fix: upgrade OpenTelemetry packages from 0.48b0 to 0.49b0

Fixes "Failed to detach context" error in production by upgrading to OTEL 0.49b0,
which includes None token guards in Celery instrumentor (PR opentelemetry-python-contrib#2927).

Package Updates:
- OTEL instrumentation: 0.48b0 → 0.49b0
- OTEL SDK/API: 1.27.0 → 1.28.0
- protobuf: 4.25.8 → 5.29.6 (required by opentelemetry-proto 1.28.0)
- Google Cloud packages upgraded for protobuf 5.x compatibility:
  - google-api-core: 2.18.0 → 2.19.1+
  - google-auth: 2.29.0 → 2.47.0+
  - google-cloud-aiplatform: 1.49.0 → 1.123.0+
  - googleapis-common-protos: 1.63.0 → 1.65.0+
  - google-cloud-storage: 2.16.0 → 3.0.0+
- httpx: 0.27.0 → 0.28.0 (required by google-genai 1.37+)

Also removed duplicate opentelemetry-instrumentation-httpx entry in pyproject.toml.

api/commands.py

@@ -30,6 +30,7 @@ from extensions.ext_redis import redis_client
 from extensions.ext_storage import storage
 from extensions.storage.opendal_storage import OpenDALStorage
 from extensions.storage.storage_type import StorageType
+from libs.db_migration_lock import DbMigrationAutoRenewLock
 from libs.helper import email as email_validate
 from libs.password import hash_password, password_pattern, valid_password
 from libs.rsa import generate_key_pair
@@ -54,6 +55,8 @@ from tasks.remove_app_and_related_data_task import delete_draft_variables_batch
 
 logger = logging.getLogger(__name__)
 
+DB_UPGRADE_LOCK_TTL_SECONDS = 60
+
 
 @click.command("reset-password", help="Reset the account password.")
 @click.option("--email", prompt=True, help="Account email to reset password for")
@@ -727,8 +730,15 @@ def create_tenant(email: str, language: str | None = None, name: str | None = No
 @click.command("upgrade-db", help="Upgrade the database")
 def upgrade_db():
     click.echo("Preparing database migration...")
-    lock = redis_client.lock(name="db_upgrade_lock", timeout=60)
+    lock = DbMigrationAutoRenewLock(
+        redis_client=redis_client,
+        name="db_upgrade_lock",
+        ttl_seconds=DB_UPGRADE_LOCK_TTL_SECONDS,
+        logger=logger,
+        log_context="db_migration",
+    )
     if lock.acquire(blocking=False):
+        migration_succeeded = False
         try:
             click.echo(click.style("Starting database migration.", fg="green"))
 
@@ -737,12 +747,16 @@ def upgrade_db():
 
             flask_migrate.upgrade()
 
+            migration_succeeded = True
             click.echo(click.style("Database migration successful!", fg="green"))
 
-        except Exception:
+        except Exception as e:
             logger.exception("Failed to execute database migration")
+            click.echo(click.style(f"Database migration failed: {e}", fg="red"))
+            raise SystemExit(1)
         finally:
-            lock.release()
+            status = "successful" if migration_succeeded else "failed"
+            lock.release_safely(status=status)
     else:
         click.echo("Database migration skipped")
 

api/controllers/console/app/app.py

@@ -1,3 +1,4 @@
+import logging
 import uuid
 from datetime import datetime
 from typing import Any, Literal, TypeAlias
@@ -54,6 +55,8 @@ ALLOW_CREATE_APP_MODES = ["chat", "agent-chat", "advanced-chat", "workflow", "co
 
 register_enum_models(console_ns, IconType)
 
+_logger = logging.getLogger(__name__)
+
 
 class AppListQuery(BaseModel):
     page: int = Field(default=1, ge=1, le=99999, description="Page number (1-99999)")
@@ -499,6 +502,7 @@ class AppListApi(Resource):
                     select(Workflow).where(
                         Workflow.version == Workflow.VERSION_DRAFT,
                         Workflow.app_id.in_(workflow_capable_app_ids),
+                        Workflow.tenant_id == current_tenant_id,
                     )
                 )
                 .scalars()
@@ -510,12 +514,14 @@ class AppListApi(Resource):
                 NodeType.TRIGGER_PLUGIN,
             }
             for workflow in draft_workflows:
+                node_id = None
                 try:
-                    for _, node_data in workflow.walk_nodes():
+                    for node_id, node_data in workflow.walk_nodes():
                         if node_data.get("type") in trigger_node_types:
                             draft_trigger_app_ids.add(str(workflow.app_id))
                             break
                 except Exception:
+                    _logger.exception("error while walking nodes, workflow_id=%s, node_id=%s", workflow.id, node_id)
                     continue
 
         for app in app_pagination.items:
@@ -654,6 +660,19 @@ class AppCopyApi(Resource):
             )
             session.commit()
 
+            # Inherit web app permission from original app
+            if result.app_id and FeatureService.get_system_features().webapp_auth.enabled:
+                try:
+                    # Get the original app's access mode
+                    original_settings = EnterpriseService.WebAppAuth.get_app_access_mode_by_id(app_model.id)
+                    access_mode = original_settings.access_mode
+                except Exception:
+                    # If original app has no settings (old app), default to public to match fallback behavior
+                    access_mode = "public"
+
+                # Apply the same access mode to the copied app
+                EnterpriseService.WebAppAuth.update_app_access_mode(result.app_id, access_mode)
+
             stmt = select(App).where(App.id == result.app_id)
             app = session.scalar(stmt)
 

api/controllers/console/workspace/tool_providers.py

@@ -878,7 +878,11 @@ class ToolBuiltinProviderSetDefaultApi(Resource):
         current_user, current_tenant_id = current_account_with_tenant()
         payload = BuiltinProviderDefaultCredentialPayload.model_validate(console_ns.payload or {})
         return BuiltinToolManageService.set_default_provider(
-            tenant_id=current_tenant_id, user_id=current_user.id, provider=provider, id=payload.id
+            tenant_id=current_tenant_id,
+            user_id=current_user.id,
+            provider=provider,
+            id=args["id"],
+            account=current_user,
         )
 
 

api/core/app/task_pipeline/easy_ui_based_generate_task_pipeline.py

@@ -45,6 +45,8 @@ from core.app.entities.task_entities import (
 from core.app.task_pipeline.based_generate_task_pipeline import BasedGenerateTaskPipeline
 from core.app.task_pipeline.message_cycle_manager import MessageCycleManager
 from core.base.tts import AppGeneratorTTSPublisher, AudioTrunk
+from core.file import helpers as file_helpers
+from core.file.enums import FileTransferMethod
 from core.model_manager import ModelInstance
 from core.model_runtime.entities.llm_entities import LLMResult, LLMResultChunk, LLMResultChunkDelta, LLMUsage
 from core.model_runtime.entities.message_entities import (
@@ -56,10 +58,11 @@ from core.ops.entities.trace_entity import TraceTaskName
 from core.ops.ops_trace_manager import TraceQueueManager, TraceTask
 from core.prompt.utils.prompt_message_util import PromptMessageUtil
 from core.prompt.utils.prompt_template_parser import PromptTemplateParser
+from core.tools.signature import sign_tool_file
 from events.message_event import message_was_created
 from extensions.ext_database import db
 from libs.datetime_utils import naive_utc_now
-from models.model import AppMode, Conversation, Message, MessageAgentThought
+from models.model import AppMode, Conversation, Message, MessageAgentThought, MessageFile, UploadFile
 
 logger = logging.getLogger(__name__)
 
@@ -463,6 +466,85 @@ class EasyUIBasedGenerateTaskPipeline(BasedGenerateTaskPipeline):
             metadata=metadata_dict,
         )
 
+    def _record_files(self):
+        with Session(db.engine, expire_on_commit=False) as session:
+            message_files = session.scalars(select(MessageFile).where(MessageFile.message_id == self._message_id)).all()
+            if not message_files:
+                return None
+
+            files_list = []
+            upload_file_ids = [
+                mf.upload_file_id
+                for mf in message_files
+                if mf.transfer_method == FileTransferMethod.LOCAL_FILE and mf.upload_file_id
+            ]
+            upload_files_map = {}
+            if upload_file_ids:
+                upload_files = session.scalars(select(UploadFile).where(UploadFile.id.in_(upload_file_ids))).all()
+                upload_files_map = {uf.id: uf for uf in upload_files}
+
+            for message_file in message_files:
+                upload_file = None
+                if message_file.transfer_method == FileTransferMethod.LOCAL_FILE and message_file.upload_file_id:
+                    upload_file = upload_files_map.get(message_file.upload_file_id)
+
+                url = None
+                filename = "file"
+                mime_type = "application/octet-stream"
+                size = 0
+                extension = ""
+
+                if message_file.transfer_method == FileTransferMethod.REMOTE_URL:
+                    url = message_file.url
+                    if message_file.url:
+                        filename = message_file.url.split("/")[-1].split("?")[0]  # Remove query params
+                elif message_file.transfer_method == FileTransferMethod.LOCAL_FILE:
+                    if upload_file:
+                        url = file_helpers.get_signed_file_url(upload_file_id=str(upload_file.id))
+                        filename = upload_file.name
+                        mime_type = upload_file.mime_type or "application/octet-stream"
+                        size = upload_file.size or 0
+                        extension = f".{upload_file.extension}" if upload_file.extension else ""
+                    elif message_file.upload_file_id:
+                        # Fallback: generate URL even if upload_file not found
+                        url = file_helpers.get_signed_file_url(upload_file_id=str(message_file.upload_file_id))
+                elif message_file.transfer_method == FileTransferMethod.TOOL_FILE and message_file.url:
+                    # For tool files, use URL directly if it's HTTP, otherwise sign it
+                    if message_file.url.startswith("http"):
+                        url = message_file.url
+                        filename = message_file.url.split("/")[-1].split("?")[0]
+                    else:
+                        # Extract tool file id and extension from URL
+                        url_parts = message_file.url.split("/")
+                        if url_parts:
+                            file_part = url_parts[-1].split("?")[0]  # Remove query params first
+                            # Use rsplit to correctly handle filenames with multiple dots
+                            if "." in file_part:
+                                tool_file_id, ext = file_part.rsplit(".", 1)
+                                extension = f".{ext}"
+                            else:
+                                tool_file_id = file_part
+                                extension = ".bin"
+                            url = sign_tool_file(tool_file_id=tool_file_id, extension=extension)
+                            filename = file_part
+
+                transfer_method_value = message_file.transfer_method
+                remote_url = message_file.url if message_file.transfer_method == FileTransferMethod.REMOTE_URL else ""
+                file_dict = {
+                    "related_id": message_file.id,
+                    "extension": extension,
+                    "filename": filename,
+                    "size": size,
+                    "mime_type": mime_type,
+                    "transfer_method": transfer_method_value,
+                    "type": message_file.type,
+                    "url": url or "",
+                    "upload_file_id": message_file.upload_file_id or message_file.id,
+                    "remote_url": remote_url,
+                }
+                files_list.append(file_dict)
+            return files_list or None
+
     def _agent_message_to_stream_response(self, answer: str, message_id: str) -> AgentMessageStreamResponse:
         """
         Agent message to stream response.

api/core/app/task_pipeline/message_cycle_manager.py

@@ -64,7 +64,13 @@ class MessageCycleManager:
 
         # Use SQLAlchemy 2.x style session.scalar(select(...))
         with session_factory.create_session() as session:
-            message_file = session.scalar(select(MessageFile).where(MessageFile.message_id == message_id))
+            message_file = session.scalar(
+                select(MessageFile)
+                .where(
+                    MessageFile.message_id == message_id,
+                )
+                .where(MessageFile.belongs_to == "assistant")
+            )
 
         if message_file:
             self._message_has_file.add(message_id)

api/libs/db_migration_lock.py

@@ -0,0 +1,213 @@
+"""
+DB migration Redis lock with heartbeat renewal.
+
+This is intentionally migration-specific. Background renewal is a trade-off that makes sense
+for unbounded, blocking operations like DB migrations (DDL/DML) where the main thread cannot
+periodically refresh the lock TTL.
+
+Do NOT use this as a general-purpose lock primitive for normal application code. Prefer explicit
+lock lifecycle management (e.g. redis-py Lock context manager + `extend()` / `reacquire()` from
+the same thread) when execution flow is under control.
+"""
+
+from __future__ import annotations
+
+import logging
+import threading
+from typing import Any
+
+from redis.exceptions import LockNotOwnedError, RedisError
+
+logger = logging.getLogger(__name__)
+
+MIN_RENEW_INTERVAL_SECONDS = 0.1
+DEFAULT_RENEW_INTERVAL_DIVISOR = 3
+MIN_JOIN_TIMEOUT_SECONDS = 0.5
+MAX_JOIN_TIMEOUT_SECONDS = 5.0
+JOIN_TIMEOUT_MULTIPLIER = 2.0
+
+
+class DbMigrationAutoRenewLock:
+    """
+    Redis lock wrapper that automatically renews TTL while held (migration-only).
+
+    Notes:
+    - We force `thread_local=False` when creating the underlying redis-py lock, because the
+      lock token must be accessible from the heartbeat thread for `reacquire()` to work.
+    - `release_safely()` is best-effort: it never raises, so it won't mask the caller's
+      primary error/exit code.
+    """
+
+    _redis_client: Any
+    _name: str
+    _ttl_seconds: float
+    _renew_interval_seconds: float
+    _log_context: str | None
+    _logger: logging.Logger
+
+    _lock: Any
+    _stop_event: threading.Event | None
+    _thread: threading.Thread | None
+    _acquired: bool
+
+    def __init__(
+        self,
+        redis_client: Any,
+        name: str,
+        ttl_seconds: float = 60,
+        renew_interval_seconds: float | None = None,
+        *,
+        logger: logging.Logger | None = None,
+        log_context: str | None = None,
+    ) -> None:
+        self._redis_client = redis_client
+        self._name = name
+        self._ttl_seconds = float(ttl_seconds)
+        self._renew_interval_seconds = (
+            float(renew_interval_seconds)
+            if renew_interval_seconds is not None
+            else max(MIN_RENEW_INTERVAL_SECONDS, self._ttl_seconds / DEFAULT_RENEW_INTERVAL_DIVISOR)
+        )
+        self._logger = logger or logging.getLogger(__name__)
+        self._log_context = log_context
+
+        self._lock = None
+        self._stop_event = None
+        self._thread = None
+        self._acquired = False
+
+    @property
+    def name(self) -> str:
+        return self._name
+
+    def acquire(self, *args: Any, **kwargs: Any) -> bool:
+        """
+        Acquire the lock and start heartbeat renewal on success.
+
+        Accepts the same args/kwargs as redis-py `Lock.acquire()`.
+        """
+        # Prevent accidental double-acquire which could leave the previous heartbeat thread running.
+        if self._acquired:
+            raise RuntimeError("DB migration lock is already acquired; call release_safely() before acquiring again.")
+
+        # Reuse the lock object if we already created one.
+        if self._lock is None:
+            self._lock = self._redis_client.lock(
+                name=self._name,
+                timeout=self._ttl_seconds,
+                thread_local=False,
+            )
+        acquired = bool(self._lock.acquire(*args, **kwargs))
+        self._acquired = acquired
+        if acquired:
+            self._start_heartbeat()
+        return acquired
+
+    def owned(self) -> bool:
+        if self._lock is None:
+            return False
+        try:
+            return bool(self._lock.owned())
+        except Exception:
+            # Ownership checks are best-effort and must not break callers.
+            return False
+
+    def _start_heartbeat(self) -> None:
+        if self._lock is None:
+            return
+        if self._stop_event is not None:
+            return
+
+        self._stop_event = threading.Event()
+        self._thread = threading.Thread(
+            target=self._heartbeat_loop,
+            args=(self._lock, self._stop_event),
+            daemon=True,
+            name=f"DbMigrationAutoRenewLock({self._name})",
+        )
+        self._thread.start()
+
+    def _heartbeat_loop(self, lock: Any, stop_event: threading.Event) -> None:
+        while not stop_event.wait(self._renew_interval_seconds):
+            try:
+                lock.reacquire()
+            except LockNotOwnedError:
+                self._logger.warning(
+                    "DB migration lock is no longer owned during heartbeat; stop renewing. log_context=%s",
+                    self._log_context,
+                    exc_info=True,
+                )
+                return
+            except RedisError:
+                self._logger.warning(
+                    "Failed to renew DB migration lock due to Redis error; will retry. log_context=%s",
+                    self._log_context,
+                    exc_info=True,
+                )
+            except Exception:
+                self._logger.warning(
+                    "Unexpected error while renewing DB migration lock; will retry. log_context=%s",
+                    self._log_context,
+                    exc_info=True,
+                )
+
+    def release_safely(self, *, status: str | None = None) -> None:
+        """
+        Stop heartbeat and release lock. Never raises.
+
+        Args:
+            status: Optional caller-provided status (e.g. 'successful'/'failed') to add context to logs.
+        """
+        lock = self._lock
+        if lock is None:
+            return
+
+        self._stop_heartbeat()
+
+        # Lock release errors should never mask the real error/exit code.
+        try:
+            lock.release()
+        except LockNotOwnedError:
+            self._logger.warning(
+                "DB migration lock not owned on release; ignoring. status=%s log_context=%s",
+                status,
+                self._log_context,
+                exc_info=True,
+            )
+        except RedisError:
+            self._logger.warning(
+                "Failed to release DB migration lock due to Redis error; ignoring. status=%s log_context=%s",
+                status,
+                self._log_context,
+                exc_info=True,
+            )
+        except Exception:
+            self._logger.warning(
+                "Unexpected error while releasing DB migration lock; ignoring. status=%s log_context=%s",
+                status,
+                self._log_context,
+                exc_info=True,
+            )
+        finally:
+            self._acquired = False
+            self._lock = None
+
+    def _stop_heartbeat(self) -> None:
+        if self._stop_event is None:
+            return
+        self._stop_event.set()
+        if self._thread is not None:
+            # Best-effort join: if Redis calls are blocked, the daemon thread may remain alive.
+            join_timeout_seconds = max(
+                MIN_JOIN_TIMEOUT_SECONDS,
+                min(MAX_JOIN_TIMEOUT_SECONDS, self._renew_interval_seconds * JOIN_TIMEOUT_MULTIPLIER),
+            )
+            self._thread.join(timeout=join_timeout_seconds)
+            if self._thread.is_alive():
+                self._logger.warning(
+                    "DB migration lock heartbeat thread did not stop within %.2fs; ignoring. log_context=%s",
+                    join_timeout_seconds,
+                    self._log_context,
+                )
+        self._stop_event = None
+        self._thread = None

api/migrations/versions/2025_12_25_1039-7df29de0f6be_add_credit_pool.py

@@ -8,7 +8,6 @@ Create Date: 2025-12-25 10:39:15.139304
 from alembic import op
 import models as models
 import sqlalchemy as sa
-from sqlalchemy.dialects import postgresql
 
 # revision identifiers, used by Alembic.
 revision = '7df29de0f6be'
@@ -20,7 +19,7 @@ depends_on = None
 def upgrade():
     # ### commands auto generated by Alembic - please adjust! ###
     op.create_table('tenant_credit_pools',
-    sa.Column('id', models.types.StringUUID(), server_default=sa.text('uuid_generate_v4()'), nullable=False),
+    sa.Column('id', models.types.StringUUID(), nullable=False),
     sa.Column('tenant_id', models.types.StringUUID(), nullable=False),
     sa.Column('pool_type', sa.String(length=40), server_default='trial', nullable=False),
     sa.Column('quota_limit', sa.BigInteger(), nullable=False),

api/migrations/versions/2026_01_17_1110-f9f6d18a37f9_add_table_explore_banner_and_trial.py

@@ -8,7 +8,6 @@ Create Date: 2026-01-017 11:10:18.079355
 from alembic import op
 import models as models
 import sqlalchemy as sa
-from sqlalchemy.dialects import postgresql
 
 # revision identifiers, used by Alembic.
 revision = 'f9f6d18a37f9'
@@ -20,7 +19,7 @@ depends_on = None
 def upgrade():
     # ### commands auto generated by Alembic - please adjust! ###
     op.create_table('account_trial_app_records',
-    sa.Column('id', models.types.StringUUID(), server_default=sa.text('uuid_generate_v4()'), nullable=False),
+    sa.Column('id', models.types.StringUUID(), nullable=False),
     sa.Column('account_id', models.types.StringUUID(), nullable=False),
     sa.Column('app_id', models.types.StringUUID(), nullable=False),
     sa.Column('count', sa.Integer(), nullable=False),
@@ -33,17 +32,17 @@ def upgrade():
         batch_op.create_index('account_trial_app_record_app_id_idx', ['app_id'], unique=False)
 
     op.create_table('exporle_banners',
-    sa.Column('id', models.types.StringUUID(), server_default=sa.text('uuid_generate_v4()'), nullable=False),
+    sa.Column('id', models.types.StringUUID(), nullable=False),
     sa.Column('content', sa.JSON(), nullable=False),
     sa.Column('link', sa.String(length=255), nullable=False),
     sa.Column('sort', sa.Integer(), nullable=False),
-    sa.Column('status', sa.String(length=255), server_default=sa.text("'enabled'::character varying"), nullable=False),
+    sa.Column('status', sa.String(length=255), server_default='enabled', nullable=False),
     sa.Column('created_at', sa.DateTime(), server_default=sa.text('CURRENT_TIMESTAMP'), nullable=False),
-    sa.Column('language', sa.String(length=255), server_default=sa.text("'en-US'::character varying"), nullable=False),
+    sa.Column('language', sa.String(length=255), server_default='en-US', nullable=False),
     sa.PrimaryKeyConstraint('id', name='exporler_banner_pkey')
     )
     op.create_table('trial_apps',
-    sa.Column('id', models.types.StringUUID(), server_default=sa.text('uuid_generate_v4()'), nullable=False),
+    sa.Column('id', models.types.StringUUID(), nullable=False),
     sa.Column('app_id', models.types.StringUUID(), nullable=False),
     sa.Column('tenant_id', models.types.StringUUID(), nullable=False),
     sa.Column('created_at', sa.DateTime(), server_default=sa.text('CURRENT_TIMESTAMP'), nullable=False),

api/models/model.py

@@ -620,7 +620,7 @@ class TrialApp(Base):
         sa.UniqueConstraint("app_id", name="unique_trail_app_id"),
     )
 
-    id = mapped_column(StringUUID, server_default=sa.text("uuid_generate_v4()"))
+    id = mapped_column(StringUUID, default=lambda: str(uuid4()))
     app_id = mapped_column(StringUUID, nullable=False)
     tenant_id = mapped_column(StringUUID, nullable=False)
     created_at = mapped_column(sa.DateTime, nullable=False, server_default=func.current_timestamp())
@@ -640,7 +640,7 @@ class AccountTrialAppRecord(Base):
         sa.Index("account_trial_app_record_app_id_idx", "app_id"),
         sa.UniqueConstraint("account_id", "app_id", name="unique_account_trial_app_record"),
     )
-    id = mapped_column(StringUUID, server_default=sa.text("uuid_generate_v4()"))
+    id = mapped_column(StringUUID, default=lambda: str(uuid4()))
     account_id = mapped_column(StringUUID, nullable=False)
     app_id = mapped_column(StringUUID, nullable=False)
     count = mapped_column(sa.Integer, nullable=False, default=0)
@@ -660,18 +660,18 @@ class AccountTrialAppRecord(Base):
 class ExporleBanner(TypeBase):
     __tablename__ = "exporle_banners"
     __table_args__ = (sa.PrimaryKeyConstraint("id", name="exporler_banner_pkey"),)
-    id: Mapped[str] = mapped_column(StringUUID, server_default=sa.text("uuid_generate_v4()"), init=False)
+    id: Mapped[str] = mapped_column(StringUUID, default=lambda: str(uuid4()), init=False)
     content: Mapped[dict[str, Any]] = mapped_column(sa.JSON, nullable=False)
     link: Mapped[str] = mapped_column(String(255), nullable=False)
     sort: Mapped[int] = mapped_column(sa.Integer, nullable=False)
     status: Mapped[str] = mapped_column(
-        sa.String(255), nullable=False, server_default=sa.text("'enabled'::character varying"), default="enabled"
+        sa.String(255), nullable=False, server_default='enabled', default="enabled"
     )
     created_at: Mapped[datetime] = mapped_column(
         sa.DateTime, nullable=False, server_default=func.current_timestamp(), init=False
     )
     language: Mapped[str] = mapped_column(
-        String(255), nullable=False, server_default=sa.text("'en-US'::character varying"), default="en-US"
+        String(255), nullable=False, server_default='en-US', default="en-US"
     )
 
 
@@ -2166,7 +2166,7 @@ class TenantCreditPool(TypeBase):
         sa.Index("tenant_credit_pool_pool_type_idx", "pool_type"),
     )
 
-    id: Mapped[str] = mapped_column(StringUUID, primary_key=True, server_default=text("uuid_generate_v4()"), init=False)
+    id: Mapped[str] = mapped_column(StringUUID, primary_key=True, default=lambda: str(uuid4()), init=False)
     tenant_id: Mapped[str] = mapped_column(StringUUID, nullable=False)
     pool_type: Mapped[str] = mapped_column(String(40), nullable=False, default="trial", server_default="trial")
     quota_limit: Mapped[int] = mapped_column(BigInteger, nullable=False, default=0)

api/pyproject.toml

@@ -1,6 +1,6 @@
 [project]
 name = "dify-api"
-version = "1.12.0"
+version = "1.12.1"
 requires-python = ">=3.11,<3.13"
 
 dependencies = [
@@ -22,14 +22,14 @@ dependencies = [
     "flask-sqlalchemy~=3.1.1",
     "gevent~=25.9.1",
     "gmpy2~=2.2.1",
-    "google-api-core==2.18.0",
+    "google-api-core>=2.19.1",
     "google-api-python-client==2.90.0",
-    "google-auth==2.29.0",
+    "google-auth>=2.47.0",
     "google-auth-httplib2==0.2.0",
-    "google-cloud-aiplatform==1.49.0",
-    "googleapis-common-protos==1.63.0",
+    "google-cloud-aiplatform>=1.123.0",
+    "googleapis-common-protos>=1.65.0",
     "gunicorn~=23.0.0",
-    "httpx[socks]~=0.27.0",
+    "httpx[socks]~=0.28.0",
     "jieba==0.42.1",
     "json-repair>=0.55.1",
     "jsonschema>=4.25.1",
@@ -41,26 +41,23 @@ dependencies = [
     "openpyxl~=3.1.5",
     "opik~=1.8.72",
     "litellm==1.77.1", # Pinned to avoid madoka dependency issue
-    "opentelemetry-api==1.27.0",
-    "opentelemetry-distro==0.48b0",
-    "opentelemetry-exporter-otlp==1.27.0",
-    "opentelemetry-exporter-otlp-proto-common==1.27.0",
-    "opentelemetry-exporter-otlp-proto-grpc==1.27.0",
-    "opentelemetry-exporter-otlp-proto-http==1.27.0",
-    "opentelemetry-instrumentation==0.48b0",
-    "opentelemetry-instrumentation-celery==0.48b0",
-    "opentelemetry-instrumentation-flask==0.48b0",
-    "opentelemetry-instrumentation-httpx==0.48b0",
-    "opentelemetry-instrumentation-redis==0.48b0",
-    "opentelemetry-instrumentation-httpx==0.48b0",
-    "opentelemetry-instrumentation-sqlalchemy==0.48b0",
-    "opentelemetry-propagator-b3==1.27.0",
-    # opentelemetry-proto1.28.0 depends on protobuf (>=5.0,<6.0),
-    # which is conflict with googleapis-common-protos (1.63.0)
-    "opentelemetry-proto==1.27.0",
-    "opentelemetry-sdk==1.27.0",
-    "opentelemetry-semantic-conventions==0.48b0",
-    "opentelemetry-util-http==0.48b0",
+    "opentelemetry-api==1.28.0",
+    "opentelemetry-distro==0.49b0",
+    "opentelemetry-exporter-otlp==1.28.0",
+    "opentelemetry-exporter-otlp-proto-common==1.28.0",
+    "opentelemetry-exporter-otlp-proto-grpc==1.28.0",
+    "opentelemetry-exporter-otlp-proto-http==1.28.0",
+    "opentelemetry-instrumentation==0.49b0",
+    "opentelemetry-instrumentation-celery==0.49b0",
+    "opentelemetry-instrumentation-flask==0.49b0",
+    "opentelemetry-instrumentation-httpx==0.49b0",
+    "opentelemetry-instrumentation-redis==0.49b0",
+    "opentelemetry-instrumentation-sqlalchemy==0.49b0",
+    "opentelemetry-propagator-b3==1.28.0",
+    "opentelemetry-proto==1.28.0",
+    "opentelemetry-sdk==1.28.0",
+    "opentelemetry-semantic-conventions==0.49b0",
+    "opentelemetry-util-http==0.49b0",
     "pandas[excel,output-formatting,performance]~=2.2.2",
     "psycogreen~=1.0.2",
     "psycopg2-binary~=2.9.6",
@@ -81,7 +78,7 @@ dependencies = [
     "starlette==0.49.1",
     "tiktoken~=0.9.0",
     "transformers~=4.56.1",
-    "unstructured[docx,epub,md,ppt,pptx]~=0.16.1",
+    "unstructured[docx,epub,md,ppt,pptx]~=0.18.18",
     "yarl~=1.18.3",
     "webvtt-py~=0.5.1",
     "sseclient-py~=1.8.0",

api/services/account_service.py

@@ -327,6 +327,12 @@ class AccountService:
     @staticmethod
     def delete_account(account: Account):
         """Delete account. This method only adds a task to the queue for deletion."""
+        # Queue account deletion sync tasks for all workspaces BEFORE account deletion (enterprise only)
+        from services.enterprise.account_deletion_sync import sync_account_deletion
+
+        sync_account_deletion(account_id=account.id, source="account_deleted")
+
+        # Now proceed with async account deletion
         delete_account_task.delay(account.id)
 
     @staticmethod
@@ -1230,6 +1236,11 @@ class TenantService:
         if dify_config.BILLING_ENABLED:
             BillingService.clean_billing_info_cache(tenant.id)
 
+        # Queue account deletion sync task for enterprise backend to reassign resources (enterprise only)
+        from services.enterprise.account_deletion_sync import sync_workspace_member_removal
+
+        sync_workspace_member_removal(workspace_id=tenant.id, member_id=account.id, source="workspace_member_removed")
+
     @staticmethod
     def update_member_role(tenant: Tenant, member: Account, new_role: str, operator: Account):
         """Update member role"""

api/services/enterprise/account_deletion_sync.py

@@ -0,0 +1,115 @@
+import json
+import logging
+import uuid
+from datetime import UTC, datetime
+
+from redis import RedisError
+
+from configs import dify_config
+from extensions.ext_database import db
+from extensions.ext_redis import redis_client
+from models.account import TenantAccountJoin
+
+logger = logging.getLogger(__name__)
+
+ACCOUNT_DELETION_SYNC_QUEUE = "enterprise:member:sync:queue"
+ACCOUNT_DELETION_SYNC_TASK_TYPE = "sync_member_deletion_from_workspace"
+
+
+def _queue_task(workspace_id: str, member_id: str, *, source: str) -> bool:
+    """
+    Queue an account deletion sync task to Redis.
+
+    Internal helper function. Do not call directly - use the public functions instead.
+
+    Args:
+        workspace_id: The workspace/tenant ID to sync
+        member_id: The member/account ID that was removed
+        source: Source of the sync request (for debugging/tracking)
+
+    Returns:
+        bool: True if task was queued successfully, False otherwise
+    """
+    try:
+        task = {
+            "task_id": str(uuid.uuid4()),
+            "workspace_id": workspace_id,
+            "member_id": member_id,
+            "retry_count": 0,
+            "created_at": datetime.now(UTC).isoformat(),
+            "source": source,
+            "type": ACCOUNT_DELETION_SYNC_TASK_TYPE,
+        }
+
+        # Push to Redis list (queue) - LPUSH adds to the head, worker consumes from tail with RPOP
+        redis_client.lpush(ACCOUNT_DELETION_SYNC_QUEUE, json.dumps(task))
+
+        logger.info(
+            "Queued account deletion sync task for workspace %s, member %s, task_id: %s, source: %s",
+            workspace_id,
+            member_id,
+            task["task_id"],
+            source,
+        )
+        return True
+
+    except (RedisError, TypeError) as e:
+        logger.error(
+            "Failed to queue account deletion sync for workspace %s, member %s: %s",
+            workspace_id,
+            member_id,
+            str(e),
+            exc_info=True,
+        )
+        # Don't raise - we don't want to fail member deletion if queueing fails
+        return False
+
+
+def sync_workspace_member_removal(workspace_id: str, member_id: str, *, source: str) -> bool:
+    """
+    Sync a single workspace member removal (enterprise only).
+
+    Queues a task for the enterprise backend to reassign resources from the removed member.
+    Handles enterprise edition check internally. Safe to call in community edition (no-op).
+
+    Args:
+        workspace_id: The workspace/tenant ID
+        member_id: The member/account ID that was removed
+        source: Source of the sync request (e.g., "workspace_member_removed")
+
+    Returns:
+        bool: True if task was queued (or skipped in community), False if queueing failed
+    """
+    if not dify_config.ENTERPRISE_ENABLED:
+        return True 
+
+    return _queue_task(workspace_id=workspace_id, member_id=member_id, source=source)
+
+
+def sync_account_deletion(account_id: str, *, source: str) -> bool:
+    """
+    Sync full account deletion across all workspaces (enterprise only).
+
+    Fetches all workspace memberships for the account and queues a sync task for each.
+    Handles enterprise edition check internally. Safe to call in community edition (no-op).
+
+    Args:
+        account_id: The account ID being deleted
+        source: Source of the sync request (e.g., "account_deleted")
+
+    Returns:
+        bool: True if all tasks were queued (or skipped in community), False if any queueing failed
+    """
+    if not dify_config.ENTERPRISE_ENABLED:
+        return True 
+
+    # Fetch all workspaces the account belongs to
+    workspace_joins = db.session.query(TenantAccountJoin).filter_by(account_id=account_id).all()
+
+    # Queue sync task for each workspace
+    success = True
+    for join in workspace_joins:
+        if not _queue_task(workspace_id=join.tenant_id, member_id=account_id, source=source):
+            success = False
+
+    return success

api/services/enterprise/enterprise_service.py

@@ -4,6 +4,8 @@ from pydantic import BaseModel, Field
 
 from services.enterprise.base import EnterpriseRequest
 
+ALLOWED_ACCESS_MODES = ["public", "private", "private_all", "sso_verified"]
+
 
 class WebAppSettings(BaseModel):
     access_mode: str = Field(
@@ -123,8 +125,8 @@ class EnterpriseService:
         def update_app_access_mode(cls, app_id: str, access_mode: str):
             if not app_id:
                 raise ValueError("app_id must be provided.")
-            if access_mode not in ["public", "private", "private_all"]:
-                raise ValueError("access_mode must be either 'public', 'private', or 'private_all'")
+            if access_mode not in ALLOWED_ACCESS_MODES:
+                raise ValueError(f"access_mode must be one of: {', '.join(ALLOWED_ACCESS_MODES)}")
 
             data = {"appId": app_id, "accessMode": access_mode}
 

api/services/tools/builtin_tools_manage_service.py

@@ -2,7 +2,10 @@ import json
 import logging
 from collections.abc import Mapping
 from pathlib import Path
-from typing import Any
+from typing import TYPE_CHECKING, Any
+
+if TYPE_CHECKING:
+    from models.account import Account
 
 from sqlalchemy import exists, select
 from sqlalchemy.orm import Session
@@ -406,20 +409,37 @@ class BuiltinToolManageService:
         return {"result": "success"}
 
     @staticmethod
-    def set_default_provider(tenant_id: str, user_id: str, provider: str, id: str):
+    def set_default_provider(tenant_id: str, user_id: str, provider: str, id: str, account: "Account | None" = None):
         """
         set default provider
         """
         with Session(db.engine) as session:
-            # get provider
-            target_provider = session.query(BuiltinToolProvider).filter_by(id=id).first()
+            # get provider (verify tenant ownership to prevent IDOR)
+            target_provider = session.query(BuiltinToolProvider).filter_by(id=id, tenant_id=tenant_id).first()
             if target_provider is None:
                 raise ValueError("provider not found")
 
             # clear default provider
-            session.query(BuiltinToolProvider).filter_by(
-                tenant_id=tenant_id, user_id=user_id, provider=provider, is_default=True
-            ).update({"is_default": False})
+            if dify_config.ENTERPRISE_ENABLED:
+                # Enterprise: verify admin permission for tenant-wide operation
+                from models.account import TenantAccountRole
+
+                if account is None:
+                    # In enterprise mode, an account context is required to perform permission checks
+                    raise ValueError("Account is required to set default credentials in enterprise mode")
+
+                if not TenantAccountRole.is_privileged_role(account.current_role):
+                    raise ValueError("Only workspace admins/owners can set default credentials in enterprise mode")
+                # Enterprise: clear ALL defaults for this provider in the tenant
+                # (regardless of user_id, since enterprise credentials may have different user_id)
+                session.query(BuiltinToolProvider).filter_by(
+                    tenant_id=tenant_id, provider=provider, is_default=True
+                ).update({"is_default": False})
+            else:
+                # Non-enterprise: only clear defaults for the current user
+                session.query(BuiltinToolProvider).filter_by(
+                    tenant_id=tenant_id, user_id=user_id, provider=provider, is_default=True
+                ).update({"is_default": False})
 
             # set new default provider
             target_provider.is_default = True

api/tasks/annotation/add_annotation_to_index_task.py

@@ -6,7 +6,6 @@ from celery import shared_task
 
 from core.rag.datasource.vdb.vector_factory import Vector
 from core.rag.models.document import Document
-from extensions.ext_database import db
 from models.dataset import Dataset
 from services.dataset_service import DatasetCollectionBindingService
 
@@ -58,5 +57,3 @@ def add_annotation_to_index_task(
         )
     except Exception:
         logger.exception("Build index for annotation failed")
-    finally:
-        db.session.close()

api/tasks/annotation/delete_annotation_index_task.py

@@ -5,7 +5,6 @@ import click
 from celery import shared_task
 
 from core.rag.datasource.vdb.vector_factory import Vector
-from extensions.ext_database import db
 from models.dataset import Dataset
 from services.dataset_service import DatasetCollectionBindingService
 
@@ -40,5 +39,3 @@ def delete_annotation_index_task(annotation_id: str, app_id: str, tenant_id: str
         logger.info(click.style(f"App annotations index deleted : {app_id} latency: {end_at - start_at}", fg="green"))
     except Exception:
         logger.exception("Annotation deleted index failed")
-    finally:
-        db.session.close()

api/tasks/annotation/update_annotation_to_index_task.py

@@ -6,7 +6,6 @@ from celery import shared_task
 
 from core.rag.datasource.vdb.vector_factory import Vector
 from core.rag.models.document import Document
-from extensions.ext_database import db
 from models.dataset import Dataset
 from services.dataset_service import DatasetCollectionBindingService
 
@@ -59,5 +58,3 @@ def update_annotation_to_index_task(
         )
     except Exception:
         logger.exception("Build index for annotation failed")
-    finally:
-        db.session.close()

api/tasks/batch_clean_document_task.py

@@ -14,6 +14,9 @@ from models.model import UploadFile
 
 logger = logging.getLogger(__name__)
 
+# Batch size for database operations to keep transactions short
+BATCH_SIZE = 1000
+
 
 @shared_task(queue="dataset")
 def batch_clean_document_task(document_ids: list[str], dataset_id: str, doc_form: str | None, file_ids: list[str]):
@@ -31,63 +34,179 @@ def batch_clean_document_task(document_ids: list[str], dataset_id: str, doc_form
     if not doc_form:
         raise ValueError("doc_form is required")
 
-    with session_factory.create_session() as session:
-        try:
-            dataset = session.query(Dataset).where(Dataset.id == dataset_id).first()
-
-            if not dataset:
-                raise Exception("Document has no dataset")
-
-            session.query(DatasetMetadataBinding).where(
-                DatasetMetadataBinding.dataset_id == dataset_id,
-                DatasetMetadataBinding.document_id.in_(document_ids),
-            ).delete(synchronize_session=False)
+    storage_keys_to_delete: list[str] = []
+    index_node_ids: list[str] = []
+    segment_ids: list[str] = []
+    total_image_upload_file_ids: list[str] = []
 
+    try:
+        # ============ Step 1: Query segment and file data (short read-only transaction) ============
+        with session_factory.create_session() as session:
+            # Get segments info
             segments = session.scalars(
                 select(DocumentSegment).where(DocumentSegment.document_id.in_(document_ids))
             ).all()
-            # check segment is exist
+
             if segments:
                 index_node_ids = [segment.index_node_id for segment in segments]
-                index_processor = IndexProcessorFactory(doc_form).init_index_processor()
-                index_processor.clean(
-                    dataset, index_node_ids, with_keywords=True, delete_child_chunks=True, delete_summaries=True
-                )
+                segment_ids = [segment.id for segment in segments]
 
+                # Collect image file IDs from segment content
                 for segment in segments:
                     image_upload_file_ids = get_image_upload_file_ids(segment.content)
-                    image_files = session.query(UploadFile).where(UploadFile.id.in_(image_upload_file_ids)).all()
-                    for image_file in image_files:
-                        try:
-                            if image_file and image_file.key:
-                                storage.delete(image_file.key)
-                        except Exception:
-                            logger.exception(
-                                "Delete image_files failed when storage deleted, \
-                                              image_upload_file_is: %s",
-                                image_file.id,
-                            )
-                    stmt = delete(UploadFile).where(UploadFile.id.in_(image_upload_file_ids))
-                    session.execute(stmt)
-                    session.delete(segment)
+                    total_image_upload_file_ids.extend(image_upload_file_ids)
+
+            # Query storage keys for image files
+            if total_image_upload_file_ids:
+                image_files = session.scalars(
+                    select(UploadFile).where(UploadFile.id.in_(total_image_upload_file_ids))
+                ).all()
+                storage_keys_to_delete.extend([f.key for f in image_files if f and f.key])
+
+            # Query storage keys for document files
             if file_ids:
                 files = session.scalars(select(UploadFile).where(UploadFile.id.in_(file_ids))).all()
-                for file in files:
-                    try:
-                        storage.delete(file.key)
-                    except Exception:
-                        logger.exception("Delete file failed when document deleted, file_id: %s", file.id)
-                stmt = delete(UploadFile).where(UploadFile.id.in_(file_ids))
-                session.execute(stmt)
+                storage_keys_to_delete.extend([f.key for f in files if f and f.key])
 
-            session.commit()
-
-            end_at = time.perf_counter()
-            logger.info(
-                click.style(
-                    f"Cleaned documents when documents deleted latency: {end_at - start_at}",
-                    fg="green",
+        # ============ Step 2: Clean vector index (external service, fresh session for dataset) ============
+        if index_node_ids:
+            try:
+                # Fetch dataset in a fresh session to avoid DetachedInstanceError
+                with session_factory.create_session() as session:
+                    dataset = session.query(Dataset).where(Dataset.id == dataset_id).first()
+                    if not dataset:
+                        logger.warning("Dataset not found for vector index cleanup, dataset_id: %s", dataset_id)
+                    else:
+                        index_processor = IndexProcessorFactory(doc_form).init_index_processor()
+                        index_processor.clean(
+                            dataset, index_node_ids, with_keywords=True, delete_child_chunks=True, delete_summaries=True
+                        )
+            except Exception:
+                logger.exception(
+                    "Failed to clean vector index for dataset_id: %s, document_ids: %s, index_node_ids count: %d",
+                    dataset_id,
+                    document_ids,
+                    len(index_node_ids),
                 )
-            )
+
+        # ============ Step 3: Delete metadata binding (separate short transaction) ============
+        try:
+            with session_factory.create_session() as session:
+                deleted_count = (
+                    session.query(DatasetMetadataBinding)
+                    .where(
+                        DatasetMetadataBinding.dataset_id == dataset_id,
+                        DatasetMetadataBinding.document_id.in_(document_ids),
+                    )
+                    .delete(synchronize_session=False)
+                )
+                session.commit()
+                logger.debug("Deleted %d metadata bindings for dataset_id: %s", deleted_count, dataset_id)
         except Exception:
-            logger.exception("Cleaned documents when documents deleted failed")
+            logger.exception(
+                "Failed to delete metadata bindings for dataset_id: %s, document_ids: %s",
+                dataset_id,
+                document_ids,
+            )
+
+        # ============ Step 4: Batch delete UploadFile records (multiple short transactions) ============
+        if total_image_upload_file_ids:
+            failed_batches = 0
+            total_batches = (len(total_image_upload_file_ids) + BATCH_SIZE - 1) // BATCH_SIZE
+            for i in range(0, len(total_image_upload_file_ids), BATCH_SIZE):
+                batch = total_image_upload_file_ids[i : i + BATCH_SIZE]
+                try:
+                    with session_factory.create_session() as session:
+                        stmt = delete(UploadFile).where(UploadFile.id.in_(batch))
+                        session.execute(stmt)
+                        session.commit()
+                except Exception:
+                    failed_batches += 1
+                    logger.exception(
+                        "Failed to delete image UploadFile batch %d-%d for dataset_id: %s",
+                        i,
+                        i + len(batch),
+                        dataset_id,
+                    )
+            if failed_batches > 0:
+                logger.warning(
+                    "Image UploadFile deletion: %d/%d batches failed for dataset_id: %s",
+                    failed_batches,
+                    total_batches,
+                    dataset_id,
+                )
+
+        # ============ Step 5: Batch delete DocumentSegment records (multiple short transactions) ============
+        if segment_ids:
+            failed_batches = 0
+            total_batches = (len(segment_ids) + BATCH_SIZE - 1) // BATCH_SIZE
+            for i in range(0, len(segment_ids), BATCH_SIZE):
+                batch = segment_ids[i : i + BATCH_SIZE]
+                try:
+                    with session_factory.create_session() as session:
+                        segment_delete_stmt = delete(DocumentSegment).where(DocumentSegment.id.in_(batch))
+                        session.execute(segment_delete_stmt)
+                        session.commit()
+                except Exception:
+                    failed_batches += 1
+                    logger.exception(
+                        "Failed to delete DocumentSegment batch %d-%d for dataset_id: %s, document_ids: %s",
+                        i,
+                        i + len(batch),
+                        dataset_id,
+                        document_ids,
+                    )
+            if failed_batches > 0:
+                logger.warning(
+                    "DocumentSegment deletion: %d/%d batches failed, document_ids: %s",
+                    failed_batches,
+                    total_batches,
+                    document_ids,
+                )
+
+        # ============ Step 6: Delete document-associated files (separate short transaction) ============
+        if file_ids:
+            try:
+                with session_factory.create_session() as session:
+                    stmt = delete(UploadFile).where(UploadFile.id.in_(file_ids))
+                    session.execute(stmt)
+                    session.commit()
+            except Exception:
+                logger.exception(
+                    "Failed to delete document UploadFile records for dataset_id: %s, file_ids: %s",
+                    dataset_id,
+                    file_ids,
+                )
+
+        # ============ Step 7: Delete storage files (I/O operations, no DB transaction) ============
+        storage_delete_failures = 0
+        for storage_key in storage_keys_to_delete:
+            try:
+                storage.delete(storage_key)
+            except Exception:
+                storage_delete_failures += 1
+                logger.exception("Failed to delete file from storage, key: %s", storage_key)
+        if storage_delete_failures > 0:
+            logger.warning(
+                "Storage file deletion completed with %d failures out of %d total files for dataset_id: %s",
+                storage_delete_failures,
+                len(storage_keys_to_delete),
+                dataset_id,
+            )
+
+        end_at = time.perf_counter()
+        logger.info(
+            click.style(
+                f"Cleaned documents when documents deleted latency: {end_at - start_at:.2f}s, "
+                f"dataset_id: {dataset_id}, document_ids: {document_ids}, "
+                f"segments: {len(segment_ids)}, image_files: {len(total_image_upload_file_ids)}, "
+                f"storage_files: {len(storage_keys_to_delete)}",
+                fg="green",
+            )
+        )
+    except Exception:
+        logger.exception(
+            "Batch clean documents failed for dataset_id: %s, document_ids: %s",
+            dataset_id,
+            document_ids,
+        )

api/tasks/batch_create_segment_to_index_task.py

@@ -48,6 +48,11 @@ def batch_create_segment_to_index_task(
 
     indexing_cache_key = f"segment_batch_import_{job_id}"
 
+    # Initialize variables with default values
+    upload_file_key: str | None = None
+    dataset_config: dict | None = None
+    document_config: dict | None = None
+
     with session_factory.create_session() as session:
         try:
             dataset = session.get(Dataset, dataset_id)
@@ -69,86 +74,115 @@ def batch_create_segment_to_index_task(
             if not upload_file:
                 raise ValueError("UploadFile not found.")
 
-            with tempfile.TemporaryDirectory() as temp_dir:
-                suffix = Path(upload_file.key).suffix
-                file_path = f"{temp_dir}/{next(tempfile._get_candidate_names())}{suffix}"  # type: ignore
-                storage.download(upload_file.key, file_path)
+            dataset_config = {
+                "id": dataset.id,
+                "indexing_technique": dataset.indexing_technique,
+                "tenant_id": dataset.tenant_id,
+                "embedding_model_provider": dataset.embedding_model_provider,
+                "embedding_model": dataset.embedding_model,
+            }
 
-                df = pd.read_csv(file_path)
-                content = []
-                for _, row in df.iterrows():
-                    if dataset_document.doc_form == "qa_model":
-                        data = {"content": row.iloc[0], "answer": row.iloc[1]}
-                    else:
-                        data = {"content": row.iloc[0]}
-                    content.append(data)
-                if len(content) == 0:
-                    raise ValueError("The CSV file is empty.")
+            document_config = {
+                "id": dataset_document.id,
+                "doc_form": dataset_document.doc_form,
+                "word_count": dataset_document.word_count or 0,
+            }
 
-            document_segments = []
-            embedding_model = None
-            if dataset.indexing_technique == "high_quality":
-                model_manager = ModelManager()
-                embedding_model = model_manager.get_model_instance(
-                    tenant_id=dataset.tenant_id,
-                    provider=dataset.embedding_model_provider,
-                    model_type=ModelType.TEXT_EMBEDDING,
-                    model=dataset.embedding_model,
-                )
+            upload_file_key = upload_file.key
 
-            word_count_change = 0
-            if embedding_model:
-                tokens_list = embedding_model.get_text_embedding_num_tokens(
-                    texts=[segment["content"] for segment in content]
-                )
+        except Exception:
+            logger.exception("Segments batch created index failed")
+            redis_client.setex(indexing_cache_key, 600, "error")
+            return
+
+    # Ensure required variables are set before proceeding
+    if upload_file_key is None or dataset_config is None or document_config is None:
+        logger.error("Required configuration not set due to session error")
+        redis_client.setex(indexing_cache_key, 600, "error")
+        return
+
+    with tempfile.TemporaryDirectory() as temp_dir:
+        suffix = Path(upload_file_key).suffix
+        file_path = f"{temp_dir}/{next(tempfile._get_candidate_names())}{suffix}"  # type: ignore
+        storage.download(upload_file_key, file_path)
+
+        df = pd.read_csv(file_path)
+        content = []
+        for _, row in df.iterrows():
+            if document_config["doc_form"] == "qa_model":
+                data = {"content": row.iloc[0], "answer": row.iloc[1]}
             else:
-                tokens_list = [0] * len(content)
+                data = {"content": row.iloc[0]}
+            content.append(data)
+        if len(content) == 0:
+            raise ValueError("The CSV file is empty.")
 
-            for segment, tokens in zip(content, tokens_list):
-                content = segment["content"]
-                doc_id = str(uuid.uuid4())
-                segment_hash = helper.generate_text_hash(content)
-                max_position = (
-                    session.query(func.max(DocumentSegment.position))
-                    .where(DocumentSegment.document_id == dataset_document.id)
-                    .scalar()
-                )
-                segment_document = DocumentSegment(
-                    tenant_id=tenant_id,
-                    dataset_id=dataset_id,
-                    document_id=document_id,
-                    index_node_id=doc_id,
-                    index_node_hash=segment_hash,
-                    position=max_position + 1 if max_position else 1,
-                    content=content,
-                    word_count=len(content),
-                    tokens=tokens,
-                    created_by=user_id,
-                    indexing_at=naive_utc_now(),
-                    status="completed",
-                    completed_at=naive_utc_now(),
-                )
-                if dataset_document.doc_form == "qa_model":
-                    segment_document.answer = segment["answer"]
-                    segment_document.word_count += len(segment["answer"])
-                word_count_change += segment_document.word_count
-                session.add(segment_document)
-                document_segments.append(segment_document)
+    document_segments = []
+    embedding_model = None
+    if dataset_config["indexing_technique"] == "high_quality":
+        model_manager = ModelManager()
+        embedding_model = model_manager.get_model_instance(
+            tenant_id=dataset_config["tenant_id"],
+            provider=dataset_config["embedding_model_provider"],
+            model_type=ModelType.TEXT_EMBEDDING,
+            model=dataset_config["embedding_model"],
+        )
 
+    word_count_change = 0
+    if embedding_model:
+        tokens_list = embedding_model.get_text_embedding_num_tokens(texts=[segment["content"] for segment in content])
+    else:
+        tokens_list = [0] * len(content)
+
+    with session_factory.create_session() as session, session.begin():
+        for segment, tokens in zip(content, tokens_list):
+            content = segment["content"]
+            doc_id = str(uuid.uuid4())
+            segment_hash = helper.generate_text_hash(content)
+            max_position = (
+                session.query(func.max(DocumentSegment.position))
+                .where(DocumentSegment.document_id == document_config["id"])
+                .scalar()
+            )
+            segment_document = DocumentSegment(
+                tenant_id=tenant_id,
+                dataset_id=dataset_id,
+                document_id=document_id,
+                index_node_id=doc_id,
+                index_node_hash=segment_hash,
+                position=max_position + 1 if max_position else 1,
+                content=content,
+                word_count=len(content),
+                tokens=tokens,
+                created_by=user_id,
+                indexing_at=naive_utc_now(),
+                status="completed",
+                completed_at=naive_utc_now(),
+            )
+            if document_config["doc_form"] == "qa_model":
+                segment_document.answer = segment["answer"]
+                segment_document.word_count += len(segment["answer"])
+            word_count_change += segment_document.word_count
+            session.add(segment_document)
+            document_segments.append(segment_document)
+
+    with session_factory.create_session() as session, session.begin():
+        dataset_document = session.get(Document, document_id)
+        if dataset_document:
             assert dataset_document.word_count is not None
             dataset_document.word_count += word_count_change
             session.add(dataset_document)
 
-            VectorService.create_segments_vector(None, document_segments, dataset, dataset_document.doc_form)
-            session.commit()
-            redis_client.setex(indexing_cache_key, 600, "completed")
-            end_at = time.perf_counter()
-            logger.info(
-                click.style(
-                    f"Segment batch created job: {job_id} latency: {end_at - start_at}",
-                    fg="green",
-                )
-            )
-        except Exception:
-            logger.exception("Segments batch created index failed")
-            redis_client.setex(indexing_cache_key, 600, "error")
+    with session_factory.create_session() as session:
+        dataset = session.get(Dataset, dataset_id)
+        if dataset:
+            VectorService.create_segments_vector(None, document_segments, dataset, document_config["doc_form"])
+
+    redis_client.setex(indexing_cache_key, 600, "completed")
+    end_at = time.perf_counter()
+    logger.info(
+        click.style(
+            f"Segment batch created job: {job_id} latency: {end_at - start_at}",
+            fg="green",
+        )
+    )

api/tasks/clean_document_task.py

@@ -28,6 +28,7 @@ def clean_document_task(document_id: str, dataset_id: str, doc_form: str, file_i
     """
     logger.info(click.style(f"Start clean document when document deleted: {document_id}", fg="green"))
     start_at = time.perf_counter()
+    total_attachment_files = []
 
     with session_factory.create_session() as session:
         try:
@@ -47,78 +48,91 @@ def clean_document_task(document_id: str, dataset_id: str, doc_form: str, file_i
                     SegmentAttachmentBinding.document_id == document_id,
                 )
             ).all()
-            # check segment is exist
-            if segments:
-                index_node_ids = [segment.index_node_id for segment in segments]
-                index_processor = IndexProcessorFactory(doc_form).init_index_processor()
+
+            attachment_ids = [attachment_file.id for _, attachment_file in attachments_with_bindings]
+            binding_ids = [binding.id for binding, _ in attachments_with_bindings]
+            total_attachment_files.extend([attachment_file.key for _, attachment_file in attachments_with_bindings])
+
+            index_node_ids = [segment.index_node_id for segment in segments]
+            segment_contents = [segment.content for segment in segments]
+        except Exception:
+            logger.exception("Cleaned document when document deleted failed")
+            return
+
+    # check segment is exist
+    if index_node_ids:
+        index_processor = IndexProcessorFactory(doc_form).init_index_processor()
+        with session_factory.create_session() as session:
+            dataset = session.query(Dataset).where(Dataset.id == dataset_id).first()
+            if dataset:
                 index_processor.clean(
                     dataset, index_node_ids, with_keywords=True, delete_child_chunks=True, delete_summaries=True
                 )
 
-                for segment in segments:
-                    image_upload_file_ids = get_image_upload_file_ids(segment.content)
-                    image_files = session.scalars(
-                        select(UploadFile).where(UploadFile.id.in_(image_upload_file_ids))
-                    ).all()
-                    for image_file in image_files:
-                        if image_file is None:
-                            continue
-                        try:
-                            storage.delete(image_file.key)
-                        except Exception:
-                            logger.exception(
-                                "Delete image_files failed when storage deleted, \
-                                                  image_upload_file_is: %s",
-                                image_file.id,
-                            )
+    total_image_files = []
+    with session_factory.create_session() as session, session.begin():
+        for segment_content in segment_contents:
+            image_upload_file_ids = get_image_upload_file_ids(segment_content)
+            image_files = session.scalars(select(UploadFile).where(UploadFile.id.in_(image_upload_file_ids))).all()
+            total_image_files.extend([image_file.key for image_file in image_files])
+            image_file_delete_stmt = delete(UploadFile).where(UploadFile.id.in_(image_upload_file_ids))
+            session.execute(image_file_delete_stmt)
 
-                    image_file_delete_stmt = delete(UploadFile).where(UploadFile.id.in_(image_upload_file_ids))
-                    session.execute(image_file_delete_stmt)
-                    session.delete(segment)
+    with session_factory.create_session() as session, session.begin():
+        segment_delete_stmt = delete(DocumentSegment).where(DocumentSegment.document_id == document_id)
+        session.execute(segment_delete_stmt)
 
-                session.commit()
-            if file_id:
-                file = session.query(UploadFile).where(UploadFile.id == file_id).first()
-                if file:
-                    try:
-                        storage.delete(file.key)
-                    except Exception:
-                        logger.exception("Delete file failed when document deleted, file_id: %s", file_id)
-                    session.delete(file)
-            # delete segment attachments
-            if attachments_with_bindings:
-                attachment_ids = [attachment_file.id for _, attachment_file in attachments_with_bindings]
-                binding_ids = [binding.id for binding, _ in attachments_with_bindings]
-                for binding, attachment_file in attachments_with_bindings:
-                    try:
-                        storage.delete(attachment_file.key)
-                    except Exception:
-                        logger.exception(
-                            "Delete attachment_file failed when storage deleted, \
-                                            attachment_file_id: %s",
-                            binding.attachment_id,
-                        )
-                attachment_file_delete_stmt = delete(UploadFile).where(UploadFile.id.in_(attachment_ids))
-                session.execute(attachment_file_delete_stmt)
-
-                binding_delete_stmt = delete(SegmentAttachmentBinding).where(
-                    SegmentAttachmentBinding.id.in_(binding_ids)
-                )
-                session.execute(binding_delete_stmt)
-
-            # delete dataset metadata binding
-            session.query(DatasetMetadataBinding).where(
-                DatasetMetadataBinding.dataset_id == dataset_id,
-                DatasetMetadataBinding.document_id == document_id,
-            ).delete()
-            session.commit()
-
-            end_at = time.perf_counter()
-            logger.info(
-                click.style(
-                    f"Cleaned document when document deleted: {document_id} latency: {end_at - start_at}",
-                    fg="green",
-                )
-            )
+    for image_file_key in total_image_files:
+        try:
+            storage.delete(image_file_key)
         except Exception:
-            logger.exception("Cleaned document when document deleted failed")
+            logger.exception(
+                "Delete image_files failed when storage deleted, \
+                                          image_upload_file_is: %s",
+                image_file_key,
+            )
+
+    with session_factory.create_session() as session, session.begin():
+        if file_id:
+            file = session.query(UploadFile).where(UploadFile.id == file_id).first()
+            if file:
+                try:
+                    storage.delete(file.key)
+                except Exception:
+                    logger.exception("Delete file failed when document deleted, file_id: %s", file_id)
+                session.delete(file)
+
+    with session_factory.create_session() as session, session.begin():
+        # delete segment attachments
+        if attachment_ids:
+            attachment_file_delete_stmt = delete(UploadFile).where(UploadFile.id.in_(attachment_ids))
+            session.execute(attachment_file_delete_stmt)
+
+        if binding_ids:
+            binding_delete_stmt = delete(SegmentAttachmentBinding).where(SegmentAttachmentBinding.id.in_(binding_ids))
+            session.execute(binding_delete_stmt)
+
+    for attachment_file_key in total_attachment_files:
+        try:
+            storage.delete(attachment_file_key)
+        except Exception:
+            logger.exception(
+                "Delete attachment_file failed when storage deleted, \
+                                    attachment_file_id: %s",
+                attachment_file_key,
+            )
+
+    with session_factory.create_session() as session, session.begin():
+        # delete dataset metadata binding
+        session.query(DatasetMetadataBinding).where(
+            DatasetMetadataBinding.dataset_id == dataset_id,
+            DatasetMetadataBinding.document_id == document_id,
+        ).delete()
+
+    end_at = time.perf_counter()
+    logger.info(
+        click.style(
+            f"Cleaned document when document deleted: {document_id} latency: {end_at - start_at}",
+            fg="green",
+        )
+    )

api/tasks/clean_notion_document_task.py

@@ -23,40 +23,40 @@ def clean_notion_document_task(document_ids: list[str], dataset_id: str):
     """
     logger.info(click.style(f"Start clean document when import form notion document deleted: {dataset_id}", fg="green"))
     start_at = time.perf_counter()
+    total_index_node_ids = []
 
     with session_factory.create_session() as session:
-        try:
-            dataset = session.query(Dataset).where(Dataset.id == dataset_id).first()
+        dataset = session.query(Dataset).where(Dataset.id == dataset_id).first()
 
-            if not dataset:
-                raise Exception("Document has no dataset")
-            index_type = dataset.doc_form
-            index_processor = IndexProcessorFactory(index_type).init_index_processor()
+        if not dataset:
+            raise Exception("Document has no dataset")
+        index_type = dataset.doc_form
+        index_processor = IndexProcessorFactory(index_type).init_index_processor()
 
-            document_delete_stmt = delete(Document).where(Document.id.in_(document_ids))
-            session.execute(document_delete_stmt)
+        document_delete_stmt = delete(Document).where(Document.id.in_(document_ids))
+        session.execute(document_delete_stmt)
 
-            for document_id in document_ids:
-                segments = session.scalars(
-                    select(DocumentSegment).where(DocumentSegment.document_id == document_id)
-                ).all()
-                index_node_ids = [segment.index_node_id for segment in segments]
+        for document_id in document_ids:
+            segments = session.scalars(select(DocumentSegment).where(DocumentSegment.document_id == document_id)).all()
+            total_index_node_ids.extend([segment.index_node_id for segment in segments])
 
-                index_processor.clean(
-                    dataset, index_node_ids, with_keywords=True, delete_child_chunks=True, delete_summaries=True
-                )
-                segment_ids = [segment.id for segment in segments]
-                segment_delete_stmt = delete(DocumentSegment).where(DocumentSegment.id.in_(segment_ids))
-                session.execute(segment_delete_stmt)
-            session.commit()
-            end_at = time.perf_counter()
-            logger.info(
-                click.style(
-                    "Clean document when import form notion document deleted end :: {} latency: {}".format(
-                        dataset_id, end_at - start_at
-                    ),
-                    fg="green",
-                )
+    with session_factory.create_session() as session:
+        dataset = session.query(Dataset).where(Dataset.id == dataset_id).first()
+        if dataset:
+            index_processor.clean(
+                dataset, total_index_node_ids, with_keywords=True, delete_child_chunks=True, delete_summaries=True
             )
-        except Exception:
-            logger.exception("Cleaned document when import form notion document deleted  failed")
+
+    with session_factory.create_session() as session, session.begin():
+        segment_delete_stmt = delete(DocumentSegment).where(DocumentSegment.document_id.in_(document_ids))
+        session.execute(segment_delete_stmt)
+
+    end_at = time.perf_counter()
+    logger.info(
+        click.style(
+            "Clean document when import form notion document deleted end :: {} latency: {}".format(
+                dataset_id, end_at - start_at
+            ),
+            fg="green",
+        )
+    )

api/tasks/delete_segment_from_index_task.py

@@ -3,6 +3,7 @@ import time
 
 import click
 from celery import shared_task
+from sqlalchemy import delete
 
 from core.db.session_factory import session_factory
 from core.rag.index_processor.index_processor_factory import IndexProcessorFactory
@@ -67,8 +68,14 @@ def delete_segment_from_index_task(
                 if segment_attachment_bindings:
                     attachment_ids = [binding.attachment_id for binding in segment_attachment_bindings]
                     index_processor.clean(dataset=dataset, node_ids=attachment_ids, with_keywords=False)
-                    for binding in segment_attachment_bindings:
-                        session.delete(binding)
+                    segment_attachment_bind_ids = [i.id for i in segment_attachment_bindings]
+
+                    for i in range(0, len(segment_attachment_bind_ids), 1000):
+                        segment_attachment_bind_delete_stmt = delete(SegmentAttachmentBinding).where(
+                            SegmentAttachmentBinding.id.in_(segment_attachment_bind_ids[i : i + 1000])
+                        )
+                        session.execute(segment_attachment_bind_delete_stmt)
+
                     # delete upload file
                     session.query(UploadFile).where(UploadFile.id.in_(attachment_ids)).delete(synchronize_session=False)
                     session.commit()

api/tasks/document_indexing_sync_task.py

@@ -27,104 +27,129 @@ def document_indexing_sync_task(dataset_id: str, document_id: str):
     """
     logger.info(click.style(f"Start sync document: {document_id}", fg="green"))
     start_at = time.perf_counter()
+    tenant_id = None
 
-    with session_factory.create_session() as session:
+    with session_factory.create_session() as session, session.begin():
         document = session.query(Document).where(Document.id == document_id, Document.dataset_id == dataset_id).first()
 
         if not document:
             logger.info(click.style(f"Document not found: {document_id}", fg="red"))
             return
 
+        if document.indexing_status == "parsing":
+            logger.info(click.style(f"Document {document_id} is already being processed, skipping", fg="yellow"))
+            return
+
+        dataset = session.query(Dataset).where(Dataset.id == dataset_id).first()
+        if not dataset:
+            raise Exception("Dataset not found")
+
         data_source_info = document.data_source_info_dict
-        if document.data_source_type == "notion_import":
-            if (
-                not data_source_info
-                or "notion_page_id" not in data_source_info
-                or "notion_workspace_id" not in data_source_info
-            ):
-                raise ValueError("no notion page found")
-            workspace_id = data_source_info["notion_workspace_id"]
-            page_id = data_source_info["notion_page_id"]
-            page_type = data_source_info["type"]
-            page_edited_time = data_source_info["last_edited_time"]
-            credential_id = data_source_info.get("credential_id")
+        if document.data_source_type != "notion_import":
+            logger.info(click.style(f"Document {document_id} is not a notion_import, skipping", fg="yellow"))
+            return
 
-            # Get credentials from datasource provider
-            datasource_provider_service = DatasourceProviderService()
-            credential = datasource_provider_service.get_datasource_credentials(
-                tenant_id=document.tenant_id,
-                credential_id=credential_id,
-                provider="notion_datasource",
-                plugin_id="langgenius/notion_datasource",
-            )
+        if (
+            not data_source_info
+            or "notion_page_id" not in data_source_info
+            or "notion_workspace_id" not in data_source_info
+        ):
+            raise ValueError("no notion page found")
 
