chore: workflow performance

Signed-off-by: yihong0618 <zouzou0208@gmail.com>

.devcontainer/Dockerfile

@@ -1,4 +1,4 @@
-FROM mcr.microsoft.com/devcontainers/python:3.12-bullseye
+FROM mcr.microsoft.com/devcontainers/python:3.12-bookworm
 
 RUN apt-get update && export DEBIAN_FRONTEND=noninteractive \
      && apt-get -y install libgmp-dev libmpfr-dev libmpc-dev

Makefile

@@ -26,7 +26,6 @@ prepare-web:
 	@echo "🌐 Setting up web environment..."
 	@cp -n web/.env.example web/.env 2>/dev/null || echo "Web .env already exists"
 	@cd web && pnpm install
-	@cd web && pnpm build
 	@echo "✅ Web environment prepared (not started)"
 
 # Step 3: Prepare API environment

README.md

@@ -40,18 +40,18 @@
 
 <p align="center">
   <a href="./README.md"><img alt="README in English" src="https://img.shields.io/badge/English-d9d9d9"></a>
-  <a href="./README/README_TW.md"><img alt="繁體中文文件" src="https://img.shields.io/badge/繁體中文-d9d9d9"></a>
-  <a href="./README/README_CN.md"><img alt="简体中文版自述文件" src="https://img.shields.io/badge/简体中文-d9d9d9"></a>
-  <a href="./README/README_JA.md"><img alt="日本語のREADME" src="https://img.shields.io/badge/日本語-d9d9d9"></a>
-  <a href="./README/README_ES.md"><img alt="README en Español" src="https://img.shields.io/badge/Español-d9d9d9"></a>
-  <a href="./README/README_FR.md"><img alt="README en Français" src="https://img.shields.io/badge/Français-d9d9d9"></a>
-  <a href="./README/README_KL.md"><img alt="README tlhIngan Hol" src="https://img.shields.io/badge/Klingon-d9d9d9"></a>
-  <a href="./README/README_KR.md"><img alt="README in Korean" src="https://img.shields.io/badge/한국어-d9d9d9"></a>
-  <a href="./README/README_AR.md"><img alt="README بالعربية" src="https://img.shields.io/badge/العربية-d9d9d9"></a>
-  <a href="./README/README_TR.md"><img alt="Türkçe README" src="https://img.shields.io/badge/Türkçe-d9d9d9"></a>
-  <a href="./README/README_VI.md"><img alt="README Tiếng Việt" src="https://img.shields.io/badge/Ti%E1%BA%BFng%20Vi%E1%BB%87t-d9d9d9"></a>
-  <a href="./README/README_DE.md"><img alt="README in Deutsch" src="https://img.shields.io/badge/German-d9d9d9"></a>
-  <a href="./README/README_BN.md"><img alt="README in বাংলা" src="https://img.shields.io/badge/বাংলা-d9d9d9"></a>
+  <a href="./docs/zh-TW/README.md"><img alt="繁體中文文件" src="https://img.shields.io/badge/繁體中文-d9d9d9"></a>
+  <a href="./docs/zh-CN/README.md"><img alt="简体中文文件" src="https://img.shields.io/badge/简体中文-d9d9d9"></a>
+  <a href="./docs/ja-JP/README.md"><img alt="日本語のREADME" src="https://img.shields.io/badge/日本語-d9d9d9"></a>
+  <a href="./docs/es-ES/README.md"><img alt="README en Español" src="https://img.shields.io/badge/Español-d9d9d9"></a>
+  <a href="./docs/fr-FR/README.md"><img alt="README en Français" src="https://img.shields.io/badge/Français-d9d9d9"></a>
+  <a href="./docs/tlh/README.md"><img alt="README tlhIngan Hol" src="https://img.shields.io/badge/Klingon-d9d9d9"></a>
+  <a href="./docs/ko-KR/README.md"><img alt="README in Korean" src="https://img.shields.io/badge/한국어-d9d9d9"></a>
+  <a href="./docs/ar-SA/README.md"><img alt="README بالعربية" src="https://img.shields.io/badge/العربية-d9d9d9"></a>
+  <a href="./docs/tr-TR/README.md"><img alt="Türkçe README" src="https://img.shields.io/badge/Türkçe-d9d9d9"></a>
+  <a href="./docs/vi-VN/README.md"><img alt="README Tiếng Việt" src="https://img.shields.io/badge/Ti%E1%BA%BFng%20Vi%E1%BB%87t-d9d9d9"></a>
+  <a href="./docs/de-DE/README.md"><img alt="README in Deutsch" src="https://img.shields.io/badge/German-d9d9d9"></a>
+  <a href="./docs/bn-BD/README.md"><img alt="README in বাংলা" src="https://img.shields.io/badge/বাংলা-d9d9d9"></a>
 </p>
 
 Dify is an open-source platform for developing LLM applications. Its intuitive interface combines agentic AI workflows, RAG pipelines, agent capabilities, model management, observability features, and more—allowing you to quickly move from prototype to production.

api/.env.example

@@ -427,8 +427,8 @@ CODE_EXECUTION_POOL_MAX_KEEPALIVE_CONNECTIONS=20
 CODE_EXECUTION_POOL_KEEPALIVE_EXPIRY=5.0
 CODE_MAX_NUMBER=9223372036854775807
 CODE_MIN_NUMBER=-9223372036854775808
-CODE_MAX_STRING_LENGTH=80000
-TEMPLATE_TRANSFORM_MAX_LENGTH=80000
+CODE_MAX_STRING_LENGTH=400000
+TEMPLATE_TRANSFORM_MAX_LENGTH=400000
 CODE_MAX_STRING_ARRAY_LENGTH=30
 CODE_MAX_OBJECT_ARRAY_LENGTH=30
 CODE_MAX_NUMBER_ARRAY_LENGTH=1000

api/configs/feature/__init__.py

@@ -150,7 +150,7 @@ class CodeExecutionSandboxConfig(BaseSettings):
 
     CODE_MAX_STRING_LENGTH: PositiveInt = Field(
         description="Maximum allowed length for strings in code execution",
-        default=80000,
+        default=400_000,
     )
 
     CODE_MAX_STRING_ARRAY_LENGTH: PositiveInt = Field(
@@ -582,6 +582,11 @@ class WorkflowConfig(BaseSettings):
         default=200 * 1024,
     )
 
+    TEMPLATE_TRANSFORM_MAX_LENGTH: PositiveInt = Field(
+        description="Maximum number of characters allowed in Template Transform node output",
+        default=400_000,
+    )
+
     # GraphEngine Worker Pool Configuration
     GRAPH_ENGINE_MIN_WORKERS: PositiveInt = Field(
         description="Minimum number of workers per GraphEngine instance",

api/constants/__init__.py

@@ -1,4 +1,5 @@
 from configs import dify_config
+from libs.collection_utils import convert_to_lower_and_upper_set
 
 HIDDEN_VALUE = "[__HIDDEN__]"
 UNKNOWN_VALUE = "[__UNKNOWN__]"
@@ -6,24 +7,39 @@ UUID_NIL = "00000000-0000-0000-0000-000000000000"
 
 DEFAULT_FILE_NUMBER_LIMITS = 3
 
-IMAGE_EXTENSIONS = ["jpg", "jpeg", "png", "webp", "gif", "svg"]
-IMAGE_EXTENSIONS.extend([ext.upper() for ext in IMAGE_EXTENSIONS])
+IMAGE_EXTENSIONS = convert_to_lower_and_upper_set({"jpg", "jpeg", "png", "webp", "gif", "svg"})
 
-VIDEO_EXTENSIONS = ["mp4", "mov", "mpeg", "webm"]
-VIDEO_EXTENSIONS.extend([ext.upper() for ext in VIDEO_EXTENSIONS])
+VIDEO_EXTENSIONS = convert_to_lower_and_upper_set({"mp4", "mov", "mpeg", "webm"})
 
-AUDIO_EXTENSIONS = ["mp3", "m4a", "wav", "amr", "mpga"]
-AUDIO_EXTENSIONS.extend([ext.upper() for ext in AUDIO_EXTENSIONS])
+AUDIO_EXTENSIONS = convert_to_lower_and_upper_set({"mp3", "m4a", "wav", "amr", "mpga"})
 
-
-_doc_extensions: list[str]
+_doc_extensions: set[str]
 if dify_config.ETL_TYPE == "Unstructured":
-    _doc_extensions = ["txt", "markdown", "md", "mdx", "pdf", "html", "htm", "xlsx", "xls", "vtt", "properties"]
-    _doc_extensions.extend(("doc", "docx", "csv", "eml", "msg", "pptx", "xml", "epub"))
+    _doc_extensions = {
+        "txt",
+        "markdown",
+        "md",
+        "mdx",
+        "pdf",
+        "html",
+        "htm",
+        "xlsx",
+        "xls",
+        "vtt",
+        "properties",
+        "doc",
+        "docx",
+        "csv",
+        "eml",
+        "msg",
+        "pptx",
+        "xml",
+        "epub",
+    }
     if dify_config.UNSTRUCTURED_API_URL:
-        _doc_extensions.append("ppt")
+        _doc_extensions.add("ppt")
 else:
-    _doc_extensions = [
+    _doc_extensions = {
         "txt",
         "markdown",
         "md",
@@ -37,5 +53,5 @@ else:
         "csv",
         "vtt",
         "properties",
-    ]
-DOCUMENT_EXTENSIONS = _doc_extensions + [ext.upper() for ext in _doc_extensions]
+    }
+DOCUMENT_EXTENSIONS: set[str] = convert_to_lower_and_upper_set(_doc_extensions)

api/controllers/console/app/app.py

@@ -19,6 +19,7 @@ from core.ops.ops_trace_manager import OpsTraceManager
 from extensions.ext_database import db
 from fields.app_fields import app_detail_fields, app_detail_fields_with_site, app_pagination_fields
 from libs.login import login_required
+from libs.validators import validate_description_length
 from models import Account, App
 from services.app_dsl_service import AppDslService, ImportMode
 from services.app_service import AppService
@@ -28,12 +29,6 @@ from services.feature_service import FeatureService
 ALLOW_CREATE_APP_MODES = ["chat", "agent-chat", "advanced-chat", "workflow", "completion"]
 
 
-def _validate_description_length(description):
-    if description and len(description) > 400:
-        raise ValueError("Description cannot exceed 400 characters.")
-    return description
-
-
 @console_ns.route("/apps")
 class AppListApi(Resource):
     @api.doc("list_apps")
@@ -138,7 +133,7 @@ class AppListApi(Resource):
         """Create app"""
         parser = reqparse.RequestParser()
         parser.add_argument("name", type=str, required=True, location="json")
-        parser.add_argument("description", type=_validate_description_length, location="json")
+        parser.add_argument("description", type=validate_description_length, location="json")
         parser.add_argument("mode", type=str, choices=ALLOW_CREATE_APP_MODES, location="json")
         parser.add_argument("icon_type", type=str, location="json")
         parser.add_argument("icon", type=str, location="json")
@@ -219,7 +214,7 @@ class AppApi(Resource):
 
         parser = reqparse.RequestParser()
         parser.add_argument("name", type=str, required=True, nullable=False, location="json")
-        parser.add_argument("description", type=_validate_description_length, location="json")
+        parser.add_argument("description", type=validate_description_length, location="json")
         parser.add_argument("icon_type", type=str, location="json")
         parser.add_argument("icon", type=str, location="json")
         parser.add_argument("icon_background", type=str, location="json")
@@ -297,7 +292,7 @@ class AppCopyApi(Resource):
 
         parser = reqparse.RequestParser()
         parser.add_argument("name", type=str, location="json")
-        parser.add_argument("description", type=_validate_description_length, location="json")
+        parser.add_argument("description", type=validate_description_length, location="json")
         parser.add_argument("icon_type", type=str, location="json")
         parser.add_argument("icon", type=str, location="json")
         parser.add_argument("icon_background", type=str, location="json")

api/controllers/console/datasets/datasets.py

@@ -1,4 +1,5 @@
-import flask_restx
+from typing import Any, cast
+
 from flask import request
 from flask_login import current_user
 from flask_restx import Resource, fields, marshal, marshal_with, reqparse
@@ -30,24 +31,20 @@ from fields.app_fields import related_app_list
 from fields.dataset_fields import dataset_detail_fields, dataset_query_detail_fields
 from fields.document_fields import document_status_fields
 from libs.login import login_required
+from libs.validators import validate_description_length
 from models import ApiToken, Dataset, Document, DocumentSegment, UploadFile
+from models.account import Account
 from models.dataset import DatasetPermissionEnum
 from models.provider_ids import ModelProviderID
 from services.dataset_service import DatasetPermissionService, DatasetService, DocumentService
 
 
-def _validate_name(name):
+def _validate_name(name: str) -> str:
     if not name or len(name) < 1 or len(name) > 40:
         raise ValueError("Name must be between 1 to 40 characters.")
     return name
 
 
-def _validate_description_length(description):
-    if description and len(description) > 400:
-        raise ValueError("Description cannot exceed 400 characters.")
-    return description
-
-
 @console_ns.route("/datasets")
 class DatasetListApi(Resource):
     @api.doc("get_datasets")
@@ -92,7 +89,7 @@ class DatasetListApi(Resource):
         for embedding_model in embedding_models:
             model_names.append(f"{embedding_model.model}:{embedding_model.provider.provider}")
 
-        data = marshal(datasets, dataset_detail_fields)
+        data = cast(list[dict[str, Any]], marshal(datasets, dataset_detail_fields))
         for item in data:
             # convert embedding_model_provider to plugin standard format
             if item["indexing_technique"] == "high_quality" and item["embedding_model_provider"]:
@@ -147,7 +144,7 @@ class DatasetListApi(Resource):
         )
         parser.add_argument(
             "description",
-            type=_validate_description_length,
+            type=validate_description_length,
             nullable=True,
             required=False,
             default="",
@@ -192,7 +189,7 @@ class DatasetListApi(Resource):
                 name=args["name"],
                 description=args["description"],
                 indexing_technique=args["indexing_technique"],
-                account=current_user,
+                account=cast(Account, current_user),
                 permission=DatasetPermissionEnum.ONLY_ME,
                 provider=args["provider"],
                 external_knowledge_api_id=args["external_knowledge_api_id"],
@@ -224,7 +221,7 @@ class DatasetApi(Resource):
             DatasetService.check_dataset_permission(dataset, current_user)
         except services.errors.account.NoPermissionError as e:
             raise Forbidden(str(e))
-        data = marshal(dataset, dataset_detail_fields)
+        data = cast(dict[str, Any], marshal(dataset, dataset_detail_fields))
         if dataset.indexing_technique == "high_quality":
             if dataset.embedding_model_provider:
                 provider_id = ModelProviderID(dataset.embedding_model_provider)
@@ -288,7 +285,7 @@ class DatasetApi(Resource):
             help="type is required. Name must be between 1 to 40 characters.",
             type=_validate_name,
         )
-        parser.add_argument("description", location="json", store_missing=False, type=_validate_description_length)
+        parser.add_argument("description", location="json", store_missing=False, type=validate_description_length)
         parser.add_argument(
             "indexing_technique",
             type=str,
@@ -369,7 +366,7 @@ class DatasetApi(Resource):
         if dataset is None:
             raise NotFound("Dataset not found.")
 
-        result_data = marshal(dataset, dataset_detail_fields)
+        result_data = cast(dict[str, Any], marshal(dataset, dataset_detail_fields))
         tenant_id = current_user.current_tenant_id
 
         if data.get("partial_member_list") and data.get("permission") == "partial_members":
@@ -688,7 +685,7 @@ class DatasetApiKeyApi(Resource):
         )
 
         if current_key_count >= self.max_keys:
-            flask_restx.abort(
+            api.abort(
                 400,
                 message=f"Cannot create more than {self.max_keys} API keys for this resource type.",
                 code="max_keys_exceeded",
@@ -733,7 +730,7 @@ class DatasetApiDeleteApi(Resource):
         )
 
         if key is None:
-            flask_restx.abort(404, message="API key not found")
+            api.abort(404, message="API key not found")
 
         db.session.query(ApiToken).where(ApiToken.id == api_key_id).delete()
         db.session.commit()

api/controllers/console/datasets/datasets_document.py

@@ -55,6 +55,7 @@ from fields.document_fields import (
 from libs.datetime_utils import naive_utc_now
 from libs.login import login_required
 from models import Dataset, DatasetProcessRule, Document, DocumentSegment, UploadFile
+from models.account import Account
 from models.dataset import DocumentPipelineExecutionLog
 from services.dataset_service import DatasetService, DocumentService
 from services.entities.knowledge_entities.knowledge_entities import KnowledgeConfig
@@ -418,7 +419,9 @@ class DatasetInitApi(Resource):
 
         try:
             dataset, documents, batch = DocumentService.save_document_without_dataset_id(
-                tenant_id=current_user.current_tenant_id, knowledge_config=knowledge_config, account=current_user
+                tenant_id=current_user.current_tenant_id,
+                knowledge_config=knowledge_config,
+                account=cast(Account, current_user),
             )
         except ProviderTokenNotInitError as ex:
             raise ProviderNotInitializeError(ex.description)
@@ -452,7 +455,7 @@ class DocumentIndexingEstimateApi(DocumentResource):
             raise DocumentAlreadyFinishedError()
 
         data_process_rule = document.dataset_process_rule
-        data_process_rule_dict = data_process_rule.to_dict()
+        data_process_rule_dict = data_process_rule.to_dict() if data_process_rule else {}
 
         response = {"tokens": 0, "total_price": 0, "currency": "USD", "total_segments": 0, "preview": []}
 
@@ -514,7 +517,7 @@ class DocumentBatchIndexingEstimateApi(DocumentResource):
         if not documents:
             return {"tokens": 0, "total_price": 0, "currency": "USD", "total_segments": 0, "preview": []}, 200
         data_process_rule = documents[0].dataset_process_rule
-        data_process_rule_dict = data_process_rule.to_dict()
+        data_process_rule_dict = data_process_rule.to_dict() if data_process_rule else {}
         extract_settings = []
         for document in documents:
             if document.indexing_status in {"completed", "error"}:
@@ -753,7 +756,7 @@ class DocumentApi(DocumentResource):
             }
         else:
             dataset_process_rules = DatasetService.get_process_rules(dataset_id)
-            document_process_rules = document.dataset_process_rule.to_dict()
+            document_process_rules = document.dataset_process_rule.to_dict() if document.dataset_process_rule else {}
             data_source_info = document.data_source_detail_dict
             response = {
                 "id": document.id,
@@ -1073,7 +1076,9 @@ class DocumentRenameApi(DocumentResource):
         if not current_user.is_dataset_editor:
             raise Forbidden()
         dataset = DatasetService.get_dataset(dataset_id)
-        DatasetService.check_dataset_operator_permission(current_user, dataset)
+        if not dataset:
+            raise NotFound("Dataset not found.")
+        DatasetService.check_dataset_operator_permission(cast(Account, current_user), dataset)
         parser = reqparse.RequestParser()
         parser.add_argument("name", type=str, required=True, nullable=False, location="json")
         args = parser.parse_args()

api/controllers/console/datasets/datasets_segments.py

@@ -392,7 +392,12 @@ class DatasetDocumentSegmentBatchImportApi(Resource):
             # send batch add segments task
             redis_client.setnx(indexing_cache_key, "waiting")
             batch_create_segment_to_index_task.delay(
-                str(job_id), upload_file_id, dataset_id, document_id, current_user.current_tenant_id, current_user.id
+                str(job_id),
+                upload_file_id,
+                dataset_id,
+                document_id,
+                current_user.current_tenant_id,
+                current_user.id,
             )
         except Exception as e:
             return {"error": str(e)}, 500
@@ -468,7 +473,8 @@ class ChildChunkAddApi(Resource):
         parser.add_argument("content", type=str, required=True, nullable=False, location="json")
         args = parser.parse_args()
         try:
-            child_chunk = SegmentService.create_child_chunk(args.get("content"), segment, document, dataset)
+            content = args["content"]
+            child_chunk = SegmentService.create_child_chunk(content, segment, document, dataset)
         except ChildChunkIndexingServiceError as e:
             raise ChildChunkIndexingError(str(e))
         return {"data": marshal(child_chunk, child_chunk_fields)}, 200
@@ -557,7 +563,8 @@ class ChildChunkAddApi(Resource):
         parser.add_argument("chunks", type=list, required=True, nullable=False, location="json")
         args = parser.parse_args()
         try:
-            chunks = [ChildChunkUpdateArgs(**chunk) for chunk in args.get("chunks")]
+            chunks_data = args["chunks"]
+            chunks = [ChildChunkUpdateArgs(**chunk) for chunk in chunks_data]
             child_chunks = SegmentService.update_child_chunks(chunks, segment, document, dataset)
         except ChildChunkIndexingServiceError as e:
             raise ChildChunkIndexingError(str(e))
@@ -674,9 +681,8 @@ class ChildChunkUpdateApi(Resource):
         parser.add_argument("content", type=str, required=True, nullable=False, location="json")
         args = parser.parse_args()
         try:
-            child_chunk = SegmentService.update_child_chunk(
-                args.get("content"), child_chunk, segment, document, dataset
-            )
+            content = args["content"]
+            child_chunk = SegmentService.update_child_chunk(content, child_chunk, segment, document, dataset)
         except ChildChunkIndexingServiceError as e:
             raise ChildChunkIndexingError(str(e))
         return {"data": marshal(child_chunk, child_chunk_fields)}, 200

api/controllers/console/datasets/external.py

@@ -1,3 +1,5 @@
+from typing import cast
+
 from flask import request
 from flask_login import current_user
 from flask_restx import Resource, fields, marshal, reqparse
@@ -9,13 +11,14 @@ from controllers.console.datasets.error import DatasetNameDuplicateError
 from controllers.console.wraps import account_initialization_required, setup_required
 from fields.dataset_fields import dataset_detail_fields
 from libs.login import login_required
+from models.account import Account
 from services.dataset_service import DatasetService
 from services.external_knowledge_service import ExternalDatasetService
 from services.hit_testing_service import HitTestingService
 from services.knowledge_service import ExternalDatasetTestService
 
 
-def _validate_name(name):
+def _validate_name(name: str) -> str:
     if not name or len(name) < 1 or len(name) > 100:
         raise ValueError("Name must be between 1 to 100 characters.")
     return name
@@ -274,7 +277,7 @@ class ExternalKnowledgeHitTestingApi(Resource):
             response = HitTestingService.external_retrieve(
                 dataset=dataset,
                 query=args["query"],
-                account=current_user,
+                account=cast(Account, current_user),
                 external_retrieval_model=args["external_retrieval_model"],
                 metadata_filtering_conditions=args["metadata_filtering_conditions"],
             )

api/controllers/console/datasets/hit_testing_base.py

@@ -1,10 +1,11 @@
 import logging
+from typing import cast
 
 from flask_login import current_user
 from flask_restx import marshal, reqparse
 from werkzeug.exceptions import Forbidden, InternalServerError, NotFound
 
-import services.dataset_service
+import services
 from controllers.console.app.error import (
     CompletionRequestError,
     ProviderModelCurrentlyNotSupportError,
@@ -20,6 +21,7 @@ from core.errors.error import (
 )
 from core.model_runtime.errors.invoke import InvokeError
 from fields.hit_testing_fields import hit_testing_record_fields
+from models.account import Account
 from services.dataset_service import DatasetService
 from services.hit_testing_service import HitTestingService
 
@@ -59,7 +61,7 @@ class DatasetsHitTestingBase:
             response = HitTestingService.retrieve(
                 dataset=dataset,
                 query=args["query"],
-                account=current_user,
+                account=cast(Account, current_user),
                 retrieval_model=args["retrieval_model"],
                 external_retrieval_model=args["external_retrieval_model"],
                 limit=10,

api/controllers/console/datasets/metadata.py

@@ -62,6 +62,7 @@ class DatasetMetadataApi(Resource):
         parser = reqparse.RequestParser()
         parser.add_argument("name", type=str, required=True, nullable=False, location="json")
         args = parser.parse_args()
+        name = args["name"]
 
         dataset_id_str = str(dataset_id)
         metadata_id_str = str(metadata_id)
@@ -70,7 +71,7 @@ class DatasetMetadataApi(Resource):
             raise NotFound("Dataset not found.")
         DatasetService.check_dataset_permission(dataset, current_user)
 
-        metadata = MetadataService.update_metadata_name(dataset_id_str, metadata_id_str, args.get("name"))
+        metadata = MetadataService.update_metadata_name(dataset_id_str, metadata_id_str, name)
         return metadata, 200
 
     @setup_required

api/controllers/console/datasets/rag_pipeline/datasource_auth.py

@@ -1,4 +1,3 @@
-from fastapi.encoders import jsonable_encoder
 from flask import make_response, redirect, request
 from flask_login import current_user
 from flask_restx import Resource, reqparse
@@ -11,6 +10,7 @@ from controllers.console.wraps import (
     setup_required,
 )
 from core.model_runtime.errors.validate import CredentialsValidateFailedError
+from core.model_runtime.utils.encoders import jsonable_encoder
 from core.plugin.impl.oauth import OAuthHandler
 from libs.helper import StrLen
 from libs.login import login_required

api/controllers/console/datasets/rag_pipeline/rag_pipeline.py

@@ -20,13 +20,13 @@ from services.rag_pipeline.rag_pipeline import RagPipelineService
 logger = logging.getLogger(__name__)
 
 
-def _validate_name(name):
+def _validate_name(name: str) -> str:
     if not name or len(name) < 1 or len(name) > 40:
         raise ValueError("Name must be between 1 to 40 characters.")
     return name
 
 
-def _validate_description_length(description):
+def _validate_description_length(description: str) -> str:
     if len(description) > 400:
         raise ValueError("Description cannot exceed 400 characters.")
     return description
@@ -76,7 +76,7 @@ class CustomizedPipelineTemplateApi(Resource):
         )
         parser.add_argument(
             "description",
-            type=str,
+            type=_validate_description_length,
             nullable=True,
             required=False,
             default="",
@@ -133,7 +133,7 @@ class PublishCustomizedPipelineTemplateApi(Resource):
         )
         parser.add_argument(
             "description",
-            type=str,
+            type=_validate_description_length,
             nullable=True,
             required=False,
             default="",

api/controllers/console/datasets/rag_pipeline/rag_pipeline_datasets.py

@@ -1,5 +1,5 @@
-from flask_login import current_user  # type: ignore  # type: ignore
-from flask_restx import Resource, marshal, reqparse  # type: ignore
+from flask_login import current_user
+from flask_restx import Resource, marshal, reqparse
 from sqlalchemy.orm import Session
 from werkzeug.exceptions import Forbidden
 
@@ -20,18 +20,6 @@ from services.entities.knowledge_entities.rag_pipeline_entities import IconInfo,
 from services.rag_pipeline.rag_pipeline_dsl_service import RagPipelineDslService
 
 
-def _validate_name(name):
-    if not name or len(name) < 1 or len(name) > 40:
-        raise ValueError("Name must be between 1 to 40 characters.")
-    return name
-
-
-def _validate_description_length(description):
-    if len(description) > 400:
-        raise ValueError("Description cannot exceed 400 characters.")
-    return description
-
-
 @console_ns.route("/rag/pipeline/dataset")
 class CreateRagPipelineDatasetApi(Resource):
     @setup_required

api/controllers/console/datasets/rag_pipeline/rag_pipeline_draft_variable.py

@@ -1,5 +1,5 @@
 import logging
-from typing import Any, NoReturn
+from typing import NoReturn
 
 from flask import Response
 from flask_restx import Resource, fields, inputs, marshal, marshal_with, reqparse
@@ -11,14 +11,12 @@ from controllers.console.app.error import (
     DraftWorkflowNotExist,
 )
 from controllers.console.app.workflow_draft_variable import (
-    _WORKFLOW_DRAFT_VARIABLE_FIELDS,
-    _WORKFLOW_DRAFT_VARIABLE_WITHOUT_VALUE_FIELDS,
+    _WORKFLOW_DRAFT_VARIABLE_FIELDS,  # type: ignore[private-usage]
+    _WORKFLOW_DRAFT_VARIABLE_WITHOUT_VALUE_FIELDS,  # type: ignore[private-usage]
 )
 from controllers.console.datasets.wraps import get_rag_pipeline
 from controllers.console.wraps import account_initialization_required, setup_required
 from controllers.web.error import InvalidArgumentError, NotFoundError
-from core.variables.segment_group import SegmentGroup
-from core.variables.segments import ArrayFileSegment, FileSegment, Segment
 from core.variables.types import SegmentType
 from core.workflow.constants import CONVERSATION_VARIABLE_NODE_ID, SYSTEM_VARIABLE_NODE_ID
 from extensions.ext_database import db
@@ -34,32 +32,6 @@ from services.workflow_draft_variable_service import WorkflowDraftVariableList,
 logger = logging.getLogger(__name__)
 
 
-def _convert_values_to_json_serializable_object(value: Segment) -> Any:
-    if isinstance(value, FileSegment):
-        return value.value.model_dump()
-    elif isinstance(value, ArrayFileSegment):
-        return [i.model_dump() for i in value.value]
-    elif isinstance(value, SegmentGroup):
-        return [_convert_values_to_json_serializable_object(i) for i in value.value]
-    else:
-        return value.value
-
-
-def _serialize_var_value(variable: WorkflowDraftVariable) -> Any:
-    value = variable.get_value()
-    # create a copy of the value to avoid affecting the model cache.
-    value = value.model_copy(deep=True)
-    # Refresh the url signature before returning it to client.
-    if isinstance(value, FileSegment):
-        file = value.value
-        file.remote_url = file.generate_url()
-    elif isinstance(value, ArrayFileSegment):
-        files = value.value
-        for file in files:
-            file.remote_url = file.generate_url()
-    return _convert_values_to_json_serializable_object(value)
-
-
 def _create_pagination_parser():
     parser = reqparse.RequestParser()
     parser.add_argument(
@@ -104,7 +76,7 @@ def _api_prerequisite(f):
     @account_initialization_required
     @get_rag_pipeline
     def wrapper(*args, **kwargs):
-        if not isinstance(current_user, Account) or not current_user.is_editor:
+        if not isinstance(current_user, Account) or not current_user.has_edit_permission:
             raise Forbidden()
         return f(*args, **kwargs)
 

api/controllers/console/tag/tags.py

@@ -3,7 +3,7 @@ from flask_login import current_user
 from flask_restx import Resource, marshal_with, reqparse
 from werkzeug.exceptions import Forbidden
 
-from controllers.console import api
+from controllers.console import console_ns
 from controllers.console.wraps import account_initialization_required, setup_required
 from fields.tag_fields import dataset_tag_fields
 from libs.login import login_required
@@ -17,6 +17,7 @@ def _validate_name(name):
     return name
 
 
+@console_ns.route("/tags")
 class TagListApi(Resource):
     @setup_required
     @login_required
@@ -52,6 +53,7 @@ class TagListApi(Resource):
         return response, 200
 
 
+@console_ns.route("/tags/<uuid:tag_id>")
 class TagUpdateDeleteApi(Resource):
     @setup_required
     @login_required
@@ -89,6 +91,7 @@ class TagUpdateDeleteApi(Resource):
         return 204
 
 
+@console_ns.route("/tag-bindings/create")
 class TagBindingCreateApi(Resource):
     @setup_required
     @login_required
@@ -114,6 +117,7 @@ class TagBindingCreateApi(Resource):
         return {"result": "success"}, 200
 
 
+@console_ns.route("/tag-bindings/remove")
 class TagBindingDeleteApi(Resource):
     @setup_required
     @login_required
@@ -133,9 +137,3 @@ class TagBindingDeleteApi(Resource):
         TagService.delete_tag_binding(args)
 
         return {"result": "success"}, 200
-
-
-api.add_resource(TagListApi, "/tags")
-api.add_resource(TagUpdateDeleteApi, "/tags/<uuid:tag_id>")
-api.add_resource(TagBindingCreateApi, "/tag-bindings/create")
-api.add_resource(TagBindingDeleteApi, "/tag-bindings/remove")

api/controllers/service_api/dataset/dataset.py

@@ -17,6 +17,7 @@ from core.provider_manager import ProviderManager
 from fields.dataset_fields import dataset_detail_fields
 from fields.tag_fields import build_dataset_tag_fields
 from libs.login import current_user
+from libs.validators import validate_description_length
 from models.account import Account
 from models.dataset import Dataset, DatasetPermissionEnum
 from models.provider_ids import ModelProviderID
@@ -31,12 +32,6 @@ def _validate_name(name):
     return name
 
 
-def _validate_description_length(description):
-    if description and len(description) > 400:
-        raise ValueError("Description cannot exceed 400 characters.")
-    return description
-
-
 # Define parsers for dataset operations
 dataset_create_parser = reqparse.RequestParser()
 dataset_create_parser.add_argument(
@@ -48,7 +43,7 @@ dataset_create_parser.add_argument(
 )
 dataset_create_parser.add_argument(
     "description",
-    type=_validate_description_length,
+    type=validate_description_length,
     nullable=True,
     required=False,
     default="",
@@ -101,7 +96,7 @@ dataset_update_parser.add_argument(
     type=_validate_name,
 )
 dataset_update_parser.add_argument(
-    "description", location="json", store_missing=False, type=_validate_description_length
+    "description", location="json", store_missing=False, type=validate_description_length
 )
 dataset_update_parser.add_argument(
     "indexing_technique",

api/core/app/app_config/easy_ui_based_app/dataset/manager.py

@@ -1,4 +1,5 @@
 import uuid
+from typing import Literal, cast
 
 from core.app.app_config.entities import (
     DatasetEntity,
@@ -74,6 +75,9 @@ class DatasetConfigManager:
             return None
         query_variable = config.get("dataset_query_variable")
 
+        metadata_model_config_dict = dataset_configs.get("metadata_model_config")
+        metadata_filtering_conditions_dict = dataset_configs.get("metadata_filtering_conditions")
+
         if dataset_configs["retrieval_model"] == "single":
             return DatasetEntity(
                 dataset_ids=dataset_ids,
@@ -82,18 +86,23 @@ class DatasetConfigManager:
                     retrieve_strategy=DatasetRetrieveConfigEntity.RetrieveStrategy.value_of(
                         dataset_configs["retrieval_model"]
                     ),
-                    metadata_filtering_mode=dataset_configs.get("metadata_filtering_mode", "disabled"),
-                    metadata_model_config=ModelConfig(**dataset_configs.get("metadata_model_config"))
-                    if dataset_configs.get("metadata_model_config")
+                    metadata_filtering_mode=cast(
+                        Literal["disabled", "automatic", "manual"],
+                        dataset_configs.get("metadata_filtering_mode", "disabled"),
+                    ),
+                    metadata_model_config=ModelConfig(**metadata_model_config_dict)
+                    if isinstance(metadata_model_config_dict, dict)
                     else None,
-                    metadata_filtering_conditions=MetadataFilteringCondition(
-                        **dataset_configs.get("metadata_filtering_conditions", {})
-                    )
-                    if dataset_configs.get("metadata_filtering_conditions")
+                    metadata_filtering_conditions=MetadataFilteringCondition(**metadata_filtering_conditions_dict)
+                    if isinstance(metadata_filtering_conditions_dict, dict)
                     else None,
                 ),
             )
         else:
+            score_threshold_val = dataset_configs.get("score_threshold")
+            reranking_model_val = dataset_configs.get("reranking_model")
+            weights_val = dataset_configs.get("weights")
+
             return DatasetEntity(
                 dataset_ids=dataset_ids,
                 retrieve_config=DatasetRetrieveConfigEntity(
@@ -101,22 +110,23 @@ class DatasetConfigManager:
                     retrieve_strategy=DatasetRetrieveConfigEntity.RetrieveStrategy.value_of(
                         dataset_configs["retrieval_model"]
                     ),
-                    top_k=dataset_configs.get("top_k", 4),
-                    score_threshold=dataset_configs.get("score_threshold")
-                    if dataset_configs.get("score_threshold_enabled", False)
+                    top_k=int(dataset_configs.get("top_k", 4)),
+                    score_threshold=float(score_threshold_val)
+                    if dataset_configs.get("score_threshold_enabled", False) and score_threshold_val is not None
                     else None,
-                    reranking_model=dataset_configs.get("reranking_model"),
-                    weights=dataset_configs.get("weights"),
-                    reranking_enabled=dataset_configs.get("reranking_enabled", True),
+                    reranking_model=reranking_model_val if isinstance(reranking_model_val, dict) else None,
+                    weights=weights_val if isinstance(weights_val, dict) else None,
+                    reranking_enabled=bool(dataset_configs.get("reranking_enabled", True)),
                     rerank_mode=dataset_configs.get("reranking_mode", "reranking_model"),
-                    metadata_filtering_mode=dataset_configs.get("metadata_filtering_mode", "disabled"),
-                    metadata_model_config=ModelConfig(**dataset_configs.get("metadata_model_config"))
-                    if dataset_configs.get("metadata_model_config")
+                    metadata_filtering_mode=cast(
+                        Literal["disabled", "automatic", "manual"],
+                        dataset_configs.get("metadata_filtering_mode", "disabled"),
+                    ),
+                    metadata_model_config=ModelConfig(**metadata_model_config_dict)
+                    if isinstance(metadata_model_config_dict, dict)
                     else None,
-                    metadata_filtering_conditions=MetadataFilteringCondition(
-                        **dataset_configs.get("metadata_filtering_conditions", {})
-                    )
-                    if dataset_configs.get("metadata_filtering_conditions")
+                    metadata_filtering_conditions=MetadataFilteringCondition(**metadata_filtering_conditions_dict)
+                    if isinstance(metadata_filtering_conditions_dict, dict)
                     else None,
                 ),
             )
@@ -134,18 +144,17 @@ class DatasetConfigManager:
         config = cls.extract_dataset_config_for_legacy_compatibility(tenant_id, app_mode, config)
 
         # dataset_configs
-        if not config.get("dataset_configs"):
-            config["dataset_configs"] = {"retrieval_model": "single"}
+        if "dataset_configs" not in config or not config.get("dataset_configs"):
+            config["dataset_configs"] = {}
+        config["dataset_configs"]["retrieval_model"] = config["dataset_configs"].get("retrieval_model", "single")
 
         if not isinstance(config["dataset_configs"], dict):
             raise ValueError("dataset_configs must be of object type")
 
-        if not config["dataset_configs"].get("datasets"):
+        if "datasets" not in config["dataset_configs"] or not config["dataset_configs"].get("datasets"):
             config["dataset_configs"]["datasets"] = {"strategy": "router", "datasets": []}
 
-        need_manual_query_datasets = config.get("dataset_configs") and config["dataset_configs"].get(
-            "datasets", {}
-        ).get("datasets")
+        need_manual_query_datasets = config.get("dataset_configs", {}).get("datasets", {}).get("datasets")
 
         if need_manual_query_datasets and app_mode == AppMode.COMPLETION:
             # Only check when mode is completion
@@ -166,8 +175,8 @@ class DatasetConfigManager:
         :param config: app model config args
         """
         # Extract dataset config for legacy compatibility
-        if not config.get("agent_mode"):
-            config["agent_mode"] = {"enabled": False, "tools": []}
+        if "agent_mode" not in config or not config.get("agent_mode"):
+            config["agent_mode"] = {}
 
         if not isinstance(config["agent_mode"], dict):
             raise ValueError("agent_mode must be of object type")
@@ -180,19 +189,22 @@ class DatasetConfigManager:
             raise ValueError("enabled in agent_mode must be of boolean type")
 
         # tools
-        if not config["agent_mode"].get("tools"):
+        if "tools" not in config["agent_mode"] or not config["agent_mode"].get("tools"):
             config["agent_mode"]["tools"] = []
 
         if not isinstance(config["agent_mode"]["tools"], list):
             raise ValueError("tools in agent_mode must be a list of objects")
 
         # strategy
-        if not config["agent_mode"].get("strategy"):
+        if "strategy" not in config["agent_mode"] or not config["agent_mode"].get("strategy"):
             config["agent_mode"]["strategy"] = PlanningStrategy.ROUTER.value
 
         has_datasets = False
-        if config["agent_mode"]["strategy"] in {PlanningStrategy.ROUTER.value, PlanningStrategy.REACT_ROUTER.value}:
-            for tool in config["agent_mode"]["tools"]:
+        if config.get("agent_mode", {}).get("strategy") in {
+            PlanningStrategy.ROUTER.value,
+            PlanningStrategy.REACT_ROUTER.value,
+        }:
+            for tool in config.get("agent_mode", {}).get("tools", []):
                 key = list(tool.keys())[0]
                 if key == "dataset":
                     # old style, use tool name as key
@@ -217,7 +229,7 @@ class DatasetConfigManager:
 
                     has_datasets = True
 
-        need_manual_query_datasets = has_datasets and config["agent_mode"]["enabled"]
+        need_manual_query_datasets = has_datasets and config.get("agent_mode", {}).get("enabled")
 
         if need_manual_query_datasets and app_mode == AppMode.COMPLETION:
             # Only check when mode is completion

api/core/app/apps/base_app_queue_manager.py

@@ -1,9 +1,11 @@
+import logging
 import queue
 import time
 from abc import abstractmethod
 from enum import IntEnum, auto
 from typing import Any
 
+from redis.exceptions import RedisError
 from sqlalchemy.orm import DeclarativeMeta
 
 from configs import dify_config
@@ -18,6 +20,8 @@ from core.app.entities.queue_entities import (
 )
 from extensions.ext_redis import redis_client
 
+logger = logging.getLogger(__name__)
+
 
 class PublishFrom(IntEnum):
     APPLICATION_MANAGER = auto()
@@ -35,9 +39,8 @@ class AppQueueManager:
         self.invoke_from = invoke_from  # Public accessor for invoke_from
 
         user_prefix = "account" if self._invoke_from in {InvokeFrom.EXPLORE, InvokeFrom.DEBUGGER} else "end-user"
-        redis_client.setex(
-            AppQueueManager._generate_task_belong_cache_key(self._task_id), 1800, f"{user_prefix}-{self._user_id}"
-        )
+        self._task_belong_cache_key = AppQueueManager._generate_task_belong_cache_key(self._task_id)
+        redis_client.setex(self._task_belong_cache_key, 1800, f"{user_prefix}-{self._user_id}")
 
         q: queue.Queue[WorkflowQueueMessage | MessageQueueMessage | None] = queue.Queue()
 
@@ -79,9 +82,21 @@ class AppQueueManager:
         Stop listen to queue
         :return:
         """
+        self._clear_task_belong_cache()
         self._q.put(None)
 
-    def publish_error(self, e, pub_from: PublishFrom):
+    def _clear_task_belong_cache(self) -> None:
+        """
+        Remove the task belong cache key once listening is finished.
+        """
+        try:
+            redis_client.delete(self._task_belong_cache_key)
+        except RedisError:
+            logger.exception(
+                "Failed to clear task belong cache for task %s (key: %s)", self._task_id, self._task_belong_cache_key
+            )
+
+    def publish_error(self, e, pub_from: PublishFrom) -> None:
         """
         Publish error
         :param e: error

api/core/app/task_pipeline/message_cycle_manager.py

@@ -107,7 +107,6 @@ class MessageCycleManager:
                     if dify_config.DEBUG:
                         logger.exception("generate conversation name failed, conversation_id: %s", conversation_id)
 
-                db.session.merge(conversation)
                 db.session.commit()
                 db.session.close()
 

api/core/datasource/__base/datasource_runtime.py

@@ -1,7 +1,6 @@
 from typing import TYPE_CHECKING, Any, Optional
 
-from openai import BaseModel
-from pydantic import Field
+from pydantic import BaseModel, Field
 
 # Import InvokeFrom locally to avoid circular import
 from core.app.entities.app_invoke_entities import InvokeFrom

api/core/model_runtime/entities/message_entities.py

@@ -74,7 +74,7 @@ class TextPromptMessageContent(PromptMessageContent):
     Model class for text prompt message content.
     """
 
-    type: Literal[PromptMessageContentType.TEXT] = PromptMessageContentType.TEXT
+    type: Literal[PromptMessageContentType.TEXT] = PromptMessageContentType.TEXT  # type: ignore
     data: str
 
 
@@ -95,11 +95,11 @@ class MultiModalPromptMessageContent(PromptMessageContent):
 
 
 class VideoPromptMessageContent(MultiModalPromptMessageContent):
-    type: Literal[PromptMessageContentType.VIDEO] = PromptMessageContentType.VIDEO
+    type: Literal[PromptMessageContentType.VIDEO] = PromptMessageContentType.VIDEO  # type: ignore
 
 
 class AudioPromptMessageContent(MultiModalPromptMessageContent):
-    type: Literal[PromptMessageContentType.AUDIO] = PromptMessageContentType.AUDIO
+    type: Literal[PromptMessageContentType.AUDIO] = PromptMessageContentType.AUDIO  # type: ignore
 
 
 class ImagePromptMessageContent(MultiModalPromptMessageContent):
@@ -111,12 +111,12 @@ class ImagePromptMessageContent(MultiModalPromptMessageContent):
         LOW = auto()
         HIGH = auto()
 
-    type: Literal[PromptMessageContentType.IMAGE] = PromptMessageContentType.IMAGE
+    type: Literal[PromptMessageContentType.IMAGE] = PromptMessageContentType.IMAGE  # type: ignore
     detail: DETAIL = DETAIL.LOW
 
 
 class DocumentPromptMessageContent(MultiModalPromptMessageContent):
-    type: Literal[PromptMessageContentType.DOCUMENT] = PromptMessageContentType.DOCUMENT
+    type: Literal[PromptMessageContentType.DOCUMENT] = PromptMessageContentType.DOCUMENT  # type: ignore
 
 
 PromptMessageContentUnionTypes = Annotated[

api/core/model_runtime/model_providers/__base/tokenizers/gpt2_tokenizer.py

@@ -15,7 +15,7 @@ class GPT2Tokenizer:
         use gpt2 tokenizer to get num tokens
         """
         _tokenizer = GPT2Tokenizer.get_encoder()
-        tokens = _tokenizer.encode(text)
+        tokens = _tokenizer.encode(text)  # type: ignore
         return len(tokens)
 
     @staticmethod

api/core/model_runtime/utils/encoders.py

@@ -196,15 +196,15 @@ def jsonable_encoder(
             return encoder(obj)
 
     try:
-        data = dict(obj)
+        data = dict(obj)  # type: ignore
     except Exception as e:
         errors: list[Exception] = []
         errors.append(e)
         try:
-            data = vars(obj)
+            data = vars(obj)  # type: ignore
         except Exception as e:
             errors.append(e)
-            raise ValueError(errors) from e
+            raise ValueError(str(errors)) from e
     return jsonable_encoder(
         data,
         by_alias=by_alias,

api/core/ops/aliyun_trace/entities/aliyun_trace_entity.py

@@ -3,7 +3,8 @@ from dataclasses import dataclass
 from typing import Any
 
 from opentelemetry import trace as trace_api
-from opentelemetry.sdk.trace import Event, Status, StatusCode
+from opentelemetry.sdk.trace import Event
+from opentelemetry.trace import Status, StatusCode
 from pydantic import BaseModel, Field
 
 

api/core/ops/ops_trace_manager.py

@@ -155,7 +155,10 @@ class OpsTraceManager:
             if key in tracing_config:
                 if "*" in tracing_config[key]:
                     # If the key contains '*', retain the original value from the current config
-                    new_config[key] = current_trace_config.get(key, tracing_config[key])
+                    if current_trace_config:
+                        new_config[key] = current_trace_config.get(key, tracing_config[key])
+                    else:
+                        new_config[key] = tracing_config[key]
                 else:
                     # Otherwise, encrypt the key
                     new_config[key] = encrypt_token(tenant_id, tracing_config[key])

api/core/ops/weave_trace/weave_trace.py

@@ -62,7 +62,8 @@ class WeaveDataTrace(BaseTraceInstance):
         self,
     ):
         try:
-            project_url = f"https://wandb.ai/{self.weave_client._project_id()}"
+            project_identifier = f"{self.entity}/{self.project_name}" if self.entity else self.project_name
+            project_url = f"https://wandb.ai/{project_identifier}"
             return project_url
         except Exception as e:
             logger.debug("Weave get run url failed: %s", str(e))
@@ -424,7 +425,23 @@ class WeaveDataTrace(BaseTraceInstance):
             raise ValueError(f"Weave API check failed: {str(e)}")
 
     def start_call(self, run_data: WeaveTraceModel, parent_run_id: str | None = None):
-        call = self.weave_client.create_call(op=run_data.op, inputs=run_data.inputs, attributes=run_data.attributes)
+        inputs = run_data.inputs
+        if inputs is None:
+            inputs = {}
+        elif not isinstance(inputs, dict):
+            inputs = {"inputs": str(inputs)}
+
+        attributes = run_data.attributes
+        if attributes is None:
+            attributes = {}
+        elif not isinstance(attributes, dict):
+            attributes = {"attributes": str(attributes)}
+
+        call = self.weave_client.create_call(
+            op=run_data.op,
+            inputs=inputs,
+            attributes=attributes,
+        )
         self.calls[run_data.id] = call
         if parent_run_id:
             self.calls[run_data.id].parent_id = parent_run_id
@@ -432,6 +449,7 @@ class WeaveDataTrace(BaseTraceInstance):
     def finish_call(self, run_data: WeaveTraceModel):
         call = self.calls.get(run_data.id)
         if call:
-            self.weave_client.finish_call(call=call, output=run_data.outputs, exception=run_data.exception)
+            exception = Exception(run_data.exception) if run_data.exception else None
+            self.weave_client.finish_call(call=call, output=run_data.outputs, exception=exception)
         else:
             raise ValueError(f"Call with id {run_data.id} not found")

api/core/rag/datasource/retrieval_service.py

@@ -106,7 +106,9 @@ class RetrievalService:
         if exceptions:
             raise ValueError(";\n".join(exceptions))
 
+        # Deduplicate documents for hybrid search to avoid duplicate chunks
         if retrieval_method == RetrievalMethod.HYBRID_SEARCH.value:
+            all_documents = cls._deduplicate_documents(all_documents)
             data_post_processor = DataPostProcessor(
                 str(dataset.tenant_id), reranking_mode, reranking_model, weights, False
             )
@@ -143,6 +145,40 @@ class RetrievalService:
         )
         return all_documents
 
+    @classmethod
+    def _deduplicate_documents(cls, documents: list[Document]) -> list[Document]:
+        """Deduplicate documents based on doc_id to avoid duplicate chunks in hybrid search."""
+        if not documents:
+            return documents
+
+        unique_documents = []
+        seen_doc_ids = set()
+
+        for document in documents:
+            # For dify provider documents, use doc_id for deduplication
+            if document.provider == "dify" and document.metadata is not None and "doc_id" in document.metadata:
+                doc_id = document.metadata["doc_id"]
+                if doc_id not in seen_doc_ids:
+                    seen_doc_ids.add(doc_id)
+                    unique_documents.append(document)
+                # If duplicate, keep the one with higher score
+                elif "score" in document.metadata:
+                    # Find existing document with same doc_id and compare scores
+                    for i, existing_doc in enumerate(unique_documents):
+                        if (
+                            existing_doc.metadata
+                            and existing_doc.metadata.get("doc_id") == doc_id
+                            and existing_doc.metadata.get("score", 0) < document.metadata.get("score", 0)
+                        ):
+                            unique_documents[i] = document
+                            break
+            else:
+                # For non-dify documents, use content-based deduplication
+                if document not in unique_documents:
+                    unique_documents.append(document)
+
+        return unique_documents
+
     @classmethod
     def _get_dataset(cls, dataset_id: str) -> Dataset | None:
         with Session(db.engine) as session:

api/core/tools/__base/tool_runtime.py

@@ -1,7 +1,6 @@
 from typing import Any
 
-from openai import BaseModel
-from pydantic import Field
+from pydantic import BaseModel, Field
 
 from core.app.entities.app_invoke_entities import InvokeFrom
 from core.tools.entities.tool_entities import CredentialType, ToolInvokeFrom

api/core/workflow/node_events/node.py

@@ -20,6 +20,7 @@ class ModelInvokeCompletedEvent(NodeEventBase):
     usage: LLMUsage
     finish_reason: str | None = None
     reasoning_content: str | None = None
+    structured_output: dict | None = None
 
 
 class RunRetryEvent(NodeEventBase):

api/core/workflow/nodes/http_request/executor.py

@@ -87,7 +87,7 @@ class Executor:
                 node_data.authorization.config.api_key
             ).text
 
-        self.url: str = node_data.url
+        self.url = node_data.url
         self.method = node_data.method
         self.auth = node_data.authorization
         self.timeout = timeout
@@ -349,11 +349,10 @@ class Executor:
             "timeout": (self.timeout.connect, self.timeout.read, self.timeout.write),
             "ssl_verify": self.ssl_verify,
             "follow_redirects": True,
-            "max_retries": self.max_retries,
         }
         # request_args = {k: v for k, v in request_args.items() if v is not None}
         try:
-            response: httpx.Response = _METHOD_MAP[method_lc](**request_args)
+            response: httpx.Response = _METHOD_MAP[method_lc](**request_args, max_retries=self.max_retries)
         except (ssrf_proxy.MaxRetriesExceededError, httpx.RequestError) as e:
             raise HttpRequestNodeError(str(e)) from e
         # FIXME: fix type ignore, this maybe httpx type issue

api/core/workflow/nodes/http_request/node.py

@@ -165,6 +165,8 @@ class HttpRequestNode(Node):
             body_type = typed_node_data.body.type
             data = typed_node_data.body.data
             match body_type:
+                case "none":
+                    pass
                 case "binary":
                     if len(data) != 1:
                         raise RequestBodyError("invalid body data, should have only one item")

api/core/workflow/nodes/if_else/if_else_node.py

@@ -83,7 +83,7 @@ class IfElseNode(Node):
             else:
                 # TODO: Update database then remove this
                 # Fallback to old structure if cases are not defined
-                input_conditions, group_result, final_result = _should_not_use_old_function(  # ty: ignore [deprecated]
+                input_conditions, group_result, final_result = _should_not_use_old_function(  # pyright: ignore [reportDeprecated]
                     condition_processor=condition_processor,
                     variable_pool=self.graph_runtime_state.variable_pool,
                     conditions=self._node_data.conditions or [],

api/core/workflow/nodes/knowledge_index/knowledge_index_node.py

@@ -136,6 +136,11 @@ class KnowledgeIndexNode(Node):
         document = db.session.query(Document).filter_by(id=document_id.value).first()
         if not document:
             raise KnowledgeIndexNodeError(f"Document {document_id.value} not found.")
+        doc_id_value = document.id
+        ds_id_value = dataset.id
+        dataset_name_value = dataset.name
+        document_name_value = document.name
+        created_at_value = document.created_at
         # chunk nodes by chunk size
         indexing_start_at = time.perf_counter()
         index_processor = IndexProcessorFactory(dataset.chunk_structure).init_index_processor()
@@ -161,16 +166,16 @@ class KnowledgeIndexNode(Node):
         document.word_count = (
             db.session.query(func.sum(DocumentSegment.word_count))
             .where(
-                DocumentSegment.document_id == document.id,
-                DocumentSegment.dataset_id == dataset.id,
+                DocumentSegment.document_id == doc_id_value,
+                DocumentSegment.dataset_id == ds_id_value,
             )
             .scalar()
         )
         db.session.add(document)
         # update document segment status
         db.session.query(DocumentSegment).where(
-            DocumentSegment.document_id == document.id,
-            DocumentSegment.dataset_id == dataset.id,
+            DocumentSegment.document_id == doc_id_value,
+            DocumentSegment.dataset_id == ds_id_value,
         ).update(
             {
                 DocumentSegment.status: "completed",
@@ -182,13 +187,13 @@ class KnowledgeIndexNode(Node):
         db.session.commit()
 
         return {
-            "dataset_id": dataset.id,
-            "dataset_name": dataset.name,
+            "dataset_id": ds_id_value,
+            "dataset_name": dataset_name_value,
             "batch": batch.value,
-            "document_id": document.id,
-            "document_name": document.name,
-            "created_at": document.created_at.timestamp(),
-            "display_status": document.indexing_status,
+            "document_id": doc_id_value,
+            "document_name": document_name_value,
+            "created_at": created_at_value.timestamp(),
+            "display_status": "completed",
         }
 
     def _get_preview_output(self, chunk_structure: str, chunks: Any) -> Mapping[str, Any]:

api/core/workflow/nodes/knowledge_retrieval/knowledge_retrieval_node.py

@@ -107,7 +107,7 @@ class KnowledgeRetrievalNode(Node):
             graph_runtime_state=graph_runtime_state,
         )
         # LLM file outputs, used for MultiModal outputs.
-        self._file_outputs: list[File] = []
+        self._file_outputs = []
 
         if llm_file_saver is None:
             llm_file_saver = FileSaverImpl(

api/core/workflow/nodes/list_operator/node.py

@@ -161,6 +161,8 @@ class ListOperatorNode(Node):
             elif isinstance(variable, ArrayFileSegment):
                 if isinstance(condition.value, str):
                     value = self.graph_runtime_state.variable_pool.convert_template(condition.value).text
+                elif isinstance(condition.value, bool):
+                    raise ValueError(f"File filter expects a string value, got {type(condition.value)}")
                 else:
                     value = condition.value
                 filter_func = _get_file_filter_func(

api/core/workflow/nodes/llm/file_saver.py

@@ -46,7 +46,7 @@ class LLMFileSaver(tp.Protocol):
             dot (`.`). For example, `.py` and `.tar.gz` are both valid values, while `py`
             and `tar.gz` are not.
         """
-        pass
+        raise NotImplementedError()
 
     def save_remote_url(self, url: str, file_type: FileType) -> File:
         """save_remote_url saves the file from a remote url returned by LLM.
@@ -56,7 +56,7 @@ class LLMFileSaver(tp.Protocol):
         :param url: the url of the file.
         :param file_type: the file type of the file, check `FileType` enum for reference.
         """
-        pass
+        raise NotImplementedError()
 
 
 EngineFactory: tp.TypeAlias = tp.Callable[[], Engine]

api/core/workflow/nodes/llm/node.py

@@ -23,6 +23,7 @@ from core.model_runtime.entities.llm_entities import (
     LLMResult,
     LLMResultChunk,
     LLMResultChunkWithStructuredOutput,
+    LLMResultWithStructuredOutput,
     LLMStructuredOutput,
     LLMUsage,
 )
@@ -127,7 +128,7 @@ class LLMNode(Node):
             graph_runtime_state=graph_runtime_state,
         )
         # LLM file outputs, used for MultiModal outputs.
-        self._file_outputs: list[File] = []
+        self._file_outputs = []
 
         if llm_file_saver is None:
             llm_file_saver = FileSaverImpl(
@@ -165,6 +166,7 @@ class LLMNode(Node):
         node_inputs: dict[str, Any] = {}
         process_data: dict[str, Any] = {}
         result_text = ""
+        clean_text = ""
         usage = LLMUsage.empty_usage()
         finish_reason = None
         reasoning_content = None
@@ -278,6 +280,13 @@ class LLMNode(Node):
                         # Extract clean text from <think> tags
                         clean_text, _ = LLMNode._split_reasoning(result_text, self._node_data.reasoning_format)
 
+                    # Process structured output if available from the event.
+                    structured_output = (
+                        LLMStructuredOutput(structured_output=event.structured_output)
+                        if event.structured_output
+                        else None
+                    )
+
                     # deduct quota
                     llm_utils.deduct_llm_quota(tenant_id=self.tenant_id, model_instance=model_instance, usage=usage)
                     break
@@ -1048,7 +1057,7 @@ class LLMNode(Node):
     @staticmethod
     def handle_blocking_result(
         *,
-        invoke_result: LLMResult,
+        invoke_result: LLMResult | LLMResultWithStructuredOutput,
         saver: LLMFileSaver,
         file_outputs: list["File"],
         reasoning_format: Literal["separated", "tagged"] = "tagged",
@@ -1079,6 +1088,8 @@ class LLMNode(Node):
             finish_reason=None,
             # Reasoning content for workflow variables and downstream nodes
             reasoning_content=reasoning_content,
+            # Pass structured output if enabled
+            structured_output=getattr(invoke_result, "structured_output", None),
         )
 
     @staticmethod

api/core/workflow/nodes/parameter_extractor/prompts.py

@@ -179,6 +179,6 @@ CHAT_EXAMPLE = [
                 "required": ["food"],
             },
         },
-        "assistant": {"text": "I need to output a valid JSON object.", "json": {"result": "apple pie"}},
+        "assistant": {"text": "I need to output a valid JSON object.", "json": {"food": "apple pie"}},
     },
 ]

api/core/workflow/nodes/question_classifier/question_classifier_node.py

@@ -68,7 +68,7 @@ class QuestionClassifierNode(Node):
             graph_runtime_state=graph_runtime_state,
         )
         # LLM file outputs, used for MultiModal outputs.
-        self._file_outputs: list[File] = []
+        self._file_outputs = []
 
         if llm_file_saver is None:
             llm_file_saver = FileSaverImpl(
@@ -111,9 +111,9 @@ class QuestionClassifierNode(Node):
         query = variable.value if variable else None
         variables = {"query": query}
         # fetch model config
-        model_instance, model_config = LLMNode._fetch_model_config(
-            node_data_model=node_data.model,
+        model_instance, model_config = llm_utils.fetch_model_config(
             tenant_id=self.tenant_id,
+            node_data_model=node_data.model,
         )
         # fetch memory
         memory = llm_utils.fetch_memory(

api/core/workflow/nodes/template_transform/template_transform_node.py

@@ -1,7 +1,7 @@
-import os
 from collections.abc import Mapping, Sequence
 from typing import Any
 
+from configs import dify_config
 from core.helper.code_executor.code_executor import CodeExecutionError, CodeExecutor, CodeLanguage
 from core.workflow.enums import ErrorStrategy, NodeType, WorkflowNodeExecutionStatus
 from core.workflow.node_events import NodeRunResult
@@ -9,7 +9,7 @@ from core.workflow.nodes.base.entities import BaseNodeData, RetryConfig
 from core.workflow.nodes.base.node import Node
 from core.workflow.nodes.template_transform.entities import TemplateTransformNodeData
 
-MAX_TEMPLATE_TRANSFORM_OUTPUT_LENGTH = int(os.environ.get("TEMPLATE_TRANSFORM_MAX_LENGTH", "80000"))
+MAX_TEMPLATE_TRANSFORM_OUTPUT_LENGTH = dify_config.TEMPLATE_TRANSFORM_MAX_LENGTH
 
 
 class TemplateTransformNode(Node):

api/core/workflow/workflow_entry.py

@@ -416,4 +416,8 @@ class WorkflowEntry:
 
             # append variable and value to variable pool
             if variable_node_id != ENVIRONMENT_VARIABLE_NODE_ID:
+                # In single run, the input_value is set as the LLM's structured output value within the variable_pool.
+                if len(variable_key_list) == 2 and variable_key_list[0] == "structured_output":
+                    input_value = {variable_key_list[1]: input_value}
+                    variable_key_list = variable_key_list[0:1]
                 variable_pool.add([variable_node_id] + variable_key_list, input_value)

api/extensions/ext_app_metrics.py

@@ -10,14 +10,14 @@ from dify_app import DifyApp
 
 def init_app(app: DifyApp):
     @app.after_request
-    def after_request(response):
+    def after_request(response):  # pyright: ignore[reportUnusedFunction]
         """Add Version headers to the response."""
         response.headers.add("X-Version", dify_config.project.version)
         response.headers.add("X-Env", dify_config.DEPLOY_ENV)
         return response
 
     @app.route("/health")
-    def health():
+    def health():  # pyright: ignore[reportUnusedFunction]
         return Response(
             json.dumps({"pid": os.getpid(), "status": "ok", "version": dify_config.project.version}),
             status=200,
@@ -25,7 +25,7 @@ def init_app(app: DifyApp):
         )
 
     @app.route("/threads")
-    def threads():
+    def threads():  # pyright: ignore[reportUnusedFunction]
         num_threads = threading.active_count()
         threads = threading.enumerate()
 
@@ -50,7 +50,7 @@ def init_app(app: DifyApp):
         }
 
     @app.route("/db-pool-stat")
-    def pool_stat():
+    def pool_stat():  # pyright: ignore[reportUnusedFunction]
         from extensions.ext_database import db
 
         engine = db.engine

api/extensions/ext_database.py

@@ -10,7 +10,7 @@ from models.engine import db
 logger = logging.getLogger(__name__)
 
 # Global flag to avoid duplicate registration of event listener
-_GEVENT_COMPATIBILITY_SETUP: bool = False
+_gevent_compatibility_setup: bool = False
 
 
 def _safe_rollback(connection):
@@ -26,14 +26,14 @@ def _safe_rollback(connection):
 
 
 def _setup_gevent_compatibility():
-    global _GEVENT_COMPATIBILITY_SETUP  # pylint: disable=global-statement
+    global _gevent_compatibility_setup  # pylint: disable=global-statement
 
     # Avoid duplicate registration
-    if _GEVENT_COMPATIBILITY_SETUP:
+    if _gevent_compatibility_setup:
         return
 
     @event.listens_for(Pool, "reset")
-    def _safe_reset(dbapi_connection, connection_record, reset_state):  # pylint: disable=unused-argument
+    def _safe_reset(dbapi_connection, connection_record, reset_state):  # pyright: ignore[reportUnusedFunction]
         if reset_state.terminate_only:
             return
 
@@ -47,7 +47,7 @@ def _setup_gevent_compatibility():
         except (AttributeError, ImportError):
             _safe_rollback(dbapi_connection)
 
