feat(oauth): improve error handling for provider retrieval and clarify logging messages

Signed-off-by: -LAN- <laipz8200@outlook.com>

README.md

@@ -54,7 +54,7 @@
   <a href="./README_BN.md"><img alt="README in বাংলা" src="https://img.shields.io/badge/বাংলা-d9d9d9"></a>
 </p>
 
-Dify is an open-source LLM app development platform. Its intuitive interface combines agentic AI workflow, RAG pipeline, agent capabilities, model management, observability features, and more, allowing you to quickly move from prototype to production.
+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.
 
 ## Quick start
 
@@ -65,7 +65,7 @@ Dify is an open-source LLM app development platform. Its intuitive interface com
 
 </br>
 
-The easiest way to start the Dify server is through [docker compose](docker/docker-compose.yaml). Before running Dify with the following commands, make sure that [Docker](https://docs.docker.com/get-docker/) and [Docker Compose](https://docs.docker.com/compose/install/) are installed on your machine:
+The easiest way to start the Dify server is through [Docker Compose](docker/docker-compose.yaml). Before running Dify with the following commands, make sure that [Docker](https://docs.docker.com/get-docker/) and [Docker Compose](https://docs.docker.com/compose/install/) are installed on your machine:
 
 ```bash
 cd dify
@@ -205,6 +205,7 @@ If you'd like to configure a highly-available setup, there are community-contrib
 - [Helm Chart by @magicsong](https://github.com/magicsong/ai-charts)
 - [YAML file by @Winson-030](https://github.com/Winson-030/dify-kubernetes)
 - [YAML file by @wyy-holding](https://github.com/wyy-holding/dify-k8s)
+- [🚀 NEW! YAML files (Supports Dify v1.6.0) by @Zhoneym](https://github.com/Zhoneym/DifyAI-Kubernetes)
 
 #### Using Terraform for Deployment
 
@@ -261,8 +262,8 @@ At the same time, please consider supporting Dify by sharing it on social media
 
 ## Security disclosure
 
-To protect your privacy, please avoid posting security issues on GitHub. Instead, send your questions to security@dify.ai and we will provide you with a more detailed answer.
+To protect your privacy, please avoid posting security issues on GitHub. Instead, report issues to security@dify.ai, and our team will respond with detailed answer.
 
 ## License
 
-This repository is available under the [Dify Open Source License](LICENSE), which is essentially Apache 2.0 with a few additional restrictions.
+This repository is licensed under the [Dify Open Source License](LICENSE), based on Apache 2.0 with additional conditions.

README_AR.md

@@ -188,6 +188,7 @@ docker compose up -d
 - [رسم بياني Helm من قبل @magicsong](https://github.com/magicsong/ai-charts)
 - [ملف YAML من قبل @Winson-030](https://github.com/Winson-030/dify-kubernetes)
 - [ملف YAML من قبل @wyy-holding](https://github.com/wyy-holding/dify-k8s)
+- [🚀 جديد! ملفات YAML (تدعم Dify v1.6.0) بواسطة @Zhoneym](https://github.com/Zhoneym/DifyAI-Kubernetes)
 
 #### استخدام Terraform للتوزيع
 

README_BN.md

@@ -204,6 +204,8 @@ GitHub-এ ডিফাইকে স্টার দিয়ে রাখুন
 - [Helm Chart by @magicsong](https://github.com/magicsong/ai-charts)
 - [YAML file by @Winson-030](https://github.com/Winson-030/dify-kubernetes)
 - [YAML file by @wyy-holding](https://github.com/wyy-holding/dify-k8s)
+- [🚀 নতুন! YAML ফাইলসমূহ (Dify v1.6.0 সমর্থিত) তৈরি করেছেন @Zhoneym](https://github.com/Zhoneym/DifyAI-Kubernetes)
+
 
 #### টেরাফর্ম ব্যবহার করে ডিপ্লয়
 

README_CN.md

@@ -194,9 +194,9 @@ docker compose up -d
 
 如果您需要自定义配置，请参考 [.env.example](docker/.env.example) 文件中的注释，并更新 `.env` 文件中对应的值。此外，您可能需要根据您的具体部署环境和需求对 `docker-compose.yaml` 文件本身进行调整，例如更改镜像版本、端口映射或卷挂载。完成任何更改后，请重新运行 `docker-compose up -d`。您可以在[此处](https://docs.dify.ai/getting-started/install-self-hosted/environments)找到可用环境变量的完整列表。
 
-#### 使用 Helm Chart 部署
+#### 使用 Helm Chart 或 Kubernetes 资源清单（YAML）部署
 
-使用 [Helm Chart](https://helm.sh/) 版本或者 YAML 文件，可以在 Kubernetes 上部署 Dify。
+使用 [Helm Chart](https://helm.sh/) 版本或者 Kubernetes 资源清单（YAML），可以在 Kubernetes 上部署 Dify。
 
 - [Helm Chart by @LeoQuote](https://github.com/douban/charts/tree/master/charts/dify)
 - [Helm Chart by @BorisPolonsky](https://github.com/BorisPolonsky/dify-helm)
@@ -204,6 +204,10 @@ docker compose up -d
 - [YAML 文件 by @Winson-030](https://github.com/Winson-030/dify-kubernetes)
 - [YAML file by @wyy-holding](https://github.com/wyy-holding/dify-k8s)
 
+- [🚀 NEW! YAML 文件 (支持 Dify v1.6.0) by @Zhoneym](https://github.com/Zhoneym/DifyAI-Kubernetes)
+
+
+
 #### 使用 Terraform 部署
 
 使用 [terraform](https://www.terraform.io/) 一键将 Dify 部署到云平台

README_DE.md

@@ -203,6 +203,7 @@ Falls Sie eine hochverfügbare Konfiguration einrichten möchten, gibt es von de
 - [Helm Chart by @magicsong](https://github.com/magicsong/ai-charts)
 - [YAML file by @Winson-030](https://github.com/Winson-030/dify-kubernetes)
 - [YAML file by @wyy-holding](https://github.com/wyy-holding/dify-k8s)
+- [🚀 NEW! YAML files (Supports Dify v1.6.0) by @Zhoneym](https://github.com/Zhoneym/DifyAI-Kubernetes)
 
 #### Terraform für die Bereitstellung verwenden
 

README_ES.md

@@ -203,6 +203,7 @@ Si desea configurar una configuración de alta disponibilidad, la comunidad prop
 - [Gráfico Helm por @magicsong](https://github.com/magicsong/ai-charts)
 - [Ficheros YAML por @Winson-030](https://github.com/Winson-030/dify-kubernetes)
 - [Ficheros YAML por @wyy-holding](https://github.com/wyy-holding/dify-k8s)
+- [🚀 ¡NUEVO! Archivos YAML (compatible con Dify v1.6.0) por @Zhoneym](https://github.com/Zhoneym/DifyAI-Kubernetes)
 
 #### Uso de Terraform para el despliegue
 

README_FR.md

@@ -201,6 +201,7 @@ Si vous souhaitez configurer une configuration haute disponibilité, la communau
 - [Helm Chart par @magicsong](https://github.com/magicsong/ai-charts)
 - [Fichier YAML par @Winson-030](https://github.com/Winson-030/dify-kubernetes)
 - [Fichier YAML par @wyy-holding](https://github.com/wyy-holding/dify-k8s)
+- [🚀 NOUVEAU ! Fichiers YAML (compatible avec Dify v1.6.0) par @Zhoneym](https://github.com/Zhoneym/DifyAI-Kubernetes)
 
 #### Utilisation de Terraform pour le déploiement
 

README_JA.md

@@ -202,6 +202,7 @@ docker compose up -d
 - [Helm Chart by @magicsong](https://github.com/magicsong/ai-charts)
 - [YAML file by @Winson-030](https://github.com/Winson-030/dify-kubernetes)
 - [YAML file by @wyy-holding](https://github.com/wyy-holding/dify-k8s)
+- [🚀 新着！YAML ファイル（Dify v1.6.0 対応）by @Zhoneym](https://github.com/Zhoneym/DifyAI-Kubernetes)
 
 #### Terraformを使用したデプロイ
 

README_KL.md

@@ -201,6 +201,7 @@ If you'd like to configure a highly-available setup, there are community-contrib
 - [Helm Chart by @magicsong](https://github.com/magicsong/ai-charts)
 - [YAML file by @Winson-030](https://github.com/Winson-030/dify-kubernetes)
 - [YAML file by @wyy-holding](https://github.com/wyy-holding/dify-k8s)
+- [🚀 NEW! YAML files (Supports Dify v1.6.0) by @Zhoneym](https://github.com/Zhoneym/DifyAI-Kubernetes)
 
 #### Terraform atorlugu pilersitsineq
 

README_KR.md

@@ -195,6 +195,7 @@ Dify를 Kubernetes에 배포하고 프리미엄 스케일링 설정을 구성했
 - [Helm Chart by @magicsong](https://github.com/magicsong/ai-charts)
 - [YAML file by @Winson-030](https://github.com/Winson-030/dify-kubernetes)
 - [YAML file by @wyy-holding](https://github.com/wyy-holding/dify-k8s)
+- [🚀 NEW! YAML files (Supports Dify v1.6.0) by @Zhoneym](https://github.com/Zhoneym/DifyAI-Kubernetes)
 
 #### Terraform을 사용한 배포
 

README_PT.md

@@ -200,6 +200,7 @@ Se deseja configurar uma instalação de alta disponibilidade, há [Helm Charts]
 - [Helm Chart de @magicsong](https://github.com/magicsong/ai-charts)
 - [Arquivo YAML por @Winson-030](https://github.com/Winson-030/dify-kubernetes)
 - [Arquivo YAML por @wyy-holding](https://github.com/wyy-holding/dify-k8s)
+- [🚀 NOVO! Arquivos YAML (Compatível com Dify v1.6.0) por @Zhoneym](https://github.com/Zhoneym/DifyAI-Kubernetes)
 
 #### Usando o Terraform para Implantação
 

README_SI.md

@@ -201,6 +201,7 @@ Star Dify on GitHub and be instantly notified of new releases.
 - [Helm Chart by @BorisPolonsky](https://github.com/BorisPolonsky/dify-helm)
 - [YAML file by @Winson-030](https://github.com/Winson-030/dify-kubernetes)
 - [YAML file by @wyy-holding](https://github.com/wyy-holding/dify-k8s)
+- [🚀 NEW! YAML files (Supports Dify v1.6.0) by @Zhoneym](https://github.com/Zhoneym/DifyAI-Kubernetes)
 
 #### Uporaba Terraform za uvajanje
 

README_TR.md

@@ -194,6 +194,7 @@ Yüksek kullanılabilirliğe sahip bir kurulum yapılandırmak isterseniz, Dify'
 - [@BorisPolonsky tarafından Helm Chart](https://github.com/BorisPolonsky/dify-helm)
 - [@Winson-030 tarafından YAML dosyası](https://github.com/Winson-030/dify-kubernetes)
 - [@wyy-holding tarafından YAML dosyası](https://github.com/wyy-holding/dify-k8s)
+- [🚀 YENİ! YAML dosyaları (Dify v1.6.0 destekli) @Zhoneym tarafından](https://github.com/Zhoneym/DifyAI-Kubernetes)
 
 #### Dağıtım için Terraform Kullanımı
 

README_TW.md

@@ -197,12 +197,13 @@ Dify 的所有功能都提供相應的 API，因此您可以輕鬆地將 Dify
 
 如果您需要自定義配置，請參考我們的 [.env.example](docker/.env.example) 文件中的註釋，並在您的 `.env` 文件中更新相應的值。此外，根據您特定的部署環境和需求，您可能需要調整 `docker-compose.yaml` 文件本身，例如更改映像版本、端口映射或卷掛載。進行任何更改後，請重新運行 `docker-compose up -d`。您可以在[這裡](https://docs.dify.ai/getting-started/install-self-hosted/environments)找到可用環境變數的完整列表。
 
-如果您想配置高可用性設置，社區貢獻的 [Helm Charts](https://helm.sh/) 和 YAML 文件允許在 Kubernetes 上部署 Dify。
+如果您想配置高可用性設置，社區貢獻的 [Helm Charts](https://helm.sh/) 和 Kubernetes 資源清單（YAML）允許在 Kubernetes 上部署 Dify。
 
 - [由 @LeoQuote 提供的 Helm Chart](https://github.com/douban/charts/tree/master/charts/dify)
 - [由 @BorisPolonsky 提供的 Helm Chart](https://github.com/BorisPolonsky/dify-helm)
 - [由 @Winson-030 提供的 YAML 文件](https://github.com/Winson-030/dify-kubernetes)
 - [由 @wyy-holding 提供的 YAML 文件](https://github.com/wyy-holding/dify-k8s)
+- [🚀 NEW! YAML 檔案（支援 Dify v1.6.0）by @Zhoneym](https://github.com/Zhoneym/DifyAI-Kubernetes)
 
 ### 使用 Terraform 進行部署
 

README_VI.md

@@ -196,6 +196,7 @@ Nếu bạn muốn cấu hình một cài đặt có độ sẵn sàng cao, có
 - [Helm Chart bởi @BorisPolonsky](https://github.com/BorisPolonsky/dify-helm)
 - [Tệp YAML bởi @Winson-030](https://github.com/Winson-030/dify-kubernetes)
 - [Tệp YAML bởi @wyy-holding](https://github.com/wyy-holding/dify-k8s)
+- [🚀 MỚI! Tệp YAML (Hỗ trợ Dify v1.6.0) bởi @Zhoneym](https://github.com/Zhoneym/DifyAI-Kubernetes)
 
 #### Sử dụng Terraform để Triển khai
 

api/.env.example

@@ -5,17 +5,22 @@
 SECRET_KEY=
 
 # Console API base URL
-CONSOLE_API_URL=http://127.0.0.1:5001
-CONSOLE_WEB_URL=http://127.0.0.1:3000
+CONSOLE_API_URL=http://localhost:5001
+CONSOLE_WEB_URL=http://localhost:3000
 
 # Service API base URL
-SERVICE_API_URL=http://127.0.0.1:5001
+SERVICE_API_URL=http://localhost:5001
 
 # Web APP base URL
-APP_WEB_URL=http://127.0.0.1:3000
+APP_WEB_URL=http://localhost:3000
 
 # Files URL
-FILES_URL=http://127.0.0.1:5001
+FILES_URL=http://localhost:5001
+
+# INTERNAL_FILES_URL is used for plugin daemon communication within Docker network.
+# Set this to the internal Docker service URL for proper plugin file access.
+# Example: INTERNAL_FILES_URL=http://api:5001
+INTERNAL_FILES_URL=http://127.0.0.1:5001
 
 # The time in seconds after the signature is rejected
 FILES_ACCESS_TIMEOUT=300
@@ -133,8 +138,8 @@ SUPABASE_API_KEY=your-access-key
 SUPABASE_URL=your-server-url
 
 # CORS configuration
-WEB_API_CORS_ALLOW_ORIGINS=http://127.0.0.1:3000,*
-CONSOLE_CORS_ALLOW_ORIGINS=http://127.0.0.1:3000,*
+WEB_API_CORS_ALLOW_ORIGINS=http://localhost:3000,*
+CONSOLE_CORS_ALLOW_ORIGINS=http://localhost:3000,*
 
 # Vector database configuration
 # support: weaviate, qdrant, milvus, myscale, relyt, pgvecto_rs, pgvector, pgvector, chroma, opensearch, tidb_vector, couchbase, vikingdb, upstash, lindorm, oceanbase, opengauss, tablestore, matrixone
@@ -444,6 +449,19 @@ MAX_VARIABLE_SIZE=204800
 # hybrid: Save new data to object storage, read from both object storage and RDBMS
 WORKFLOW_NODE_EXECUTION_STORAGE=rdbms
 
+# Repository configuration
+# Core workflow execution repository implementation
+CORE_WORKFLOW_EXECUTION_REPOSITORY=core.repositories.sqlalchemy_workflow_execution_repository.SQLAlchemyWorkflowExecutionRepository
+
+# Core workflow node execution repository implementation
+CORE_WORKFLOW_NODE_EXECUTION_REPOSITORY=core.repositories.sqlalchemy_workflow_node_execution_repository.SQLAlchemyWorkflowNodeExecutionRepository
+
+# API workflow node execution repository implementation
+API_WORKFLOW_NODE_EXECUTION_REPOSITORY=repositories.sqlalchemy_api_workflow_node_execution_repository.DifyAPISQLAlchemyWorkflowNodeExecutionRepository
+
+# API workflow run repository implementation
+API_WORKFLOW_RUN_REPOSITORY=repositories.sqlalchemy_api_workflow_run_repository.DifyAPISQLAlchemyWorkflowRunRepository
+
 # App configuration
 APP_MAX_EXECUTION_TIME=1200
 APP_MAX_ACTIVE_REQUESTS=0

api/commands.py

@@ -11,10 +11,12 @@ from werkzeug.exceptions import NotFound
 
 from configs import dify_config
 from constants.languages import languages
+from core.plugin.entities.plugin import ToolProviderID
 from core.rag.datasource.vdb.vector_factory import Vector
 from core.rag.datasource.vdb.vector_type import VectorType
 from core.rag.index_processor.constant.built_in_field import BuiltInField
 from core.rag.models.document import Document
+from core.tools.utils.system_oauth_encryption import encrypt_system_oauth_params
 from events.app_event import app_was_created
 from extensions.ext_database import db
 from extensions.ext_redis import redis_client
@@ -27,6 +29,7 @@ from models.dataset import Dataset, DatasetCollectionBinding, DatasetMetadata, D
 from models.dataset import Document as DatasetDocument
 from models.model import Account, App, AppAnnotationSetting, AppMode, Conversation, MessageAnnotation
 from models.provider import Provider, ProviderModel
+from models.tools import ToolOAuthSystemClient
 from services.account_service import AccountService, RegisterService, TenantService
 from services.clear_free_plan_tenant_expired_logs import ClearFreePlanTenantExpiredLogs
 from services.plugin.data_migration import PluginDataMigration
@@ -1155,3 +1158,49 @@ def remove_orphaned_files_on_storage(force: bool):
         click.echo(click.style(f"Removed {removed_files} orphaned files without errors.", fg="green"))
     else:
         click.echo(click.style(f"Removed {removed_files} orphaned files, with {error_files} errors.", fg="yellow"))
+
+
+@click.command("setup-system-tool-oauth-client", help="Setup system tool oauth client.")
+@click.option("--provider", prompt=True, help="Provider name")
+@click.option("--client-params", prompt=True, help="Client Params")
+def setup_system_tool_oauth_client(provider, client_params):
+    """
+    Setup system tool oauth client
+    """
+    provider_id = ToolProviderID(provider)
+    provider_name = provider_id.provider_name
+    plugin_id = provider_id.plugin_id
+
+    try:
+        # json validate
+        click.echo(click.style(f"Validating client params: {client_params}", fg="yellow"))
+        json.loads(client_params)
+        click.echo(click.style("Client params validated successfully.", fg="green"))
+
+        click.echo(click.style(f"Encrypting client params: {client_params}", fg="yellow"))
+        click.echo(click.style(f"Using SECRET_KEY: `{dify_config.SECRET_KEY}`", fg="yellow"))
+        oauth_client_params = encrypt_system_oauth_params(client_params)
+        click.echo(click.style("Client params encrypted successfully.", fg="green"))
+    except Exception as e:
+        click.echo(click.style(f"Error parsing client params: {str(e)}", fg="red"))
+        return
+
+    deleted_count = (
+        db.session.query(ToolOAuthSystemClient)
+        .filter_by(
+            provider=provider_name,
+            plugin_id=plugin_id,
+        )
+        .delete()
+    )
+    if deleted_count > 0:
+        click.echo(click.style(f"Deleted {deleted_count} existing oauth client params.", fg="yellow"))
+
+    oauth_client = ToolOAuthSystemClient(
+        provider=provider_name,
+        plugin_id=plugin_id,
+        encrypted_oauth_params=oauth_client_params,
+    )
+    db.session.add(oauth_client)
+    db.session.commit()
+    click.echo(click.style(f"OAuth client params setup successfully. id: {oauth_client.id}", fg="green"))

api/configs/feature/__init__.py

@@ -237,6 +237,13 @@ class FileAccessConfig(BaseSettings):
         default="",
     )
 
+    INTERNAL_FILES_URL: str = Field(
+        description="Internal base URL for file access within Docker network,"
+        " used for plugin daemon and internal service communication."