-            if not credential:
-                logger.error(
-                    "Datasource credential not found for document %s, tenant_id: %s, credential_id: %s",
-                    document_id,
-                    document.tenant_id,
-                    credential_id,
-                )
+        workspace_id = data_source_info["notion_workspace_id"]
+        page_id = data_source_info["notion_page_id"]
+        page_type = data_source_info["type"]
+        page_edited_time = data_source_info["last_edited_time"]
+        credential_id = data_source_info.get("credential_id")
+        tenant_id = document.tenant_id
+        index_type = document.doc_form
+
+        segments = session.scalars(select(DocumentSegment).where(DocumentSegment.document_id == document_id)).all()
+        index_node_ids = [segment.index_node_id for segment in segments]
+
+    # Get credentials from datasource provider
+    datasource_provider_service = DatasourceProviderService()
+    credential = datasource_provider_service.get_datasource_credentials(
+        tenant_id=tenant_id,
+        credential_id=credential_id,
+        provider="notion_datasource",
+        plugin_id="langgenius/notion_datasource",
+    )
+
+    if not credential:
+        logger.error(
+            "Datasource credential not found for document %s, tenant_id: %s, credential_id: %s",
+            document_id,
+            tenant_id,
+            credential_id,
+        )
+
+        with session_factory.create_session() as session, session.begin():
+            document = session.query(Document).filter_by(id=document_id).first()
+            if document:
                 document.indexing_status = "error"
                 document.error = "Datasource credential not found. Please reconnect your Notion workspace."
                 document.stopped_at = naive_utc_now()
-                session.commit()
-                return
+        return
 
-            loader = NotionExtractor(
-                notion_workspace_id=workspace_id,
-                notion_obj_id=page_id,
-                notion_page_type=page_type,
-                notion_access_token=credential.get("integration_secret"),
-                tenant_id=document.tenant_id,
-            )
+    loader = NotionExtractor(
+        notion_workspace_id=workspace_id,
+        notion_obj_id=page_id,
+        notion_page_type=page_type,
+        notion_access_token=credential.get("integration_secret"),
+        tenant_id=tenant_id,
+    )
 
-            last_edited_time = loader.get_notion_last_edited_time()
+    last_edited_time = loader.get_notion_last_edited_time()
+    if last_edited_time == page_edited_time:
+        logger.info(click.style(f"Document {document_id} content unchanged, skipping sync", fg="yellow"))
+        return
 
-            # check the page is updated
-            if last_edited_time != page_edited_time:
-                document.indexing_status = "parsing"
-                document.processing_started_at = naive_utc_now()
-                session.commit()
+    logger.info(click.style(f"Document {document_id} content changed, starting sync", fg="green"))
 
-                # delete all document segment and index
-                try:
-                    dataset = session.query(Dataset).where(Dataset.id == dataset_id).first()
-                    if not dataset:
-                        raise Exception("Dataset not found")
-                    index_type = document.doc_form
-                    index_processor = IndexProcessorFactory(index_type).init_index_processor()
+    try:
+        index_processor = IndexProcessorFactory(index_type).init_index_processor()
+        with session_factory.create_session() as session:
+            dataset = session.query(Dataset).where(Dataset.id == dataset_id).first()
+            if dataset:
+                index_processor.clean(dataset, index_node_ids, with_keywords=True, delete_child_chunks=True)
+        logger.info(click.style(f"Cleaned vector index for document {document_id}", fg="green"))
+    except Exception:
+        logger.exception("Failed to clean vector index for document %s", document_id)
 
-                    segments = session.scalars(
-                        select(DocumentSegment).where(DocumentSegment.document_id == document_id)
-                    ).all()
-                    index_node_ids = [segment.index_node_id for segment in segments]
+    with session_factory.create_session() as session, session.begin():
+        document = session.query(Document).filter_by(id=document_id).first()
+        if not document:
+            logger.warning(click.style(f"Document {document_id} not found during sync", fg="yellow"))
+            return
 
-                    # delete from vector index
-                    index_processor.clean(dataset, index_node_ids, with_keywords=True, delete_child_chunks=True)
+        data_source_info = document.data_source_info_dict
+        data_source_info["last_edited_time"] = last_edited_time
+        document.data_source_info = data_source_info
 
-                    segment_ids = [segment.id for segment in segments]
-                    segment_delete_stmt = delete(DocumentSegment).where(DocumentSegment.id.in_(segment_ids))
-                    session.execute(segment_delete_stmt)
+        document.indexing_status = "parsing"
+        document.processing_started_at = naive_utc_now()
 
-                    end_at = time.perf_counter()
-                    logger.info(
-                        click.style(
-                            "Cleaned document when document update data source or process rule: {} latency: {}".format(
-                                document_id, end_at - start_at
-                            ),
-                            fg="green",
-                        )
-                    )
-                except Exception:
-                    logger.exception("Cleaned document when document update data source or process rule failed")
+        segment_delete_stmt = delete(DocumentSegment).where(DocumentSegment.document_id == document_id)
+        session.execute(segment_delete_stmt)
 
-                try:
-                    indexing_runner = IndexingRunner()
-                    indexing_runner.run([document])
-                    end_at = time.perf_counter()
-                    logger.info(click.style(f"update document: {document.id} latency: {end_at - start_at}", fg="green"))
-                except DocumentIsPausedError as ex:
-                    logger.info(click.style(str(ex), fg="yellow"))
-                except Exception:
-                    logger.exception("document_indexing_sync_task failed, document_id: %s", document_id)
+        logger.info(click.style(f"Deleted segments for document {document_id}", fg="green"))
+
+    try:
+        indexing_runner = IndexingRunner()
+        with session_factory.create_session() as session:
+            document = session.query(Document).filter_by(id=document_id).first()
+            if document:
+                indexing_runner.run([document])
+        end_at = time.perf_counter()
+        logger.info(click.style(f"Sync completed for document {document_id} latency: {end_at - start_at}", fg="green"))
+    except DocumentIsPausedError as ex:
+        logger.info(click.style(str(ex), fg="yellow"))
+    except Exception as e:
+        logger.exception("document_indexing_sync_task failed for document_id: %s", document_id)
+        with session_factory.create_session() as session, session.begin():
+            document = session.query(Document).filter_by(id=document_id).first()
+            if document:
+                document.indexing_status = "error"
+                document.error = str(e)
+                document.stopped_at = naive_utc_now()

api/tasks/document_indexing_task.py

@@ -81,26 +81,35 @@ def _document_indexing(dataset_id: str, document_ids: Sequence[str]):
             session.commit()
             return
 
-        for document_id in document_ids:
-            logger.info(click.style(f"Start process document: {document_id}", fg="green"))
-
-            document = (
-                session.query(Document).where(Document.id == document_id, Document.dataset_id == dataset_id).first()
-            )
+    # Phase 1: Update status to parsing (short transaction)
+    with session_factory.create_session() as session, session.begin():
+        documents = (
+            session.query(Document).where(Document.id.in_(document_ids), Document.dataset_id == dataset_id).all()
+        )
 
+        for document in documents:
             if document:
                 document.indexing_status = "parsing"
                 document.processing_started_at = naive_utc_now()
-                documents.append(document)
                 session.add(document)
-        session.commit()
+    # Transaction committed and closed
 
-        try:
-            indexing_runner = IndexingRunner()
-            indexing_runner.run(documents)
-            end_at = time.perf_counter()
-            logger.info(click.style(f"Processed dataset: {dataset_id} latency: {end_at - start_at}", fg="green"))
+    # Phase 2: Execute indexing (no transaction - IndexingRunner creates its own sessions)
+    has_error = False
+    try:
+        indexing_runner = IndexingRunner()
+        indexing_runner.run(documents)
+        end_at = time.perf_counter()
+        logger.info(click.style(f"Processed dataset: {dataset_id} latency: {end_at - start_at}", fg="green"))
+    except DocumentIsPausedError as ex:
+        logger.info(click.style(str(ex), fg="yellow"))
+        has_error = True
+    except Exception:
+        logger.exception("Document indexing task failed, dataset_id: %s", dataset_id)
+        has_error = True
 
+    if not has_error:
+        with session_factory.create_session() as session:
             # Trigger summary index generation for completed documents if enabled
             # Only generate for high_quality indexing technique and when summary_index_setting is enabled
             # Re-query dataset to get latest summary_index_setting (in case it was updated)
@@ -115,17 +124,18 @@ def _document_indexing(dataset_id: str, document_ids: Sequence[str]):
                     # expire all session to get latest document's indexing status
                     session.expire_all()
                     # Check each document's indexing status and trigger summary generation if completed
-                    for document_id in document_ids:
-                        # Re-query document to get latest status (IndexingRunner may have updated it)
-                        document = (
-                            session.query(Document)
-                            .where(Document.id == document_id, Document.dataset_id == dataset_id)
-                            .first()
-                        )
+
+                    documents = (
+                        session.query(Document)
+                        .where(Document.id.in_(document_ids), Document.dataset_id == dataset_id)
+                        .all()
+                    )
+
+                    for document in documents:
                         if document:
                             logger.info(
                                 "Checking document %s for summary generation: status=%s, doc_form=%s, need_summary=%s",
-                                document_id,
+                                document.id,
                                 document.indexing_status,
                                 document.doc_form,
                                 document.need_summary,
@@ -136,46 +146,36 @@ def _document_indexing(dataset_id: str, document_ids: Sequence[str]):
                                 and document.need_summary is True
                             ):
                                 try:
-                                    generate_summary_index_task.delay(dataset.id, document_id, None)
+                                    generate_summary_index_task.delay(dataset.id, document.id, None)
                                     logger.info(
                                         "Queued summary index generation task for document %s in dataset %s "
                                         "after indexing completed",
-                                        document_id,
+                                        document.id,
                                         dataset.id,
                                     )
                                 except Exception:
                                     logger.exception(
                                         "Failed to queue summary index generation task for document %s",
-                                        document_id,
+                                        document.id,
                                     )
                                     # Don't fail the entire indexing process if summary task queuing fails
                             else:
                                 logger.info(
                                     "Skipping summary generation for document %s: "
                                     "status=%s, doc_form=%s, need_summary=%s",
-                                    document_id,
+                                    document.id,
                                     document.indexing_status,
                                     document.doc_form,
                                     document.need_summary,
                                 )
                         else:
-                            logger.warning("Document %s not found after indexing", document_id)
-                else:
-                    logger.info(
-                        "Summary index generation skipped for dataset %s: summary_index_setting.enable=%s",
-                        dataset.id,
-                        summary_index_setting.get("enable") if summary_index_setting else None,
-                    )
+                            logger.warning("Document %s not found after indexing", document.id)
             else:
                 logger.info(
                     "Summary index generation skipped for dataset %s: indexing_technique=%s (not 'high_quality')",
                     dataset.id,
                     dataset.indexing_technique,
                 )
-        except DocumentIsPausedError as ex:
-            logger.info(click.style(str(ex), fg="yellow"))
-        except Exception:
-            logger.exception("Document indexing task failed, dataset_id: %s", dataset_id)
 
 
 def _document_indexing_with_tenant_queue(

api/tasks/document_indexing_update_task.py

@@ -8,7 +8,6 @@ from sqlalchemy import delete, select
 from core.db.session_factory import session_factory
 from core.indexing_runner import DocumentIsPausedError, IndexingRunner
 from core.rag.index_processor.index_processor_factory import IndexProcessorFactory
-from extensions.ext_database import db
 from libs.datetime_utils import naive_utc_now
 from models.dataset import Dataset, Document, DocumentSegment
 
@@ -27,7 +26,7 @@ def document_indexing_update_task(dataset_id: str, document_id: str):
     logger.info(click.style(f"Start update document: {document_id}", fg="green"))
     start_at = time.perf_counter()
 
-    with session_factory.create_session() as session:
+    with session_factory.create_session() as session, session.begin():
         document = session.query(Document).where(Document.id == document_id, Document.dataset_id == dataset_id).first()
 
         if not document:
@@ -36,27 +35,20 @@ def document_indexing_update_task(dataset_id: str, document_id: str):
 
         document.indexing_status = "parsing"
         document.processing_started_at = naive_utc_now()
-        session.commit()
 
-        # delete all document segment and index
-        try:
-            dataset = session.query(Dataset).where(Dataset.id == dataset_id).first()
-            if not dataset:
-                raise Exception("Dataset not found")
+        dataset = session.query(Dataset).where(Dataset.id == dataset_id).first()
+        if not dataset:
+            return
 
-            index_type = document.doc_form
-            index_processor = IndexProcessorFactory(index_type).init_index_processor()
+        index_type = document.doc_form
+        segments = session.scalars(select(DocumentSegment).where(DocumentSegment.document_id == document_id)).all()
+        index_node_ids = [segment.index_node_id for segment in segments]
 
-            segments = session.scalars(select(DocumentSegment).where(DocumentSegment.document_id == document_id)).all()
-            if segments:
-                index_node_ids = [segment.index_node_id for segment in segments]
-
-                # delete from vector index
-                index_processor.clean(dataset, index_node_ids, with_keywords=True, delete_child_chunks=True)
-                segment_ids = [segment.id for segment in segments]
-                segment_delete_stmt = delete(DocumentSegment).where(DocumentSegment.id.in_(segment_ids))
-                session.execute(segment_delete_stmt)
-                db.session.commit()
+    clean_success = False
+    try:
+        index_processor = IndexProcessorFactory(index_type).init_index_processor()
+        if index_node_ids:
+            index_processor.clean(dataset, index_node_ids, with_keywords=True, delete_child_chunks=True)
             end_at = time.perf_counter()
             logger.info(
                 click.style(
@@ -66,15 +58,21 @@ def document_indexing_update_task(dataset_id: str, document_id: str):
                     fg="green",
                 )
             )
-        except Exception:
-            logger.exception("Cleaned document when document update data source or process rule failed")
+            clean_success = True
+    except Exception:
+        logger.exception("Failed to clean document index during update, document_id: %s", document_id)
 
-        try:
-            indexing_runner = IndexingRunner()
-            indexing_runner.run([document])
-            end_at = time.perf_counter()
-            logger.info(click.style(f"update document: {document.id} latency: {end_at - start_at}", fg="green"))
-        except DocumentIsPausedError as ex:
-            logger.info(click.style(str(ex), fg="yellow"))
-        except Exception:
-            logger.exception("document_indexing_update_task failed, document_id: %s", document_id)
+    if clean_success:
+        with session_factory.create_session() as session, session.begin():
+            segment_delete_stmt = delete(DocumentSegment).where(DocumentSegment.document_id == document_id)
+            session.execute(segment_delete_stmt)
+
+    try:
+        indexing_runner = IndexingRunner()
+        indexing_runner.run([document])
+        end_at = time.perf_counter()
+        logger.info(click.style(f"update document: {document.id} latency: {end_at - start_at}", fg="green"))
+    except DocumentIsPausedError as ex:
+        logger.info(click.style(str(ex), fg="yellow"))
+    except Exception:
+        logger.exception("document_indexing_update_task failed, document_id: %s", document_id)

api/tasks/remove_app_and_related_data_task.py

@@ -259,8 +259,8 @@ def _delete_app_workflow_app_logs(tenant_id: str, app_id: str):
 
 
 def _delete_app_workflow_archive_logs(tenant_id: str, app_id: str):
-    def del_workflow_archive_log(workflow_archive_log_id: str):
-        db.session.query(WorkflowArchiveLog).where(WorkflowArchiveLog.id == workflow_archive_log_id).delete(
+    def del_workflow_archive_log(session, workflow_archive_log_id: str):
+        session.query(WorkflowArchiveLog).where(WorkflowArchiveLog.id == workflow_archive_log_id).delete(
             synchronize_session=False
         )
 
@@ -420,7 +420,7 @@ def delete_draft_variables_batch(app_id: str, batch_size: int = 1000) -> int:
     total_files_deleted = 0
 
     while True:
-        with session_factory.create_session() as session:
+        with session_factory.create_session() as session, session.begin():
             # Get a batch of draft variable IDs along with their file_ids
             query_sql = """
                 SELECT id, file_id FROM workflow_draft_variables

api/tasks/workflow_draft_var_tasks.py

@@ -6,9 +6,8 @@ improving performance by offloading storage operations to background workers.
 """
 
 from celery import shared_task  # type: ignore[import-untyped]
-from sqlalchemy.orm import Session
 
-from extensions.ext_database import db
+from core.db.session_factory import session_factory
 from services.workflow_draft_variable_service import DraftVarFileDeletion, WorkflowDraftVariableService
 
 
@@ -17,6 +16,6 @@ def save_workflow_execution_task(
     self,
     deletions: list[DraftVarFileDeletion],
 ):
-    with Session(bind=db.engine) as session, session.begin():
+    with session_factory.create_session() as session, session.begin():
         srv = WorkflowDraftVariableService(session=session)
         srv.delete_workflow_draft_variable_file(deletions=deletions)

api/tests/integration_tests/tasks/test_remove_app_and_related_data_task.py

@@ -10,7 +10,10 @@ from models import Tenant
 from models.enums import CreatorUserRole
 from models.model import App, UploadFile
 from models.workflow import WorkflowDraftVariable, WorkflowDraftVariableFile
-from tasks.remove_app_and_related_data_task import _delete_draft_variables, delete_draft_variables_batch
+from tasks.remove_app_and_related_data_task import (
+    _delete_draft_variables,
+    delete_draft_variables_batch,
+)
 
 
 @pytest.fixture
@@ -297,12 +300,18 @@ class TestDeleteDraftVariablesWithOffloadIntegration:
     def test_delete_draft_variables_with_offload_data(self, mock_storage, setup_offload_test_data):
         data = setup_offload_test_data
         app_id = data["app"].id
+        upload_file_ids = [uf.id for uf in data["upload_files"]]
+        variable_file_ids = [vf.id for vf in data["variable_files"]]
         mock_storage.delete.return_value = None
 
         with session_factory.create_session() as session:
             draft_vars_before = session.query(WorkflowDraftVariable).filter_by(app_id=app_id).count()
-            var_files_before = session.query(WorkflowDraftVariableFile).count()
-            upload_files_before = session.query(UploadFile).count()
+            var_files_before = (
+                session.query(WorkflowDraftVariableFile)
+                .where(WorkflowDraftVariableFile.id.in_(variable_file_ids))
+                .count()
+            )
+            upload_files_before = session.query(UploadFile).where(UploadFile.id.in_(upload_file_ids)).count()
         assert draft_vars_before == 3
         assert var_files_before == 2
         assert upload_files_before == 2
@@ -315,8 +324,12 @@ class TestDeleteDraftVariablesWithOffloadIntegration:
         assert draft_vars_after == 0
 
         with session_factory.create_session() as session:
-            var_files_after = session.query(WorkflowDraftVariableFile).count()
-            upload_files_after = session.query(UploadFile).count()
+            var_files_after = (
+                session.query(WorkflowDraftVariableFile)
+                .where(WorkflowDraftVariableFile.id.in_(variable_file_ids))
+                .count()
+            )
+            upload_files_after = session.query(UploadFile).where(UploadFile.id.in_(upload_file_ids)).count()
         assert var_files_after == 0
         assert upload_files_after == 0
 
@@ -329,6 +342,8 @@ class TestDeleteDraftVariablesWithOffloadIntegration:
     def test_delete_draft_variables_storage_failure_continues_cleanup(self, mock_storage, setup_offload_test_data):
         data = setup_offload_test_data
         app_id = data["app"].id
+        upload_file_ids = [uf.id for uf in data["upload_files"]]
+        variable_file_ids = [vf.id for vf in data["variable_files"]]
         mock_storage.delete.side_effect = [Exception("Storage error"), None]
 
         deleted_count = delete_draft_variables_batch(app_id, batch_size=10)
@@ -339,8 +354,12 @@ class TestDeleteDraftVariablesWithOffloadIntegration:
         assert draft_vars_after == 0
 
         with session_factory.create_session() as session:
-            var_files_after = session.query(WorkflowDraftVariableFile).count()
-            upload_files_after = session.query(UploadFile).count()
+            var_files_after = (
+                session.query(WorkflowDraftVariableFile)
+                .where(WorkflowDraftVariableFile.id.in_(variable_file_ids))
+                .count()
+            )
+            upload_files_after = session.query(UploadFile).where(UploadFile.id.in_(upload_file_ids)).count()
         assert var_files_after == 0
         assert upload_files_after == 0
 
@@ -395,3 +414,275 @@ class TestDeleteDraftVariablesWithOffloadIntegration:
                 if app2_obj:
                     session.delete(app2_obj)
                 session.commit()
+
+
+class TestDeleteDraftVariablesSessionCommit:
+    """Test suite to verify session commit behavior in delete_draft_variables_batch."""
+
+    @pytest.fixture
+    def setup_offload_test_data(self, app_and_tenant):
+        """Create test data with offload files for session commit tests."""
+        from core.variables.types import SegmentType
+        from libs.datetime_utils import naive_utc_now
+
+        tenant, app = app_and_tenant
+
+        with session_factory.create_session() as session:
+            upload_file1 = UploadFile(
+                tenant_id=tenant.id,
+                storage_type="local",
+                key="test/file1.json",
+                name="file1.json",
+                size=1024,
+                extension="json",
+                mime_type="application/json",
+                created_by_role=CreatorUserRole.ACCOUNT,
+                created_by=str(uuid.uuid4()),
+                created_at=naive_utc_now(),
+                used=False,
+            )
+            upload_file2 = UploadFile(
+                tenant_id=tenant.id,
+                storage_type="local",
+                key="test/file2.json",
+                name="file2.json",
+                size=2048,
+                extension="json",
+                mime_type="application/json",
+                created_by_role=CreatorUserRole.ACCOUNT,
+                created_by=str(uuid.uuid4()),
+                created_at=naive_utc_now(),
+                used=False,
+            )
+            session.add(upload_file1)
+            session.add(upload_file2)
+            session.flush()
+
+            var_file1 = WorkflowDraftVariableFile(
+                tenant_id=tenant.id,
+                app_id=app.id,
+                user_id=str(uuid.uuid4()),
+                upload_file_id=upload_file1.id,
+                size=1024,
+                length=10,
+                value_type=SegmentType.STRING,
+            )
+            var_file2 = WorkflowDraftVariableFile(
+                tenant_id=tenant.id,
+                app_id=app.id,
+                user_id=str(uuid.uuid4()),
+                upload_file_id=upload_file2.id,
+                size=2048,
+                length=20,
+                value_type=SegmentType.OBJECT,
+            )
+            session.add(var_file1)
+            session.add(var_file2)
+            session.flush()
+
+            draft_var1 = WorkflowDraftVariable.new_node_variable(
+                app_id=app.id,
+                node_id="node_1",
+                name="large_var_1",
+                value=StringSegment(value="truncated..."),
+                node_execution_id=str(uuid.uuid4()),
+                file_id=var_file1.id,
+            )
+            draft_var2 = WorkflowDraftVariable.new_node_variable(
+                app_id=app.id,
+                node_id="node_2",
+                name="large_var_2",
+                value=StringSegment(value="truncated..."),
+                node_execution_id=str(uuid.uuid4()),
+                file_id=var_file2.id,
+            )
+            draft_var3 = WorkflowDraftVariable.new_node_variable(
+                app_id=app.id,
+                node_id="node_3",
+                name="regular_var",
+                value=StringSegment(value="regular_value"),
+                node_execution_id=str(uuid.uuid4()),
+            )
+            session.add(draft_var1)
+            session.add(draft_var2)
+            session.add(draft_var3)
+            session.commit()
+
+            data = {
+                "app": app,
+                "tenant": tenant,
+                "upload_files": [upload_file1, upload_file2],
+                "variable_files": [var_file1, var_file2],
+                "draft_variables": [draft_var1, draft_var2, draft_var3],
+            }
+
+        yield data
+
+        with session_factory.create_session() as session:
+            for table, ids in [
+                (WorkflowDraftVariable, [v.id for v in data["draft_variables"]]),
+                (WorkflowDraftVariableFile, [vf.id for vf in data["variable_files"]]),
+                (UploadFile, [uf.id for uf in data["upload_files"]]),
+            ]:
+                cleanup_query = delete(table).where(table.id.in_(ids)).execution_options(synchronize_session=False)
+                session.execute(cleanup_query)
+            session.commit()
+
+    @pytest.fixture
+    def setup_commit_test_data(self, app_and_tenant):
+        """Create test data for session commit tests."""
+        tenant, app = app_and_tenant
+        variable_ids: list[str] = []
+
+        with session_factory.create_session() as session:
+            variables = []
+            for i in range(10):
+                var = WorkflowDraftVariable.new_node_variable(
+                    app_id=app.id,
+                    node_id=f"node_{i}",
+                    name=f"var_{i}",
+                    value=StringSegment(value="test_value"),
+                    node_execution_id=str(uuid.uuid4()),
+                )
+                session.add(var)
+                variables.append(var)
+            session.commit()
+            variable_ids = [v.id for v in variables]
+
+        yield {
+            "app": app,
+            "tenant": tenant,
+            "variable_ids": variable_ids,
+        }
+
+        with session_factory.create_session() as session:
+            cleanup_query = (
+                delete(WorkflowDraftVariable)
+                .where(WorkflowDraftVariable.id.in_(variable_ids))
+                .execution_options(synchronize_session=False)
+            )
+            session.execute(cleanup_query)
+            session.commit()
+
+    def test_session_commit_is_called_after_each_batch(self, setup_commit_test_data):
+        """Test that session.begin() is used for automatic transaction management."""
+        data = setup_commit_test_data
+        app_id = data["app"].id
+
+        # Since session.begin() is used, the transaction is automatically committed
+        # when the with block exits successfully. We verify this by checking that
+        # data is actually persisted.
+        deleted_count = delete_draft_variables_batch(app_id, batch_size=3)
+
+        # Verify all data was deleted (proves transaction was committed)
+        with session_factory.create_session() as session:
+            remaining_count = session.query(WorkflowDraftVariable).filter_by(app_id=app_id).count()
+
+        assert deleted_count == 10
+        assert remaining_count == 0
+
+    def test_data_persisted_after_batch_deletion(self, setup_commit_test_data):
+        """Test that data is actually persisted to database after batch deletion with commits."""
+        data = setup_commit_test_data
+        app_id = data["app"].id
+        variable_ids = data["variable_ids"]
+
+        # Verify initial state
+        with session_factory.create_session() as session:
+            initial_count = session.query(WorkflowDraftVariable).filter_by(app_id=app_id).count()
+        assert initial_count == 10
+
+        # Perform deletion with small batch size to force multiple commits
+        deleted_count = delete_draft_variables_batch(app_id, batch_size=3)
+
+        assert deleted_count == 10
+
+        # Verify all data is deleted in a new session (proves commits worked)
+        with session_factory.create_session() as session:
+            final_count = session.query(WorkflowDraftVariable).filter_by(app_id=app_id).count()
+        assert final_count == 0
+
+        # Verify specific IDs are deleted
+        with session_factory.create_session() as session:
+            remaining_vars = (
+                session.query(WorkflowDraftVariable).where(WorkflowDraftVariable.id.in_(variable_ids)).count()
+            )
+        assert remaining_vars == 0
+
+    def test_session_commit_with_empty_dataset(self, setup_commit_test_data):
+        """Test session behavior when deleting from an empty dataset."""
+        nonexistent_app_id = str(uuid.uuid4())
+
+        # Should not raise any errors and should return 0
+        deleted_count = delete_draft_variables_batch(nonexistent_app_id, batch_size=10)
+        assert deleted_count == 0
+
+    def test_session_commit_with_single_batch(self, setup_commit_test_data):
+        """Test that commit happens correctly when all data fits in a single batch."""
+        data = setup_commit_test_data
+        app_id = data["app"].id
+
+        with session_factory.create_session() as session:
+            initial_count = session.query(WorkflowDraftVariable).filter_by(app_id=app_id).count()
+        assert initial_count == 10
+
+        # Delete all in a single batch
+        deleted_count = delete_draft_variables_batch(app_id, batch_size=100)
+        assert deleted_count == 10
+
+        # Verify data is persisted
+        with session_factory.create_session() as session:
+            final_count = session.query(WorkflowDraftVariable).filter_by(app_id=app_id).count()
+        assert final_count == 0
+
+    def test_invalid_batch_size_raises_error(self, setup_commit_test_data):
+        """Test that invalid batch size raises ValueError."""
+        data = setup_commit_test_data
+        app_id = data["app"].id
+
+        with pytest.raises(ValueError, match="batch_size must be positive"):
+            delete_draft_variables_batch(app_id, batch_size=0)
+
+        with pytest.raises(ValueError, match="batch_size must be positive"):
+            delete_draft_variables_batch(app_id, batch_size=-1)
+
+    @patch("extensions.ext_storage.storage")
+    def test_session_commit_with_offload_data_cleanup(self, mock_storage, setup_offload_test_data):
+        """Test that session commits correctly when cleaning up offload data."""
+        data = setup_offload_test_data
+        app_id = data["app"].id
+        upload_file_ids = [uf.id for uf in data["upload_files"]]
+        mock_storage.delete.return_value = None
+
+        # Verify initial state
+        with session_factory.create_session() as session:
+            draft_vars_before = session.query(WorkflowDraftVariable).filter_by(app_id=app_id).count()
+            var_files_before = (
+                session.query(WorkflowDraftVariableFile)
+                .where(WorkflowDraftVariableFile.id.in_([vf.id for vf in data["variable_files"]]))
+                .count()
+            )
+            upload_files_before = session.query(UploadFile).where(UploadFile.id.in_(upload_file_ids)).count()
+        assert draft_vars_before == 3
+        assert var_files_before == 2
+        assert upload_files_before == 2
+
+        # Delete variables with offload data
+        deleted_count = delete_draft_variables_batch(app_id, batch_size=10)
+        assert deleted_count == 3
+
+        # Verify all data is persisted (deleted) in new session
+        with session_factory.create_session() as session:
+            draft_vars_after = session.query(WorkflowDraftVariable).filter_by(app_id=app_id).count()
+            var_files_after = (
+                session.query(WorkflowDraftVariableFile)
+                .where(WorkflowDraftVariableFile.id.in_([vf.id for vf in data["variable_files"]]))
+                .count()
+            )
+            upload_files_after = session.query(UploadFile).where(UploadFile.id.in_(upload_file_ids)).count()
+        assert draft_vars_after == 0
+        assert var_files_after == 0
+        assert upload_files_after == 0
+
+        # Verify storage cleanup was called
+        assert mock_storage.delete.call_count == 2

api/tests/test_containers_integration_tests/libs/test_auto_renew_redis_lock_integration.py

@@ -0,0 +1,38 @@
+"""
+Integration tests for DbMigrationAutoRenewLock using real Redis via TestContainers.
+"""
+
+import time
+import uuid
+
+import pytest
+
+from extensions.ext_redis import redis_client
+from libs.db_migration_lock import DbMigrationAutoRenewLock
+
+
+@pytest.mark.usefixtures("flask_app_with_containers")
+def test_db_migration_lock_renews_ttl_and_releases():
+    lock_name = f"test:db_migration_auto_renew_lock:{uuid.uuid4().hex}"
+
+    # Keep base TTL very small, and renew frequently so the test is stable even on slower CI.
+    lock = DbMigrationAutoRenewLock(
+        redis_client=redis_client,
+        name=lock_name,
+        ttl_seconds=1.0,
+        renew_interval_seconds=0.2,
+        log_context="test_db_migration_lock",
+    )
+
+    acquired = lock.acquire(blocking=True, blocking_timeout=5)
+    assert acquired is True
+
+    # Wait beyond the base TTL; key should still exist due to renewal.
+    time.sleep(1.5)
+    ttl = redis_client.ttl(lock_name)
+    assert ttl > 0
+
+    lock.release_safely(status="successful")
+
+    # After release, the key should not exist.
+    assert redis_client.exists(lock_name) == 0

api/tests/test_containers_integration_tests/tasks/test_batch_create_segment_to_index_task.py

@@ -605,26 +605,20 @@ class TestBatchCreateSegmentToIndexTask:
 
         mock_storage.download.side_effect = mock_download
 
-        # Execute the task
+        # Execute the task - should raise ValueError for empty CSV
         job_id = str(uuid.uuid4())
-        batch_create_segment_to_index_task(
-            job_id=job_id,
-            upload_file_id=upload_file.id,
-            dataset_id=dataset.id,
-            document_id=document.id,
-            tenant_id=tenant.id,
-            user_id=account.id,
-        )
+        with pytest.raises(ValueError, match="The CSV file is empty"):
+            batch_create_segment_to_index_task(
+                job_id=job_id,
+                upload_file_id=upload_file.id,
+                dataset_id=dataset.id,
+                document_id=document.id,
+                tenant_id=tenant.id,
+                user_id=account.id,
+            )
 
         # Verify error handling
-        # Check Redis cache was set to error status
-        from extensions.ext_redis import redis_client
-
-        cache_key = f"segment_batch_import_{job_id}"
-        cache_value = redis_client.get(cache_key)
-        assert cache_value == b"error"
-
-        # Verify no segments were created
+        # Since exception was raised, no segments should be created
         from extensions.ext_database import db
 
         segments = db.session.query(DocumentSegment).all()

api/tests/test_containers_integration_tests/tasks/test_clean_notion_document_task.py

@@ -153,8 +153,7 @@ class TestCleanNotionDocumentTask:
         # Execute cleanup task
         clean_notion_document_task(document_ids, dataset.id)
 
-        # Verify documents and segments are deleted
-        assert db_session_with_containers.query(Document).filter(Document.id.in_(document_ids)).count() == 0
+        # Verify segments are deleted
         assert (
             db_session_with_containers.query(DocumentSegment)
             .filter(DocumentSegment.document_id.in_(document_ids))
@@ -162,9 +161,9 @@ class TestCleanNotionDocumentTask:
             == 0
         )
 
-        # Verify index processor was called for each document
+        # Verify index processor was called
         mock_processor = mock_index_processor_factory.return_value.init_index_processor.return_value
-        assert mock_processor.clean.call_count == len(document_ids)
+        mock_processor.clean.assert_called_once()
 
         # This test successfully verifies:
         # 1. Document records are properly deleted from the database
@@ -186,12 +185,12 @@ class TestCleanNotionDocumentTask:
         non_existent_dataset_id = str(uuid.uuid4())
         document_ids = [str(uuid.uuid4()), str(uuid.uuid4())]
 
-        # Execute cleanup task with non-existent dataset
-        clean_notion_document_task(document_ids, non_existent_dataset_id)
+        # Execute cleanup task with non-existent dataset - expect exception
+        with pytest.raises(Exception, match="Document has no dataset"):
+            clean_notion_document_task(document_ids, non_existent_dataset_id)
 
-        # Verify that the index processor was not called
-        mock_processor = mock_index_processor_factory.return_value.init_index_processor.return_value
-        mock_processor.clean.assert_not_called()
+        # Verify that the index processor factory was not used
+        mock_index_processor_factory.return_value.init_index_processor.assert_not_called()
 
     def test_clean_notion_document_task_empty_document_list(
         self, db_session_with_containers, mock_index_processor_factory, mock_external_service_dependencies
@@ -229,9 +228,13 @@ class TestCleanNotionDocumentTask:
         # Execute cleanup task with empty document list
         clean_notion_document_task([], dataset.id)
 
-        # Verify that the index processor was not called
+        # Verify that the index processor was called once with empty node list
         mock_processor = mock_index_processor_factory.return_value.init_index_processor.return_value
-        mock_processor.clean.assert_not_called()
+        assert mock_processor.clean.call_count == 1
+        args, kwargs = mock_processor.clean.call_args
+        # args: (dataset, total_index_node_ids)
+        assert isinstance(args[0], Dataset)
+        assert args[1] == []
 
     def test_clean_notion_document_task_with_different_index_types(
         self, db_session_with_containers, mock_index_processor_factory, mock_external_service_dependencies
@@ -315,8 +318,7 @@ class TestCleanNotionDocumentTask:
             # Note: This test successfully verifies cleanup with different document types.
             # The task properly handles various index types and document configurations.
 
-            # Verify documents and segments are deleted
-            assert db_session_with_containers.query(Document).filter(Document.id == document.id).count() == 0
+            # Verify segments are deleted
             assert (
                 db_session_with_containers.query(DocumentSegment)
                 .filter(DocumentSegment.document_id == document.id)
@@ -404,8 +406,7 @@ class TestCleanNotionDocumentTask:
         # Execute cleanup task
         clean_notion_document_task([document.id], dataset.id)
 
-        # Verify documents and segments are deleted
-        assert db_session_with_containers.query(Document).filter(Document.id == document.id).count() == 0
+        # Verify segments are deleted
         assert (
             db_session_with_containers.query(DocumentSegment).filter(DocumentSegment.document_id == document.id).count()
             == 0
@@ -508,8 +509,7 @@ class TestCleanNotionDocumentTask:
 
         clean_notion_document_task(documents_to_clean, dataset.id)
 
-        # Verify only specified documents and segments are deleted
-        assert db_session_with_containers.query(Document).filter(Document.id.in_(documents_to_clean)).count() == 0
+        # Verify only specified documents' segments are deleted
         assert (
             db_session_with_containers.query(DocumentSegment)
             .filter(DocumentSegment.document_id.in_(documents_to_clean))
@@ -697,11 +697,12 @@ class TestCleanNotionDocumentTask:
         db_session_with_containers.commit()
 
         # Mock index processor to raise an exception
-        mock_index_processor = mock_index_processor_factory.init_index_processor.return_value
+        mock_index_processor = mock_index_processor_factory.return_value.init_index_processor.return_value
         mock_index_processor.clean.side_effect = Exception("Index processor error")
 
-        # Execute cleanup task - it should handle the exception gracefully
-        clean_notion_document_task([document.id], dataset.id)
+        # Execute cleanup task - current implementation propagates the exception
+        with pytest.raises(Exception, match="Index processor error"):
+            clean_notion_document_task([document.id], dataset.id)
 
         # Note: This test demonstrates the task's error handling capability.
         # Even with external service errors, the database operations complete successfully.
@@ -803,8 +804,7 @@ class TestCleanNotionDocumentTask:
         all_document_ids = [doc.id for doc in documents]
         clean_notion_document_task(all_document_ids, dataset.id)
 
-        # Verify all documents and segments are deleted
-        assert db_session_with_containers.query(Document).filter(Document.dataset_id == dataset.id).count() == 0
+        # Verify all segments are deleted
         assert (
             db_session_with_containers.query(DocumentSegment).filter(DocumentSegment.dataset_id == dataset.id).count()
             == 0
@@ -914,8 +914,7 @@ class TestCleanNotionDocumentTask:
 
         clean_notion_document_task([target_document.id], target_dataset.id)
 
-        # Verify only documents from target dataset are deleted
-        assert db_session_with_containers.query(Document).filter(Document.id == target_document.id).count() == 0
+        # Verify only documents' segments from target dataset are deleted
         assert (
             db_session_with_containers.query(DocumentSegment)
             .filter(DocumentSegment.document_id == target_document.id)
@@ -1030,8 +1029,7 @@ class TestCleanNotionDocumentTask:
         all_document_ids = [doc.id for doc in documents]
         clean_notion_document_task(all_document_ids, dataset.id)
 
-        # Verify all documents and segments are deleted regardless of status
-        assert db_session_with_containers.query(Document).filter(Document.dataset_id == dataset.id).count() == 0
+        # Verify all segments are deleted regardless of status
         assert (
             db_session_with_containers.query(DocumentSegment).filter(DocumentSegment.dataset_id == dataset.id).count()
             == 0
@@ -1142,8 +1140,7 @@ class TestCleanNotionDocumentTask:
         # Execute cleanup task
         clean_notion_document_task([document.id], dataset.id)
 
-        # Verify documents and segments are deleted
-        assert db_session_with_containers.query(Document).filter(Document.id == document.id).count() == 0
+        # Verify segments are deleted
         assert (
             db_session_with_containers.query(DocumentSegment).filter(DocumentSegment.document_id == document.id).count()
             == 0

api/tests/test_containers_integration_tests/tasks/test_document_indexing_update_task.py

@@ -0,0 +1,182 @@
+from unittest.mock import MagicMock, patch
+
+import pytest
+from faker import Faker
+
+from models import Account, Tenant, TenantAccountJoin, TenantAccountRole
+from models.dataset import Dataset, Document, DocumentSegment
+from tasks.document_indexing_update_task import document_indexing_update_task
+
+
+class TestDocumentIndexingUpdateTask:
+    @pytest.fixture
+    def mock_external_dependencies(self):
+        """Patch external collaborators used by the update task.
+        - IndexProcessorFactory.init_index_processor().clean(...)
+        - IndexingRunner.run([...])
+        """
+        with (
+            patch("tasks.document_indexing_update_task.IndexProcessorFactory") as mock_factory,
+            patch("tasks.document_indexing_update_task.IndexingRunner") as mock_runner,
+        ):
+            processor_instance = MagicMock()
+            mock_factory.return_value.init_index_processor.return_value = processor_instance
+
+            runner_instance = MagicMock()
+            mock_runner.return_value = runner_instance
+
+            yield {
+                "factory": mock_factory,
+                "processor": processor_instance,
+                "runner": mock_runner,
+                "runner_instance": runner_instance,
+            }
+
+    def _create_dataset_document_with_segments(self, db_session_with_containers, *, segment_count: int = 2):
+        fake = Faker()
+
+        # Account and tenant
+        account = Account(
+            email=fake.email(),
+            name=fake.name(),
+            interface_language="en-US",
+            status="active",
+        )
+        db_session_with_containers.add(account)
+        db_session_with_containers.commit()
+
+        tenant = Tenant(name=fake.company(), status="normal")
+        db_session_with_containers.add(tenant)
+        db_session_with_containers.commit()
+
+        join = TenantAccountJoin(
+            tenant_id=tenant.id,
+            account_id=account.id,
+            role=TenantAccountRole.OWNER,
+            current=True,
+        )
+        db_session_with_containers.add(join)
+        db_session_with_containers.commit()
+
+        # Dataset and document
+        dataset = Dataset(
+            tenant_id=tenant.id,
+            name=fake.company(),
+            description=fake.text(max_nb_chars=64),
+            data_source_type="upload_file",
+            indexing_technique="high_quality",
+            created_by=account.id,
+        )
+        db_session_with_containers.add(dataset)
+        db_session_with_containers.commit()
+
+        document = Document(
+            tenant_id=tenant.id,
+            dataset_id=dataset.id,
+            position=0,
+            data_source_type="upload_file",
+            batch="test_batch",
+            name=fake.file_name(),
+            created_from="upload_file",
+            created_by=account.id,
+            indexing_status="waiting",
+            enabled=True,
+            doc_form="text_model",
+        )
+        db_session_with_containers.add(document)
+        db_session_with_containers.commit()
+
+        # Segments
+        node_ids = []
+        for i in range(segment_count):
+            node_id = f"node-{i + 1}"
+            seg = DocumentSegment(
+                tenant_id=tenant.id,
+                dataset_id=dataset.id,
+                document_id=document.id,
+                position=i,
+                content=fake.text(max_nb_chars=32),
+                answer=None,
+                word_count=10,
+                tokens=5,
+                index_node_id=node_id,
+                status="completed",
+                created_by=account.id,
+            )
+            db_session_with_containers.add(seg)
+            node_ids.append(node_id)
+        db_session_with_containers.commit()
+
+        # Refresh to ensure ORM state
+        db_session_with_containers.refresh(dataset)
+        db_session_with_containers.refresh(document)
+
+        return dataset, document, node_ids
+
+    def test_cleans_segments_and_reindexes(self, db_session_with_containers, mock_external_dependencies):
+        dataset, document, node_ids = self._create_dataset_document_with_segments(db_session_with_containers)
+
+        # Act
+        document_indexing_update_task(dataset.id, document.id)
+
+        # Ensure we see committed changes from another session
+        db_session_with_containers.expire_all()
+
+        # Assert document status updated before reindex
+        updated = db_session_with_containers.query(Document).where(Document.id == document.id).first()
+        assert updated.indexing_status == "parsing"
+        assert updated.processing_started_at is not None
+
+        # Segments should be deleted
+        remaining = (
+            db_session_with_containers.query(DocumentSegment).where(DocumentSegment.document_id == document.id).count()
+        )
+        assert remaining == 0
+
+        # Assert index processor clean was called with expected args
+        clean_call = mock_external_dependencies["processor"].clean.call_args
+        assert clean_call is not None
+        args, kwargs = clean_call
+        # args[0] is a Dataset instance (from another session) — validate by id
+        assert getattr(args[0], "id", None) == dataset.id
+        # args[1] should contain our node_ids
+        assert set(args[1]) == set(node_ids)
+        assert kwargs.get("with_keywords") is True
+        assert kwargs.get("delete_child_chunks") is True
+
+        # Assert indexing runner invoked with the updated document
+        run_call = mock_external_dependencies["runner_instance"].run.call_args
+        assert run_call is not None
+        run_docs = run_call[0][0]
+        assert len(run_docs) == 1
+        first = run_docs[0]
+        assert getattr(first, "id", None) == document.id
+
+    def test_clean_error_is_logged_and_indexing_continues(self, db_session_with_containers, mock_external_dependencies):
+        dataset, document, node_ids = self._create_dataset_document_with_segments(db_session_with_containers)
+
+        # Force clean to raise; task should continue to indexing
+        mock_external_dependencies["processor"].clean.side_effect = Exception("boom")
+
+        document_indexing_update_task(dataset.id, document.id)
+
+        # Ensure we see committed changes from another session
+        db_session_with_containers.expire_all()
+
+        # Indexing should still be triggered
+        mock_external_dependencies["runner_instance"].run.assert_called_once()
+
+        # Segments should remain (since clean failed before DB delete)
+        remaining = (
+            db_session_with_containers.query(DocumentSegment).where(DocumentSegment.document_id == document.id).count()
+        )
+        assert remaining > 0
+
+    def test_document_not_found_noop(self, db_session_with_containers, mock_external_dependencies):
+        fake = Faker()
+        # Act with non-existent document id
+        document_indexing_update_task(dataset_id=fake.uuid4(), document_id=fake.uuid4())
+
+        # Neither processor nor runner should be called
+        mock_external_dependencies["processor"].clean.assert_not_called()
+        mock_external_dependencies["runner_instance"].run.assert_not_called()

api/tests/unit_tests/commands/test_upgrade_db.py

@@ -0,0 +1,146 @@
+import sys
+import threading
+import types
+from unittest.mock import MagicMock
+
+import commands
+from libs.db_migration_lock import LockNotOwnedError, RedisError
+
+HEARTBEAT_WAIT_TIMEOUT_SECONDS = 5.0
+
+
+def _install_fake_flask_migrate(monkeypatch, upgrade_impl) -> None:
+    module = types.ModuleType("flask_migrate")
+    module.upgrade = upgrade_impl
+    monkeypatch.setitem(sys.modules, "flask_migrate", module)
+
+
+def _invoke_upgrade_db() -> int:
+    try:
+        commands.upgrade_db.callback()
+    except SystemExit as e:
+        return int(e.code or 0)
+    return 0
+
+
+def test_upgrade_db_skips_when_lock_not_acquired(monkeypatch, capsys):
+    monkeypatch.setattr(commands, "DB_UPGRADE_LOCK_TTL_SECONDS", 1234)
+
+    lock = MagicMock()
+    lock.acquire.return_value = False
+    commands.redis_client.lock.return_value = lock
+
+    exit_code = _invoke_upgrade_db()
+    captured = capsys.readouterr()
+
+    assert exit_code == 0
+    assert "Database migration skipped" in captured.out
+
+    commands.redis_client.lock.assert_called_once_with(name="db_upgrade_lock", timeout=1234, thread_local=False)
+    lock.acquire.assert_called_once_with(blocking=False)
+    lock.release.assert_not_called()
+
+
+def test_upgrade_db_failure_not_masked_by_lock_release(monkeypatch, capsys):
+    monkeypatch.setattr(commands, "DB_UPGRADE_LOCK_TTL_SECONDS", 321)
+
+    lock = MagicMock()
+    lock.acquire.return_value = True
+    lock.release.side_effect = LockNotOwnedError("simulated")
+    commands.redis_client.lock.return_value = lock
+
+    def _upgrade():
+        raise RuntimeError("boom")
+
+    _install_fake_flask_migrate(monkeypatch, _upgrade)
+
+    exit_code = _invoke_upgrade_db()
+    captured = capsys.readouterr()
+
+    assert exit_code == 1
+    assert "Database migration failed: boom" in captured.out
+
+    commands.redis_client.lock.assert_called_once_with(name="db_upgrade_lock", timeout=321, thread_local=False)
+    lock.acquire.assert_called_once_with(blocking=False)
+    lock.release.assert_called_once()
+
+
+def test_upgrade_db_success_ignores_lock_not_owned_on_release(monkeypatch, capsys):
+    monkeypatch.setattr(commands, "DB_UPGRADE_LOCK_TTL_SECONDS", 999)
+
+    lock = MagicMock()
+    lock.acquire.return_value = True
+    lock.release.side_effect = LockNotOwnedError("simulated")
+    commands.redis_client.lock.return_value = lock
+
+    _install_fake_flask_migrate(monkeypatch, lambda: None)
+
+    exit_code = _invoke_upgrade_db()
+    captured = capsys.readouterr()
+
+    assert exit_code == 0
+    assert "Database migration successful!" in captured.out
+
+    commands.redis_client.lock.assert_called_once_with(name="db_upgrade_lock", timeout=999, thread_local=False)
+    lock.acquire.assert_called_once_with(blocking=False)
+    lock.release.assert_called_once()
+
+
+def test_upgrade_db_renews_lock_during_migration(monkeypatch, capsys):
+    """
+    Ensure the lock is renewed while migrations are running, so the base TTL can stay short.
+    """
+
+    # Use a small TTL so the heartbeat interval triggers quickly.
+    monkeypatch.setattr(commands, "DB_UPGRADE_LOCK_TTL_SECONDS", 0.3)
+
+    lock = MagicMock()
+    lock.acquire.return_value = True
+    commands.redis_client.lock.return_value = lock
+
+    renewed = threading.Event()
+
+    def _reacquire():
+        renewed.set()
+        return True
+
+    lock.reacquire.side_effect = _reacquire
+
+    def _upgrade():
+        assert renewed.wait(HEARTBEAT_WAIT_TIMEOUT_SECONDS)
+
+    _install_fake_flask_migrate(monkeypatch, _upgrade)
+
+    exit_code = _invoke_upgrade_db()
+    _ = capsys.readouterr()
+
+    assert exit_code == 0
+    assert lock.reacquire.call_count >= 1
+
+
+def test_upgrade_db_ignores_reacquire_errors(monkeypatch, capsys):
+    # Use a small TTL so heartbeat runs during the upgrade call.
+    monkeypatch.setattr(commands, "DB_UPGRADE_LOCK_TTL_SECONDS", 0.3)
+
+    lock = MagicMock()
+    lock.acquire.return_value = True
+    commands.redis_client.lock.return_value = lock
+
+    attempted = threading.Event()
+
+    def _reacquire():
+        attempted.set()
+        raise RedisError("simulated")
+
+    lock.reacquire.side_effect = _reacquire
+
+    def _upgrade():
+        assert attempted.wait(HEARTBEAT_WAIT_TIMEOUT_SECONDS)
+
+    _install_fake_flask_migrate(monkeypatch, _upgrade)
+
+    exit_code = _invoke_upgrade_db()
+    _ = capsys.readouterr()
+
+    assert exit_code == 0
+    assert lock.reacquire.call_count >= 1

api/tests/unit_tests/core/app/task_pipeline/test_message_cycle_manager_optimization.py

@@ -25,15 +25,19 @@ class TestMessageCycleManagerOptimization:
         task_state = Mock()
         return MessageCycleManager(application_generate_entity=mock_application_generate_entity, task_state=task_state)
 
-    def test_get_message_event_type_with_message_file(self, message_cycle_manager):
-        """Test get_message_event_type returns MESSAGE_FILE when message has files."""
+    def test_get_message_event_type_with_assistant_file(self, message_cycle_manager):
+        """Test get_message_event_type returns MESSAGE_FILE when message has assistant-generated files.
+
+        This ensures that AI-generated images (belongs_to='assistant') trigger the MESSAGE_FILE event,
+        allowing the frontend to properly display generated image files with url field.
+        """
         with patch("core.app.task_pipeline.message_cycle_manager.session_factory") as mock_session_factory:
             # Setup mock session and message file
             mock_session = Mock()
             mock_session_factory.create_session.return_value.__enter__.return_value = mock_session
 
             mock_message_file = Mock()
-            # Current implementation uses session.scalar(select(...))
+            mock_message_file.belongs_to = "assistant"
             mock_session.scalar.return_value = mock_message_file
 
             # Execute
@@ -44,6 +48,31 @@ class TestMessageCycleManagerOptimization:
             assert result == StreamEvent.MESSAGE_FILE
             mock_session.scalar.assert_called_once()
 
+    def test_get_message_event_type_with_user_file(self, message_cycle_manager):
+        """Test get_message_event_type returns MESSAGE when message only has user-uploaded files.
+
+        This is a regression test for the issue where user-uploaded images (belongs_to='user')
+        caused the LLM text response to be incorrectly tagged with MESSAGE_FILE event,
+        resulting in broken images in the chat UI. The query filters for belongs_to='assistant',
+        so when only user files exist, the database query returns None, resulting in MESSAGE event type.
+        """
+        with patch("core.app.task_pipeline.message_cycle_manager.session_factory") as mock_session_factory:
+            # Setup mock session and message file
+            mock_session = Mock()
+            mock_session_factory.create_session.return_value.__enter__.return_value = mock_session
+
+            # When querying for assistant files with only user files present, return None
+            # (simulates database query with belongs_to='assistant' filter returning no results)
+            mock_session.scalar.return_value = None
+
+            # Execute
+            with current_app.app_context():
+                result = message_cycle_manager.get_message_event_type("test-message-id")
+
+            # Assert
+            assert result == StreamEvent.MESSAGE
+            mock_session.scalar.assert_called_once()
+
     def test_get_message_event_type_without_message_file(self, message_cycle_manager):
         """Test get_message_event_type returns MESSAGE when message has no files."""
         with patch("core.app.task_pipeline.message_cycle_manager.session_factory") as mock_session_factory:
@@ -69,7 +98,7 @@ class TestMessageCycleManagerOptimization:
             mock_session_factory.create_session.return_value.__enter__.return_value = mock_session
 
             mock_message_file = Mock()
-            # Current implementation uses session.scalar(select(...))
+            mock_message_file.belongs_to = "assistant"
             mock_session.scalar.return_value = mock_message_file
 
             # Execute: compute event type once, then pass to message_to_stream_response

api/tests/unit_tests/factories/test_variable_factory.py

@@ -4,7 +4,7 @@ from typing import Any
 from uuid import uuid4
 
 import pytest
-from hypothesis import given, settings
+from hypothesis import HealthCheck, given, settings
 from hypothesis import strategies as st
 
 from core.file import File, FileTransferMethod, FileType
@@ -493,7 +493,7 @@ def _scalar_value() -> st.SearchStrategy[int | float | str | File | None]:
     )
 
 
-@settings(max_examples=50)
+@settings(max_examples=30, suppress_health_check=[HealthCheck.too_slow, HealthCheck.filter_too_much], deadline=None)
 @given(_scalar_value())
 def test_build_segment_and_extract_values_for_scalar_types(value):
     seg = variable_factory.build_segment(value)
@@ -504,7 +504,7 @@ def test_build_segment_and_extract_values_for_scalar_types(value):
         assert seg.value == value
 
 
-@settings(max_examples=50)
+@settings(max_examples=30, suppress_health_check=[HealthCheck.too_slow, HealthCheck.filter_too_much], deadline=None)
 @given(values=st.lists(_scalar_value(), max_size=20))
 def test_build_segment_and_extract_values_for_array_types(values):
     seg = variable_factory.build_segment(values)

api/tests/unit_tests/tasks/test_dataset_indexing_task.py

@@ -83,23 +83,127 @@ def mock_documents(document_ids, dataset_id):
 def mock_db_session():
     """Mock database session via session_factory.create_session()."""
     with patch("tasks.document_indexing_task.session_factory") as mock_sf:
-        session = MagicMock()
-        # Ensure tests that expect session.close() to be called can observe it via the context manager
-        session.close = MagicMock()
-        cm = MagicMock()
-        cm.__enter__.return_value = session
-        # Link __exit__ to session.close so "close" expectations reflect context manager teardown
+        sessions = []  # Track all created sessions
+        # Shared mock data that all sessions will access
+        shared_mock_data = {"dataset": None, "documents": None, "doc_iter": None}
 
-        def _exit_side_effect(*args, **kwargs):
-            session.close()
+        def create_session_side_effect():
+            session = MagicMock()
+            session.close = MagicMock()
 
-        cm.__exit__.side_effect = _exit_side_effect
-        mock_sf.create_session.return_value = cm
+            # Track commit calls
+            commit_mock = MagicMock()
+            session.commit = commit_mock
+            cm = MagicMock()
+            cm.__enter__.return_value = session
 
-        query = MagicMock()
-        session.query.return_value = query
-        query.where.return_value = query
-        yield session
+            def _exit_side_effect(*args, **kwargs):
+                session.close()
+
+            cm.__exit__.side_effect = _exit_side_effect
+
+            # Support session.begin() for transactions
+            begin_cm = MagicMock()
+            begin_cm.__enter__.return_value = session
+
+            def begin_exit_side_effect(*args, **kwargs):
+                # Auto-commit on transaction exit (like SQLAlchemy)
+                session.commit()
+                # Also mark wrapper's commit as called
+                if sessions:
+                    sessions[0].commit()
+
+            begin_cm.__exit__ = MagicMock(side_effect=begin_exit_side_effect)
+            session.begin = MagicMock(return_value=begin_cm)
+
+            sessions.append(session)
+
+            # Setup query with side_effect to handle both Dataset and Document queries
+            def query_side_effect(*args):
+                query = MagicMock()
+                if args and args[0] == Dataset and shared_mock_data["dataset"] is not None:
+                    where_result = MagicMock()
+                    where_result.first.return_value = shared_mock_data["dataset"]
+                    query.where = MagicMock(return_value=where_result)
+                elif args and args[0] == Document and shared_mock_data["documents"] is not None:
+                    # Support both .first() and .all() calls with chaining
+                    where_result = MagicMock()
+                    where_result.where = MagicMock(return_value=where_result)
+
+                    # Create an iterator for .first() calls if not exists
+                    if shared_mock_data["doc_iter"] is None:
+                        docs = shared_mock_data["documents"] or [None]
+                        shared_mock_data["doc_iter"] = iter(docs)
+
+                    where_result.first = lambda: next(shared_mock_data["doc_iter"], None)
+                    docs_or_empty = shared_mock_data["documents"] or []
+                    where_result.all = MagicMock(return_value=docs_or_empty)
+                    query.where = MagicMock(return_value=where_result)
+                else:
+                    query.where = MagicMock(return_value=query)
+                return query
+
+            session.query = MagicMock(side_effect=query_side_effect)
+            return cm
+
+        mock_sf.create_session.side_effect = create_session_side_effect
+
+        # Create a wrapper that behaves like the first session but has access to all sessions
+        class SessionWrapper:
+            def __init__(self):
+                self._sessions = sessions
+                self._shared_data = shared_mock_data
+                # Create a default session for setup phase
+                self._default_session = MagicMock()
+                self._default_session.close = MagicMock()
+                self._default_session.commit = MagicMock()
+
+                # Support session.begin() for default session too
+                begin_cm = MagicMock()
+                begin_cm.__enter__.return_value = self._default_session
+
+                def default_begin_exit_side_effect(*args, **kwargs):
+                    self._default_session.commit()
+
+                begin_cm.__exit__ = MagicMock(side_effect=default_begin_exit_side_effect)
+                self._default_session.begin = MagicMock(return_value=begin_cm)
+
+                def default_query_side_effect(*args):
+                    query = MagicMock()
+                    if args and args[0] == Dataset and shared_mock_data["dataset"] is not None:
+                        where_result = MagicMock()
+                        where_result.first.return_value = shared_mock_data["dataset"]
+                        query.where = MagicMock(return_value=where_result)
+                    elif args and args[0] == Document and shared_mock_data["documents"] is not None:
+                        where_result = MagicMock()
+                        where_result.where = MagicMock(return_value=where_result)
+
+                        if shared_mock_data["doc_iter"] is None:
+                            docs = shared_mock_data["documents"] or [None]
+                            shared_mock_data["doc_iter"] = iter(docs)
+
+                        where_result.first = lambda: next(shared_mock_data["doc_iter"], None)
+                        docs_or_empty = shared_mock_data["documents"] or []
+                        where_result.all = MagicMock(return_value=docs_or_empty)
+                        query.where = MagicMock(return_value=where_result)
+                    else:
+                        query.where = MagicMock(return_value=query)
+                    return query
+
+                self._default_session.query = MagicMock(side_effect=default_query_side_effect)
+
+            def __getattr__(self, name):
+                # Forward all attribute access to the first session, or default if none created yet
+                target_session = self._sessions[0] if self._sessions else self._default_session
+                return getattr(target_session, name)
+
+            @property
+            def all_sessions(self):
+                """Access all created sessions for testing."""
+                return self._sessions
+
+        wrapper = SessionWrapper()
+        yield wrapper
 
 
 @pytest.fixture
@@ -252,18 +356,9 @@ class TestTaskEnqueuing:
         use the deprecated function.
         """
         # Arrange
-        mock_db_session.query.return_value.where.return_value.first.return_value = mock_dataset
-
-        def mock_query_side_effect(*args):
-            mock_query = MagicMock()
-            if args[0] == Dataset:
-                mock_query.where.return_value.first.return_value = mock_dataset
-            elif args[0] == Document:
-                # Return documents one by one for each call
-                mock_query.where.return_value.first.side_effect = mock_documents
-            return mock_query
-
-        mock_db_session.query.side_effect = mock_query_side_effect
+        # Set shared mock data so all sessions can access it
+        mock_db_session._shared_data["dataset"] = mock_dataset
+        mock_db_session._shared_data["documents"] = mock_documents
 
         with patch("tasks.document_indexing_task.FeatureService.get_features") as mock_features:
             mock_features.return_value.billing.enabled = False
@@ -304,21 +399,9 @@ class TestBatchProcessing:
             doc.processing_started_at = None
             mock_documents.append(doc)
 
-        mock_db_session.query.return_value.where.return_value.first.return_value = mock_dataset
-
-        # Create an iterator for documents
-        doc_iter = iter(mock_documents)
-
-        def mock_query_side_effect(*args):
-            mock_query = MagicMock()
-            if args[0] == Dataset:
-                mock_query.where.return_value.first.return_value = mock_dataset
-            elif args[0] == Document:
-                # Return documents one by one for each call
-                mock_query.where.return_value.first = lambda: next(doc_iter, None)
-            return mock_query
-
-        mock_db_session.query.side_effect = mock_query_side_effect
+        # Set shared mock data so all sessions can access it
+        mock_db_session._shared_data["dataset"] = mock_dataset
+        mock_db_session._shared_data["documents"] = mock_documents
 
         with patch("tasks.document_indexing_task.FeatureService.get_features") as mock_features:
             mock_features.return_value.billing.enabled = False
@@ -357,19 +440,9 @@ class TestBatchProcessing:
             doc.stopped_at = None
             mock_documents.append(doc)
 
-        mock_db_session.query.return_value.where.return_value.first.return_value = mock_dataset
-
-        doc_iter = iter(mock_documents)
-
-        def mock_query_side_effect(*args):
-            mock_query = MagicMock()
-            if args[0] == Dataset:
-                mock_query.where.return_value.first.return_value = mock_dataset
-            elif args[0] == Document:
-                mock_query.where.return_value.first = lambda: next(doc_iter, None)
-            return mock_query
-
-        mock_db_session.query.side_effect = mock_query_side_effect
+        # Set shared mock data so all sessions can access it
+        mock_db_session._shared_data["dataset"] = mock_dataset
+        mock_db_session._shared_data["documents"] = mock_documents
 
         mock_feature_service.get_features.return_value.billing.enabled = True
         mock_feature_service.get_features.return_value.billing.subscription.plan = CloudPlan.PROFESSIONAL
@@ -407,19 +480,9 @@ class TestBatchProcessing:
             doc.stopped_at = None
             mock_documents.append(doc)
 
-        mock_db_session.query.return_value.where.return_value.first.return_value = mock_dataset
-
-        doc_iter = iter(mock_documents)
-
-        def mock_query_side_effect(*args):
-            mock_query = MagicMock()
-            if args[0] == Dataset:
-                mock_query.where.return_value.first.return_value = mock_dataset
-            elif args[0] == Document:
-                mock_query.where.return_value.first = lambda: next(doc_iter, None)
-            return mock_query
-
-        mock_db_session.query.side_effect = mock_query_side_effect
+        # Set shared mock data so all sessions can access it
+        mock_db_session._shared_data["dataset"] = mock_dataset
+        mock_db_session._shared_data["documents"] = mock_documents
 
         mock_feature_service.get_features.return_value.billing.enabled = True
         mock_feature_service.get_features.return_value.billing.subscription.plan = CloudPlan.SANDBOX
@@ -444,7 +507,10 @@ class TestBatchProcessing:
         """
         # Arrange
         document_ids = []
-        mock_db_session.query.return_value.where.return_value.first.return_value = mock_dataset
+
+        # Set shared mock data with empty documents list
+        mock_db_session._shared_data["dataset"] = mock_dataset
+        mock_db_session._shared_data["documents"] = []
 
         with patch("tasks.document_indexing_task.FeatureService.get_features") as mock_features:
             mock_features.return_value.billing.enabled = False
@@ -482,19 +548,9 @@ class TestProgressTracking:
             doc.processing_started_at = None
             mock_documents.append(doc)
 
-        mock_db_session.query.return_value.where.return_value.first.return_value = mock_dataset
-
-        doc_iter = iter(mock_documents)
-
-        def mock_query_side_effect(*args):
-            mock_query = MagicMock()
-            if args[0] == Dataset:
-                mock_query.where.return_value.first.return_value = mock_dataset
-            elif args[0] == Document:
-                mock_query.where.return_value.first = lambda: next(doc_iter, None)
-            return mock_query
-
-        mock_db_session.query.side_effect = mock_query_side_effect
+        # Set shared mock data so all sessions can access it
+        mock_db_session._shared_data["dataset"] = mock_dataset
+        mock_db_session._shared_data["documents"] = mock_documents
 
         with patch("tasks.document_indexing_task.FeatureService.get_features") as mock_features:
             mock_features.return_value.billing.enabled = False
@@ -528,19 +584,9 @@ class TestProgressTracking:
             doc.processing_started_at = None
             mock_documents.append(doc)
 
-        mock_db_session.query.return_value.where.return_value.first.return_value = mock_dataset
-
-        doc_iter = iter(mock_documents)
-
-        def mock_query_side_effect(*args):
-            mock_query = MagicMock()
-            if args[0] == Dataset:
-                mock_query.where.return_value.first.return_value = mock_dataset
-            elif args[0] == Document:
-                mock_query.where.return_value.first = lambda: next(doc_iter, None)
-            return mock_query
-
-        mock_db_session.query.side_effect = mock_query_side_effect
+        # Set shared mock data so all sessions can access it
+        mock_db_session._shared_data["dataset"] = mock_dataset
+        mock_db_session._shared_data["documents"] = mock_documents
 
         with patch("tasks.document_indexing_task.FeatureService.get_features") as mock_features:
             mock_features.return_value.billing.enabled = False
@@ -635,19 +681,9 @@ class TestErrorHandling:
             doc.stopped_at = None
             mock_documents.append(doc)
 
-        mock_db_session.query.return_value.where.return_value.first.return_value = mock_dataset
-
-        doc_iter = iter(mock_documents)
-
-        def mock_query_side_effect(*args):
-            mock_query = MagicMock()
-            if args[0] == Dataset:
-                mock_query.where.return_value.first.return_value = mock_dataset
-            elif args[0] == Document:
-                mock_query.where.return_value.first = lambda: next(doc_iter, None)
-            return mock_query
-
-        mock_db_session.query.side_effect = mock_query_side_effect
+        # Set shared mock data so all sessions can access it
+        mock_db_session._shared_data["dataset"] = mock_dataset
+        mock_db_session._shared_data["documents"] = mock_documents
 
         # Set up to trigger vector space limit error
         mock_feature_service.get_features.return_value.billing.enabled = True
@@ -674,17 +710,9 @@ class TestErrorHandling:
         Errors during indexing should be caught and logged, but not crash the task.
         """
         # Arrange
-        mock_db_session.query.return_value.where.return_value.first.return_value = mock_dataset
-
-        def mock_query_side_effect(*args):
-            mock_query = MagicMock()
-            if args[0] == Dataset:
-                mock_query.where.return_value.first.return_value = mock_dataset
-            elif args[0] == Document:
-                mock_query.where.return_value.first.side_effect = mock_documents
-            return mock_query
-
-        mock_db_session.query.side_effect = mock_query_side_effect
+        # Set shared mock data so all sessions can access it
+        mock_db_session._shared_data["dataset"] = mock_dataset
+        mock_db_session._shared_data["documents"] = mock_documents
 
         # Make IndexingRunner raise an exception
         mock_indexing_runner.run.side_effect = Exception("Indexing failed")
@@ -708,17 +736,9 @@ class TestErrorHandling:
         but not treated as a failure.
         """
         # Arrange
-        mock_db_session.query.return_value.where.return_value.first.return_value = mock_dataset
-
-        def mock_query_side_effect(*args):
-            mock_query = MagicMock()
-            if args[0] == Dataset:
-                mock_query.where.return_value.first.return_value = mock_dataset
-            elif args[0] == Document:
-                mock_query.where.return_value.first.side_effect = mock_documents
-            return mock_query
-
-        mock_db_session.query.side_effect = mock_query_side_effect
+        # Set shared mock data so all sessions can access it
+        mock_db_session._shared_data["dataset"] = mock_dataset
+        mock_db_session._shared_data["documents"] = mock_documents
 