-    _GEVENT_COMPATIBILITY_SETUP = True
+    _gevent_compatibility_setup = True
 
 
 def init_app(app: DifyApp):

api/extensions/ext_import_modules.py

@@ -2,4 +2,4 @@ from dify_app import DifyApp
 
 
 def init_app(app: DifyApp):
-    from events import event_handlers  # noqa: F401
+    from events import event_handlers  # noqa: F401 # pyright: ignore[reportUnusedImport]

api/extensions/ext_otel.py

@@ -136,6 +136,7 @@ def init_app(app: DifyApp):
     from opentelemetry.exporter.otlp.proto.http.trace_exporter import OTLPSpanExporter as HTTPSpanExporter
     from opentelemetry.instrumentation.celery import CeleryInstrumentor
     from opentelemetry.instrumentation.flask import FlaskInstrumentor
+    from opentelemetry.instrumentation.httpx import HTTPXClientInstrumentor
     from opentelemetry.instrumentation.redis import RedisInstrumentor
     from opentelemetry.instrumentation.requests import RequestsInstrumentor
     from opentelemetry.instrumentation.sqlalchemy import SQLAlchemyInstrumentor
@@ -238,6 +239,7 @@ def init_app(app: DifyApp):
     init_sqlalchemy_instrumentor(app)
     RedisInstrumentor().instrument()
     RequestsInstrumentor().instrument()
+    HTTPXClientInstrumentor().instrument()
     atexit.register(shutdown_tracer)
 
 

api/extensions/ext_sentry.py

@@ -4,7 +4,6 @@ from dify_app import DifyApp
 
 def init_app(app: DifyApp):
     if dify_config.SENTRY_DSN:
-        import openai
         import sentry_sdk
         from langfuse import parse_error  # type: ignore
         from sentry_sdk.integrations.celery import CeleryIntegration
@@ -28,7 +27,6 @@ def init_app(app: DifyApp):
                 HTTPException,
                 ValueError,
                 FileNotFoundError,
-                openai.APIStatusError,
                 InvokeRateLimitError,
                 parse_error.defaultErrorResponse,
             ],

api/extensions/storage/aliyun_oss_storage.py

@@ -33,7 +33,9 @@ class AliyunOssStorage(BaseStorage):
 
     def load_once(self, filename: str) -> bytes:
         obj = self.client.get_object(self.__wrapper_folder_filename(filename))
-        data: bytes = obj.read()
+        data = obj.read()
+        if not isinstance(data, bytes):
+            return b""
         return data
 
     def load_stream(self, filename: str) -> Generator:

api/extensions/storage/aws_s3_storage.py

@@ -39,10 +39,10 @@ class AwsS3Storage(BaseStorage):
             self.client.head_bucket(Bucket=self.bucket_name)
         except ClientError as e:
             # if bucket not exists, create it
-            if e.response["Error"]["Code"] == "404":
+            if e.response.get("Error", {}).get("Code") == "404":
                 self.client.create_bucket(Bucket=self.bucket_name)
             # if bucket is not accessible, pass, maybe the bucket is existing but not accessible
-            elif e.response["Error"]["Code"] == "403":
+            elif e.response.get("Error", {}).get("Code") == "403":
                 pass
             else:
                 # other error, raise exception
@@ -55,7 +55,7 @@ class AwsS3Storage(BaseStorage):
         try:
             data: bytes = self.client.get_object(Bucket=self.bucket_name, Key=filename)["Body"].read()
         except ClientError as ex:
-            if ex.response["Error"]["Code"] == "NoSuchKey":
+            if ex.response.get("Error", {}).get("Code") == "NoSuchKey":
                 raise FileNotFoundError("File not found")
             else:
                 raise
@@ -66,7 +66,7 @@ class AwsS3Storage(BaseStorage):
             response = self.client.get_object(Bucket=self.bucket_name, Key=filename)
             yield from response["Body"].iter_chunks()
         except ClientError as ex:
-            if ex.response["Error"]["Code"] == "NoSuchKey":
+            if ex.response.get("Error", {}).get("Code") == "NoSuchKey":
                 raise FileNotFoundError("file not found")
             elif "reached max retries" in str(ex):
                 raise ValueError("please do not request the same file too frequently")

api/extensions/storage/azure_blob_storage.py

@@ -27,24 +27,38 @@ class AzureBlobStorage(BaseStorage):
             self.credential = None
 
     def save(self, filename, data):
+        if not self.bucket_name:
+            return
+
         client = self._sync_client()
         blob_container = client.get_container_client(container=self.bucket_name)
         blob_container.upload_blob(filename, data)
 
     def load_once(self, filename: str) -> bytes:
+        if not self.bucket_name:
+            raise FileNotFoundError("Azure bucket name is not configured.")
+
         client = self._sync_client()
         blob = client.get_container_client(container=self.bucket_name)
         blob = blob.get_blob_client(blob=filename)
-        data: bytes = blob.download_blob().readall()
+        data = blob.download_blob().readall()
+        if not isinstance(data, bytes):
+            raise TypeError(f"Expected bytes from blob.readall(), got {type(data).__name__}")
         return data
 
     def load_stream(self, filename: str) -> Generator:
+        if not self.bucket_name:
+            raise FileNotFoundError("Azure bucket name is not configured.")
+
         client = self._sync_client()
         blob = client.get_blob_client(container=self.bucket_name, blob=filename)
         blob_data = blob.download_blob()
         yield from blob_data.chunks()
 
     def download(self, filename, target_filepath):
+        if not self.bucket_name:
+            return
+
         client = self._sync_client()
 
         blob = client.get_blob_client(container=self.bucket_name, blob=filename)
@@ -53,12 +67,18 @@ class AzureBlobStorage(BaseStorage):
             blob_data.readinto(my_blob)
 
     def exists(self, filename):
+        if not self.bucket_name:
+            return False
+
         client = self._sync_client()
 
         blob = client.get_blob_client(container=self.bucket_name, blob=filename)
         return blob.exists()
 
     def delete(self, filename):
+        if not self.bucket_name:
+            return
+
         client = self._sync_client()
 
         blob_container = client.get_container_client(container=self.bucket_name)

api/extensions/storage/clickzetta_volume/clickzetta_volume_storage.py

@@ -430,7 +430,7 @@ class ClickZettaVolumeStorage(BaseStorage):
 
             rows = self._execute_sql(sql, fetch=True)
 
-            exists = len(rows) > 0
+            exists = len(rows) > 0 if rows else False
             logger.debug("File %s exists check: %s", filename, exists)
             return exists
         except Exception as e:
@@ -509,16 +509,17 @@ class ClickZettaVolumeStorage(BaseStorage):
             rows = self._execute_sql(sql, fetch=True)
 
             result = []
-            for row in rows:
-                file_path = row[0]  # relative_path column
+            if rows:
+                for row in rows:
+                    file_path = row[0]  # relative_path column
 
-                # For User Volume, remove dify prefix from results
-                dify_prefix_with_slash = f"{self._config.dify_prefix}/"
-                if volume_prefix == "USER VOLUME" and file_path.startswith(dify_prefix_with_slash):
-                    file_path = file_path[len(dify_prefix_with_slash) :]  # Remove prefix
+                    # For User Volume, remove dify prefix from results
+                    dify_prefix_with_slash = f"{self._config.dify_prefix}/"
+                    if volume_prefix == "USER VOLUME" and file_path.startswith(dify_prefix_with_slash):
+                        file_path = file_path[len(dify_prefix_with_slash) :]  # Remove prefix
 
-                if files and not file_path.endswith("/") or directories and file_path.endswith("/"):
-                    result.append(file_path)
+                    if files and not file_path.endswith("/") or directories and file_path.endswith("/"):
+                        result.append(file_path)
 
             logger.debug("Scanned %d items in path %s", len(result), path)
             return result

api/extensions/storage/clickzetta_volume/volume_permissions.py

@@ -439,6 +439,11 @@ class VolumePermissionManager:
         self._permission_cache.clear()
         logger.debug("Permission cache cleared")
 
+    @property
+    def volume_type(self) -> str | None:
+        """Get the volume type."""
+        return self._volume_type
+
     def get_permission_summary(self, dataset_id: str | None = None) -> dict[str, bool]:
         """Get permission summary
 
@@ -632,13 +637,13 @@ def check_volume_permission(permission_manager: VolumePermissionManager, operati
         VolumePermissionError: If no permission
     """
     if not permission_manager.validate_operation(operation, dataset_id):
-        error_message = f"Permission denied for operation '{operation}' on {permission_manager._volume_type} volume"
+        error_message = f"Permission denied for operation '{operation}' on {permission_manager.volume_type} volume"
         if dataset_id:
             error_message += f" (dataset: {dataset_id})"
 
         raise VolumePermissionError(
             error_message,
             operation=operation,
-            volume_type=permission_manager._volume_type or "unknown",
+            volume_type=permission_manager.volume_type or "unknown",
             dataset_id=dataset_id,
         )

api/extensions/storage/google_cloud_storage.py

@@ -35,12 +35,16 @@ class GoogleCloudStorage(BaseStorage):
     def load_once(self, filename: str) -> bytes:
         bucket = self.client.get_bucket(self.bucket_name)
         blob = bucket.get_blob(filename)
+        if blob is None:
+            raise FileNotFoundError("File not found")
         data: bytes = blob.download_as_bytes()
         return data
 
     def load_stream(self, filename: str) -> Generator:
         bucket = self.client.get_bucket(self.bucket_name)
         blob = bucket.get_blob(filename)
+        if blob is None:
+            raise FileNotFoundError("File not found")
         with blob.open(mode="rb") as blob_stream:
             while chunk := blob_stream.read(4096):
                 yield chunk
@@ -48,6 +52,8 @@ class GoogleCloudStorage(BaseStorage):
     def download(self, filename, target_filepath):
         bucket = self.client.get_bucket(self.bucket_name)
         blob = bucket.get_blob(filename)
+        if blob is None:
+            raise FileNotFoundError("File not found")
         blob.download_to_filename(target_filepath)
 
     def exists(self, filename):

api/extensions/storage/huawei_obs_storage.py

@@ -45,7 +45,7 @@ class HuaweiObsStorage(BaseStorage):
 
     def _get_meta(self, filename):
         res = self.client.getObjectMetadata(bucketName=self.bucket_name, objectKey=filename)
-        if res.status < 300:
+        if res and res.status and res.status < 300:
             return res
         else:
             return None

api/extensions/storage/opendal_storage.py

@@ -3,9 +3,9 @@ import os
 from collections.abc import Generator
 from pathlib import Path
 
+import opendal
 from dotenv import dotenv_values
 from opendal import Operator
-from opendal.layers import RetryLayer
 
 from extensions.storage.base_storage import BaseStorage
 
@@ -35,7 +35,7 @@ class OpenDALStorage(BaseStorage):
             root = kwargs.get("root", "storage")
             Path(root).mkdir(parents=True, exist_ok=True)
 
-        retry_layer = RetryLayer(max_times=3, factor=2.0, jitter=True)
+        retry_layer = opendal.layers.RetryLayer(max_times=3, factor=2.0, jitter=True)
         self.op = Operator(scheme=scheme, **kwargs).layer(retry_layer)
         logger.debug("opendal operator created with scheme %s", scheme)
         logger.debug("added retry layer to opendal operator")

api/extensions/storage/oracle_oci_storage.py

@@ -29,7 +29,7 @@ class OracleOCIStorage(BaseStorage):
         try:
             data: bytes = self.client.get_object(Bucket=self.bucket_name, Key=filename)["Body"].read()
         except ClientError as ex:
-            if ex.response["Error"]["Code"] == "NoSuchKey":
+            if ex.response.get("Error", {}).get("Code") == "NoSuchKey":
                 raise FileNotFoundError("File not found")
             else:
                 raise
@@ -40,7 +40,7 @@ class OracleOCIStorage(BaseStorage):
             response = self.client.get_object(Bucket=self.bucket_name, Key=filename)
             yield from response["Body"].iter_chunks()
         except ClientError as ex:
-            if ex.response["Error"]["Code"] == "NoSuchKey":
+            if ex.response.get("Error", {}).get("Code") == "NoSuchKey":
                 raise FileNotFoundError("File not found")
             else:
                 raise

api/extensions/storage/supabase_storage.py

@@ -46,13 +46,13 @@ class SupabaseStorage(BaseStorage):
         Path(target_filepath).write_bytes(result)
 
     def exists(self, filename):
-        result = self.client.storage.from_(self.bucket_name).list(filename)
-        if result.count() > 0:
+        result = self.client.storage.from_(self.bucket_name).list(path=filename)
+        if len(result) > 0:
             return True
         return False
 
     def delete(self, filename):
-        self.client.storage.from_(self.bucket_name).remove(filename)
+        self.client.storage.from_(self.bucket_name).remove([filename])
 
     def bucket_exists(self):
         buckets = self.client.storage.list_buckets()

api/extensions/storage/volcengine_tos_storage.py

@@ -11,6 +11,14 @@ class VolcengineTosStorage(BaseStorage):
 
     def __init__(self):
         super().__init__()
+        if not dify_config.VOLCENGINE_TOS_ACCESS_KEY:
+            raise ValueError("VOLCENGINE_TOS_ACCESS_KEY is not set")
+        if not dify_config.VOLCENGINE_TOS_SECRET_KEY:
+            raise ValueError("VOLCENGINE_TOS_SECRET_KEY is not set")
+        if not dify_config.VOLCENGINE_TOS_ENDPOINT:
+            raise ValueError("VOLCENGINE_TOS_ENDPOINT is not set")
+        if not dify_config.VOLCENGINE_TOS_REGION:
+            raise ValueError("VOLCENGINE_TOS_REGION is not set")
         self.bucket_name = dify_config.VOLCENGINE_TOS_BUCKET_NAME
         self.client = tos.TosClientV2(
             ak=dify_config.VOLCENGINE_TOS_ACCESS_KEY,
@@ -20,27 +28,39 @@ class VolcengineTosStorage(BaseStorage):
         )
 
     def save(self, filename, data):
+        if not self.bucket_name:
+            raise ValueError("VOLCENGINE_TOS_BUCKET_NAME is not set")
         self.client.put_object(bucket=self.bucket_name, key=filename, content=data)
 
     def load_once(self, filename: str) -> bytes:
+        if not self.bucket_name:
+            raise FileNotFoundError("VOLCENGINE_TOS_BUCKET_NAME is not set")
         data = self.client.get_object(bucket=self.bucket_name, key=filename).read()
         if not isinstance(data, bytes):
             raise TypeError(f"Expected bytes, got {type(data).__name__}")
         return data
 
     def load_stream(self, filename: str) -> Generator:
+        if not self.bucket_name:
+            raise FileNotFoundError("VOLCENGINE_TOS_BUCKET_NAME is not set")
         response = self.client.get_object(bucket=self.bucket_name, key=filename)
         while chunk := response.read(4096):
             yield chunk
 
     def download(self, filename, target_filepath):
+        if not self.bucket_name:
+            raise ValueError("VOLCENGINE_TOS_BUCKET_NAME is not set")
         self.client.get_object_to_file(bucket=self.bucket_name, key=filename, file_path=target_filepath)
 
     def exists(self, filename):
+        if not self.bucket_name:
+            return False
         res = self.client.head_object(bucket=self.bucket_name, key=filename)
         if res.status_code != 200:
             return False
         return True
 
     def delete(self, filename):
+        if not self.bucket_name:
+            return
         self.client.delete_object(bucket=self.bucket_name, key=filename)

api/libs/collection_utils.py

@@ -0,0 +1,14 @@
+def convert_to_lower_and_upper_set(inputs: list[str] | set[str]) -> set[str]:
+    """
+    Convert a list or set of strings to a set containing both lower and upper case versions of each string.
+
+    Args:
+        inputs (list[str] | set[str]): A list or set of strings to be converted.
+
+    Returns:
+        set[str]: A set containing both lower and upper case versions of each string.
+    """
+    if not inputs:
+        return set()
+    else:
+        return {case for s in inputs if s for case in (s.lower(), s.upper())}

api/libs/validators.py

@@ -0,0 +1,5 @@
+def validate_description_length(description: str | None) -> str | None:
+    """Validate description length."""
+    if description and len(description) > 400:
+        raise ValueError("Description cannot exceed 400 characters.")
+    return description

api/pyproject.toml

@@ -5,7 +5,6 @@ requires-python = ">=3.11,<3.13"
 
 dependencies = [
     "arize-phoenix-otel~=0.9.2",
-    "authlib==1.6.4",
     "azure-identity==1.16.1",
     "beautifulsoup4==4.12.2",
     "boto3==1.35.99",
@@ -34,10 +33,8 @@ dependencies = [
     "json-repair>=0.41.1",
     "langfuse~=2.51.3",
     "langsmith~=0.1.77",
-    "mailchimp-transactional~=1.0.50",
     "markdown~=3.5.1",
     "numpy~=1.26.4",
-    "openai~=1.61.0",
     "openpyxl~=3.1.5",
     "opik~=1.7.25",
     "opentelemetry-api==1.27.0",
@@ -49,6 +46,7 @@ dependencies = [
     "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-requests==0.48b0",
     "opentelemetry-instrumentation-sqlalchemy==0.48b0",
@@ -60,7 +58,6 @@ dependencies = [
     "opentelemetry-semantic-conventions==0.48b0",
     "opentelemetry-util-http==0.48b0",
     "pandas[excel,output-formatting,performance]~=2.2.2",
-    "pandoc~=2.4",
     "psycogreen~=1.0.2",
     "psycopg2-binary~=2.9.6",
     "pycryptodome==3.19.1",
@@ -178,10 +175,10 @@ dev = [
 # Required for storage clients
 ############################################################
 storage = [
-    "azure-storage-blob==12.13.0",
+    "azure-storage-blob==12.26.0",
     "bce-python-sdk~=0.9.23",
     "cos-python-sdk-v5==1.9.38",
-    "esdk-obs-python==3.24.6.1",
+    "esdk-obs-python==3.25.8",
     "google-cloud-storage==2.16.0",
     "opendal~=0.46.0",
     "oss2==2.18.5",

api/pyrightconfig.json

@@ -1,16 +1,10 @@
 {
   "include": ["."],
   "exclude": [
-    ".venv",
     "tests/",
+    ".venv",
     "migrations/",
-    "core/rag",
-    "extensions",
-    "controllers/console/datasets",
-    "core/ops",
-    "core/model_runtime",
-    "core/workflow/nodes",
-    "core/app/app_config/easy_ui_based_app/dataset"
+    "core/rag"
   ],
   "typeCheckingMode": "strict",
   "allowedUntypedLibraries": [
@@ -18,6 +12,7 @@
     "flask_login",
     "opentelemetry.instrumentation.celery",
     "opentelemetry.instrumentation.flask",
+    "opentelemetry.instrumentation.httpx",
     "opentelemetry.instrumentation.requests",
     "opentelemetry.instrumentation.sqlalchemy",
     "opentelemetry.instrumentation.redis"
@@ -38,4 +33,4 @@
   "reportAttributeAccessIssue": "hint",
   "pythonVersion": "3.11",
   "pythonPlatform": "All"
-}
+}

api/pytest.ini

@@ -7,7 +7,7 @@ env =
     CHATGLM_API_BASE = http://a.abc.com:11451
     CODE_EXECUTION_API_KEY = dify-sandbox
     CODE_EXECUTION_ENDPOINT = http://127.0.0.1:8194
-    CODE_MAX_STRING_LENGTH = 80000
+    CODE_MAX_STRING_LENGTH = 400000
     PLUGIN_DAEMON_KEY=lYkiYYT6owG+71oLerGzA7GXCgOT++6ovaezWAjpCjf+Sjc3ZtU+qUEi
     PLUGIN_DAEMON_URL=http://127.0.0.1:5002
     PLUGIN_MAX_PACKAGE_SIZE=15728640

api/schedule/check_upgradable_plugin_task.py

@@ -52,7 +52,8 @@ def check_upgradable_plugin_task():
                 strategy.include_plugins,
             )
 
-        if batch_interval_time > 0.0001:  # if lower than 1ms, skip
+        # Only sleep if batch_interval_time > 0.0001 AND current batch is not the last one
+        if batch_interval_time > 0.0001 and i + MAX_CONCURRENT_CHECK_TASKS < total_strategies:
             time.sleep(batch_interval_time)
 
     end_at = time.perf_counter()

api/services/app_generate_service.py

@@ -2,8 +2,6 @@ import uuid
 from collections.abc import Generator, Mapping
 from typing import Any, Union
 
-from openai._exceptions import RateLimitError
-
 from configs import dify_config
 from core.app.apps.advanced_chat.app_generator import AdvancedChatAppGenerator
 from core.app.apps.agent_chat.app_generator import AgentChatAppGenerator
@@ -122,8 +120,6 @@ class AppGenerateService:
                 )
             else:
                 raise ValueError(f"Invalid app mode {app_model.mode}")
-        except RateLimitError as e:
-            raise InvokeRateLimitError(str(e))
         except Exception:
             rate_limit.exit(request_id)
             raise

api/services/dataset_service.py

@@ -93,7 +93,7 @@ logger = logging.getLogger(__name__)
 class DatasetService:
     @staticmethod
     def get_datasets(page, per_page, tenant_id=None, user=None, search=None, tag_ids=None, include_all=False):
-        query = select(Dataset).where(Dataset.tenant_id == tenant_id).order_by(Dataset.created_at.desc())
+        query = select(Dataset).where(Dataset.tenant_id == tenant_id).order_by(Dataset.created_at.desc(), Dataset.id)
 
         if user:
             # get permitted dataset ids

api/services/rag_pipeline/rag_pipeline_transform_service.py

@@ -149,8 +149,7 @@ class RagPipelineTransformService:
         file_extensions = node.get("data", {}).get("fileExtensions", [])
         if not file_extensions:
             return node
-        file_extensions = [file_extension.lower() for file_extension in file_extensions]
-        node["data"]["fileExtensions"] = DOCUMENT_EXTENSIONS
+        node["data"]["fileExtensions"] = [ext.lower() for ext in file_extensions if ext in DOCUMENT_EXTENSIONS]
         return node
 
     def _deal_knowledge_index(

api/services/tools/builtin_tools_manage_service.py

@@ -349,14 +349,10 @@ class BuiltinToolManageService:
             provider_controller = ToolManager.get_builtin_provider(default_provider.provider, tenant_id)
 
             credentials: list[ToolProviderCredentialApiEntity] = []
-            encrypters = {}
             for provider in providers:
-                credential_type = provider.credential_type
-                if credential_type not in encrypters:
-                    encrypters[credential_type] = BuiltinToolManageService.create_tool_encrypter(
-                        tenant_id, provider, provider.provider, provider_controller
-                    )[0]
-                encrypter = encrypters[credential_type]
+                encrypter, _ = BuiltinToolManageService.create_tool_encrypter(
+                    tenant_id, provider, provider.provider, provider_controller
+                )
                 decrypt_credential = encrypter.mask_tool_credentials(encrypter.decrypt(provider.credentials))
                 credential_entity = ToolTransformService.convert_builtin_provider_to_credential_entity(
                     provider=provider,

api/services/workflow/workflow_converter.py

@@ -79,7 +79,6 @@ class WorkflowConverter:
         new_app.updated_by = account.id
         db.session.add(new_app)
         db.session.flush()
-        db.session.commit()
 
         workflow.app_id = new_app.id
         db.session.commit()

api/tasks/rag_pipeline/priority_rag_pipeline_run_task.py

@@ -29,23 +29,10 @@ def priority_rag_pipeline_run_task(
     tenant_id: str,
 ):
     """
-    Async Run rag pipeline
-    :param rag_pipeline_invoke_entities: Rag pipeline invoke entities
-    rag_pipeline_invoke_entities include:
-    :param pipeline_id: Pipeline ID
-    :param user_id: User ID
-    :param tenant_id: Tenant ID
-    :param workflow_id: Workflow ID
-    :param invoke_from: Invoke source (debugger, published, etc.)
-    :param streaming: Whether to stream results
-    :param datasource_type: Type of datasource
-    :param datasource_info: Datasource information dict
-    :param batch: Batch identifier
-    :param document_id: Document ID (optional)
-    :param start_node_id: Starting node ID
-    :param inputs: Input parameters dict
-    :param workflow_execution_id: Workflow execution ID
-    :param workflow_thread_pool_id: Thread pool ID for workflow execution
+    Async Run rag pipeline task using high priority queue.
+
+    :param rag_pipeline_invoke_entities_file_id: File ID containing serialized RAG pipeline invoke entities
+    :param tenant_id: Tenant ID for the pipeline execution
     """
     # run with threading, thread pool size is 10
 

api/tasks/rag_pipeline/rag_pipeline_run_task.py

@@ -30,23 +30,10 @@ def rag_pipeline_run_task(
     tenant_id: str,
 ):
     """
-    Async Run rag pipeline
-    :param rag_pipeline_invoke_entities: Rag pipeline invoke entities
-    rag_pipeline_invoke_entities include:
-    :param pipeline_id: Pipeline ID
-    :param user_id: User ID
-    :param tenant_id: Tenant ID
-    :param workflow_id: Workflow ID
-    :param invoke_from: Invoke source (debugger, published, etc.)
-    :param streaming: Whether to stream results
-    :param datasource_type: Type of datasource
-    :param datasource_info: Datasource information dict
-    :param batch: Batch identifier
-    :param document_id: Document ID (optional)
-    :param start_node_id: Starting node ID
-    :param inputs: Input parameters dict
-    :param workflow_execution_id: Workflow execution ID
-    :param workflow_thread_pool_id: Thread pool ID for workflow execution
+    Async Run rag pipeline task using regular priority queue.
+
+    :param rag_pipeline_invoke_entities_file_id: File ID containing serialized RAG pipeline invoke entities
+    :param tenant_id: Tenant ID for the pipeline execution
     """
     # run with threading, thread pool size is 10
 

api/tasks/workflow_draft_var_tasks.py

@@ -5,15 +5,10 @@ These tasks provide asynchronous storage capabilities for workflow execution dat
 improving performance by offloading storage operations to background workers.
 """
 
-import logging
-
 from celery import shared_task  # type: ignore[import-untyped]
 from sqlalchemy.orm import Session
 
 from extensions.ext_database import db
-
-_logger = logging.getLogger(__name__)
-
 from services.workflow_draft_variable_service import DraftVarFileDeletion, WorkflowDraftVariableService
 
 

api/tests/integration_tests/controllers/console/app/test_chat_message_permissions.py

@@ -11,8 +11,8 @@ from controllers.console.app import completion as completion_api
 from controllers.console.app import message as message_api
 from controllers.console.app import wraps
 from libs.datetime_utils import naive_utc_now
-from models import Account, App, Tenant
-from models.account import TenantAccountRole
+from models import App, Tenant
+from models.account import Account, TenantAccountJoin, TenantAccountRole
 from models.model import AppMode
 from services.app_generate_service import AppGenerateService
 
@@ -31,9 +31,8 @@ class TestChatMessageApiPermissions:
         return app
 
     @pytest.fixture
-    def mock_account(self):
+    def mock_account(self, monkeypatch: pytest.MonkeyPatch):
         """Create a mock Account for testing."""
-
         account = Account()
         account.id = str(uuid.uuid4())
         account.name = "Test User"
@@ -42,12 +41,24 @@ class TestChatMessageApiPermissions:
         account.created_at = naive_utc_now()
         account.updated_at = naive_utc_now()
 
-        # Create mock tenant
         tenant = Tenant()
         tenant.id = str(uuid.uuid4())
         tenant.name = "Test Tenant"
 
-        account._current_tenant = tenant
+        mock_session_instance = mock.Mock()
+
+        mock_tenant_join = TenantAccountJoin(role=TenantAccountRole.OWNER)
+        monkeypatch.setattr(mock_session_instance, "scalar", mock.Mock(return_value=mock_tenant_join))
+
+        mock_scalars_result = mock.Mock()
+        mock_scalars_result.one.return_value = tenant
+        monkeypatch.setattr(mock_session_instance, "scalars", mock.Mock(return_value=mock_scalars_result))
+
+        mock_session_context = mock.Mock()
+        mock_session_context.__enter__.return_value = mock_session_instance
+        monkeypatch.setattr("models.account.Session", lambda _, expire_on_commit: mock_session_context)
+
+        account.current_tenant = tenant
         return account
 
     @pytest.mark.parametrize(

api/tests/integration_tests/controllers/console/app/test_description_validation.py

@@ -18,124 +18,87 @@ class TestAppDescriptionValidationUnit:
     """Unit tests for description validation function"""
 
     def test_validate_description_length_function(self):
-        """Test the _validate_description_length function directly"""
-        from controllers.console.app.app import _validate_description_length
+        """Test the validate_description_length function directly"""
+        from libs.validators import validate_description_length
 
         # Test valid descriptions
-        assert _validate_description_length("") == ""
-        assert _validate_description_length("x" * 400) == "x" * 400
-        assert _validate_description_length(None) is None
+        assert validate_description_length("") == ""
+        assert validate_description_length("x" * 400) == "x" * 400
+        assert validate_description_length(None) is None
 
         # Test invalid descriptions
         with pytest.raises(ValueError) as exc_info:
-            _validate_description_length("x" * 401)
+            validate_description_length("x" * 401)
         assert "Description cannot exceed 400 characters." in str(exc_info.value)
 
         with pytest.raises(ValueError) as exc_info:
-            _validate_description_length("x" * 500)
+            validate_description_length("x" * 500)
         assert "Description cannot exceed 400 characters." in str(exc_info.value)
 
         with pytest.raises(ValueError) as exc_info:
-            _validate_description_length("x" * 1000)
+            validate_description_length("x" * 1000)
         assert "Description cannot exceed 400 characters." in str(exc_info.value)
 
-    def test_validation_consistency_with_dataset(self):
-        """Test that App and Dataset validation functions are consistent"""
-        from controllers.console.app.app import _validate_description_length as app_validate
-        from controllers.console.datasets.datasets import _validate_description_length as dataset_validate
-        from controllers.service_api.dataset.dataset import _validate_description_length as service_dataset_validate
-
-        # Test same valid inputs
-        valid_desc = "x" * 400
-        assert app_validate(valid_desc) == dataset_validate(valid_desc) == service_dataset_validate(valid_desc)
-        assert app_validate("") == dataset_validate("") == service_dataset_validate("")
-        assert app_validate(None) == dataset_validate(None) == service_dataset_validate(None)
-
-        # Test same invalid inputs produce same error
-        invalid_desc = "x" * 401
-
-        app_error = None
-        dataset_error = None
-        service_dataset_error = None
-
-        try:
-            app_validate(invalid_desc)
-        except ValueError as e:
-            app_error = str(e)
-
-        try:
-            dataset_validate(invalid_desc)
-        except ValueError as e:
-            dataset_error = str(e)
-
-        try:
-            service_dataset_validate(invalid_desc)
-        except ValueError as e:
-            service_dataset_error = str(e)
-
-        assert app_error == dataset_error == service_dataset_error
-        assert app_error == "Description cannot exceed 400 characters."
-
     def test_boundary_values(self):
         """Test boundary values for description validation"""
-        from controllers.console.app.app import _validate_description_length
+        from libs.validators import validate_description_length
 
         # Test exact boundary
         exactly_400 = "x" * 400
-        assert _validate_description_length(exactly_400) == exactly_400
+        assert validate_description_length(exactly_400) == exactly_400
 
         # Test just over boundary
         just_over_400 = "x" * 401
         with pytest.raises(ValueError):
-            _validate_description_length(just_over_400)
+            validate_description_length(just_over_400)
 
         # Test just under boundary
         just_under_400 = "x" * 399
-        assert _validate_description_length(just_under_400) == just_under_400
+        assert validate_description_length(just_under_400) == just_under_400
 
     def test_edge_cases(self):
         """Test edge cases for description validation"""
-        from controllers.console.app.app import _validate_description_length
+        from libs.validators import validate_description_length
 
         # Test None input
-        assert _validate_description_length(None) is None
+        assert validate_description_length(None) is None
 
         # Test empty string
-        assert _validate_description_length("") == ""
+        assert validate_description_length("") == ""
 
         # Test single character
-        assert _validate_description_length("a") == "a"
+        assert validate_description_length("a") == "a"
 
         # Test unicode characters
         unicode_desc = "测试" * 200  # 400 characters in Chinese
-        assert _validate_description_length(unicode_desc) == unicode_desc
+        assert validate_description_length(unicode_desc) == unicode_desc
 
         # Test unicode over limit
         unicode_over = "测试" * 201  # 402 characters
         with pytest.raises(ValueError):
-            _validate_description_length(unicode_over)
+            validate_description_length(unicode_over)
 
     def test_whitespace_handling(self):
         """Test how validation handles whitespace"""
-        from controllers.console.app.app import _validate_description_length
+        from libs.validators import validate_description_length
 
         # Test description with spaces
         spaces_400 = " " * 400
-        assert _validate_description_length(spaces_400) == spaces_400
+        assert validate_description_length(spaces_400) == spaces_400
 
         # Test description with spaces over limit
         spaces_401 = " " * 401
         with pytest.raises(ValueError):
-            _validate_description_length(spaces_401)
+            validate_description_length(spaces_401)
 
         # Test mixed content
         mixed_400 = "a" * 200 + " " * 200
-        assert _validate_description_length(mixed_400) == mixed_400
+        assert validate_description_length(mixed_400) == mixed_400
 
         # Test mixed over limit
         mixed_401 = "a" * 200 + " " * 201
         with pytest.raises(ValueError):
-            _validate_description_length(mixed_401)
+            validate_description_length(mixed_401)
 
 
 if __name__ == "__main__":

api/tests/integration_tests/controllers/console/app/test_model_config_permissions.py

@@ -9,8 +9,8 @@ from flask.testing import FlaskClient
 from controllers.console.app import model_config as model_config_api
 from controllers.console.app import wraps
 from libs.datetime_utils import naive_utc_now
-from models import Account, App, Tenant
-from models.account import TenantAccountRole
+from models import App, Tenant
+from models.account import Account, TenantAccountJoin, TenantAccountRole
 from models.model import AppMode
 from services.app_model_config_service import AppModelConfigService
 
@@ -30,9 +30,8 @@ class TestModelConfigResourcePermissions:
         return app
 
     @pytest.fixture
-    def mock_account(self):
+    def mock_account(self, monkeypatch: pytest.MonkeyPatch):
         """Create a mock Account for testing."""
-
         account = Account()
         account.id = str(uuid.uuid4())
         account.name = "Test User"
@@ -41,12 +40,24 @@ class TestModelConfigResourcePermissions:
         account.created_at = naive_utc_now()
         account.updated_at = naive_utc_now()
 
-        # Create mock tenant
         tenant = Tenant()
         tenant.id = str(uuid.uuid4())
         tenant.name = "Test Tenant"
 
-        account._current_tenant = tenant
+        mock_session_instance = mock.Mock()
+
+        mock_tenant_join = TenantAccountJoin(role=TenantAccountRole.OWNER)
+        monkeypatch.setattr(mock_session_instance, "scalar", mock.Mock(return_value=mock_tenant_join))
+
+        mock_scalars_result = mock.Mock()
+        mock_scalars_result.one.return_value = tenant
+        monkeypatch.setattr(mock_session_instance, "scalars", mock.Mock(return_value=mock_scalars_result))
+
+        mock_session_context = mock.Mock()
+        mock_session_context.__enter__.return_value = mock_session_instance
+        monkeypatch.setattr("models.account.Session", lambda _, expire_on_commit: mock_session_context)
+
+        account.current_tenant = tenant
         return account
 
     @pytest.mark.parametrize(

api/tests/integration_tests/workflow/nodes/test_code.py

@@ -1,9 +1,9 @@
 import time
 import uuid
-from os import getenv
 
 import pytest
 
+from configs import dify_config
 from core.app.entities.app_invoke_entities import InvokeFrom
 from core.workflow.entities import GraphInitParams, GraphRuntimeState, VariablePool
 from core.workflow.enums import WorkflowNodeExecutionStatus
@@ -15,7 +15,7 @@ from core.workflow.system_variable import SystemVariable
 from models.enums import UserFrom
 from tests.integration_tests.workflow.nodes.__mock.code_executor import setup_code_executor_mock
 
-CODE_MAX_STRING_LENGTH = int(getenv("CODE_MAX_STRING_LENGTH", "10000"))
+CODE_MAX_STRING_LENGTH = dify_config.CODE_MAX_STRING_LENGTH
 
 
 def init_code_node(code_config: dict):

api/tests/test_containers_integration_tests/conftest.py

@@ -18,6 +18,7 @@ from flask.testing import FlaskClient
 from sqlalchemy import Engine, text
 from sqlalchemy.orm import Session
 from testcontainers.core.container import DockerContainer
+from testcontainers.core.network import Network
 from testcontainers.core.waiting_utils import wait_for_logs
 from testcontainers.postgres import PostgresContainer
 from testcontainers.redis import RedisContainer
@@ -41,6 +42,7 @@ class DifyTestContainers:
 
     def __init__(self):
         """Initialize container management with default configurations."""
+        self.network: Network | None = None
         self.postgres: PostgresContainer | None = None
         self.redis: RedisContainer | None = None
         self.dify_sandbox: DockerContainer | None = None
@@ -62,12 +64,18 @@ class DifyTestContainers:
 
         logger.info("Starting test containers for Dify integration tests...")
 