+        " Falls back to FILES_URL if not specified.",
+        default="",
+    )
+
     FILES_ACCESS_TIMEOUT: int = Field(
         description="Expiration time in seconds for file access URLs",
         default=300,
@@ -530,6 +537,33 @@ class WorkflowNodeExecutionConfig(BaseSettings):
     )
 
 
+class RepositoryConfig(BaseSettings):
+    """
+    Configuration for repository implementations
+    """
+
+    CORE_WORKFLOW_EXECUTION_REPOSITORY: str = Field(
+        description="Repository implementation for WorkflowExecution. Specify as a module path",
+        default="core.repositories.sqlalchemy_workflow_execution_repository.SQLAlchemyWorkflowExecutionRepository",
+    )
+
+    CORE_WORKFLOW_NODE_EXECUTION_REPOSITORY: str = Field(
+        description="Repository implementation for WorkflowNodeExecution. Specify as a module path",
+        default="core.repositories.sqlalchemy_workflow_node_execution_repository.SQLAlchemyWorkflowNodeExecutionRepository",
+    )
+
+    API_WORKFLOW_NODE_EXECUTION_REPOSITORY: str = Field(
+        description="Service-layer repository implementation for WorkflowNodeExecutionModel operations. "
+        "Specify as a module path",
+        default="repositories.sqlalchemy_api_workflow_node_execution_repository.DifyAPISQLAlchemyWorkflowNodeExecutionRepository",
+    )
+
+    API_WORKFLOW_RUN_REPOSITORY: str = Field(
+        description="Service-layer repository implementation for WorkflowRun operations. Specify as a module path",
+        default="repositories.sqlalchemy_api_workflow_run_repository.DifyAPISQLAlchemyWorkflowRunRepository",
+    )
+
+
 class AuthConfig(BaseSettings):
     """
     Configuration for authentication and OAuth
@@ -896,6 +930,7 @@ class FeatureConfig(
     MultiModalTransferConfig,
     PositionConfig,
     RagEtlConfig,
+    RepositoryConfig,
     SecurityConfig,
     ToolConfig,
     UpdateConfig,

api/configs/packaging/__init__.py

@@ -8,11 +8,6 @@ class PackagingInfo(PyProjectTomlConfig):
     Packaging build information
     """
 
-    CURRENT_VERSION: str = Field(
-        description="Dify version",
-        default="1.5.1",
-    )
-
     COMMIT_SHA: str = Field(
         description="SHA-1 checksum of the git commit used to build the app",
         default="",

api/constants/__init__.py

@@ -1,6 +1,7 @@
 from configs import dify_config
 
 HIDDEN_VALUE = "[__HIDDEN__]"
+UNKNOWN_VALUE = "[__UNKNOWN__]"
 UUID_NIL = "00000000-0000-0000-0000-000000000000"
 
 DEFAULT_FILE_NUMBER_LIMITS = 3

api/controllers/console/__init__.py

@@ -56,6 +56,7 @@ from .app import (
     conversation,
     conversation_variables,
     generator,
+    mcp_server,
     message,
     model_config,
     ops_trace,

api/controllers/console/app/audio.py

@@ -90,23 +90,11 @@ class ChatMessageTextApi(Resource):
 
             message_id = args.get("message_id", None)
             text = args.get("text", None)
-            if (
-                app_model.mode in {AppMode.ADVANCED_CHAT.value, AppMode.WORKFLOW.value}
-                and app_model.workflow
-                and app_model.workflow.features_dict
-            ):
-                text_to_speech = app_model.workflow.features_dict.get("text_to_speech")
-                if text_to_speech is None:
-                    raise ValueError("TTS is not enabled")
-                voice = args.get("voice") or text_to_speech.get("voice")
-            else:
-                try:
-                    if app_model.app_model_config is None:
-                        raise ValueError("AppModelConfig not found")
-                    voice = args.get("voice") or app_model.app_model_config.text_to_speech_dict.get("voice")
-                except Exception:
-                    voice = None
-            response = AudioService.transcript_tts(app_model=app_model, text=text, message_id=message_id, voice=voice)
+            voice = args.get("voice", None)
+
+            response = AudioService.transcript_tts(
+                app_model=app_model, text=text, voice=voice, message_id=message_id, is_draft=True
+            )
             return response
         except services.errors.app_model_config.AppModelConfigBrokenError:
             logging.exception("App model config broken.")

api/controllers/console/app/mcp_server.py

@@ -0,0 +1,107 @@
+import json
+from enum import StrEnum
+
+from flask_login import current_user
+from flask_restful import Resource, marshal_with, reqparse
+from werkzeug.exceptions import NotFound
+
+from controllers.console import api
+from controllers.console.app.wraps import get_app_model
+from controllers.console.wraps import account_initialization_required, setup_required
+from extensions.ext_database import db
+from fields.app_fields import app_server_fields
+from libs.login import login_required
+from models.model import AppMCPServer
+
+
+class AppMCPServerStatus(StrEnum):
+    ACTIVE = "active"
+    INACTIVE = "inactive"
+
+
+class AppMCPServerController(Resource):
+    @setup_required
+    @login_required
+    @account_initialization_required
+    @get_app_model
+    @marshal_with(app_server_fields)
+    def get(self, app_model):
+        server = db.session.query(AppMCPServer).filter(AppMCPServer.app_id == app_model.id).first()
+        return server
+
+    @setup_required
+    @login_required
+    @account_initialization_required
+    @get_app_model
+    @marshal_with(app_server_fields)
+    def post(self, app_model):
+        # The role of the current user in the ta table must be editor, admin, or owner
+        if not current_user.is_editor:
+            raise NotFound()
+        parser = reqparse.RequestParser()
+        parser.add_argument("description", type=str, required=True, location="json")
+        parser.add_argument("parameters", type=dict, required=True, location="json")
+        args = parser.parse_args()
+        server = AppMCPServer(
+            name=app_model.name,
+            description=args["description"],
+            parameters=json.dumps(args["parameters"], ensure_ascii=False),
+            status=AppMCPServerStatus.ACTIVE,
+            app_id=app_model.id,
+            tenant_id=current_user.current_tenant_id,
+            server_code=AppMCPServer.generate_server_code(16),
+        )
+        db.session.add(server)
+        db.session.commit()
+        return server
+
+    @setup_required
+    @login_required
+    @account_initialization_required
+    @get_app_model
+    @marshal_with(app_server_fields)
+    def put(self, app_model):
+        if not current_user.is_editor:
+            raise NotFound()
+        parser = reqparse.RequestParser()
+        parser.add_argument("id", type=str, required=True, location="json")
+        parser.add_argument("description", type=str, required=True, location="json")
+        parser.add_argument("parameters", type=dict, required=True, location="json")
+        parser.add_argument("status", type=str, required=False, location="json")
+        args = parser.parse_args()
+        server = db.session.query(AppMCPServer).filter(AppMCPServer.id == args["id"]).first()
+        if not server:
+            raise NotFound()
+        server.description = args["description"]
+        server.parameters = json.dumps(args["parameters"], ensure_ascii=False)
+        if args["status"]:
+            if args["status"] not in [status.value for status in AppMCPServerStatus]:
+                raise ValueError("Invalid status")
+            server.status = args["status"]
+        db.session.commit()
+        return server
+
+
+class AppMCPServerRefreshController(Resource):
+    @setup_required
+    @login_required
+    @account_initialization_required
+    @marshal_with(app_server_fields)
+    def get(self, server_id):
+        if not current_user.is_editor:
+            raise NotFound()
+        server = (
+            db.session.query(AppMCPServer)
+            .filter(AppMCPServer.id == server_id)
+            .filter(AppMCPServer.tenant_id == current_user.current_tenant_id)
+            .first()
+        )
+        if not server:
+            raise NotFound()
+        server.server_code = AppMCPServer.generate_server_code(16)
+        db.session.commit()
+        return server
+
+
+api.add_resource(AppMCPServerController, "/apps/<uuid:app_id>/server")
+api.add_resource(AppMCPServerRefreshController, "/apps/<uuid:server_id>/server/refresh")

api/controllers/console/app/statistic.py

@@ -2,6 +2,7 @@ from datetime import datetime
 from decimal import Decimal
 
 import pytz
+import sqlalchemy as sa
 from flask import jsonify
 from flask_login import current_user
 from flask_restful import Resource, reqparse
@@ -9,10 +10,11 @@ from flask_restful import Resource, reqparse
 from controllers.console import api
 from controllers.console.app.wraps import get_app_model
 from controllers.console.wraps import account_initialization_required, setup_required
+from core.app.entities.app_invoke_entities import InvokeFrom
 from extensions.ext_database import db
 from libs.helper import DatetimeString
 from libs.login import login_required
-from models.model import AppMode
+from models import AppMode, Message
 
 
 class DailyMessageStatistic(Resource):
@@ -85,46 +87,41 @@ class DailyConversationStatistic(Resource):
         parser.add_argument("end", type=DatetimeString("%Y-%m-%d %H:%M"), location="args")
         args = parser.parse_args()
 
-        sql_query = """SELECT
-    DATE(DATE_TRUNC('day', created_at AT TIME ZONE 'UTC' AT TIME ZONE :tz )) AS date,
-    COUNT(DISTINCT messages.conversation_id) AS conversation_count
-FROM
-    messages
-WHERE
-    app_id = :app_id"""
-        arg_dict = {"tz": account.timezone, "app_id": app_model.id}
-
         timezone = pytz.timezone(account.timezone)
         utc_timezone = pytz.utc
 
+        stmt = (
+            sa.select(
+                sa.func.date(
+                    sa.func.date_trunc("day", sa.text("created_at AT TIME ZONE 'UTC' AT TIME ZONE :tz"))
+                ).label("date"),
+                sa.func.count(sa.distinct(Message.conversation_id)).label("conversation_count"),
+            )
+            .select_from(Message)
+            .where(Message.app_id == app_model.id, Message.invoke_from != InvokeFrom.DEBUGGER.value)
+        )
+
         if args["start"]:
             start_datetime = datetime.strptime(args["start"], "%Y-%m-%d %H:%M")
             start_datetime = start_datetime.replace(second=0)
-
             start_datetime_timezone = timezone.localize(start_datetime)
             start_datetime_utc = start_datetime_timezone.astimezone(utc_timezone)
-
-            sql_query += " AND created_at >= :start"
-            arg_dict["start"] = start_datetime_utc
+            stmt = stmt.where(Message.created_at >= start_datetime_utc)
 
         if args["end"]:
             end_datetime = datetime.strptime(args["end"], "%Y-%m-%d %H:%M")
             end_datetime = end_datetime.replace(second=0)
-
             end_datetime_timezone = timezone.localize(end_datetime)
             end_datetime_utc = end_datetime_timezone.astimezone(utc_timezone)
+            stmt = stmt.where(Message.created_at < end_datetime_utc)
 
-            sql_query += " AND created_at < :end"
-            arg_dict["end"] = end_datetime_utc
-
-        sql_query += " GROUP BY date ORDER BY date"
+        stmt = stmt.group_by("date").order_by("date")
 
         response_data = []
-
         with db.engine.begin() as conn:
-            rs = conn.execute(db.text(sql_query), arg_dict)
-            for i in rs:
-                response_data.append({"date": str(i.date), "conversation_count": i.conversation_count})
+            rs = conn.execute(stmt, {"tz": account.timezone})
+            for row in rs:
+                response_data.append({"date": str(row.date), "conversation_count": row.conversation_count})
 
         return jsonify({"data": response_data})
 

api/controllers/console/app/wraps.py

@@ -35,8 +35,6 @@ def get_app_model(view: Optional[Callable] = None, *, mode: Union[AppMode, list[
                 raise AppNotFoundError()
 
             app_mode = AppMode.value_of(app_model.mode)
-            if app_mode == AppMode.CHANNEL:
-                raise AppNotFoundError()
 
             if mode is not None:
                 if isinstance(mode, list):

api/controllers/console/explore/audio.py

@@ -18,7 +18,6 @@ from controllers.console.app.error import (
 from controllers.console.explore.wraps import InstalledAppResource
 from core.errors.error import ModelCurrentlyNotSupportError, ProviderTokenNotInitError, QuotaExceededError
 from core.model_runtime.errors.invoke import InvokeError
-from models.model import AppMode
 from services.audio_service import AudioService
 from services.errors.audio import (
     AudioTooLargeServiceError,
@@ -79,19 +78,9 @@ class ChatTextApi(InstalledAppResource):
 
             message_id = args.get("message_id", None)
             text = args.get("text", None)
-            if (
-                app_model.mode in {AppMode.ADVANCED_CHAT.value, AppMode.WORKFLOW.value}
-                and app_model.workflow
-                and app_model.workflow.features_dict
-            ):
-                text_to_speech = app_model.workflow.features_dict.get("text_to_speech")
-                voice = args.get("voice") or text_to_speech.get("voice")
-            else:
-                try:
-                    voice = args.get("voice") or app_model.app_model_config.text_to_speech_dict.get("voice")
-                except Exception:
-                    voice = None
-            response = AudioService.transcript_tts(app_model=app_model, message_id=message_id, voice=voice, text=text)
+            voice = args.get("voice", None)
+
+            response = AudioService.transcript_tts(app_model=app_model, text=text, voice=voice, message_id=message_id)
             return response
         except services.errors.app_model_config.AppModelConfigBrokenError:
             logging.exception("App model config broken.")

