feature: Add logic to handle AppInvokeQuotaExceededError in the servi…

…ce API interface.

api/controllers/console/app/completion.py

@@ -80,7 +80,7 @@ def post(self, app_model):
             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.")

api/controllers/service_api/app/completion.py

@@ -17,7 +17,12 @@
 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 @@ def post(self, app_model: App, end_user: EndUser):
             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 @@ def post(self, app_model: App, end_user: EndUser):
             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.")

api/controllers/service_api/app/workflow.py

@@ -14,7 +14,12 @@
 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 models.model import App, AppMode, EndUser
@@ -59,7 +64,7 @@ def post(self, app_model: App, end_user: EndUser):
             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.")

api/core/app/features/rate_limiting/rate_limit.py

@@ -51,6 +51,7 @@ def enter(self, request_id: Optional[str] = None) -> str:
             request_id = RateLimit.gen_request_key()
         if time.time() - self.last_recalculate_time > RateLimit._ACTIVE_REQUESTS_COUNT_FLUSH_INTERVAL:
             self.flush_active_requests()
+
         redis_client.hset(self.active_requests_key, request_id, str(time.time()))
         active_requests_count = redis_client.hlen(self.active_requests_key)
         if active_requests_count > self.max_active_requests: