fix: ensure advanced-chat workflows stop correctly (#27803)

Co-authored-by: autofix-ci[bot] <114827586+autofix-ci[bot]@users.noreply.github.com>
Co-authored-by: crazywoola <100913391+crazywoola@users.noreply.github.com>

api/controllers/console/app/completion.py

@@ -17,7 +17,6 @@ from controllers.console.app.error import (
 from controllers.console.app.wraps import get_app_model
 from controllers.console.wraps import account_initialization_required, edit_permission_required, setup_required
 from controllers.web.error import InvokeRateLimitError as InvokeRateLimitHttpError
-from core.app.apps.base_app_queue_manager import AppQueueManager
 from core.app.entities.app_invoke_entities import InvokeFrom
 from core.errors.error import (
     ModelCurrentlyNotSupportError,
@@ -32,6 +31,7 @@ from libs.login import current_user, login_required
 from models import Account
 from models.model import AppMode
 from services.app_generate_service import AppGenerateService
+from services.app_task_service import AppTaskService
 from services.errors.llm import InvokeRateLimitError
 
 logger = logging.getLogger(__name__)
@@ -121,7 +121,13 @@ class CompletionMessageStopApi(Resource):
     def post(self, app_model, task_id):
         if not isinstance(current_user, Account):
             raise ValueError("current_user must be an Account instance")
-        AppQueueManager.set_stop_flag(task_id, InvokeFrom.DEBUGGER, current_user.id)
+
+        AppTaskService.stop_task(
+            task_id=task_id,
+            invoke_from=InvokeFrom.DEBUGGER,
+            user_id=current_user.id,
+            app_mode=AppMode.value_of(app_model.mode),
+        )
 
         return {"result": "success"}, 200
 
@@ -220,6 +226,12 @@ class ChatMessageStopApi(Resource):
     def post(self, app_model, task_id):
         if not isinstance(current_user, Account):
             raise ValueError("current_user must be an Account instance")
-        AppQueueManager.set_stop_flag(task_id, InvokeFrom.DEBUGGER, current_user.id)
+
+        AppTaskService.stop_task(
+            task_id=task_id,
+            invoke_from=InvokeFrom.DEBUGGER,
+            user_id=current_user.id,
+            app_mode=AppMode.value_of(app_model.mode),
+        )
 
         return {"result": "success"}, 200

api/controllers/console/explore/completion.py

@@ -15,7 +15,6 @@ from controllers.console.app.error import (
 from controllers.console.explore.error import NotChatAppError, NotCompletionAppError
 from controllers.console.explore.wraps import InstalledAppResource
 from controllers.web.error import InvokeRateLimitError as InvokeRateLimitHttpError
-from core.app.apps.base_app_queue_manager import AppQueueManager
 from core.app.entities.app_invoke_entities import InvokeFrom
 from core.errors.error import (
     ModelCurrentlyNotSupportError,
@@ -31,6 +30,7 @@ from libs.login import current_user
 from models import Account
 from models.model import AppMode
 from services.app_generate_service import AppGenerateService
+from services.app_task_service import AppTaskService
 from services.errors.llm import InvokeRateLimitError
 
 from .. import console_ns
@@ -46,7 +46,7 @@ logger = logging.getLogger(__name__)
 class CompletionApi(InstalledAppResource):
     def post(self, installed_app):
         app_model = installed_app.app
-        if app_model.mode != "completion":
+        if app_model.mode != AppMode.COMPLETION:
             raise NotCompletionAppError()
 
         parser = (
@@ -102,12 +102,18 @@ class CompletionApi(InstalledAppResource):
 class CompletionStopApi(InstalledAppResource):
     def post(self, installed_app, task_id):
         app_model = installed_app.app
-        if app_model.mode != "completion":
+        if app_model.mode != AppMode.COMPLETION:
             raise NotCompletionAppError()
 
         if not isinstance(current_user, Account):
             raise ValueError("current_user must be an Account instance")
-        AppQueueManager.set_stop_flag(task_id, InvokeFrom.EXPLORE, current_user.id)
+
+        AppTaskService.stop_task(
+            task_id=task_id,
+            invoke_from=InvokeFrom.EXPLORE,
+            user_id=current_user.id,
+            app_mode=AppMode.value_of(app_model.mode),
+        )
 
         return {"result": "success"}, 200
 
@@ -184,6 +190,12 @@ class ChatStopApi(InstalledAppResource):
 
         if not isinstance(current_user, Account):
             raise ValueError("current_user must be an Account instance")
-        AppQueueManager.set_stop_flag(task_id, InvokeFrom.EXPLORE, current_user.id)
+
+        AppTaskService.stop_task(
+            task_id=task_id,
+            invoke_from=InvokeFrom.EXPLORE,
+            user_id=current_user.id,
+            app_mode=app_mode,
+        )
 