api/controllers/console/workspace/tool_providers.py

@@ -1,25 +1,52 @@
 import io
+from urllib.parse import urlparse
 
-from flask import send_file
+from flask import make_response, redirect, request, send_file
 from flask_login import current_user
-from flask_restful import Resource, reqparse
-from sqlalchemy.orm import Session
+from flask_restful import (
+    Resource,
+    reqparse,
+)
 from werkzeug.exceptions import Forbidden
 
 from configs import dify_config
 from controllers.console import api
-from controllers.console.wraps import account_initialization_required, enterprise_license_required, setup_required
+from controllers.console.wraps import (
+    account_initialization_required,
+    enterprise_license_required,
+    setup_required,
+)
+from core.mcp.auth.auth_flow import auth, handle_callback
+from core.mcp.auth.auth_provider import OAuthClientProvider
+from core.mcp.error import MCPAuthError, MCPError
+from core.mcp.mcp_client import MCPClient
 from core.model_runtime.utils.encoders import jsonable_encoder
-from extensions.ext_database import db
-from libs.helper import alphanumeric, uuid_value
+from core.plugin.entities.plugin import ToolProviderID
+from core.plugin.impl.oauth import OAuthHandler
+from core.tools.entities.tool_entities import CredentialType
+from libs.helper import StrLen, alphanumeric, uuid_value
 from libs.login import login_required
+from services.plugin.oauth_service import OAuthProxyService
 from services.tools.api_tools_manage_service import ApiToolManageService
 from services.tools.builtin_tools_manage_service import BuiltinToolManageService
+from services.tools.mcp_tools_mange_service import MCPToolManageService
 from services.tools.tool_labels_service import ToolLabelsService
 from services.tools.tools_manage_service import ToolCommonService
+from services.tools.tools_transform_service import ToolTransformService
 from services.tools.workflow_tools_manage_service import WorkflowToolManageService
 
 
+def is_valid_url(url: str) -> bool:
+    if not url:
+        return False
+
+    try:
+        parsed = urlparse(url)
+        return all([parsed.scheme, parsed.netloc]) and parsed.scheme in ["http", "https"]
+    except Exception:
+        return False
+
+
 class ToolProviderListApi(Resource):
     @setup_required
     @login_required
@@ -34,7 +61,7 @@ class ToolProviderListApi(Resource):
         req.add_argument(
             "type",
             type=str,
-            choices=["builtin", "model", "api", "workflow"],
+            choices=["builtin", "model", "api", "workflow", "mcp"],
             required=False,
             nullable=True,
             location="args",
@@ -71,7 +98,7 @@ class ToolBuiltinProviderInfoApi(Resource):
         user_id = user.id
         tenant_id = user.current_tenant_id
 
-        return jsonable_encoder(BuiltinToolManageService.get_builtin_tool_provider_info(user_id, tenant_id, provider))
+        return jsonable_encoder(BuiltinToolManageService.get_builtin_tool_provider_info(tenant_id, provider))
 
 
 class ToolBuiltinProviderDeleteApi(Resource):
@@ -80,17 +107,47 @@ class ToolBuiltinProviderDeleteApi(Resource):
     @account_initialization_required
     def post(self, provider):
         user = current_user
-
         if not user.is_admin_or_owner:
             raise Forbidden()
 
+        tenant_id = user.current_tenant_id
+        req = reqparse.RequestParser()
+        req.add_argument("credential_id", type=str, required=True, nullable=False, location="json")
+        args = req.parse_args()
+
+        return BuiltinToolManageService.delete_builtin_tool_provider(
+            tenant_id,
+            provider,
+            args["credential_id"],
+        )
+
+
+class ToolBuiltinProviderAddApi(Resource):
+    @setup_required
+    @login_required
+    @account_initialization_required
+    def post(self, provider):
+        user = current_user
+
         user_id = user.id
         tenant_id = user.current_tenant_id
 
-        return BuiltinToolManageService.delete_builtin_tool_provider(
-            user_id,
-            tenant_id,
-            provider,
+        parser = reqparse.RequestParser()
+        parser.add_argument("credentials", type=dict, required=True, nullable=False, location="json")
+        parser.add_argument("name", type=StrLen(30), required=False, nullable=False, location="json")
+        parser.add_argument("type", type=str, required=True, nullable=False, location="json")
+        args = parser.parse_args()
+
+        if args["type"] not in CredentialType.values():
+            raise ValueError(f"Invalid credential type: {args['type']}")
+
+        return BuiltinToolManageService.add_builtin_tool_provider(
+            user_id=user_id,
+            tenant_id=tenant_id,
+            provider=provider,
+            credentials=args["credentials"],
+            name=args["name"],
+            api_type=CredentialType.of(args["type"]),
         )
 
 
@@ -108,19 +165,20 @@ class ToolBuiltinProviderUpdateApi(Resource):
         tenant_id = user.current_tenant_id
 
         parser = reqparse.RequestParser()
-        parser.add_argument("credentials", type=dict, required=True, nullable=False, location="json")
+        parser.add_argument("credential_id", type=str, required=True, nullable=False, location="json")
+        parser.add_argument("credentials", type=dict, required=False, nullable=True, location="json")
+        parser.add_argument("name", type=StrLen(30), required=False, nullable=True, location="json")
 
         args = parser.parse_args()
 
-        with Session(db.engine) as session:
-            result = BuiltinToolManageService.update_builtin_tool_provider(
-                session=session,
-                user_id=user_id,
-                tenant_id=tenant_id,
-                provider_name=provider,
-                credentials=args["credentials"],
-            )
-            session.commit()
+        result = BuiltinToolManageService.update_builtin_tool_provider(
+            user_id=user_id,
+            tenant_id=tenant_id,
+            provider=provider,
+            credential_id=args["credential_id"],
+            credentials=args.get("credentials", None),
+            name=args.get("name", ""),
+        )
         return result
 
 
@@ -131,9 +189,11 @@ class ToolBuiltinProviderGetCredentialsApi(Resource):
     def get(self, provider):
         tenant_id = current_user.current_tenant_id
 
-        return BuiltinToolManageService.get_builtin_tool_provider_credentials(
-            tenant_id=tenant_id,
-            provider_name=provider,
+        return jsonable_encoder(
+            BuiltinToolManageService.get_builtin_tool_provider_credentials(
+                tenant_id=tenant_id,
+                provider_name=provider,
+            )
         )
 
 
@@ -326,12 +386,15 @@ class ToolBuiltinProviderCredentialsSchemaApi(Resource):
     @setup_required
     @login_required
     @account_initialization_required
-    def get(self, provider):
+    def get(self, provider, credential_type):
         user = current_user
-
         tenant_id = user.current_tenant_id
 
-        return BuiltinToolManageService.list_builtin_provider_credentials_schema(provider, tenant_id)
+        return jsonable_encoder(
+            BuiltinToolManageService.list_builtin_provider_credentials_schema(
+                provider, CredentialType.of(credential_type), tenant_id
+            )
+        )
 
 
 class ToolApiProviderSchemaApi(Resource):
@@ -568,15 +631,12 @@ class ToolApiListApi(Resource):
     @account_initialization_required
     def get(self):
         user = current_user
-
-        user_id = user.id
         tenant_id = user.current_tenant_id
 
         return jsonable_encoder(
             [
                 provider.to_dict()
                 for provider in ApiToolManageService.list_api_tools(
-                    user_id,
                     tenant_id,
                 )
             ]
@@ -613,20 +673,368 @@ class ToolLabelsApi(Resource):
         return jsonable_encoder(ToolLabelsService.list_tool_labels())
 
 
+class ToolPluginOAuthApi(Resource):
+    @setup_required
+    @login_required
+    @account_initialization_required
+    def get(self, provider):
+        tool_provider = ToolProviderID(provider)
+        plugin_id = tool_provider.plugin_id
+        provider_name = tool_provider.provider_name
+
+        # todo check permission
+        user = current_user
+
+        if not user.is_admin_or_owner:
+            raise Forbidden()
+
+        tenant_id = user.current_tenant_id
+        oauth_client_params = BuiltinToolManageService.get_oauth_client(tenant_id=tenant_id, provider=provider)
+        if oauth_client_params is None:
+            raise Forbidden("no oauth available client config found for this tool provider")
+
+        oauth_handler = OAuthHandler()
+        context_id = OAuthProxyService.create_proxy_context(
+            user_id=current_user.id, tenant_id=tenant_id, plugin_id=plugin_id, provider=provider_name
+        )
+        redirect_uri = f"{dify_config.CONSOLE_API_URL}/console/api/oauth/plugin/{provider}/tool/callback"
+        authorization_url_response = oauth_handler.get_authorization_url(
+            tenant_id=tenant_id,
+            user_id=user.id,
+            plugin_id=plugin_id,
+            provider=provider_name,
+            redirect_uri=redirect_uri,
+            system_credentials=oauth_client_params,
+        )
+        response = make_response(jsonable_encoder(authorization_url_response))
+        response.set_cookie(
+            "context_id",
+            context_id,
+            httponly=True,
+            samesite="Lax",
+            max_age=OAuthProxyService.__MAX_AGE__,
+        )
+        return response
+
+
+class ToolOAuthCallback(Resource):
+    @setup_required
+    def get(self, provider):
+        context_id = request.cookies.get("context_id")
+        if not context_id:
+            raise Forbidden("context_id not found")
+
+        context = OAuthProxyService.use_proxy_context(context_id)
+        if context is None:
+            raise Forbidden("Invalid context_id")
+
+        tool_provider = ToolProviderID(provider)
+        plugin_id = tool_provider.plugin_id
+        provider_name = tool_provider.provider_name
+        user_id, tenant_id = context.get("user_id"), context.get("tenant_id")
+
+        oauth_handler = OAuthHandler()
+        oauth_client_params = BuiltinToolManageService.get_oauth_client(tenant_id, provider)
+        if oauth_client_params is None:
+            raise Forbidden("no oauth available client config found for this tool provider")
+
+        redirect_uri = f"{dify_config.CONSOLE_API_URL}/console/api/oauth/plugin/{provider}/tool/callback"
+        credentials = oauth_handler.get_credentials(
+            tenant_id=tenant_id,
+            user_id=user_id,
+            plugin_id=plugin_id,
+            provider=provider_name,
+            redirect_uri=redirect_uri,
+            system_credentials=oauth_client_params,
+            request=request,
+        ).credentials
+
+        if not credentials:
+            raise Exception("the plugin credentials failed")
+
+        # add credentials to database
+        BuiltinToolManageService.add_builtin_tool_provider(
+            user_id=user_id,
+            tenant_id=tenant_id,
+            provider=provider,
+            credentials=dict(credentials),
+            api_type=CredentialType.OAUTH2,
+        )
+        return redirect(f"{dify_config.CONSOLE_WEB_URL}/oauth-callback")
+
+
+class ToolBuiltinProviderSetDefaultApi(Resource):
+    @setup_required
+    @login_required
+    @account_initialization_required
+    def post(self, provider):
+        parser = reqparse.RequestParser()
+        parser.add_argument("id", type=str, required=True, nullable=False, location="json")
+        args = parser.parse_args()
+        return BuiltinToolManageService.set_default_provider(
+            tenant_id=current_user.current_tenant_id, user_id=current_user.id, provider=provider, id=args["id"]
+        )
+
+
+class ToolOAuthCustomClient(Resource):
+    @setup_required
+    @login_required
+    @account_initialization_required
+    def post(self, provider):
+        parser = reqparse.RequestParser()
+        parser.add_argument("client_params", type=dict, required=False, nullable=True, location="json")
+        parser.add_argument("enable_oauth_custom_client", type=bool, required=False, nullable=True, location="json")
+        args = parser.parse_args()
+
+        user = current_user
+
+        if not user.is_admin_or_owner:
+            raise Forbidden()
+
+        return BuiltinToolManageService.save_custom_oauth_client_params(
+            tenant_id=user.current_tenant_id,
+            provider=provider,
+            client_params=args.get("client_params", {}),
+            enable_oauth_custom_client=args.get("enable_oauth_custom_client", True),
+        )
+
+    @setup_required
+    @login_required
+    @account_initialization_required
+    def get(self, provider):
+        return jsonable_encoder(
+            BuiltinToolManageService.get_custom_oauth_client_params(
+                tenant_id=current_user.current_tenant_id, provider=provider
+            )
+        )
+    
+    @setup_required
+    @login_required
+    @account_initialization_required
+    def delete(self, provider):
+        return jsonable_encoder(
+            BuiltinToolManageService.delete_custom_oauth_client_params(
+                tenant_id=current_user.current_tenant_id, provider=provider
+            )
+        )
+
+
+class ToolBuiltinProviderGetOauthClientSchemaApi(Resource):
+    @setup_required
+    @login_required
+    @account_initialization_required
+    def get(self, provider):
+        return jsonable_encoder(
+            BuiltinToolManageService.get_builtin_tool_provider_oauth_client_schema(
+                tenant_id=current_user.current_tenant_id, provider_name=provider
+            )
+        )
+
+
+class ToolBuiltinProviderGetCredentialInfoApi(Resource):
+    @setup_required
+    @login_required
+    @account_initialization_required
+    def get(self, provider):
+        tenant_id = current_user.current_tenant_id
+
+        return jsonable_encoder(
+            BuiltinToolManageService.get_builtin_tool_provider_credential_info(
+                tenant_id=tenant_id,
+                provider=provider,
+            )
+        )
+
+class ToolProviderMCPApi(Resource):
+    @setup_required
+    @login_required
+    @account_initialization_required
+    def post(self):
+        parser = reqparse.RequestParser()
+        parser.add_argument("server_url", type=str, required=True, nullable=False, location="json")
+        parser.add_argument("name", type=str, required=True, nullable=False, location="json")
+        parser.add_argument("icon", type=str, required=True, nullable=False, location="json")
+        parser.add_argument("icon_type", type=str, required=True, nullable=False, location="json")
+        parser.add_argument("icon_background", type=str, required=False, nullable=True, location="json", default="")
+        parser.add_argument("server_identifier", type=str, required=True, nullable=False, location="json")
+        args = parser.parse_args()
+        user = current_user
+        if not is_valid_url(args["server_url"]):
+            raise ValueError("Server URL is not valid.")
+        return jsonable_encoder(
+            MCPToolManageService.create_mcp_provider(
+                tenant_id=user.current_tenant_id,
+                server_url=args["server_url"],
+                name=args["name"],
+                icon=args["icon"],
+                icon_type=args["icon_type"],
+                icon_background=args["icon_background"],
+                user_id=user.id,
+                server_identifier=args["server_identifier"],
+            )
+        )
+
+    @setup_required
+    @login_required
+    @account_initialization_required
+    def put(self):
+        parser = reqparse.RequestParser()
+        parser.add_argument("server_url", type=str, required=True, nullable=False, location="json")
+        parser.add_argument("name", type=str, required=True, nullable=False, location="json")
+        parser.add_argument("icon", type=str, required=True, nullable=False, location="json")
+        parser.add_argument("icon_type", type=str, required=True, nullable=False, location="json")
+        parser.add_argument("icon_background", type=str, required=False, nullable=True, location="json")
+        parser.add_argument("provider_id", type=str, required=True, nullable=False, location="json")
+        parser.add_argument("server_identifier", type=str, required=True, nullable=False, location="json")
+        args = parser.parse_args()
+        if not is_valid_url(args["server_url"]):
+            if "[__HIDDEN__]" in args["server_url"]:
+                pass
+            else:
+                raise ValueError("Server URL is not valid.")
+        MCPToolManageService.update_mcp_provider(
+            tenant_id=current_user.current_tenant_id,
+            provider_id=args["provider_id"],
+            server_url=args["server_url"],
+            name=args["name"],
+            icon=args["icon"],
+            icon_type=args["icon_type"],
+            icon_background=args["icon_background"],
+            server_identifier=args["server_identifier"],
+        )
+        return {"result": "success"}
+
+    @setup_required
+    @login_required
+    @account_initialization_required
+    def delete(self):
+        parser = reqparse.RequestParser()
+        parser.add_argument("provider_id", type=str, required=True, nullable=False, location="json")
+        args = parser.parse_args()
+        MCPToolManageService.delete_mcp_tool(tenant_id=current_user.current_tenant_id, provider_id=args["provider_id"])
+        return {"result": "success"}
+
+
+class ToolMCPAuthApi(Resource):
+    @setup_required
+    @login_required
+    @account_initialization_required
+    def post(self):
+        parser = reqparse.RequestParser()
+        parser.add_argument("provider_id", type=str, required=True, nullable=False, location="json")
+        parser.add_argument("authorization_code", type=str, required=False, nullable=True, location="json")
+        args = parser.parse_args()
+        provider_id = args["provider_id"]
+        tenant_id = current_user.current_tenant_id
+        provider = MCPToolManageService.get_mcp_provider_by_provider_id(provider_id, tenant_id)
+        if not provider:
+            raise ValueError("provider not found")
+        try:
+            with MCPClient(
+                provider.decrypted_server_url,
+                provider_id,
+                tenant_id,
+                authed=False,
+                authorization_code=args["authorization_code"],
+                for_list=True,
+            ):
+                MCPToolManageService.update_mcp_provider_credentials(
+                    mcp_provider=provider,
+                    credentials=provider.decrypted_credentials,
+                    authed=True,
+                )
+                return {"result": "success"}
+
+        except MCPAuthError:
+            auth_provider = OAuthClientProvider(provider_id, tenant_id, for_list=True)
+            return auth(auth_provider, provider.decrypted_server_url, args["authorization_code"])
+        except MCPError as e:
+            MCPToolManageService.update_mcp_provider_credentials(
+                mcp_provider=provider,
+                credentials={},
+                authed=False,
+            )
+            raise ValueError(f"Failed to connect to MCP server: {e}") from e
+
+
+class ToolMCPDetailApi(Resource):
+    @setup_required
+    @login_required
+    @account_initialization_required
+    def get(self, provider_id):
+        user = current_user
+        provider = MCPToolManageService.get_mcp_provider_by_provider_id(provider_id, user.current_tenant_id)
+        return jsonable_encoder(ToolTransformService.mcp_provider_to_user_provider(provider, for_list=True))
+
+
+class ToolMCPListAllApi(Resource):
+    @setup_required
+    @login_required
+    @account_initialization_required
+    def get(self):
+        user = current_user
+        tenant_id = user.current_tenant_id
+
+        tools = MCPToolManageService.retrieve_mcp_tools(tenant_id=tenant_id)
+
+        return [tool.to_dict() for tool in tools]
+
+
+class ToolMCPUpdateApi(Resource):
+    @setup_required
+    @login_required
+    @account_initialization_required
+    def get(self, provider_id):
+        tenant_id = current_user.current_tenant_id
+        tools = MCPToolManageService.list_mcp_tool_from_remote_server(
+            tenant_id=tenant_id,
+            provider_id=provider_id,
+        )
+        return jsonable_encoder(tools)
+
+
+class ToolMCPCallbackApi(Resource):
+    def get(self):
+        parser = reqparse.RequestParser()
+        parser.add_argument("code", type=str, required=True, nullable=False, location="args")
+        parser.add_argument("state", type=str, required=True, nullable=False, location="args")