         # Make IndexingRunner raise DocumentIsPausedError
         mock_indexing_runner.run.side_effect = DocumentIsPausedError("Document is paused")
@@ -853,17 +873,9 @@ class TestTaskCancellation:
         Session cleanup should happen in finally block.
         """
         # Arrange
-        mock_db_session.query.return_value.where.return_value.first.return_value = mock_dataset
-
-        def mock_query_side_effect(*args):
-            mock_query = MagicMock()
-            if args[0] == Dataset:
-                mock_query.where.return_value.first.return_value = mock_dataset
-            elif args[0] == Document:
-                mock_query.where.return_value.first.side_effect = mock_documents
-            return mock_query
-
-        mock_db_session.query.side_effect = mock_query_side_effect
+        # Set shared mock data so all sessions can access it
+        mock_db_session._shared_data["dataset"] = mock_dataset
+        mock_db_session._shared_data["documents"] = mock_documents
 
         with patch("tasks.document_indexing_task.FeatureService.get_features") as mock_features:
             mock_features.return_value.billing.enabled = False
@@ -883,17 +895,9 @@ class TestTaskCancellation:
         Session cleanup should happen even when errors occur.
         """
         # Arrange
-        mock_db_session.query.return_value.where.return_value.first.return_value = mock_dataset
-
-        def mock_query_side_effect(*args):
-            mock_query = MagicMock()
-            if args[0] == Dataset:
-                mock_query.where.return_value.first.return_value = mock_dataset
-            elif args[0] == Document:
-                mock_query.where.return_value.first.side_effect = mock_documents
-            return mock_query
-
-        mock_db_session.query.side_effect = mock_query_side_effect
+        # Set shared mock data so all sessions can access it
+        mock_db_session._shared_data["dataset"] = mock_dataset
+        mock_db_session._shared_data["documents"] = mock_documents
 
         # Make IndexingRunner raise an exception
         mock_indexing_runner.run.side_effect = Exception("Test error")
@@ -962,6 +966,7 @@ class TestAdvancedScenarios:
         document_ids = [str(uuid.uuid4()) for _ in range(3)]
 
         # Create only 2 documents (simulate one missing)
+        # The new code uses .all() which will only return existing documents
         mock_documents = []
         for i, doc_id in enumerate([document_ids[0], document_ids[2]]):  # Skip middle one
             doc = MagicMock(spec=Document)
@@ -971,21 +976,9 @@ class TestAdvancedScenarios:
             doc.processing_started_at = None
             mock_documents.append(doc)
 
-        mock_db_session.query.return_value.where.return_value.first.return_value = mock_dataset
-
-        # Create iterator that returns None for missing document
-        doc_responses = [mock_documents[0], None, mock_documents[1]]
-        doc_iter = iter(doc_responses)
-
-        def mock_query_side_effect(*args):
-            mock_query = MagicMock()
-            if args[0] == Dataset:
-                mock_query.where.return_value.first.return_value = mock_dataset
-            elif args[0] == Document:
-                mock_query.where.return_value.first = lambda: next(doc_iter, None)
-            return mock_query
-
-        mock_db_session.query.side_effect = mock_query_side_effect
+        # Set shared mock data - .all() will only return existing documents
+        mock_db_session._shared_data["dataset"] = mock_dataset
+        mock_db_session._shared_data["documents"] = mock_documents
 
         with patch("tasks.document_indexing_task.FeatureService.get_features") as mock_features:
             mock_features.return_value.billing.enabled = False
@@ -1075,19 +1068,9 @@ class TestAdvancedScenarios:
             doc.stopped_at = None
             mock_documents.append(doc)
 
-        mock_db_session.query.return_value.where.return_value.first.return_value = mock_dataset
-
-        doc_iter = iter(mock_documents)
-
-        def mock_query_side_effect(*args):
-            mock_query = MagicMock()
-            if args[0] == Dataset:
-                mock_query.where.return_value.first.return_value = mock_dataset
-            elif args[0] == Document:
-                mock_query.where.return_value.first = lambda: next(doc_iter, None)
-            return mock_query
-
-        mock_db_session.query.side_effect = mock_query_side_effect
+        # Set shared mock data so all sessions can access it
+        mock_db_session._shared_data["dataset"] = mock_dataset
+        mock_db_session._shared_data["documents"] = mock_documents
 
         # Set vector space exactly at limit
         mock_feature_service.get_features.return_value.billing.enabled = True
@@ -1219,19 +1202,9 @@ class TestAdvancedScenarios:
             doc.processing_started_at = None
             mock_documents.append(doc)
 
-        mock_db_session.query.return_value.where.return_value.first.return_value = mock_dataset
-
-        doc_iter = iter(mock_documents)
-
-        def mock_query_side_effect(*args):
-            mock_query = MagicMock()
-            if args[0] == Dataset:
-                mock_query.where.return_value.first.return_value = mock_dataset
-            elif args[0] == Document:
-                mock_query.where.return_value.first = lambda: next(doc_iter, None)
-            return mock_query
-
-        mock_db_session.query.side_effect = mock_query_side_effect
+        # Set shared mock data so all sessions can access it
+        mock_db_session._shared_data["dataset"] = mock_dataset
+        mock_db_session._shared_data["documents"] = mock_documents
 
         # Billing disabled - limits should not be checked
         mock_feature_service.get_features.return_value.billing.enabled = False
@@ -1273,19 +1246,9 @@ class TestIntegration:
 
         # Set up rpop to return None for concurrency check (no more tasks)
         mock_redis.rpop.side_effect = [None]
-        mock_db_session.query.return_value.where.return_value.first.return_value = mock_dataset
-
-        doc_iter = iter(mock_documents)
-
-        def mock_query_side_effect(*args):
-            mock_query = MagicMock()
-            if args[0] == Dataset:
-                mock_query.where.return_value.first.return_value = mock_dataset
-            elif args[0] == Document:
-                mock_query.where.return_value.first = lambda: next(doc_iter, None)
-            return mock_query
-
-        mock_db_session.query.side_effect = mock_query_side_effect
+        # Set shared mock data so all sessions can access it
+        mock_db_session._shared_data["dataset"] = mock_dataset
+        mock_db_session._shared_data["documents"] = mock_documents
 
         with patch("tasks.document_indexing_task.FeatureService.get_features") as mock_features:
             mock_features.return_value.billing.enabled = False
@@ -1321,19 +1284,9 @@ class TestIntegration:
 
         # Set up rpop to return None for concurrency check (no more tasks)
         mock_redis.rpop.side_effect = [None]
-        mock_db_session.query.return_value.where.return_value.first.return_value = mock_dataset
-
-        doc_iter = iter(mock_documents)
-
-        def mock_query_side_effect(*args):
-            mock_query = MagicMock()
-            if args[0] == Dataset:
-                mock_query.where.return_value.first.return_value = mock_dataset
-            elif args[0] == Document:
-                mock_query.where.return_value.first = lambda: next(doc_iter, None)
-            return mock_query
-
-        mock_db_session.query.side_effect = mock_query_side_effect
+        # Set shared mock data so all sessions can access it
+        mock_db_session._shared_data["dataset"] = mock_dataset
+        mock_db_session._shared_data["documents"] = mock_documents
 
         with patch("tasks.document_indexing_task.FeatureService.get_features") as mock_features:
             mock_features.return_value.billing.enabled = False
@@ -1415,17 +1368,9 @@ class TestEdgeCases:
         mock_document.indexing_status = "waiting"
         mock_document.processing_started_at = None
 
-        mock_db_session.query.return_value.where.return_value.first.return_value = mock_dataset
-
-        def mock_query_side_effect(*args):
-            mock_query = MagicMock()
-            if args[0] == Dataset:
-                mock_query.where.return_value.first.return_value = mock_dataset
-            elif args[0] == Document:
-                mock_query.where.return_value.first = lambda: mock_document
-            return mock_query
-
-        mock_db_session.query.side_effect = mock_query_side_effect
+        # Set shared mock data so all sessions can access it
+        mock_db_session._shared_data["dataset"] = mock_dataset
+        mock_db_session._shared_data["documents"] = [mock_document]
 
         with patch("tasks.document_indexing_task.FeatureService.get_features") as mock_features:
             mock_features.return_value.billing.enabled = False
@@ -1465,17 +1410,9 @@ class TestEdgeCases:
         mock_document.indexing_status = "waiting"
         mock_document.processing_started_at = None
 
-        mock_db_session.query.return_value.where.return_value.first.return_value = mock_dataset
-
-        def mock_query_side_effect(*args):
-            mock_query = MagicMock()
-            if args[0] == Dataset:
-                mock_query.where.return_value.first.return_value = mock_dataset
-            elif args[0] == Document:
-                mock_query.where.return_value.first = lambda: mock_document
-            return mock_query
-
-        mock_db_session.query.side_effect = mock_query_side_effect
+        # Set shared mock data so all sessions can access it
+        mock_db_session._shared_data["dataset"] = mock_dataset
+        mock_db_session._shared_data["documents"] = [mock_document]
 
         with patch("tasks.document_indexing_task.FeatureService.get_features") as mock_features:
             mock_features.return_value.billing.enabled = False
@@ -1555,19 +1492,9 @@ class TestEdgeCases:
             doc.processing_started_at = None
             mock_documents.append(doc)
 
-        mock_db_session.query.return_value.where.return_value.first.return_value = mock_dataset
-
-        doc_iter = iter(mock_documents)
-
-        def mock_query_side_effect(*args):
-            mock_query = MagicMock()
-            if args[0] == Dataset:
-                mock_query.where.return_value.first.return_value = mock_dataset
-            elif args[0] == Document:
-                mock_query.where.return_value.first = lambda: next(doc_iter, None)
-            return mock_query
-
-        mock_db_session.query.side_effect = mock_query_side_effect
+        # Set shared mock data so all sessions can access it
+        mock_db_session._shared_data["dataset"] = mock_dataset
+        mock_db_session._shared_data["documents"] = mock_documents
 
         # Set vector space limit to 0 (unlimited)
         mock_feature_service.get_features.return_value.billing.enabled = True
@@ -1612,19 +1539,9 @@ class TestEdgeCases:
             doc.processing_started_at = None
             mock_documents.append(doc)
 
-        mock_db_session.query.return_value.where.return_value.first.return_value = mock_dataset
-
-        doc_iter = iter(mock_documents)
-
-        def mock_query_side_effect(*args):
-            mock_query = MagicMock()
-            if args[0] == Dataset:
-                mock_query.where.return_value.first.return_value = mock_dataset
-            elif args[0] == Document:
-                mock_query.where.return_value.first = lambda: next(doc_iter, None)
-            return mock_query
-
-        mock_db_session.query.side_effect = mock_query_side_effect
+        # Set shared mock data so all sessions can access it
+        mock_db_session._shared_data["dataset"] = mock_dataset
+        mock_db_session._shared_data["documents"] = mock_documents
 
         # Set negative vector space limit
         mock_feature_service.get_features.return_value.billing.enabled = True
@@ -1675,19 +1592,9 @@ class TestPerformanceScenarios:
             doc.processing_started_at = None
             mock_documents.append(doc)
 
-        mock_db_session.query.return_value.where.return_value.first.return_value = mock_dataset
-
-        doc_iter = iter(mock_documents)
-
-        def mock_query_side_effect(*args):
-            mock_query = MagicMock()
-            if args[0] == Dataset:
-                mock_query.where.return_value.first.return_value = mock_dataset
-            elif args[0] == Document:
-                mock_query.where.return_value.first = lambda: next(doc_iter, None)
-            return mock_query
-
-        mock_db_session.query.side_effect = mock_query_side_effect
+        # Set shared mock data so all sessions can access it
+        mock_db_session._shared_data["dataset"] = mock_dataset
+        mock_db_session._shared_data["documents"] = mock_documents
 
         # Configure billing with sufficient limits
         mock_feature_service.get_features.return_value.billing.enabled = True
@@ -1826,19 +1733,9 @@ class TestRobustness:
             doc.processing_started_at = None
             mock_documents.append(doc)
 
-        mock_db_session.query.return_value.where.return_value.first.return_value = mock_dataset
-
-        doc_iter = iter(mock_documents)
-
-        def mock_query_side_effect(*args):
-            mock_query = MagicMock()
-            if args[0] == Dataset:
-                mock_query.where.return_value.first.return_value = mock_dataset
-            elif args[0] == Document:
-                mock_query.where.return_value.first = lambda: next(doc_iter, None)
-            return mock_query
-
-        mock_db_session.query.side_effect = mock_query_side_effect
+        # Set shared mock data so all sessions can access it
+        mock_db_session._shared_data["dataset"] = mock_dataset
+        mock_db_session._shared_data["documents"] = mock_documents
 
         # Make IndexingRunner raise an exception
         mock_indexing_runner.run.side_effect = RuntimeError("Unexpected indexing error")
@@ -1866,7 +1763,7 @@ class TestRobustness:
         - No exceptions occur
 
         Expected behavior:
-        - Database session is closed
+        - All database sessions are closed
         - No connection leaks
         """
         # Arrange
@@ -1879,19 +1776,9 @@ class TestRobustness:
             doc.processing_started_at = None
             mock_documents.append(doc)
 
-        mock_db_session.query.return_value.where.return_value.first.return_value = mock_dataset
-
-        doc_iter = iter(mock_documents)
-
-        def mock_query_side_effect(*args):
-            mock_query = MagicMock()
-            if args[0] == Dataset:
-                mock_query.where.return_value.first.return_value = mock_dataset
-            elif args[0] == Document:
-                mock_query.where.return_value.first = lambda: next(doc_iter, None)
-            return mock_query
-
-        mock_db_session.query.side_effect = mock_query_side_effect
+        # Set shared mock data so all sessions can access it
+        mock_db_session._shared_data["dataset"] = mock_dataset
+        mock_db_session._shared_data["documents"] = mock_documents
 
         with patch("tasks.document_indexing_task.FeatureService.get_features") as mock_features:
             mock_features.return_value.billing.enabled = False
@@ -1899,10 +1786,11 @@ class TestRobustness:
             # Act
             _document_indexing(dataset_id, document_ids)
 
-            # Assert
-            assert mock_db_session.close.called
-            # Verify close is called exactly once
-            assert mock_db_session.close.call_count == 1
+            # Assert - All created sessions should be closed
+            # The code creates multiple sessions: validation, Phase 1 (parsing), Phase 3 (summary)
+            assert len(mock_db_session.all_sessions) >= 1
+            for session in mock_db_session.all_sessions:
+                assert session.close.called, "All sessions should be closed"
 
     def test_task_proxy_handles_feature_service_failure(self, tenant_id, dataset_id, document_ids, mock_redis):
         """

api/tests/unit_tests/tasks/test_document_indexing_sync_task.py

@@ -109,25 +109,87 @@ def mock_document_segments(document_id):
 
 @pytest.fixture
 def mock_db_session():
-    """Mock database session via session_factory.create_session()."""
+    """Mock database session via session_factory.create_session().
+
+    After session split refactor, the code calls create_session() multiple times.
+    This fixture creates shared query mocks so all sessions use the same
+    query configuration, simulating database persistence across sessions.
+
+    The fixture automatically converts side_effect to cycle to prevent StopIteration.
+    Tests configure mocks the same way as before, but behind the scenes the values
+    are cycled infinitely for all sessions.
+    """
+    from itertools import cycle
+
     with patch("tasks.document_indexing_sync_task.session_factory") as mock_sf:
-        session = MagicMock()
-        # Ensure tests can observe session.close() via context manager teardown
-        session.close = MagicMock()
-        cm = MagicMock()
-        cm.__enter__.return_value = session
+        sessions = []
 
-        def _exit_side_effect(*args, **kwargs):
-            session.close()
+        # Shared query mocks - all sessions use these
+        shared_query = MagicMock()
+        shared_filter_by = MagicMock()
+        shared_scalars_result = MagicMock()
 
-        cm.__exit__.side_effect = _exit_side_effect
-        mock_sf.create_session.return_value = cm
+        # Create custom first mock that auto-cycles side_effect
+        class CyclicMock(MagicMock):
+            def __setattr__(self, name, value):
+                if name == "side_effect" and value is not None:
+                    # Convert list/tuple to infinite cycle
+                    if isinstance(value, (list, tuple)):
+                        value = cycle(value)
+                super().__setattr__(name, value)
 
-        query = MagicMock()
-        session.query.return_value = query
-        query.where.return_value = query
-        session.scalars.return_value = MagicMock()
-        yield session
+        shared_query.where.return_value.first = CyclicMock()
+        shared_filter_by.first = CyclicMock()
+
+        def _create_session():
+            """Create a new mock session for each create_session() call."""
+            session = MagicMock()
+            session.close = MagicMock()
+            session.commit = MagicMock()
+
+            # Mock session.begin() context manager
+            begin_cm = MagicMock()
+            begin_cm.__enter__.return_value = session
+
+            def _begin_exit_side_effect(exc_type, exc, tb):
+                # commit on success
+                if exc_type is None:
+                    session.commit()
+                # return False to propagate exceptions
+                return False
+
+            begin_cm.__exit__.side_effect = _begin_exit_side_effect
+            session.begin.return_value = begin_cm
+
+            # Mock create_session() context manager
+            cm = MagicMock()
+            cm.__enter__.return_value = session
+
+            def _exit_side_effect(exc_type, exc, tb):
+                session.close()
+                return False
+
+            cm.__exit__.side_effect = _exit_side_effect
+
+            # All sessions use the same shared query mocks
+            session.query.return_value = shared_query
+            shared_query.where.return_value = shared_query
+            shared_query.filter_by.return_value = shared_filter_by
+            session.scalars.return_value = shared_scalars_result
+
+            sessions.append(session)
+            # Attach helpers on the first created session for assertions across all sessions
+            if len(sessions) == 1:
+                session.get_all_sessions = lambda: sessions
+                session.any_close_called = lambda: any(s.close.called for s in sessions)
+                session.any_commit_called = lambda: any(s.commit.called for s in sessions)
+            return cm
+
+        mock_sf.create_session.side_effect = _create_session
+
+        # Create first session and return it
+        _create_session()
+        yield sessions[0]
 
 
 @pytest.fixture
@@ -186,8 +248,8 @@ class TestDocumentIndexingSyncTask:
         # Act
         document_indexing_sync_task(dataset_id, document_id)
 
-        # Assert
-        mock_db_session.close.assert_called_once()
+        # Assert - at least one session should have been closed
+        assert mock_db_session.any_close_called()
 
     def test_missing_notion_workspace_id(self, mock_db_session, mock_document, dataset_id, document_id):
         """Test that task raises error when notion_workspace_id is missing."""
@@ -230,6 +292,7 @@ class TestDocumentIndexingSyncTask:
         """Test that task handles missing credentials by updating document status."""
         # Arrange
         mock_db_session.query.return_value.where.return_value.first.return_value = mock_document
+        mock_db_session.query.return_value.filter_by.return_value.first.return_value = mock_document
         mock_datasource_provider_service.get_datasource_credentials.return_value = None
 
         # Act
@@ -239,8 +302,8 @@ class TestDocumentIndexingSyncTask:
         assert mock_document.indexing_status == "error"
         assert "Datasource credential not found" in mock_document.error
         assert mock_document.stopped_at is not None
-        mock_db_session.commit.assert_called()
-        mock_db_session.close.assert_called()
+        assert mock_db_session.any_commit_called()
+        assert mock_db_session.any_close_called()
 
     def test_page_not_updated(
         self,
@@ -254,6 +317,7 @@ class TestDocumentIndexingSyncTask:
         """Test that task does nothing when page has not been updated."""
         # Arrange
         mock_db_session.query.return_value.where.return_value.first.return_value = mock_document
+        mock_db_session.query.return_value.filter_by.return_value.first.return_value = mock_document
         # Return same time as stored in document
         mock_notion_extractor.get_notion_last_edited_time.return_value = "2024-01-01T00:00:00Z"
 
@@ -263,8 +327,8 @@ class TestDocumentIndexingSyncTask:
         # Assert
         # Document status should remain unchanged
         assert mock_document.indexing_status == "completed"
-        # Session should still be closed via context manager teardown
-        assert mock_db_session.close.called
+        # At least one session should have been closed via context manager teardown
+        assert mock_db_session.any_close_called()
 
     def test_successful_sync_when_page_updated(
         self,
@@ -281,7 +345,20 @@ class TestDocumentIndexingSyncTask:
     ):
         """Test successful sync flow when Notion page has been updated."""
         # Arrange
-        mock_db_session.query.return_value.where.return_value.first.side_effect = [mock_document, mock_dataset]
+        # Set exact sequence of returns across calls to `.first()`:
+        # 1) document (initial fetch)
+        # 2) dataset (pre-check)
+        # 3) dataset (cleaning phase)
+        # 4) document (pre-indexing update)
+        # 5) document (indexing runner fetch)
+        mock_db_session.query.return_value.where.return_value.first.side_effect = [
+            mock_document,
+            mock_dataset,
+            mock_dataset,
+            mock_document,
+            mock_document,
+        ]
+        mock_db_session.query.return_value.filter_by.return_value.first.return_value = mock_document
         mock_db_session.scalars.return_value.all.return_value = mock_document_segments
         # NotionExtractor returns updated time
         mock_notion_extractor.get_notion_last_edited_time.return_value = "2024-01-02T00:00:00Z"
@@ -299,28 +376,40 @@ class TestDocumentIndexingSyncTask:
         mock_processor.clean.assert_called_once()
 
         # Verify segments were deleted from database in batch (DELETE FROM document_segments)
-        execute_sqls = [" ".join(str(c[0][0]).split()) for c in mock_db_session.execute.call_args_list]
+        # Aggregate execute calls across all created sessions
+        execute_sqls = []
+        for s in mock_db_session.get_all_sessions():
+            execute_sqls.extend([" ".join(str(c[0][0]).split()) for c in s.execute.call_args_list])
         assert any("DELETE FROM document_segments" in sql for sql in execute_sqls)
 
         # Verify indexing runner was called
         mock_indexing_runner.run.assert_called_once_with([mock_document])
 
-        # Verify session operations
-        assert mock_db_session.commit.called
-        mock_db_session.close.assert_called_once()
+        # Verify session operations (across any created session)
+        assert mock_db_session.any_commit_called()
+        assert mock_db_session.any_close_called()
 
     def test_dataset_not_found_during_cleaning(
         self,
         mock_db_session,
         mock_datasource_provider_service,
         mock_notion_extractor,
+        mock_indexing_runner,
         mock_document,
         dataset_id,
         document_id,
     ):
         """Test that task handles dataset not found during cleaning phase."""
         # Arrange
-        mock_db_session.query.return_value.where.return_value.first.side_effect = [mock_document, None]
+        # Sequence: document (initial), dataset (pre-check), None (cleaning), document (update), document (indexing)
+        mock_db_session.query.return_value.where.return_value.first.side_effect = [
+            mock_document,
+            mock_dataset,
+            None,
+            mock_document,
+            mock_document,
+        ]
+        mock_db_session.query.return_value.filter_by.return_value.first.return_value = mock_document
         mock_notion_extractor.get_notion_last_edited_time.return_value = "2024-01-02T00:00:00Z"
 
         # Act
@@ -329,8 +418,8 @@ class TestDocumentIndexingSyncTask:
         # Assert
         # Document should still be set to parsing
         assert mock_document.indexing_status == "parsing"
-        # Session should be closed after error
-        mock_db_session.close.assert_called_once()
+        # At least one session should be closed after error
+        assert mock_db_session.any_close_called()
 
     def test_cleaning_error_continues_to_indexing(
         self,
@@ -346,8 +435,14 @@ class TestDocumentIndexingSyncTask:
     ):
         """Test that indexing continues even if cleaning fails."""
         # Arrange
-        mock_db_session.query.return_value.where.return_value.first.side_effect = [mock_document, mock_dataset]
-        mock_db_session.scalars.return_value.all.side_effect = Exception("Cleaning error")
+        from itertools import cycle
+
+        mock_db_session.query.return_value.where.return_value.first.side_effect = cycle([mock_document, mock_dataset])
+        mock_db_session.query.return_value.filter_by.return_value.first.return_value = mock_document
+        # Make the cleaning step fail but not the segment fetch
+        processor = mock_index_processor_factory.return_value.init_index_processor.return_value
+        processor.clean.side_effect = Exception("Cleaning error")
+        mock_db_session.scalars.return_value.all.return_value = []
         mock_notion_extractor.get_notion_last_edited_time.return_value = "2024-01-02T00:00:00Z"
 
         # Act
@@ -356,7 +451,7 @@ class TestDocumentIndexingSyncTask:
         # Assert
         # Indexing should still be attempted despite cleaning error
         mock_indexing_runner.run.assert_called_once_with([mock_document])
-        mock_db_session.close.assert_called_once()
+        assert mock_db_session.any_close_called()
 
     def test_indexing_runner_document_paused_error(
         self,
@@ -373,7 +468,10 @@ class TestDocumentIndexingSyncTask:
     ):
         """Test that DocumentIsPausedError is handled gracefully."""
         # Arrange
-        mock_db_session.query.return_value.where.return_value.first.side_effect = [mock_document, mock_dataset]
+        from itertools import cycle
+
+        mock_db_session.query.return_value.where.return_value.first.side_effect = cycle([mock_document, mock_dataset])
+        mock_db_session.query.return_value.filter_by.return_value.first.return_value = mock_document
         mock_db_session.scalars.return_value.all.return_value = mock_document_segments
         mock_notion_extractor.get_notion_last_edited_time.return_value = "2024-01-02T00:00:00Z"
         mock_indexing_runner.run.side_effect = DocumentIsPausedError("Document paused")
@@ -383,7 +481,7 @@ class TestDocumentIndexingSyncTask:
 
         # Assert
         # Session should be closed after handling error
-        mock_db_session.close.assert_called_once()
+        assert mock_db_session.any_close_called()
 
     def test_indexing_runner_general_error(
         self,
@@ -400,7 +498,10 @@ class TestDocumentIndexingSyncTask:
     ):
         """Test that general exceptions during indexing are handled."""
         # Arrange
-        mock_db_session.query.return_value.where.return_value.first.side_effect = [mock_document, mock_dataset]
+        from itertools import cycle
+
+        mock_db_session.query.return_value.where.return_value.first.side_effect = cycle([mock_document, mock_dataset])
+        mock_db_session.query.return_value.filter_by.return_value.first.return_value = mock_document
         mock_db_session.scalars.return_value.all.return_value = mock_document_segments
         mock_notion_extractor.get_notion_last_edited_time.return_value = "2024-01-02T00:00:00Z"
         mock_indexing_runner.run.side_effect = Exception("Indexing error")
@@ -410,7 +511,7 @@ class TestDocumentIndexingSyncTask:
 
         # Assert
         # Session should be closed after error
-        mock_db_session.close.assert_called_once()
+        assert mock_db_session.any_close_called()
 
     def test_notion_extractor_initialized_with_correct_params(
         self,
@@ -517,7 +618,14 @@ class TestDocumentIndexingSyncTask:
     ):
         """Test that index processor clean is called with correct parameters."""
         # Arrange
-        mock_db_session.query.return_value.where.return_value.first.side_effect = [mock_document, mock_dataset]
+        # Sequence: document (initial), dataset (pre-check), dataset (cleaning), document (update), document (indexing)
+        mock_db_session.query.return_value.where.return_value.first.side_effect = [
+            mock_document,
+            mock_dataset,
+            mock_dataset,
+            mock_document,
+            mock_document,
+        ]
         mock_db_session.scalars.return_value.all.return_value = mock_document_segments
         mock_notion_extractor.get_notion_last_edited_time.return_value = "2024-01-02T00:00:00Z"
 

api/tests/unit_tests/tasks/test_remove_app_and_related_data_task.py

@@ -350,7 +350,7 @@ class TestDeleteWorkflowArchiveLogs:
         mock_query.where.return_value = mock_delete_query
         mock_db.session.query.return_value = mock_query
 
-        delete_func("log-1")
+        delete_func(mock_db.session, "log-1")
 
         mock_db.session.query.assert_called_once_with(WorkflowArchiveLog)
         mock_query.where.assert_called_once()

api/uv.lock

@@ -1368,7 +1368,7 @@ wheels = [
 
 [[package]]
 name = "dify-api"
-version = "1.12.0"
+version = "1.12.1"
 source = { virtual = "." }
 dependencies = [
     { name = "aliyun-log-python-sdk" },
@@ -1593,14 +1593,14 @@ requires-dist = [
     { name = "flask-sqlalchemy", specifier = "~=3.1.1" },
     { name = "gevent", specifier = "~=25.9.1" },
     { name = "gmpy2", specifier = "~=2.2.1" },
-    { name = "google-api-core", specifier = "==2.18.0" },
+    { name = "google-api-core", specifier = ">=2.19.1" },
     { name = "google-api-python-client", specifier = "==2.90.0" },
-    { name = "google-auth", specifier = "==2.29.0" },
+    { name = "google-auth", specifier = ">=2.47.0" },
     { name = "google-auth-httplib2", specifier = "==0.2.0" },
-    { name = "google-cloud-aiplatform", specifier = "==1.49.0" },
-    { name = "googleapis-common-protos", specifier = "==1.63.0" },
+    { name = "google-cloud-aiplatform", specifier = ">=1.123.0" },
+    { name = "googleapis-common-protos", specifier = ">=1.65.0" },
     { name = "gunicorn", specifier = "~=23.0.0" },
-    { name = "httpx", extras = ["socks"], specifier = "~=0.27.0" },
+    { name = "httpx", extras = ["socks"], specifier = "~=0.28.0" },
     { name = "httpx-sse", specifier = "~=0.4.0" },
     { name = "jieba", specifier = "==0.42.1" },
     { name = "json-repair", specifier = ">=0.55.1" },
@@ -1612,23 +1612,23 @@ requires-dist = [
     { name = "mlflow-skinny", specifier = ">=3.0.0" },
     { name = "numpy", specifier = "~=1.26.4" },
     { name = "openpyxl", specifier = "~=3.1.5" },
-    { name = "opentelemetry-api", specifier = "==1.27.0" },
-    { name = "opentelemetry-distro", specifier = "==0.48b0" },
-    { name = "opentelemetry-exporter-otlp", specifier = "==1.27.0" },
-    { name = "opentelemetry-exporter-otlp-proto-common", specifier = "==1.27.0" },
-    { name = "opentelemetry-exporter-otlp-proto-grpc", specifier = "==1.27.0" },
-    { name = "opentelemetry-exporter-otlp-proto-http", specifier = "==1.27.0" },
-    { name = "opentelemetry-instrumentation", specifier = "==0.48b0" },
-    { name = "opentelemetry-instrumentation-celery", specifier = "==0.48b0" },
-    { name = "opentelemetry-instrumentation-flask", specifier = "==0.48b0" },
-    { name = "opentelemetry-instrumentation-httpx", specifier = "==0.48b0" },
-    { name = "opentelemetry-instrumentation-redis", specifier = "==0.48b0" },
-    { name = "opentelemetry-instrumentation-sqlalchemy", specifier = "==0.48b0" },
-    { name = "opentelemetry-propagator-b3", specifier = "==1.27.0" },
-    { name = "opentelemetry-proto", specifier = "==1.27.0" },
-    { name = "opentelemetry-sdk", specifier = "==1.27.0" },
-    { name = "opentelemetry-semantic-conventions", specifier = "==0.48b0" },
-    { name = "opentelemetry-util-http", specifier = "==0.48b0" },
+    { name = "opentelemetry-api", specifier = "==1.28.0" },
+    { name = "opentelemetry-distro", specifier = "==0.49b0" },
+    { name = "opentelemetry-exporter-otlp", specifier = "==1.28.0" },
+    { name = "opentelemetry-exporter-otlp-proto-common", specifier = "==1.28.0" },
+    { name = "opentelemetry-exporter-otlp-proto-grpc", specifier = "==1.28.0" },
+    { name = "opentelemetry-exporter-otlp-proto-http", specifier = "==1.28.0" },
+    { name = "opentelemetry-instrumentation", specifier = "==0.49b0" },
+    { name = "opentelemetry-instrumentation-celery", specifier = "==0.49b0" },
+    { name = "opentelemetry-instrumentation-flask", specifier = "==0.49b0" },
+    { name = "opentelemetry-instrumentation-httpx", specifier = "==0.49b0" },
+    { name = "opentelemetry-instrumentation-redis", specifier = "==0.49b0" },
+    { name = "opentelemetry-instrumentation-sqlalchemy", specifier = "==0.49b0" },
+    { name = "opentelemetry-propagator-b3", specifier = "==1.28.0" },
+    { name = "opentelemetry-proto", specifier = "==1.28.0" },
+    { name = "opentelemetry-sdk", specifier = "==1.28.0" },
+    { name = "opentelemetry-semantic-conventions", specifier = "==0.49b0" },
+    { name = "opentelemetry-util-http", specifier = "==0.49b0" },
     { name = "opik", specifier = "~=1.8.72" },
     { name = "packaging", specifier = "~=23.2" },
     { name = "pandas", extras = ["excel", "output-formatting", "performance"], specifier = "~=2.2.2" },
@@ -1653,7 +1653,7 @@ requires-dist = [
     { name = "starlette", specifier = "==0.49.1" },
     { name = "tiktoken", specifier = "~=0.9.0" },
     { name = "transformers", specifier = "~=4.56.1" },
-    { name = "unstructured", extras = ["docx", "epub", "md", "ppt", "pptx"], specifier = "~=0.16.1" },
+    { name = "unstructured", extras = ["docx", "epub", "md", "ppt", "pptx"], specifier = "~=0.18.18" },
     { name = "weave", specifier = ">=0.52.16" },
     { name = "weaviate-client", specifier = "==4.17.0" },
     { name = "webvtt-py", specifier = "~=0.5.1" },
@@ -2284,7 +2284,7 @@ wheels = [
 
 [[package]]
 name = "google-api-core"
-version = "2.18.0"
+version = "2.30.0"
 source = { registry = "https://pypi.org/simple" }
 dependencies = [
     { name = "google-auth" },
@@ -2293,9 +2293,9 @@ dependencies = [
     { name = "protobuf" },
     { name = "requests" },
 ]
-sdist = { url = "https://files.pythonhosted.org/packages/b2/8f/ecd68579bd2bf5e9321df60dcdee6e575adf77fedacb1d8378760b2b16b6/google-api-core-2.18.0.tar.gz", hash = "sha256:62d97417bfc674d6cef251e5c4d639a9655e00c45528c4364fbfebb478ce72a9", size = 148047, upload-time = "2024-03-21T20:16:56.269Z" }
+sdist = { url = "https://files.pythonhosted.org/packages/22/98/586ec94553b569080caef635f98a3723db36a38eac0e3d7eb3ea9d2e4b9a/google_api_core-2.30.0.tar.gz", hash = "sha256:02edfa9fab31e17fc0befb5f161b3bf93c9096d99aed584625f38065c511ad9b", size = 176959, upload-time = "2026-02-18T20:28:11.926Z" }
 wheels = [
-    { url = "https://files.pythonhosted.org/packages/86/75/59a3ad90d9b4ff5b3e0537611dbe885aeb96124521c9d35aa079f1e0f2c9/google_api_core-2.18.0-py3-none-any.whl", hash = "sha256:5a63aa102e0049abe85b5b88cb9409234c1f70afcda21ce1e40b285b9629c1d6", size = 138293, upload-time = "2024-03-21T20:16:53.645Z" },
+    { url = "https://files.pythonhosted.org/packages/45/27/09c33d67f7e0dcf06d7ac17d196594e66989299374bfb0d4331d1038e76b/google_api_core-2.30.0-py3-none-any.whl", hash = "sha256:80be49ee937ff9aba0fd79a6eddfde35fe658b9953ab9b79c57dd7061afa8df5", size = 173288, upload-time = "2026-02-18T20:28:10.367Z" },
 ]
 
