fix(files): bound YAML expansion and buffered reads on the file-serve path

apps/sim/app/api/files/public/[token]/content/route.test.ts

@@ -3,6 +3,8 @@
  */
 import { NextRequest } from 'next/server'
 import { beforeEach, describe, expect, it, vi } from 'vitest'
+import { PayloadSizeLimitError } from '@/lib/core/utils/stream-limits'
+import { MAX_BUFFERED_TRANSFER_BYTES } from '@/lib/uploads/shared/types'
 
 const {
   mockResolveActiveShareByToken,
@@ -78,13 +80,47 @@ describe('GET /api/files/public/[token]/content', () => {
     expect(mockDownloadFile).not.toHaveBeenCalled()
   })
 
-  it('serves the bytes once authorized', async () => {
+  it('serves the bytes once authorized, bounded by the shared transfer ceiling', async () => {
     mockValidateDeploymentAuth.mockResolvedValueOnce({ authorized: true })
     const res = await GET(request(), params())
     expect(res.status).toBe(200)
+    // The ceiling matters most here: this is the only surface that reads a workspace
+    // object for a caller with no session, and the object is admitted at 5 GB.
     expect(mockDownloadFile).toHaveBeenCalledWith({
       key: passwordShare.file.key,
       context: 'workspace',
+      maxBytes: MAX_BUFFERED_TRANSFER_BYTES,
     })
   })
+
+  it('413s when a compiled artifact outgrows the ceiling its source fit inside', async () => {
+    mockValidateDeploymentAuth.mockResolvedValueOnce({ authorized: true })
+    // The source read is bounded, but the artifact is fetched separately — a small
+    // generation source can resolve to a document far larger than the source ever was.
+    mockDownloadFile.mockResolvedValueOnce(Buffer.from('generation source'))
+    mockResolveServableDoc.mockResolvedValueOnce({
+      kind: 'artifact',
+      buffer: Buffer.alloc(MAX_BUFFERED_TRANSFER_BYTES + 1),
+      contentType: 'application/pdf',
+    })
+
+    const res = await GET(request(), params())
+
+    expect(res.status).toBe(413)
+  })
+
+  it('answers 413 rather than 500 when the shared file is too large to serve resident', async () => {
+    mockValidateDeploymentAuth.mockResolvedValueOnce({ authorized: true })
+    mockDownloadFile.mockRejectedValueOnce(
+      new PayloadSizeLimitError({
+        label: 'storage download',
+        maxBytes: MAX_BUFFERED_TRANSFER_BYTES,
+        observedBytes: 5 * 1024 * 1024 * 1024,
+      })
+    )
+
+    const res = await GET(request(), params())
+
+    expect(res.status).toBe(413)
+  })
 })

apps/sim/app/api/files/public/[token]/content/route.ts

@@ -7,11 +7,13 @@ import { parseRequest } from '@/lib/api/server'
 import { resolveServableDoc } from '@/lib/copilot/tools/server/files/doc-compile'
 import { validateDeploymentAuth } from '@/lib/core/security/deployment-auth'
 import { generateRequestId } from '@/lib/core/utils/request'
+import { assertKnownSizeWithinLimit } from '@/lib/core/utils/stream-limits'
 import { withRouteHandler } from '@/lib/core/utils/with-route-handler'
 import { enforcePublicFileRateLimit } from '@/lib/public-shares/rate-limit'
 import { resolveActiveShareByToken } from '@/lib/public-shares/share-manager'
 import { downloadFile } from '@/lib/uploads/core/storage-service'
 import { resolveServableImageBytes } from '@/lib/uploads/server/image-derivative'
+import { MAX_BUFFERED_TRANSFER_BYTES } from '@/lib/uploads/shared/types'
 import { isSimPageSource, SIM_PAGE_CONTENT_TYPE } from '@/lib/workspace-files/page-compile'
 import { renderSimPageDocumentWithAssets } from '@/lib/workspace-files/page-document.server'
 import {
@@ -69,7 +71,14 @@ export const GET = withRouteHandler(
       }
 
       const { file } = resolved
-      const raw = await downloadFile({ key: file.key, context: 'workspace' })
+      // The same ceiling the authenticated serve route reads this object under
+      // (`fetchWorkspaceFileBuffer`). Without it a share link is the one way to ask
+      // an unauthenticated caller's request to hold a 5 GB workspace file resident.
+      const raw = await downloadFile({
+        key: file.key,
+        context: 'workspace',
+        maxBytes: MAX_BUFFERED_TRANSFER_BYTES,
+      })
 
       const servable = file.workspaceId
         ? await resolveServableDoc(file.workspaceId, raw, file.originalName)
@@ -116,6 +125,12 @@ export const GET = withRouteHandler(
         if (image) ({ buffer, contentType } = image)
       }
 