+        args = parser.parse_args()
+        state_key = args["state"]
+        authorization_code = args["code"]
+        handle_callback(state_key, authorization_code)
+        return redirect(f"{dify_config.CONSOLE_WEB_URL}/oauth-callback")
+
+
 # tool provider
 api.add_resource(ToolProviderListApi, "/workspaces/current/tool-providers")
 
+# tool oauth
+api.add_resource(ToolPluginOAuthApi, "/oauth/plugin/<path:provider>/tool/authorization-url")
+api.add_resource(ToolOAuthCallback, "/oauth/plugin/<path:provider>/tool/callback")
+api.add_resource(ToolOAuthCustomClient, "/workspaces/current/tool-provider/builtin/<path:provider>/oauth/custom-client")
+
 # builtin tool provider
 api.add_resource(ToolBuiltinProviderListToolsApi, "/workspaces/current/tool-provider/builtin/<path:provider>/tools")
 api.add_resource(ToolBuiltinProviderInfoApi, "/workspaces/current/tool-provider/builtin/<path:provider>/info")
+api.add_resource(ToolBuiltinProviderAddApi, "/workspaces/current/tool-provider/builtin/<path:provider>/add")
 api.add_resource(ToolBuiltinProviderDeleteApi, "/workspaces/current/tool-provider/builtin/<path:provider>/delete")
 api.add_resource(ToolBuiltinProviderUpdateApi, "/workspaces/current/tool-provider/builtin/<path:provider>/update")
+api.add_resource(
+    ToolBuiltinProviderSetDefaultApi, "/workspaces/current/tool-provider/builtin/<path:provider>/default-credential"
+)
+api.add_resource(
+    ToolBuiltinProviderGetCredentialInfoApi, "/workspaces/current/tool-provider/builtin/<path:provider>/credential/info"
+)
 api.add_resource(
     ToolBuiltinProviderGetCredentialsApi, "/workspaces/current/tool-provider/builtin/<path:provider>/credentials"
 )
 api.add_resource(
     ToolBuiltinProviderCredentialsSchemaApi,
-    "/workspaces/current/tool-provider/builtin/<path:provider>/credentials_schema",
+    "/workspaces/current/tool-provider/builtin/<path:provider>/credential/schema/<path:credential_type>",
+)
+api.add_resource(
+    ToolBuiltinProviderGetOauthClientSchemaApi,
+    "/workspaces/current/tool-provider/builtin/<path:provider>/oauth/client-schema",
 )
 api.add_resource(ToolBuiltinProviderIconApi, "/workspaces/current/tool-provider/builtin/<path:provider>/icon")
 
@@ -647,8 +1055,15 @@ api.add_resource(ToolWorkflowProviderDeleteApi, "/workspaces/current/tool-provid
 api.add_resource(ToolWorkflowProviderGetApi, "/workspaces/current/tool-provider/workflow/get")
 api.add_resource(ToolWorkflowProviderListToolApi, "/workspaces/current/tool-provider/workflow/tools")
 
+# mcp tool provider
+api.add_resource(ToolMCPDetailApi, "/workspaces/current/tool-provider/mcp/tools/<path:provider_id>")
+api.add_resource(ToolProviderMCPApi, "/workspaces/current/tool-provider/mcp")
+api.add_resource(ToolMCPUpdateApi, "/workspaces/current/tool-provider/mcp/update/<path:provider_id>")
+api.add_resource(ToolMCPAuthApi, "/workspaces/current/tool-provider/mcp/auth")
+api.add_resource(ToolMCPCallbackApi, "/mcp/oauth/callback")
+
 api.add_resource(ToolBuiltinListApi, "/workspaces/current/tools/builtin")
 api.add_resource(ToolApiListApi, "/workspaces/current/tools/api")
+api.add_resource(ToolMCPListAllApi, "/workspaces/current/tools/mcp")
 api.add_resource(ToolWorkflowListApi, "/workspaces/current/tools/workflow")
-
 api.add_resource(ToolLabelsApi, "/workspaces/current/tool-labels")

api/controllers/files/upload.py

@@ -87,7 +87,5 @@ class PluginUploadFileApi(Resource):
         except services.errors.file.UnsupportedFileTypeError:
             raise UnsupportedFileTypeError()
 
-        return tool_file, 201
-
 
 api.add_resource(PluginUploadFileApi, "/files/upload/for-plugin")

api/controllers/inner_api/plugin/plugin.py

@@ -175,6 +175,7 @@ class PluginInvokeToolApi(Resource):
                     provider=payload.provider,
                     tool_name=payload.tool,
                     tool_parameters=payload.tool_parameters,
+                    credential_id=payload.credential_id
                 ),
             )
 

api/controllers/mcp/__init__.py

@@ -0,0 +1,8 @@
+from flask import Blueprint
+
+from libs.external_api import ExternalApi
+
+bp = Blueprint("mcp", __name__, url_prefix="/mcp")
+api = ExternalApi(bp)
+
+from . import mcp

api/controllers/mcp/mcp.py

@@ -0,0 +1,104 @@
+from flask_restful import Resource, reqparse
+from pydantic import ValidationError
+
+from controllers.console.app.mcp_server import AppMCPServerStatus
+from controllers.mcp import api
+from core.app.app_config.entities import VariableEntity
+from core.mcp import types
+from core.mcp.server.streamable_http import MCPServerStreamableHTTPRequestHandler
+from core.mcp.types import ClientNotification, ClientRequest
+from core.mcp.utils import create_mcp_error_response
+from extensions.ext_database import db
+from libs import helper
+from models.model import App, AppMCPServer, AppMode
+
+
+class MCPAppApi(Resource):
+    def post(self, server_code):
+        def int_or_str(value):
+            if isinstance(value, (int, str)):
+                return value
+            else:
+                return None
+
+        parser = reqparse.RequestParser()
+        parser.add_argument("jsonrpc", type=str, required=True, location="json")
+        parser.add_argument("method", type=str, required=True, location="json")
+        parser.add_argument("params", type=dict, required=False, location="json")
+        parser.add_argument("id", type=int_or_str, required=False, location="json")
+        args = parser.parse_args()
+
+        request_id = args.get("id")
+
+        server = db.session.query(AppMCPServer).filter(AppMCPServer.server_code == server_code).first()
+        if not server:
+            return helper.compact_generate_response(
+                create_mcp_error_response(request_id, types.INVALID_REQUEST, "Server Not Found")
+            )
+
+        if server.status != AppMCPServerStatus.ACTIVE:
+            return helper.compact_generate_response(
+                create_mcp_error_response(request_id, types.INVALID_REQUEST, "Server is not active")
+            )
+
+        app = db.session.query(App).filter(App.id == server.app_id).first()
+        if not app:
+            return helper.compact_generate_response(
+                create_mcp_error_response(request_id, types.INVALID_REQUEST, "App Not Found")
+            )
+
+        if app.mode in {AppMode.ADVANCED_CHAT.value, AppMode.WORKFLOW.value}:
+            workflow = app.workflow
+            if workflow is None:
+                return helper.compact_generate_response(
+                    create_mcp_error_response(request_id, types.INVALID_REQUEST, "App is unavailable")
+                )
+
+            user_input_form = workflow.user_input_form(to_old_structure=True)
+        else:
+            app_model_config = app.app_model_config
+            if app_model_config is None:
+                return helper.compact_generate_response(
+                    create_mcp_error_response(request_id, types.INVALID_REQUEST, "App is unavailable")
+                )
+
+            features_dict = app_model_config.to_dict()
+            user_input_form = features_dict.get("user_input_form", [])
+        converted_user_input_form: list[VariableEntity] = []
+        try:
+            for item in user_input_form:
+                variable_type = item.get("type", "") or list(item.keys())[0]
+                variable = item[variable_type]
+                converted_user_input_form.append(
+                    VariableEntity(
+                        type=variable_type,
+                        variable=variable.get("variable"),
+                        description=variable.get("description") or "",
+                        label=variable.get("label"),
+                        required=variable.get("required", False),
+                        max_length=variable.get("max_length"),
+                        options=variable.get("options") or [],
+                    )
+                )
+        except ValidationError as e:
+            return helper.compact_generate_response(
+                create_mcp_error_response(request_id, types.INVALID_PARAMS, f"Invalid user_input_form: {str(e)}")
+            )
+
+        try:
+            request: ClientRequest | ClientNotification = ClientRequest.model_validate(args)
+        except ValidationError as e:
+            try:
+                notification = ClientNotification.model_validate(args)
+                request = notification
+            except ValidationError as e:
+                return helper.compact_generate_response(
+                    create_mcp_error_response(request_id, types.INVALID_PARAMS, f"Invalid MCP request: {str(e)}")
+                )
+
+        mcp_server_handler = MCPServerStreamableHTTPRequestHandler(app, request, converted_user_input_form)
+        response = mcp_server_handler.handle()
+        return helper.compact_generate_response(response)
+
+
+api.add_resource(MCPAppApi, "/server/<string:server_code>/mcp")

api/controllers/service_api/app/audio.py

@@ -20,7 +20,7 @@ from controllers.service_api.app.error import (
 from controllers.service_api.wraps import FetchUserArg, WhereisUserArg, validate_app_token
 from core.errors.error import ModelCurrentlyNotSupportError, ProviderTokenNotInitError, QuotaExceededError
 from core.model_runtime.errors.invoke import InvokeError
-from models.model import App, AppMode, EndUser
+from models.model import App, EndUser
 from services.audio_service import AudioService
 from services.errors.audio import (
     AudioTooLargeServiceError,
@@ -78,20 +78,9 @@ class TextApi(Resource):
 
             message_id = args.get("message_id", None)
             text = args.get("text", None)
-            if (
-                app_model.mode in {AppMode.ADVANCED_CHAT.value, AppMode.WORKFLOW.value}
-                and app_model.workflow
-                and app_model.workflow.features_dict
-            ):
-                text_to_speech = app_model.workflow.features_dict.get("text_to_speech", {})
-                voice = args.get("voice") or text_to_speech.get("voice")
-            else:
-                try:
-                    voice = args.get("voice") or app_model.app_model_config.text_to_speech_dict.get("voice")
-                except Exception:
-                    voice = None
+            voice = args.get("voice", None)
             response = AudioService.transcript_tts(
-                app_model=app_model, message_id=message_id, end_user=end_user.external_user_id, voice=voice, text=text
+                app_model=app_model, text=text, voice=voice, end_user=end_user.external_user_id, message_id=message_id
             )
 
             return response

api/controllers/service_api/app/workflow.py

@@ -3,7 +3,7 @@ import logging
 from dateutil.parser import isoparse
 from flask_restful import Resource, fields, marshal_with, reqparse
 from flask_restful.inputs import int_range
-from sqlalchemy.orm import Session
+from sqlalchemy.orm import Session, sessionmaker
 from werkzeug.exceptions import InternalServerError
 
 from controllers.service_api import api
@@ -30,7 +30,7 @@ from fields.workflow_app_log_fields import workflow_app_log_pagination_fields
 from libs import helper
 from libs.helper import TimestampField
 from models.model import App, AppMode, EndUser
-from models.workflow import WorkflowRun
+from repositories.factory import DifyAPIRepositoryFactory
 from services.app_generate_service import AppGenerateService
 from services.errors.llm import InvokeRateLimitError
 from services.workflow_app_service import WorkflowAppService
@@ -63,7 +63,15 @@ class WorkflowRunDetailApi(Resource):
         if app_mode not in [AppMode.WORKFLOW, AppMode.ADVANCED_CHAT]:
             raise NotWorkflowAppError()
 
-        workflow_run = db.session.query(WorkflowRun).filter(WorkflowRun.id == workflow_run_id).first()
+        # Use repository to get workflow run
+        session_maker = sessionmaker(bind=db.engine, expire_on_commit=False)
+        workflow_run_repo = DifyAPIRepositoryFactory.create_api_workflow_run_repository(session_maker)
+
+        workflow_run = workflow_run_repo.get_workflow_run_by_id(
+            tenant_id=app_model.tenant_id,
+            app_id=app_model.id,
+            run_id=workflow_run_id,
+        )
         return workflow_run
 
 

api/controllers/service_api/dataset/document.py

@@ -211,6 +211,9 @@ class DocumentAddByFileApi(DatasetApiResource):
         if not dataset:
             raise ValueError("Dataset does not exist.")
 
+        if dataset.provider == "external":
+            raise ValueError("External datasets are not supported.")
+
         indexing_technique = args.get("indexing_technique") or dataset.indexing_technique
         if not indexing_technique:
             raise ValueError("indexing_technique is required.")
@@ -301,6 +304,9 @@ class DocumentUpdateByFileApi(DatasetApiResource):
         if not dataset:
             raise ValueError("Dataset does not exist.")
 
+        if dataset.provider == "external":
+            raise ValueError("External datasets are not supported.")
+
         # indexing_technique is already set in dataset since this is an update
         args["indexing_technique"] = dataset.indexing_technique
 

api/controllers/web/audio.py

@@ -19,7 +19,7 @@ from controllers.web.error import (
 from controllers.web.wraps import WebApiResource
 from core.errors.error import ModelCurrentlyNotSupportError, ProviderTokenNotInitError, QuotaExceededError
 from core.model_runtime.errors.invoke import InvokeError
-from models.model import App, AppMode
+from models.model import App
 from services.audio_service import AudioService
 from services.errors.audio import (
     AudioTooLargeServiceError,
@@ -77,21 +77,9 @@ class TextApi(WebApiResource):
 
             message_id = args.get("message_id", None)
             text = args.get("text", None)
-            if (
-                app_model.mode in {AppMode.ADVANCED_CHAT.value, AppMode.WORKFLOW.value}
-                and app_model.workflow
-                and app_model.workflow.features_dict
-            ):
-                text_to_speech = app_model.workflow.features_dict.get("text_to_speech", {})
-                voice = args.get("voice") or text_to_speech.get("voice")
-            else:
-                try:
-                    voice = args.get("voice") or app_model.app_model_config.text_to_speech_dict.get("voice")
-                except Exception:
-                    voice = None
-
+            voice = args.get("voice", None)
             response = AudioService.transcript_tts(
-                app_model=app_model, message_id=message_id, end_user=end_user.external_user_id, voice=voice, text=text
+                app_model=app_model, text=text, voice=voice, end_user=end_user.external_user_id, message_id=message_id
             )
 
             return response

api/core/agent/base_agent_runner.py

@@ -3,6 +3,8 @@ import logging
 import uuid
 from typing import Optional, Union, cast
 
+from sqlalchemy import select
+
 from core.agent.entities import AgentEntity, AgentToolEntity
 from core.app.app_config.features.file_upload.manager import FileUploadConfigManager
 from core.app.apps.agent_chat.app_config_manager import AgentChatAppConfig
@@ -161,10 +163,14 @@ class BaseAgentRunner(AppRunner):
             if parameter.type == ToolParameter.ToolParameterType.SELECT:
                 enum = [option.value for option in parameter.options] if parameter.options else []
 
-            message_tool.parameters["properties"][parameter.name] = {
-                "type": parameter_type,
-                "description": parameter.llm_description or "",
-            }
+            message_tool.parameters["properties"][parameter.name] = (
+                {
+                    "type": parameter_type,
+                    "description": parameter.llm_description or "",
+                }
+                if parameter.input_schema is None
+                else parameter.input_schema
+            )
 
             if len(enum) > 0:
                 message_tool.parameters["properties"][parameter.name]["enum"] = enum
@@ -254,10 +260,14 @@ class BaseAgentRunner(AppRunner):
             if parameter.type == ToolParameter.ToolParameterType.SELECT:
                 enum = [option.value for option in parameter.options] if parameter.options else []
 
-            prompt_tool.parameters["properties"][parameter.name] = {
-                "type": parameter_type,
-                "description": parameter.llm_description or "",
-            }
+            prompt_tool.parameters["properties"][parameter.name] = (
+                {
+                    "type": parameter_type,
+                    "description": parameter.llm_description or "",
+                }
+                if parameter.input_schema is None
+                else parameter.input_schema
+            )
 
             if len(enum) > 0:
                 prompt_tool.parameters["properties"][parameter.name]["enum"] = enum
@@ -409,12 +419,15 @@ class BaseAgentRunner(AppRunner):
             if isinstance(prompt_message, SystemPromptMessage):
                 result.append(prompt_message)
 
-        messages: list[Message] = (
-            db.session.query(Message)
-            .filter(
-                Message.conversation_id == self.message.conversation_id,
+        messages = (
+            (
+                db.session.execute(
+                    select(Message)
+                    .where(Message.conversation_id == self.message.conversation_id)
+                    .order_by(Message.created_at.desc())
+                )
             )
-            .order_by(Message.created_at.desc())
+            .scalars()
             .all()
         )
 

api/core/agent/entities.py

@@ -16,6 +16,7 @@ class AgentToolEntity(BaseModel):
     tool_name: str
     tool_parameters: dict[str, Any] = Field(default_factory=dict)
     plugin_unique_identifier: str | None = None
+    credential_id: str | None = None
 
 
 class AgentPromptEntity(BaseModel):

api/core/agent/plugin_entities.py

@@ -85,7 +85,7 @@ class AgentStrategyEntity(BaseModel):
     description: I18nObject = Field(..., description="The description of the agent strategy")
     output_schema: Optional[dict] = None
     features: Optional[list[AgentFeature]] = None
-
+    meta_version: Optional[str] = None
     # pydantic configs
     model_config = ConfigDict(protected_namespaces=())
 

api/core/agent/strategy/base.py

@@ -4,6 +4,7 @@ from typing import Any, Optional
 
 from core.agent.entities import AgentInvokeMessage
 from core.agent.plugin_entities import AgentStrategyParameter
+from core.plugin.entities.request import InvokeCredentials
 
 
 class BaseAgentStrategy(ABC):
@@ -18,11 +19,12 @@ class BaseAgentStrategy(ABC):
         conversation_id: Optional[str] = None,
         app_id: Optional[str] = None,
         message_id: Optional[str] = None,
+        credentials: Optional[InvokeCredentials] = None,
     ) -> Generator[AgentInvokeMessage, None, None]:
         """
         Invoke the agent strategy.
         """
-        yield from self._invoke(params, user_id, conversation_id, app_id, message_id)
+        yield from self._invoke(params, user_id, conversation_id, app_id, message_id, credentials)
 
     def get_parameters(self) -> Sequence[AgentStrategyParameter]:
         """
@@ -38,5 +40,6 @@ class BaseAgentStrategy(ABC):
         conversation_id: Optional[str] = None,
         app_id: Optional[str] = None,
         message_id: Optional[str] = None,
+        credentials: Optional[InvokeCredentials] = None,
     ) -> Generator[AgentInvokeMessage, None, None]:
         pass

api/core/agent/strategy/plugin.py

@@ -4,6 +4,7 @@ from typing import Any, Optional
 from core.agent.entities import AgentInvokeMessage
 from core.agent.plugin_entities import AgentStrategyEntity, AgentStrategyParameter
 from core.agent.strategy.base import BaseAgentStrategy
+from core.plugin.entities.request import InvokeCredentials, PluginInvokeContext
 from core.plugin.impl.agent import PluginAgentClient
 from core.plugin.utils.converter import convert_parameters_to_plugin_format
 
@@ -15,10 +16,12 @@ class PluginAgentStrategy(BaseAgentStrategy):
 
     tenant_id: str
     declaration: AgentStrategyEntity
+    meta_version: str | None = None
 
-    def __init__(self, tenant_id: str, declaration: AgentStrategyEntity):
+    def __init__(self, tenant_id: str, declaration: AgentStrategyEntity, meta_version: str | None):
         self.tenant_id = tenant_id
         self.declaration = declaration
+        self.meta_version = meta_version
 
     def get_parameters(self) -> Sequence[AgentStrategyParameter]:
         return self.declaration.parameters
@@ -38,6 +41,7 @@ class PluginAgentStrategy(BaseAgentStrategy):
         conversation_id: Optional[str] = None,
         app_id: Optional[str] = None,
         message_id: Optional[str] = None,
+        credentials: Optional[InvokeCredentials] = None,
     ) -> Generator[AgentInvokeMessage, None, None]:
         """
         Invoke the agent strategy.