 [package.optional-dependencies]
@@ -2322,16 +2322,21 @@ wheels = [
 
 [[package]]
 name = "google-auth"
-version = "2.29.0"
+version = "2.48.0"
 source = { registry = "https://pypi.org/simple" }
 dependencies = [
-    { name = "cachetools" },
+    { name = "cryptography" },
     { name = "pyasn1-modules" },
     { name = "rsa" },
 ]
-sdist = { url = "https://files.pythonhosted.org/packages/18/b2/f14129111cfd61793609643a07ecb03651a71dd65c6974f63b0310ff4b45/google-auth-2.29.0.tar.gz", hash = "sha256:672dff332d073227550ffc7457868ac4218d6c500b155fe6cc17d2b13602c360", size = 244326, upload-time = "2024-03-20T17:24:27.72Z" }
+sdist = { url = "https://files.pythonhosted.org/packages/0c/41/242044323fbd746615884b1c16639749e73665b718209946ebad7ba8a813/google_auth-2.48.0.tar.gz", hash = "sha256:4f7e706b0cd3208a3d940a19a822c37a476ddba5450156c3e6624a71f7c841ce", size = 326522, upload-time = "2026-01-26T19:22:47.157Z" }
 wheels = [
-    { url = "https://files.pythonhosted.org/packages/9e/8d/ddbcf81ec751d8ee5fd18ac11ff38a0e110f39dfbf105e6d9db69d556dd0/google_auth-2.29.0-py2.py3-none-any.whl", hash = "sha256:d452ad095688cd52bae0ad6fafe027f6a6d6f560e810fec20914e17a09526415", size = 189186, upload-time = "2024-03-20T17:24:24.292Z" },
+    { url = "https://files.pythonhosted.org/packages/83/1d/d6466de3a5249d35e832a52834115ca9d1d0de6abc22065f049707516d47/google_auth-2.48.0-py3-none-any.whl", hash = "sha256:2e2a537873d449434252a9632c28bfc268b0adb1e53f9fb62afc5333a975903f", size = 236499, upload-time = "2026-01-26T19:22:45.099Z" },
+]
+
+[package.optional-dependencies]
+requests = [
+    { name = "requests" },
 ]
 
 [[package]]
@@ -2349,7 +2354,7 @@ wheels = [
 
 [[package]]
 name = "google-cloud-aiplatform"
-version = "1.49.0"
+version = "1.139.0"
 source = { registry = "https://pypi.org/simple" }
 dependencies = [
     { name = "docstring-parser" },
@@ -2358,15 +2363,16 @@ dependencies = [
     { name = "google-cloud-bigquery" },
     { name = "google-cloud-resource-manager" },
     { name = "google-cloud-storage" },
+    { name = "google-genai" },
     { name = "packaging" },
     { name = "proto-plus" },
     { name = "protobuf" },
     { name = "pydantic" },
-    { name = "shapely" },
+    { name = "typing-extensions" },
 ]
-sdist = { url = "https://files.pythonhosted.org/packages/47/21/5930a1420f82bec246ae09e1b7cc8458544f3befe669193b33a7b5c0691c/google-cloud-aiplatform-1.49.0.tar.gz", hash = "sha256:e6e6d01079bb5def49e4be4db4d12b13c624b5c661079c869c13c855e5807429", size = 5766450, upload-time = "2024-04-29T17:25:31.646Z" }
+sdist = { url = "https://files.pythonhosted.org/packages/20/40/6767bd4d694354fd55842990da66f7b6ccfdce283d10f65d4a82d9a8e8df/google_cloud_aiplatform-1.139.0.tar.gz", hash = "sha256:cfaa95375bfb79a97b8c949c3ec1600505a4a9c08ca2b01c36ed659a5e05e37c", size = 9964138, upload-time = "2026-02-25T00:51:06.976Z" }
 wheels = [
-    { url = "https://files.pythonhosted.org/packages/39/6a/7d9e1c03c814e760361fe8b0ffd373ead4124ace66ed33bb16d526ae1ecf/google_cloud_aiplatform-1.49.0-py2.py3-none-any.whl", hash = "sha256:8072d9e0c18d8942c704233d1a93b8d6312fc7b278786a283247950e28ae98df", size = 4914049, upload-time = "2024-04-29T17:25:27.625Z" },
+    { url = "https://files.pythonhosted.org/packages/1d/20/a8a77dfdbf2a8169a3cce2d4e9cfbbfc168454ddd435891e59908ea8bf33/google_cloud_aiplatform-1.139.0-py2.py3-none-any.whl", hash = "sha256:3190b255cf510bce9e4b1adc8162ab0b3f9eca48801657d7af058d8e1d5ad9d0", size = 8209776, upload-time = "2026-02-25T00:51:03.526Z" },
 ]
 
 [[package]]
@@ -2454,6 +2460,27 @@ wheels = [
     { url = "https://files.pythonhosted.org/packages/fd/3c/2a19a60a473de48717b4efb19398c3f914795b64a96cf3fbe82588044f78/google_crc32c-1.7.1-pp311-pypy311_pp73-manylinux_2_17_x86_64.manylinux2014_x86_64.whl", hash = "sha256:6efb97eb4369d52593ad6f75e7e10d053cf00c48983f7a973105bc70b0ac4d82", size = 28048, upload-time = "2025-03-26T14:41:46.696Z" },
 ]
 
+[[package]]
+name = "google-genai"
+version = "1.65.0"
+source = { registry = "https://pypi.org/simple" }
+dependencies = [
+    { name = "anyio" },
+    { name = "distro" },
+    { name = "google-auth", extra = ["requests"] },
+    { name = "httpx" },
+    { name = "pydantic" },
+    { name = "requests" },
+    { name = "sniffio" },
+    { name = "tenacity" },
+    { name = "typing-extensions" },
+    { name = "websockets" },
+]
+sdist = { url = "https://files.pythonhosted.org/packages/79/f9/cc1191c2540d6a4e24609a586c4ed45d2db57cfef47931c139ee70e5874a/google_genai-1.65.0.tar.gz", hash = "sha256:d470eb600af802d58a79c7f13342d9ea0d05d965007cae8f76c7adff3d7a4750", size = 497206, upload-time = "2026-02-26T00:20:33.824Z" }
+wheels = [
+    { url = "https://files.pythonhosted.org/packages/68/3c/3fea4e7c91357c71782d7dcaad7a2577d636c90317e003386893c25bc62c/google_genai-1.65.0-py3-none-any.whl", hash = "sha256:68c025205856919bc03edb0155c11b4b833810b7ce17ad4b7a9eeba5158f6c44", size = 724429, upload-time = "2026-02-26T00:20:32.186Z" },
+]
+
 [[package]]
 name = "google-resumable-media"
 version = "2.8.0"
@@ -2468,14 +2495,14 @@ wheels = [
 
 [[package]]
 name = "googleapis-common-protos"
-version = "1.63.0"
+version = "1.72.0"
 source = { registry = "https://pypi.org/simple" }
 dependencies = [
     { name = "protobuf" },
 ]
-sdist = { url = "https://files.pythonhosted.org/packages/d2/dc/291cebf3c73e108ef8210f19cb83d671691354f4f7dd956445560d778715/googleapis-common-protos-1.63.0.tar.gz", hash = "sha256:17ad01b11d5f1d0171c06d3ba5c04c54474e883b66b949722b4938ee2694ef4e", size = 121646, upload-time = "2024-03-11T12:33:15.765Z" }
+sdist = { url = "https://files.pythonhosted.org/packages/e5/7b/adfd75544c415c487b33061fe7ae526165241c1ea133f9a9125a56b39fd8/googleapis_common_protos-1.72.0.tar.gz", hash = "sha256:e55a601c1b32b52d7a3e65f43563e2aa61bcd737998ee672ac9b951cd49319f5", size = 147433, upload-time = "2025-11-06T18:29:24.087Z" }
 wheels = [
-    { url = "https://files.pythonhosted.org/packages/dc/a6/12a0c976140511d8bc8a16ad15793b2aef29ac927baa0786ccb7ddbb6e1c/googleapis_common_protos-1.63.0-py2.py3-none-any.whl", hash = "sha256:ae45f75702f7c08b541f750854a678bd8f534a1a6bace6afe975f1d0a82d6632", size = 229141, upload-time = "2024-03-11T12:33:14.052Z" },
+    { url = "https://files.pythonhosted.org/packages/c4/ab/09169d5a4612a5f92490806649ac8d41e3ec9129c636754575b3553f4ea4/googleapis_common_protos-1.72.0-py3-none-any.whl", hash = "sha256:4299c5a82d5ae1a9702ada957347726b167f9f8d1fc352477702a1e851ff4038", size = 297515, upload-time = "2025-11-06T18:29:13.14Z" },
 ]
 
 [package.optional-dependencies]
@@ -2665,31 +2692,35 @@ wheels = [
 
 [[package]]
 name = "grpcio-tools"
-version = "1.62.3"
+version = "1.71.2"
 source = { registry = "https://pypi.org/simple" }
 dependencies = [
     { name = "grpcio" },
     { name = "protobuf" },
     { name = "setuptools" },
 ]
-sdist = { url = "https://files.pythonhosted.org/packages/54/fa/b69bd8040eafc09b88bb0ec0fea59e8aacd1a801e688af087cead213b0d0/grpcio-tools-1.62.3.tar.gz", hash = "sha256:7c7136015c3d62c3eef493efabaf9e3380e3e66d24ee8e94c01cb71377f57833", size = 4538520, upload-time = "2024-08-06T00:37:11.035Z" }
+sdist = { url = "https://files.pythonhosted.org/packages/ad/9a/edfefb47f11ef6b0f39eea4d8f022c5bb05ac1d14fcc7058e84a51305b73/grpcio_tools-1.71.2.tar.gz", hash = "sha256:b5304d65c7569b21270b568e404a5a843cf027c66552a6a0978b23f137679c09", size = 5330655, upload-time = "2025-06-28T04:22:00.308Z" }
 wheels = [
-    { url = "https://files.pythonhosted.org/packages/23/52/2dfe0a46b63f5ebcd976570aa5fc62f793d5a8b169e211c6a5aede72b7ae/grpcio_tools-1.62.3-cp311-cp311-macosx_10_10_universal2.whl", hash = "sha256:703f46e0012af83a36082b5f30341113474ed0d91e36640da713355cd0ea5d23", size = 5147623, upload-time = "2024-08-06T00:30:54.894Z" },
-    { url = "https://files.pythonhosted.org/packages/f0/2e/29fdc6c034e058482e054b4a3c2432f84ff2e2765c1342d4f0aa8a5c5b9a/grpcio_tools-1.62.3-cp311-cp311-manylinux_2_17_aarch64.whl", hash = "sha256:7cc83023acd8bc72cf74c2edbe85b52098501d5b74d8377bfa06f3e929803492", size = 2719538, upload-time = "2024-08-06T00:30:57.928Z" },
-    { url = "https://files.pythonhosted.org/packages/f9/60/abe5deba32d9ec2c76cdf1a2f34e404c50787074a2fee6169568986273f1/grpcio_tools-1.62.3-cp311-cp311-manylinux_2_17_i686.manylinux2014_i686.whl", hash = "sha256:7ff7d58a45b75df67d25f8f144936a3e44aabd91afec833ee06826bd02b7fbe7", size = 3070964, upload-time = "2024-08-06T00:31:00.267Z" },
-    { url = "https://files.pythonhosted.org/packages/bc/ad/e2b066684c75f8d9a48508cde080a3a36618064b9cadac16d019ca511444/grpcio_tools-1.62.3-cp311-cp311-manylinux_2_17_x86_64.manylinux2014_x86_64.whl", hash = "sha256:7f2483ea232bd72d98a6dc6d7aefd97e5bc80b15cd909b9e356d6f3e326b6e43", size = 2805003, upload-time = "2024-08-06T00:31:02.565Z" },
-    { url = "https://files.pythonhosted.org/packages/9c/3f/59bf7af786eae3f9d24ee05ce75318b87f541d0950190ecb5ffb776a1a58/grpcio_tools-1.62.3-cp311-cp311-musllinux_1_1_i686.whl", hash = "sha256:962c84b4da0f3b14b3cdb10bc3837ebc5f136b67d919aea8d7bb3fd3df39528a", size = 3685154, upload-time = "2024-08-06T00:31:05.339Z" },
-    { url = "https://files.pythonhosted.org/packages/f1/79/4dd62478b91e27084c67b35a2316ce8a967bd8b6cb8d6ed6c86c3a0df7cb/grpcio_tools-1.62.3-cp311-cp311-musllinux_1_1_x86_64.whl", hash = "sha256:8ad0473af5544f89fc5a1ece8676dd03bdf160fb3230f967e05d0f4bf89620e3", size = 3297942, upload-time = "2024-08-06T00:31:08.456Z" },
-    { url = "https://files.pythonhosted.org/packages/b8/cb/86449ecc58bea056b52c0b891f26977afc8c4464d88c738f9648da941a75/grpcio_tools-1.62.3-cp311-cp311-win32.whl", hash = "sha256:db3bc9fa39afc5e4e2767da4459df82b095ef0cab2f257707be06c44a1c2c3e5", size = 910231, upload-time = "2024-08-06T00:31:11.464Z" },
-    { url = "https://files.pythonhosted.org/packages/45/a4/9736215e3945c30ab6843280b0c6e1bff502910156ea2414cd77fbf1738c/grpcio_tools-1.62.3-cp311-cp311-win_amd64.whl", hash = "sha256:e0898d412a434e768a0c7e365acabe13ff1558b767e400936e26b5b6ed1ee51f", size = 1052496, upload-time = "2024-08-06T00:31:13.665Z" },
-    { url = "https://files.pythonhosted.org/packages/2a/a5/d6887eba415ce318ae5005e8dfac3fa74892400b54b6d37b79e8b4f14f5e/grpcio_tools-1.62.3-cp312-cp312-macosx_10_10_universal2.whl", hash = "sha256:d102b9b21c4e1e40af9a2ab3c6d41afba6bd29c0aa50ca013bf85c99cdc44ac5", size = 5147690, upload-time = "2024-08-06T00:31:16.436Z" },
-    { url = "https://files.pythonhosted.org/packages/8a/7c/3cde447a045e83ceb4b570af8afe67ffc86896a2fe7f59594dc8e5d0a645/grpcio_tools-1.62.3-cp312-cp312-manylinux_2_17_aarch64.whl", hash = "sha256:0a52cc9444df978438b8d2332c0ca99000521895229934a59f94f37ed896b133", size = 2720538, upload-time = "2024-08-06T00:31:18.905Z" },
-    { url = "https://files.pythonhosted.org/packages/88/07/f83f2750d44ac4f06c07c37395b9c1383ef5c994745f73c6bfaf767f0944/grpcio_tools-1.62.3-cp312-cp312-manylinux_2_17_i686.manylinux2014_i686.whl", hash = "sha256:141d028bf5762d4a97f981c501da873589df3f7e02f4c1260e1921e565b376fa", size = 3071571, upload-time = "2024-08-06T00:31:21.684Z" },
-    { url = "https://files.pythonhosted.org/packages/37/74/40175897deb61e54aca716bc2e8919155b48f33aafec8043dda9592d8768/grpcio_tools-1.62.3-cp312-cp312-manylinux_2_17_x86_64.manylinux2014_x86_64.whl", hash = "sha256:47a5c093ab256dec5714a7a345f8cc89315cb57c298b276fa244f37a0ba507f0", size = 2806207, upload-time = "2024-08-06T00:31:24.208Z" },
-    { url = "https://files.pythonhosted.org/packages/ec/ee/d8de915105a217cbcb9084d684abdc032030dcd887277f2ef167372287fe/grpcio_tools-1.62.3-cp312-cp312-musllinux_1_1_i686.whl", hash = "sha256:f6831fdec2b853c9daa3358535c55eed3694325889aa714070528cf8f92d7d6d", size = 3685815, upload-time = "2024-08-06T00:31:26.917Z" },
-    { url = "https://files.pythonhosted.org/packages/fd/d9/4360a6c12be3d7521b0b8c39e5d3801d622fbb81cc2721dbd3eee31e28c8/grpcio_tools-1.62.3-cp312-cp312-musllinux_1_1_x86_64.whl", hash = "sha256:e02d7c1a02e3814c94ba0cfe43d93e872c758bd8fd5c2797f894d0c49b4a1dfc", size = 3298378, upload-time = "2024-08-06T00:31:30.401Z" },
-    { url = "https://files.pythonhosted.org/packages/29/3b/7cdf4a9e5a3e0a35a528b48b111355cd14da601413a4f887aa99b6da468f/grpcio_tools-1.62.3-cp312-cp312-win32.whl", hash = "sha256:b881fd9505a84457e9f7e99362eeedd86497b659030cf57c6f0070df6d9c2b9b", size = 910416, upload-time = "2024-08-06T00:31:33.118Z" },
-    { url = "https://files.pythonhosted.org/packages/6c/66/dd3ec249e44c1cc15e902e783747819ed41ead1336fcba72bf841f72c6e9/grpcio_tools-1.62.3-cp312-cp312-win_amd64.whl", hash = "sha256:11c625eebefd1fd40a228fc8bae385e448c7e32a6ae134e43cf13bbc23f902b7", size = 1052856, upload-time = "2024-08-06T00:31:36.519Z" },
+    { url = "https://files.pythonhosted.org/packages/17/e4/0568d38b8da6237ea8ea15abb960fb7ab83eb7bb51e0ea5926dab3d865b1/grpcio_tools-1.71.2-cp311-cp311-linux_armv7l.whl", hash = "sha256:0acb8151ea866be5b35233877fbee6445c36644c0aa77e230c9d1b46bf34b18b", size = 2385557, upload-time = "2025-06-28T04:20:54.323Z" },
+    { url = "https://files.pythonhosted.org/packages/76/fb/700d46f72b0f636cf0e625f3c18a4f74543ff127471377e49a071f64f1e7/grpcio_tools-1.71.2-cp311-cp311-macosx_10_14_universal2.whl", hash = "sha256:b28f8606f4123edb4e6da281547465d6e449e89f0c943c376d1732dc65e6d8b3", size = 5447590, upload-time = "2025-06-28T04:20:55.836Z" },
+    { url = "https://files.pythonhosted.org/packages/12/69/d9bb2aec3de305162b23c5c884b9f79b1a195d42b1e6dabcc084cc9d0804/grpcio_tools-1.71.2-cp311-cp311-manylinux_2_17_aarch64.whl", hash = "sha256:cbae6f849ad2d1f5e26cd55448b9828e678cb947fa32c8729d01998238266a6a", size = 2348495, upload-time = "2025-06-28T04:20:57.33Z" },
+    { url = "https://files.pythonhosted.org/packages/d5/83/f840aba1690461b65330efbca96170893ee02fae66651bcc75f28b33a46c/grpcio_tools-1.71.2-cp311-cp311-manylinux_2_17_i686.manylinux2014_i686.whl", hash = "sha256:e4d1027615cfb1e9b1f31f2f384251c847d68c2f3e025697e5f5c72e26ed1316", size = 2742333, upload-time = "2025-06-28T04:20:59.051Z" },
+    { url = "https://files.pythonhosted.org/packages/30/34/c02cd9b37de26045190ba665ee6ab8597d47f033d098968f812d253bbf8c/grpcio_tools-1.71.2-cp311-cp311-manylinux_2_17_x86_64.manylinux2014_x86_64.whl", hash = "sha256:9bac95662dc69338edb9eb727cc3dd92342131b84b12b3e8ec6abe973d4cbf1b", size = 2473490, upload-time = "2025-06-28T04:21:00.614Z" },
+    { url = "https://files.pythonhosted.org/packages/4d/c7/375718ae091c8f5776828ce97bdcb014ca26244296f8b7f70af1a803ed2f/grpcio_tools-1.71.2-cp311-cp311-musllinux_1_1_aarch64.whl", hash = "sha256:c50250c7248055040f89eb29ecad39d3a260a4b6d3696af1575945f7a8d5dcdc", size = 2850333, upload-time = "2025-06-28T04:21:01.95Z" },
+    { url = "https://files.pythonhosted.org/packages/19/37/efc69345bd92a73b2bc80f4f9e53d42dfdc234b2491ae58c87da20ca0ea5/grpcio_tools-1.71.2-cp311-cp311-musllinux_1_1_i686.whl", hash = "sha256:6ab1ad955e69027ef12ace4d700c5fc36341bdc2f420e87881e9d6d02af3d7b8", size = 3300748, upload-time = "2025-06-28T04:21:03.451Z" },
+    { url = "https://files.pythonhosted.org/packages/d2/1f/15f787eb25ae42086f55ed3e4260e85f385921c788debf0f7583b34446e3/grpcio_tools-1.71.2-cp311-cp311-musllinux_1_1_x86_64.whl", hash = "sha256:dd75dde575781262b6b96cc6d0b2ac6002b2f50882bf5e06713f1bf364ee6e09", size = 2913178, upload-time = "2025-06-28T04:21:04.879Z" },
+    { url = "https://files.pythonhosted.org/packages/12/aa/69cb3a9dff7d143a05e4021c3c9b5cde07aacb8eb1c892b7c5b9fb4973e3/grpcio_tools-1.71.2-cp311-cp311-win32.whl", hash = "sha256:9a3cb244d2bfe0d187f858c5408d17cb0e76ca60ec9a274c8fd94cc81457c7fc", size = 946256, upload-time = "2025-06-28T04:21:06.518Z" },
+    { url = "https://files.pythonhosted.org/packages/1e/df/fb951c5c87eadb507a832243942e56e67d50d7667b0e5324616ffd51b845/grpcio_tools-1.71.2-cp311-cp311-win_amd64.whl", hash = "sha256:00eb909997fd359a39b789342b476cbe291f4dd9c01ae9887a474f35972a257e", size = 1117661, upload-time = "2025-06-28T04:21:08.18Z" },
+    { url = "https://files.pythonhosted.org/packages/9c/d3/3ed30a9c5b2424627b4b8411e2cd6a1a3f997d3812dbc6a8630a78bcfe26/grpcio_tools-1.71.2-cp312-cp312-linux_armv7l.whl", hash = "sha256:bfc0b5d289e383bc7d317f0e64c9dfb59dc4bef078ecd23afa1a816358fb1473", size = 2385479, upload-time = "2025-06-28T04:21:10.413Z" },
+    { url = "https://files.pythonhosted.org/packages/54/61/e0b7295456c7e21ef777eae60403c06835160c8d0e1e58ebfc7d024c51d3/grpcio_tools-1.71.2-cp312-cp312-macosx_14_0_arm64.whl", hash = "sha256:b4669827716355fa913b1376b1b985855d5cfdb63443f8d18faf210180199006", size = 5431521, upload-time = "2025-06-28T04:21:12.261Z" },
+    { url = "https://files.pythonhosted.org/packages/75/d7/7bcad6bcc5f5b7fab53e6bce5db87041f38ef3e740b1ec2d8c49534fa286/grpcio_tools-1.71.2-cp312-cp312-manylinux_2_17_aarch64.whl", hash = "sha256:d4071f9b44564e3f75cdf0f05b10b3e8c7ea0ca5220acbf4dc50b148552eef2f", size = 2350289, upload-time = "2025-06-28T04:21:13.625Z" },
+    { url = "https://files.pythonhosted.org/packages/b2/8a/e4c1c4cb8c9ff7f50b7b2bba94abe8d1e98ea05f52a5db476e7f1c1a3c70/grpcio_tools-1.71.2-cp312-cp312-manylinux_2_17_i686.manylinux2014_i686.whl", hash = "sha256:a28eda8137d587eb30081384c256f5e5de7feda34776f89848b846da64e4be35", size = 2743321, upload-time = "2025-06-28T04:21:15.007Z" },
+    { url = "https://files.pythonhosted.org/packages/fd/aa/95bc77fda5c2d56fb4a318c1b22bdba8914d5d84602525c99047114de531/grpcio_tools-1.71.2-cp312-cp312-manylinux_2_17_x86_64.manylinux2014_x86_64.whl", hash = "sha256:b19c083198f5eb15cc69c0a2f2c415540cbc636bfe76cea268e5894f34023b40", size = 2474005, upload-time = "2025-06-28T04:21:16.443Z" },
+    { url = "https://files.pythonhosted.org/packages/c9/ff/ca11f930fe1daa799ee0ce1ac9630d58a3a3deed3dd2f465edb9a32f299d/grpcio_tools-1.71.2-cp312-cp312-musllinux_1_1_aarch64.whl", hash = "sha256:784c284acda0d925052be19053d35afbf78300f4d025836d424cf632404f676a", size = 2851559, upload-time = "2025-06-28T04:21:18.139Z" },
+    { url = "https://files.pythonhosted.org/packages/64/10/c6fc97914c7e19c9bb061722e55052fa3f575165da9f6510e2038d6e8643/grpcio_tools-1.71.2-cp312-cp312-musllinux_1_1_i686.whl", hash = "sha256:381e684d29a5d052194e095546eef067201f5af30fd99b07b5d94766f44bf1ae", size = 3300622, upload-time = "2025-06-28T04:21:20.291Z" },
+    { url = "https://files.pythonhosted.org/packages/e5/d6/965f36cfc367c276799b730d5dd1311b90a54a33726e561393b808339b04/grpcio_tools-1.71.2-cp312-cp312-musllinux_1_1_x86_64.whl", hash = "sha256:3e4b4801fabd0427fc61d50d09588a01b1cfab0ec5e8a5f5d515fbdd0891fd11", size = 2913863, upload-time = "2025-06-28T04:21:22.196Z" },
+    { url = "https://files.pythonhosted.org/packages/8d/f0/c05d5c3d0c1d79ac87df964e9d36f1e3a77b60d948af65bec35d3e5c75a3/grpcio_tools-1.71.2-cp312-cp312-win32.whl", hash = "sha256:84ad86332c44572305138eafa4cc30040c9a5e81826993eae8227863b700b490", size = 945744, upload-time = "2025-06-28T04:21:23.463Z" },
+    { url = "https://files.pythonhosted.org/packages/e2/e9/c84c1078f0b7af7d8a40f5214a9bdd8d2a567ad6c09975e6e2613a08d29d/grpcio_tools-1.71.2-cp312-cp312-win_amd64.whl", hash = "sha256:8e1108d37eecc73b1c4a27350a6ed921b5dda25091700c1da17cfe30761cd462", size = 1117695, upload-time = "2025-06-28T04:21:25.22Z" },
 ]
 
 [[package]]
@@ -2846,18 +2877,17 @@ wheels = [
 
 [[package]]
 name = "httpx"
-version = "0.27.2"
+version = "0.28.1"
 source = { registry = "https://pypi.org/simple" }
 dependencies = [
     { name = "anyio" },
     { name = "certifi" },
     { name = "httpcore" },
     { name = "idna" },
-    { name = "sniffio" },
 ]
-sdist = { url = "https://files.pythonhosted.org/packages/78/82/08f8c936781f67d9e6b9eeb8a0c8b4e406136ea4c3d1f89a5db71d42e0e6/httpx-0.27.2.tar.gz", hash = "sha256:f7c2be1d2f3c3c3160d441802406b206c2b76f5947b11115e6df10c6c65e66c2", size = 144189, upload-time = "2024-08-27T12:54:01.334Z" }
+sdist = { url = "https://files.pythonhosted.org/packages/b1/df/48c586a5fe32a0f01324ee087459e112ebb7224f646c0b5023f5e79e9956/httpx-0.28.1.tar.gz", hash = "sha256:75e98c5f16b0f35b567856f597f06ff2270a374470a5c2392242528e3e3e42fc", size = 141406, upload-time = "2024-12-06T15:37:23.222Z" }
 wheels = [
-    { url = "https://files.pythonhosted.org/packages/56/95/9377bcb415797e44274b51d46e3249eba641711cf3348050f76ee7b15ffc/httpx-0.27.2-py3-none-any.whl", hash = "sha256:7bb2708e112d8fdd7829cd4243970f0c223274051cb35ee80c03301ee29a3df0", size = 76395, upload-time = "2024-08-27T12:53:59.653Z" },
+    { url = "https://files.pythonhosted.org/packages/2a/39/e50c7c3a983047577ee07d2a9e53faf5a69493943ec3f6a384bdc792deb2/httpx-0.28.1-py3-none-any.whl", hash = "sha256:d909fcccc110f8c7faf814ca82a9a4d816bc5a6dbfea25d6591d6985b8ba59ad", size = 73517, upload-time = "2024-12-06T15:37:21.509Z" },
 ]
 
 [package.optional-dependencies]
@@ -3941,59 +3971,59 @@ wheels = [
 
 [[package]]
 name = "opentelemetry-api"
-version = "1.27.0"
+version = "1.28.0"
 source = { registry = "https://pypi.org/simple" }
 dependencies = [
     { name = "deprecated" },
     { name = "importlib-metadata" },
 ]
-sdist = { url = "https://files.pythonhosted.org/packages/c9/83/93114b6de85a98963aec218a51509a52ed3f8de918fe91eb0f7299805c3f/opentelemetry_api-1.27.0.tar.gz", hash = "sha256:ed673583eaa5f81b5ce5e86ef7cdaf622f88ef65f0b9aab40b843dcae5bef342", size = 62693, upload-time = "2024-08-28T21:35:31.445Z" }
+sdist = { url = "https://files.pythonhosted.org/packages/79/36/260eaea0f74fdd0c0d8f22ed3a3031109ea1c85531f94f4fde266c29e29a/opentelemetry_api-1.28.0.tar.gz", hash = "sha256:578610bcb8aa5cdcb11169d136cc752958548fb6ccffb0969c1036b0ee9e5353", size = 62803, upload-time = "2024-11-05T19:14:45.497Z" }
 wheels = [
-    { url = "https://files.pythonhosted.org/packages/fb/1f/737dcdbc9fea2fa96c1b392ae47275165a7c641663fbb08a8d252968eed2/opentelemetry_api-1.27.0-py3-none-any.whl", hash = "sha256:953d5871815e7c30c81b56d910c707588000fff7a3ca1c73e6531911d53065e7", size = 63970, upload-time = "2024-08-28T21:35:00.598Z" },
+    { url = "https://files.pythonhosted.org/packages/22/e4/3b25d8b856791c04d8a62b1257b5fc09dc41a057800db06885af8ddcdce1/opentelemetry_api-1.28.0-py3-none-any.whl", hash = "sha256:8457cd2c59ea1bd0988560f021656cecd254ad7ef6be4ba09dbefeca2409ce52", size = 64314, upload-time = "2024-11-05T19:14:21.659Z" },
 ]
 
 [[package]]
 name = "opentelemetry-distro"
-version = "0.48b0"
+version = "0.49b0"
 source = { registry = "https://pypi.org/simple" }
 dependencies = [
     { name = "opentelemetry-api" },
     { name = "opentelemetry-instrumentation" },
     { name = "opentelemetry-sdk" },
 ]
-sdist = { url = "https://files.pythonhosted.org/packages/f4/09/423e17c439ed24c45110affe84aad886a536b7871a42637d2ad14a179b47/opentelemetry_distro-0.48b0.tar.gz", hash = "sha256:5cb15915780ac4972583286a56683d43bd4ca95371d72f5f3f179c8b0b2ddc91", size = 2556, upload-time = "2024-08-28T21:27:40.455Z" }
+sdist = { url = "https://files.pythonhosted.org/packages/4d/75/7cb7c33899e66bb366d40a889111a78c22df0951038b6699f1663e715a9f/opentelemetry_distro-0.49b0.tar.gz", hash = "sha256:1bafa274f9e83baa0d2a5d47ed02caffcf9bcca60107b389b145400d82b07513", size = 2560, upload-time = "2024-11-05T19:21:39.379Z" }
 wheels = [
-    { url = "https://files.pythonhosted.org/packages/82/cf/fa9a5fe954f1942e03b319ae0e319ebc93d9f984b548bcd9b3f232a1434d/opentelemetry_distro-0.48b0-py3-none-any.whl", hash = "sha256:b2f8fce114325b020769af3b9bf503efb8af07efc190bd1b9deac7843171664a", size = 3321, upload-time = "2024-08-28T21:26:26.584Z" },
+    { url = "https://files.pythonhosted.org/packages/4c/db/806172b6a4933966eee518db814b375e620602f7fe776b74ef795690f135/opentelemetry_distro-0.49b0-py3-none-any.whl", hash = "sha256:1af4074702f605ea210753dd41947dc2fd61b39724f23cdcf15d5654867cd3c2", size = 3318, upload-time = "2024-11-05T19:20:34.065Z" },
 ]
 
 [[package]]
 name = "opentelemetry-exporter-otlp"
-version = "1.27.0"
+version = "1.28.0"
 source = { registry = "https://pypi.org/simple" }
 dependencies = [
     { name = "opentelemetry-exporter-otlp-proto-grpc" },
     { name = "opentelemetry-exporter-otlp-proto-http" },
 ]
-sdist = { url = "https://files.pythonhosted.org/packages/fc/d3/8156cc14e8f4573a3572ee7f30badc7aabd02961a09acc72ab5f2c789ef1/opentelemetry_exporter_otlp-1.27.0.tar.gz", hash = "sha256:4a599459e623868cc95d933c301199c2367e530f089750e115599fccd67cb2a1", size = 6166, upload-time = "2024-08-28T21:35:33.746Z" }
+sdist = { url = "https://files.pythonhosted.org/packages/eb/16/14e3fc163930ea68f0980a4cdd4ae5796e60aeb898965990e13263d64baf/opentelemetry_exporter_otlp-1.28.0.tar.gz", hash = "sha256:31ae7495831681dd3da34ac457f6970f147465ae4b9aae3a888d7a581c7cd868", size = 6170, upload-time = "2024-11-05T19:14:47.349Z" }
 wheels = [
-    { url = "https://files.pythonhosted.org/packages/59/6d/95e1fc2c8d945a734db32e87a5aa7a804f847c1657a21351df9338bd1c9c/opentelemetry_exporter_otlp-1.27.0-py3-none-any.whl", hash = "sha256:7688791cbdd951d71eb6445951d1cfbb7b6b2d7ee5948fac805d404802931145", size = 7001, upload-time = "2024-08-28T21:35:04.02Z" },
+    { url = "https://files.pythonhosted.org/packages/c2/82/3f521b3c1f2a411ed60a24a8c9f486c1beeaf8c6c55337c87d3ae1642151/opentelemetry_exporter_otlp-1.28.0-py3-none-any.whl", hash = "sha256:1fd02d70f2c1b7ac5579c81e78de4594b188d3317c8ceb69e8b53900fb7b40fd", size = 7024, upload-time = "2024-11-05T19:14:24.534Z" },
 ]
 