+      // Bounding the source read does not bound the response: each branch above can
+      // replace it with bytes fetched or produced separately — a compiled artifact, a
+      // page with its images inlined, a transcoded derivative. This is an anonymous
+      // route, so the bytes it actually returns are what has to fit.
+      assertKnownSizeWithinLimit(buffer.length, MAX_BUFFERED_TRANSFER_BYTES, 'served file response')
+
       logger.info('Public shared file served', { token, key: file.key, size: buffer.length })
 
       // Anonymous access: null actor (owner-as-actor would misread as a self-download).

apps/sim/app/api/files/public/[token]/inline/route.test.ts

@@ -3,6 +3,8 @@
  */
 import { NextRequest } from 'next/server'
 import { beforeEach, describe, expect, it, vi } from 'vitest'
+import { PayloadSizeLimitError } from '@/lib/core/utils/stream-limits'
+import { MAX_BUFFERED_TRANSFER_BYTES } from '@/lib/uploads/shared/types'
 
 const { mockResolveShare, mockRateLimit, mockValidateAuth, mockDownloadFile, mockResolveImage } =
   vi.hoisted(() => ({
@@ -122,4 +124,37 @@ describe('GET /api/files/public/[token]/inline', () => {
     expect(res.status).toBe(404)
     expect(mockDownloadFile).not.toHaveBeenCalled()
   })
+
+  it('bounds both reads: the doc scan tightly, the served image at the transfer ceiling', async () => {
+    await GET(req(`fileId=${FILE_ID}`), params)
+
+    const [docRead, imageRead] = mockDownloadFile.mock.calls.map(([args]) => args)
+    // The doc is scanned and discarded (and decoded to UTF-16 on top of the buffer),
+    // so it must not inherit the ceiling of a file this route actually serves.
+    expect(docRead.key).toBe(DOC_KEY)
+    expect(docRead.maxBytes).toBeGreaterThan(0)
+    expect(docRead.maxBytes).toBeLessThan(MAX_BUFFERED_TRANSFER_BYTES)
+    expect(imageRead.key).toBe(IMG_KEY)
+    expect(imageRead.maxBytes).toBe(MAX_BUFFERED_TRANSFER_BYTES)
+  })
+
+  it('fails the referenced-by-doc gate closed when the document is too large to scan', async () => {
+    mockDownloadFile.mockImplementation(({ key }: { key: string }) =>
+      key === DOC_KEY
+        ? Promise.reject(
+            new PayloadSizeLimitError({
+              label: 'storage download',
+              maxBytes: 10 * 1024 * 1024,
+              observedBytes: 5 * 1024 * 1024 * 1024,
+            })
+          )
+        : Promise.resolve(PNG)
+    )
+
+    const res = await GET(req(`fileId=${FILE_ID}`), params)
+
+    expect(res.status).toBe(404)
+    // The gate could not be verified, so the image must never be read at all.
+    expect(mockDownloadFile).toHaveBeenCalledTimes(1)
+  })
 })

apps/sim/app/api/files/public/[token]/inline/route.ts

@@ -6,6 +6,7 @@ import { getPublicInlineFileContract } from '@/lib/api/contracts/public-shares'
 import { parseRequest } from '@/lib/api/server'
 import { validateDeploymentAuth } from '@/lib/core/security/deployment-auth'
 import { generateRequestId } from '@/lib/core/utils/request'
+import { isPayloadSizeLimitError } from '@/lib/core/utils/stream-limits'
 import { withRouteHandler } from '@/lib/core/utils/with-route-handler'
 import { enforcePublicFileRateLimit } from '@/lib/public-shares/rate-limit'
 import { resolveActiveShareByToken } from '@/lib/public-shares/share-manager'
@@ -20,6 +21,17 @@ export const dynamic = 'force-dynamic'
 
 const logger = createLogger('PublicInlineFileAPI')
 
+/**
+ * Ceiling on the shared document read for the referenced-by-doc gate below.
+ *
+ * Far tighter than the ceiling on a file this route SERVES, because these bytes are
+ * never served — they are scanned for image references and discarded, and scanning
+ * decodes them to UTF-16 on top of the buffer, so the resident cost is roughly double
+ * the read. A share can point at any workspace file, admitted at 5 GB, and this route
+ * is anonymous; nothing a person writes as a document approaches even this bound.
+ */
+const MAX_INLINE_REF_SCAN_BYTES = 10 * 1024 * 1024
+
 /**
  * GET /api/files/public/[token]/inline?key=<cloudKey>|fileId=<id>
  *
@@ -72,7 +84,21 @@ export const GET = withRouteHandler(
       }
 
