feat: app rate limit (#5844)

Co-authored-by: liuzhenghua-jk <liuzhenghua-jk@360shuke.com>
Co-authored-by: takatost <takatost@gmail.com>

api/controllers/service_api/app/completion.py

@@ -17,7 +17,12 @@ from controllers.service_api.app.error import (
 from controllers.service_api.wraps import FetchUserArg, WhereisUserArg, validate_app_token
 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, ProviderTokenNotInitError, QuotaExceededError
+from core.errors.error import (
+    AppInvokeQuotaExceededError,
+    ModelCurrentlyNotSupportError,
+    ProviderTokenNotInitError,
+    QuotaExceededError,
+)
 from core.model_runtime.errors.invoke import InvokeError
 from libs import helper
 from libs.helper import uuid_value
@@ -69,7 +74,7 @@ class CompletionApi(Resource):
             raise ProviderModelCurrentlyNotSupportError()
         except InvokeError as e:
             raise CompletionRequestError(e.description)
-        except ValueError as e:
+        except (ValueError, AppInvokeQuotaExceededError) as e:
             raise e
         except Exception as e:
             logging.exception("internal server error.")
@@ -132,7 +137,7 @@ class ChatApi(Resource):
             raise ProviderModelCurrentlyNotSupportError()
         except InvokeError as e:
             raise CompletionRequestError(e.description)
-        except ValueError as e:
+        except (ValueError, AppInvokeQuotaExceededError) as e:
             raise e
         except Exception as e:
             logging.exception("internal server error.")