 [[package]]
 name = "opentelemetry-exporter-otlp-proto-common"
-version = "1.27.0"
+version = "1.28.0"
 source = { registry = "https://pypi.org/simple" }
 dependencies = [
     { name = "opentelemetry-proto" },
 ]
-sdist = { url = "https://files.pythonhosted.org/packages/cd/2e/7eaf4ba595fb5213cf639c9158dfb64aacb2e4c7d74bfa664af89fa111f4/opentelemetry_exporter_otlp_proto_common-1.27.0.tar.gz", hash = "sha256:159d27cf49f359e3798c4c3eb8da6ef4020e292571bd8c5604a2a573231dd5c8", size = 17860, upload-time = "2024-08-28T21:35:34.896Z" }
+sdist = { url = "https://files.pythonhosted.org/packages/c2/8d/5d411084ac441052f4c9bae03a1aec65ae5d16b439fea7b9c5ac3842c013/opentelemetry_exporter_otlp_proto_common-1.28.0.tar.gz", hash = "sha256:5fa0419b0c8e291180b0fc8430a20dd44a3f3236f8e0827992145914f273ec4f", size = 18505, upload-time = "2024-11-05T19:14:48.204Z" }
 wheels = [
-    { url = "https://files.pythonhosted.org/packages/41/27/4610ab3d9bb3cde4309b6505f98b3aabca04a26aa480aa18cede23149837/opentelemetry_exporter_otlp_proto_common-1.27.0-py3-none-any.whl", hash = "sha256:675db7fffcb60946f3a5c43e17d1168a3307a94a930ecf8d2ea1f286f3d4f79a", size = 17848, upload-time = "2024-08-28T21:35:05.412Z" },
+    { url = "https://files.pythonhosted.org/packages/e1/72/3c44aabc74db325aaba09361b6a0d80f6d601f0ff86ecea8ee655c9538fc/opentelemetry_exporter_otlp_proto_common-1.28.0-py3-none-any.whl", hash = "sha256:467e6437d24e020156dffecece8c0a4471a8a60f6a34afeda7386df31a092410", size = 18403, upload-time = "2024-11-05T19:14:25.798Z" },
 ]
 
 [[package]]
 name = "opentelemetry-exporter-otlp-proto-grpc"
-version = "1.27.0"
+version = "1.28.0"
 source = { registry = "https://pypi.org/simple" }
 dependencies = [
     { name = "deprecated" },
@@ -4004,14 +4034,14 @@ dependencies = [
     { name = "opentelemetry-proto" },
     { name = "opentelemetry-sdk" },
 ]
-sdist = { url = "https://files.pythonhosted.org/packages/a1/d0/c1e375b292df26e0ffebf194e82cd197e4c26cc298582bda626ce3ce74c5/opentelemetry_exporter_otlp_proto_grpc-1.27.0.tar.gz", hash = "sha256:af6f72f76bcf425dfb5ad11c1a6d6eca2863b91e63575f89bb7b4b55099d968f", size = 26244, upload-time = "2024-08-28T21:35:36.314Z" }
+sdist = { url = "https://files.pythonhosted.org/packages/43/4d/f215162e58041afb4bdf5dbd0d8faf0b7fc9bf7b3d3fc0e44e06f9e7e869/opentelemetry_exporter_otlp_proto_grpc-1.28.0.tar.gz", hash = "sha256:47a11c19dc7f4289e220108e113b7de90d59791cb4c37fc29f69a6a56f2c3735", size = 26237, upload-time = "2024-11-05T19:14:49.026Z" }
 wheels = [
-    { url = "https://files.pythonhosted.org/packages/8d/80/32217460c2c64c0568cea38410124ff680a9b65f6732867bbf857c4d8626/opentelemetry_exporter_otlp_proto_grpc-1.27.0-py3-none-any.whl", hash = "sha256:56b5bbd5d61aab05e300d9d62a6b3c134827bbd28d0b12f2649c2da368006c9e", size = 18541, upload-time = "2024-08-28T21:35:06.493Z" },
+    { url = "https://files.pythonhosted.org/packages/1d/b5/afabc8106abc0f9cfeecf5b3e682622b3e04bba1d9b967dbfcd91b9c4ebe/opentelemetry_exporter_otlp_proto_grpc-1.28.0-py3-none-any.whl", hash = "sha256:edbdc53e7783f88d4535db5807cb91bd7b1ec9e9b9cdbfee14cd378f29a3b328", size = 18532, upload-time = "2024-11-05T19:14:26.853Z" },
 ]
 
 [[package]]
 name = "opentelemetry-exporter-otlp-proto-http"
-version = "1.27.0"
+version = "1.28.0"
 source = { registry = "https://pypi.org/simple" }
 dependencies = [
     { name = "deprecated" },
@@ -4022,28 +4052,29 @@ dependencies = [
     { name = "opentelemetry-sdk" },
     { name = "requests" },
 ]
-sdist = { url = "https://files.pythonhosted.org/packages/31/0a/f05c55e8913bf58a033583f2580a0ec31a5f4cf2beacc9e286dcb74d6979/opentelemetry_exporter_otlp_proto_http-1.27.0.tar.gz", hash = "sha256:2103479092d8eb18f61f3fbff084f67cc7f2d4a7d37e75304b8b56c1d09ebef5", size = 15059, upload-time = "2024-08-28T21:35:37.079Z" }
+sdist = { url = "https://files.pythonhosted.org/packages/f1/2a/555f2845928086cd51aa6941c7a546470805b68ed631ec139ce7d841763d/opentelemetry_exporter_otlp_proto_http-1.28.0.tar.gz", hash = "sha256:d83a9a03a8367ead577f02a64127d827c79567de91560029688dd5cfd0152a8e", size = 15051, upload-time = "2024-11-05T19:14:49.813Z" }
 wheels = [
-    { url = "https://files.pythonhosted.org/packages/2d/8d/4755884afc0b1db6000527cac0ca17273063b6142c773ce4ecd307a82e72/opentelemetry_exporter_otlp_proto_http-1.27.0-py3-none-any.whl", hash = "sha256:688027575c9da42e179a69fe17e2d1eba9b14d81de8d13553a21d3114f3b4d75", size = 17203, upload-time = "2024-08-28T21:35:08.141Z" },
+    { url = "https://files.pythonhosted.org/packages/b2/ce/80d5adabbf7ab4a0ca7b5e0f4039b24d273be370c3ba85fc05b13794411c/opentelemetry_exporter_otlp_proto_http-1.28.0-py3-none-any.whl", hash = "sha256:e8f3f7961b747edb6b44d51de4901a61e9c01d50debd747b120a08c4996c7e7b", size = 17228, upload-time = "2024-11-05T19:14:28.613Z" },
 ]
 
 [[package]]
 name = "opentelemetry-instrumentation"
-version = "0.48b0"
+version = "0.49b0"
 source = { registry = "https://pypi.org/simple" }
 dependencies = [
     { name = "opentelemetry-api" },
-    { name = "setuptools" },
+    { name = "opentelemetry-semantic-conventions" },
+    { name = "packaging" },
     { name = "wrapt" },
 ]
-sdist = { url = "https://files.pythonhosted.org/packages/04/0e/d9394839af5d55c8feb3b22cd11138b953b49739b20678ca96289e30f904/opentelemetry_instrumentation-0.48b0.tar.gz", hash = "sha256:94929685d906380743a71c3970f76b5f07476eea1834abd5dd9d17abfe23cc35", size = 24724, upload-time = "2024-08-28T21:27:42.82Z" }
+sdist = { url = "https://files.pythonhosted.org/packages/de/6b/6c25b15063c92a011cf3f68375971e2c58a9c764690847edc97df2d94eeb/opentelemetry_instrumentation-0.49b0.tar.gz", hash = "sha256:398a93e0b9dc2d11cc8627e1761665c506fe08c6b2df252a2ab3ade53d751c46", size = 26478, upload-time = "2024-11-05T19:21:41.402Z" }
 wheels = [
-    { url = "https://files.pythonhosted.org/packages/0a/7f/405c41d4f359121376c9d5117dcf68149b8122d3f6c718996d037bd4d800/opentelemetry_instrumentation-0.48b0-py3-none-any.whl", hash = "sha256:a69750dc4ba6a5c3eb67986a337185a25b739966d80479befe37b546fc870b44", size = 29449, upload-time = "2024-08-28T21:26:31.288Z" },
+    { url = "https://files.pythonhosted.org/packages/93/61/e0d21e958d6072ce25c4f5e26a1d22835fc86f80836660adf6badb6038ce/opentelemetry_instrumentation-0.49b0-py3-none-any.whl", hash = "sha256:68364d73a1ff40894574cbc6138c5f98674790cae1f3b0865e21cf702f24dcb3", size = 30694, upload-time = "2024-11-05T19:20:38.584Z" },
 ]
 
 [[package]]
 name = "opentelemetry-instrumentation-asgi"
-version = "0.48b0"
+version = "0.49b0"
 source = { registry = "https://pypi.org/simple" }
 dependencies = [
     { name = "asgiref" },
@@ -4052,28 +4083,28 @@ dependencies = [
     { name = "opentelemetry-semantic-conventions" },
     { name = "opentelemetry-util-http" },
 ]
-sdist = { url = "https://files.pythonhosted.org/packages/44/ac/fd3d40bab3234ec3f5c052a815100676baaae1832fa1067935f11e5c59c6/opentelemetry_instrumentation_asgi-0.48b0.tar.gz", hash = "sha256:04c32174b23c7fa72ddfe192dad874954968a6a924608079af9952964ecdf785", size = 23435, upload-time = "2024-08-28T21:27:47.276Z" }
+sdist = { url = "https://files.pythonhosted.org/packages/e8/55/693c3d0938ba5fead5c3aa4ac7022a992b4ff99a8e9979800d0feb843ff4/opentelemetry_instrumentation_asgi-0.49b0.tar.gz", hash = "sha256:959fd9b1345c92f20c6ef1d42f92ef6a76b3c3083fbc4104d59da6859b15b083", size = 24117, upload-time = "2024-11-05T19:21:46.769Z" }
 wheels = [
-    { url = "https://files.pythonhosted.org/packages/db/74/a0e0d38622856597dd8e630f2bd793760485eb165708e11b8be1696bbb5a/opentelemetry_instrumentation_asgi-0.48b0-py3-none-any.whl", hash = "sha256:ddb1b5fc800ae66e85a4e2eca4d9ecd66367a8c7b556169d9e7b57e10676e44d", size = 15958, upload-time = "2024-08-28T21:26:38.139Z" },
+    { url = "https://files.pythonhosted.org/packages/2c/0b/7900c782a1dfaa584588d724bc3bbdf8405a32497537dd96b3fcbf8461b9/opentelemetry_instrumentation_asgi-0.49b0-py3-none-any.whl", hash = "sha256:722a90856457c81956c88f35a6db606cc7db3231046b708aae2ddde065723dbe", size = 16326, upload-time = "2024-11-05T19:20:46.176Z" },
 ]
 
 [[package]]
 name = "opentelemetry-instrumentation-celery"
-version = "0.48b0"
+version = "0.49b0"
 source = { registry = "https://pypi.org/simple" }
 dependencies = [
     { name = "opentelemetry-api" },
     { name = "opentelemetry-instrumentation" },
     { name = "opentelemetry-semantic-conventions" },
 ]
-sdist = { url = "https://files.pythonhosted.org/packages/42/68/72975eff50cc22d8f65f96c425a2e8844f91488e78ffcfb603ac7cee0e5a/opentelemetry_instrumentation_celery-0.48b0.tar.gz", hash = "sha256:1d33aa6c4a1e6c5d17a64215245208a96e56c9d07611685dbae09a557704af26", size = 14445, upload-time = "2024-08-28T21:27:56.392Z" }
+sdist = { url = "https://files.pythonhosted.org/packages/4c/8b/9b8a9dda3ed53354c6f707a45cdb7a4730e1c109b50fc1b413525493f811/opentelemetry_instrumentation_celery-0.49b0.tar.gz", hash = "sha256:afbaee97cc9c75f29bcc9784f16f8e37c415d4fe9b334748c5b90a3d30d12473", size = 14702, upload-time = "2024-11-05T19:21:53.672Z" }
 wheels = [
-    { url = "https://files.pythonhosted.org/packages/28/59/f09e8f9f596d375fd86b7677751525bbc485c8cc8c5388e39786a3d3b968/opentelemetry_instrumentation_celery-0.48b0-py3-none-any.whl", hash = "sha256:c1904e38cc58fb2a33cd657d6e296285c5ffb0dca3f164762f94b905e5abc88e", size = 13697, upload-time = "2024-08-28T21:26:50.01Z" },
+    { url = "https://files.pythonhosted.org/packages/21/8c/d7d4adb36abbc0e517a69f7a069f32742122ae22d6017202f64570d9f4c5/opentelemetry_instrumentation_celery-0.49b0-py3-none-any.whl", hash = "sha256:38d4a78c78f33020032ef77ef0ead756bdf7838bcfb603de10f5925d39f14929", size = 13749, upload-time = "2024-11-05T19:20:54.98Z" },
 ]
 
 [[package]]
 name = "opentelemetry-instrumentation-fastapi"
-version = "0.48b0"
+version = "0.49b0"
 source = { registry = "https://pypi.org/simple" }
 dependencies = [
     { name = "opentelemetry-api" },
@@ -4082,17 +4113,16 @@ dependencies = [
     { name = "opentelemetry-semantic-conventions" },
     { name = "opentelemetry-util-http" },
 ]
-sdist = { url = "https://files.pythonhosted.org/packages/58/20/43477da5850ef2cd3792715d442aecd051e885e0603b6ee5783b2104ba8f/opentelemetry_instrumentation_fastapi-0.48b0.tar.gz", hash = "sha256:21a72563ea412c0b535815aeed75fc580240f1f02ebc72381cfab672648637a2", size = 18497, upload-time = "2024-08-28T21:28:01.14Z" }
+sdist = { url = "https://files.pythonhosted.org/packages/fe/bf/8e6d2a4807360f2203192017eb4845f5628dbeaf0597adf3d141cc5c24e1/opentelemetry_instrumentation_fastapi-0.49b0.tar.gz", hash = "sha256:6d14935c41fd3e49328188b6a59dd4c37bd17a66b01c15b0c64afa9714a1f905", size = 19230, upload-time = "2024-11-05T19:21:59.361Z" }
 wheels = [
-    { url = "https://files.pythonhosted.org/packages/ee/50/745ab075a3041b7a5f29a579d2c28eaad54f64b4589d8f9fd364c62cf0f3/opentelemetry_instrumentation_fastapi-0.48b0-py3-none-any.whl", hash = "sha256:afeb820a59e139d3e5d96619600f11ce0187658b8ae9e3480857dd790bc024f2", size = 11777, upload-time = "2024-08-28T21:26:57.457Z" },
+    { url = "https://files.pythonhosted.org/packages/b1/f4/0895b9410c10abf987c90dee1b7688a8f2214a284fe15e575648f6a1473a/opentelemetry_instrumentation_fastapi-0.49b0-py3-none-any.whl", hash = "sha256:646e1b18523cbe6860ae9711eb2c7b9c85466c3c7697cd6b8fb5180d85d3fe6e", size = 12101, upload-time = "2024-11-05T19:21:01.805Z" },
 ]
 
 [[package]]
 name = "opentelemetry-instrumentation-flask"
-version = "0.48b0"
+version = "0.49b0"
 source = { registry = "https://pypi.org/simple" }
 dependencies = [
-    { name = "importlib-metadata" },
     { name = "opentelemetry-api" },
     { name = "opentelemetry-instrumentation" },
     { name = "opentelemetry-instrumentation-wsgi" },
@@ -4100,29 +4130,30 @@ dependencies = [
     { name = "opentelemetry-util-http" },
     { name = "packaging" },
 ]
-sdist = { url = "https://files.pythonhosted.org/packages/ed/2f/5c3af780a69f9ba78445fe0e5035c41f67281a31b08f3c3e7ec460bda726/opentelemetry_instrumentation_flask-0.48b0.tar.gz", hash = "sha256:e03a34428071aebf4864ea6c6a564acef64f88c13eb3818e64ea90da61266c3d", size = 19196, upload-time = "2024-08-28T21:28:01.986Z" }
+sdist = { url = "https://files.pythonhosted.org/packages/17/12/dc72873fb1e35699941d8eb6a53ef25e8c5843dea37665dad33bd720f047/opentelemetry_instrumentation_flask-0.49b0.tar.gz", hash = "sha256:f7c5ab67753c4781a2e21c8f43dc5fc02ece74fdd819466c75d025db80aa7576", size = 19176, upload-time = "2024-11-05T19:22:00.816Z" }
 wheels = [
-    { url = "https://files.pythonhosted.org/packages/78/3d/fcde4f8f0bf9fa1ee73a12304fa538076fb83fe0a2ae966ab0f0b7da5109/opentelemetry_instrumentation_flask-0.48b0-py3-none-any.whl", hash = "sha256:26b045420b9d76e85493b1c23fcf27517972423480dc6cf78fd6924248ba5808", size = 14588, upload-time = "2024-08-28T21:26:58.504Z" },
+    { url = "https://files.pythonhosted.org/packages/a2/fc/354da8f33ef0daebfc8e4eac995d342ae13a35097bbad512cfe0d2f3c61a/opentelemetry_instrumentation_flask-0.49b0-py3-none-any.whl", hash = "sha256:f3ef330c3cee3e2c161f27f1e7017c8800b9bfb6f9204f2f7bfb0b274874be0e", size = 14582, upload-time = "2024-11-05T19:21:02.793Z" },
 ]
 
 [[package]]
 name = "opentelemetry-instrumentation-httpx"
-version = "0.48b0"
+version = "0.49b0"
 source = { registry = "https://pypi.org/simple" }
 dependencies = [
     { name = "opentelemetry-api" },
     { name = "opentelemetry-instrumentation" },
     { name = "opentelemetry-semantic-conventions" },
     { name = "opentelemetry-util-http" },
+    { name = "wrapt" },
 ]
-sdist = { url = "https://files.pythonhosted.org/packages/d3/d9/c65d818607c16d1b7ea8d2de6111c6cecadf8d2fd38c1885a72733a7c6d3/opentelemetry_instrumentation_httpx-0.48b0.tar.gz", hash = "sha256:ee977479e10398931921fb995ac27ccdeea2e14e392cb27ef012fc549089b60a", size = 16931, upload-time = "2024-08-28T21:28:03.794Z" }
+sdist = { url = "https://files.pythonhosted.org/packages/a0/53/8b5e05e55a513d846ead5afb0509bec37a34a1c3e82f30b13d14156334b1/opentelemetry_instrumentation_httpx-0.49b0.tar.gz", hash = "sha256:07165b624f3e58638cee47ecf1c81939a8c2beb7e42ce9f69e25a9f21dc3f4cf", size = 17750, upload-time = "2024-11-05T19:22:02.911Z" }
 wheels = [
-    { url = "https://files.pythonhosted.org/packages/c2/fe/f2daa9d6d988c093b8c7b1d35df675761a8ece0b600b035dc04982746c9d/opentelemetry_instrumentation_httpx-0.48b0-py3-none-any.whl", hash = "sha256:d94f9d612c82d09fe22944d1904a30a464c19bea2ba76be656c99a28ad8be8e5", size = 13900, upload-time = "2024-08-28T21:27:01.566Z" },
+    { url = "https://files.pythonhosted.org/packages/3b/9f/843391c6d645cd4f6914b27bc807fc1ff52b97f84cbe3ca675641976b23f/opentelemetry_instrumentation_httpx-0.49b0-py3-none-any.whl", hash = "sha256:e59e0d2fda5ef841630c68da1d78ff9192f63590a9099f12f0eab614abdf239a", size = 14110, upload-time = "2024-11-05T19:21:04.698Z" },
 ]
 
 [[package]]
 name = "opentelemetry-instrumentation-redis"
-version = "0.48b0"
+version = "0.49b0"
 source = { registry = "https://pypi.org/simple" }
 dependencies = [
     { name = "opentelemetry-api" },
@@ -4130,14 +4161,14 @@ dependencies = [
     { name = "opentelemetry-semantic-conventions" },
     { name = "wrapt" },
 ]
-sdist = { url = "https://files.pythonhosted.org/packages/70/be/92e98e4c7f275be3d373899a41b0a7d4df64266657d985dbbdb9a54de0d5/opentelemetry_instrumentation_redis-0.48b0.tar.gz", hash = "sha256:61e33e984b4120e1b980d9fba6e9f7ca0c8d972f9970654d8f6e9f27fa115a8c", size = 10511, upload-time = "2024-08-28T21:28:15.061Z" }
+sdist = { url = "https://files.pythonhosted.org/packages/19/5b/1398eb2f92fd76787ccec28d24dc4c7dfaaf97a7557e7729e2f7c2c05d84/opentelemetry_instrumentation_redis-0.49b0.tar.gz", hash = "sha256:922542c3bd192ad4ba74e2c7e0a253c7c58a5cefbd6f89da2aba4d193a974703", size = 11353, upload-time = "2024-11-05T19:22:12.822Z" }
 wheels = [
-    { url = "https://files.pythonhosted.org/packages/94/40/892f30d400091106309cc047fd3f6d76a828fedd984a953fd5386b78a2fb/opentelemetry_instrumentation_redis-0.48b0-py3-none-any.whl", hash = "sha256:48c7f2e25cbb30bde749dc0d8b9c74c404c851f554af832956b9630b27f5bcb7", size = 11610, upload-time = "2024-08-28T21:27:18.759Z" },
+    { url = "https://files.pythonhosted.org/packages/24/e4/4f258fef0759629f2e8a0210d5533cfef3ecad69ff35be044637a3e2783e/opentelemetry_instrumentation_redis-0.49b0-py3-none-any.whl", hash = "sha256:b7d8f758bac53e77b7e7ca98ce80f91230577502dacb619ebe8e8b6058042067", size = 12453, upload-time = "2024-11-05T19:21:18.534Z" },
 ]
 
 [[package]]
 name = "opentelemetry-instrumentation-sqlalchemy"
-version = "0.48b0"
+version = "0.49b0"
 source = { registry = "https://pypi.org/simple" }
 dependencies = [
     { name = "opentelemetry-api" },
@@ -4146,14 +4177,14 @@ dependencies = [
     { name = "packaging" },
     { name = "wrapt" },
 ]
-sdist = { url = "https://files.pythonhosted.org/packages/4c/77/3fcebbca8bd729da50dc2130d8ca869a235aa5483a85ef06c5dc8643476b/opentelemetry_instrumentation_sqlalchemy-0.48b0.tar.gz", hash = "sha256:dbf2d5a755b470e64e5e2762b56f8d56313787e4c7d71a87fe25c33f48eb3493", size = 13194, upload-time = "2024-08-28T21:28:18.122Z" }
+sdist = { url = "https://files.pythonhosted.org/packages/a0/a7/24f6cce3808ae1802dd1b60d752fbab877db5655198929cf4ee8ea416923/opentelemetry_instrumentation_sqlalchemy-0.49b0.tar.gz", hash = "sha256:32658e520fc8b35823c722f5d8831d3a410b76dd2724adb2887befc041ddef04", size = 13194, upload-time = "2024-11-05T19:22:14.92Z" }
 wheels = [
-    { url = "https://files.pythonhosted.org/packages/e1/84/4b6f1e9e9f83a52d966e91963f5a8424edc4a3d5ea32854c96c2d1618284/opentelemetry_instrumentation_sqlalchemy-0.48b0-py3-none-any.whl", hash = "sha256:625848a34aa5770cb4b1dcdbd95afce4307a0230338711101325261d739f391f", size = 13360, upload-time = "2024-08-28T21:27:22.102Z" },
+    { url = "https://files.pythonhosted.org/packages/ec/6b/a1a3685fed593282999cdc374ece15efbd56f8d774bd368bf7ff2cf5923c/opentelemetry_instrumentation_sqlalchemy-0.49b0-py3-none-any.whl", hash = "sha256:d854052d2b02cd0562e5628a514c8153fceada7f585137e173165dfd0a46ef6a", size = 13358, upload-time = "2024-11-05T19:21:23.654Z" },
 ]
 
 [[package]]
 name = "opentelemetry-instrumentation-wsgi"
-version = "0.48b0"
+version = "0.49b0"
 source = { registry = "https://pypi.org/simple" }
 dependencies = [
     { name = "opentelemetry-api" },
@@ -4161,70 +4192,70 @@ dependencies = [
     { name = "opentelemetry-semantic-conventions" },
     { name = "opentelemetry-util-http" },
 ]
-sdist = { url = "https://files.pythonhosted.org/packages/de/a5/f45cdfba18f22aefd2378eac8c07c1f8c9656d6bf7ce315ced48c67f3437/opentelemetry_instrumentation_wsgi-0.48b0.tar.gz", hash = "sha256:1a1e752367b0df4397e0b835839225ef5c2c3c053743a261551af13434fc4d51", size = 17974, upload-time = "2024-08-28T21:28:24.902Z" }
+sdist = { url = "https://files.pythonhosted.org/packages/17/2b/91b022b004ac9e9ab0eefd10bc4257975291f88adc81b4ef2c601ddb1adf/opentelemetry_instrumentation_wsgi-0.49b0.tar.gz", hash = "sha256:0812a02e132f8fc3d5c897bba84e530c37b85c315b199bb97ca6508279e7eb23", size = 17733, upload-time = "2024-11-05T19:22:24.3Z" }
 wheels = [
-    { url = "https://files.pythonhosted.org/packages/fb/87/fa420007e0ba7e8cd43799ab204717ab515f000236fa2726a6be3299efdd/opentelemetry_instrumentation_wsgi-0.48b0-py3-none-any.whl", hash = "sha256:c6051124d741972090fe94b2fa302555e1e2a22e9cdda32dd39ed49a5b34e0c6", size = 13691, upload-time = "2024-08-28T21:27:33.257Z" },
+    { url = "https://files.pythonhosted.org/packages/02/1d/59979665778ed8c85bc31c92b75571cd7afb8e3322fb513c87fe1bad6d78/opentelemetry_instrumentation_wsgi-0.49b0-py3-none-any.whl", hash = "sha256:8869ccf96611827e4448417718920e9eec6d25bffb5bf72c7952c7346ec33fbc", size = 13699, upload-time = "2024-11-05T19:21:35.039Z" },
 ]
 
 [[package]]
 name = "opentelemetry-propagator-b3"
-version = "1.27.0"
+version = "1.28.0"
 source = { registry = "https://pypi.org/simple" }
 dependencies = [
     { name = "deprecated" },
     { name = "opentelemetry-api" },
 ]
-sdist = { url = "https://files.pythonhosted.org/packages/53/a3/3ceeb5ff5a1906371834d5c594e24e5b84f35528d219054833deca4ac44c/opentelemetry_propagator_b3-1.27.0.tar.gz", hash = "sha256:39377b6aa619234e08fbc6db79bf880aff36d7e2761efa9afa28b78d5937308f", size = 9590, upload-time = "2024-08-28T21:35:43.971Z" }
+sdist = { url = "https://files.pythonhosted.org/packages/6f/1d/225ea036785119964509e92f4e1bc0313ba6ec790fbf51bd363abafeafae/opentelemetry_propagator_b3-1.28.0.tar.gz", hash = "sha256:cf6f0d2a1881c4858898be47e8a94b11bc5b16fc73b6c37ebfa2121c4825adc6", size = 9592, upload-time = "2024-11-05T19:14:57.193Z" }
 wheels = [
-    { url = "https://files.pythonhosted.org/packages/03/3f/75ba77b8d9938bae575bc457a5c56ca2246ff5367b54c7d4252a31d1c91f/opentelemetry_propagator_b3-1.27.0-py3-none-any.whl", hash = "sha256:1dd75e9801ba02e870df3830097d35771a64c123127c984d9b05c352a35aa9cc", size = 8899, upload-time = "2024-08-28T21:35:18.317Z" },
+    { url = "https://files.pythonhosted.org/packages/4e/fa/438d53d73a6c45df5d416b56dc371a65d0b07859bc107ab632349a079d4a/opentelemetry_propagator_b3-1.28.0-py3-none-any.whl", hash = "sha256:9f6923a5da56d7da6724e4fdd758a67ede2a2732efb929e538cf6fea337700c5", size = 8917, upload-time = "2024-11-05T19:14:37.317Z" },
 ]
 
 [[package]]
 name = "opentelemetry-proto"
-version = "1.27.0"
+version = "1.28.0"
 source = { registry = "https://pypi.org/simple" }
 dependencies = [
     { name = "protobuf" },
 ]
-sdist = { url = "https://files.pythonhosted.org/packages/9a/59/959f0beea798ae0ee9c979b90f220736fbec924eedbefc60ca581232e659/opentelemetry_proto-1.27.0.tar.gz", hash = "sha256:33c9345d91dafd8a74fc3d7576c5a38f18b7fdf8d02983ac67485386132aedd6", size = 34749, upload-time = "2024-08-28T21:35:45.839Z" }
+sdist = { url = "https://files.pythonhosted.org/packages/c9/63/ac4cef4d30ea0ca1d2153ad2fc62d91d1cf3b89b0e4e5cbd61a8c567885f/opentelemetry_proto-1.28.0.tar.gz", hash = "sha256:4a45728dfefa33f7908b828b9b7c9f2c6de42a05d5ec7b285662ddae71c4c870", size = 34331, upload-time = "2024-11-05T19:14:59.503Z" }
 wheels = [
-    { url = "https://files.pythonhosted.org/packages/94/56/3d2d826834209b19a5141eed717f7922150224d1a982385d19a9444cbf8d/opentelemetry_proto-1.27.0-py3-none-any.whl", hash = "sha256:b133873de5581a50063e1e4b29cdcf0c5e253a8c2d8dc1229add20a4c3830ace", size = 52464, upload-time = "2024-08-28T21:35:21.434Z" },
+    { url = "https://files.pythonhosted.org/packages/86/94/c0b43d16e1d96ee1e699373aa59f14a3aa2e7126af3f11d6adc5dcc531cd/opentelemetry_proto-1.28.0-py3-none-any.whl", hash = "sha256:d5ad31b997846543b8e15504657d9a8cf1ad3c71dcbbb6c4799b1ab29e38f7f9", size = 55832, upload-time = "2024-11-05T19:14:40.446Z" },
 ]
 
 [[package]]
 name = "opentelemetry-sdk"
-version = "1.27.0"
+version = "1.28.0"
 source = { registry = "https://pypi.org/simple" }
 dependencies = [
     { name = "opentelemetry-api" },
     { name = "opentelemetry-semantic-conventions" },
     { name = "typing-extensions" },
 ]
-sdist = { url = "https://files.pythonhosted.org/packages/0d/9a/82a6ac0f06590f3d72241a587cb8b0b751bd98728e896cc4cbd4847248e6/opentelemetry_sdk-1.27.0.tar.gz", hash = "sha256:d525017dea0ccce9ba4e0245100ec46ecdc043f2d7b8315d56b19aff0904fa6f", size = 145019, upload-time = "2024-08-28T21:35:46.708Z" }
+sdist = { url = "https://files.pythonhosted.org/packages/0c/5b/a509ccab93eacc6044591d5ec437d8266e76f893d0389bbf7e5592c7da32/opentelemetry_sdk-1.28.0.tar.gz", hash = "sha256:41d5420b2e3fb7716ff4981b510d551eff1fc60eb5a95cf7335b31166812a893", size = 156155, upload-time = "2024-11-05T19:15:00.451Z" }
 wheels = [
-    { url = "https://files.pythonhosted.org/packages/c1/bd/a6602e71e315055d63b2ff07172bd2d012b4cba2d4e00735d74ba42fc4d6/opentelemetry_sdk-1.27.0-py3-none-any.whl", hash = "sha256:365f5e32f920faf0fd9e14fdfd92c086e317eaa5f860edba9cdc17a380d9197d", size = 110505, upload-time = "2024-08-28T21:35:24.769Z" },
+    { url = "https://files.pythonhosted.org/packages/c3/fe/c8decbebb5660529f1d6ba65e50a45b1294022dfcba2968fc9c8697c42b2/opentelemetry_sdk-1.28.0-py3-none-any.whl", hash = "sha256:4b37da81d7fad67f6683c4420288c97f4ed0d988845d5886435f428ec4b8429a", size = 118692, upload-time = "2024-11-05T19:14:41.669Z" },
 ]
 
 [[package]]
 name = "opentelemetry-semantic-conventions"
-version = "0.48b0"
+version = "0.49b0"
 source = { registry = "https://pypi.org/simple" }
 dependencies = [
     { name = "deprecated" },
     { name = "opentelemetry-api" },
 ]
-sdist = { url = "https://files.pythonhosted.org/packages/0a/89/1724ad69f7411772446067cdfa73b598694c8c91f7f8c922e344d96d81f9/opentelemetry_semantic_conventions-0.48b0.tar.gz", hash = "sha256:12d74983783b6878162208be57c9effcb89dc88691c64992d70bb89dc00daa1a", size = 89445, upload-time = "2024-08-28T21:35:47.673Z" }
+sdist = { url = "https://files.pythonhosted.org/packages/ee/c8/433b0e54143f8c9369f5c4a7a83e73eec7eb2ee7d0b7e81a9243e78c8e80/opentelemetry_semantic_conventions-0.49b0.tar.gz", hash = "sha256:dbc7b28339e5390b6b28e022835f9bac4e134a80ebf640848306d3c5192557e8", size = 95227, upload-time = "2024-11-05T19:15:01.443Z" }
 wheels = [
-    { url = "https://files.pythonhosted.org/packages/b7/7a/4f0063dbb0b6c971568291a8bc19a4ca70d3c185db2d956230dd67429dfc/opentelemetry_semantic_conventions-0.48b0-py3-none-any.whl", hash = "sha256:a0de9f45c413a8669788a38569c7e0a11ce6ce97861a628cca785deecdc32a1f", size = 149685, upload-time = "2024-08-28T21:35:25.983Z" },
+    { url = "https://files.pythonhosted.org/packages/25/05/20104df4ef07d3bf5c3fd6bcc796ef70ab4ea4309378a9ba57bc4b4d01fa/opentelemetry_semantic_conventions-0.49b0-py3-none-any.whl", hash = "sha256:0458117f6ead0b12e3221813e3e511d85698c31901cac84682052adb9c17c7cd", size = 159214, upload-time = "2024-11-05T19:14:43.047Z" },
 ]
 