+        # Create Docker network for container communication
+        logger.info("Creating Docker network for container communication...")
+        self.network = Network()
+        self.network.create()
+        logger.info("Docker network created successfully with name: %s", self.network.name)
+
         # Start PostgreSQL container for main application database
         # PostgreSQL is used for storing user data, workflows, and application state
         logger.info("Initializing PostgreSQL container...")
         self.postgres = PostgresContainer(
             image="postgres:14-alpine",
-        )
+        ).with_network(self.network)
         self.postgres.start()
         db_host = self.postgres.get_container_host_ip()
         db_port = self.postgres.get_exposed_port(5432)
@@ -137,7 +145,7 @@ class DifyTestContainers:
         # Start Redis container for caching and session management
         # Redis is used for storing session data, cache entries, and temporary data
         logger.info("Initializing Redis container...")
-        self.redis = RedisContainer(image="redis:6-alpine", port=6379)
+        self.redis = RedisContainer(image="redis:6-alpine", port=6379).with_network(self.network)
         self.redis.start()
         redis_host = self.redis.get_container_host_ip()
         redis_port = self.redis.get_exposed_port(6379)
@@ -153,7 +161,7 @@ class DifyTestContainers:
         # Start Dify Sandbox container for code execution environment
         # Dify Sandbox provides a secure environment for executing user code
         logger.info("Initializing Dify Sandbox container...")
-        self.dify_sandbox = DockerContainer(image="langgenius/dify-sandbox:latest")
+        self.dify_sandbox = DockerContainer(image="langgenius/dify-sandbox:latest").with_network(self.network)
         self.dify_sandbox.with_exposed_ports(8194)
         self.dify_sandbox.env = {
             "API_KEY": "test_api_key",
@@ -173,22 +181,28 @@ class DifyTestContainers:
         # Start Dify Plugin Daemon container for plugin management
         # Dify Plugin Daemon provides plugin lifecycle management and execution
         logger.info("Initializing Dify Plugin Daemon container...")
-        self.dify_plugin_daemon = DockerContainer(image="langgenius/dify-plugin-daemon:0.3.0-local")
+        self.dify_plugin_daemon = DockerContainer(image="langgenius/dify-plugin-daemon:0.3.0-local").with_network(
+            self.network
+        )
         self.dify_plugin_daemon.with_exposed_ports(5002)
+        # Get container internal network addresses
+        postgres_container_name = self.postgres.get_wrapped_container().name
+        redis_container_name = self.redis.get_wrapped_container().name
+
         self.dify_plugin_daemon.env = {
-            "DB_HOST": db_host,
-            "DB_PORT": str(db_port),
+            "DB_HOST": postgres_container_name,  # Use container name for internal network communication
+            "DB_PORT": "5432",  # Use internal port
             "DB_USERNAME": self.postgres.username,
             "DB_PASSWORD": self.postgres.password,
             "DB_DATABASE": "dify_plugin",
-            "REDIS_HOST": redis_host,
-            "REDIS_PORT": str(redis_port),
+            "REDIS_HOST": redis_container_name,  # Use container name for internal network communication
+            "REDIS_PORT": "6379",  # Use internal port
             "REDIS_PASSWORD": "",
             "SERVER_PORT": "5002",
             "SERVER_KEY": "test_plugin_daemon_key",
             "MAX_PLUGIN_PACKAGE_SIZE": "52428800",
             "PPROF_ENABLED": "false",
-            "DIFY_INNER_API_URL": f"http://{db_host}:5001",
+            "DIFY_INNER_API_URL": f"http://{postgres_container_name}:5001",
             "DIFY_INNER_API_KEY": "test_inner_api_key",
             "PLUGIN_REMOTE_INSTALLING_HOST": "0.0.0.0",
             "PLUGIN_REMOTE_INSTALLING_PORT": "5003",
@@ -253,6 +267,15 @@ class DifyTestContainers:
                     # Log error but don't fail the test cleanup
                     logger.warning("Failed to stop container %s: %s", container, e)
 
+        # Stop and remove the network
+        if self.network:
+            try:
+                logger.info("Removing Docker network...")
+                self.network.remove()
+                logger.info("Successfully removed Docker network")
+            except Exception as e:
+                logger.warning("Failed to remove Docker network: %s", e)
+
         self._containers_started = False
         logger.info("All test containers stopped and cleaned up successfully")
 

api/tests/test_containers_integration_tests/services/test_app_generate_service.py

@@ -3,7 +3,6 @@ from unittest.mock import MagicMock, patch
 
 import pytest
 from faker import Faker
-from openai._exceptions import RateLimitError
 
 from core.app.entities.app_invoke_entities import InvokeFrom
 from models.model import EndUser
@@ -484,36 +483,6 @@ class TestAppGenerateService:
             # Verify error message
             assert "Rate limit exceeded" in str(exc_info.value)
 
-    def test_generate_with_rate_limit_error_from_openai(
-        self, db_session_with_containers, mock_external_service_dependencies
-    ):
-        """
-        Test generation when OpenAI rate limit error occurs.
-        """
-        fake = Faker()
-        app, account = self._create_test_app_and_account(
-            db_session_with_containers, mock_external_service_dependencies, mode="completion"
-        )
-
-        # Setup completion generator to raise RateLimitError
-        mock_response = MagicMock()
-        mock_response.request = MagicMock()
-        mock_external_service_dependencies["completion_generator"].return_value.generate.side_effect = RateLimitError(
-            "Rate limit exceeded", response=mock_response, body=None
-        )
-
-        # Setup test arguments
-        args = {"inputs": {"query": fake.text(max_nb_chars=50)}, "response_mode": "streaming"}
-
-        # Execute the method under test and expect rate limit error
-        with pytest.raises(InvokeRateLimitError) as exc_info:
-            AppGenerateService.generate(
-                app_model=app, user=account, args=args, invoke_from=InvokeFrom.SERVICE_API, streaming=True
-            )
-
-        # Verify error message
-        assert "Rate limit exceeded" in str(exc_info.value)
-
     def test_generate_with_invalid_app_mode(self, db_session_with_containers, mock_external_service_dependencies):
         """
         Test generation with invalid app mode.

api/tests/test_containers_integration_tests/tasks/test_clean_dataset_task.py

@@ -784,133 +784,6 @@ class TestCleanDatasetTask:
         print(f"Total cleanup time: {cleanup_duration:.3f} seconds")
         print(f"Average time per document: {cleanup_duration / len(documents):.3f} seconds")
 
-    def test_clean_dataset_task_concurrent_cleanup_scenarios(
-        self, db_session_with_containers, mock_external_service_dependencies
-    ):
-        """
-        Test dataset cleanup with concurrent cleanup scenarios and race conditions.
-
-        This test verifies that the task can properly:
-        1. Handle multiple cleanup operations on the same dataset
-        2. Prevent data corruption during concurrent access
-        3. Maintain data consistency across multiple cleanup attempts
-        4. Handle race conditions gracefully
-        5. Ensure idempotent cleanup operations
-        """
-        # Create test data
-        account, tenant = self._create_test_account_and_tenant(db_session_with_containers)
-        dataset = self._create_test_dataset(db_session_with_containers, account, tenant)
-        document = self._create_test_document(db_session_with_containers, account, tenant, dataset)
-        segment = self._create_test_segment(db_session_with_containers, account, tenant, dataset, document)
-        upload_file = self._create_test_upload_file(db_session_with_containers, account, tenant)
-
-        # Update document with file reference
-        import json
-
-        document.data_source_info = json.dumps({"upload_file_id": upload_file.id})
-        from extensions.ext_database import db
-
-        db.session.commit()
-
-        # Save IDs for verification
-        dataset_id = dataset.id
-        tenant_id = tenant.id
-        upload_file_id = upload_file.id
-
-        # Mock storage to simulate slow operations
-        mock_storage = mock_external_service_dependencies["storage"]
-        original_delete = mock_storage.delete
-
-        def slow_delete(key):
-            import time
-
-            time.sleep(0.1)  # Simulate slow storage operation
-            return original_delete(key)
-
-        mock_storage.delete.side_effect = slow_delete
-
-        # Execute multiple cleanup operations concurrently
-        import threading
-
-        cleanup_results = []
-        cleanup_errors = []
-
-        def run_cleanup():
-            try:
-                clean_dataset_task(
-                    dataset_id=dataset_id,
-                    tenant_id=tenant_id,
-                    indexing_technique="high_quality",
-                    index_struct='{"type": "paragraph"}',
-                    collection_binding_id=str(uuid.uuid4()),
-                    doc_form="paragraph_index",
-                )
-                cleanup_results.append("success")
-            except Exception as e:
-                cleanup_errors.append(str(e))
-
-        # Start multiple cleanup threads
-        threads = []
-        for i in range(3):
-            thread = threading.Thread(target=run_cleanup)
-            threads.append(thread)
-            thread.start()
-
-        # Wait for all threads to complete
-        for thread in threads:
-            thread.join()
-
-        # Verify results
-        # Check that all documents were deleted (only once)
-        remaining_documents = db.session.query(Document).filter_by(dataset_id=dataset_id).all()
-        assert len(remaining_documents) == 0
-
-        # Check that all segments were deleted (only once)
-        remaining_segments = db.session.query(DocumentSegment).filter_by(dataset_id=dataset_id).all()
-        assert len(remaining_segments) == 0
-
-        # Check that upload file was deleted (only once)
-        # Note: In concurrent scenarios, the first thread deletes documents and segments,
-        # subsequent threads may not find the related data to clean up upload files
-        # This demonstrates the idempotent nature of the cleanup process
-        remaining_files = db.session.query(UploadFile).filter_by(id=upload_file_id).all()
-        # The upload file should be deleted by the first successful cleanup operation
-        # However, in concurrent scenarios, this may not always happen due to race conditions
-        # This test demonstrates the idempotent nature of the cleanup process
-        if len(remaining_files) > 0:
-            print(f"Warning: Upload file {upload_file_id} was not deleted in concurrent scenario")
-            print("This is expected behavior demonstrating the idempotent nature of cleanup")
-        # We don't assert here as the behavior depends on timing and race conditions
-
-        # Verify that storage.delete was called (may be called multiple times in concurrent scenarios)
-        # In concurrent scenarios, storage operations may be called multiple times due to race conditions
-        assert mock_storage.delete.call_count > 0
-
-        # Verify that index processor was called (may be called multiple times in concurrent scenarios)
-        mock_index_processor = mock_external_service_dependencies["index_processor"]
-        assert mock_index_processor.clean.call_count > 0
-
-        # Check cleanup results
-        assert len(cleanup_results) == 3, "All cleanup operations should complete"
-        assert len(cleanup_errors) == 0, "No cleanup errors should occur"
-
-        # Verify idempotency by running cleanup again on the same dataset
-        # This should not perform any additional operations since data is already cleaned
-        clean_dataset_task(
-            dataset_id=dataset_id,
-            tenant_id=tenant_id,
-            indexing_technique="high_quality",
-            index_struct='{"type": "paragraph"}',
-            collection_binding_id=str(uuid.uuid4()),
-            doc_form="paragraph_index",
-        )
-
-        # Verify that no additional storage operations were performed
-        # Note: In concurrent scenarios, the exact count may vary due to race conditions
-        print(f"Final storage delete calls: {mock_storage.delete.call_count}")
-        print(f"Final index processor calls: {mock_index_processor.clean.call_count}")
-        print("Note: Multiple calls in concurrent scenarios are expected due to race conditions")
-
     def test_clean_dataset_task_storage_exception_handling(
         self, db_session_with_containers, mock_external_service_dependencies
     ):

api/tests/test_containers_integration_tests/tasks/test_enable_segments_to_index_task.py

@@ -0,0 +1,450 @@
+from unittest.mock import MagicMock, patch
+
+import pytest
+from faker import Faker
+
+from core.rag.index_processor.constant.index_type import IndexType
+from extensions.ext_database import db
+from extensions.ext_redis import redis_client
+from models.account import Account, Tenant, TenantAccountJoin, TenantAccountRole
+from models.dataset import Dataset, Document, DocumentSegment
+from tasks.enable_segments_to_index_task import enable_segments_to_index_task
+
+
+class TestEnableSegmentsToIndexTask:
+    """Integration tests for enable_segments_to_index_task using testcontainers."""
+
+    @pytest.fixture
+    def mock_external_service_dependencies(self):
+        """Mock setup for external service dependencies."""
+        with (
+            patch("tasks.enable_segments_to_index_task.IndexProcessorFactory") as mock_index_processor_factory,
+        ):
+            # Setup mock index processor
+            mock_processor = MagicMock()
+            mock_index_processor_factory.return_value.init_index_processor.return_value = mock_processor
+
+            yield {
+                "index_processor_factory": mock_index_processor_factory,
+                "index_processor": mock_processor,
+            }
+
+    def _create_test_dataset_and_document(self, db_session_with_containers, mock_external_service_dependencies):
+        """
+        Helper method to create a test dataset and document for testing.
+
+        Args:
+            db_session_with_containers: Database session from testcontainers infrastructure
+            mock_external_service_dependencies: Mock dependencies
+
+        Returns:
+            tuple: (dataset, document) - Created dataset and document instances
+        """
+        fake = Faker()
+
+        # Create account and tenant
+        account = Account(
+            email=fake.email(),
+            name=fake.name(),
+            interface_language="en-US",
+            status="active",
+        )
+        db.session.add(account)
+        db.session.commit()
+
+        tenant = Tenant(
+            name=fake.company(),
+            status="normal",
+        )
+        db.session.add(tenant)
+        db.session.commit()
+
+        # Create tenant-account join
+        join = TenantAccountJoin(
+            tenant_id=tenant.id,
+            account_id=account.id,
+            role=TenantAccountRole.OWNER.value,
+            current=True,
+        )
+        db.session.add(join)
+        db.session.commit()
+
+        # Create dataset
+        dataset = Dataset(
+            id=fake.uuid4(),
+            tenant_id=tenant.id,
+            name=fake.company(),
+            description=fake.text(max_nb_chars=100),
+            data_source_type="upload_file",
+            indexing_technique="high_quality",
+            created_by=account.id,
+        )
+        db.session.add(dataset)
+        db.session.commit()
+
+        # Create document
+        document = Document(
+            id=fake.uuid4(),
+            tenant_id=tenant.id,
+            dataset_id=dataset.id,
+            position=1,
+            data_source_type="upload_file",
+            batch="test_batch",
+            name=fake.file_name(),
+            created_from="upload_file",
+            created_by=account.id,
+            indexing_status="completed",
+            enabled=True,
+            doc_form=IndexType.PARAGRAPH_INDEX,
+        )
+        db.session.add(document)
+        db.session.commit()
+
+        # Refresh dataset to ensure doc_form property works correctly
+        db.session.refresh(dataset)
+
+        return dataset, document
+
+    def _create_test_segments(
+        self, db_session_with_containers, document, dataset, count=3, enabled=False, status="completed"
+    ):
+        """
+        Helper method to create test document segments.
+
+        Args:
+            db_session_with_containers: Database session from testcontainers infrastructure
+            document: Document instance
+            dataset: Dataset instance
+            count: Number of segments to create
+            enabled: Whether segments should be enabled
+            status: Status of the segments
+
+        Returns:
+            list: List of created DocumentSegment instances
+        """
+        fake = Faker()
+        segments = []
+
+        for i in range(count):
+            text = fake.text(max_nb_chars=200)
+            segment = DocumentSegment(
+                id=fake.uuid4(),
+                tenant_id=document.tenant_id,
+                dataset_id=dataset.id,
+                document_id=document.id,
+                position=i,
+                content=text,
+                word_count=len(text.split()),
+                tokens=len(text.split()) * 2,
+                index_node_id=f"node_{i}",
+                index_node_hash=f"hash_{i}",
+                enabled=enabled,
+                status=status,
+                created_by=document.created_by,
+            )
+            db.session.add(segment)
+            segments.append(segment)
+
+        db.session.commit()
+        return segments
+
+    def test_enable_segments_to_index_with_different_index_type(
+        self, db_session_with_containers, mock_external_service_dependencies
+    ):
+        """
+        Test segments indexing with different index types.
+
+        This test verifies:
+        - Proper handling of different index types
+        - Index processor factory integration
+        - Document processing with various configurations
+        - Redis cache key deletion
+        """
+        # Arrange: Create test data with different index type
+        dataset, document = self._create_test_dataset_and_document(
+            db_session_with_containers, mock_external_service_dependencies
+        )
+
+        # Update document to use different index type
+        document.doc_form = IndexType.QA_INDEX
+        db.session.commit()
+
+        # Refresh dataset to ensure doc_form property reflects the updated document
+        db.session.refresh(dataset)
+
+        # Create segments
+        segments = self._create_test_segments(db_session_with_containers, document, dataset)
+
+        # Set up Redis cache keys
+        segment_ids = [segment.id for segment in segments]
+        for segment in segments:
+            indexing_cache_key = f"segment_{segment.id}_indexing"
+            redis_client.set(indexing_cache_key, "processing", ex=300)
+
+        # Act: Execute the task
+        enable_segments_to_index_task(segment_ids, dataset.id, document.id)
+
+        # Assert: Verify different index type handling
+        mock_external_service_dependencies["index_processor_factory"].assert_called_once_with(IndexType.QA_INDEX)
+        mock_external_service_dependencies["index_processor"].load.assert_called_once()
+
+        # Verify the load method was called with correct parameters
+        call_args = mock_external_service_dependencies["index_processor"].load.call_args
+        assert call_args is not None
+        documents = call_args[0][1]  # Second argument should be documents list
+        assert len(documents) == 3
+
+        # Verify Redis cache keys were deleted
+        for segment in segments:
+            indexing_cache_key = f"segment_{segment.id}_indexing"
+            assert redis_client.exists(indexing_cache_key) == 0
+
+    def test_enable_segments_to_index_dataset_not_found(
+        self, db_session_with_containers, mock_external_service_dependencies
+    ):
+        """
+        Test handling of non-existent dataset.
+
+        This test verifies:
+        - Proper error handling for missing datasets
+        - Early return without processing
+        - Database session cleanup
+        - No unnecessary index processor calls
+        """
+        # Arrange: Use non-existent dataset ID
+        fake = Faker()
+        non_existent_dataset_id = fake.uuid4()
+        non_existent_document_id = fake.uuid4()
+        segment_ids = [fake.uuid4()]
+
+        # Act: Execute the task with non-existent dataset
+        enable_segments_to_index_task(segment_ids, non_existent_dataset_id, non_existent_document_id)
+
+        # Assert: Verify no processing occurred
+        mock_external_service_dependencies["index_processor_factory"].assert_not_called()
+        mock_external_service_dependencies["index_processor"].load.assert_not_called()
+
+    def test_enable_segments_to_index_document_not_found(
+        self, db_session_with_containers, mock_external_service_dependencies
+    ):
+        """
+        Test handling of non-existent document.
+
+        This test verifies:
+        - Proper error handling for missing documents
+        - Early return without processing
+        - Database session cleanup
+        - No unnecessary index processor calls
+        """
+        # Arrange: Create dataset but use non-existent document ID
+        dataset, _ = self._create_test_dataset_and_document(
+            db_session_with_containers, mock_external_service_dependencies
+        )
+        fake = Faker()
+        non_existent_document_id = fake.uuid4()
+        segment_ids = [fake.uuid4()]
+
+        # Act: Execute the task with non-existent document
+        enable_segments_to_index_task(segment_ids, dataset.id, non_existent_document_id)
+
+        # Assert: Verify no processing occurred
+        mock_external_service_dependencies["index_processor_factory"].assert_not_called()
+        mock_external_service_dependencies["index_processor"].load.assert_not_called()
+
+    def test_enable_segments_to_index_invalid_document_status(
+        self, db_session_with_containers, mock_external_service_dependencies
+    ):
+        """
+        Test handling of document with invalid status.
+
+        This test verifies:
+        - Early return when document is disabled, archived, or not completed
+        - No index processing for documents not ready for indexing
+        - Proper database session cleanup
+        - No unnecessary external service calls
+        """
+        # Arrange: Create test data with invalid document status
+        dataset, document = self._create_test_dataset_and_document(
+            db_session_with_containers, mock_external_service_dependencies
+        )
+
+        # Test different invalid statuses
+        invalid_statuses = [
+            ("disabled", {"enabled": False}),
+            ("archived", {"archived": True}),
+            ("not_completed", {"indexing_status": "processing"}),
+        ]
+
+        for _, status_attrs in invalid_statuses:
+            # Reset document status
+            document.enabled = True
+            document.archived = False
+            document.indexing_status = "completed"
+            db.session.commit()
+
+            # Set invalid status
+            for attr, value in status_attrs.items():
+                setattr(document, attr, value)
+            db.session.commit()
+
+            # Create segments
+            segments = self._create_test_segments(db_session_with_containers, document, dataset)
+            segment_ids = [segment.id for segment in segments]
+
+            # Act: Execute the task
+            enable_segments_to_index_task(segment_ids, dataset.id, document.id)
+
+            # Assert: Verify no processing occurred
+            mock_external_service_dependencies["index_processor_factory"].assert_not_called()
+            mock_external_service_dependencies["index_processor"].load.assert_not_called()
+
+            # Clean up segments for next iteration
+            for segment in segments:
+                db.session.delete(segment)
+            db.session.commit()
+
+    def test_enable_segments_to_index_segments_not_found(
+        self, db_session_with_containers, mock_external_service_dependencies
+    ):
+        """
+        Test handling when no segments are found.
+
+        This test verifies:
+        - Proper handling when segments don't exist
+        - Early return without processing
+        - Database session cleanup
+        - Index processor is created but load is not called
+        """
+        # Arrange: Create test data
+        dataset, document = self._create_test_dataset_and_document(
+            db_session_with_containers, mock_external_service_dependencies
+        )
+
+        # Use non-existent segment IDs
+        fake = Faker()
+        non_existent_segment_ids = [fake.uuid4() for _ in range(3)]
+
+        # Act: Execute the task with non-existent segments
+        enable_segments_to_index_task(non_existent_segment_ids, dataset.id, document.id)
+
+        # Assert: Verify index processor was created but load was not called
+        mock_external_service_dependencies["index_processor_factory"].assert_called_once_with(IndexType.PARAGRAPH_INDEX)
+        mock_external_service_dependencies["index_processor"].load.assert_not_called()
+
+    def test_enable_segments_to_index_with_parent_child_structure(
+        self, db_session_with_containers, mock_external_service_dependencies
+    ):
+        """
+        Test segments indexing with parent-child structure.
+
+        This test verifies:
+        - Proper handling of PARENT_CHILD_INDEX type
+        - Child document creation from segments
+        - Correct document structure for parent-child indexing
+        - Index processor receives properly structured documents
+        - Redis cache key deletion
+        """
+        # Arrange: Create test data with parent-child index type
+        dataset, document = self._create_test_dataset_and_document(
+            db_session_with_containers, mock_external_service_dependencies
+        )
+
+        # Update document to use parent-child index type
+        document.doc_form = IndexType.PARENT_CHILD_INDEX
+        db.session.commit()
+
+        # Refresh dataset to ensure doc_form property reflects the updated document
+        db.session.refresh(dataset)
+
+        # Create segments with mock child chunks
+        segments = self._create_test_segments(db_session_with_containers, document, dataset)
+
+        # Set up Redis cache keys
+        segment_ids = [segment.id for segment in segments]
+        for segment in segments:
+            indexing_cache_key = f"segment_{segment.id}_indexing"
+            redis_client.set(indexing_cache_key, "processing", ex=300)
+
+        # Mock the get_child_chunks method for each segment
+        with patch.object(DocumentSegment, "get_child_chunks") as mock_get_child_chunks:
+            # Setup mock to return child chunks for each segment
+            mock_child_chunks = []
+            for i in range(2):  # Each segment has 2 child chunks
+                mock_child = MagicMock()
+                mock_child.content = f"child_content_{i}"
+                mock_child.index_node_id = f"child_node_{i}"
+                mock_child.index_node_hash = f"child_hash_{i}"
+                mock_child_chunks.append(mock_child)
+
+            mock_get_child_chunks.return_value = mock_child_chunks
+
+            # Act: Execute the task
+            enable_segments_to_index_task(segment_ids, dataset.id, document.id)
+
+            # Assert: Verify parent-child index processing
+            mock_external_service_dependencies["index_processor_factory"].assert_called_once_with(
+                IndexType.PARENT_CHILD_INDEX
+            )
+            mock_external_service_dependencies["index_processor"].load.assert_called_once()
+
+            # Verify the load method was called with correct parameters
+            call_args = mock_external_service_dependencies["index_processor"].load.call_args
+            assert call_args is not None
+            documents = call_args[0][1]  # Second argument should be documents list
+            assert len(documents) == 3  # 3 segments
+
+            # Verify each document has children
+            for doc in documents:
+                assert hasattr(doc, "children")
+                assert len(doc.children) == 2  # Each document has 2 children
+
+            # Verify Redis cache keys were deleted
+            for segment in segments:
+                indexing_cache_key = f"segment_{segment.id}_indexing"
+                assert redis_client.exists(indexing_cache_key) == 0
+
+    def test_enable_segments_to_index_general_exception_handling(
+        self, db_session_with_containers, mock_external_service_dependencies
+    ):
+        """
+        Test general exception handling during indexing process.
+
+        This test verifies:
+        - Exceptions are properly caught and handled
+        - Segment status is set to error
+        - Segments are disabled
+        - Error information is recorded
+        - Redis cache is still cleared
+        - Database session is properly closed
+        """
+        # Arrange: Create test data
+        dataset, document = self._create_test_dataset_and_document(
+            db_session_with_containers, mock_external_service_dependencies
+        )
+        segments = self._create_test_segments(db_session_with_containers, document, dataset)
+
+        # Set up Redis cache keys
+        segment_ids = [segment.id for segment in segments]
+        for segment in segments:
+            indexing_cache_key = f"segment_{segment.id}_indexing"
+            redis_client.set(indexing_cache_key, "processing", ex=300)
+
+        # Mock the index processor to raise an exception
+        mock_external_service_dependencies["index_processor"].load.side_effect = Exception("Index processing failed")
+
+        # Act: Execute the task
+        enable_segments_to_index_task(segment_ids, dataset.id, document.id)
+
+        # Assert: Verify error handling
+        for segment in segments:
+            db.session.refresh(segment)
+            assert segment.enabled is False
+            assert segment.status == "error"
+            assert segment.error is not None
+            assert "Index processing failed" in segment.error
+            assert segment.disabled_at is not None
+
+        # Verify Redis cache keys were still cleared despite error
+        for segment in segments:
+            indexing_cache_key = f"segment_{segment.id}_indexing"
+            assert redis_client.exists(indexing_cache_key) == 0

api/tests/test_containers_integration_tests/tasks/test_mail_account_deletion_task.py

@@ -0,0 +1,242 @@
+from unittest.mock import MagicMock, patch
+
+import pytest
+from faker import Faker
+
+from extensions.ext_database import db
+from libs.email_i18n import EmailType
+from models.account import Account, Tenant, TenantAccountJoin, TenantAccountRole
+from tasks.mail_account_deletion_task import send_account_deletion_verification_code, send_deletion_success_task
+
+
+class TestMailAccountDeletionTask:
+    """Integration tests for mail account deletion tasks using testcontainers."""
+
+    @pytest.fixture
+    def mock_external_service_dependencies(self):
+        """Mock setup for external service dependencies."""
+        with (
+            patch("tasks.mail_account_deletion_task.mail") as mock_mail,
+            patch("tasks.mail_account_deletion_task.get_email_i18n_service") as mock_get_email_service,
+        ):
+            # Setup mock mail service
+            mock_mail.is_inited.return_value = True
+
+            # Setup mock email service
+            mock_email_service = MagicMock()
+            mock_get_email_service.return_value = mock_email_service
+
+            yield {
+                "mail": mock_mail,
+                "get_email_service": mock_get_email_service,
+                "email_service": mock_email_service,
+            }
+
+    def _create_test_account(self, db_session_with_containers):
+        """
+        Helper method to create a test account for testing.
+
+        Args:
+            db_session_with_containers: Database session from testcontainers infrastructure
+
+        Returns:
+            Account: Created account instance
+        """
+        fake = Faker()
+
+        # Create account
+        account = Account(
+            email=fake.email(),
+            name=fake.name(),
+            interface_language="en-US",
+            status="active",
+        )
+        db.session.add(account)
+        db.session.commit()
+
+        # Create tenant
+        tenant = Tenant(
+            name=fake.company(),
+            status="normal",
+        )
+        db.session.add(tenant)
+        db.session.commit()
+
+        # Create tenant-account join
+        join = TenantAccountJoin(
+            tenant_id=tenant.id,
+            account_id=account.id,
+            role=TenantAccountRole.OWNER.value,
+            current=True,
+        )
+        db.session.add(join)
+        db.session.commit()
+
+        return account
+
+    def test_send_deletion_success_task_success(self, db_session_with_containers, mock_external_service_dependencies):
+        """
+        Test successful account deletion success email sending.
+
+        This test verifies:
+        - Proper email service initialization check
+        - Correct email service method calls
+        - Template context is properly formatted
+        - Email type is correctly specified
+        """
+        # Arrange: Create test data
+        account = self._create_test_account(db_session_with_containers)
+        test_email = account.email
+        test_language = "en-US"
+
+        # Act: Execute the task
+        send_deletion_success_task(test_email, test_language)
+
+        # Assert: Verify the expected outcomes
+        # Verify mail service was checked
+        mock_external_service_dependencies["mail"].is_inited.assert_called_once()
+
+        # Verify email service was retrieved
+        mock_external_service_dependencies["get_email_service"].assert_called_once()
+
+        # Verify email was sent with correct parameters
+        mock_external_service_dependencies["email_service"].send_email.assert_called_once_with(
+            email_type=EmailType.ACCOUNT_DELETION_SUCCESS,
+            language_code=test_language,
+            to=test_email,
+            template_context={
+                "to": test_email,
+                "email": test_email,
+            },
+        )
+
+    def test_send_deletion_success_task_mail_not_initialized(
+        self, db_session_with_containers, mock_external_service_dependencies
+    ):
+        """
+        Test account deletion success email when mail service is not initialized.
+
+        This test verifies:
+        - Early return when mail service is not initialized
+        - No email service calls are made
+        - No exceptions are raised
+        """
+        # Arrange: Setup mail service to return not initialized
+        mock_external_service_dependencies["mail"].is_inited.return_value = False
+        account = self._create_test_account(db_session_with_containers)
+        test_email = account.email
+
+        # Act: Execute the task
+        send_deletion_success_task(test_email)
+
+        # Assert: Verify no email service calls were made
+        mock_external_service_dependencies["get_email_service"].assert_not_called()
+        mock_external_service_dependencies["email_service"].send_email.assert_not_called()
+
+    def test_send_deletion_success_task_email_service_exception(
+        self, db_session_with_containers, mock_external_service_dependencies
+    ):
+        """
+        Test account deletion success email when email service raises exception.
+
+        This test verifies:
+        - Exception is properly caught and logged
+        - Task completes without raising exception
+        - Error logging is recorded
+        """
+        # Arrange: Setup email service to raise exception
+        mock_external_service_dependencies["email_service"].send_email.side_effect = Exception("Email service failed")
+        account = self._create_test_account(db_session_with_containers)
+        test_email = account.email
+
+        # Act: Execute the task (should not raise exception)
+        send_deletion_success_task(test_email)
+
+        # Assert: Verify email service was called but exception was handled
+        mock_external_service_dependencies["email_service"].send_email.assert_called_once()
+
+    def test_send_account_deletion_verification_code_success(
+        self, db_session_with_containers, mock_external_service_dependencies
+    ):
+        """
+        Test successful account deletion verification code email sending.
+
+        This test verifies:
+        - Proper email service initialization check
+        - Correct email service method calls
+        - Template context includes verification code
+        - Email type is correctly specified
+        """
+        # Arrange: Create test data
+        account = self._create_test_account(db_session_with_containers)
+        test_email = account.email
+        test_code = "123456"
+        test_language = "en-US"
+
+        # Act: Execute the task
+        send_account_deletion_verification_code(test_email, test_code, test_language)
+
+        # Assert: Verify the expected outcomes
+        # Verify mail service was checked
+        mock_external_service_dependencies["mail"].is_inited.assert_called_once()
+
+        # Verify email service was retrieved
+        mock_external_service_dependencies["get_email_service"].assert_called_once()
+
+        # Verify email was sent with correct parameters
+        mock_external_service_dependencies["email_service"].send_email.assert_called_once_with(
+            email_type=EmailType.ACCOUNT_DELETION_VERIFICATION,
+            language_code=test_language,
+            to=test_email,
+            template_context={
+                "to": test_email,
+                "code": test_code,
+            },
+        )
+
+    def test_send_account_deletion_verification_code_mail_not_initialized(
+        self, db_session_with_containers, mock_external_service_dependencies
+    ):
+        """
+        Test account deletion verification code email when mail service is not initialized.
+
+        This test verifies:
+        - Early return when mail service is not initialized
+        - No email service calls are made
+        - No exceptions are raised
+        """
+        # Arrange: Setup mail service to return not initialized
+        mock_external_service_dependencies["mail"].is_inited.return_value = False
+        account = self._create_test_account(db_session_with_containers)
+        test_email = account.email
+        test_code = "123456"
+
+        # Act: Execute the task
+        send_account_deletion_verification_code(test_email, test_code)
+
+        # Assert: Verify no email service calls were made
+        mock_external_service_dependencies["get_email_service"].assert_not_called()
+        mock_external_service_dependencies["email_service"].send_email.assert_not_called()
+
+    def test_send_account_deletion_verification_code_email_service_exception(
+        self, db_session_with_containers, mock_external_service_dependencies
+    ):
+        """
+        Test account deletion verification code email when email service raises exception.
+
+        This test verifies:
+        - Exception is properly caught and logged
+        - Task completes without raising exception
+        - Error logging is recorded
+        """
+        # Arrange: Setup email service to raise exception
+        mock_external_service_dependencies["email_service"].send_email.side_effect = Exception("Email service failed")
+        account = self._create_test_account(db_session_with_containers)
+        test_email = account.email
+        test_code = "123456"
+
+        # Act: Execute the task (should not raise exception)
+        send_account_deletion_verification_code(test_email, test_code)
+
+        # Assert: Verify email service was called but exception was handled
+        mock_external_service_dependencies["email_service"].send_email.assert_called_once()

api/tests/test_containers_integration_tests/tasks/test_mail_change_mail_task.py

@@ -0,0 +1,282 @@
+from unittest.mock import MagicMock, patch
+
+import pytest
+from faker import Faker
+
+from libs.email_i18n import EmailType
+from models.account import Account, Tenant, TenantAccountJoin, TenantAccountRole
+from tasks.mail_change_mail_task import send_change_mail_completed_notification_task, send_change_mail_task
+
+
+class TestMailChangeMailTask:
+    """Integration tests for mail_change_mail_task using testcontainers."""
+
+    @pytest.fixture
+    def mock_external_service_dependencies(self):
+        """Mock setup for external service dependencies."""
+        with (
+            patch("tasks.mail_change_mail_task.mail") as mock_mail,
+            patch("tasks.mail_change_mail_task.get_email_i18n_service") as mock_get_email_i18n_service,
+        ):
+            # Setup mock mail service
+            mock_mail.is_inited.return_value = True
+
+            # Setup mock email i18n service
+            mock_email_service = MagicMock()
+            mock_get_email_i18n_service.return_value = mock_email_service
+
+            yield {
+                "mail": mock_mail,
+                "email_i18n_service": mock_email_service,
+                "get_email_i18n_service": mock_get_email_i18n_service,
+            }
+
+    def _create_test_account(self, db_session_with_containers):
+        """
+        Helper method to create a test account for testing.
+
+        Args:
+            db_session_with_containers: Database session from testcontainers infrastructure
+
+        Returns:
+            Account: Created account instance
+        """
+        fake = Faker()
+
+        # Create account
+        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()
+
+        # Create tenant
+        tenant = Tenant(
+            name=fake.company(),
+            status="normal",
+        )
+        db_session_with_containers.add(tenant)
+        db_session_with_containers.commit()
+
+        # Create tenant-account join
+        join = TenantAccountJoin(
+            tenant_id=tenant.id,
+            account_id=account.id,
+            role=TenantAccountRole.OWNER.value,
+            current=True,
+        )
+        db_session_with_containers.add(join)
+        db_session_with_containers.commit()
+
+        return account
+
+    def test_send_change_mail_task_success_old_email_phase(
+        self, db_session_with_containers, mock_external_service_dependencies
+    ):
+        """
+        Test successful change email task execution for old_email phase.
+
+        This test verifies:
+        - Proper mail service initialization check
+        - Correct email service method call with old_email phase
+        - Successful task completion
+        """
+        # Arrange: Create test data
+        account = self._create_test_account(db_session_with_containers)
+        test_language = "en-US"
+        test_email = account.email
+        test_code = "123456"
+        test_phase = "old_email"
+
+        # Act: Execute the task
+        send_change_mail_task(test_language, test_email, test_code, test_phase)
+
+        # Assert: Verify the expected outcomes
+        mock_external_service_dependencies["mail"].is_inited.assert_called_once()
+        mock_external_service_dependencies["get_email_i18n_service"].assert_called_once()
+        mock_external_service_dependencies["email_i18n_service"].send_change_email.assert_called_once_with(
+            language_code=test_language,
+            to=test_email,
+            code=test_code,
+            phase=test_phase,
+        )
+
+    def test_send_change_mail_task_success_new_email_phase(
+        self, db_session_with_containers, mock_external_service_dependencies
+    ):
+        """
+        Test successful change email task execution for new_email phase.
+
+        This test verifies:
+        - Proper mail service initialization check
+        - Correct email service method call with new_email phase
+        - Successful task completion
+        """
+        # Arrange: Create test data
+        account = self._create_test_account(db_session_with_containers)
+        test_language = "zh-Hans"
+        test_email = "new@example.com"
+        test_code = "789012"
+        test_phase = "new_email"
+
+        # Act: Execute the task
+        send_change_mail_task(test_language, test_email, test_code, test_phase)
+
+        # Assert: Verify the expected outcomes
+        mock_external_service_dependencies["mail"].is_inited.assert_called_once()
+        mock_external_service_dependencies["get_email_i18n_service"].assert_called_once()
+        mock_external_service_dependencies["email_i18n_service"].send_change_email.assert_called_once_with(
+            language_code=test_language,
+            to=test_email,
+            code=test_code,
+            phase=test_phase,
+        )
+
+    def test_send_change_mail_task_mail_not_initialized(
+        self, db_session_with_containers, mock_external_service_dependencies
+    ):
+        """
+        Test change email task when mail service is not initialized.
+
+        This test verifies:
+        - Early return when mail service is not initialized
+        - No email service calls when mail is not available
+        """
+        # Arrange: Setup mail service as not initialized
+        mock_external_service_dependencies["mail"].is_inited.return_value = False
+        test_language = "en-US"
+        test_email = "test@example.com"
+        test_code = "123456"
+        test_phase = "old_email"
+
+        # Act: Execute the task
+        send_change_mail_task(test_language, test_email, test_code, test_phase)
+
+        # Assert: Verify no email service calls
+        mock_external_service_dependencies["mail"].is_inited.assert_called_once()
+        mock_external_service_dependencies["get_email_i18n_service"].assert_not_called()
+        mock_external_service_dependencies["email_i18n_service"].send_change_email.assert_not_called()
+
+    def test_send_change_mail_task_email_service_exception(
+        self, db_session_with_containers, mock_external_service_dependencies
+    ):
+        """
+        Test change email task when email service raises an exception.
+
+        This test verifies:
+        - Exception is properly caught and logged
+        - Task completes without raising exception
+        """
+        # Arrange: Setup email service to raise exception
+        mock_external_service_dependencies["email_i18n_service"].send_change_email.side_effect = Exception(
+            "Email service failed"
+        )
+        test_language = "en-US"
+        test_email = "test@example.com"
+        test_code = "123456"
+        test_phase = "old_email"
+
+        # Act: Execute the task (should not raise exception)
+        send_change_mail_task(test_language, test_email, test_code, test_phase)
+
+        # Assert: Verify email service was called despite exception
+        mock_external_service_dependencies["mail"].is_inited.assert_called_once()
+        mock_external_service_dependencies["get_email_i18n_service"].assert_called_once()
+        mock_external_service_dependencies["email_i18n_service"].send_change_email.assert_called_once_with(
+            language_code=test_language,
+            to=test_email,
+            code=test_code,
+            phase=test_phase,
+        )
+
+    def test_send_change_mail_completed_notification_task_success(
+        self, db_session_with_containers, mock_external_service_dependencies
+    ):
+        """
+        Test successful change email completed notification task execution.
+
+        This test verifies:
+        - Proper mail service initialization check
+        - Correct email service method call with CHANGE_EMAIL_COMPLETED type
+        - Template context is properly constructed
+        - Successful task completion
+        """
+        # Arrange: Create test data
+        account = self._create_test_account(db_session_with_containers)
+        test_language = "en-US"
+        test_email = account.email
+
+        # Act: Execute the task
+        send_change_mail_completed_notification_task(test_language, test_email)
+
+        # Assert: Verify the expected outcomes
+        mock_external_service_dependencies["mail"].is_inited.assert_called_once()
+        mock_external_service_dependencies["get_email_i18n_service"].assert_called_once()
+        mock_external_service_dependencies["email_i18n_service"].send_email.assert_called_once_with(
+            email_type=EmailType.CHANGE_EMAIL_COMPLETED,
+            language_code=test_language,
+            to=test_email,
+            template_context={
+                "to": test_email,
+                "email": test_email,
+            },
+        )
+
+    def test_send_change_mail_completed_notification_task_mail_not_initialized(
+        self, db_session_with_containers, mock_external_service_dependencies
+    ):
+        """
+        Test change email completed notification task when mail service is not initialized.
+
+        This test verifies:
+        - Early return when mail service is not initialized
+        - No email service calls when mail is not available
+        """
+        # Arrange: Setup mail service as not initialized
+        mock_external_service_dependencies["mail"].is_inited.return_value = False
+        test_language = "en-US"
+        test_email = "test@example.com"
+
+        # Act: Execute the task
+        send_change_mail_completed_notification_task(test_language, test_email)
+
+        # Assert: Verify no email service calls
+        mock_external_service_dependencies["mail"].is_inited.assert_called_once()
+        mock_external_service_dependencies["get_email_i18n_service"].assert_not_called()
+        mock_external_service_dependencies["email_i18n_service"].send_email.assert_not_called()
+
+    def test_send_change_mail_completed_notification_task_email_service_exception(
+        self, db_session_with_containers, mock_external_service_dependencies
+    ):
+        """
+        Test change email completed notification task when email service raises an exception.
+
+        This test verifies:
+        - Exception is properly caught and logged
+        - Task completes without raising exception
+        """
+        # Arrange: Setup email service to raise exception
+        mock_external_service_dependencies["email_i18n_service"].send_email.side_effect = Exception(
+            "Email service failed"
+        )
+        test_language = "en-US"
+        test_email = "test@example.com"
+
+        # Act: Execute the task (should not raise exception)
+        send_change_mail_completed_notification_task(test_language, test_email)
+
+        # Assert: Verify email service was called despite exception
+        mock_external_service_dependencies["mail"].is_inited.assert_called_once()
+        mock_external_service_dependencies["get_email_i18n_service"].assert_called_once()
+        mock_external_service_dependencies["email_i18n_service"].send_email.assert_called_once_with(
+            email_type=EmailType.CHANGE_EMAIL_COMPLETED,
+            language_code=test_language,
+            to=test_email,
+            template_context={
+                "to": test_email,
+                "email": test_email,
+            },
+        )

api/tests/test_containers_integration_tests/tasks/test_mail_email_code_login_task.py

@@ -0,0 +1,598 @@
+"""
+TestContainers-based integration tests for send_email_code_login_mail_task.
+
+This module provides comprehensive integration tests for the email code login mail task
+using TestContainers infrastructure. The tests ensure that the task properly sends
+email verification codes for login with internationalization support and handles
+various error scenarios in a real database environment.
+
+All tests use the testcontainers infrastructure to ensure proper database isolation
+and realistic testing scenarios with actual PostgreSQL and Redis instances.
+"""
+
+from unittest.mock import MagicMock, patch
+
+import pytest
+from faker import Faker
+
+from libs.email_i18n import EmailType
+from models.account import Account, Tenant, TenantAccountJoin, TenantAccountRole
+from tasks.mail_email_code_login import send_email_code_login_mail_task
+
+
+class TestSendEmailCodeLoginMailTask:
+    """
+    Comprehensive integration tests for send_email_code_login_mail_task using testcontainers.
+
+    This test class covers all major functionality of the email code login mail task:
+    - Successful email sending with different languages
+    - Email service integration and template rendering
+    - Error handling for various failure scenarios
+    - Performance metrics and logging verification
+    - Edge cases and boundary conditions
+
+    All tests use the testcontainers infrastructure to ensure proper database isolation
+    and realistic testing environment with actual database interactions.
+    """
+
+    @pytest.fixture(autouse=True)
+    def cleanup_database(self, db_session_with_containers):
+        """Clean up database before each test to ensure isolation."""
+        from extensions.ext_redis import redis_client
+
+        # Clear all test data
+        db_session_with_containers.query(TenantAccountJoin).delete()
+        db_session_with_containers.query(Tenant).delete()
+        db_session_with_containers.query(Account).delete()
+        db_session_with_containers.commit()
+
+        # Clear Redis cache
+        redis_client.flushdb()
+
+    @pytest.fixture
+    def mock_external_service_dependencies(self):
+        """Mock setup for external service dependencies."""
+        with (
+            patch("tasks.mail_email_code_login.mail") as mock_mail,
+            patch("tasks.mail_email_code_login.get_email_i18n_service") as mock_email_service,
+        ):
+            # Setup default mock returns
+            mock_mail.is_inited.return_value = True
+
+            # Mock email service
+            mock_email_service_instance = MagicMock()
+            mock_email_service_instance.send_email.return_value = None
+            mock_email_service.return_value = mock_email_service_instance
+
+            yield {
+                "mail": mock_mail,
+                "email_service": mock_email_service,
+                "email_service_instance": mock_email_service_instance,
+            }
+
+    def _create_test_account(self, db_session_with_containers, fake=None):
+        """
+        Helper method to create a test account for testing.
+
+        Args:
+            db_session_with_containers: Database session from testcontainers infrastructure
+            fake: Faker instance for generating test data
+
+        Returns:
+            Account: Created account instance
+        """
+        if fake is None:
+            fake = Faker()
+
+        # Create account
+        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()
+
+        return account
+
+    def _create_test_tenant_and_account(self, db_session_with_containers, fake=None):
+        """
+        Helper method to create a test tenant and account for testing.
+
+        Args:
+            db_session_with_containers: Database session from testcontainers infrastructure
+            fake: Faker instance for generating test data
+
+        Returns:
+            tuple: (Account, Tenant) created instances
+        """
+        if fake is None:
+            fake = Faker()
+
+        # Create account using the existing helper method
+        account = self._create_test_account(db_session_with_containers, fake)
+
+        # Create tenant
+        tenant = Tenant(
+            name=fake.company(),
+            plan="basic",
+            status="active",
+        )
+
+        db_session_with_containers.add(tenant)
+        db_session_with_containers.commit()
+
+        # Create tenant-account relationship
+        tenant_account_join = TenantAccountJoin(
+            tenant_id=tenant.id,
+            account_id=account.id,
+            role=TenantAccountRole.OWNER,
+        )
+
+        db_session_with_containers.add(tenant_account_join)
+        db_session_with_containers.commit()
+
+        return account, tenant
+
+    def test_send_email_code_login_mail_task_success_english(
+        self, db_session_with_containers, mock_external_service_dependencies
+    ):
+        """
+        Test successful email code login mail sending in English.
+
+        This test verifies that the task can successfully:
+        1. Send email code login mail with English language
+        2. Use proper email service integration
+        3. Pass correct template context to email service
+        4. Log performance metrics correctly
+        5. Complete task execution without errors
+        """
+        # Arrange: Setup test data
+        fake = Faker()
+        test_email = fake.email()
+        test_code = "123456"
+        test_language = "en-US"
+
+        # Act: Execute the task
+        send_email_code_login_mail_task(
+            language=test_language,
+            to=test_email,
+            code=test_code,
+        )
+
+        # Assert: Verify expected outcomes
+        mock_mail = mock_external_service_dependencies["mail"]
+        mock_email_service_instance = mock_external_service_dependencies["email_service_instance"]
+
+        # Verify mail service was checked for initialization
+        mock_mail.is_inited.assert_called_once()
+
+        # Verify email service was called with correct parameters
+        mock_email_service_instance.send_email.assert_called_once_with(
+            email_type=EmailType.EMAIL_CODE_LOGIN,
+            language_code=test_language,
+            to=test_email,
+            template_context={
+                "to": test_email,
+                "code": test_code,
+            },
+        )
+
+    def test_send_email_code_login_mail_task_success_chinese(
+        self, db_session_with_containers, mock_external_service_dependencies
+    ):
+        """
+        Test successful email code login mail sending in Chinese.
+
+        This test verifies that the task can successfully:
+        1. Send email code login mail with Chinese language
+        2. Handle different language codes properly
+        3. Use correct template context for Chinese emails
+        4. Complete task execution without errors
+        """
+        # Arrange: Setup test data
+        fake = Faker()
+        test_email = fake.email()
+        test_code = "789012"
+        test_language = "zh-Hans"
+
+        # Act: Execute the task
+        send_email_code_login_mail_task(
+            language=test_language,
+            to=test_email,
+            code=test_code,
+        )
+
+        # Assert: Verify expected outcomes
+        mock_email_service_instance = mock_external_service_dependencies["email_service_instance"]
+
+        # Verify email service was called with Chinese language
+        mock_email_service_instance.send_email.assert_called_once_with(
+            email_type=EmailType.EMAIL_CODE_LOGIN,
+            language_code=test_language,
+            to=test_email,
+            template_context={
+                "to": test_email,
+                "code": test_code,
+            },
+        )
+
+    def test_send_email_code_login_mail_task_success_multiple_languages(
+        self, db_session_with_containers, mock_external_service_dependencies
+    ):
+        """
+        Test successful email code login mail sending with multiple languages.
+
+        This test verifies that the task can successfully:
+        1. Handle various language codes correctly
+        2. Send emails with different language configurations
+        3. Maintain proper template context for each language
+        4. Complete multiple task executions without conflicts
+        """
+        # Arrange: Setup test data
+        fake = Faker()
+        test_languages = ["en-US", "zh-Hans", "zh-CN", "ja-JP", "ko-KR"]
+        test_emails = [fake.email() for _ in test_languages]
+        test_codes = [fake.numerify("######") for _ in test_languages]
+
+        # Act: Execute the task for each language
+        for i, language in enumerate(test_languages):
+            send_email_code_login_mail_task(
+                language=language,
+                to=test_emails[i],
+                code=test_codes[i],
+            )
+
+        # Assert: Verify expected outcomes
+        mock_email_service_instance = mock_external_service_dependencies["email_service_instance"]
+
+        # Verify email service was called for each language
+        assert mock_email_service_instance.send_email.call_count == len(test_languages)
+
+        # Verify each call had correct parameters
+        for i, language in enumerate(test_languages):
+            call_args = mock_email_service_instance.send_email.call_args_list[i]
+            assert call_args[1]["email_type"] == EmailType.EMAIL_CODE_LOGIN
+            assert call_args[1]["language_code"] == language
+            assert call_args[1]["to"] == test_emails[i]
+            assert call_args[1]["template_context"]["code"] == test_codes[i]
+
+    def test_send_email_code_login_mail_task_mail_not_initialized(
+        self, db_session_with_containers, mock_external_service_dependencies
+    ):
+        """
+        Test email code login mail task when mail service is not initialized.
+
+        This test verifies that the task can properly:
+        1. Check mail service initialization status
+        2. Return early when mail is not initialized
+        3. Not attempt to send email when service is unavailable
+        4. Handle gracefully without errors
+        """
+        # Arrange: Setup test data
+        fake = Faker()
+        test_email = fake.email()
+        test_code = "123456"
+        test_language = "en-US"
+
+        # Mock mail service as not initialized
+        mock_mail = mock_external_service_dependencies["mail"]
+        mock_mail.is_inited.return_value = False
+
+        # Act: Execute the task
+        send_email_code_login_mail_task(
+            language=test_language,
+            to=test_email,
+            code=test_code,
+        )
+
+        # Assert: Verify expected outcomes
+        mock_email_service_instance = mock_external_service_dependencies["email_service_instance"]
+
+        # Verify mail service was checked for initialization
+        mock_mail.is_inited.assert_called_once()
+
+        # Verify email service was not called
+        mock_email_service_instance.send_email.assert_not_called()
+
+    def test_send_email_code_login_mail_task_email_service_exception(
+        self, db_session_with_containers, mock_external_service_dependencies
+    ):
+        """
+        Test email code login mail task when email service raises an exception.
+
+        This test verifies that the task can properly:
+        1. Handle email service exceptions gracefully
+        2. Log appropriate error messages
+        3. Continue execution without crashing
+        4. Maintain proper error handling
+        """
+        # Arrange: Setup test data
+        fake = Faker()
+        test_email = fake.email()
+        test_code = "123456"
+        test_language = "en-US"
+
+        # Mock email service to raise an exception
+        mock_email_service_instance = mock_external_service_dependencies["email_service_instance"]
+        mock_email_service_instance.send_email.side_effect = Exception("Email service unavailable")
+
+        # Act: Execute the task - it should handle the exception gracefully
+        send_email_code_login_mail_task(
+            language=test_language,
+            to=test_email,
+            code=test_code,
+        )
+
+        # Assert: Verify expected outcomes
+        mock_mail = mock_external_service_dependencies["mail"]
+        mock_email_service_instance = mock_external_service_dependencies["email_service_instance"]
+
+        # Verify mail service was checked for initialization
+        mock_mail.is_inited.assert_called_once()
+
+        # Verify email service was called (and failed)
+        mock_email_service_instance.send_email.assert_called_once_with(
+            email_type=EmailType.EMAIL_CODE_LOGIN,
+            language_code=test_language,
+            to=test_email,
+            template_context={
+                "to": test_email,
+                "code": test_code,
+            },
+        )
+
+    def test_send_email_code_login_mail_task_invalid_parameters(
+        self, db_session_with_containers, mock_external_service_dependencies
+    ):
+        """
+        Test email code login mail task with invalid parameters.
+
+        This test verifies that the task can properly:
+        1. Handle empty or None email addresses
+        2. Process empty or None verification codes
+        3. Handle invalid language codes
+        4. Maintain proper error handling for invalid inputs
+        """
+        # Arrange: Setup test data
+        fake = Faker()
+        test_language = "en-US"
+
+        # Test cases for invalid parameters
+        invalid_test_cases = [
+            {"email": "", "code": "123456", "description": "empty email"},
+            {"email": None, "code": "123456", "description": "None email"},
+            {"email": fake.email(), "code": "", "description": "empty code"},
+            {"email": fake.email(), "code": None, "description": "None code"},
+            {"email": "invalid-email", "code": "123456", "description": "invalid email format"},
+        ]
+
+        for test_case in invalid_test_cases:
+            # Reset mocks for each test case
+            mock_email_service_instance = mock_external_service_dependencies["email_service_instance"]
+            mock_email_service_instance.reset_mock()
+
+            # Act: Execute the task with invalid parameters
+            send_email_code_login_mail_task(
+                language=test_language,
+                to=test_case["email"],
+                code=test_case["code"],
+            )
+
+            # Assert: Verify that email service was still called
+            # The task should pass parameters to email service as-is
+            # and let the email service handle validation
+            mock_email_service_instance.send_email.assert_called_once()
+
+    def test_send_email_code_login_mail_task_edge_cases(
+        self, db_session_with_containers, mock_external_service_dependencies
+    ):
+        """
+        Test email code login mail task with edge cases and boundary conditions.
+
+        This test verifies that the task can properly:
+        1. Handle very long email addresses
+        2. Process very long verification codes
+        3. Handle special characters in parameters
+        4. Process extreme language codes
+        """
+        # Arrange: Setup test data
+        fake = Faker()
+        test_language = "en-US"
+
+        # Edge case test data
+        edge_cases = [
+            {
+                "email": "a" * 100 + "@example.com",  # Very long email
+                "code": "1" * 20,  # Very long code
+                "description": "very long email and code",
+            },
+            {
+                "email": "test+tag@example.com",  # Email with special characters
+                "code": "123-456",  # Code with special characters
+                "description": "special characters",
+            },
+            {
+                "email": "test@sub.domain.example.com",  # Complex domain
+                "code": "000000",  # All zeros
+                "description": "complex domain and all zeros code",
+            },
+            {
+                "email": "test@example.co.uk",  # International domain
+                "code": "999999",  # All nines
+                "description": "international domain and all nines code",
+            },
+        ]
+
+        for test_case in edge_cases:
+            # Reset mocks for each test case
+            mock_email_service_instance = mock_external_service_dependencies["email_service_instance"]
+            mock_email_service_instance.reset_mock()
+
+            # Act: Execute the task with edge case data
+            send_email_code_login_mail_task(
+                language=test_language,
+                to=test_case["email"],
+                code=test_case["code"],
+            )
+
+            # Assert: Verify that email service was called with edge case data
+            mock_email_service_instance.send_email.assert_called_once_with(
+                email_type=EmailType.EMAIL_CODE_LOGIN,
+                language_code=test_language,
+                to=test_case["email"],
+                template_context={
+                    "to": test_case["email"],
+                    "code": test_case["code"],
+                },
+            )
+
+    def test_send_email_code_login_mail_task_database_integration(
+        self, db_session_with_containers, mock_external_service_dependencies
+    ):
+        """
+        Test email code login mail task with database integration.
+
+        This test verifies that the task can properly:
+        1. Work with real database connections
+        2. Handle database session management
+        3. Maintain proper database state
+        4. Complete without database-related errors
+        """
+        # Arrange: Setup test data with database
+        fake = Faker()
+        account, tenant = self._create_test_tenant_and_account(db_session_with_containers, fake)
+
+        test_email = account.email
+        test_code = "123456"
+        test_language = "en-US"
+
+        # Act: Execute the task
+        send_email_code_login_mail_task(
+            language=test_language,
+            to=test_email,
+            code=test_code,
+        )
+
+        # Assert: Verify expected outcomes
+        mock_email_service_instance = mock_external_service_dependencies["email_service_instance"]
+
+        # Verify email service was called with database account email
+        mock_email_service_instance.send_email.assert_called_once_with(
+            email_type=EmailType.EMAIL_CODE_LOGIN,
+            language_code=test_language,
+            to=test_email,
+            template_context={
+                "to": test_email,
+                "code": test_code,
+            },
+        )
+
+        # Verify database state is maintained
+        db_session_with_containers.refresh(account)
+        assert account.email == test_email
+        assert account.status == "active"
+
+    def test_send_email_code_login_mail_task_redis_integration(
+        self, db_session_with_containers, mock_external_service_dependencies
+    ):
+        """
+        Test email code login mail task with Redis integration.
+
+        This test verifies that the task can properly:
+        1. Work with Redis cache connections
+        2. Handle Redis operations without errors
+        3. Maintain proper cache state
+        4. Complete without Redis-related errors
+        """
+        # Arrange: Setup test data
+        fake = Faker()
+        test_email = fake.email()
+        test_code = "123456"
+        test_language = "en-US"
+
+        # Setup Redis cache data
+        from extensions.ext_redis import redis_client
+
+        cache_key = f"email_code_login_test_{test_email}"
+        redis_client.set(cache_key, "test_value", ex=300)
+
+        # Act: Execute the task
+        send_email_code_login_mail_task(
+            language=test_language,
+            to=test_email,
+            code=test_code,
+        )
+
+        # Assert: Verify expected outcomes
+        mock_email_service_instance = mock_external_service_dependencies["email_service_instance"]
+
+        # Verify email service was called
+        mock_email_service_instance.send_email.assert_called_once()
+
+        # Verify Redis cache is still accessible
+        assert redis_client.exists(cache_key) == 1
+        assert redis_client.get(cache_key) == b"test_value"
+
+        # Clean up Redis cache
+        redis_client.delete(cache_key)
+
+    def test_send_email_code_login_mail_task_error_handling_comprehensive(
+        self, db_session_with_containers, mock_external_service_dependencies
+    ):
+        """
+        Test comprehensive error handling for email code login mail task.
+
+        This test verifies that the task can properly:
+        1. Handle various types of exceptions
+        2. Log appropriate error messages
+        3. Continue execution despite errors
+        4. Maintain proper error reporting
+        """
+        # Arrange: Setup test data
+        fake = Faker()
+        test_email = fake.email()
+        test_code = "123456"
+        test_language = "en-US"
+
+        # Test different exception types
+        exception_types = [
+            ("ValueError", ValueError("Invalid email format")),
+            ("RuntimeError", RuntimeError("Service unavailable")),
+            ("ConnectionError", ConnectionError("Network error")),
+            ("TimeoutError", TimeoutError("Request timeout")),
+            ("Exception", Exception("Generic error")),
+        ]
+
+        for error_name, exception in exception_types:
+            # Reset mocks for each test case
+            mock_email_service_instance = mock_external_service_dependencies["email_service_instance"]
+            mock_email_service_instance.reset_mock()
+            mock_email_service_instance.send_email.side_effect = exception
+
+            # Mock logging to capture error messages
+            with patch("tasks.mail_email_code_login.logger") as mock_logger:
+                # Act: Execute the task - it should handle the exception gracefully
+                send_email_code_login_mail_task(
+                    language=test_language,
+                    to=test_email,
+                    code=test_code,
+                )
+
+                # Assert: Verify error handling
+                # Verify email service was called (and failed)
+                mock_email_service_instance.send_email.assert_called_once()
+
+                # Verify error was logged
+                error_calls = [
+                    call
+                    for call in mock_logger.exception.call_args_list
+                    if f"Send email code login mail to {test_email} failed" in str(call)
+                ]
+                # Check if any exception call was made (the exact message format may vary)
+                assert mock_logger.exception.call_count >= 1, f"Error should be logged for {error_name}"
+
+            # Reset side effect for next iteration
+            mock_email_service_instance.send_email.side_effect = None

