ai comments fixes

Author: Subash-Mohan

backend/onyx/access/access.py

@@ -1,6 +1,7 @@
 from collections.abc import Callable
 from typing import cast
 
+from sqlalchemy.orm import joinedload
 from sqlalchemy.orm import Session
 
 from onyx.access.models import DocumentAccess
@@ -131,7 +132,12 @@ def get_access_for_user_files(
     user_file_ids: list[str],
     db_session: Session,
 ) -> dict[str, DocumentAccess]:
-    user_files = db_session.query(UserFile).filter(UserFile.id.in_(user_file_ids)).all()
+    user_files = (
+        db_session.query(UserFile)
+        .options(joinedload(UserFile.user))  # Eager load the user relationship
+        .filter(UserFile.id.in_(user_file_ids))
+        .all()
+    )
     return {
         str(user_file.id): DocumentAccess.build(
             user_emails=[user_file.user.email] if user_file.user else [],

backend/onyx/background/celery/tasks/user_file_processing/tasks.py

@@ -107,7 +107,7 @@ def check_user_file_processing(self: Task, *, tenant_id: str) -> None:
             for user_file_id in user_file_ids:
                 self.app.send_task(
                     OnyxCeleryTask.PROCESS_SINGLE_USER_FILE,
-                    kwargs={"user_file_id": user_file_id, "tenant_id": tenant_id},
+                    kwargs={"user_file_id": str(user_file_id), "tenant_id": tenant_id},
                     queue=OnyxCeleryQueues.USER_FILE_PROCESSING,
                     priority=OnyxCeleryPriority.HIGH,
                 )
@@ -247,7 +247,7 @@ def process_single_user_file(self: Task, *, user_file_id: str, tenant_id: str) -
 
             except Exception as e:
                 task_logger.exception(
-                    f"process_single_user_file - Error id={user_file_id}: {e}"
+                    f"process_single_user_file - Error processing file id={user_file_id} - {e.__class__.__name__}"
                 )
                 uf.status = UserFileStatus.FAILED
                 db_session.add(uf)
@@ -269,7 +269,7 @@ def process_single_user_file(self: Task, *, user_file_id: str, tenant_id: str) -
                 db_session.commit()
 
         task_logger.exception(
-            f"process_single_user_file - Error id={user_file_id}: {e}"
+            f"process_single_user_file - Error processing file id={user_file_id} - {e.__class__.__name__}"
         )
         return None
     finally:
@@ -313,7 +313,7 @@ def check_for_user_file_project_sync(self: Task, *, tenant_id: str) -> None:
             for user_file_id in user_file_ids:
                 self.app.send_task(
                     OnyxCeleryTask.PROCESS_SINGLE_USER_FILE_PROJECT_SYNC,
-                    kwargs={"user_file_id": user_file_id, "tenant_id": tenant_id},
+                    kwargs={"user_file_id": str(user_file_id), "tenant_id": tenant_id},
                     queue=OnyxCeleryQueues.USER_FILE_PROJECT_SYNC,
                     priority=OnyxCeleryPriority.HIGH,
                 )
@@ -392,7 +392,7 @@ def process_single_user_file_project_sync(
 
     except Exception as e:
         task_logger.exception(
-            f"process_single_user_file_project_sync - Error id={user_file_id}: {e}"
+            f"process_single_user_file_project_sync - Error syncing project for file id={user_file_id} - {e.__class__.__name__}"
         )
         return None
     finally:
@@ -529,7 +529,7 @@ def user_file_docid_migration_task(self: Task, *, tenant_id: str) -> bool:
                         user_project_ids = [project.id for project in uf.projects]
                 except Exception as e:
                     task_logger.warning(
-                        f"Tenant={tenant_id} failed fetching projects for doc_id={new_uuid}: {e}"
+                        f"Tenant={tenant_id} failed fetching projects for doc_id={new_uuid} - {e.__class__.__name__}"
                     )
                 try:
                     _update_document_id_in_vespa(
@@ -540,7 +540,7 @@ def user_file_docid_migration_task(self: Task, *, tenant_id: str) -> bool:
                     )
                 except Exception as e:
                     task_logger.warning(
-                        f"Tenant={tenant_id} failed Vespa update for {old_doc_id} -> {new_uuid}: {e}"
+                        f"Tenant={tenant_id} failed Vespa update for doc_id={new_uuid} - {e.__class__.__name__}"
                     )
 
             # Update search_doc records to refer to the UUID string
@@ -627,7 +627,8 @@ def user_file_docid_migration_task(self: Task, *, tenant_id: str) -> bool:
                             normalized += 1
                         except Exception as e:
                             task_logger.warning(
-                                f"Tenant={tenant_id} failed plaintext object normalize for id={fr.file_id}: {e}"
+                                f"Tenant={tenant_id} failed plaintext object normalize for "
+                                f"id={fr.file_id} - {e.__class__.__name__}"
                             )
 
                     if normalized:
@@ -641,7 +642,7 @@ def user_file_docid_migration_task(self: Task, *, tenant_id: str) -> bool:
                     )
             except Exception:
                 task_logger.exception(
-                    f"user_file_docid_migration_task encountered an error during plaintext normalization for tenant={tenant_id}"
+                    f"user_file_docid_migration_task - Error during plaintext normalization for tenant={tenant_id}"
                 )
 
         task_logger.info(
@@ -650,6 +651,6 @@ def user_file_docid_migration_task(self: Task, *, tenant_id: str) -> bool:
         return True
     except Exception:
         task_logger.exception(
-            f"user_file_docid_migration_task encountered an error for tenant={tenant_id}"
+            f"user_file_docid_migration_task - Error during execution for tenant={tenant_id}"
         )
         return False

backend/onyx/configs/constants.py

@@ -304,6 +304,7 @@ class FileOrigin(str, Enum):
     PLAINTEXT_CACHE = "plaintext_cache"
     OTHER = "other"
     QUERY_HISTORY_CSV = "query_history_csv"
+    USER_FILE = "user_file"
 
 
 class FileType(str, Enum):

backend/onyx/db/chat.py

@@ -170,7 +170,7 @@ def get_chat_sessions_by_user(
     db_session: Session,
     include_onyxbot_flows: bool = False,
     limit: int = 50,
-    project_id: UUID | None = None,
+    project_id: int | None = None,
     only_non_project_chats: bool = False,
 ) -> list[ChatSession]:
     stmt = select(ChatSession).where(ChatSession.user_id == user_id)

backend/onyx/db/models.py

@@ -3271,7 +3271,7 @@ class UserDocument(str, Enum):
 class UserFile(Base):
     __tablename__ = "user_file"
 
-    id: Mapped[UUID] = mapped_column(PGUUID, primary_key=True)
+    id: Mapped[UUID] = mapped_column(PGUUID(as_uuid=True), primary_key=True)
     user_id: Mapped[UUID | None] = mapped_column(ForeignKey("user.id"), nullable=False)
     assistants: Mapped[list["Persona"]] = relationship(
         "Persona",

backend/onyx/db/projects.py

@@ -3,12 +3,14 @@
 from typing import List
 from uuid import UUID
 
+from fastapi import HTTPException
 from fastapi import UploadFile
 from pydantic import BaseModel
 from pydantic import ConfigDict
 from sqlalchemy.orm import Session
 
 from onyx.background.celery.versioned_apps.client import app as client_app
+from onyx.configs.constants import FileOrigin
 from onyx.configs.constants import OnyxCeleryPriority
 from onyx.configs.constants import OnyxCeleryQueues
 from onyx.configs.constants import OnyxCeleryTask
@@ -44,7 +46,7 @@ def create_user_files(
     categorized_files = categorize_uploaded_files(files)
     # NOTE: At the moment, zip metadata is not used for user files.
     # Should revisit to decide whether this should be a feature.
-    upload_response = upload_files(categorized_files.acceptable)
+    upload_response = upload_files(categorized_files.acceptable, FileOrigin.USER_FILE)
     user_files = []
     non_accepted_files = categorized_files.non_accepted
     unsupported_files = categorized_files.unsupported
@@ -92,6 +94,11 @@ def upload_files_to_user_files_with_indexing(
     user: User | None,
     db_session: Session,
 ) -> CategorizedFilesResult:
+    # Validate project ownership if a project_id is provided
+    if project_id is not None and user is not None:
+        if not check_project_ownership(project_id, user.id, db_session):
+            raise HTTPException(status_code=404, detail="Project not found")
+
     categorized_files_result = create_user_files(files, project_id, user, db_session)
     user_files = categorized_files_result.user_files
     non_accepted_files = categorized_files_result.non_accepted_files

backend/onyx/server/features/projects/api.py

@@ -81,8 +81,11 @@ def upload_user_files(
         return CategorizedFilesSnapshot.from_result(categorized_files_result)
 
     except Exception as e:
-        logger.error(f"Error uploading files: {str(e)}")
-        raise HTTPException(status_code=500, detail=f"Failed to upload files: {str(e)}")
+        logger.error(f"Error uploading files - type: {type(e).__name__}")
+        raise HTTPException(
+            status_code=500,
+            detail="Failed to upload files. Please try again or contact support if the issue persists.",
+        )
 
 
 @router.get("/{project_id}")

backend/onyx/server/features/projects/projects_file_utils.py

@@ -19,6 +19,16 @@
 
 logger = setup_logger()
 FILE_TOKEN_COUNT_THRESHOLD = 50000
+UNKNOWN_FILENAME = "[unknown_file]"  # More descriptive than empty string
+
+
+def get_safe_filename(upload: UploadFile) -> str:
+    """Get filename from upload, with fallback to UNKNOWN_FILENAME if None."""
+    if not upload.filename:
+        logger.warning("Received upload with no filename")
+        return UNKNOWN_FILENAME
+    return upload.filename
+
 
 # Guard against extremely large images
 Image.MAX_IMAGE_PIXELS = 12000 * 12000
@@ -118,23 +128,25 @@ def categorize_uploaded_files(files: list[UploadFile]) -> CategorizedFiles:
 
     for upload in files:
         try:
-            extension = get_file_ext(upload.filename or "")
+            filename = get_safe_filename(upload)
+            extension = get_file_ext(filename)
 
             # If image, estimate tokens via dedicated method first
             if extension in ACCEPTED_IMAGE_FILE_EXTENSIONS:
                 try:
                     token_count = estimate_image_tokens_for_upload(upload)
-                except (UnidentifiedImageError, OSError):
-                    results.unsupported.append(upload.filename or "")
+                except (UnidentifiedImageError, OSError) as e:
+                    logger.warning(
+                        f"Failed to process image file '{filename}': {str(e)}"
+                    )
+                    results.unsupported.append(filename)
                     continue
 
                 if token_count > FILE_TOKEN_COUNT_THRESHOLD:
-                    results.non_accepted.append(upload.filename or "")
+                    results.non_accepted.append(filename)
                 else:
                     results.acceptable.append(upload)
-                    results.acceptable_file_to_token_count[upload.filename or ""] = (
-                        token_count
-                    )
+                    results.acceptable_file_to_token_count[filename] = token_count
                 continue
 
             # Otherwise, handle as text/document: extract text and count tokens
@@ -144,35 +156,40 @@ def categorize_uploaded_files(files: list[UploadFile]) -> CategorizedFiles:
             ):
                 text_content = extract_file_text(
                     file=upload.file,
-                    file_name=upload.filename or "",
+                    file_name=filename,
                     break_on_unprocessable=False,
                     extension=extension,
                 )
                 if not text_content:
-                    results.unsupported.append(upload.filename or "")
+                    logger.warning(f"No text content extracted from '{filename}'")
+                    results.unsupported.append(filename)
                     continue
 
                 token_count = len(tokenizer.encode(text_content))
                 if token_count > FILE_TOKEN_COUNT_THRESHOLD:
-                    results.non_accepted.append(upload.filename or "")
+                    results.non_accepted.append(filename)
                 else:
                     results.acceptable.append(upload)
-                    results.acceptable_file_to_token_count[upload.filename or ""] = (
-                        token_count
-                    )
+                    results.acceptable_file_to_token_count[filename] = token_count
+
                 # Reset file pointer for subsequent upload handling
                 try:
                     upload.file.seek(0)
-                except Exception:
-                    pass
+                except Exception as e:
+                    logger.warning(
+                        f"Failed to reset file pointer for '{filename}': {str(e)}"
+                    )
                 continue
 
             # If not recognized as supported types above, mark unsupported
-            results.unsupported.append(upload.filename or "")
+            logger.warning(
+                f"Unsupported file extension '{extension}' for file '{filename}'"
+            )
+            results.unsupported.append(filename)
         except Exception as e:
             logger.warning(
-                f"Failed to process uploaded file '{getattr(upload, 'filename', 'unknown')}': {e}"
+                f"Failed to process uploaded file '{get_safe_filename(upload)}' (error_type={type(e).__name__}, error={str(e)})"
             )
-            results.unsupported.append(upload.filename or "")
+            results.unsupported.append(get_safe_filename(upload))
 
     return results

backend/onyx/server/query_and_chat/chat_backend.py

@@ -99,7 +99,7 @@
 def get_user_chat_sessions(
     user: User | None = Depends(current_user),
     db_session: Session = Depends(get_session),
-    project_id: UUID | None = None,
+    project_id: int | None = None,
     only_non_project_chats: bool = True,
 ) -> ChatSessionsResponse:
     user_id = user.id if user is not None else None

web/src/app/chat/components/input/ChatInputBar.tsx

@@ -291,8 +291,6 @@ export const ChatInputBar = React.memo(function ChatInputBar({
       );
       const totalTokens =
         (currentSessionFileTokenCount || 0) + currentFilesTokenTotal;
-      console.log("totalTokens", totalTokens);
-      console.log("availableContextTokens", availableContextTokens);
       // Hide processing state when files are within context limits
       return totalTokens < availableContextTokens;
     }