         return {"result": "success"}, 200

api/controllers/service_api/app/completion.py

@@ -17,7 +17,6 @@ from controllers.service_api.app.error import (
 )
 from controllers.service_api.wraps import FetchUserArg, WhereisUserArg, validate_app_token
 from controllers.web.error import InvokeRateLimitError as InvokeRateLimitHttpError
-from core.app.apps.base_app_queue_manager import AppQueueManager
 from core.app.entities.app_invoke_entities import InvokeFrom
 from core.errors.error import (
     ModelCurrentlyNotSupportError,
@@ -30,6 +29,7 @@ from libs import helper
 from libs.helper import uuid_value
 from models.model import App, AppMode, EndUser
 from services.app_generate_service import AppGenerateService
+from services.app_task_service import AppTaskService
 from services.errors.app import IsDraftWorkflowError, WorkflowIdFormatError, WorkflowNotFoundError
 from services.errors.llm import InvokeRateLimitError
 
@@ -88,7 +88,7 @@ class CompletionApi(Resource):
         This endpoint generates a completion based on the provided inputs and query.
         Supports both blocking and streaming response modes.
         """
-        if app_model.mode != "completion":
+        if app_model.mode != AppMode.COMPLETION:
             raise AppUnavailableError()
 
         args = completion_parser.parse_args()
@@ -147,10 +147,15 @@ class CompletionStopApi(Resource):
     @validate_app_token(fetch_user_arg=FetchUserArg(fetch_from=WhereisUserArg.JSON, required=True))
     def post(self, app_model: App, end_user: EndUser, task_id: str):
         """Stop a running completion task."""
-        if app_model.mode != "completion":
+        if app_model.mode != AppMode.COMPLETION:
             raise AppUnavailableError()
 
-        AppQueueManager.set_stop_flag(task_id, InvokeFrom.SERVICE_API, end_user.id)
+        AppTaskService.stop_task(
+            task_id=task_id,
+            invoke_from=InvokeFrom.SERVICE_API,
+            user_id=end_user.id,
+            app_mode=AppMode.value_of(app_model.mode),
+        )
 
         return {"result": "success"}, 200
 
@@ -244,6 +249,11 @@ class ChatStopApi(Resource):
         if app_mode not in {AppMode.CHAT, AppMode.AGENT_CHAT, AppMode.ADVANCED_CHAT}:
             raise NotChatAppError()
 
-        AppQueueManager.set_stop_flag(task_id, InvokeFrom.SERVICE_API, end_user.id)
+        AppTaskService.stop_task(
+            task_id=task_id,
+            invoke_from=InvokeFrom.SERVICE_API,
+            user_id=end_user.id,
+            app_mode=app_mode,
+        )
 
         return {"result": "success"}, 200

api/controllers/web/completion.py

@@ -17,7 +17,6 @@ from controllers.web.error import (
 )
 from controllers.web.error import InvokeRateLimitError as InvokeRateLimitHttpError
 from controllers.web.wraps import WebApiResource
-from core.app.apps.base_app_queue_manager import AppQueueManager
 from core.app.entities.app_invoke_entities import InvokeFrom
 from core.errors.error import (
     ModelCurrentlyNotSupportError,
@@ -29,6 +28,7 @@ from libs import helper
 from libs.helper import uuid_value
 from models.model import AppMode
 from services.app_generate_service import AppGenerateService
+from services.app_task_service import AppTaskService
 from services.errors.llm import InvokeRateLimitError
 
 logger = logging.getLogger(__name__)
@@ -64,7 +64,7 @@ class CompletionApi(WebApiResource):
         }
     )
     def post(self, app_model, end_user):
-        if app_model.mode != "completion":
+        if app_model.mode != AppMode.COMPLETION:
             raise NotCompletionAppError()
 
         parser = (
@@ -125,10 +125,15 @@ class CompletionStopApi(WebApiResource):
         }
     )
     def post(self, app_model, end_user, task_id):
-        if app_model.mode != "completion":
+        if app_model.mode != AppMode.COMPLETION:
             raise NotCompletionAppError()
 
-        AppQueueManager.set_stop_flag(task_id, InvokeFrom.WEB_APP, end_user.id)
+        AppTaskService.stop_task(
+            task_id=task_id,
+            invoke_from=InvokeFrom.WEB_APP,
+            user_id=end_user.id,
+            app_mode=AppMode.value_of(app_model.mode),
+        )
 
         return {"result": "success"}, 200
 
@@ -234,6 +239,11 @@ class ChatStopApi(WebApiResource):
         if app_mode not in {AppMode.CHAT, AppMode.AGENT_CHAT, AppMode.ADVANCED_CHAT}:
             raise NotChatAppError()
 
-        AppQueueManager.set_stop_flag(task_id, InvokeFrom.WEB_APP, end_user.id)
+        AppTaskService.stop_task(
+            task_id=task_id,
+            invoke_from=InvokeFrom.WEB_APP,
+            user_id=end_user.id,
+            app_mode=app_mode,
+        )
 
         return {"result": "success"}, 200