@@ -56,4 +60,7 @@ class PluginAgentStrategy(BaseAgentStrategy):
             conversation_id=conversation_id,
             app_id=app_id,
             message_id=message_id,
+            context=PluginInvokeContext(
+                credentials=credentials or InvokeCredentials()
+            ),
         )

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

@@ -39,6 +39,7 @@ class AgentConfigManager:
                         "provider_id": tool["provider_id"],
                         "tool_name": tool["tool_name"],
                         "tool_parameters": tool.get("tool_parameters", {}),
+                        "credential_id": tool.get("credential_id", None),
                     }
 
                     agent_tools.append(AgentToolEntity(**agent_tool_properties))

api/core/app/apps/advanced_chat/app_generator.py

@@ -25,8 +25,7 @@ from core.app.entities.task_entities import ChatbotAppBlockingResponse, ChatbotA
 from core.model_runtime.errors.invoke import InvokeAuthorizationError
 from core.ops.ops_trace_manager import TraceQueueManager
 from core.prompt.utils.get_thread_messages_length import get_thread_messages_length
-from core.repositories import SQLAlchemyWorkflowNodeExecutionRepository
-from core.repositories.sqlalchemy_workflow_execution_repository import SQLAlchemyWorkflowExecutionRepository
+from core.repositories import DifyCoreRepositoryFactory
 from core.workflow.repositories.draft_variable_repository import (
     DraftVariableSaverFactory,
 )
@@ -183,14 +182,14 @@ class AdvancedChatAppGenerator(MessageBasedAppGenerator):
             workflow_triggered_from = WorkflowRunTriggeredFrom.DEBUGGING
         else:
             workflow_triggered_from = WorkflowRunTriggeredFrom.APP_RUN
-        workflow_execution_repository = SQLAlchemyWorkflowExecutionRepository(
+        workflow_execution_repository = DifyCoreRepositoryFactory.create_workflow_execution_repository(
             session_factory=session_factory,
             user=user,
             app_id=application_generate_entity.app_config.app_id,
             triggered_from=workflow_triggered_from,
         )
         # Create workflow node execution repository
-        workflow_node_execution_repository = SQLAlchemyWorkflowNodeExecutionRepository(
+        workflow_node_execution_repository = DifyCoreRepositoryFactory.create_workflow_node_execution_repository(
             session_factory=session_factory,
             user=user,
             app_id=application_generate_entity.app_config.app_id,
@@ -260,14 +259,14 @@ class AdvancedChatAppGenerator(MessageBasedAppGenerator):
         # Create session factory
         session_factory = sessionmaker(bind=db.engine, expire_on_commit=False)
         # Create workflow execution(aka workflow run) repository
-        workflow_execution_repository = SQLAlchemyWorkflowExecutionRepository(
+        workflow_execution_repository = DifyCoreRepositoryFactory.create_workflow_execution_repository(
             session_factory=session_factory,
             user=user,
             app_id=application_generate_entity.app_config.app_id,
             triggered_from=WorkflowRunTriggeredFrom.DEBUGGING,
         )
         # Create workflow node execution repository
-        workflow_node_execution_repository = SQLAlchemyWorkflowNodeExecutionRepository(
+        workflow_node_execution_repository = DifyCoreRepositoryFactory.create_workflow_node_execution_repository(
             session_factory=session_factory,
             user=user,
             app_id=application_generate_entity.app_config.app_id,
@@ -343,14 +342,14 @@ class AdvancedChatAppGenerator(MessageBasedAppGenerator):
         # Create session factory
         session_factory = sessionmaker(bind=db.engine, expire_on_commit=False)
         # Create workflow execution(aka workflow run) repository
-        workflow_execution_repository = SQLAlchemyWorkflowExecutionRepository(
+        workflow_execution_repository = DifyCoreRepositoryFactory.create_workflow_execution_repository(
             session_factory=session_factory,
             user=user,
             app_id=application_generate_entity.app_config.app_id,
             triggered_from=WorkflowRunTriggeredFrom.DEBUGGING,
         )
         # Create workflow node execution repository
-        workflow_node_execution_repository = SQLAlchemyWorkflowNodeExecutionRepository(
+        workflow_node_execution_repository = DifyCoreRepositoryFactory.create_workflow_node_execution_repository(
             session_factory=session_factory,
             user=user,
             app_id=application_generate_entity.app_config.app_id,

api/core/app/apps/workflow/app_generator.py

@@ -23,8 +23,7 @@ from core.app.entities.app_invoke_entities import InvokeFrom, WorkflowAppGenerat
 from core.app.entities.task_entities import WorkflowAppBlockingResponse, WorkflowAppStreamResponse
 from core.model_runtime.errors.invoke import InvokeAuthorizationError
 from core.ops.ops_trace_manager import TraceQueueManager
-from core.repositories import SQLAlchemyWorkflowNodeExecutionRepository
-from core.repositories.sqlalchemy_workflow_execution_repository import SQLAlchemyWorkflowExecutionRepository
+from core.repositories import DifyCoreRepositoryFactory
 from core.workflow.repositories.draft_variable_repository import DraftVariableSaverFactory
 from core.workflow.repositories.workflow_execution_repository import WorkflowExecutionRepository
 from core.workflow.repositories.workflow_node_execution_repository import WorkflowNodeExecutionRepository
@@ -156,14 +155,14 @@ class WorkflowAppGenerator(BaseAppGenerator):
             workflow_triggered_from = WorkflowRunTriggeredFrom.DEBUGGING
         else:
             workflow_triggered_from = WorkflowRunTriggeredFrom.APP_RUN
-        workflow_execution_repository = SQLAlchemyWorkflowExecutionRepository(
+        workflow_execution_repository = DifyCoreRepositoryFactory.create_workflow_execution_repository(
             session_factory=session_factory,
             user=user,
             app_id=application_generate_entity.app_config.app_id,
             triggered_from=workflow_triggered_from,
         )
         # Create workflow node execution repository
-        workflow_node_execution_repository = SQLAlchemyWorkflowNodeExecutionRepository(
+        workflow_node_execution_repository = DifyCoreRepositoryFactory.create_workflow_node_execution_repository(
             session_factory=session_factory,
             user=user,
             app_id=application_generate_entity.app_config.app_id,
@@ -306,16 +305,14 @@ class WorkflowAppGenerator(BaseAppGenerator):
         # Create session factory
         session_factory = sessionmaker(bind=db.engine, expire_on_commit=False)
         # Create workflow execution(aka workflow run) repository
-        workflow_execution_repository = SQLAlchemyWorkflowExecutionRepository(
+        workflow_execution_repository = DifyCoreRepositoryFactory.create_workflow_execution_repository(
             session_factory=session_factory,
             user=user,
             app_id=application_generate_entity.app_config.app_id,
             triggered_from=WorkflowRunTriggeredFrom.DEBUGGING,
         )
         # Create workflow node execution repository
-        session_factory = sessionmaker(bind=db.engine, expire_on_commit=False)
-
-        workflow_node_execution_repository = SQLAlchemyWorkflowNodeExecutionRepository(
+        workflow_node_execution_repository = DifyCoreRepositoryFactory.create_workflow_node_execution_repository(
             session_factory=session_factory,
             user=user,
             app_id=application_generate_entity.app_config.app_id,
@@ -390,16 +387,14 @@ class WorkflowAppGenerator(BaseAppGenerator):
         # Create session factory
         session_factory = sessionmaker(bind=db.engine, expire_on_commit=False)
         # Create workflow execution(aka workflow run) repository
-        workflow_execution_repository = SQLAlchemyWorkflowExecutionRepository(
+        workflow_execution_repository = DifyCoreRepositoryFactory.create_workflow_execution_repository(
             session_factory=session_factory,
             user=user,
             app_id=application_generate_entity.app_config.app_id,
             triggered_from=WorkflowRunTriggeredFrom.DEBUGGING,
         )
         # Create workflow node execution repository
-        session_factory = sessionmaker(bind=db.engine, expire_on_commit=False)
-
-        workflow_node_execution_repository = SQLAlchemyWorkflowNodeExecutionRepository(
+        workflow_node_execution_repository = DifyCoreRepositoryFactory.create_workflow_node_execution_repository(
             session_factory=session_factory,
             user=user,
             app_id=application_generate_entity.app_config.app_id,

api/core/app/apps/workflow/generate_task_pipeline.py

@@ -3,7 +3,6 @@ import time
 from collections.abc import Generator
 from typing import Optional, Union
 
-from sqlalchemy import select
 from sqlalchemy.orm import Session
 
 from constants.tts_auto_play_timeout import TTS_AUTO_PLAY_TIMEOUT, TTS_AUTO_PLAY_YIELD_CPU_TIME
@@ -68,7 +67,6 @@ from models.workflow import (
     Workflow,
     WorkflowAppLog,
     WorkflowAppLogCreatedFrom,
-    WorkflowRun,
 )
 
 logger = logging.getLogger(__name__)
@@ -562,8 +560,6 @@ class WorkflowAppGenerateTaskPipeline:
             tts_publisher.publish(None)
 
     def _save_workflow_app_log(self, *, session: Session, workflow_execution: WorkflowExecution) -> None:
-        workflow_run = session.scalar(select(WorkflowRun).where(WorkflowRun.id == workflow_execution.id_))
-        assert workflow_run is not None
         invoke_from = self._application_generate_entity.invoke_from
         if invoke_from == InvokeFrom.SERVICE_API:
             created_from = WorkflowAppLogCreatedFrom.SERVICE_API
@@ -576,10 +572,10 @@ class WorkflowAppGenerateTaskPipeline:
             return
 
         workflow_app_log = WorkflowAppLog()
-        workflow_app_log.tenant_id = workflow_run.tenant_id
-        workflow_app_log.app_id = workflow_run.app_id
-        workflow_app_log.workflow_id = workflow_run.workflow_id
-        workflow_app_log.workflow_run_id = workflow_run.id
+        workflow_app_log.tenant_id = self._application_generate_entity.app_config.tenant_id
+        workflow_app_log.app_id = self._application_generate_entity.app_config.app_id
+        workflow_app_log.workflow_id = workflow_execution.workflow_id
+        workflow_app_log.workflow_run_id = workflow_execution.id_
         workflow_app_log.created_from = created_from.value
         workflow_app_log.created_by_role = self._created_by_role
         workflow_app_log.created_by = self._user_id

api/core/app/task_pipeline/based_generate_task_pipeline.py

@@ -19,6 +19,7 @@ from core.app.entities.task_entities import (
 from core.errors.error import QuotaExceededError
 from core.model_runtime.errors.invoke import InvokeAuthorizationError, InvokeError
 from core.moderation.output_moderation import ModerationRule, OutputModeration
+from models.enums import MessageStatus
 from models.model import Message
 
 logger = logging.getLogger(__name__)
@@ -62,7 +63,7 @@ class BasedGenerateTaskPipeline:
             return err
 
         err_desc = self._error_to_desc(err)
-        message.status = "error"
+        message.status = MessageStatus.ERROR
         message.error = err_desc
         return err
 

api/core/entities/parameter_entities.py

@@ -21,6 +21,9 @@ class CommonParameterType(StrEnum):
     DYNAMIC_SELECT = "dynamic-select"
 
     # TOOL_SELECTOR = "tool-selector"
+    # MCP object and array type parameters
+    ARRAY = "array"
+    OBJECT = "object"
 
 
 class AppSelectorScope(StrEnum):

api/core/file/helpers.py

@@ -21,7 +21,9 @@ def get_signed_file_url(upload_file_id: str) -> str:
 
 
 def get_signed_file_url_for_plugin(filename: str, mimetype: str, tenant_id: str, user_id: str) -> str:
-    url = f"{dify_config.FILES_URL}/files/upload/for-plugin"
+    # Plugin access should use internal URL for Docker network communication
+    base_url = dify_config.INTERNAL_FILES_URL or dify_config.FILES_URL
+    url = f"{base_url}/files/upload/for-plugin"
 
     if user_id is None:
         user_id = "DEFAULT-USER"

api/core/file/models.py

@@ -51,7 +51,7 @@ class File(BaseModel):
     # It should be set to `ToolFile.id` when `transfer_method` is `tool_file`.
     related_id: Optional[str] = None
     filename: Optional[str] = None
-    extension: Optional[str] = Field(default=None, description="File extension, should contains dot")
+    extension: Optional[str] = Field(default=None, description="File extension, should contain dot")
     mime_type: Optional[str] = None
     size: int = -1
 

api/core/file/upload_file_parser.py

@@ -1,67 +0,0 @@
-import base64
-import logging
-import time
-from typing import Optional
-
-from configs import dify_config
-from constants import IMAGE_EXTENSIONS
-from core.helper.url_signer import UrlSigner
-from extensions.ext_storage import storage
-
-
-class UploadFileParser:
-    @classmethod
-    def get_image_data(cls, upload_file, force_url: bool = False) -> Optional[str]:
-        if not upload_file:
-            return None
-
-        if upload_file.extension not in IMAGE_EXTENSIONS:
-            return None
-
-        if dify_config.MULTIMODAL_SEND_FORMAT == "url" or force_url:
-            return cls.get_signed_temp_image_url(upload_file.id)
-        else:
-            # get image file base64
-            try:
-                data = storage.load(upload_file.key)
-            except FileNotFoundError:
-                logging.exception(f"File not found: {upload_file.key}")
-                return None
-
-            encoded_string = base64.b64encode(data).decode("utf-8")
-            return f"data:{upload_file.mime_type};base64,{encoded_string}"
-
-    @classmethod
-    def get_signed_temp_image_url(cls, upload_file_id) -> str:
-        """
-        get signed url from upload file
-
-        :param upload_file_id: the id of UploadFile object
-        :return:
-        """
-        base_url = dify_config.FILES_URL
-        image_preview_url = f"{base_url}/files/{upload_file_id}/image-preview"
-
-        return UrlSigner.get_signed_url(url=image_preview_url, sign_key=upload_file_id, prefix="image-preview")
-
-    @classmethod
-    def verify_image_file_signature(cls, upload_file_id: str, timestamp: str, nonce: str, sign: str) -> bool:
-        """
-        verify signature
-
-        :param upload_file_id: file id
-        :param timestamp: timestamp
-        :param nonce: nonce
-        :param sign: signature
-        :return:
-        """
-        result = UrlSigner.verify(
-            sign_key=upload_file_id, timestamp=timestamp, nonce=nonce, sign=sign, prefix="image-preview"
-        )
-
-        # verify signature
-        if not result:
-            return False
-
-        current_time = int(time.time())
-        return current_time - int(timestamp) <= dify_config.FILES_ACCESS_TIMEOUT

api/core/helper/code_executor/template_transformer.py

@@ -5,6 +5,8 @@ from base64 import b64encode
 from collections.abc import Mapping
 from typing import Any
 
+from core.variables.utils import SegmentJSONEncoder
+
 
 class TemplateTransformer(ABC):
     _code_placeholder: str = "{{code}}"
@@ -28,7 +30,7 @@ class TemplateTransformer(ABC):
     def extract_result_str_from_response(cls, response: str):
         result = re.search(rf"{cls._result_tag}(.*){cls._result_tag}", response, re.DOTALL)
         if not result:
-            raise ValueError("Failed to parse result")
+            raise ValueError(f"Failed to parse result: no result tag found in response. Response: {response[:200]}...")
         return result.group(1)
 
     @classmethod
@@ -38,16 +40,49 @@ class TemplateTransformer(ABC):
         :param response: response
         :return:
         """
+
         try:
-            result = json.loads(cls.extract_result_str_from_response(response))
-        except json.JSONDecodeError:
-            raise ValueError("failed to parse response")
+            result_str = cls.extract_result_str_from_response(response)
+            result = json.loads(result_str)
+        except json.JSONDecodeError as e:
+            raise ValueError(f"Failed to parse JSON response: {str(e)}.")
+        except ValueError as e:
+            # Re-raise ValueError from extract_result_str_from_response
+            raise e
+        except Exception as e:
+            raise ValueError(f"Unexpected error during response transformation: {str(e)}")
+
         if not isinstance(result, dict):
-            raise ValueError("result must be a dict")
+            raise ValueError(f"Result must be a dict, got {type(result).__name__}")
         if not all(isinstance(k, str) for k in result):
-            raise ValueError("result keys must be strings")
+            raise ValueError("Result keys must be strings")
+
+        # Post-process the result to convert scientific notation strings back to numbers
+        result = cls._post_process_result(result)
         return result
 
+    @classmethod
+    def _post_process_result(cls, result: dict[Any, Any]) -> dict[Any, Any]:
+        """
+        Post-process the result to convert scientific notation strings back to numbers
+        """
+
+        def convert_scientific_notation(value):
+            if isinstance(value, str):
+                # Check if the string looks like scientific notation
+                if re.match(r"^-?\d+\.?\d*e[+-]\d+$", value, re.IGNORECASE):
+                    try:
+                        return float(value)
+                    except ValueError:
+                        pass
+            elif isinstance(value, dict):
+                return {k: convert_scientific_notation(v) for k, v in value.items()}
+            elif isinstance(value, list):
+                return [convert_scientific_notation(v) for v in value]
+            return value
+
+        return convert_scientific_notation(result)  # type: ignore[no-any-return]
+
     @classmethod
     @abstractmethod
     def get_runner_script(cls) -> str:
@@ -58,7 +93,7 @@ class TemplateTransformer(ABC):
 
     @classmethod
     def serialize_inputs(cls, inputs: Mapping[str, Any]) -> str:
-        inputs_json_str = json.dumps(inputs, ensure_ascii=False).encode()
+        inputs_json_str = json.dumps(inputs, ensure_ascii=False, cls=SegmentJSONEncoder).encode()
         input_base64_encoded = b64encode(inputs_json_str).decode("utf-8")
         return input_base64_encoded
 

api/core/helper/lru_cache.py

@@ -1,22 +0,0 @@
-from collections import OrderedDict
-from typing import Any
-
-
-class LRUCache:
-    def __init__(self, capacity: int):
-        self.cache: OrderedDict[Any, Any] = OrderedDict()
-        self.capacity = capacity
-
-    def get(self, key: Any) -> Any:
-        if key not in self.cache:
-            return None
-        else:
-            self.cache.move_to_end(key)  # move the key to the end of the OrderedDict
-            return self.cache[key]
-
-    def put(self, key: Any, value: Any) -> None:
-        if key in self.cache:
-            self.cache.move_to_end(key)
-        self.cache[key] = value
-        if len(self.cache) > self.capacity:
-            self.cache.popitem(last=False)  # pop the first item

api/core/helper/provider_cache.py

@@ -0,0 +1,84 @@
+import json
+from abc import ABC, abstractmethod
+from json import JSONDecodeError
+from typing import Any, Optional
+
+from extensions.ext_redis import redis_client
+
+
+class ProviderCredentialsCache(ABC):
+    """Base class for provider credentials cache"""
+
+    def __init__(self, **kwargs):
+        self.cache_key = self._generate_cache_key(**kwargs)
+
+    @abstractmethod
+    def _generate_cache_key(self, **kwargs) -> str:
+        """Generate cache key based on subclass implementation"""
+        pass
+
+    def get(self) -> Optional[dict]:
+        """Get cached provider credentials"""
+        cached_credentials = redis_client.get(self.cache_key)
+        if cached_credentials:
+            try:
+                cached_credentials = cached_credentials.decode("utf-8")
+                return dict(json.loads(cached_credentials))
+            except JSONDecodeError:
+                return None
+        return None
+
+    def set(self, config: dict[str, Any]) -> None:
+        """Cache provider credentials"""
+        redis_client.setex(self.cache_key, 86400, json.dumps(config))
+
+    def delete(self) -> None:
+        """Delete cached provider credentials"""
+        redis_client.delete(self.cache_key)
+
+
+class SingletonProviderCredentialsCache(ProviderCredentialsCache):
+    """Cache for tool single provider credentials"""
+
+    def __init__(self, tenant_id: str, provider_type: str, provider_identity: str):
+        super().__init__(
+            tenant_id=tenant_id,
+            provider_type=provider_type,
+            provider_identity=provider_identity,
+        )
+
+    def _generate_cache_key(self, **kwargs) -> str:
+        tenant_id = kwargs["tenant_id"]
+        provider_type = kwargs["provider_type"]
+        identity_name = kwargs["provider_identity"]
+        identity_id = f"{provider_type}.{identity_name}"
+        return f"{provider_type}_credentials:tenant_id:{tenant_id}:id:{identity_id}"
+
+
+class ToolProviderCredentialsCache(ProviderCredentialsCache):
+    """Cache for tool provider credentials"""
+
+    def __init__(self, tenant_id: str, provider: str, credential_id: str):
+        super().__init__(tenant_id=tenant_id, provider=provider, credential_id=credential_id)
+
+    def _generate_cache_key(self, **kwargs) -> str:
+        tenant_id = kwargs["tenant_id"]
+        provider = kwargs["provider"]
+        credential_id = kwargs["credential_id"]
+        return f"tool_credentials:tenant_id:{tenant_id}:provider:{provider}:credential_id:{credential_id}"
+
+
+class NoOpProviderCredentialCache:
+    """No-op provider credential cache"""
+
+    def get(self) -> Optional[dict]:
+        """Get cached provider credentials"""
+        return None
+
+    def set(self, config: dict[str, Any]) -> None:
+        """Cache provider credentials"""
+        pass
+
+    def delete(self) -> None:
+        """Delete cached provider credentials"""
+        pass

api/core/helper/tool_provider_cache.py

@@ -1,51 +0,0 @@
-import json
-from enum import Enum
-from json import JSONDecodeError
-from typing import Optional
-
-from extensions.ext_redis import redis_client
-
-
-class ToolProviderCredentialsCacheType(Enum):
-    PROVIDER = "tool_provider"
-    ENDPOINT = "endpoint"
-
-
-class ToolProviderCredentialsCache:
-    def __init__(self, tenant_id: str, identity_id: str, cache_type: ToolProviderCredentialsCacheType):
-        self.cache_key = f"{cache_type.value}_credentials:tenant_id:{tenant_id}:id:{identity_id}"
-
-    def get(self) -> Optional[dict]:
-        """
-        Get cached model provider credentials.
-
-        :return:
-        """
-        cached_provider_credentials = redis_client.get(self.cache_key)
-        if cached_provider_credentials:
-            try:
-                cached_provider_credentials = cached_provider_credentials.decode("utf-8")
-                cached_provider_credentials = json.loads(cached_provider_credentials)
-            except JSONDecodeError:
-                return None
-
-            return dict(cached_provider_credentials)
-        else:
-            return None
-
-    def set(self, credentials: dict) -> None:
-        """
-        Cache model provider credentials.
-
-        :param credentials: provider credentials
-        :return:
-        """
-        redis_client.setex(self.cache_key, 86400, json.dumps(credentials))
-
-    def delete(self) -> None:
-        """
-        Delete cached model provider credentials.
-
-        :return:
-        """
-        redis_client.delete(self.cache_key)

api/core/indexing_runner.py

@@ -317,9 +317,10 @@ class IndexingRunner:
                 image_upload_file_ids = get_image_upload_file_ids(document.page_content)
                 for upload_file_id in image_upload_file_ids:
                     image_file = db.session.query(UploadFile).filter(UploadFile.id == upload_file_id).first()
+                    if image_file is None:
+                        continue
                     try:
-                        if image_file:
-                            storage.delete(image_file.key)
+                        storage.delete(image_file.key)
                     except Exception:
                         logging.exception(
                             "Delete image_files failed while indexing_estimate, \

api/core/llm_generator/output_parser/structured_output.py

@@ -23,6 +23,7 @@ from core.model_runtime.entities.message_entities import (
     PromptMessage,
     PromptMessageTool,
     SystemPromptMessage,
+    TextPromptMessageContent,
 )
 from core.model_runtime.entities.model_entities import AIModelEntity, ParameterRule
 
@@ -170,10 +171,15 @@ def invoke_llm_with_structured_output(
             system_fingerprint: Optional[str] = None
             for event in llm_result:
                 if isinstance(event, LLMResultChunk):
+                    prompt_messages = event.prompt_messages
+                    system_fingerprint = event.system_fingerprint
+
                     if isinstance(event.delta.message.content, str):
                         result_text += event.delta.message.content
-                        prompt_messages = event.prompt_messages
-                        system_fingerprint = event.system_fingerprint
+                    elif isinstance(event.delta.message.content, list):
+                        for item in event.delta.message.content:
+                            if isinstance(item, TextPromptMessageContent):
+                                result_text += item.data
 
                 yield LLMResultChunkWithStructuredOutput(
                     model=model_schema.model,

api/core/mcp/auth/auth_flow.py

@@ -0,0 +1,342 @@
+import base64
+import hashlib
+import json
+import os
+import secrets
+import urllib.parse
+from typing import Optional
+from urllib.parse import urljoin
+
+import requests
+from pydantic import BaseModel, ValidationError
+
+from core.mcp.auth.auth_provider import OAuthClientProvider
+from core.mcp.types import (
+    OAuthClientInformation,
+    OAuthClientInformationFull,
+    OAuthClientMetadata,
+    OAuthMetadata,
+    OAuthTokens,
+)
+from extensions.ext_redis import redis_client
+
+LATEST_PROTOCOL_VERSION = "1.0"
+OAUTH_STATE_EXPIRY_SECONDS = 5 * 60  # 5 minutes expiry
+OAUTH_STATE_REDIS_KEY_PREFIX = "oauth_state:"
+
+
+class OAuthCallbackState(BaseModel):
+    provider_id: str
+    tenant_id: str
+    server_url: str
+    metadata: OAuthMetadata | None = None
+    client_information: OAuthClientInformation
+    code_verifier: str
+    redirect_uri: str
+
+
+def generate_pkce_challenge() -> tuple[str, str]:
+    """Generate PKCE challenge and verifier."""
+    code_verifier = base64.urlsafe_b64encode(os.urandom(40)).decode("utf-8")
+    code_verifier = code_verifier.replace("=", "").replace("+", "-").replace("/", "_")
+
+    code_challenge_hash = hashlib.sha256(code_verifier.encode("utf-8")).digest()
+    code_challenge = base64.urlsafe_b64encode(code_challenge_hash).decode("utf-8")
+    code_challenge = code_challenge.replace("=", "").replace("+", "-").replace("/", "_")
+
+    return code_verifier, code_challenge
+
+
+def _create_secure_redis_state(state_data: OAuthCallbackState) -> str:
+    """Create a secure state parameter by storing state data in Redis and returning a random state key."""
+    # Generate a secure random state key
+    state_key = secrets.token_urlsafe(32)
+
+    # Store the state data in Redis with expiration
+    redis_key = f"{OAUTH_STATE_REDIS_KEY_PREFIX}{state_key}"
+    redis_client.setex(redis_key, OAUTH_STATE_EXPIRY_SECONDS, state_data.model_dump_json())
+
+    return state_key
+
+
+def _retrieve_redis_state(state_key: str) -> OAuthCallbackState:
+    """Retrieve and decode OAuth state data from Redis using the state key, then delete it."""
+    redis_key = f"{OAUTH_STATE_REDIS_KEY_PREFIX}{state_key}"
+
+    # Get state data from Redis
+    state_data = redis_client.get(redis_key)
+
+    if not state_data:
+        raise ValueError("State parameter has expired or does not exist")
+
+    # Delete the state data from Redis immediately after retrieval to prevent reuse
+    redis_client.delete(redis_key)
+
+    try:
+        # Parse and validate the state data
+        oauth_state = OAuthCallbackState.model_validate_json(state_data)
+
+        return oauth_state
+    except ValidationError as e:
+        raise ValueError(f"Invalid state parameter: {str(e)}")
+
+
+def handle_callback(state_key: str, authorization_code: str) -> OAuthCallbackState:
+    """Handle the callback from the OAuth provider."""
+    # Retrieve state data from Redis (state is automatically deleted after retrieval)
+    full_state_data = _retrieve_redis_state(state_key)
+
+    tokens = exchange_authorization(
+        full_state_data.server_url,
+        full_state_data.metadata,
+        full_state_data.client_information,
+        authorization_code,
+        full_state_data.code_verifier,
+        full_state_data.redirect_uri,
+    )
+    provider = OAuthClientProvider(full_state_data.provider_id, full_state_data.tenant_id, for_list=True)
+    provider.save_tokens(tokens)
+    return full_state_data
+
+
+def discover_oauth_metadata(server_url: str, protocol_version: Optional[str] = None) -> Optional[OAuthMetadata]:
+    """Looks up RFC 8414 OAuth 2.0 Authorization Server Metadata."""
+    url = urljoin(server_url, "/.well-known/oauth-authorization-server")
+
+    try:
+        headers = {"MCP-Protocol-Version": protocol_version or LATEST_PROTOCOL_VERSION}
+        response = requests.get(url, headers=headers)
+        if response.status_code == 404:
+            return None
+        if not response.ok:
+            raise ValueError(f"HTTP {response.status_code} trying to load well-known OAuth metadata")
+        return OAuthMetadata.model_validate(response.json())
+    except requests.RequestException as e:
+        if isinstance(e, requests.ConnectionError):
+            response = requests.get(url)
+            if response.status_code == 404:
+                return None
+            if not response.ok:
+                raise ValueError(f"HTTP {response.status_code} trying to load well-known OAuth metadata")
+            return OAuthMetadata.model_validate(response.json())
+        raise
+
+
+def start_authorization(
+    server_url: str,
+    metadata: Optional[OAuthMetadata],
+    client_information: OAuthClientInformation,
+    redirect_url: str,
+    provider_id: str,
+    tenant_id: str,
+) -> tuple[str, str]:
+    """Begins the authorization flow with secure Redis state storage."""
+    response_type = "code"
+    code_challenge_method = "S256"
+
+    if metadata:
+        authorization_url = metadata.authorization_endpoint
+        if response_type not in metadata.response_types_supported:
+            raise ValueError(f"Incompatible auth server: does not support response type {response_type}")
+        if (
+            not metadata.code_challenge_methods_supported
+            or code_challenge_method not in metadata.code_challenge_methods_supported
+        ):
+            raise ValueError(
+                f"Incompatible auth server: does not support code challenge method {code_challenge_method}"
+            )
+    else:
+        authorization_url = urljoin(server_url, "/authorize")
+
+    code_verifier, code_challenge = generate_pkce_challenge()
+
+    # Prepare state data with all necessary information
+    state_data = OAuthCallbackState(
+        provider_id=provider_id,
+        tenant_id=tenant_id,
+        server_url=server_url,
+        metadata=metadata,
+        client_information=client_information,
+        code_verifier=code_verifier,
+        redirect_uri=redirect_url,
+    )
+
+    # Store state data in Redis and generate secure state key
+    state_key = _create_secure_redis_state(state_data)
+
+    params = {
+        "response_type": response_type,
+        "client_id": client_information.client_id,
+        "code_challenge": code_challenge,
+        "code_challenge_method": code_challenge_method,
+        "redirect_uri": redirect_url,
+        "state": state_key,
+    }
+
+    authorization_url = f"{authorization_url}?{urllib.parse.urlencode(params)}"
+    return authorization_url, code_verifier
+
+
+def exchange_authorization(
+    server_url: str,
+    metadata: Optional[OAuthMetadata],
+    client_information: OAuthClientInformation,
+    authorization_code: str,
+    code_verifier: str,
+    redirect_uri: str,
+) -> OAuthTokens:
+    """Exchanges an authorization code for an access token."""
+    grant_type = "authorization_code"
+
+    if metadata:
+        token_url = metadata.token_endpoint
+        if metadata.grant_types_supported and grant_type not in metadata.grant_types_supported:
+            raise ValueError(f"Incompatible auth server: does not support grant type {grant_type}")
+    else:
+        token_url = urljoin(server_url, "/token")
+
+    params = {
+        "grant_type": grant_type,
+        "client_id": client_information.client_id,
+        "code": authorization_code,
+        "code_verifier": code_verifier,
+        "redirect_uri": redirect_uri,
+    }
+
+    if client_information.client_secret:
+        params["client_secret"] = client_information.client_secret
+
+    response = requests.post(token_url, data=params)
+    if not response.ok:
+        raise ValueError(f"Token exchange failed: HTTP {response.status_code}")
+    return OAuthTokens.model_validate(response.json())
+
+
+def refresh_authorization(
+    server_url: str,
+    metadata: Optional[OAuthMetadata],
+    client_information: OAuthClientInformation,
+    refresh_token: str,
+) -> OAuthTokens:
+    """Exchange a refresh token for an updated access token."""
+    grant_type = "refresh_token"
+
+    if metadata:
+        token_url = metadata.token_endpoint
+        if metadata.grant_types_supported and grant_type not in metadata.grant_types_supported:
+            raise ValueError(f"Incompatible auth server: does not support grant type {grant_type}")
+    else:
+        token_url = urljoin(server_url, "/token")
+
+    params = {
+        "grant_type": grant_type,
+        "client_id": client_information.client_id,
+        "refresh_token": refresh_token,
+    }
+
+    if client_information.client_secret:
+        params["client_secret"] = client_information.client_secret
+
+    response = requests.post(token_url, data=params)
+    if not response.ok:
+        raise ValueError(f"Token refresh failed: HTTP {response.status_code}")
+    return OAuthTokens.parse_obj(response.json())
+
+
+def register_client(
+    server_url: str,
+    metadata: Optional[OAuthMetadata],
+    client_metadata: OAuthClientMetadata,
+) -> OAuthClientInformationFull:
+    """Performs OAuth 2.0 Dynamic Client Registration."""
+    if metadata:
+        if not metadata.registration_endpoint:
+            raise ValueError("Incompatible auth server: does not support dynamic client registration")
+        registration_url = metadata.registration_endpoint
+    else:
+        registration_url = urljoin(server_url, "/register")
+
+    response = requests.post(
+        registration_url,
+        json=client_metadata.model_dump(),
+        headers={"Content-Type": "application/json"},
+    )
+    if not response.ok:
+        response.raise_for_status()
+    return OAuthClientInformationFull.model_validate(response.json())
+
+
+def auth(
+    provider: OAuthClientProvider,
+    server_url: str,
+    authorization_code: Optional[str] = None,
+    state_param: Optional[str] = None,
+    for_list: bool = False,
+) -> dict[str, str]:
+    """Orchestrates the full auth flow with a server using secure Redis state storage."""
+    metadata = discover_oauth_metadata(server_url)
+
+    # Handle client registration if needed
+    client_information = provider.client_information()
+    if not client_information:
+        if authorization_code is not None:
+            raise ValueError("Existing OAuth client information is required when exchanging an authorization code")
+        try:
+            full_information = register_client(server_url, metadata, provider.client_metadata)
+        except requests.RequestException as e:
+            raise ValueError(f"Could not register OAuth client: {e}")
+        provider.save_client_information(full_information)
+        client_information = full_information
+
+    # Exchange authorization code for tokens
+    if authorization_code is not None:
+        if not state_param:
+            raise ValueError("State parameter is required when exchanging authorization code")
+
+        try:
+            # Retrieve state data from Redis using state key
+            full_state_data = _retrieve_redis_state(state_param)
+
+            code_verifier = full_state_data.code_verifier
+            redirect_uri = full_state_data.redirect_uri
+
+            if not code_verifier or not redirect_uri:
+                raise ValueError("Missing code_verifier or redirect_uri in state data")
+
+        except (json.JSONDecodeError, ValueError) as e:
+            raise ValueError(f"Invalid state parameter: {e}")
+
+        tokens = exchange_authorization(
+            server_url,
+            metadata,
+            client_information,
+            authorization_code,
+            code_verifier,
+            redirect_uri,
+        )
+        provider.save_tokens(tokens)
+        return {"result": "success"}
+
+    provider_tokens = provider.tokens()
+
+    # Handle token refresh or new authorization
+    if provider_tokens and provider_tokens.refresh_token:
+        try:
+            new_tokens = refresh_authorization(server_url, metadata, client_information, provider_tokens.refresh_token)
+            provider.save_tokens(new_tokens)
+            return {"result": "success"}
+        except Exception as e:
+            raise ValueError(f"Could not refresh OAuth tokens: {e}")
+
+    # Start new authorization flow
+    authorization_url, code_verifier = start_authorization(
+        server_url,
+        metadata,
+        client_information,
+        provider.redirect_url,
+        provider.mcp_provider.id,
+        provider.mcp_provider.tenant_id,
+    )
+
+    provider.save_code_verifier(code_verifier)
+    return {"authorization_url": authorization_url}

api/core/mcp/auth/auth_provider.py

@@ -0,0 +1,81 @@
+from typing import Optional
+
+from configs import dify_config
+from core.mcp.types import (
+    OAuthClientInformation,
+    OAuthClientInformationFull,
+    OAuthClientMetadata,
+    OAuthTokens,
+)
+from models.tools import MCPToolProvider
+from services.tools.mcp_tools_mange_service import MCPToolManageService
+
+LATEST_PROTOCOL_VERSION = "1.0"
+
+
+class OAuthClientProvider:
+    mcp_provider: MCPToolProvider
+
+    def __init__(self, provider_id: str, tenant_id: str, for_list: bool = False):
+        if for_list:
+            self.mcp_provider = MCPToolManageService.get_mcp_provider_by_provider_id(provider_id, tenant_id)
+        else:
+            self.mcp_provider = MCPToolManageService.get_mcp_provider_by_server_identifier(provider_id, tenant_id)
+
+    @property
+    def redirect_url(self) -> str:
+        """The URL to redirect the user agent to after authorization."""
+        return dify_config.CONSOLE_API_URL + "/console/api/mcp/oauth/callback"
+
+    @property
+    def client_metadata(self) -> OAuthClientMetadata:
+        """Metadata about this OAuth client."""
+        return OAuthClientMetadata(
+            redirect_uris=[self.redirect_url],
+            token_endpoint_auth_method="none",
+            grant_types=["authorization_code", "refresh_token"],
+            response_types=["code"],
+            client_name="Dify",
+            client_uri="https://github.com/langgenius/dify",
+        )
+
+    def client_information(self) -> Optional[OAuthClientInformation]:
+        """Loads information about this OAuth client."""
+        client_information = self.mcp_provider.decrypted_credentials.get("client_information", {})
+        if not client_information:
+            return None
+        return OAuthClientInformation.model_validate(client_information)
+
+    def save_client_information(self, client_information: OAuthClientInformationFull) -> None:
+        """Saves client information after dynamic registration."""
+        MCPToolManageService.update_mcp_provider_credentials(
+            self.mcp_provider,
+            {"client_information": client_information.model_dump()},
+        )
+
+    def tokens(self) -> Optional[OAuthTokens]:
+        """Loads any existing OAuth tokens for the current session."""
+        credentials = self.mcp_provider.decrypted_credentials
+        if not credentials:
+            return None
+        return OAuthTokens(
+            access_token=credentials.get("access_token", ""),
+            token_type=credentials.get("token_type", "Bearer"),
+            expires_in=int(credentials.get("expires_in", "3600") or 3600),
+            refresh_token=credentials.get("refresh_token", ""),
+        )
+
+    def save_tokens(self, tokens: OAuthTokens) -> None:
+        """Stores new OAuth tokens for the current session."""
+        # update mcp provider credentials
+        token_dict = tokens.model_dump()
+        MCPToolManageService.update_mcp_provider_credentials(self.mcp_provider, token_dict, authed=True)
+
+    def save_code_verifier(self, code_verifier: str) -> None:
+        """Saves a PKCE code verifier for the current session."""
+        MCPToolManageService.update_mcp_provider_credentials(self.mcp_provider, {"code_verifier": code_verifier})
+
+    def code_verifier(self) -> str:
+        """Loads the PKCE code verifier for the current session."""
+        # get code verifier from mcp provider credentials
+        return str(self.mcp_provider.decrypted_credentials.get("code_verifier", ""))

api/core/mcp/client/sse_client.py

@@ -0,0 +1,361 @@
+import logging
+import queue
+from collections.abc import Generator
+from concurrent.futures import ThreadPoolExecutor
+from contextlib import contextmanager
+from typing import Any, TypeAlias, final
+from urllib.parse import urljoin, urlparse
+
+import httpx
+from sseclient import SSEClient
+
+from core.mcp import types
+from core.mcp.error import MCPAuthError, MCPConnectionError
+from core.mcp.types import SessionMessage
+from core.mcp.utils import create_ssrf_proxy_mcp_http_client, ssrf_proxy_sse_connect
+
+logger = logging.getLogger(__name__)
+
+DEFAULT_QUEUE_READ_TIMEOUT = 3
+
+
+@final
+class _StatusReady:
+    def __init__(self, endpoint_url: str):
+        self._endpoint_url = endpoint_url
+
+
+@final
+class _StatusError:
+    def __init__(self, exc: Exception):
+        self._exc = exc
+
+
+# Type aliases for better readability
+ReadQueue: TypeAlias = queue.Queue[SessionMessage | Exception | None]
+WriteQueue: TypeAlias = queue.Queue[SessionMessage | Exception | None]
+StatusQueue: TypeAlias = queue.Queue[_StatusReady | _StatusError]
+
+
+def remove_request_params(url: str) -> str:
+    """Remove request parameters from URL, keeping only the path."""
+    return urljoin(url, urlparse(url).path)
+
+
+class SSETransport:
+    """SSE client transport implementation."""
+
+    def __init__(
+        self,
+        url: str,
+        headers: dict[str, Any] | None = None,
+        timeout: float = 5.0,
+        sse_read_timeout: float = 5 * 60,
+    ) -> None:
+        """Initialize the SSE transport.
+
+        Args:
+            url: The SSE endpoint URL.
+            headers: Optional headers to include in requests.
+            timeout: HTTP timeout for regular operations.
+            sse_read_timeout: Timeout for SSE read operations.
+        """
+        self.url = url
+        self.headers = headers or {}
+        self.timeout = timeout
+        self.sse_read_timeout = sse_read_timeout
+        self.endpoint_url: str | None = None
+
+    def _validate_endpoint_url(self, endpoint_url: str) -> bool:
+        """Validate that the endpoint URL matches the connection origin.
+
+        Args:
+            endpoint_url: The endpoint URL to validate.
+
+        Returns:
+            True if valid, False otherwise.
+        """
+        url_parsed = urlparse(self.url)
+        endpoint_parsed = urlparse(endpoint_url)
+
+        return url_parsed.netloc == endpoint_parsed.netloc and url_parsed.scheme == endpoint_parsed.scheme
+
+    def _handle_endpoint_event(self, sse_data: str, status_queue: StatusQueue) -> None:
+        """Handle an 'endpoint' SSE event.
+
+        Args:
+            sse_data: The SSE event data.
+            status_queue: Queue to put status updates.
+        """
+        endpoint_url = urljoin(self.url, sse_data)
+        logger.info(f"Received endpoint URL: {endpoint_url}")
+
+        if not self._validate_endpoint_url(endpoint_url):
+            error_msg = f"Endpoint origin does not match connection origin: {endpoint_url}"
+            logger.error(error_msg)
+            status_queue.put(_StatusError(ValueError(error_msg)))
+            return
+
+        status_queue.put(_StatusReady(endpoint_url))
+
+    def _handle_message_event(self, sse_data: str, read_queue: ReadQueue) -> None:
+        """Handle a 'message' SSE event.
+
+        Args:
+            sse_data: The SSE event data.
+            read_queue: Queue to put parsed messages.
+        """
+        try:
+            message = types.JSONRPCMessage.model_validate_json(sse_data)
+            logger.debug(f"Received server message: {message}")
+            session_message = SessionMessage(message)
+            read_queue.put(session_message)
+        except Exception as exc:
+            logger.exception("Error parsing server message")
+            read_queue.put(exc)
+
+    def _handle_sse_event(self, sse, read_queue: ReadQueue, status_queue: StatusQueue) -> None:
+        """Handle a single SSE event.
+
+        Args:
+            sse: The SSE event object.
+            read_queue: Queue for message events.
+            status_queue: Queue for status events.
+        """
+        match sse.event:
+            case "endpoint":
+                self._handle_endpoint_event(sse.data, status_queue)
+            case "message":
+                self._handle_message_event(sse.data, read_queue)
+            case _:
+                logger.warning(f"Unknown SSE event: {sse.event}")
+
+    def sse_reader(self, event_source, read_queue: ReadQueue, status_queue: StatusQueue) -> None:
+        """Read and process SSE events.
+
+        Args:
+            event_source: The SSE event source.
+            read_queue: Queue to put received messages.
+            status_queue: Queue to put status updates.
+        """
+        try:
+            for sse in event_source.iter_sse():
+                self._handle_sse_event(sse, read_queue, status_queue)
+        except httpx.ReadError as exc:
+            logger.debug(f"SSE reader shutting down normally: {exc}")
+        except Exception as exc:
+            read_queue.put(exc)
+        finally:
+            read_queue.put(None)
+
+    def _send_message(self, client: httpx.Client, endpoint_url: str, message: SessionMessage) -> None:
+        """Send a single message to the server.
+
+        Args:
+            client: HTTP client to use.
+            endpoint_url: The endpoint URL to send to.
+            message: The message to send.
+        """
+        response = client.post(
+            endpoint_url,
+            json=message.message.model_dump(
+                by_alias=True,
+                mode="json",
+                exclude_none=True,
+            ),
+        )
+        response.raise_for_status()
+        logger.debug(f"Client message sent successfully: {response.status_code}")
+
+    def post_writer(self, client: httpx.Client, endpoint_url: str, write_queue: WriteQueue) -> None:
+        """Handle writing messages to the server.
+
+        Args:
+            client: HTTP client to use.
+            endpoint_url: The endpoint URL to send messages to.
+            write_queue: Queue to read messages from.
+        """
+        try:
+            while True:
+                try:
+                    message = write_queue.get(timeout=DEFAULT_QUEUE_READ_TIMEOUT)
+                    if message is None:
+                        break
+                    if isinstance(message, Exception):
+                        write_queue.put(message)
+                        continue
+
+                    self._send_message(client, endpoint_url, message)
+
+                except queue.Empty:
+                    continue
+        except httpx.ReadError as exc:
+            logger.debug(f"Post writer shutting down normally: {exc}")
+        except Exception as exc:
+            logger.exception("Error writing messages")
+            write_queue.put(exc)
+        finally:
+            write_queue.put(None)
+
+    def _wait_for_endpoint(self, status_queue: StatusQueue) -> str:
+        """Wait for the endpoint URL from the status queue.
+
+        Args:
+            status_queue: Queue to read status from.
+
+        Returns:
+            The endpoint URL.
+
+        Raises:
+            ValueError: If endpoint URL is not received or there's an error.
+        """
+        try:
+            status = status_queue.get(timeout=1)
+        except queue.Empty:
+            raise ValueError("failed to get endpoint URL")
+
+        if isinstance(status, _StatusReady):
+            return status._endpoint_url
+        elif isinstance(status, _StatusError):
+            raise status._exc
+        else:
+            raise ValueError("failed to get endpoint URL")
+
+    def connect(
+        self,
+        executor: ThreadPoolExecutor,
+        client: httpx.Client,
+        event_source,
+    ) -> tuple[ReadQueue, WriteQueue]:
+        """Establish connection and start worker threads.
+
+        Args:
+            executor: Thread pool executor.
+            client: HTTP client.
+            event_source: SSE event source.
+
+        Returns:
+            Tuple of (read_queue, write_queue).
+        """
+        read_queue: ReadQueue = queue.Queue()
+        write_queue: WriteQueue = queue.Queue()
+        status_queue: StatusQueue = queue.Queue()
+
+        # Start SSE reader thread
+        executor.submit(self.sse_reader, event_source, read_queue, status_queue)
+
+        # Wait for endpoint URL
+        endpoint_url = self._wait_for_endpoint(status_queue)
+        self.endpoint_url = endpoint_url
+
+        # Start post writer thread
+        executor.submit(self.post_writer, client, endpoint_url, write_queue)
+
+        return read_queue, write_queue
+
+
+@contextmanager
+def sse_client(
+    url: str,
+    headers: dict[str, Any] | None = None,
+    timeout: float = 5.0,
+    sse_read_timeout: float = 5 * 60,
+) -> Generator[tuple[ReadQueue, WriteQueue], None, None]:
+    """
+    Client transport for SSE.
+    `sse_read_timeout` determines how long (in seconds) the client will wait for a new
+    event before disconnecting. All other HTTP operations are controlled by `timeout`.
+
+    Args:
+        url: The SSE endpoint URL.
+        headers: Optional headers to include in requests.
+        timeout: HTTP timeout for regular operations.
+        sse_read_timeout: Timeout for SSE read operations.
+
+    Yields:
+        Tuple of (read_queue, write_queue) for message communication.
+    """
+    transport = SSETransport(url, headers, timeout, sse_read_timeout)
+
+    read_queue: ReadQueue | None = None
+    write_queue: WriteQueue | None = None
+
+    with ThreadPoolExecutor() as executor:
+        try:
+            with create_ssrf_proxy_mcp_http_client(headers=transport.headers) as client:
+                with ssrf_proxy_sse_connect(
+                    url, timeout=httpx.Timeout(timeout, read=sse_read_timeout), client=client
+                ) as event_source:
+                    event_source.response.raise_for_status()
+
+                    read_queue, write_queue = transport.connect(executor, client, event_source)
+
+                    yield read_queue, write_queue
+
+        except httpx.HTTPStatusError as exc:
+            if exc.response.status_code == 401:
+                raise MCPAuthError()
+            raise MCPConnectionError()
+        except Exception:
+            logger.exception("Error connecting to SSE endpoint")
+            raise
+        finally:
+            # Clean up queues
+            if read_queue:
+                read_queue.put(None)
+            if write_queue:
+                write_queue.put(None)
+
+
+def send_message(http_client: httpx.Client, endpoint_url: str, session_message: SessionMessage) -> None:
+    """
+    Send a message to the server using the provided HTTP client.
+
+    Args:
+        http_client: The HTTP client to use for sending
+        endpoint_url: The endpoint URL to send the message to
+        session_message: The message to send
+    """
+    try:
+        response = http_client.post(
+            endpoint_url,
+            json=session_message.message.model_dump(
+                by_alias=True,
+                mode="json",
+                exclude_none=True,
+            ),
+        )
+        response.raise_for_status()
+        logger.debug(f"Client message sent successfully: {response.status_code}")
+    except Exception as exc:
+        logger.exception("Error sending message")
+        raise
+
+
+def read_messages(
+    sse_client: SSEClient,
+) -> Generator[SessionMessage | Exception, None, None]:
+    """
+    Read messages from the SSE client.
+
+    Args:
+        sse_client: The SSE client to read from
+
+    Yields:
+        SessionMessage or Exception for each event received
+    """
+    try:
+        for sse in sse_client.events():
+            if sse.event == "message":
+                try:
+                    message = types.JSONRPCMessage.model_validate_json(sse.data)
+                    logger.debug(f"Received server message: {message}")
+                    yield SessionMessage(message)
+                except Exception as exc:
+                    logger.exception("Error parsing server message")
+                    yield exc
+            else:
+                logger.warning(f"Unknown SSE event: {sse.event}")
+    except Exception as exc:
+        logger.exception("Error reading SSE messages")
+        yield exc

api/core/mcp/client/streamable_client.py

@@ -0,0 +1,476 @@
+"""
+StreamableHTTP Client Transport Module
+
+This module implements the StreamableHTTP transport for MCP clients,
+providing support for HTTP POST requests with optional SSE streaming responses
+and session management.
+"""
+
+import logging
+import queue
+from collections.abc import Callable, Generator
+from concurrent.futures import ThreadPoolExecutor
+from contextlib import contextmanager
+from dataclasses import dataclass
+from datetime import timedelta
+from typing import Any, cast
+
+import httpx
+from httpx_sse import EventSource, ServerSentEvent
+
+from core.mcp.types import (
+    ClientMessageMetadata,
+    ErrorData,
+    JSONRPCError,
+    JSONRPCMessage,
+    JSONRPCNotification,
+    JSONRPCRequest,
+    JSONRPCResponse,
+    RequestId,
+    SessionMessage,
+)
+from core.mcp.utils import create_ssrf_proxy_mcp_http_client, ssrf_proxy_sse_connect
+
+logger = logging.getLogger(__name__)
+
+
+SessionMessageOrError = SessionMessage | Exception | None
+# Queue types with clearer names for their roles
+ServerToClientQueue = queue.Queue[SessionMessageOrError]  # Server to client messages
+ClientToServerQueue = queue.Queue[SessionMessage | None]  # Client to server messages
+GetSessionIdCallback = Callable[[], str | None]
+
+MCP_SESSION_ID = "mcp-session-id"
+LAST_EVENT_ID = "last-event-id"
+CONTENT_TYPE = "content-type"
+ACCEPT = "Accept"
+
+
+JSON = "application/json"
+SSE = "text/event-stream"
+
+DEFAULT_QUEUE_READ_TIMEOUT = 3
+
+
+class StreamableHTTPError(Exception):
+    """Base exception for StreamableHTTP transport errors."""
+
+    pass
+
+
+class ResumptionError(StreamableHTTPError):
+    """Raised when resumption request is invalid."""
+
+    pass
+
+
+@dataclass
+class RequestContext:
+    """Context for a request operation."""
+
+    client: httpx.Client
+    headers: dict[str, str]
+    session_id: str | None
+    session_message: SessionMessage
+    metadata: ClientMessageMetadata | None
+    server_to_client_queue: ServerToClientQueue  # Renamed for clarity
+    sse_read_timeout: timedelta
+
+
+class StreamableHTTPTransport:
+    """StreamableHTTP client transport implementation."""
+
+    def __init__(
+        self,
+        url: str,
+        headers: dict[str, Any] | None = None,
+        timeout: timedelta = timedelta(seconds=30),
+        sse_read_timeout: timedelta = timedelta(seconds=60 * 5),
+    ) -> None:
+        """Initialize the StreamableHTTP transport.
+
+        Args:
+            url: The endpoint URL.
+            headers: Optional headers to include in requests.
+            timeout: HTTP timeout for regular operations.
+            sse_read_timeout: Timeout for SSE read operations.
+        """
+        self.url = url
+        self.headers = headers or {}
+        self.timeout = timeout
+        self.sse_read_timeout = sse_read_timeout
+        self.session_id: str | None = None
+        self.request_headers = {
+            ACCEPT: f"{JSON}, {SSE}",
+            CONTENT_TYPE: JSON,
+            **self.headers,
+        }
+
+    def _update_headers_with_session(self, base_headers: dict[str, str]) -> dict[str, str]:
+        """Update headers with session ID if available."""
+        headers = base_headers.copy()
+        if self.session_id:
+            headers[MCP_SESSION_ID] = self.session_id
+        return headers
+
+    def _is_initialization_request(self, message: JSONRPCMessage) -> bool:
+        """Check if the message is an initialization request."""
+        return isinstance(message.root, JSONRPCRequest) and message.root.method == "initialize"
+
+    def _is_initialized_notification(self, message: JSONRPCMessage) -> bool:
+        """Check if the message is an initialized notification."""
+        return isinstance(message.root, JSONRPCNotification) and message.root.method == "notifications/initialized"
+
+    def _maybe_extract_session_id_from_response(
+        self,
+        response: httpx.Response,
+    ) -> None:
+        """Extract and store session ID from response headers."""
+        new_session_id = response.headers.get(MCP_SESSION_ID)
+        if new_session_id:
+            self.session_id = new_session_id
+            logger.info(f"Received session ID: {self.session_id}")
+
+    def _handle_sse_event(
+        self,
+        sse: ServerSentEvent,
+        server_to_client_queue: ServerToClientQueue,
+        original_request_id: RequestId | None = None,
+        resumption_callback: Callable[[str], None] | None = None,
+    ) -> bool:
+        """Handle an SSE event, returning True if the response is complete."""
+        if sse.event == "message":
+            try:
+                message = JSONRPCMessage.model_validate_json(sse.data)
+                logger.debug(f"SSE message: {message}")
+
+                # If this is a response and we have original_request_id, replace it
+                if original_request_id is not None and isinstance(message.root, JSONRPCResponse | JSONRPCError):
+                    message.root.id = original_request_id
+
+                session_message = SessionMessage(message)
+                # Put message in queue that goes to client
+                server_to_client_queue.put(session_message)
+
+                # Call resumption token callback if we have an ID
+                if sse.id and resumption_callback:
+                    resumption_callback(sse.id)
+
+                # If this is a response or error return True indicating completion
+                # Otherwise, return False to continue listening
+                return isinstance(message.root, JSONRPCResponse | JSONRPCError)
+
+            except Exception as exc:
+                # Put exception in queue that goes to client
+                server_to_client_queue.put(exc)
+                return False
+        elif sse.event == "ping":
+            logger.debug("Received ping event")
+            return False
+        else:
+            logger.warning(f"Unknown SSE event: {sse.event}")
+            return False
+
+    def handle_get_stream(
+        self,
+        client: httpx.Client,
+        server_to_client_queue: ServerToClientQueue,
+    ) -> None:
+        """Handle GET stream for server-initiated messages."""
+        try:
+            if not self.session_id:
+                return
+
+            headers = self._update_headers_with_session(self.request_headers)
+
+            with ssrf_proxy_sse_connect(
+                self.url,
+                headers=headers,
+                timeout=httpx.Timeout(self.timeout.seconds, read=self.sse_read_timeout.seconds),
+                client=client,
+                method="GET",
+            ) as event_source:
+                event_source.response.raise_for_status()
+                logger.debug("GET SSE connection established")
+
+                for sse in event_source.iter_sse():
+                    self._handle_sse_event(sse, server_to_client_queue)
+
+        except Exception as exc:
+            logger.debug(f"GET stream error (non-fatal): {exc}")
+
+    def _handle_resumption_request(self, ctx: RequestContext) -> None:
+        """Handle a resumption request using GET with SSE."""
+        headers = self._update_headers_with_session(ctx.headers)
+        if ctx.metadata and ctx.metadata.resumption_token:
+            headers[LAST_EVENT_ID] = ctx.metadata.resumption_token
+        else:
+            raise ResumptionError("Resumption request requires a resumption token")
+
+        # Extract original request ID to map responses
+        original_request_id = None
+        if isinstance(ctx.session_message.message.root, JSONRPCRequest):
+            original_request_id = ctx.session_message.message.root.id
+
+        with ssrf_proxy_sse_connect(
+            self.url,
+            headers=headers,
+            timeout=httpx.Timeout(self.timeout.seconds, read=ctx.sse_read_timeout.seconds),
+            client=ctx.client,
+            method="GET",
+        ) as event_source:
+            event_source.response.raise_for_status()
+            logger.debug("Resumption GET SSE connection established")
+
+            for sse in event_source.iter_sse():
+                is_complete = self._handle_sse_event(
+                    sse,
+                    ctx.server_to_client_queue,
+                    original_request_id,
+                    ctx.metadata.on_resumption_token_update if ctx.metadata else None,
+                )
+                if is_complete:
+                    break
+
+    def _handle_post_request(self, ctx: RequestContext) -> None:
+        """Handle a POST request with response processing."""
+        headers = self._update_headers_with_session(ctx.headers)
+        message = ctx.session_message.message
+        is_initialization = self._is_initialization_request(message)
+
+        with ctx.client.stream(
+            "POST",
+            self.url,
+            json=message.model_dump(by_alias=True, mode="json", exclude_none=True),
+            headers=headers,
+        ) as response:
+            if response.status_code == 202:
+                logger.debug("Received 202 Accepted")
+                return
+
+            if response.status_code == 404:
+                if isinstance(message.root, JSONRPCRequest):
+                    self._send_session_terminated_error(
+                        ctx.server_to_client_queue,
+                        message.root.id,
+                    )
+                return
+
+            response.raise_for_status()
+            if is_initialization:
+                self._maybe_extract_session_id_from_response(response)
+
+            content_type = cast(str, response.headers.get(CONTENT_TYPE, "").lower())
+
+            if content_type.startswith(JSON):
+                self._handle_json_response(response, ctx.server_to_client_queue)
+            elif content_type.startswith(SSE):
+                self._handle_sse_response(response, ctx)
+            else:
+                self._handle_unexpected_content_type(
+                    content_type,
+                    ctx.server_to_client_queue,
+                )
+
+    def _handle_json_response(
+        self,
+        response: httpx.Response,
+        server_to_client_queue: ServerToClientQueue,
+    ) -> None:
+        """Handle JSON response from the server."""
+        try:
+            content = response.read()
+            message = JSONRPCMessage.model_validate_json(content)
+            session_message = SessionMessage(message)
+            server_to_client_queue.put(session_message)
+        except Exception as exc:
+            server_to_client_queue.put(exc)
+
+    def _handle_sse_response(self, response: httpx.Response, ctx: RequestContext) -> None:
+        """Handle SSE response from the server."""
+        try:
+            event_source = EventSource(response)
+            for sse in event_source.iter_sse():
+                is_complete = self._handle_sse_event(
+                    sse,
+                    ctx.server_to_client_queue,
+                    resumption_callback=(ctx.metadata.on_resumption_token_update if ctx.metadata else None),
+                )
+                if is_complete:
+                    break
+        except Exception as e:
+            ctx.server_to_client_queue.put(e)
+
+    def _handle_unexpected_content_type(
+        self,
+        content_type: str,
+        server_to_client_queue: ServerToClientQueue,
+    ) -> None:
+        """Handle unexpected content type in response."""
+        error_msg = f"Unexpected content type: {content_type}"
+        logger.error(error_msg)
+        server_to_client_queue.put(ValueError(error_msg))
+
+    def _send_session_terminated_error(
+        self,
+        server_to_client_queue: ServerToClientQueue,
+        request_id: RequestId,
+    ) -> None:
+        """Send a session terminated error response."""
+        jsonrpc_error = JSONRPCError(
+            jsonrpc="2.0",
+            id=request_id,
+            error=ErrorData(code=32600, message="Session terminated by server"),
+        )
+        session_message = SessionMessage(JSONRPCMessage(jsonrpc_error))
+        server_to_client_queue.put(session_message)
+
+    def post_writer(
+        self,
+        client: httpx.Client,
+        client_to_server_queue: ClientToServerQueue,
+        server_to_client_queue: ServerToClientQueue,
+        start_get_stream: Callable[[], None],
+    ) -> None:
+        """Handle writing requests to the server.
+
+        This method processes messages from the client_to_server_queue and sends them to the server.
+        Responses are written to the server_to_client_queue.
+        """
+        while True:
+            try:
+                # Read message from client queue with timeout to check stop_event periodically
+                session_message = client_to_server_queue.get(timeout=DEFAULT_QUEUE_READ_TIMEOUT)
+                if session_message is None:
+                    break
+
+                message = session_message.message
+                metadata = (
+                    session_message.metadata if isinstance(session_message.metadata, ClientMessageMetadata) else None
+                )
+
+                # Check if this is a resumption request
+                is_resumption = bool(metadata and metadata.resumption_token)
+
+                logger.debug(f"Sending client message: {message}")
+
+                # Handle initialized notification
+                if self._is_initialized_notification(message):
+                    start_get_stream()
+
+                ctx = RequestContext(
+                    client=client,
+                    headers=self.request_headers,
+                    session_id=self.session_id,
+                    session_message=session_message,
+                    metadata=metadata,
+                    server_to_client_queue=server_to_client_queue,  # Queue to write responses to client
+                    sse_read_timeout=self.sse_read_timeout,
+                )
+
+                if is_resumption:
+                    self._handle_resumption_request(ctx)
+                else:
+                    self._handle_post_request(ctx)
+            except queue.Empty:
+                continue
+            except Exception as exc:
+                server_to_client_queue.put(exc)
+
+    def terminate_session(self, client: httpx.Client) -> None:
+        """Terminate the session by sending a DELETE request."""