api/tests/test_containers_integration_tests/tasks/test_mail_inner_task.py

@@ -0,0 +1,261 @@
+from unittest.mock import MagicMock, patch
+
+import pytest
+from faker import Faker
+
+from tasks.mail_inner_task import send_inner_email_task
+
+
+class TestMailInnerTask:
+    """Integration tests for send_inner_email_task using testcontainers."""
+
+    @pytest.fixture
+    def mock_external_service_dependencies(self):
+        """Mock setup for external service dependencies."""
+        with (
+            patch("tasks.mail_inner_task.mail") as mock_mail,
+            patch("tasks.mail_inner_task.get_email_i18n_service") as mock_get_email_i18n_service,
+            patch("tasks.mail_inner_task._render_template_with_strategy") as mock_render_template,
+        ):
+            # Setup mock mail service
+            mock_mail.is_inited.return_value = True
+
+            # Setup mock email i18n service
+            mock_email_service = MagicMock()
+            mock_get_email_i18n_service.return_value = mock_email_service
+
+            # Setup mock template rendering
+            mock_render_template.return_value = "<html>Test email content</html>"
+
+            yield {
+                "mail": mock_mail,
+                "email_service": mock_email_service,
+                "render_template": mock_render_template,
+            }
+
+    def _create_test_email_data(self, fake: Faker) -> dict:
+        """
+        Helper method to create test email data for testing.
+
+        Args:
+            fake: Faker instance for generating test data
+
+        Returns:
+            dict: Test email data including recipients, subject, body, and substitutions
+        """
+        return {
+            "to": [fake.email() for _ in range(3)],
+            "subject": fake.sentence(nb_words=4),
+            "body": "Hello {{name}}, this is a test email from {{company}}.",
+            "substitutions": {
+                "name": fake.name(),
+                "company": fake.company(),
+                "date": fake.date(),
+            },
+        }
+
+    def test_send_inner_email_success(self, db_session_with_containers, mock_external_service_dependencies):
+        """
+        Test successful email sending with valid data.
+
+        This test verifies:
+        - Proper email service initialization check
+        - Template rendering with substitutions
+        - Email service integration
+        - Multiple recipient handling
+        """
+        # Arrange: Create test data
+        fake = Faker()
+        email_data = self._create_test_email_data(fake)
+
+        # Act: Execute the task
+        send_inner_email_task(
+            to=email_data["to"],
+            subject=email_data["subject"],
+            body=email_data["body"],
+            substitutions=email_data["substitutions"],
+        )
+
+        # Assert: Verify the expected outcomes
+        # Verify mail service was checked for initialization
+        mock_external_service_dependencies["mail"].is_inited.assert_called_once()
+
+        # Verify template rendering was called with correct parameters
+        mock_external_service_dependencies["render_template"].assert_called_once_with(
+            email_data["body"], email_data["substitutions"]
+        )
+
+        # Verify email service was called once with the full recipient list
+        mock_email_service = mock_external_service_dependencies["email_service"]
+        mock_email_service.send_raw_email.assert_called_once_with(
+            to=email_data["to"],
+            subject=email_data["subject"],
+            html_content="<html>Test email content</html>",
+        )
+
+    def test_send_inner_email_single_recipient(self, db_session_with_containers, mock_external_service_dependencies):
+        """
+        Test email sending with single recipient.
+
+        This test verifies:
+        - Single recipient handling
+        - Template rendering
+        - Email service integration
+        """
+        # Arrange: Create test data with single recipient
+        fake = Faker()
+        email_data = {
+            "to": [fake.email()],
+            "subject": fake.sentence(nb_words=3),
+            "body": "Welcome {{user_name}}!",
+            "substitutions": {
+                "user_name": fake.name(),
+            },
+        }
+
+        # Act: Execute the task
+        send_inner_email_task(
+            to=email_data["to"],
+            subject=email_data["subject"],
+            body=email_data["body"],
+            substitutions=email_data["substitutions"],
+        )
+
+        # Assert: Verify the expected outcomes
+        mock_email_service = mock_external_service_dependencies["email_service"]
+        mock_email_service.send_raw_email.assert_called_once_with(
+            to=email_data["to"],
+            subject=email_data["subject"],
+            html_content="<html>Test email content</html>",
+        )
+
+    def test_send_inner_email_empty_substitutions(self, db_session_with_containers, mock_external_service_dependencies):
+        """
+        Test email sending with empty substitutions.
+
+        This test verifies:
+        - Template rendering with empty substitutions
+        - Email service integration
+        - Handling of minimal template context
+        """
+        # Arrange: Create test data with empty substitutions
+        fake = Faker()
+        email_data = {
+            "to": [fake.email()],
+            "subject": fake.sentence(nb_words=3),
+            "body": "This is a simple email without variables.",
+            "substitutions": {},
+        }
+
+        # Act: Execute the task
+        send_inner_email_task(
+            to=email_data["to"],
+            subject=email_data["subject"],
+            body=email_data["body"],
+            substitutions=email_data["substitutions"],
+        )
+
+        # Assert: Verify the expected outcomes
+        mock_external_service_dependencies["render_template"].assert_called_once_with(email_data["body"], {})
+
+        mock_email_service = mock_external_service_dependencies["email_service"]
+        mock_email_service.send_raw_email.assert_called_once_with(
+            to=email_data["to"],
+            subject=email_data["subject"],
+            html_content="<html>Test email content</html>",
+        )
+
+    def test_send_inner_email_mail_not_initialized(
+        self, db_session_with_containers, mock_external_service_dependencies
+    ):
+        """
+        Test email sending when mail service is not initialized.
+
+        This test verifies:
+        - Early return when mail service is not initialized
+        - No template rendering occurs
+        - No email service calls
+        - No exceptions raised
+        """
+        # Arrange: Setup mail service as not initialized
+        mock_external_service_dependencies["mail"].is_inited.return_value = False
+
+        fake = Faker()
+        email_data = self._create_test_email_data(fake)
+
+        # Act: Execute the task
+        send_inner_email_task(
+            to=email_data["to"],
+            subject=email_data["subject"],
+            body=email_data["body"],
+            substitutions=email_data["substitutions"],
+        )
+
+        # Assert: Verify no processing occurred
+        mock_external_service_dependencies["render_template"].assert_not_called()
+        mock_external_service_dependencies["email_service"].send_raw_email.assert_not_called()
+
+    def test_send_inner_email_template_rendering_error(
+        self, db_session_with_containers, mock_external_service_dependencies
+    ):
+        """
+        Test email sending when template rendering fails.
+
+        This test verifies:
+        - Exception handling during template rendering
+        - No email service calls when template fails
+        """
+        # Arrange: Setup template rendering to raise an exception
+        mock_external_service_dependencies["render_template"].side_effect = Exception("Template rendering failed")
+
+        fake = Faker()
+        email_data = self._create_test_email_data(fake)
+
+        # Act: Execute the task
+        send_inner_email_task(
+            to=email_data["to"],
+            subject=email_data["subject"],
+            body=email_data["body"],
+            substitutions=email_data["substitutions"],
+        )
+
+        # Assert: Verify template rendering was attempted
+        mock_external_service_dependencies["render_template"].assert_called_once()
+
+        # Verify no email service calls due to exception
+        mock_external_service_dependencies["email_service"].send_raw_email.assert_not_called()
+
+    def test_send_inner_email_service_error(self, db_session_with_containers, mock_external_service_dependencies):
+        """
+        Test email sending when email service fails.
+
+        This test verifies:
+        - Exception handling during email sending
+        - Graceful error handling
+        """
+        # Arrange: Setup email service to raise an exception
+        mock_external_service_dependencies["email_service"].send_raw_email.side_effect = Exception(
+            "Email service failed"
+        )
+
+        fake = Faker()
+        email_data = self._create_test_email_data(fake)
+
+        # Act: Execute the task
+        send_inner_email_task(
+            to=email_data["to"],
+            subject=email_data["subject"],
+            body=email_data["body"],
+            substitutions=email_data["substitutions"],
+        )
+
+        # Assert: Verify template rendering occurred
+        mock_external_service_dependencies["render_template"].assert_called_once()
+
+        # Verify email service was called (and failed)
+        mock_email_service = mock_external_service_dependencies["email_service"]
+        mock_email_service.send_raw_email.assert_called_once_with(
+            to=email_data["to"],
+            subject=email_data["subject"],
+            html_content="<html>Test email content</html>",
+        )

api/tests/test_containers_integration_tests/tasks/test_mail_invite_member_task.py

@@ -0,0 +1,543 @@
+"""
+Integration tests for mail_invite_member_task using testcontainers.
+
+This module provides integration tests for the invite member email task
+using TestContainers infrastructure. The tests ensure that the task properly sends
+invitation emails with internationalization support, handles error scenarios,
+and integrates correctly with the database and Redis for token management.
+
+All tests use the testcontainers infrastructure to ensure proper database isolation
+and realistic testing scenarios with actual PostgreSQL and Redis instances.
+"""
+
+import json
+import uuid
+from datetime import UTC, datetime
+from unittest.mock import MagicMock, patch
+
+import pytest
+from faker import Faker
+
+from extensions.ext_redis import redis_client
+from libs.email_i18n import EmailType
+from models.account import Account, AccountStatus, Tenant, TenantAccountJoin, TenantAccountRole
+from tasks.mail_invite_member_task import send_invite_member_mail_task
+
+
+class TestMailInviteMemberTask:
+    """
+    Integration tests for send_invite_member_mail_task using testcontainers.
+
+    This test class covers the core functionality of the invite member email task:
+    - Email sending with proper internationalization
+    - Template context generation and URL construction
+    - Error handling for failure scenarios
+    - Integration with Redis for token validation
+    - Mail service initialization checks
+    - Real database integration with actual invitation flow
+
+    All tests use the testcontainers infrastructure to ensure proper database isolation
+    and realistic testing environment with actual database and Redis interactions.
+    """
+
+    @pytest.fixture(autouse=True)
+    def cleanup_database(self, db_session_with_containers):
+        """Clean up database before each test to ensure isolation."""
+        # Clear all test data
+        db_session_with_containers.query(TenantAccountJoin).delete()
+        db_session_with_containers.query(Tenant).delete()
+        db_session_with_containers.query(Account).delete()
+        db_session_with_containers.commit()
+
+        # Clear Redis cache
+        redis_client.flushdb()
+
+    @pytest.fixture
+    def mock_external_service_dependencies(self):
+        """Mock setup for external service dependencies."""
+        with (
+            patch("tasks.mail_invite_member_task.mail") as mock_mail,
+            patch("tasks.mail_invite_member_task.get_email_i18n_service") as mock_email_service,
+            patch("tasks.mail_invite_member_task.dify_config") as mock_config,
+        ):
+            # Setup mail service mock
+            mock_mail.is_inited.return_value = True
+
+            # Setup email service mock
+            mock_email_service_instance = MagicMock()
+            mock_email_service_instance.send_email.return_value = None
+            mock_email_service.return_value = mock_email_service_instance
+
+            # Setup config mock
+            mock_config.CONSOLE_WEB_URL = "https://console.dify.ai"
+
+            yield {
+                "mail": mock_mail,
+                "email_service": mock_email_service_instance,
+                "config": mock_config,
+            }
+
+    def _create_test_account_and_tenant(self, db_session_with_containers):
+        """
+        Helper method to create a test account and tenant for testing.
+
+        Args:
+            db_session_with_containers: Database session from testcontainers infrastructure
+
+        Returns:
+            tuple: (Account, Tenant) created instances
+        """
+        fake = Faker()
+
+        # Create account
+        account = Account(
+            email=fake.email(),
+            name=fake.name(),
+            password=fake.password(),
+            interface_language="en-US",
+            status=AccountStatus.ACTIVE.value,
+            created_at=datetime.now(UTC),
+            updated_at=datetime.now(UTC),
+        )
+        db_session_with_containers.add(account)
+        db_session_with_containers.commit()
+        db_session_with_containers.refresh(account)
+
+        # Create tenant
+        tenant = Tenant(
+            name=fake.company(),
+            created_at=datetime.now(UTC),
+            updated_at=datetime.now(UTC),
+        )
+        db_session_with_containers.add(tenant)
+        db_session_with_containers.commit()
+        db_session_with_containers.refresh(tenant)
+
+        # Create tenant member relationship
+        tenant_join = TenantAccountJoin(
+            tenant_id=tenant.id,
+            account_id=account.id,
+            role=TenantAccountRole.OWNER.value,
+            created_at=datetime.now(UTC),
+        )
+        db_session_with_containers.add(tenant_join)
+        db_session_with_containers.commit()
+
+        return account, tenant
+
+    def _create_invitation_token(self, tenant, account):
+        """
+        Helper method to create a valid invitation token in Redis.
+
+        Args:
+            tenant: Tenant instance
+            account: Account instance
+
+        Returns:
+            str: Generated invitation token
+        """
+        token = str(uuid.uuid4())
+        invitation_data = {
+            "account_id": account.id,
+            "email": account.email,
+            "workspace_id": tenant.id,
+        }
+        cache_key = f"member_invite:token:{token}"
+        redis_client.setex(cache_key, 24 * 60 * 60, json.dumps(invitation_data))  # 24 hours
+        return token
+
+    def _create_pending_account_for_invitation(self, db_session_with_containers, email, tenant):
+        """
+        Helper method to create a pending account for invitation testing.
+
+        Args:
+            db_session_with_containers: Database session
+            email: Email address for the account
+            tenant: Tenant instance
+
+        Returns:
+            Account: Created pending account
+        """
+        account = Account(
+            email=email,
+            name=email.split("@")[0],
+            password="",
+            interface_language="en-US",
+            status=AccountStatus.PENDING.value,
+            created_at=datetime.now(UTC),
+            updated_at=datetime.now(UTC),
+        )
+        db_session_with_containers.add(account)
+        db_session_with_containers.commit()
+        db_session_with_containers.refresh(account)
+
+        # Create tenant member relationship
+        tenant_join = TenantAccountJoin(
+            tenant_id=tenant.id,
+            account_id=account.id,
+            role=TenantAccountRole.NORMAL.value,
+            created_at=datetime.now(UTC),
+        )
+        db_session_with_containers.add(tenant_join)
+        db_session_with_containers.commit()
+
+        return account
+
+    def test_send_invite_member_mail_success(self, db_session_with_containers, mock_external_service_dependencies):
+        """
+        Test successful invitation email sending with all parameters.
+
+        This test verifies:
+        - Email service is called with correct parameters
+        - Template context includes all required fields
+        - URL is constructed correctly with token
+        - Performance logging is recorded
+        - No exceptions are raised
+        """
+        # Arrange: Create test data
+        inviter, tenant = self._create_test_account_and_tenant(db_session_with_containers)
+        invitee_email = "test@example.com"
+        language = "en-US"
+        token = self._create_invitation_token(tenant, inviter)
+        inviter_name = inviter.name
+        workspace_name = tenant.name
+
+        # Act: Execute the task
+        send_invite_member_mail_task(
+            language=language,
+            to=invitee_email,
+            token=token,
+            inviter_name=inviter_name,
+            workspace_name=workspace_name,
+        )
+
+        # Assert: Verify email service was called correctly
+        mock_email_service = mock_external_service_dependencies["email_service"]
+        mock_email_service.send_email.assert_called_once()
+
+        # Verify call arguments
+        call_args = mock_email_service.send_email.call_args
+        assert call_args[1]["email_type"] == EmailType.INVITE_MEMBER
+        assert call_args[1]["language_code"] == language
+        assert call_args[1]["to"] == invitee_email
+
+        # Verify template context
+        template_context = call_args[1]["template_context"]
+        assert template_context["to"] == invitee_email
+        assert template_context["inviter_name"] == inviter_name
+        assert template_context["workspace_name"] == workspace_name
+        assert template_context["url"] == f"https://console.dify.ai/activate?token={token}"
+
+    def test_send_invite_member_mail_different_languages(
+        self, db_session_with_containers, mock_external_service_dependencies
+    ):
+        """
+        Test invitation email sending with different language codes.
+
+        This test verifies:
+        - Email service handles different language codes correctly
+        - Template context is passed correctly for each language
+        - No language-specific errors occur
+        """
+        # Arrange: Create test data
+        inviter, tenant = self._create_test_account_and_tenant(db_session_with_containers)
+        token = self._create_invitation_token(tenant, inviter)
+
+        test_languages = ["en-US", "zh-CN", "ja-JP", "fr-FR", "de-DE", "es-ES"]
+
+        for language in test_languages:
+            # Act: Execute the task with different language
+            send_invite_member_mail_task(
+                language=language,
+                to="test@example.com",
+                token=token,
+                inviter_name=inviter.name,
+                workspace_name=tenant.name,
+            )
+
+            # Assert: Verify language code was passed correctly
+            mock_email_service = mock_external_service_dependencies["email_service"]
+            call_args = mock_email_service.send_email.call_args
+            assert call_args[1]["language_code"] == language
+
+    def test_send_invite_member_mail_mail_not_initialized(
+        self, db_session_with_containers, mock_external_service_dependencies
+    ):
+        """
+        Test behavior when mail service is not initialized.
+
+        This test verifies:
+        - Task returns early when mail is not initialized
+        - Email service is not called
+        - No exceptions are raised
+        """
+        # Arrange: Setup mail service as not initialized
+        mock_mail = mock_external_service_dependencies["mail"]
+        mock_mail.is_inited.return_value = False
+
+        # Act: Execute the task
+        result = send_invite_member_mail_task(
+            language="en-US",
+            to="test@example.com",
+            token="test-token",
+            inviter_name="Test User",
+            workspace_name="Test Workspace",
+        )
+
+        # Assert: Verify early return
+        assert result is None
+        mock_email_service = mock_external_service_dependencies["email_service"]
+        mock_email_service.send_email.assert_not_called()
+
+    def test_send_invite_member_mail_email_service_exception(
+        self, db_session_with_containers, mock_external_service_dependencies
+    ):
+        """
+        Test error handling when email service raises an exception.
+
+        This test verifies:
+        - Exception is caught and logged
+        - Task completes without raising exception
+        - Error logging is performed
+        """
+        # Arrange: Setup email service to raise exception
+        mock_email_service = mock_external_service_dependencies["email_service"]
+        mock_email_service.send_email.side_effect = Exception("Email service failed")
+
+        # Act & Assert: Execute task and verify exception is handled
+        with patch("tasks.mail_invite_member_task.logger") as mock_logger:
+            send_invite_member_mail_task(
+                language="en-US",
+                to="test@example.com",
+                token="test-token",
+                inviter_name="Test User",
+                workspace_name="Test Workspace",
+            )
+
+            # Verify error was logged
+            mock_logger.exception.assert_called_once()
+            error_call = mock_logger.exception.call_args[0][0]
+            assert "Send invite member mail to %s failed" in error_call
+
+    def test_send_invite_member_mail_template_context_validation(
+        self, db_session_with_containers, mock_external_service_dependencies
+    ):
+        """
+        Test template context contains all required fields for email rendering.
+
+        This test verifies:
+        - All required template context fields are present
+        - Field values match expected data
+        - URL construction is correct
+        - No missing or None values in context
+        """
+        # Arrange: Create test data with specific values
+        inviter, tenant = self._create_test_account_and_tenant(db_session_with_containers)
+        token = "test-token-123"
+        invitee_email = "invitee@example.com"
+        inviter_name = "John Doe"
+        workspace_name = "Acme Corp"
+
+        # Act: Execute the task
+        send_invite_member_mail_task(
+            language="en-US",
+            to=invitee_email,
+            token=token,
+            inviter_name=inviter_name,
+            workspace_name=workspace_name,
+        )
+
+        # Assert: Verify template context
+        mock_email_service = mock_external_service_dependencies["email_service"]
+        call_args = mock_email_service.send_email.call_args
+        template_context = call_args[1]["template_context"]
+
+        # Verify all required fields are present
+        required_fields = ["to", "inviter_name", "workspace_name", "url"]
+        for field in required_fields:
+            assert field in template_context
+            assert template_context[field] is not None
+            assert template_context[field] != ""
+
+        # Verify specific values
+        assert template_context["to"] == invitee_email
+        assert template_context["inviter_name"] == inviter_name
+        assert template_context["workspace_name"] == workspace_name
+        assert template_context["url"] == f"https://console.dify.ai/activate?token={token}"
+
+    def test_send_invite_member_mail_integration_with_redis_token(
+        self, db_session_with_containers, mock_external_service_dependencies
+    ):
+        """
+        Test integration with Redis token validation.
+
+        This test verifies:
+        - Task works with real Redis token data
+        - Token validation can be performed after email sending
+        - Redis data integrity is maintained
+        """
+        # Arrange: Create test data and store token in Redis
+        inviter, tenant = self._create_test_account_and_tenant(db_session_with_containers)
+        token = self._create_invitation_token(tenant, inviter)
+
+        # Verify token exists in Redis before sending email
+        cache_key = f"member_invite:token:{token}"
+        assert redis_client.exists(cache_key) == 1
+
+        # Act: Execute the task
+        send_invite_member_mail_task(
+            language="en-US",
+            to=inviter.email,
+            token=token,
+            inviter_name=inviter.name,
+            workspace_name=tenant.name,
+        )
+
+        # Assert: Verify token still exists after email sending
+        assert redis_client.exists(cache_key) == 1
+
+        # Verify token data integrity
+        token_data = redis_client.get(cache_key)
+        assert token_data is not None
+        invitation_data = json.loads(token_data)
+        assert invitation_data["account_id"] == inviter.id
+        assert invitation_data["email"] == inviter.email
+        assert invitation_data["workspace_id"] == tenant.id
+
+    def test_send_invite_member_mail_with_special_characters(
+        self, db_session_with_containers, mock_external_service_dependencies
+    ):
+        """
+        Test email sending with special characters in names and workspace names.
+
+        This test verifies:
+        - Special characters are handled correctly in template context
+        - Email service receives properly formatted data
+        - No encoding issues occur
+        """
+        # Arrange: Create test data with special characters
+        inviter, tenant = self._create_test_account_and_tenant(db_session_with_containers)
+        token = self._create_invitation_token(tenant, inviter)
+
+        special_cases = [
+            ("John O'Connor", "Acme & Co."),
+            ("José María", "Café & Restaurant"),
+            ("李小明", "北京科技有限公司"),
+            ("François & Marie", "L'École Internationale"),
+            ("Александр", "ООО Технологии"),
+            ("محمد أحمد", "شركة التقنية المتقدمة"),
+        ]
+
+        for inviter_name, workspace_name in special_cases:
+            # Act: Execute the task
+            send_invite_member_mail_task(
+                language="en-US",
+                to="test@example.com",
+                token=token,
+                inviter_name=inviter_name,
+                workspace_name=workspace_name,
+            )
+
+            # Assert: Verify special characters are preserved
+            mock_email_service = mock_external_service_dependencies["email_service"]
+            call_args = mock_email_service.send_email.call_args
+            template_context = call_args[1]["template_context"]
+
+            assert template_context["inviter_name"] == inviter_name
+            assert template_context["workspace_name"] == workspace_name
+
+    def test_send_invite_member_mail_real_database_integration(
+        self, db_session_with_containers, mock_external_service_dependencies
+    ):
+        """
+        Test real database integration with actual invitation flow.
+
+        This test verifies:
+        - Task works with real database entities
+        - Account and tenant relationships are properly maintained
+        - Database state is consistent after email sending
+        - Real invitation data flow is tested
+        """
+        # Arrange: Create real database entities
+        inviter, tenant = self._create_test_account_and_tenant(db_session_with_containers)
+        invitee_email = "newmember@example.com"
+
+        # Create a pending account for invitation (simulating real invitation flow)
+        pending_account = self._create_pending_account_for_invitation(db_session_with_containers, invitee_email, tenant)
+
+        # Create invitation token with real account data
+        token = self._create_invitation_token(tenant, pending_account)
+
+        # Act: Execute the task with real data
+        send_invite_member_mail_task(
+            language="en-US",
+            to=invitee_email,
+            token=token,
+            inviter_name=inviter.name,
+            workspace_name=tenant.name,
+        )
+
+        # Assert: Verify email service was called with real data
+        mock_email_service = mock_external_service_dependencies["email_service"]
+        mock_email_service.send_email.assert_called_once()
+
+        # Verify database state is maintained
+        db_session_with_containers.refresh(pending_account)
+        db_session_with_containers.refresh(tenant)
+
+        assert pending_account.status == AccountStatus.PENDING.value
+        assert pending_account.email == invitee_email
+        assert tenant.name is not None
+
+        # Verify tenant relationship exists
+        tenant_join = (
+            db_session_with_containers.query(TenantAccountJoin)
+            .filter_by(tenant_id=tenant.id, account_id=pending_account.id)
+            .first()
+        )
+        assert tenant_join is not None
+        assert tenant_join.role == TenantAccountRole.NORMAL.value
+
+    def test_send_invite_member_mail_token_lifecycle_management(
+        self, db_session_with_containers, mock_external_service_dependencies
+    ):
+        """
+        Test token lifecycle management and validation.
+
+        This test verifies:
+        - Token is properly stored in Redis with correct TTL
+        - Token data structure is correct
+        - Token can be retrieved and validated after email sending
+        - Token expiration is handled correctly
+        """
+        # Arrange: Create test data
+        inviter, tenant = self._create_test_account_and_tenant(db_session_with_containers)
+        token = self._create_invitation_token(tenant, inviter)
+
+        # Act: Execute the task
+        send_invite_member_mail_task(
+            language="en-US",
+            to=inviter.email,
+            token=token,
+            inviter_name=inviter.name,
+            workspace_name=tenant.name,
+        )
+
+        # Assert: Verify token lifecycle
+        cache_key = f"member_invite:token:{token}"
+
+        # Token should still exist
+        assert redis_client.exists(cache_key) == 1
+
+        # Token should have correct TTL (approximately 24 hours)
+        ttl = redis_client.ttl(cache_key)
+        assert 23 * 60 * 60 <= ttl <= 24 * 60 * 60  # Allow some tolerance
+
+        # Token data should be valid
+        token_data = redis_client.get(cache_key)
+        assert token_data is not None
+
+        invitation_data = json.loads(token_data)
+        assert invitation_data["account_id"] == inviter.id
+        assert invitation_data["email"] == inviter.email
+        assert invitation_data["workspace_id"] == tenant.id

api/tests/unit_tests/configs/test_dify_config.py

@@ -33,6 +33,7 @@ def test_dify_config(monkeypatch: pytest.MonkeyPatch):
     assert config.EDITION == "SELF_HOSTED"
     assert config.API_COMPRESSION_ENABLED is False
     assert config.SENTRY_TRACES_SAMPLE_RATE == 1.0
+    assert config.TEMPLATE_TRANSFORM_MAX_LENGTH == 400_000
 
     # annotated field with default value
     assert config.HTTP_REQUEST_MAX_READ_TIMEOUT == 600

api/tests/unit_tests/controllers/console/app/test_description_validation.py

@@ -1,174 +1,53 @@
 import pytest
 
-from controllers.console.app.app import _validate_description_length as app_validate
-from controllers.console.datasets.datasets import _validate_description_length as dataset_validate
-from controllers.service_api.dataset.dataset import _validate_description_length as service_dataset_validate
+from libs.validators import validate_description_length
 
 
 class TestDescriptionValidationUnit:
-    """Unit tests for description validation functions in App and Dataset APIs"""
+    """Unit tests for the centralized description validation function."""
 
-    def test_app_validate_description_length_valid(self):
-        """Test App validation function with valid descriptions"""
+    def test_validate_description_length_valid(self):
+        """Test validation function with valid descriptions."""
         # Empty string should be valid
-        assert app_validate("") == ""
+        assert validate_description_length("") == ""
 
         # None should be valid
-        assert app_validate(None) is None
+        assert validate_description_length(None) is None
 
         # Short description should be valid
         short_desc = "Short description"
-        assert app_validate(short_desc) == short_desc
+        assert validate_description_length(short_desc) == short_desc
 
         # Exactly 400 characters should be valid
         exactly_400 = "x" * 400
-        assert app_validate(exactly_400) == exactly_400
+        assert validate_description_length(exactly_400) == exactly_400
 
         # Just under limit should be valid
         just_under = "x" * 399
-        assert app_validate(just_under) == just_under
+        assert validate_description_length(just_under) == just_under
 
-    def test_app_validate_description_length_invalid(self):
-        """Test App validation function with invalid descriptions"""
+    def test_validate_description_length_invalid(self):
+        """Test validation function with invalid descriptions."""
         # 401 characters should fail
         just_over = "x" * 401
         with pytest.raises(ValueError) as exc_info:
-            app_validate(just_over)
+            validate_description_length(just_over)
         assert "Description cannot exceed 400 characters." in str(exc_info.value)
 
         # 500 characters should fail
         way_over = "x" * 500
         with pytest.raises(ValueError) as exc_info:
-            app_validate(way_over)
+            validate_description_length(way_over)
         assert "Description cannot exceed 400 characters." in str(exc_info.value)
 
         # 1000 characters should fail
         very_long = "x" * 1000
         with pytest.raises(ValueError) as exc_info:
-            app_validate(very_long)
+            validate_description_length(very_long)
         assert "Description cannot exceed 400 characters." in str(exc_info.value)
 
-    def test_dataset_validate_description_length_valid(self):
-        """Test Dataset validation function with valid descriptions"""
-        # Empty string should be valid
-        assert dataset_validate("") == ""
-
-        # Short description should be valid
-        short_desc = "Short description"
-        assert dataset_validate(short_desc) == short_desc
-
-        # Exactly 400 characters should be valid
-        exactly_400 = "x" * 400
-        assert dataset_validate(exactly_400) == exactly_400
-
-        # Just under limit should be valid
-        just_under = "x" * 399
-        assert dataset_validate(just_under) == just_under
-
-    def test_dataset_validate_description_length_invalid(self):
-        """Test Dataset validation function with invalid descriptions"""
-        # 401 characters should fail
-        just_over = "x" * 401
-        with pytest.raises(ValueError) as exc_info:
-            dataset_validate(just_over)
-        assert "Description cannot exceed 400 characters." in str(exc_info.value)
-
-        # 500 characters should fail
-        way_over = "x" * 500
-        with pytest.raises(ValueError) as exc_info:
-            dataset_validate(way_over)
-        assert "Description cannot exceed 400 characters." in str(exc_info.value)
-
-    def test_service_dataset_validate_description_length_valid(self):
-        """Test Service Dataset validation function with valid descriptions"""
-        # Empty string should be valid
-        assert service_dataset_validate("") == ""
-
-        # None should be valid
-        assert service_dataset_validate(None) is None
-
-        # Short description should be valid
-        short_desc = "Short description"
-        assert service_dataset_validate(short_desc) == short_desc
-
-        # Exactly 400 characters should be valid
-        exactly_400 = "x" * 400
-        assert service_dataset_validate(exactly_400) == exactly_400
-
-        # Just under limit should be valid
-        just_under = "x" * 399
-        assert service_dataset_validate(just_under) == just_under
-
-    def test_service_dataset_validate_description_length_invalid(self):
-        """Test Service Dataset validation function with invalid descriptions"""
-        # 401 characters should fail
-        just_over = "x" * 401
-        with pytest.raises(ValueError) as exc_info:
-            service_dataset_validate(just_over)
-        assert "Description cannot exceed 400 characters." in str(exc_info.value)
-
-        # 500 characters should fail
-        way_over = "x" * 500
-        with pytest.raises(ValueError) as exc_info:
-            service_dataset_validate(way_over)
-        assert "Description cannot exceed 400 characters." in str(exc_info.value)
-
-    def test_app_dataset_validation_consistency(self):
-        """Test that App and Dataset validation functions behave identically"""
-        test_cases = [
-            "",  # Empty string
-            "Short description",  # Normal description
-            "x" * 100,  # Medium description
-            "x" * 400,  # Exactly at limit
-        ]
-
-        # Test valid cases produce same results
-        for test_desc in test_cases:
-            assert app_validate(test_desc) == dataset_validate(test_desc) == service_dataset_validate(test_desc)
-
-        # Test invalid cases produce same errors
-        invalid_cases = [
-            "x" * 401,  # Just over limit
-            "x" * 500,  # Way over limit
-            "x" * 1000,  # Very long
-        ]
-
-        for invalid_desc in invalid_cases:
-            app_error = None
-            dataset_error = None
-            service_dataset_error = None
-
-            # Capture App validation error
-            try:
-                app_validate(invalid_desc)
-            except ValueError as e:
-                app_error = str(e)
-
-            # Capture Dataset validation error
-            try:
-                dataset_validate(invalid_desc)
-            except ValueError as e:
-                dataset_error = str(e)
-
-            # Capture Service Dataset validation error
-            try:
-                service_dataset_validate(invalid_desc)
-            except ValueError as e:
-                service_dataset_error = str(e)
-
-            # All should produce errors
-            assert app_error is not None, f"App validation should fail for {len(invalid_desc)} characters"
-            assert dataset_error is not None, f"Dataset validation should fail for {len(invalid_desc)} characters"
-            error_msg = f"Service Dataset validation should fail for {len(invalid_desc)} characters"
-            assert service_dataset_error is not None, error_msg
-
-            # Errors should be identical
-            error_msg = f"Error messages should be identical for {len(invalid_desc)} characters"
-            assert app_error == dataset_error == service_dataset_error, error_msg
-            assert app_error == "Description cannot exceed 400 characters."
-
     def test_boundary_values(self):
-        """Test boundary values around the 400 character limit"""
+        """Test boundary values around the 400 character limit."""
         boundary_tests = [
             (0, True),  # Empty
             (1, True),  # Minimum
@@ -184,69 +63,45 @@ class TestDescriptionValidationUnit:
 
             if should_pass:
                 # Should not raise exception
-                assert app_validate(test_desc) == test_desc
-                assert dataset_validate(test_desc) == test_desc
-                assert service_dataset_validate(test_desc) == test_desc
+                assert validate_description_length(test_desc) == test_desc
             else:
                 # Should raise ValueError
                 with pytest.raises(ValueError):
-                    app_validate(test_desc)
-                with pytest.raises(ValueError):
-                    dataset_validate(test_desc)
-                with pytest.raises(ValueError):
-                    service_dataset_validate(test_desc)
+                    validate_description_length(test_desc)
 
     def test_special_characters(self):
         """Test validation with special characters, Unicode, etc."""
         # Unicode characters
         unicode_desc = "测试描述" * 100  # Chinese characters
         if len(unicode_desc) <= 400:
-            assert app_validate(unicode_desc) == unicode_desc
-            assert dataset_validate(unicode_desc) == unicode_desc
-            assert service_dataset_validate(unicode_desc) == unicode_desc
+            assert validate_description_length(unicode_desc) == unicode_desc
 
         # Special characters
         special_desc = "Special chars: !@#$%^&*()_+-=[]{}|;':\",./<>?" * 10
         if len(special_desc) <= 400:
-            assert app_validate(special_desc) == special_desc
-            assert dataset_validate(special_desc) == special_desc
-            assert service_dataset_validate(special_desc) == special_desc
+            assert validate_description_length(special_desc) == special_desc
 
         # Mixed content
         mixed_desc = "Mixed content: 测试 123 !@# " * 15
         if len(mixed_desc) <= 400:
-            assert app_validate(mixed_desc) == mixed_desc
-            assert dataset_validate(mixed_desc) == mixed_desc
-            assert service_dataset_validate(mixed_desc) == mixed_desc
+            assert validate_description_length(mixed_desc) == mixed_desc
         elif len(mixed_desc) > 400:
             with pytest.raises(ValueError):
-                app_validate(mixed_desc)
-            with pytest.raises(ValueError):
-                dataset_validate(mixed_desc)
-            with pytest.raises(ValueError):
-                service_dataset_validate(mixed_desc)
+                validate_description_length(mixed_desc)
 
     def test_whitespace_handling(self):
-        """Test validation with various whitespace scenarios"""
+        """Test validation with various whitespace scenarios."""
         # Leading/trailing whitespace
         whitespace_desc = "   Description with whitespace   "
         if len(whitespace_desc) <= 400:
-            assert app_validate(whitespace_desc) == whitespace_desc
-            assert dataset_validate(whitespace_desc) == whitespace_desc
-            assert service_dataset_validate(whitespace_desc) == whitespace_desc
+            assert validate_description_length(whitespace_desc) == whitespace_desc
 
         # Newlines and tabs
         multiline_desc = "Line 1\nLine 2\tTabbed content"
         if len(multiline_desc) <= 400:
-            assert app_validate(multiline_desc) == multiline_desc
-            assert dataset_validate(multiline_desc) == multiline_desc
-            assert service_dataset_validate(multiline_desc) == multiline_desc
+            assert validate_description_length(multiline_desc) == multiline_desc
 
         # Only whitespace over limit
         only_spaces = " " * 401
         with pytest.raises(ValueError):
-            app_validate(only_spaces)
-        with pytest.raises(ValueError):
-            dataset_validate(only_spaces)
-        with pytest.raises(ValueError):
-            service_dataset_validate(only_spaces)
+            validate_description_length(only_spaces)

api/tests/unit_tests/extensions/storage/test_supabase_storage.py

@@ -172,73 +172,31 @@ class TestSupabaseStorage:
         assert "test-bucket" in [call[0][0] for call in mock_client.storage.from_.call_args_list if call[0]]
         mock_client.storage.from_().download.assert_called_with("test.txt")
 
-    def test_exists_with_list_containing_items(self, storage_with_mock_client):
-        """Test exists returns True when list() returns items (using len() > 0)."""
+    def test_exists_returns_true_when_file_found(self, storage_with_mock_client):
+        """Test exists returns True when list() returns items."""
         storage, mock_client = storage_with_mock_client
 
-        # Mock list return with special object that has count() method
-        mock_list_result = Mock()
-        mock_list_result.count.return_value = 1
-        mock_client.storage.from_().list.return_value = mock_list_result
+        mock_client.storage.from_().list.return_value = [{"name": "test.txt"}]
 
         result = storage.exists("test.txt")
 
         assert result is True
-        # from_ gets called during init too, so just check it was called with the right bucket
         assert "test-bucket" in [call[0][0] for call in mock_client.storage.from_.call_args_list if call[0]]
-        mock_client.storage.from_().list.assert_called_with("test.txt")
+        mock_client.storage.from_().list.assert_called_with(path="test.txt")
 
-    def test_exists_with_count_method_greater_than_zero(self, storage_with_mock_client):
-        """Test exists returns True when list result has count() > 0."""
+    def test_exists_returns_false_when_file_not_found(self, storage_with_mock_client):
+        """Test exists returns False when list() returns an empty list."""
         storage, mock_client = storage_with_mock_client
 
-        # Mock list return with count() method
-        mock_list_result = Mock()
-        mock_list_result.count.return_value = 1
-        mock_client.storage.from_().list.return_value = mock_list_result
-
-        result = storage.exists("test.txt")
-
-        assert result is True
-        # Verify the correct calls were made
-        assert "test-bucket" in [call[0][0] for call in mock_client.storage.from_.call_args_list if call[0]]
-        mock_client.storage.from_().list.assert_called_with("test.txt")
-        mock_list_result.count.assert_called()
-
-    def test_exists_with_count_method_zero(self, storage_with_mock_client):
-        """Test exists returns False when list result has count() == 0."""
-        storage, mock_client = storage_with_mock_client
-
-        # Mock list return with count() method returning 0
-        mock_list_result = Mock()
-        mock_list_result.count.return_value = 0
-        mock_client.storage.from_().list.return_value = mock_list_result
+        mock_client.storage.from_().list.return_value = []
 
         result = storage.exists("test.txt")
 
         assert result is False
-        # Verify the correct calls were made
         assert "test-bucket" in [call[0][0] for call in mock_client.storage.from_.call_args_list if call[0]]
-        mock_client.storage.from_().list.assert_called_with("test.txt")
-        mock_list_result.count.assert_called()
+        mock_client.storage.from_().list.assert_called_with(path="test.txt")
 
-    def test_exists_with_empty_list(self, storage_with_mock_client):
-        """Test exists returns False when list() returns empty list."""
-        storage, mock_client = storage_with_mock_client
-
-        # Mock list return with special object that has count() method returning 0
-        mock_list_result = Mock()
-        mock_list_result.count.return_value = 0
-        mock_client.storage.from_().list.return_value = mock_list_result
-
-        result = storage.exists("test.txt")
-
-        assert result is False
-        # Verify the correct calls were made
-        assert "test-bucket" in [call[0][0] for call in mock_client.storage.from_.call_args_list if call[0]]
-        mock_client.storage.from_().list.assert_called_with("test.txt")
-
-    def test_delete_calls_remove_with_filename(self, storage_with_mock_client):
+    def test_delete_calls_remove_with_filename_in_list(self, storage_with_mock_client):
         """Test delete calls remove([...]) (some client versions require a list)."""
         storage, mock_client = storage_with_mock_client
 
@@ -247,7 +205,7 @@ class TestSupabaseStorage:
         storage.delete(filename)
 
         mock_client.storage.from_.assert_called_once_with("test-bucket")
-        mock_client.storage.from_().remove.assert_called_once_with(filename)
+        mock_client.storage.from_().remove.assert_called_once_with([filename])
 
     def test_bucket_exists_returns_true_when_bucket_found(self):
         """Test bucket_exists returns True when bucket is found in list."""

api/tests/unit_tests/oss/volcengine_tos/test_volcengine_tos.py

@@ -1,3 +1,5 @@
+from unittest.mock import patch
+
 import pytest
 from tos import TosClientV2  # type: ignore
 
@@ -13,7 +15,13 @@ class TestVolcengineTos(BaseStorageTest):
     @pytest.fixture(autouse=True)
     def setup_method(self, setup_volcengine_tos_mock):
         """Executed before each test method."""
-        self.storage = VolcengineTosStorage()
+        with patch("extensions.storage.volcengine_tos_storage.dify_config") as mock_config:
+            mock_config.VOLCENGINE_TOS_ACCESS_KEY = "test_access_key"
+            mock_config.VOLCENGINE_TOS_SECRET_KEY = "test_secret_key"
+            mock_config.VOLCENGINE_TOS_ENDPOINT = "test_endpoint"
+            mock_config.VOLCENGINE_TOS_REGION = "test_region"
+            self.storage = VolcengineTosStorage()
+
         self.storage.bucket_name = get_example_bucket()
         self.storage.client = TosClientV2(
             ak="dify",

api/uv.lock

@@ -445,16 +445,17 @@ wheels = [
 
 [[package]]
 name = "azure-storage-blob"
-version = "12.13.0"
+version = "12.26.0"
 source = { registry = "https://pypi.org/simple" }
 dependencies = [
     { name = "azure-core" },
     { name = "cryptography" },
-    { name = "msrest" },
+    { name = "isodate" },
+    { name = "typing-extensions" },
 ]
-sdist = { url = "https://files.pythonhosted.org/packages/b1/93/b13bf390e940a79a399981f75ac8d2e05a70112a95ebb7b41e9b752d2921/azure-storage-blob-12.13.0.zip", hash = "sha256:53f0d4cd32970ac9ff9b9753f83dd2fb3f9ac30e1d01e71638c436c509bfd884", size = 684838, upload-time = "2022-07-07T22:35:44.543Z" }
+sdist = { url = "https://files.pythonhosted.org/packages/96/95/3e3414491ce45025a1cde107b6ae72bf72049e6021597c201cd6a3029b9a/azure_storage_blob-12.26.0.tar.gz", hash = "sha256:5dd7d7824224f7de00bfeb032753601c982655173061e242f13be6e26d78d71f", size = 583332, upload-time = "2025-07-16T21:34:07.644Z" }
 wheels = [
-    { url = "https://files.pythonhosted.org/packages/0e/2a/b8246df35af68d64fb7292c93dbbde63cd25036f2f669a9d9ae59e518c76/azure_storage_blob-12.13.0-py3-none-any.whl", hash = "sha256:280a6ab032845bab9627582bee78a50497ca2f14772929b5c5ee8b4605af0cb3", size = 377309, upload-time = "2022-07-07T22:35:41.905Z" },
+    { url = "https://files.pythonhosted.org/packages/5b/64/63dbfdd83b31200ac58820a7951ddfdeed1fbee9285b0f3eae12d1357155/azure_storage_blob-12.26.0-py3-none-any.whl", hash = "sha256:8c5631b8b22b4f53ec5fff2f3bededf34cfef111e2af613ad42c9e6de00a77fe", size = 412907, upload-time = "2025-07-16T21:34:09.367Z" },
 ]
 
 [[package]]
@@ -1280,7 +1281,6 @@ version = "1.9.1"
 source = { virtual = "." }
 dependencies = [
     { name = "arize-phoenix-otel" },
-    { name = "authlib" },
     { name = "azure-identity" },
     { name = "beautifulsoup4" },
     { name = "boto3" },
@@ -1311,10 +1311,8 @@ dependencies = [
     { name = "json-repair" },
     { name = "langfuse" },
     { name = "langsmith" },
-    { name = "mailchimp-transactional" },
     { name = "markdown" },
     { name = "numpy" },
-    { name = "openai" },
     { name = "openpyxl" },
     { name = "opentelemetry-api" },
     { name = "opentelemetry-distro" },
@@ -1325,6 +1323,7 @@ dependencies = [
     { name = "opentelemetry-instrumentation" },
     { name = "opentelemetry-instrumentation-celery" },
     { name = "opentelemetry-instrumentation-flask" },
+    { name = "opentelemetry-instrumentation-httpx" },
     { name = "opentelemetry-instrumentation-redis" },
     { name = "opentelemetry-instrumentation-requests" },
     { name = "opentelemetry-instrumentation-sqlalchemy" },
@@ -1336,7 +1335,6 @@ dependencies = [
     { name = "opik" },
     { name = "packaging" },
     { name = "pandas", extra = ["excel", "output-formatting", "performance"] },
-    { name = "pandoc" },
     { name = "psycogreen" },
     { name = "psycopg2-binary" },
     { name = "pycryptodome" },
@@ -1474,7 +1472,6 @@ vdb = [
 [package.metadata]
 requires-dist = [
     { name = "arize-phoenix-otel", specifier = "~=0.9.2" },
-    { name = "authlib", specifier = "==1.6.4" },
     { name = "azure-identity", specifier = "==1.16.1" },
     { name = "beautifulsoup4", specifier = "==4.12.2" },
     { name = "boto3", specifier = "==1.35.99" },
@@ -1505,10 +1502,8 @@ requires-dist = [
     { name = "json-repair", specifier = ">=0.41.1" },
     { name = "langfuse", specifier = "~=2.51.3" },
     { name = "langsmith", specifier = "~=0.1.77" },
-    { name = "mailchimp-transactional", specifier = "~=1.0.50" },
     { name = "markdown", specifier = "~=3.5.1" },
     { name = "numpy", specifier = "~=1.26.4" },
-    { name = "openai", specifier = "~=1.61.0" },
     { name = "openpyxl", specifier = "~=3.1.5" },
     { name = "opentelemetry-api", specifier = "==1.27.0" },
     { name = "opentelemetry-distro", specifier = "==0.48b0" },
@@ -1519,6 +1514,7 @@ requires-dist = [
     { 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-requests", specifier = "==0.48b0" },
     { name = "opentelemetry-instrumentation-sqlalchemy", specifier = "==0.48b0" },
@@ -1530,7 +1526,6 @@ requires-dist = [
     { name = "opik", specifier = "~=1.7.25" },
     { name = "packaging", specifier = "~=23.2" },
     { name = "pandas", extras = ["excel", "output-formatting", "performance"], specifier = "~=2.2.2" },
-    { name = "pandoc", specifier = "~=2.4" },
     { name = "psycogreen", specifier = "~=1.0.2" },
     { name = "psycopg2-binary", specifier = "~=2.9.6" },
     { name = "pycryptodome", specifier = "==3.19.1" },
@@ -1625,10 +1620,10 @@ dev = [
     { name = "types-ujson", specifier = ">=5.10.0" },
 ]
 storage = [
-    { name = "azure-storage-blob", specifier = "==12.13.0" },
+    { name = "azure-storage-blob", specifier = "==12.26.0" },
     { name = "bce-python-sdk", specifier = "~=0.9.23" },
     { name = "cos-python-sdk-v5", specifier = "==1.9.38" },
-    { name = "esdk-obs-python", specifier = "==3.24.6.1" },
+    { name = "esdk-obs-python", specifier = "==3.25.8" },
     { name = "google-cloud-storage", specifier = "==2.16.0" },
     { name = "opendal", specifier = "~=0.46.0" },
     { name = "oss2", specifier = "==2.18.5" },
@@ -1779,12 +1774,14 @@ wheels = [
 
 [[package]]
 name = "esdk-obs-python"
-version = "3.24.6.1"
+version = "3.25.8"
 source = { registry = "https://pypi.org/simple" }
 dependencies = [
+    { name = "crcmod" },
     { name = "pycryptodome" },
+    { name = "requests" },
 ]
-sdist = { url = "https://files.pythonhosted.org/packages/f7/af/d83276f9e288bd6a62f44d67ae1eafd401028ba1b2b643ae4014b51da5bd/esdk-obs-python-3.24.6.1.tar.gz", hash = "sha256:c45fed143e99d9256c8560c1d78f651eae0d2e809d16e962f8b286b773c33bf0", size = 85798, upload-time = "2024-07-26T13:13:22.467Z" }
+sdist = { url = "https://files.pythonhosted.org/packages/40/99/52362d6e081a642d6de78f6ab53baa5e3f82f2386c48954e18ee7b4ab22b/esdk-obs-python-3.25.8.tar.gz", hash = "sha256:aeded00b27ecd5a25ffaec38a2cc9416b51923d48db96c663f1a735f859b5273", size = 96302, upload-time = "2025-09-01T11:35:20.432Z" }
 
 [[package]]
 name = "et-xmlfile"
@@ -3169,21 +3166,6 @@ wheels = [
     { url = "https://files.pythonhosted.org/packages/6c/e1/0686c91738f3e6c2e1a243e0fdd4371667c4d2e5009b0a3605806c2aa020/lz4-4.4.4-cp312-cp312-win_arm64.whl", hash = "sha256:2f4f2965c98ab254feddf6b5072854a6935adab7bc81412ec4fe238f07b85f62", size = 89736, upload-time = "2025-04-01T22:55:40.5Z" },
 ]
 
-[[package]]
-name = "mailchimp-transactional"
-version = "1.0.56"
-source = { registry = "https://pypi.org/simple" }
-dependencies = [
-    { name = "certifi" },
-    { name = "python-dateutil" },
-    { name = "requests" },
-    { name = "six" },
-    { name = "urllib3" },
-]
-wheels = [
-    { url = "https://files.pythonhosted.org/packages/5f/bc/cb60d02c00996839bbd87444a97d0ba5ac271b1a324001562afb8f685251/mailchimp_transactional-1.0.56-py3-none-any.whl", hash = "sha256:a76ea88b90a2d47d8b5134586aabbd3a96c459f6066d8886748ab59e50de36eb", size = 31660, upload-time = "2024-02-01T18:39:19.717Z" },
-]
-
 [[package]]
 name = "mako"
 version = "1.3.10"
@@ -3369,22 +3351,6 @@ wheels = [
     { url = "https://files.pythonhosted.org/packages/5e/75/bd9b7bb966668920f06b200e84454c8f3566b102183bc55c5473d96cb2b9/msal_extensions-1.3.1-py3-none-any.whl", hash = "sha256:96d3de4d034504e969ac5e85bae8106c8373b5c6568e4c8fa7af2eca9dbe6bca", size = 20583, upload-time = "2025-03-14T23:51:03.016Z" },
 ]
 
-[[package]]
-name = "msrest"
-version = "0.7.1"
-source = { registry = "https://pypi.org/simple" }
-dependencies = [
-    { name = "azure-core" },
-    { name = "certifi" },
-    { name = "isodate" },
-    { name = "requests" },
-    { name = "requests-oauthlib" },
-]
-sdist = { url = "https://files.pythonhosted.org/packages/68/77/8397c8fb8fc257d8ea0fa66f8068e073278c65f05acb17dcb22a02bfdc42/msrest-0.7.1.zip", hash = "sha256:6e7661f46f3afd88b75667b7187a92829924446c7ea1d169be8c4bb7eeb788b9", size = 175332, upload-time = "2022-06-13T22:41:25.111Z" }
-wheels = [
-    { url = "https://files.pythonhosted.org/packages/15/cf/f2966a2638144491f8696c27320d5219f48a072715075d168b31d3237720/msrest-0.7.1-py3-none-any.whl", hash = "sha256:21120a810e1233e5e6cc7fe40b474eeb4ec6f757a15d7cf86702c369f9567c32", size = 85384, upload-time = "2022-06-13T22:41:22.42Z" },
-]
-
 [[package]]
 name = "multidict"
 version = "6.6.4"
@@ -3914,6 +3880,21 @@ 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" },
 ]
 
+[[package]]
+name = "opentelemetry-instrumentation-httpx"
+version = "0.48b0"
+source = { registry = "https://pypi.org/simple" }
+dependencies = [
+    { name = "opentelemetry-api" },
+    { name = "opentelemetry-instrumentation" },
+    { name = "opentelemetry-semantic-conventions" },
+    { name = "opentelemetry-util-http" },
+]
+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" }
+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" },
+]
+
 [[package]]
 name = "opentelemetry-instrumentation-redis"
 version = "0.48b0"
@@ -4231,16 +4212,6 @@ wheels = [
     { url = "https://files.pythonhosted.org/packages/ec/f8/46141ba8c9d7064dc5008bfb4a6ae5bd3c30e4c61c28b5c5ed485bf358ba/pandas_stubs-2.2.3.250527-py3-none-any.whl", hash = "sha256:cd0a49a95b8c5f944e605be711042a4dd8550e2c559b43d70ba2c4b524b66163", size = 159683, upload-time = "2025-05-27T15:24:28.4Z" },
 ]
 
-[[package]]
-name = "pandoc"
-version = "2.4"
-source = { registry = "https://pypi.org/simple" }
-dependencies = [
-    { name = "plumbum" },
-    { name = "ply" },
-]
-sdist = { url = "https://files.pythonhosted.org/packages/10/9a/e3186e760c57ee5f1c27ea5cea577a0ff9abfca51eefcb4d9a4cd39aff2e/pandoc-2.4.tar.gz", hash = "sha256:ecd1f8cbb7f4180c6b5db4a17a7c1a74df519995f5f186ef81ce72a9cbd0dd9a", size = 34635, upload-time = "2024-08-07T14:33:58.016Z" }
-
 [[package]]
 name = "pathspec"
 version = "0.12.1"
@@ -4347,18 +4318,6 @@ wheels = [
     { url = "https://files.pythonhosted.org/packages/54/20/4d324d65cc6d9205fabedc306948156824eb9f0ee1633355a8f7ec5c66bf/pluggy-1.6.0-py3-none-any.whl", hash = "sha256:e920276dd6813095e9377c0bc5566d94c932c33b27a3e3945d8389c374dd4746", size = 20538, upload-time = "2025-05-15T12:30:06.134Z" },
 ]
 
-[[package]]
-name = "plumbum"
-version = "1.9.0"
-source = { registry = "https://pypi.org/simple" }
-dependencies = [
-    { name = "pywin32", marker = "platform_python_implementation != 'PyPy' and sys_platform == 'win32'" },
-]
-sdist = { url = "https://files.pythonhosted.org/packages/f0/5d/49ba324ad4ae5b1a4caefafbce7a1648540129344481f2ed4ef6bb68d451/plumbum-1.9.0.tar.gz", hash = "sha256:e640062b72642c3873bd5bdc3effed75ba4d3c70ef6b6a7b907357a84d909219", size = 319083, upload-time = "2024-10-05T05:59:27.059Z" }
-wheels = [
-    { url = "https://files.pythonhosted.org/packages/4f/9d/d03542c93bb3d448406731b80f39c3d5601282f778328c22c77d270f4ed4/plumbum-1.9.0-py3-none-any.whl", hash = "sha256:9fd0d3b0e8d86e4b581af36edf3f3bbe9d1ae15b45b8caab28de1bcb27aaa7f5", size = 127970, upload-time = "2024-10-05T05:59:25.102Z" },
-]
-
 [[package]]
 name = "ply"
 version = "3.11"

docker/.env.example

@@ -867,14 +867,14 @@ CODE_MAX_NUMBER=9223372036854775807
 CODE_MIN_NUMBER=-9223372036854775808
 CODE_MAX_DEPTH=5
 CODE_MAX_PRECISION=20
-CODE_MAX_STRING_LENGTH=80000
+CODE_MAX_STRING_LENGTH=400000
 CODE_MAX_STRING_ARRAY_LENGTH=30
 CODE_MAX_OBJECT_ARRAY_LENGTH=30
 CODE_MAX_NUMBER_ARRAY_LENGTH=1000
 CODE_EXECUTION_CONNECT_TIMEOUT=10
 CODE_EXECUTION_READ_TIMEOUT=60
 CODE_EXECUTION_WRITE_TIMEOUT=10
-TEMPLATE_TRANSFORM_MAX_LENGTH=80000
+TEMPLATE_TRANSFORM_MAX_LENGTH=400000
 
 # Workflow runtime configuration
 WORKFLOW_MAX_EXECUTION_STEPS=500

docker/docker-compose.yaml

@@ -390,14 +390,14 @@ x-shared-env: &shared-api-worker-env
   CODE_MIN_NUMBER: ${CODE_MIN_NUMBER:--9223372036854775808}
   CODE_MAX_DEPTH: ${CODE_MAX_DEPTH:-5}
   CODE_MAX_PRECISION: ${CODE_MAX_PRECISION:-20}
-  CODE_MAX_STRING_LENGTH: ${CODE_MAX_STRING_LENGTH:-80000}
+  CODE_MAX_STRING_LENGTH: ${CODE_MAX_STRING_LENGTH:-400000}
   CODE_MAX_STRING_ARRAY_LENGTH: ${CODE_MAX_STRING_ARRAY_LENGTH:-30}
   CODE_MAX_OBJECT_ARRAY_LENGTH: ${CODE_MAX_OBJECT_ARRAY_LENGTH:-30}
   CODE_MAX_NUMBER_ARRAY_LENGTH: ${CODE_MAX_NUMBER_ARRAY_LENGTH:-1000}
   CODE_EXECUTION_CONNECT_TIMEOUT: ${CODE_EXECUTION_CONNECT_TIMEOUT:-10}
   CODE_EXECUTION_READ_TIMEOUT: ${CODE_EXECUTION_READ_TIMEOUT:-60}
   CODE_EXECUTION_WRITE_TIMEOUT: ${CODE_EXECUTION_WRITE_TIMEOUT:-10}
-  TEMPLATE_TRANSFORM_MAX_LENGTH: ${TEMPLATE_TRANSFORM_MAX_LENGTH:-80000}
+  TEMPLATE_TRANSFORM_MAX_LENGTH: ${TEMPLATE_TRANSFORM_MAX_LENGTH:-400000}
   WORKFLOW_MAX_EXECUTION_STEPS: ${WORKFLOW_MAX_EXECUTION_STEPS:-500}
   WORKFLOW_MAX_EXECUTION_TIME: ${WORKFLOW_MAX_EXECUTION_TIME:-1200}
   WORKFLOW_CALL_MAX_DEPTH: ${WORKFLOW_CALL_MAX_DEPTH:-5}

docs/ar-SA/README.md

@@ -1,4 +1,4 @@
-![cover-v5-optimized](../images/GitHub_README_if.png)
+![cover-v5-optimized](../../images/GitHub_README_if.png)
 
 <p align="center">
   <a href="https://cloud.dify.ai">Dify Cloud</a> ·
@@ -35,17 +35,19 @@
 </p>
 
 <p align="center">
-  <a href="../README.md"><img alt="README in English" src="https://img.shields.io/badge/English-d9d9d9"></a>
-  <a href="./README_CN.md"><img alt="简体中文版自述文件" src="https://img.shields.io/badge/简体中文-d9d9d9"></a>
-  <a href="./README_JA.md"><img alt="日本語のREADME" src="https://img.shields.io/badge/日本語-d9d9d9"></a>
-  <a href="./README_ES.md"><img alt="README en Español" src="https://img.shields.io/badge/Español-d9d9d9"></a>
-  <a href="./README_FR.md"><img alt="README en Français" src="https://img.shields.io/badge/Français-d9d9d9"></a>
-  <a href="./README_KL.md"><img alt="README tlhIngan Hol" src="https://img.shields.io/badge/Klingon-d9d9d9"></a>
-  <a href="./README_KR.md"><img alt="README in Korean" src="https://img.shields.io/badge/한국어-d9d9d9"></a>
-  <a href="./README_AR.md"><img alt="README بالعربية" src="https://img.shields.io/badge/العربية-d9d9d9"></a>
-  <a href="./README_TR.md"><img alt="Türkçe README" src="https://img.shields.io/badge/Türkçe-d9d9d9"></a>
-  <a href="./README_VI.md"><img alt="README Tiếng Việt" src="https://img.shields.io/badge/Ti%E1%BA%BFng%20Vi%E1%BB%87t-d9d9d9"></a>
-  <a href="./README_BN.md"><img alt="README in বাংলা" src="https://img.shields.io/badge/বাংলা-d9d9d9"></a>
+  <a href="../../README.md"><img alt="README in English" src="https://img.shields.io/badge/English-d9d9d9"></a>
+  <a href="../zh-TW/README.md"><img alt="繁體中文文件" src="https://img.shields.io/badge/繁體中文-d9d9d9"></a>
+  <a href="../zh-CN/README.md"><img alt="简体中文文件" src="https://img.shields.io/badge/简体中文-d9d9d9"></a>
+  <a href="../ja-JP/README.md"><img alt="日本語のREADME" src="https://img.shields.io/badge/日本語-d9d9d9"></a>
+  <a href="../es-ES/README.md"><img alt="README en Español" src="https://img.shields.io/badge/Español-d9d9d9"></a>
+  <a href="../fr-FR/README.md"><img alt="README en Français" src="https://img.shields.io/badge/Français-d9d9d9"></a>
+  <a href="../tlh/README.md"><img alt="README tlhIngan Hol" src="https://img.shields.io/badge/Klingon-d9d9d9"></a>
+  <a href="../ko-KR/README.md"><img alt="README in Korean" src="https://img.shields.io/badge/한국어-d9d9d9"></a>
+  <a href="../ar-SA/README.md"><img alt="README بالعربية" src="https://img.shields.io/badge/العربية-d9d9d9"></a>
+  <a href="../tr-TR/README.md"><img alt="Türkçe README" src="https://img.shields.io/badge/Türkçe-d9d9d9"></a>
+  <a href="../vi-VN/README.md"><img alt="README Tiếng Việt" src="https://img.shields.io/badge/Ti%E1%BA%BFng%20Vi%E1%BB%87t-d9d9d9"></a>
+  <a href="../de-DE/README.md"><img alt="README in Deutsch" src="https://img.shields.io/badge/German-d9d9d9"></a>
+  <a href="../bn-BD/README.md"><img alt="README in বাংলা" src="https://img.shields.io/badge/বাংলা-d9d9d9"></a>
 </p>
 