 [[package]]
 name = "opentelemetry-util-http"
-version = "0.48b0"
+version = "0.49b0"
 source = { registry = "https://pypi.org/simple" }
-sdist = { url = "https://files.pythonhosted.org/packages/d6/d7/185c494754340e0a3928fd39fde2616ee78f2c9d66253affaad62d5b7935/opentelemetry_util_http-0.48b0.tar.gz", hash = "sha256:60312015153580cc20f322e5cdc3d3ecad80a71743235bdb77716e742814623c", size = 7863, upload-time = "2024-08-28T21:28:27.266Z" }
+sdist = { url = "https://files.pythonhosted.org/packages/a3/99/377ef446928808211b127b9ab31c348bc465c8da4514ebeec6e4a3de3d21/opentelemetry_util_http-0.49b0.tar.gz", hash = "sha256:02928496afcffd58a7c15baf99d2cedae9b8325a8ac52b0d0877b2e8f936dd1b", size = 7863, upload-time = "2024-11-05T19:22:26.973Z" }
 wheels = [
-    { url = "https://files.pythonhosted.org/packages/ad/2e/36097c0a4d0115b8c7e377c90bab7783ac183bc5cb4071308f8959454311/opentelemetry_util_http-0.48b0-py3-none-any.whl", hash = "sha256:76f598af93aab50328d2a69c786beaedc8b6a7770f7a818cc307eb353debfffb", size = 6946, upload-time = "2024-08-28T21:27:37.975Z" },
+    { url = "https://files.pythonhosted.org/packages/66/0e/ab0a89b315d0bacdd355a345bb69b20c50fc1f0804b52b56fe1c35a60e68/opentelemetry_util_http-0.49b0-py3-none-any.whl", hash = "sha256:8661bbd6aea1839badc44de067ec9c15c05eab05f729f496c856c50a1203caf1", size = 6945, upload-time = "2024-11-05T19:21:37.81Z" },
 ]
 
 [[package]]
@@ -4433,15 +4464,15 @@ wheels = [
 
 [[package]]
 name = "pdfminer-six"
-version = "20251230"
+version = "20260107"
 source = { registry = "https://pypi.org/simple" }
 dependencies = [
     { name = "charset-normalizer" },
     { name = "cryptography" },
 ]
-sdist = { url = "https://files.pythonhosted.org/packages/46/9a/d79d8fa6d47a0338846bb558b39b9963b8eb2dfedec61867c138c1b17eeb/pdfminer_six-20251230.tar.gz", hash = "sha256:e8f68a14c57e00c2d7276d26519ea64be1b48f91db1cdc776faa80528ca06c1e", size = 8511285, upload-time = "2025-12-30T15:49:13.104Z" }
+sdist = { url = "https://files.pythonhosted.org/packages/34/a4/5cec1112009f0439a5ca6afa8ace321f0ab2f48da3255b7a1c8953014670/pdfminer_six-20260107.tar.gz", hash = "sha256:96bfd431e3577a55a0efd25676968ca4ce8fd5b53f14565f85716ff363889602", size = 8512094, upload-time = "2026-01-07T13:29:12.937Z" }
 wheels = [
-    { url = "https://files.pythonhosted.org/packages/65/d7/b288ea32deb752a09aab73c75e1e7572ab2a2b56c3124a5d1eb24c62ceb3/pdfminer_six-20251230-py3-none-any.whl", hash = "sha256:9ff2e3466a7dfc6de6fd779478850b6b7c2d9e9405aa2a5869376a822771f485", size = 6591909, upload-time = "2025-12-30T15:49:10.76Z" },
+    { url = "https://files.pythonhosted.org/packages/20/8b/28c4eaec9d6b036a52cb44720408f26b1a143ca9bce76cc19e8f5de00ab4/pdfminer_six-20260107-py3-none-any.whl", hash = "sha256:366585ba97e80dffa8f00cebe303d2f381884d8637af4ce422f1df3ef38111a9", size = 6592252, upload-time = "2026-01-07T13:29:10.742Z" },
 ]
 
 [[package]]
@@ -4670,16 +4701,16 @@ wheels = [
 
 [[package]]
 name = "protobuf"
-version = "4.25.8"
+version = "5.29.6"
 source = { registry = "https://pypi.org/simple" }
-sdist = { url = "https://files.pythonhosted.org/packages/df/01/34c8d2b6354906d728703cb9d546a0e534de479e25f1b581e4094c4a85cc/protobuf-4.25.8.tar.gz", hash = "sha256:6135cf8affe1fc6f76cced2641e4ea8d3e59518d1f24ae41ba97bcad82d397cd", size = 380920, upload-time = "2025-05-28T14:22:25.153Z" }
+sdist = { url = "https://files.pythonhosted.org/packages/7e/57/394a763c103e0edf87f0938dafcd918d53b4c011dfc5c8ae80f3b0452dbb/protobuf-5.29.6.tar.gz", hash = "sha256:da9ee6a5424b6b30fd5e45c5ea663aef540ca95f9ad99d1e887e819cdf9b8723", size = 425623, upload-time = "2026-02-04T22:54:40.584Z" }
 wheels = [
-    { url = "https://files.pythonhosted.org/packages/45/ff/05f34305fe6b85bbfbecbc559d423a5985605cad5eda4f47eae9e9c9c5c5/protobuf-4.25.8-cp310-abi3-win32.whl", hash = "sha256:504435d831565f7cfac9f0714440028907f1975e4bed228e58e72ecfff58a1e0", size = 392745, upload-time = "2025-05-28T14:22:10.524Z" },
-    { url = "https://files.pythonhosted.org/packages/08/35/8b8a8405c564caf4ba835b1fdf554da869954712b26d8f2a98c0e434469b/protobuf-4.25.8-cp310-abi3-win_amd64.whl", hash = "sha256:bd551eb1fe1d7e92c1af1d75bdfa572eff1ab0e5bf1736716814cdccdb2360f9", size = 413736, upload-time = "2025-05-28T14:22:13.156Z" },
-    { url = "https://files.pythonhosted.org/packages/28/d7/ab27049a035b258dab43445eb6ec84a26277b16105b277cbe0a7698bdc6c/protobuf-4.25.8-cp37-abi3-macosx_10_9_universal2.whl", hash = "sha256:ca809b42f4444f144f2115c4c1a747b9a404d590f18f37e9402422033e464e0f", size = 394537, upload-time = "2025-05-28T14:22:14.768Z" },
-    { url = "https://files.pythonhosted.org/packages/bd/6d/a4a198b61808dd3d1ee187082ccc21499bc949d639feb948961b48be9a7e/protobuf-4.25.8-cp37-abi3-manylinux2014_aarch64.whl", hash = "sha256:9ad7ef62d92baf5a8654fbb88dac7fa5594cfa70fd3440488a5ca3bfc6d795a7", size = 294005, upload-time = "2025-05-28T14:22:16.052Z" },
-    { url = "https://files.pythonhosted.org/packages/d6/c6/c9deaa6e789b6fc41b88ccbdfe7a42d2b82663248b715f55aa77fbc00724/protobuf-4.25.8-cp37-abi3-manylinux2014_x86_64.whl", hash = "sha256:83e6e54e93d2b696a92cad6e6efc924f3850f82b52e1563778dfab8b355101b0", size = 294924, upload-time = "2025-05-28T14:22:17.105Z" },
-    { url = "https://files.pythonhosted.org/packages/0c/c1/6aece0ab5209981a70cd186f164c133fdba2f51e124ff92b73de7fd24d78/protobuf-4.25.8-py3-none-any.whl", hash = "sha256:15a0af558aa3b13efef102ae6e4f3efac06f1eea11afb3a57db2901447d9fb59", size = 156757, upload-time = "2025-05-28T14:22:24.135Z" },
+    { url = "https://files.pythonhosted.org/packages/d4/88/9ee58ff7863c479d6f8346686d4636dd4c415b0cbeed7a6a7d0617639c2a/protobuf-5.29.6-cp310-abi3-win32.whl", hash = "sha256:62e8a3114992c7c647bce37dcc93647575fc52d50e48de30c6fcb28a6a291eb1", size = 423357, upload-time = "2026-02-04T22:54:25.805Z" },
+    { url = "https://files.pythonhosted.org/packages/1c/66/2dc736a4d576847134fb6d80bd995c569b13cdc7b815d669050bf0ce2d2c/protobuf-5.29.6-cp310-abi3-win_amd64.whl", hash = "sha256:7e6ad413275be172f67fdee0f43484b6de5a904cc1c3ea9804cb6fe2ff366eda", size = 435175, upload-time = "2026-02-04T22:54:28.592Z" },
+    { url = "https://files.pythonhosted.org/packages/06/db/49b05966fd208ae3f44dcd33837b6243b4915c57561d730a43f881f24dea/protobuf-5.29.6-cp38-abi3-macosx_10_9_universal2.whl", hash = "sha256:b5a169e664b4057183a34bdc424540e86eea47560f3c123a0d64de4e137f9269", size = 418619, upload-time = "2026-02-04T22:54:30.266Z" },
+    { url = "https://files.pythonhosted.org/packages/b7/d7/48cbf6b0c3c39761e47a99cb483405f0fde2be22cf00d71ef316ce52b458/protobuf-5.29.6-cp38-abi3-manylinux2014_aarch64.whl", hash = "sha256:a8866b2cff111f0f863c1b3b9e7572dc7eaea23a7fae27f6fc613304046483e6", size = 320284, upload-time = "2026-02-04T22:54:31.782Z" },
+    { url = "https://files.pythonhosted.org/packages/e3/dd/cadd6ec43069247d91f6345fa7a0d2858bef6af366dbd7ba8f05d2c77d3b/protobuf-5.29.6-cp38-abi3-manylinux2014_x86_64.whl", hash = "sha256:e3387f44798ac1106af0233c04fb8abf543772ff241169946f698b3a9a3d3ab9", size = 320478, upload-time = "2026-02-04T22:54:32.909Z" },
+    { url = "https://files.pythonhosted.org/packages/5a/cb/e3065b447186cb70aa65acc70c86baf482d82bf75625bf5a2c4f6919c6a3/protobuf-5.29.6-py3-none-any.whl", hash = "sha256:6b9edb641441b2da9fa8f428760fc136a49cf97a52076010cf22a2ff73438a86", size = 173126, upload-time = "2026-02-04T22:54:39.462Z" },
 ]
 
 [[package]]
@@ -5762,33 +5793,6 @@ wheels = [
     { url = "https://files.pythonhosted.org/packages/a3/dc/17031897dae0efacfea57dfd3a82fdd2a2aeb58e0ff71b77b87e44edc772/setuptools-80.9.0-py3-none-any.whl", hash = "sha256:062d34222ad13e0cc312a4c02d73f059e86a4acbfbdea8f8f76b28c99f306922", size = 1201486, upload-time = "2025-05-27T00:56:49.664Z" },
 ]
 
-[[package]]
-name = "shapely"
-version = "2.1.2"
-source = { registry = "https://pypi.org/simple" }
-dependencies = [
-    { name = "numpy" },
-]
-sdist = { url = "https://files.pythonhosted.org/packages/4d/bc/0989043118a27cccb4e906a46b7565ce36ca7b57f5a18b78f4f1b0f72d9d/shapely-2.1.2.tar.gz", hash = "sha256:2ed4ecb28320a433db18a5bf029986aa8afcfd740745e78847e330d5d94922a9", size = 315489, upload-time = "2025-09-24T13:51:41.432Z" }
-wheels = [
-    { url = "https://files.pythonhosted.org/packages/8f/8d/1ff672dea9ec6a7b5d422eb6d095ed886e2e523733329f75fdcb14ee1149/shapely-2.1.2-cp311-cp311-macosx_10_9_x86_64.whl", hash = "sha256:91121757b0a36c9aac3427a651a7e6567110a4a67c97edf04f8d55d4765f6618", size = 1820038, upload-time = "2025-09-24T13:50:15.628Z" },
-    { url = "https://files.pythonhosted.org/packages/4f/ce/28fab8c772ce5db23a0d86bf0adaee0c4c79d5ad1db766055fa3dab442e2/shapely-2.1.2-cp311-cp311-macosx_11_0_arm64.whl", hash = "sha256:16a9c722ba774cf50b5d4541242b4cce05aafd44a015290c82ba8a16931ff63d", size = 1626039, upload-time = "2025-09-24T13:50:16.881Z" },
-    { url = "https://files.pythonhosted.org/packages/70/8b/868b7e3f4982f5006e9395c1e12343c66a8155c0374fdc07c0e6a1ab547d/shapely-2.1.2-cp311-cp311-manylinux2014_aarch64.manylinux_2_17_aarch64.whl", hash = "sha256:cc4f7397459b12c0b196c9efe1f9d7e92463cbba142632b4cc6d8bbbbd3e2b09", size = 3001519, upload-time = "2025-09-24T13:50:18.606Z" },
-    { url = "https://files.pythonhosted.org/packages/13/02/58b0b8d9c17c93ab6340edd8b7308c0c5a5b81f94ce65705819b7416dba5/shapely-2.1.2-cp311-cp311-manylinux2014_x86_64.manylinux_2_17_x86_64.whl", hash = "sha256:136ab87b17e733e22f0961504d05e77e7be8c9b5a8184f685b4a91a84efe3c26", size = 3110842, upload-time = "2025-09-24T13:50:21.77Z" },
-    { url = "https://files.pythonhosted.org/packages/af/61/8e389c97994d5f331dcffb25e2fa761aeedfb52b3ad9bcdd7b8671f4810a/shapely-2.1.2-cp311-cp311-musllinux_1_2_aarch64.whl", hash = "sha256:16c5d0fc45d3aa0a69074979f4f1928ca2734fb2e0dde8af9611e134e46774e7", size = 4021316, upload-time = "2025-09-24T13:50:23.626Z" },
-    { url = "https://files.pythonhosted.org/packages/d3/d4/9b2a9fe6039f9e42ccf2cb3e84f219fd8364b0c3b8e7bbc857b5fbe9c14c/shapely-2.1.2-cp311-cp311-musllinux_1_2_x86_64.whl", hash = "sha256:6ddc759f72b5b2b0f54a7e7cde44acef680a55019eb52ac63a7af2cf17cb9cd2", size = 4178586, upload-time = "2025-09-24T13:50:25.443Z" },
-    { url = "https://files.pythonhosted.org/packages/16/f6/9840f6963ed4decf76b08fd6d7fed14f8779fb7a62cb45c5617fa8ac6eab/shapely-2.1.2-cp311-cp311-win32.whl", hash = "sha256:2fa78b49485391224755a856ed3b3bd91c8455f6121fee0db0e71cefb07d0ef6", size = 1543961, upload-time = "2025-09-24T13:50:26.968Z" },
-    { url = "https://files.pythonhosted.org/packages/38/1e/3f8ea46353c2a33c1669eb7327f9665103aa3a8dfe7f2e4ef714c210b2c2/shapely-2.1.2-cp311-cp311-win_amd64.whl", hash = "sha256:c64d5c97b2f47e3cd9b712eaced3b061f2b71234b3fc263e0fcf7d889c6559dc", size = 1722856, upload-time = "2025-09-24T13:50:28.497Z" },
-    { url = "https://files.pythonhosted.org/packages/24/c0/f3b6453cf2dfa99adc0ba6675f9aaff9e526d2224cbd7ff9c1a879238693/shapely-2.1.2-cp312-cp312-macosx_10_13_x86_64.whl", hash = "sha256:fe2533caae6a91a543dec62e8360fe86ffcdc42a7c55f9dfd0128a977a896b94", size = 1833550, upload-time = "2025-09-24T13:50:30.019Z" },
-    { url = "https://files.pythonhosted.org/packages/86/07/59dee0bc4b913b7ab59ab1086225baca5b8f19865e6101db9ebb7243e132/shapely-2.1.2-cp312-cp312-macosx_11_0_arm64.whl", hash = "sha256:ba4d1333cc0bc94381d6d4308d2e4e008e0bd128bdcff5573199742ee3634359", size = 1643556, upload-time = "2025-09-24T13:50:32.291Z" },
-    { url = "https://files.pythonhosted.org/packages/26/29/a5397e75b435b9895cd53e165083faed5d12fd9626eadec15a83a2411f0f/shapely-2.1.2-cp312-cp312-manylinux2014_aarch64.manylinux_2_17_aarch64.whl", hash = "sha256:0bd308103340030feef6c111d3eb98d50dc13feea33affc8a6f9fa549e9458a3", size = 2988308, upload-time = "2025-09-24T13:50:33.862Z" },
-    { url = "https://files.pythonhosted.org/packages/b9/37/e781683abac55dde9771e086b790e554811a71ed0b2b8a1e789b7430dd44/shapely-2.1.2-cp312-cp312-manylinux2014_x86_64.manylinux_2_17_x86_64.whl", hash = "sha256:1e7d4d7ad262a48bb44277ca12c7c78cb1b0f56b32c10734ec9a1d30c0b0c54b", size = 3099844, upload-time = "2025-09-24T13:50:35.459Z" },
-    { url = "https://files.pythonhosted.org/packages/d8/f3/9876b64d4a5a321b9dc482c92bb6f061f2fa42131cba643c699f39317cb9/shapely-2.1.2-cp312-cp312-musllinux_1_2_aarch64.whl", hash = "sha256:e9eddfe513096a71896441a7c37db72da0687b34752c4e193577a145c71736fc", size = 3988842, upload-time = "2025-09-24T13:50:37.478Z" },
-    { url = "https://files.pythonhosted.org/packages/d1/a0/704c7292f7014c7e74ec84eddb7b109e1fbae74a16deae9c1504b1d15565/shapely-2.1.2-cp312-cp312-musllinux_1_2_x86_64.whl", hash = "sha256:980c777c612514c0cf99bc8a9de6d286f5e186dcaf9091252fcd444e5638193d", size = 4152714, upload-time = "2025-09-24T13:50:39.9Z" },
-    { url = "https://files.pythonhosted.org/packages/53/46/319c9dc788884ad0785242543cdffac0e6530e4d0deb6c4862bc4143dcf3/shapely-2.1.2-cp312-cp312-win32.whl", hash = "sha256:9111274b88e4d7b54a95218e243282709b330ef52b7b86bc6aaf4f805306f454", size = 1542745, upload-time = "2025-09-24T13:50:41.414Z" },
-    { url = "https://files.pythonhosted.org/packages/ec/bf/cb6c1c505cb31e818e900b9312d514f381fbfa5c4363edfce0fcc4f8c1a4/shapely-2.1.2-cp312-cp312-win_amd64.whl", hash = "sha256:743044b4cfb34f9a67205cee9279feaf60ba7d02e69febc2afc609047cb49179", size = 1722861, upload-time = "2025-09-24T13:50:43.35Z" },
-]
-
 [[package]]
 name = "shellingham"
 version = "1.5.4"
@@ -6814,12 +6818,12 @@ wheels = [
 
 [[package]]
 name = "unstructured"
-version = "0.16.25"
+version = "0.18.31"
 source = { registry = "https://pypi.org/simple" }
 dependencies = [
     { name = "backoff" },
     { name = "beautifulsoup4" },
-    { name = "chardet" },
+    { name = "charset-normalizer" },
     { name = "dataclasses-json" },
     { name = "emoji" },
     { name = "filetype" },
@@ -6827,6 +6831,7 @@ dependencies = [
     { name = "langdetect" },
     { name = "lxml" },
     { name = "nltk" },
+    { name = "numba" },
     { name = "numpy" },
     { name = "psutil" },
     { name = "python-iso639" },
@@ -6839,9 +6844,9 @@ dependencies = [
     { name = "unstructured-client" },
     { name = "wrapt" },
 ]
-sdist = { url = "https://files.pythonhosted.org/packages/64/31/98c4c78e305d1294888adf87fd5ee30577a4c393951341ca32b43f167f1e/unstructured-0.16.25.tar.gz", hash = "sha256:73b9b0f51dbb687af572ecdb849a6811710b9cac797ddeab8ee80fa07d8aa5e6", size = 1683097, upload-time = "2025-03-07T11:19:39.507Z" }
+sdist = { url = "https://files.pythonhosted.org/packages/a9/5f/64285bd69a538bc28753f1423fcaa9d64cd79a9e7c097171b1f0d27e9cdb/unstructured-0.18.31.tar.gz", hash = "sha256:af4bbe32d1894ae6e755f0da6fc0dd307a1d0adeebe0e7cc6278f6cf744339ca", size = 1707700, upload-time = "2026-01-27T15:33:05.378Z" }
 wheels = [
-    { url = "https://files.pythonhosted.org/packages/12/4f/ad08585b5c8a33c82ea119494c4d3023f4796958c56e668b15cc282ec0a0/unstructured-0.16.25-py3-none-any.whl", hash = "sha256:14719ccef2830216cf1c5bf654f75e2bf07b17ca5dcee9da5ac74618130fd337", size = 1769286, upload-time = "2025-03-07T11:19:37.299Z" },
+    { url = "https://files.pythonhosted.org/packages/c8/4a/9c43f39d9e443c9bc3f2e379b305bca27110adc653b071221b3132c18de5/unstructured-0.18.31-py3-none-any.whl", hash = "sha256:fab4641176cb9b192ed38048758aa0d9843121d03626d18f42275afb31e5b2d3", size = 1794889, upload-time = "2026-01-27T15:33:03.136Z" },
 ]
 
 [package.optional-dependencies]

docker/docker-compose-template.yaml

@@ -21,7 +21,7 @@ services:
 
   # API service
   api:
-    image: langgenius/dify-api:1.12.0
+    image: langgenius/dify-api:1.12.1
     restart: always
     environment:
       # Use the shared environment variables.
@@ -63,7 +63,7 @@ services:
   # worker service
   # The Celery worker for processing all queues (dataset, workflow, mail, etc.)
   worker:
-    image: langgenius/dify-api:1.12.0
+    image: langgenius/dify-api:1.12.1
     restart: always
     environment:
       # Use the shared environment variables.
@@ -102,7 +102,7 @@ services:
   # worker_beat service
   # Celery beat for scheduling periodic tasks.
   worker_beat:
-    image: langgenius/dify-api:1.12.0
+    image: langgenius/dify-api:1.12.1
     restart: always
     environment:
       # Use the shared environment variables.
@@ -132,7 +132,7 @@ services:
 
   # Frontend web application.
   web:
-    image: langgenius/dify-web:1.12.0
+    image: langgenius/dify-web:1.12.1
     restart: always
     environment:
       CONSOLE_API_URL: ${CONSOLE_API_URL:-}

docker/docker-compose.yaml

@@ -707,7 +707,7 @@ services:
 
   # API service
   api:
-    image: langgenius/dify-api:1.12.0
+    image: langgenius/dify-api:1.12.1
     restart: always
     environment:
       # Use the shared environment variables.
@@ -749,7 +749,7 @@ services:
   # worker service
   # The Celery worker for processing all queues (dataset, workflow, mail, etc.)
   worker:
-    image: langgenius/dify-api:1.12.0
+    image: langgenius/dify-api:1.12.1
     restart: always
     environment:
       # Use the shared environment variables.
@@ -788,7 +788,7 @@ services:
   # worker_beat service
   # Celery beat for scheduling periodic tasks.
   worker_beat:
-    image: langgenius/dify-api:1.12.0
+    image: langgenius/dify-api:1.12.1
     restart: always
     environment:
       # Use the shared environment variables.
@@ -818,7 +818,7 @@ services:
 
   # Frontend web application.
   web:
-    image: langgenius/dify-web:1.12.0
+    image: langgenius/dify-web:1.12.1
     restart: always
     environment:
       CONSOLE_API_URL: ${CONSOLE_API_URL:-}

web/app/components/app/configuration/config/agent/agent-tools/index.tsx

@@ -109,6 +109,7 @@ const AgentTools: FC = () => {
       tool_parameters: paramsWithDefaultValue,
       notAuthor: !tool.is_team_authorization,
       enabled: true,
+      type: tool.provider_type as CollectionType,
     }
   }
   const handleSelectTool = (tool: ToolDefaultValue) => {

web/app/components/app/configuration/config/automatic/get-automatic-res.tsx

@@ -19,19 +19,21 @@ import { useBoolean, useSessionStorageState } from 'ahooks'
 import * as React from 'react'
 import { useCallback, useEffect, useState } from 'react'
 import { useTranslation } from 'react-i18next'
+import { useShallow } from 'zustand/react/shallow'
 import Button from '@/app/components/base/button'
 import Confirm from '@/app/components/base/confirm'
 import { Generator } from '@/app/components/base/icons/src/vender/other'
-import Loading from '@/app/components/base/loading'
 
+import Loading from '@/app/components/base/loading'
 import Modal from '@/app/components/base/modal'
 import Toast from '@/app/components/base/toast'
-import { ModelTypeEnum } from '@/app/components/header/account-setting/model-provider-page/declarations'
 
+import { ModelTypeEnum } from '@/app/components/header/account-setting/model-provider-page/declarations'
 import { useModelListAndDefaultModelAndCurrentProviderAndModel } from '@/app/components/header/account-setting/model-provider-page/hooks'
 import ModelParameterModal from '@/app/components/header/account-setting/model-provider-page/model-parameter-modal'
 import { generateBasicAppFirstTimeRule, generateRule } from '@/service/debug'
 import { useGenerateRuleTemplate } from '@/service/use-apps'
+import { useStore } from '../../../store'
 import IdeaOutput from './idea-output'
 import InstructionEditorInBasic from './instruction-editor'
 import InstructionEditorInWorkflow from './instruction-editor-in-workflow'
@@ -83,6 +85,9 @@ const GetAutomaticRes: FC<IGetAutomaticResProps> = ({
   onFinished,
 }) => {
   const { t } = useTranslation()
+  const { appDetail } = useStore(useShallow(state => ({
+    appDetail: state.appDetail,
+  })))
   const localModel = localStorage.getItem('auto-gen-model')
     ? JSON.parse(localStorage.getItem('auto-gen-model') as string) as Model
     : null
@@ -235,6 +240,7 @@ const GetAutomaticRes: FC<IGetAutomaticResProps> = ({
           instruction,
           model_config: model,
           no_variable: false,
+          app_id: appDetail?.id,
         })
         apiRes = {
           ...res,
@@ -256,6 +262,7 @@ const GetAutomaticRes: FC<IGetAutomaticResProps> = ({
           instruction,
           ideal_output: ideaOutput,
           model_config: model,
+          app_id: appDetail?.id,
         })
         apiRes = res
         if (error) {

web/app/components/datasets/create/step-two/components/general-chunking-options.tsx

@@ -154,7 +154,7 @@ export const GeneralChunkingOptions: FC<GeneralChunkingOptionsProps> = ({
               </div>
             ))}
             {
-              showSummaryIndexSetting && (
+              showSummaryIndexSetting && IS_CE_EDITION && (
                 <div className="mt-3">
                   <SummaryIndexSetting
                     entry="create-document"

web/app/components/datasets/create/step-two/components/parent-child-options.tsx

@@ -12,6 +12,7 @@ import Divider from '@/app/components/base/divider'
 import { ParentChildChunk } from '@/app/components/base/icons/src/vender/knowledge'
 import RadioCard from '@/app/components/base/radio-card'
 import SummaryIndexSetting from '@/app/components/datasets/settings/summary-index-setting'
+import { IS_CE_EDITION } from '@/config'
 import { ChunkingMode } from '@/models/datasets'
 import FileList from '../../assets/file-list-3-fill.svg'
 import Note from '../../assets/note-mod.svg'
@@ -191,7 +192,7 @@ export const ParentChildOptions: FC<ParentChildOptionsProps> = ({
               </div>
             ))}
             {
-              showSummaryIndexSetting && (
+              showSummaryIndexSetting && IS_CE_EDITION && (
                 <div className="mt-3">
                   <SummaryIndexSetting
                     entry="create-document"

web/app/components/datasets/documents/components/operations.tsx

@@ -26,6 +26,7 @@ import CustomPopover from '@/app/components/base/popover'
 import Switch from '@/app/components/base/switch'
 import { ToastContext } from '@/app/components/base/toast'
 import Tooltip from '@/app/components/base/tooltip'
+import { IS_CE_EDITION } from '@/config'
 import { DataSourceType, DocumentActionType } from '@/models/datasets'
 import {
   useDocumentArchive,
@@ -263,10 +264,14 @@ const Operations = ({
                         <span className={s.actionName}>{t('list.action.sync', { ns: 'datasetDocuments' })}</span>
                       </div>
                     )}
-                    <div className={s.actionItem} onClick={() => onOperate('summary')}>
-                      <SearchLinesSparkle className="h-4 w-4 text-text-tertiary" />
-                      <span className={s.actionName}>{t('list.action.summary', { ns: 'datasetDocuments' })}</span>
-                    </div>
+                    {
+                      IS_CE_EDITION && (
+                        <div className={s.actionItem} onClick={() => onOperate('summary')}>
+                          <SearchLinesSparkle className="h-4 w-4 text-text-tertiary" />
+                          <span className={s.actionName}>{t('list.action.summary', { ns: 'datasetDocuments' })}</span>
+                        </div>
+                      )
+                    }
                     <Divider className="my-1" />
                   </>
                 )}

web/app/components/datasets/documents/detail/completed/common/batch-action.tsx

@@ -7,6 +7,7 @@ import Button from '@/app/components/base/button'
 import Confirm from '@/app/components/base/confirm'
 import Divider from '@/app/components/base/divider'
 import { SearchLinesSparkle } from '@/app/components/base/icons/src/vender/knowledge'
+import { IS_CE_EDITION } from '@/config'
 import { cn } from '@/utils/classnames'
 
 const i18nPrefix = 'batchAction'
@@ -87,7 +88,7 @@ const BatchAction: FC<IBatchActionProps> = ({
             <span className="px-0.5">{t('metadata.metadata', { ns: 'dataset' })}</span>
           </Button>
         )}
-        {onBatchSummary && (
+        {onBatchSummary && IS_CE_EDITION && (
           <Button
             variant="ghost"
             className="gap-x-0.5 px-3"

web/app/components/datasets/settings/form/index.tsx

@@ -21,6 +21,7 @@ import RetrievalMethodConfig from '@/app/components/datasets/common/retrieval-me
 import { ModelTypeEnum } from '@/app/components/header/account-setting/model-provider-page/declarations'
 import { useModelList } from '@/app/components/header/account-setting/model-provider-page/hooks'
 import ModelSelector from '@/app/components/header/account-setting/model-provider-page/model-selector'
+import { IS_CE_EDITION } from '@/config'
 import { useSelector as useAppContextWithSelector } from '@/context/app-context'
 import { useDatasetDetailContextWithSelector } from '@/context/dataset-detail'
 import { useDocLink } from '@/context/i18n'
@@ -359,7 +360,7 @@ const Form = () => {
       {
         indexMethod === IndexingType.QUALIFIED
         && [ChunkingMode.text, ChunkingMode.parentChild].includes(currentDataset?.doc_form as ChunkingMode)
-        && (
+        && IS_CE_EDITION && (
           <>
             <Divider
               type="horizontal"

web/app/components/header/account-setting/members-page/index.tsx

@@ -104,7 +104,7 @@ const MembersPage = () => {
             <UpgradeBtn className="mr-2" loc="member-invite" />
           )}
           <div className="shrink-0">
-            <InviteButton disabled={!isCurrentWorkspaceManager || isMemberFull} onClick={() => setInviteModalVisible(true)} />
+            {isCurrentWorkspaceManager && <InviteButton disabled={isMemberFull} onClick={() => setInviteModalVisible(true)} />}
           </div>
         </div>
         <div className="overflow-visible lg:overflow-visible">

web/app/components/plugins/plugin-detail-panel/tool-selector/hooks/use-tool-selector-state.ts

@@ -129,6 +129,7 @@ export const useToolSelectorState = ({
       extra: {
         description: tool.tool_description,
       },
+      type: tool.provider_type,
     }
   }, [])
 

web/app/components/workflow/block-selector/types.ts

@@ -87,6 +87,7 @@ export type ToolValue = {
   enabled?: boolean
   extra?: { description?: string } & Record<string, unknown>
   credential_id?: string
+  type?: string
 }
 
 export type DataSourceItem = {

web/app/components/workflow/nodes/knowledge-base/panel.tsx

@@ -18,6 +18,7 @@ import {
   Group,
 } from '@/app/components/workflow/nodes/_base/components/layout'
 import VarReferencePicker from '@/app/components/workflow/nodes/_base/components/variable/var-reference-picker'
+import { IS_CE_EDITION } from '@/config'
 import Split from '../_base/components/split'
 import ChunkStructure from './components/chunk-structure'
 import EmbeddingModel from './components/embedding-model'
@@ -172,7 +173,7 @@ const Panel: FC<NodePanelProps<KnowledgeBaseNodeType>> = ({
                 {
                   data.indexing_technique === IndexMethodEnum.QUALIFIED
                   && [ChunkStructureEnum.general, ChunkStructureEnum.parent_child].includes(data.chunk_structure)
-                  && (
+                  && IS_CE_EDITION && (
                     <>
                       <SummaryIndexSetting
                         summaryIndexSetting={data.summary_index_setting}

web/package.json

@@ -1,7 +1,7 @@
 {
   "name": "dify-web",
   "type": "module",
-  "version": "1.12.0",
+  "version": "1.12.1",
   "private": true,
   "packageManager": "pnpm@10.27.0+sha512.72d699da16b1179c14ba9e64dc71c9a40988cbdc65c264cb0e489db7de917f20dcf4d64d8723625f2969ba52d4b7e2a1170682d9ac2a5dcaeaab732b7e16f04a",
   "imports": {

web/service/workflow.ts

@@ -9,7 +9,6 @@ import type {
 } from '@/types/workflow'
 import { get, post } from './base'
 import { getFlowPrefix } from './utils'
-import { sanitizeWorkflowDraftPayload } from './workflow-payload'
 
 export const fetchWorkflowDraft = (url: string) => {
   return get(url, {}, { silent: true }) as Promise<FetchWorkflowDraftResponse>
@@ -19,8 +18,7 @@ export const syncWorkflowDraft = ({ url, params }: {
   url: string
   params: Pick<FetchWorkflowDraftResponse, 'graph' | 'features' | 'environment_variables' | 'conversation_variables'>
 }) => {
-  const sanitized = sanitizeWorkflowDraftPayload(params)
-  return post<CommonResponse & { updated_at: number, hash: string }>(url, { body: sanitized }, { silent: true })
+  return post<CommonResponse & { updated_at: number, hash: string }>(url, { body: params }, { silent: true })
 }
 
 export const fetchNodesDefaultConfigs = (url: string) => {