Add security fixes: SHA256 hash validation and streaming file size enforcement

- Add field_validator to ResumableUploadInitRequest to validate expected_hash
  is a valid 64-character lowercase hex SHA256 hash (normalizes to lowercase)
- Add FileSizeExceededError exception for file size limit violations
- Enforce file size limits in storage layer during streaming (prevents
  Content-Length header spoofing)
- Add FileSizeExceededError handler in upload endpoint returning HTTP 413
- Add node_modules and frontend/dist to .gitignore

.gitignore

@@ -37,6 +37,10 @@ Thumbs.db
 # Build
 /build/
 /dist/
+frontend/dist/
+
+# Node
+node_modules/
 
 # Local config overrides
 config.local.yaml

backend/app/routes.py

@@ -28,6 +28,7 @@ from .storage import (
     MULTIPART_CHUNK_SIZE,
     StorageError,
     HashComputationError,
+    FileSizeExceededError,
     S3ExistenceCheckError,
     S3UploadError,
     S3StorageUnavailableError,
@@ -1033,6 +1034,12 @@ def upload_artifact(
             status_code=500,
             detail="Data integrity error detected. Please contact support.",
         )
+    except FileSizeExceededError as e:
+        logger.warning(f"File size exceeded during upload: {e}")
+        raise HTTPException(
+            status_code=413,
+            detail=f"File too large. Maximum size is {settings.max_file_size // (1024 * 1024 * 1024)}GB",
+        )
     except StorageError as e:
         logger.error(f"Storage error during upload: {e}")
         raise HTTPException(status_code=500, detail="Internal storage error")

backend/app/schemas.py

@@ -1,6 +1,6 @@
 from datetime import datetime
 from typing import Optional, List, Dict, Any, Generic, TypeVar
-from pydantic import BaseModel
+from pydantic import BaseModel, field_validator
 from uuid import UUID
 
 T = TypeVar("T")
@@ -266,6 +266,18 @@ class ResumableUploadInitRequest(BaseModel):
     size: int
     tag: Optional[str] = None
 
+    @field_validator("expected_hash")
+    @classmethod
+    def validate_sha256_hash(cls, v: str) -> str:
+        """Validate that expected_hash is a valid 64-character lowercase hex SHA256 hash."""
+        import re
+
+        if not re.match(r"^[a-f0-9]{64}$", v.lower()):
+            raise ValueError(
+                "expected_hash must be a valid 64-character lowercase hexadecimal SHA256 hash"
+            )
+        return v.lower()  # Normalize to lowercase
+
 
 class ResumableUploadInitResponse(BaseModel):
     """Response from initiating a resumable upload"""

backend/app/storage.py

@@ -176,6 +176,12 @@ class HashComputationError(StorageError):
     pass
 
 
+class FileSizeExceededError(StorageError):
+    """Raised when file exceeds maximum size during upload"""
+
+    pass
+
+
 class S3ExistenceCheckError(StorageError):
     """Raised when S3 existence check fails after retries"""
 
@@ -261,6 +267,7 @@ class S3Storage:
 
         Raises:
             HashComputationError: If hash computation fails
+            FileSizeExceededError: If file exceeds maximum size
             S3ExistenceCheckError: If S3 existence check fails after retries
             S3UploadError: If S3 upload fails
         """
@@ -270,11 +277,18 @@ class S3Storage:
             if not content:
                 raise HashComputationError("Empty file content")
 
+            size = len(content)
+
+            # Enforce file size limit (protection against Content-Length spoofing)
+            if size > settings.max_file_size:
+                raise FileSizeExceededError(
+                    f"File size {size} exceeds maximum {settings.max_file_size}"
+                )
+
             sha256_hash = hashlib.sha256(content).hexdigest()
             md5_hash = hashlib.md5(content).hexdigest()
             sha1_hash = hashlib.sha1(content).hexdigest()
-            size = len(content)
+        except (HashComputationError, FileSizeExceededError):
-        except HashComputationError:
             raise
         except Exception as e:
             logger.error(f"Hash computation failed: {e}")
@@ -349,6 +363,7 @@ class S3Storage:
 
         Raises:
             HashComputationError: If hash computation fails
+            FileSizeExceededError: If file exceeds maximum size
             S3ExistenceCheckError: If S3 existence check fails after retries
             S3UploadError: If S3 upload fails
         """
@@ -369,13 +384,19 @@ class S3Storage:
                 sha1_hasher.update(chunk)
                 size += len(chunk)
 
+                # Enforce file size limit during streaming (protection against spoofing)
+                if size > settings.max_file_size:
+                    raise FileSizeExceededError(
+                        f"File size exceeds maximum {settings.max_file_size}"
+                    )
+
             if size == 0:
                 raise HashComputationError("Empty file content")
 
             sha256_hash = sha256_hasher.hexdigest()
             md5_hash = md5_hasher.hexdigest()
             sha1_hash = sha1_hasher.hexdigest()
-        except HashComputationError:
+        except (HashComputationError, FileSizeExceededError):
             raise
         except Exception as e:
             logger.error(f"Hash computation failed for multipart upload: {e}")