       // Referenced-by-doc gate: the share grants exactly the images the document embeds.
-      const docText = (await downloadFile({ key: doc.key, context: 'workspace' })).toString('utf-8')
+      // A document too large to scan fails the gate like any other unverifiable
+      // reference — the grant cannot be extended to an embed we were unable to confirm.
+      let docText: string
+      try {
+        const docBuffer = await downloadFile({
+          key: doc.key,
+          context: 'workspace',
+          maxBytes: MAX_INLINE_REF_SCAN_BYTES,
+        })
+        docText = docBuffer.toString('utf-8')
+      } catch (error) {
+        if (!isPayloadSizeLimitError(error)) throw error
+        logger.info('Shared document too large to scan for embedded references', { token })
+        throw new FileNotFoundError('Not found')
+      }
       const { keys, ids } = extractEmbeddedFileRefs(docText)
       const referenced = ref.fileId
         ? ids.some((id) => storedFileId(id) === ref.fileId)

apps/sim/app/api/files/serve-inline-image.ts

@@ -2,6 +2,7 @@ import { createLogger } from '@sim/logger'
 import type { NextResponse } from 'next/server'
 import { downloadFile } from '@/lib/uploads/core/storage-service'
 import type { ResolvedInlineImage } from '@/lib/uploads/server/inline-image'
+import { MAX_BUFFERED_TRANSFER_BYTES } from '@/lib/uploads/shared/types'
 import { sniffImageContentType } from '@/lib/uploads/utils/validation'
 import { createFileResponse, FileNotFoundError } from '@/app/api/files/utils'
 
@@ -25,7 +26,11 @@ export async function serveInlineImage(
   image: ResolvedInlineImage,
   { sniff }: { sniff: boolean }
 ): Promise<NextResponse> {
-  const buffer = await downloadFile({ key: image.key, context: 'workspace' })
+  const buffer = await downloadFile({
+    key: image.key,
+    context: 'workspace',
+    maxBytes: MAX_BUFFERED_TRANSFER_BYTES,
+  })
 
   let contentType = image.contentType
   if (sniff) {

apps/sim/app/api/files/serve/[...path]/route.test.ts

@@ -6,6 +6,7 @@
 import { hybridAuthMockFns, storageServiceMock, storageServiceMockFns } from '@sim/testing'
 import { NextRequest } from 'next/server'
 import { beforeEach, describe, expect, it, vi } from 'vitest'
+import { MAX_BUFFERED_TRANSFER_BYTES } from '@/lib/uploads/shared/types'
 
 vi.mock('@sim/logger', () => ({
   createLogger: vi.fn(() => serveLogger),
@@ -27,6 +28,7 @@ const {
   mockResolveServableDocBytes,
   mockGetContentType,
   mockFindLocalFile,
+  mockReadLocalFileWithinLimit,
   mockCreateFileResponse,
   mockCreateErrorResponse,
   FileNotFoundError,
@@ -52,6 +54,7 @@ const {
     mockResolveServableDocBytes: vi.fn(),
     mockGetContentType: vi.fn(),
     mockFindLocalFile: vi.fn(),
+    mockReadLocalFileWithinLimit: vi.fn(),
     mockCreateFileResponse: vi.fn(),
     mockCreateErrorResponse: vi.fn(),
     FileNotFoundError: FileNotFoundErrorClass,
@@ -119,6 +122,7 @@ vi.mock('@/app/api/files/utils', () => ({
   extractStorageKey: vi.fn().mockImplementation((path: string) => path.split('/').pop()),
   extractFilename: vi.fn().mockImplementation((path: string) => path.split('/').pop()),
   findLocalFile: mockFindLocalFile,
+  readLocalFileWithinLimit: mockReadLocalFileWithinLimit,
 }))
 
 import { GET } from '@/app/api/files/serve/[...path]/route'
@@ -162,6 +166,9 @@ describe('File Serve API Route', () => {
     )
     mockGetContentType.mockReturnValue('text/plain')
     mockFindLocalFile.mockReturnValue('/test/uploads/test-file.txt')
+    mockReadLocalFileWithinLimit.mockImplementation(async (filePath: string) =>
+      mockReadFile(filePath)
+    )
     mockCreateFileResponse.mockImplementation(
       (file: { buffer: Buffer; contentType: string; filename: string }) => {
         return new Response(file.buffer, {
@@ -181,6 +188,82 @@ describe('File Serve API Route', () => {
     })
   })
 
+  it('bounds every buffered read at the shared transfer ceiling', async () => {
+    mockIsUsingCloudStorage.mockReturnValue(true)
+    mockResolveStoredFileContext.mockResolvedValue('copilot')
+    mockInferContextFromKey.mockReturnValue('copilot')
+    mockDownloadCopilotFile.mockResolvedValue(Buffer.from('bytes'))
+
+    await GET(new NextRequest('http://localhost:3000/api/files/serve/copilot/doc.txt'), {
+      params: Promise.resolve({ path: ['copilot', 'doc.txt'] }),
+    })
+
+    expect(mockDownloadCopilotFile).toHaveBeenCalledWith('copilot/doc.txt', {
+      maxBytes: MAX_BUFFERED_TRANSFER_BYTES,
+    })
+  })
+
+  it('bounds the local read rather than trusting the stored size', async () => {
+    await GET(new NextRequest('http://localhost:3000/api/files/serve/workspace/ws/test-file.txt'), {
+      params: Promise.resolve({ path: ['workspace', 'ws', 'test-file.txt'] }),
+    })
+
+    expect(mockReadLocalFileWithinLimit).toHaveBeenCalledWith(
+      '/test/uploads/test-file.txt',
+      MAX_BUFFERED_TRANSFER_BYTES,
+      expect.any(String)
+    )
+  })
+
+  it('413s when a resolved document outgrows the ceiling its source fit inside', async () => {
+    // The stored source is a small generation script; the compiled artifact it
+    // resolves to is fetched separately and is what the response would carry.
+    mockResolveServableDocBytes.mockResolvedValue({
+      buffer: Buffer.alloc(MAX_BUFFERED_TRANSFER_BYTES + 1),
+      contentType: 'application/pdf',
+    })
+    mockCreateErrorResponse.mockImplementation(
+      (error: Error) =>
+        new Response(JSON.stringify({ error: error.name }), {
+          status: error.name === 'PayloadSizeLimitError' ? 413 : 500,
+        })
+    )
+
+    const response = await GET(
+      new NextRequest('http://localhost:3000/api/files/serve/workspace/ws/report.pdf'),
+      { params: Promise.resolve({ path: ['workspace', 'ws', 'report.pdf'] }) }
+    )
+
+    expect(response.status).toBe(413)
+  })
+
+  it('answers 413 rather than 500 when a file is too large to serve resident', async () => {
+    const { PayloadSizeLimitError } = await import('@/lib/core/utils/stream-limits')
+    mockReadLocalFileWithinLimit.mockRejectedValue(
+      new PayloadSizeLimitError({
+        label: 'served file',
+        maxBytes: MAX_BUFFERED_TRANSFER_BYTES,
+        observedBytes: MAX_BUFFERED_TRANSFER_BYTES + 1,
+      })
+    )
+    // The real createErrorResponse owns the status mapping; mirror it here so the
+    // route's own error path is what decides, not the mock's default 500.
+    mockCreateErrorResponse.mockImplementation(
+      (error: Error) =>
+        new Response(JSON.stringify({ error: error.name }), {
+          status: error.name === 'PayloadSizeLimitError' ? 413 : 500,
+        })
+    )
+
+    const response = await GET(
+      new NextRequest('http://localhost:3000/api/files/serve/workspace/ws/huge.bin'),
+      { params: Promise.resolve({ path: ['workspace', 'ws', 'huge.bin'] }) }
+    )
+
+    expect(response.status).toBe(413)
+    expect(serveLogger.error).not.toHaveBeenCalled()
+  })
+
   it('should serve local file successfully', async () => {
     const req = new NextRequest(
       'http://localhost:3000/api/files/serve/workspace/test-workspace-id/test-file.txt'
@@ -232,6 +315,7 @@ describe('File Serve API Route', () => {
     expect(storageServiceMockFns.mockDownloadFile).toHaveBeenCalledWith({
       key: 'workspace/test-workspace-id/1234567890-image.png',
       context: 'mothership',
+      maxBytes: MAX_BUFFERED_TRANSFER_BYTES,
     })
   })
 
@@ -318,6 +402,7 @@ describe('File Serve API Route', () => {
     expect(storageServiceMockFns.mockDownloadFile).toHaveBeenCalledWith({
       key: 'workspace/test-workspace-id/1234567890-photo.png',
       context: 'mothership',
+      maxBytes: MAX_BUFFERED_TRANSFER_BYTES,
     })
   })