 <div style="text-align: right;">
@@ -97,7 +99,7 @@
 
 </br>
 
-أسهل طريقة لبدء تشغيل خادم Dify هي تشغيل ملف [docker-compose.yml](docker/docker-compose.yaml) الخاص بنا. قبل تشغيل أمر التثبيت، تأكد من تثبيت [Docker](https://docs.docker.com/get-docker/) و [Docker Compose](https://docs.docker.com/compose/install/) على جهازك:
+أسهل طريقة لبدء تشغيل خادم Dify هي تشغيل ملف [docker-compose.yml](../../docker/docker-compose.yaml) الخاص بنا. قبل تشغيل أمر التثبيت، تأكد من تثبيت [Docker](https://docs.docker.com/get-docker/) و [Docker Compose](https://docs.docker.com/compose/install/) على جهازك:
 
 ```bash
 cd docker
@@ -111,7 +113,7 @@ docker compose up -d
 
 ## الخطوات التالية
 
-إذا كنت بحاجة إلى تخصيص الإعدادات، فيرجى الرجوع إلى التعليقات في ملف [.env.example](docker/.env.example) وتحديث القيم المقابلة في ملف `.env`. بالإضافة إلى ذلك، قد تحتاج إلى إجراء تعديلات على ملف `docker-compose.yaml` نفسه، مثل تغيير إصدارات الصور أو تعيينات المنافذ أو نقاط تحميل وحدات التخزين، بناءً على بيئة النشر ومتطلباتك الخاصة. بعد إجراء أي تغييرات، يرجى إعادة تشغيل `docker-compose up -d`. يمكنك العثور على قائمة كاملة بمتغيرات البيئة المتاحة [هنا](https://docs.dify.ai/getting-started/install-self-hosted/environments).
+إذا كنت بحاجة إلى تخصيص الإعدادات، فيرجى الرجوع إلى التعليقات في ملف [.env.example](../../docker/.env.example) وتحديث القيم المقابلة في ملف `.env`. بالإضافة إلى ذلك، قد تحتاج إلى إجراء تعديلات على ملف `docker-compose.yaml` نفسه، مثل تغيير إصدارات الصور أو تعيينات المنافذ أو نقاط تحميل وحدات التخزين، بناءً على بيئة النشر ومتطلباتك الخاصة. بعد إجراء أي تغييرات، يرجى إعادة تشغيل `docker-compose up -d`. يمكنك العثور على قائمة كاملة بمتغيرات البيئة المتاحة [هنا](https://docs.dify.ai/getting-started/install-self-hosted/environments).
 
 يوجد مجتمع خاص بـ [Helm Charts](https://helm.sh/) وملفات YAML التي تسمح بتنفيذ Dify على Kubernetes للنظام من الإيجابيات العلوية.
 
@@ -185,12 +187,4 @@ docker compose up -d
 
 ## الرخصة
 
-هذا المستودع متاح تحت [رخصة البرنامج الحر Dify](../LICENSE)، والتي تعتبر بشكل أساسي Apache 2.0 مع بعض القيود الإضافية.
-
-## الكشف عن الأمان
-
-لحماية خصوصيتك، يرجى تجنب نشر مشكلات الأمان على GitHub. بدلاً من ذلك، أرسل أسئلتك إلى <security@dify.ai> وسنقدم لك إجابة أكثر تفصيلاً.
-
-## الرخصة
-
-هذا المستودع متاح تحت [رخصة البرنامج الحر Dify](../LICENSE)، والتي تعتبر بشكل أساسي Apache 2.0 مع بعض القيود الإضافية.
+هذا المستودع متاح تحت [رخصة البرنامج الحر Dify](../../LICENSE)، والتي تعتبر بشكل أساسي Apache 2.0 مع بعض القيود الإضافية.

docs/bn-BD/README.md

@@ -1,4 +1,4 @@
-![cover-v5-optimized](../images/GitHub_README_if.png)
+![cover-v5-optimized](../../images/GitHub_README_if.png)
 
 <p align="center">
   📌 <a href="https://dify.ai/blog/introducing-dify-workflow-file-upload-a-demo-on-ai-podcast">ডিফাই ওয়ার্কফ্লো ফাইল আপলোড পরিচিতি: গুগল নোটবুক-এলএম পডকাস্ট পুনর্নির্মাণ</a>
@@ -39,18 +39,19 @@
 </p>
 
 <p align="center">
-  <a href="../README.md"><img alt="README in English" src="https://img.shields.io/badge/English-d9d9d9"></a>
-  <a href="./README_CN.md"><img alt="简体中文版自述文件" src="https://img.shields.io/badge/简体中文-d9d9d9"></a>
-  <a href="./README_JA.md"><img alt="日本語のREADME" src="https://img.shields.io/badge/日本語-d9d9d9"></a>
-  <a href="./README_ES.md"><img alt="README en Español" src="https://img.shields.io/badge/Español-d9d9d9"></a>
-  <a href="./README_FR.md"><img alt="README en Français" src="https://img.shields.io/badge/Français-d9d9d9"></a>
-  <a href="./README_KL.md"><img alt="README tlhIngan Hol" src="https://img.shields.io/badge/Klingon-d9d9d9"></a>
-  <a href="./README_KR.md"><img alt="README in Korean" src="https://img.shields.io/badge/한국어-d9d9d9"></a>
-  <a href="./README_AR.md"><img alt="README بالعربية" src="https://img.shields.io/badge/العربية-d9d9d9"></a>
-  <a href="./README_TR.md"><img alt="Türkçe README" src="https://img.shields.io/badge/Türkçe-d9d9d9"></a>
-  <a href="./README_VI.md"><img alt="README Tiếng Việt" src="https://img.shields.io/badge/Ti%E1%BA%BFng%20Vi%E1%BB%87t-d9d9d9"></a>
-  <a href="./README_DE.md"><img alt="README in Deutsch" src="https://img.shields.io/badge/German-d9d9d9"></a>
-  <a href="./README_BN.md"><img alt="README in বাংলা" src="https://img.shields.io/badge/বাংলা-d9d9d9"></a>
+  <a href="../../README.md"><img alt="README in English" src="https://img.shields.io/badge/English-d9d9d9"></a>
+  <a href="../zh-TW/README.md"><img alt="繁體中文文件" src="https://img.shields.io/badge/繁體中文-d9d9d9"></a>
+  <a href="../zh-CN/README.md"><img alt="简体中文文件" src="https://img.shields.io/badge/简体中文-d9d9d9"></a>
+  <a href="../ja-JP/README.md"><img alt="日本語のREADME" src="https://img.shields.io/badge/日本語-d9d9d9"></a>
+  <a href="../es-ES/README.md"><img alt="README en Español" src="https://img.shields.io/badge/Español-d9d9d9"></a>
+  <a href="../fr-FR/README.md"><img alt="README en Français" src="https://img.shields.io/badge/Français-d9d9d9"></a>
+  <a href="../tlh/README.md"><img alt="README tlhIngan Hol" src="https://img.shields.io/badge/Klingon-d9d9d9"></a>
+  <a href="../ko-KR/README.md"><img alt="README in Korean" src="https://img.shields.io/badge/한국어-d9d9d9"></a>
+  <a href="../ar-SA/README.md"><img alt="README بالعربية" src="https://img.shields.io/badge/العربية-d9d9d9"></a>
+  <a href="../tr-TR/README.md"><img alt="Türkçe README" src="https://img.shields.io/badge/Türkçe-d9d9d9"></a>
+  <a href="../vi-VN/README.md"><img alt="README Tiếng Việt" src="https://img.shields.io/badge/Ti%E1%BA%BFng%20Vi%E1%BB%87t-d9d9d9"></a>
+  <a href="../de-DE/README.md"><img alt="README in Deutsch" src="https://img.shields.io/badge/German-d9d9d9"></a>
+  <a href="../bn-BD/README.md"><img alt="README in বাংলা" src="https://img.shields.io/badge/বাংলা-d9d9d9"></a>
 </p>
 
 ডিফাই একটি ওপেন-সোর্স LLM অ্যাপ ডেভেলপমেন্ট প্ল্যাটফর্ম। এটি ইন্টুইটিভ ইন্টারফেস, এজেন্টিক AI ওয়ার্কফ্লো, RAG পাইপলাইন, এজেন্ট ক্যাপাবিলিটি, মডেল ম্যানেজমেন্ট, মনিটরিং সুবিধা এবং আরও অনেক কিছু একত্রিত করে, যা দ্রুত প্রোটোটাইপ থেকে প্রোডাকশন পর্যন্ত নিয়ে যেতে সহায়তা করে।
@@ -64,7 +65,7 @@
 
 </br>
 
-ডিফাই সার্ভার চালু করার সবচেয়ে সহজ উপায় [docker compose](docker/docker-compose.yaml) মাধ্যমে। নিম্নলিখিত কমান্ডগুলো ব্যবহার করে ডিফাই চালানোর আগে, নিশ্চিত করুন যে আপনার মেশিনে [Docker](https://docs.docker.com/get-docker/) এবং [Docker Compose](https://docs.docker.com/compose/install/) ইনস্টল করা আছে :
+ডিফাই সার্ভার চালু করার সবচেয়ে সহজ উপায় [docker compose](../../docker/docker-compose.yaml) মাধ্যমে। নিম্নলিখিত কমান্ডগুলো ব্যবহার করে ডিফাই চালানোর আগে, নিশ্চিত করুন যে আপনার মেশিনে [Docker](https://docs.docker.com/get-docker/) এবং [Docker Compose](https://docs.docker.com/compose/install/) ইনস্টল করা আছে :
 
 ```bash
 cd dify
@@ -128,7 +129,7 @@ GitHub-এ ডিফাইকে স্টার দিয়ে রাখুন
 
 ## Advanced Setup
 
-যদি আপনার কনফিগারেশনটি কাস্টমাইজ করার প্রয়োজন হয়, তাহলে অনুগ্রহ করে আমাদের [.env.example](docker/.env.example) ফাইল দেখুন এবং আপনার `.env` ফাইলে সংশ্লিষ্ট মানগুলি আপডেট করুন। এছাড়াও, আপনার নির্দিষ্ট এনভায়রনমেন্ট এবং প্রয়োজনীয়তার উপর ভিত্তি করে আপনাকে `docker-compose.yaml` ফাইলে সমন্বয় করতে হতে পারে, যেমন ইমেজ ভার্সন পরিবর্তন করা, পোর্ট ম্যাপিং করা, অথবা ভলিউম মাউন্ট করা।
+যদি আপনার কনফিগারেশনটি কাস্টমাইজ করার প্রয়োজন হয়, তাহলে অনুগ্রহ করে আমাদের [.env.example](../../docker/.env.example) ফাইল দেখুন এবং আপনার `.env` ফাইলে সংশ্লিষ্ট মানগুলি আপডেট করুন। এছাড়াও, আপনার নির্দিষ্ট এনভায়রনমেন্ট এবং প্রয়োজনীয়তার উপর ভিত্তি করে আপনাকে `docker-compose.yaml` ফাইলে সমন্বয় করতে হতে পারে, যেমন ইমেজ ভার্সন পরিবর্তন করা, পোর্ট ম্যাপিং করা, অথবা ভলিউম মাউন্ট করা।
 যেকোনো পরিবর্তন করার পর, অনুগ্রহ করে `docker-compose up -d` পুনরায় চালান। ভেরিয়েবলের সম্পূর্ণ তালিকা [এখানে] (https://docs.dify.ai/getting-started/install-self-hosted/environments) খুঁজে পেতে পারেন।
 
 যদি আপনি একটি হাইলি এভেইলেবল সেটআপ কনফিগার করতে চান, তাহলে কমিউনিটি [Helm Charts](https://helm.sh/) এবং YAML ফাইল রয়েছে যা Dify কে Kubernetes-এ ডিপ্লয় করার প্রক্রিয়া বর্ণনা করে।
@@ -175,7 +176,7 @@ GitHub-এ ডিফাইকে স্টার দিয়ে রাখুন
 
 ## Contributing
 
-যারা কোড অবদান রাখতে চান, তাদের জন্য আমাদের [অবদান নির্দেশিকা] দেখুন (https://github.com/langgenius/dify/blob/main/CONTRIBUTING.md)।
+যারা কোড অবদান রাখতে চান, তাদের জন্য আমাদের [অবদান নির্দেশিকা](https://github.com/langgenius/dify/blob/main/CONTRIBUTING.md) দেখুন।
 একই সাথে, সোশ্যাল মিডিয়া এবং ইভেন্ট এবং কনফারেন্সে এটি শেয়ার করে Dify কে সমর্থন করুন।
 
 > আমরা ম্যান্ডারিন বা ইংরেজি ছাড়া অন্য ভাষায় Dify অনুবাদ করতে সাহায্য করার জন্য অবদানকারীদের খুঁজছি। আপনি যদি সাহায্য করতে আগ্রহী হন, তাহলে আরও তথ্যের জন্য [i18n README](https://github.com/langgenius/dify/blob/main/web/i18n-config/README.md) দেখুন এবং আমাদের [ডিসকর্ড কমিউনিটি সার্ভার](https://discord.gg/8Tpq4AcN9c) এর `গ্লোবাল-ইউজারস` চ্যানেলে আমাদের একটি মন্তব্য করুন।
@@ -203,4 +204,4 @@ GitHub-এ ডিফাইকে স্টার দিয়ে রাখুন
 
 ## লাইসেন্স
 
-এই রিপোজিটরিটি [ডিফাই ওপেন সোর্স লাইসেন্স](../LICENSE) এর অধিনে , যা মূলত অ্যাপাচি ২.০, তবে কিছু অতিরিক্ত বিধিনিষেধ রয়েছে।
+এই রিপোজিটরিটি [ডিফাই ওপেন সোর্স লাইসেন্স](../../LICENSE) এর অধিনে , যা মূলত অ্যাপাচি ২.০, তবে কিছু অতিরিক্ত বিধিনিষেধ রয়েছে।

docs/de-DE/CONTRIBUTING.md

@@ -6,7 +6,7 @@ Wir müssen wendig sein und schnell liefern, aber wir möchten auch sicherstelle
 
 Dieser Leitfaden ist, wie Dify selbst, in ständiger Entwicklung. Wir sind dankbar für Ihr Verständnis, falls er manchmal hinter dem eigentlichen Projekt zurückbleibt, und begrüßen jedes Feedback zur Verbesserung.
 
-Bitte nehmen Sie sich einen Moment Zeit, um unsere [Lizenz- und Mitwirkungsvereinbarung](../LICENSE) zu lesen. Die Community hält sich außerdem an den [Verhaltenskodex](https://github.com/langgenius/.github/blob/main/CODE_OF_CONDUCT.md).
+Bitte nehmen Sie sich einen Moment Zeit, um unsere [Lizenz- und Mitwirkungsvereinbarung](../../LICENSE) zu lesen. Die Community hält sich außerdem an den [Verhaltenskodex](https://github.com/langgenius/.github/blob/main/CODE_OF_CONDUCT.md).
 
 ## Bevor Sie loslegen
 

docs/de-DE/README.md

@@ -1,4 +1,4 @@
-![cover-v5-optimized](../images/GitHub_README_if.png)
+![cover-v5-optimized](../../images/GitHub_README_if.png)
 
 <p align="center">
   📌 <a href="https://dify.ai/blog/introducing-dify-workflow-file-upload-a-demo-on-ai-podcast">Einführung in Dify Workflow File Upload: Google NotebookLM Podcast nachbilden</a>
@@ -39,18 +39,19 @@
 </p>
 
 <p align="center">
-  <a href="../README.md"><img alt="README in English" src="https://img.shields.io/badge/English-d9d9d9"></a>
-  <a href="./README_CN.md"><img alt="简体中文版自述文件" src="https://img.shields.io/badge/简体中文-d9d9d9"></a>
-  <a href="./README_JA.md"><img alt="日本語のREADME" src="https://img.shields.io/badge/日本語-d9d9d9"></a>
-  <a href="./README_ES.md"><img alt="README en Español" src="https://img.shields.io/badge/Español-d9d9d9"></a>
-  <a href="./README_FR.md"><img alt="README en Français" src="https://img.shields.io/badge/Français-d9d9d9"></a>
-  <a href="./README_KL.md"><img alt="README tlhIngan Hol" src="https://img.shields.io/badge/Klingon-d9d9d9"></a>
-  <a href="./README_KR.md"><img alt="README in Korean" src="https://img.shields.io/badge/한국어-d9d9d9"></a>
-  <a href="./README_AR.md"><img alt="README بالعربية" src="https://img.shields.io/badge/العربية-d9d9d9"></a>
-  <a href="./README_TR.md"><img alt="Türkçe README" src="https://img.shields.io/badge/Türkçe-d9d9d9"></a>
-  <a href="./README_VI.md"><img alt="README Tiếng Việt" src="https://img.shields.io/badge/Ti%E1%BA%BFng%20Vi%E1%BB%87t-d9d9d9"></a>
-  <a href="./README_DE.md"><img alt="README in Deutsch" src="https://img.shields.io/badge/German-d9d9d9"></a>
-  <a href="./README_BN.md"><img alt="README in বাংলা" src="https://img.shields.io/badge/বাংলা-d9d9d9"></a>
+  <a href="../../README.md"><img alt="README in English" src="https://img.shields.io/badge/English-d9d9d9"></a>
+  <a href="../zh-TW/README.md"><img alt="繁體中文文件" src="https://img.shields.io/badge/繁體中文-d9d9d9"></a>
+  <a href="../zh-CN/README.md"><img alt="简体中文文件" src="https://img.shields.io/badge/简体中文-d9d9d9"></a>
+  <a href="../ja-JP/README.md"><img alt="日本語のREADME" src="https://img.shields.io/badge/日本語-d9d9d9"></a>
+  <a href="../es-ES/README.md"><img alt="README en Español" src="https://img.shields.io/badge/Español-d9d9d9"></a>
+  <a href="../fr-FR/README.md"><img alt="README en Français" src="https://img.shields.io/badge/Français-d9d9d9"></a>
+  <a href="../tlh/README.md"><img alt="README tlhIngan Hol" src="https://img.shields.io/badge/Klingon-d9d9d9"></a>
+  <a href="../ko-KR/README.md"><img alt="README in Korean" src="https://img.shields.io/badge/한국어-d9d9d9"></a>
+  <a href="../ar-SA/README.md"><img alt="README بالعربية" src="https://img.shields.io/badge/العربية-d9d9d9"></a>
+  <a href="../tr-TR/README.md"><img alt="Türkçe README" src="https://img.shields.io/badge/Türkçe-d9d9d9"></a>
+  <a href="../vi-VN/README.md"><img alt="README Tiếng Việt" src="https://img.shields.io/badge/Ti%E1%BA%BFng%20Vi%E1%BB%87t-d9d9d9"></a>
+  <a href="../de-DE/README.md"><img alt="README in Deutsch" src="https://img.shields.io/badge/German-d9d9d9"></a>
+  <a href="../bn-BD/README.md"><img alt="README in বাংলা" src="https://img.shields.io/badge/বাংলা-d9d9d9"></a>
 </p>
 
 Dify ist eine Open-Source-Plattform zur Entwicklung von LLM-Anwendungen. Ihre intuitive Benutzeroberfläche vereint agentenbasierte KI-Workflows, RAG-Pipelines, Agentenfunktionen, Modellverwaltung, Überwachungsfunktionen und mehr, sodass Sie schnell von einem Prototyp in die Produktion übergehen können.
@@ -64,7 +65,7 @@ Dify ist eine Open-Source-Plattform zur Entwicklung von LLM-Anwendungen. Ihre in
 
 </br>
 
-Der einfachste Weg, den Dify-Server zu starten, ist über [docker compose](docker/docker-compose.yaml). Stellen Sie vor dem Ausführen von Dify mit den folgenden Befehlen sicher, dass [Docker](https://docs.docker.com/get-docker/) und [Docker Compose](https://docs.docker.com/compose/install/) auf Ihrem System installiert sind:
+Der einfachste Weg, den Dify-Server zu starten, ist über [docker compose](../../docker/docker-compose.yaml). Stellen Sie vor dem Ausführen von Dify mit den folgenden Befehlen sicher, dass [Docker](https://docs.docker.com/get-docker/) und [Docker Compose](https://docs.docker.com/compose/install/) auf Ihrem System installiert sind:
 
 ```bash
 cd dify
@@ -127,7 +128,7 @@ Star Dify auf GitHub und lassen Sie sich sofort über neue Releases benachrichti
 
 ## Erweiterte Einstellungen
 
-Falls Sie die Konfiguration anpassen müssen, lesen Sie bitte die Kommentare in unserer [.env.example](docker/.env.example)-Datei und aktualisieren Sie die entsprechenden Werte in Ihrer `.env`-Datei. Zusätzlich müssen Sie eventuell Anpassungen an der `docker-compose.yaml`-Datei vornehmen, wie zum Beispiel das Ändern von Image-Versionen, Portzuordnungen oder Volumen-Mounts, je nach Ihrer spezifischen Einsatzumgebung und Ihren Anforderungen. Nachdem Sie Änderungen vorgenommen haben, starten Sie `docker-compose up -d` erneut. Eine vollständige Liste der verfügbaren Umgebungsvariablen finden Sie [hier](https://docs.dify.ai/getting-started/install-self-hosted/environments).
+Falls Sie die Konfiguration anpassen müssen, lesen Sie bitte die Kommentare in unserer [.env.example](../../docker/.env.example)-Datei und aktualisieren Sie die entsprechenden Werte in Ihrer `.env`-Datei. Zusätzlich müssen Sie eventuell Anpassungen an der `docker-compose.yaml`-Datei vornehmen, wie zum Beispiel das Ändern von Image-Versionen, Portzuordnungen oder Volumen-Mounts, je nach Ihrer spezifischen Einsatzumgebung und Ihren Anforderungen. Nachdem Sie Änderungen vorgenommen haben, starten Sie `docker-compose up -d` erneut. Eine vollständige Liste der verfügbaren Umgebungsvariablen finden Sie [hier](https://docs.dify.ai/getting-started/install-self-hosted/environments).
 
 Falls Sie eine hochverfügbare Konfiguration einrichten möchten, gibt es von der Community bereitgestellte [Helm Charts](https://helm.sh/) und YAML-Dateien, die es ermöglichen, Dify auf Kubernetes bereitzustellen.
 
@@ -173,14 +174,14 @@ Stellen Sie Dify mit einem Klick in AKS bereit, indem Sie [Azure Devops Pipeline
 
 ## Contributing
 
-Falls Sie Code beitragen möchten, lesen Sie bitte unseren [Contribution Guide](https://github.com/langgenius/dify/blob/main/CONTRIBUTING/CONTRIBUTING_DE.md). Gleichzeitig bitten wir Sie, Dify zu unterstützen, indem Sie es in den sozialen Medien teilen und auf Veranstaltungen und Konferenzen präsentieren.
+Falls Sie Code beitragen möchten, lesen Sie bitte unseren [Contribution Guide](./CONTRIBUTING.md). Gleichzeitig bitten wir Sie, Dify zu unterstützen, indem Sie es in den sozialen Medien teilen und auf Veranstaltungen und Konferenzen präsentieren.
 
 > Wir suchen Mitwirkende, die dabei helfen, Dify in weitere Sprachen zu übersetzen – außer Mandarin oder Englisch. Wenn Sie Interesse an einer Mitarbeit haben, lesen Sie bitte die [i18n README](https://github.com/langgenius/dify/blob/main/web/i18n-config/README.md) für weitere Informationen und hinterlassen Sie einen Kommentar im `global-users`-Kanal unseres [Discord Community Servers](https://discord.gg/8Tpq4AcN9c).
 
 ## Gemeinschaft & Kontakt
 
 - [GitHub Discussion](https://github.com/langgenius/dify/discussions). Am besten geeignet für: den Austausch von Feedback und das Stellen von Fragen.
-- [GitHub Issues](https://github.com/langgenius/dify/issues). Am besten für: Fehler, auf die Sie bei der Verwendung von Dify.AI stoßen, und Funktionsvorschläge. Siehe unseren [Contribution Guide](https://github.com/langgenius/dify/blob/main/CONTRIBUTING.md).
+- [GitHub Issues](https://github.com/langgenius/dify/issues). Am besten für: Fehler, auf die Sie bei der Verwendung von Dify.AI stoßen, und Funktionsvorschläge. Siehe unseren [Contribution Guide](./CONTRIBUTING.md).
 - [Discord](https://discord.gg/FngNHpbcY7). Am besten geeignet für: den Austausch von Bewerbungen und den Austausch mit der Community.
 - [X(Twitter)](https://twitter.com/dify_ai). Am besten geeignet für: den Austausch von Bewerbungen und den Austausch mit der Community.
 
@@ -200,4 +201,4 @@ Um Ihre Privatsphäre zu schützen, vermeiden Sie es bitte, Sicherheitsprobleme
 
 ## Lizenz
 
-Dieses Repository steht unter der [Dify Open Source License](../LICENSE), die im Wesentlichen Apache 2.0 mit einigen zusätzlichen Einschränkungen ist.
+Dieses Repository steht unter der [Dify Open Source License](../../LICENSE), die im Wesentlichen Apache 2.0 mit einigen zusätzlichen Einschränkungen ist.

docs/es-ES/CONTRIBUTING.md

@@ -6,7 +6,7 @@ Necesitamos ser ágiles y enviar rápidamente dado donde estamos, pero también
 
 Esta guía, como Dify mismo, es un trabajo en constante progreso. Agradecemos mucho tu comprensión si a veces se queda atrás del proyecto real, y damos la bienvenida a cualquier comentario para que podamos mejorar.
 
-En términos de licencia, por favor tómate un minuto para leer nuestro breve [Acuerdo de Licencia y Colaborador](../LICENSE). La comunidad también se adhiere al [código de conducta](https://github.com/langgenius/.github/blob/main/CODE_OF_CONDUCT.md).
+En términos de licencia, por favor tómate un minuto para leer nuestro breve [Acuerdo de Licencia y Colaborador](../../LICENSE). La comunidad también se adhiere al [código de conducta](https://github.com/langgenius/.github/blob/main/CODE_OF_CONDUCT.md).
 
 ## Antes de empezar
 

docs/es-ES/README.md

@@ -1,4 +1,4 @@
-![cover-v5-optimized](../images/GitHub_README_if.png)
+![cover-v5-optimized](../../images/GitHub_README_if.png)
 
 <p align="center">
   <a href="https://cloud.dify.ai">Dify Cloud</a> ·
@@ -35,17 +35,19 @@
 </p>
 
 <p align="center">
-  <a href="../README.md"><img alt="README in English" src="https://img.shields.io/badge/English-d9d9d9"></a>
-  <a href="./README_CN.md"><img alt="简体中文版自述文件" src="https://img.shields.io/badge/简体中文-d9d9d9"></a>
-  <a href="./README_JA.md"><img alt="日本語のREADME" src="https://img.shields.io/badge/日本語-d9d9d9"></a>
-  <a href="./README_ES.md"><img alt="README en Español" src="https://img.shields.io/badge/Español-d9d9d9"></a>
-  <a href="./README_FR.md"><img alt="README en Français" src="https://img.shields.io/badge/Français-d9d9d9"></a>
-  <a href="./README_KL.md"><img alt="README tlhIngan Hol" src="https://img.shields.io/badge/Klingon-d9d9d9"></a>
-  <a href="./README_KR.md"><img alt="README in Korean" src="https://img.shields.io/badge/한국어-d9d9d9"></a>
-  <a href="./README_AR.md"><img alt="README بالعربية" src="https://img.shields.io/badge/العربية-d9d9d9"></a>
-  <a href="./README_TR.md"><img alt="Türkçe README" src="https://img.shields.io/badge/Türkçe-d9d9d9"></a>
-  <a href="./README_VI.md"><img alt="README Tiếng Việt" src="https://img.shields.io/badge/Ti%E1%BA%BFng%20Vi%E1%BB%87t-d9d9d9"></a>
-  <a href="./README_BN.md"><img alt="README in বাংলা" src="https://img.shields.io/badge/বাংলা-d9d9d9"></a>
+  <a href="../../README.md"><img alt="README in English" src="https://img.shields.io/badge/English-d9d9d9"></a>
+  <a href="../zh-TW/README.md"><img alt="繁體中文文件" src="https://img.shields.io/badge/繁體中文-d9d9d9"></a>
+  <a href="../zh-CN/README.md"><img alt="简体中文文件" src="https://img.shields.io/badge/简体中文-d9d9d9"></a>
+  <a href="../ja-JP/README.md"><img alt="日本語のREADME" src="https://img.shields.io/badge/日本語-d9d9d9"></a>
+  <a href="../es-ES/README.md"><img alt="README en Español" src="https://img.shields.io/badge/Español-d9d9d9"></a>
+  <a href="../fr-FR/README.md"><img alt="README en Français" src="https://img.shields.io/badge/Français-d9d9d9"></a>
+  <a href="../tlh/README.md"><img alt="README tlhIngan Hol" src="https://img.shields.io/badge/Klingon-d9d9d9"></a>
+  <a href="../ko-KR/README.md"><img alt="README in Korean" src="https://img.shields.io/badge/한국어-d9d9d9"></a>
+  <a href="../ar-SA/README.md"><img alt="README بالعربية" src="https://img.shields.io/badge/العربية-d9d9d9"></a>
+  <a href="../tr-TR/README.md"><img alt="Türkçe README" src="https://img.shields.io/badge/Türkçe-d9d9d9"></a>
+  <a href="../vi-VN/README.md"><img alt="README Tiếng Việt" src="https://img.shields.io/badge/Ti%E1%BA%BFng%20Vi%E1%BB%87t-d9d9d9"></a>
+  <a href="../de-DE/README.md"><img alt="README in Deutsch" src="https://img.shields.io/badge/German-d9d9d9"></a>
+  <a href="../bn-BD/README.md"><img alt="README in বাংলা" src="https://img.shields.io/badge/বাংলা-d9d9d9"></a>
 </p>
 
 # 
@@ -108,7 +110,7 @@ Dale estrella a Dify en GitHub y serás notificado instantáneamente de las nuev
 
 </br>
 
-La forma más fácil de iniciar el servidor de Dify es ejecutar nuestro archivo [docker-compose.yml](docker/docker-compose.yaml). Antes de ejecutar el comando de instalación, asegúrate de que [Docker](https://docs.docker.com/get-docker/) y [Docker Compose](https://docs.docker.com/compose/install/) estén instalados en tu máquina:
+La forma más fácil de iniciar el servidor de Dify es ejecutar nuestro archivo [docker-compose.yml](../../docker/docker-compose.yaml). Antes de ejecutar el comando de instalación, asegúrate de que [Docker](https://docs.docker.com/get-docker/) y [Docker Compose](https://docs.docker.com/compose/install/) estén instalados en tu máquina:
 
 ```bash
 cd docker
@@ -122,7 +124,7 @@ Después de ejecutarlo, puedes acceder al panel de control de Dify en tu navegad
 
 ## Próximos pasos
 
-Si necesita personalizar la configuración, consulte los comentarios en nuestro archivo [.env.example](docker/.env.example) y actualice los valores correspondientes en su archivo `.env`. Además, es posible que deba realizar ajustes en el propio archivo `docker-compose.yaml`, como cambiar las versiones de las imágenes, las asignaciones de puertos o los montajes de volúmenes, según su entorno de implementación y requisitos específicos. Después de realizar cualquier cambio, vuelva a ejecutar `docker-compose up -d`. Puede encontrar la lista completa de variables de entorno disponibles [aquí](https://docs.dify.ai/getting-started/install-self-hosted/environments).
+Si necesita personalizar la configuración, consulte los comentarios en nuestro archivo [.env.example](../../docker/.env.example) y actualice los valores correspondientes en su archivo `.env`. Además, es posible que deba realizar ajustes en el propio archivo `docker-compose.yaml`, como cambiar las versiones de las imágenes, las asignaciones de puertos o los montajes de volúmenes, según su entorno de implementación y requisitos específicos. Después de realizar cualquier cambio, vuelva a ejecutar `docker-compose up -d`. Puede encontrar la lista completa de variables de entorno disponibles [aquí](https://docs.dify.ai/getting-started/install-self-hosted/environments).
 
 . Después de realizar los cambios, ejecuta `docker-compose up -d` nuevamente. Puedes ver la lista completa de variables de entorno [aquí](https://docs.dify.ai/getting-started/install-self-hosted/environments).
 
@@ -170,7 +172,7 @@ Implementa Dify en AKS con un clic usando [Azure Devops Pipeline Helm Chart by @
 
 ## Contribuir
 
-Para aquellos que deseen contribuir con código, consulten nuestra [Guía de contribución](https://github.com/langgenius/dify/blob/main/CONTRIBUTING/CONTRIBUTING_ES.md).
+Para aquellos que deseen contribuir con código, consulten nuestra [Guía de contribución](./CONTRIBUTING.md).
 Al mismo tiempo, considera apoyar a Dify compartiéndolo en redes sociales y en eventos y conferencias.
 
 > Estamos buscando colaboradores para ayudar con la traducción de Dify a idiomas que no sean el mandarín o el inglés. Si estás interesado en ayudar, consulta el [README de i18n](https://github.com/langgenius/dify/blob/main/web/i18n-config/README.md) para obtener más información y déjanos un comentario en el canal `global-users` de nuestro [Servidor de Comunidad en Discord](https://discord.gg/8Tpq4AcN9c).
@@ -184,7 +186,7 @@ Al mismo tiempo, considera apoyar a Dify compartiéndolo en redes sociales y en
 ## Comunidad y Contacto
 
 - [Discusión en GitHub](https://github.com/langgenius/dify/discussions). Lo mejor para: compartir comentarios y hacer preguntas.
-- [Reporte de problemas en GitHub](https://github.com/langgenius/dify/issues). Lo mejor para: errores que encuentres usando Dify.AI y propuestas de características. Consulta nuestra [Guía de contribución](https://github.com/langgenius/dify/blob/main/CONTRIBUTING.md).
+- [Reporte de problemas en GitHub](https://github.com/langgenius/dify/issues). Lo mejor para: errores que encuentres usando Dify.AI y propuestas de características. Consulta nuestra [Guía de contribución](./CONTRIBUTING.md).
 - [Discord](https://discord.gg/FngNHpbcY7). Lo mejor para: compartir tus aplicaciones y pasar el rato con la comunidad.
 - [X(Twitter)](https://twitter.com/dify_ai). Lo mejor para: compartir tus aplicaciones y pasar el rato con la comunidad.
 
@@ -198,12 +200,4 @@ Para proteger tu privacidad, evita publicar problemas de seguridad en GitHub. En
 
 ## Licencia
 
-Este repositorio está disponible bajo la [Licencia de Código Abierto de Dify](../LICENSE), que es esencialmente Apache 2.0 con algunas restricciones adicionales.
-
-## Divulgación de Seguridad
-
-Para proteger tu privacidad, evita publicar problemas de seguridad en GitHub. En su lugar, envía tus preguntas a security@dify.ai y te proporcionaremos una respuesta más detallada.
-
-## Licencia
-
-Este repositorio está disponible bajo la [Licencia de Código Abierto de Dify](../LICENSE), que es esencialmente Apache 2.0 con algunas restricciones adicionales.
+Este repositorio está disponible bajo la [Licencia de Código Abierto de Dify](../../LICENSE), que es esencialmente Apache 2.0 con algunas restricciones adicionales.