploads/utils/file-utils'
 import { downloadFileFromUrl } from '@/lib/uploads/utils/file-utils.server'
 import { mistralParserTool } from '@/tools/mistral/parser'
 
@@ -759,38 +759,26 @@ async function parseDataURI(fileUrl: string, filename: string, mimeType: string)
       : decodeURIComponent(base64Data)
   }
 
-  const extension = filename.split('.').pop()?.toLowerCase() || 'txt'
+  const extension = filename.includes('.')
+    ? filename.split('.').pop()!.toLowerCase()
+    : getExtensionFromMimeType(mimeType) ?? 'txt'
   const buffer = Buffer.from(base64Data, 'base64')
   const result = await parseBuffer(buffer, extension)
   return result.content
 }
 
-const MIME_TO_EXTENSION: Record<string, string> = {
-  'text/plain': 'txt',
-  'text/markdown': 'md',
-  'text/csv': 'csv',
-  'text/html': 'html',
-  'application/pdf': 'pdf',
-  'application/json': 'json',
-  'application/yaml': 'yaml',
-  'application/vnd.openxmlformats-officedocument.wordprocessingml.document': 'docx',
-  'application/msword': 'doc',
-  'application/vnd.openxmlformats-officedocument.spreadsheetml.sheet': 'xlsx',
-  'application/vnd.ms-excel': 'xls',
-  'application/vnd.openxmlformats-officedocument.presentationml.presentation': 'pptx',
-  'application/vnd.ms-powerpoint': 'ppt',
-}
-
 async function parseHttpFile(
   fileUrl: string,
   filename: string,
   mimeType?: string
 ): Promise<{ content: string; metadata?: FileParseMetadata }> {
   const buffer = await downloadFileWithTimeout(fileUrl)
 
-  let extension = filename.split('.').pop()?.toLowerCase()
-  if (!extension || extension === filename.toLowerCase()) {
-    extension = mimeType ? MIME_TO_EXTENSION[mimeType] : undefined
+  let extension = filename.includes('.')
+    ? filename.split('.').pop()?.toLowerCase()
+    : undefined
+  if (!extension && mimeType) {
+    extension = getExtensionFromMimeType(mimeType) ?? undefined
   }
   if (!extension) {
     throw new Error(`Could not determine file type for: ${filename}`)