+        if not self.session_id:
+            return
+
+        try:
+            headers = self._update_headers_with_session(self.request_headers)
+            response = client.delete(self.url, headers=headers)
+
+            if response.status_code == 405:
+                logger.debug("Server does not allow session termination")
+            elif response.status_code != 200:
+                logger.warning(f"Session termination failed: {response.status_code}")
+        except Exception as exc:
+            logger.warning(f"Session termination failed: {exc}")
+
+    def get_session_id(self) -> str | None:
+        """Get the current session ID."""
+        return self.session_id
+
+
+@contextmanager
+def streamablehttp_client(
+    url: str,
+    headers: dict[str, Any] | None = None,
+    timeout: timedelta = timedelta(seconds=30),
+    sse_read_timeout: timedelta = timedelta(seconds=60 * 5),
+    terminate_on_close: bool = True,
+) -> Generator[
+    tuple[
+        ServerToClientQueue,  # Queue for receiving messages FROM server
+        ClientToServerQueue,  # Queue for sending messages TO server
+        GetSessionIdCallback,
+    ],
+    None,
+    None,
+]:
+    """
+    Client transport for StreamableHTTP.
+
+    `sse_read_timeout` determines how long (in seconds) the client will wait for a new
+    event before disconnecting. All other HTTP operations are controlled by `timeout`.
+
+    Yields:
+        Tuple containing:
+            - server_to_client_queue: Queue for reading messages FROM the server
+            - client_to_server_queue: Queue for sending messages TO the server
+            - get_session_id_callback: Function to retrieve the current session ID
+    """
+    transport = StreamableHTTPTransport(url, headers, timeout, sse_read_timeout)
+
+    # Create queues with clear directional meaning
+    server_to_client_queue: ServerToClientQueue = queue.Queue()  # For messages FROM server TO client
+    client_to_server_queue: ClientToServerQueue = queue.Queue()  # For messages FROM client TO server
+
+    with ThreadPoolExecutor(max_workers=2) as executor:
+        try:
+            with create_ssrf_proxy_mcp_http_client(
+                headers=transport.request_headers,
+                timeout=httpx.Timeout(transport.timeout.seconds, read=transport.sse_read_timeout.seconds),
+            ) as client:
+                # Define callbacks that need access to thread pool
+                def start_get_stream() -> None:
+                    """Start a worker thread to handle server-initiated messages."""
+                    executor.submit(transport.handle_get_stream, client, server_to_client_queue)
+
+                # Start the post_writer worker thread
+                executor.submit(
+                    transport.post_writer,
+                    client,
+                    client_to_server_queue,  # Queue for messages FROM client TO server
+                    server_to_client_queue,  # Queue for messages FROM server TO client
+                    start_get_stream,
+                )
+
+                try:
+                    yield (
+                        server_to_client_queue,  # Queue for receiving messages FROM server
+                        client_to_server_queue,  # Queue for sending messages TO server
+                        transport.get_session_id,
+                    )
+                finally:
+                    if transport.session_id and terminate_on_close:
+                        transport.terminate_session(client)
+
+                    # Signal threads to stop
+                    client_to_server_queue.put(None)
+        finally:
+            # Clear any remaining items and add None sentinel to unblock any waiting threads
+            try:
+                while not client_to_server_queue.empty():
+                    client_to_server_queue.get_nowait()
+            except queue.Empty:
+                pass
+
+            client_to_server_queue.put(None)
+            server_to_client_queue.put(None)

api/core/mcp/entities.py

@@ -0,0 +1,19 @@
+from dataclasses import dataclass
+from typing import Any, Generic, TypeVar
+
+from core.mcp.session.base_session import BaseSession
+from core.mcp.types import LATEST_PROTOCOL_VERSION, RequestId, RequestParams
+
+SUPPORTED_PROTOCOL_VERSIONS: list[str] = ["2024-11-05", LATEST_PROTOCOL_VERSION]
+
+
+SessionT = TypeVar("SessionT", bound=BaseSession[Any, Any, Any, Any, Any])
+LifespanContextT = TypeVar("LifespanContextT")
+
+
+@dataclass
+class RequestContext(Generic[SessionT, LifespanContextT]):
+    request_id: RequestId
+    meta: RequestParams.Meta | None
+    session: SessionT
+    lifespan_context: LifespanContextT

api/core/mcp/error.py

@@ -0,0 +1,10 @@
+class MCPError(Exception):
+    pass
+
+
+class MCPConnectionError(MCPError):
+    pass
+
+
+class MCPAuthError(MCPConnectionError):
+    pass

api/core/mcp/mcp_client.py

@@ -0,0 +1,150 @@
+import logging
+from collections.abc import Callable
+from contextlib import AbstractContextManager, ExitStack
+from types import TracebackType
+from typing import Any, Optional, cast
+from urllib.parse import urlparse
+
+from core.mcp.client.sse_client import sse_client
+from core.mcp.client.streamable_client import streamablehttp_client
+from core.mcp.error import MCPAuthError, MCPConnectionError
+from core.mcp.session.client_session import ClientSession
+from core.mcp.types import Tool
+
+logger = logging.getLogger(__name__)
+
+
+class MCPClient:
+    def __init__(
+        self,
+        server_url: str,
+        provider_id: str,
+        tenant_id: str,
+        authed: bool = True,
+        authorization_code: Optional[str] = None,
+        for_list: bool = False,
+    ):
+        # Initialize info
+        self.provider_id = provider_id
+        self.tenant_id = tenant_id
+        self.client_type = "streamable"
+        self.server_url = server_url
+
+        # Authentication info
+        self.authed = authed
+        self.authorization_code = authorization_code
+        if authed:
+            from core.mcp.auth.auth_provider import OAuthClientProvider
+
+            self.provider = OAuthClientProvider(self.provider_id, self.tenant_id, for_list=for_list)
+            self.token = self.provider.tokens()
+
+        # Initialize session and client objects
+        self._session: Optional[ClientSession] = None
+        self._streams_context: Optional[AbstractContextManager[Any]] = None
+        self._session_context: Optional[ClientSession] = None
+        self.exit_stack = ExitStack()
+
+        # Whether the client has been initialized
+        self._initialized = False
+
+    def __enter__(self):
+        self._initialize()
+        self._initialized = True
+        return self
+
+    def __exit__(
+        self, exc_type: Optional[type], exc_value: Optional[BaseException], traceback: Optional[TracebackType]
+    ):
+        self.cleanup()
+
+    def _initialize(
+        self,
+    ):
+        """Initialize the client with fallback to SSE if streamable connection fails"""
+        connection_methods: dict[str, Callable[..., AbstractContextManager[Any]]] = {
+            "mcp": streamablehttp_client,
+            "sse": sse_client,
+        }
+
+        parsed_url = urlparse(self.server_url)
+        path = parsed_url.path
+        method_name = path.rstrip("/").split("/")[-1] if path else ""
+        try:
+            client_factory = connection_methods[method_name]
+            self.connect_server(client_factory, method_name)
+        except KeyError:
+            try:
+                self.connect_server(sse_client, "sse")
+            except MCPConnectionError:
+                self.connect_server(streamablehttp_client, "mcp")
+
+    def connect_server(
+        self, client_factory: Callable[..., AbstractContextManager[Any]], method_name: str, first_try: bool = True
+    ):
+        from core.mcp.auth.auth_flow import auth
+
+        try:
+            headers = (
+                {"Authorization": f"{self.token.token_type.capitalize()} {self.token.access_token}"}
+                if self.authed and self.token
+                else {}
+            )
+            self._streams_context = client_factory(url=self.server_url, headers=headers)
+            if self._streams_context is None:
+                raise MCPConnectionError("Failed to create connection context")
+
+            # Use exit_stack to manage context managers properly
+            if method_name == "mcp":
+                read_stream, write_stream, _ = self.exit_stack.enter_context(self._streams_context)
+                streams = (read_stream, write_stream)
+            else:  # sse_client
+                streams = self.exit_stack.enter_context(self._streams_context)
+
+            self._session_context = ClientSession(*streams)
+            self._session = self.exit_stack.enter_context(self._session_context)
+            session = cast(ClientSession, self._session)
+            session.initialize()
+            return
+
+        except MCPAuthError:
+            if not self.authed:
+                raise
+            try:
+                auth(self.provider, self.server_url, self.authorization_code)
+            except Exception as e:
+                raise ValueError(f"Failed to authenticate: {e}")
+            self.token = self.provider.tokens()
+            if first_try:
+                return self.connect_server(client_factory, method_name, first_try=False)
+
+        except MCPConnectionError:
+            raise
+
+    def list_tools(self) -> list[Tool]:
+        """Connect to an MCP server running with SSE transport"""
+        # List available tools to verify connection
+        if not self._initialized or not self._session:
+            raise ValueError("Session not initialized.")
+        response = self._session.list_tools()
+        tools = response.tools
+        return tools
+
+    def invoke_tool(self, tool_name: str, tool_args: dict):
+        """Call a tool"""
+        if not self._initialized or not self._session:
+            raise ValueError("Session not initialized.")
+        return self._session.call_tool(tool_name, tool_args)
+
+    def cleanup(self):
+        """Clean up resources"""
+        try:
+            # ExitStack will handle proper cleanup of all managed context managers
+            self.exit_stack.close()
+            self._session = None
+            self._session_context = None
+            self._streams_context = None
+            self._initialized = False
+        except Exception as e:
+            logging.exception("Error during cleanup")
+            raise ValueError(f"Error during cleanup: {e}")

api/core/mcp/server/streamable_http.py

@@ -0,0 +1,228 @@
+import json
+import logging
+from collections.abc import Mapping
+from typing import Any, cast
+
+from configs import dify_config
+from controllers.web.passport import generate_session_id
+from core.app.app_config.entities import VariableEntity, VariableEntityType
+from core.app.entities.app_invoke_entities import InvokeFrom
+from core.app.features.rate_limiting.rate_limit import RateLimitGenerator
+from core.mcp import types
+from core.mcp.types import INTERNAL_ERROR, INVALID_PARAMS, METHOD_NOT_FOUND
+from core.mcp.utils import create_mcp_error_response
+from core.model_runtime.utils.encoders import jsonable_encoder
+from extensions.ext_database import db
+from models.model import App, AppMCPServer, AppMode, EndUser
+from services.app_generate_service import AppGenerateService
+
+"""
+Apply to MCP HTTP streamable server with stateless http
+"""
+logger = logging.getLogger(__name__)
+
+
+class MCPServerStreamableHTTPRequestHandler:
+    def __init__(
+        self, app: App, request: types.ClientRequest | types.ClientNotification, user_input_form: list[VariableEntity]
+    ):
+        self.app = app
+        self.request = request
+        mcp_server = db.session.query(AppMCPServer).filter(AppMCPServer.app_id == self.app.id).first()
+        if not mcp_server:
+            raise ValueError("MCP server not found")
+        self.mcp_server: AppMCPServer = mcp_server
+        self.end_user = self.retrieve_end_user()
+        self.user_input_form = user_input_form
+
+    @property
+    def request_type(self):
+        return type(self.request.root)
+
+    @property
+    def parameter_schema(self):
+        parameters, required = self._convert_input_form_to_parameters(self.user_input_form)
+        if self.app.mode in {AppMode.COMPLETION.value, AppMode.WORKFLOW.value}:
+            return {
+                "type": "object",
+                "properties": parameters,
+                "required": required,
+            }
+        return {
+            "type": "object",
+            "properties": {
+                "query": {"type": "string", "description": "User Input/Question content"},
+                **parameters,
+            },
+            "required": ["query", *required],
+        }
+
+    @property
+    def capabilities(self):
+        return types.ServerCapabilities(
+            tools=types.ToolsCapability(listChanged=False),
+        )
+
+    def response(self, response: types.Result | str):
+        if isinstance(response, str):
+            sse_content = f"event: ping\ndata: {response}\n\n".encode()
+            yield sse_content
+            return
+        json_response = types.JSONRPCResponse(
+            jsonrpc="2.0",
+            id=(self.request.root.model_extra or {}).get("id", 1),
+            result=response.model_dump(by_alias=True, mode="json", exclude_none=True),
+        )
+        json_data = json.dumps(jsonable_encoder(json_response))
+
+        sse_content = f"event: message\ndata: {json_data}\n\n".encode()
+
+        yield sse_content
+
+    def error_response(self, code: int, message: str, data=None):
+        request_id = (self.request.root.model_extra or {}).get("id", 1) or 1
+        return create_mcp_error_response(request_id, code, message, data)
+
+    def handle(self):
+        handle_map = {
+            types.InitializeRequest: self.initialize,
+            types.ListToolsRequest: self.list_tools,
+            types.CallToolRequest: self.invoke_tool,
+            types.InitializedNotification: self.handle_notification,
+            types.PingRequest: self.handle_ping,
+        }
+        try:
+            if self.request_type in handle_map:
+                return self.response(handle_map[self.request_type]())
+            else:
+                return self.error_response(METHOD_NOT_FOUND, f"Method not found: {self.request_type}")
+        except ValueError as e:
+            logger.exception("Invalid params")
+            return self.error_response(INVALID_PARAMS, str(e))
+        except Exception as e:
+            logger.exception("Internal server error")
+            return self.error_response(INTERNAL_ERROR, f"Internal server error: {str(e)}")
+
+    def handle_notification(self):
+        return "ping"
+
+    def handle_ping(self):
+        return types.EmptyResult()
+
+    def initialize(self):
+        request = cast(types.InitializeRequest, self.request.root)
+        client_info = request.params.clientInfo
+        client_name = f"{client_info.name}@{client_info.version}"
+        if not self.end_user:
+            end_user = EndUser(
+                tenant_id=self.app.tenant_id,
+                app_id=self.app.id,
+                type="mcp",
+                name=client_name,
+                session_id=generate_session_id(),
+                external_user_id=self.mcp_server.id,
+            )
+            db.session.add(end_user)
+            db.session.commit()
+        return types.InitializeResult(
+            protocolVersion=types.SERVER_LATEST_PROTOCOL_VERSION,
+            capabilities=self.capabilities,
+            serverInfo=types.Implementation(name="Dify", version=dify_config.project.version),
+            instructions=self.mcp_server.description,
+        )
+
+    def list_tools(self):
+        if not self.end_user:
+            raise ValueError("User not found")
+        return types.ListToolsResult(
+            tools=[
+                types.Tool(
+                    name=self.app.name,
+                    description=self.mcp_server.description,
+                    inputSchema=self.parameter_schema,
+                )
+            ],
+        )
+
+    def invoke_tool(self):
+        if not self.end_user:
+            raise ValueError("User not found")
+        request = cast(types.CallToolRequest, self.request.root)
+        args = request.params.arguments
+        if not args:
+            raise ValueError("No arguments provided")
+        if self.app.mode in {AppMode.WORKFLOW.value}:
+            args = {"inputs": args}
+        elif self.app.mode in {AppMode.COMPLETION.value}:
+            args = {"query": "", "inputs": args}
+        else:
+            args = {"query": args["query"], "inputs": {k: v for k, v in args.items() if k != "query"}}
+        response = AppGenerateService.generate(
+            self.app,
+            self.end_user,
+            args,
+            InvokeFrom.SERVICE_API,
+            streaming=self.app.mode == AppMode.AGENT_CHAT.value,
+        )
+        answer = ""
+        if isinstance(response, RateLimitGenerator):
+            for item in response.generator:
+                data = item
+                if isinstance(data, str) and data.startswith("data: "):
+                    try:
+                        json_str = data[6:].strip()
+                        parsed_data = json.loads(json_str)
+                        if parsed_data.get("event") == "agent_thought":
+                            answer += parsed_data.get("thought", "")
+                    except json.JSONDecodeError:
+                        continue
+        if isinstance(response, Mapping):
+            if self.app.mode in {
+                AppMode.ADVANCED_CHAT.value,
+                AppMode.COMPLETION.value,
+                AppMode.CHAT.value,
+                AppMode.AGENT_CHAT.value,
+            }:
+                answer = response["answer"]
+            elif self.app.mode in {AppMode.WORKFLOW.value}:
+                answer = json.dumps(response["data"]["outputs"], ensure_ascii=False)
+            else:
+                raise ValueError("Invalid app mode")
+            # Not support image yet
+        return types.CallToolResult(content=[types.TextContent(text=answer, type="text")])
+
+    def retrieve_end_user(self):
+        return (
+            db.session.query(EndUser)
+            .filter(EndUser.external_user_id == self.mcp_server.id, EndUser.type == "mcp")
+            .first()
+        )
+
+    def _convert_input_form_to_parameters(self, user_input_form: list[VariableEntity]):
+        parameters: dict[str, dict[str, Any]] = {}
+        required = []
+        for item in user_input_form:
+            parameters[item.variable] = {}
+            if item.type in (
+                VariableEntityType.FILE,
+                VariableEntityType.FILE_LIST,
+                VariableEntityType.EXTERNAL_DATA_TOOL,
+            ):
+                continue
+            if item.required:
+                required.append(item.variable)
+            # if the workflow republished, the parameters not changed
+            # we should not raise error here
+            try:
+                description = self.mcp_server.parameters_dict[item.variable]
+            except KeyError:
+                description = ""
+            parameters[item.variable]["description"] = description
+            if item.type in (VariableEntityType.TEXT_INPUT, VariableEntityType.PARAGRAPH):
+                parameters[item.variable]["type"] = "string"
+            elif item.type == VariableEntityType.SELECT:
+                parameters[item.variable]["type"] = "string"
+                parameters[item.variable]["enum"] = item.options
+            elif item.type == VariableEntityType.NUMBER:
+                parameters[item.variable]["type"] = "float"
+        return parameters, required

api/core/mcp/session/base_session.py

@@ -0,0 +1,397 @@
+import logging
+import queue
+from collections.abc import Callable
+from concurrent.futures import ThreadPoolExecutor
+from contextlib import ExitStack
+from datetime import timedelta
+from types import TracebackType
+from typing import Any, Generic, Self, TypeVar
+
+from httpx import HTTPStatusError
+from pydantic import BaseModel
+
+from core.mcp.error import MCPAuthError, MCPConnectionError
+from core.mcp.types import (
+    CancelledNotification,
+    ClientNotification,
+    ClientRequest,
+    ClientResult,
+    ErrorData,
+    JSONRPCError,
+    JSONRPCMessage,
+    JSONRPCNotification,
+    JSONRPCRequest,
+    JSONRPCResponse,
+    MessageMetadata,
+    RequestId,
+    RequestParams,
+    ServerMessageMetadata,
+    ServerNotification,
+    ServerRequest,
+    ServerResult,
+    SessionMessage,
+)
+
+SendRequestT = TypeVar("SendRequestT", ClientRequest, ServerRequest)
+SendResultT = TypeVar("SendResultT", ClientResult, ServerResult)
+SendNotificationT = TypeVar("SendNotificationT", ClientNotification, ServerNotification)
+ReceiveRequestT = TypeVar("ReceiveRequestT", ClientRequest, ServerRequest)
+ReceiveResultT = TypeVar("ReceiveResultT", bound=BaseModel)
+ReceiveNotificationT = TypeVar("ReceiveNotificationT", ClientNotification, ServerNotification)
+DEFAULT_RESPONSE_READ_TIMEOUT = 1.0
+
+
+class RequestResponder(Generic[ReceiveRequestT, SendResultT]):
+    """Handles responding to MCP requests and manages request lifecycle.
+
+    This class MUST be used as a context manager to ensure proper cleanup and
+    cancellation handling:
+
+    Example:
+        with request_responder as resp:
+            resp.respond(result)
+
+    The context manager ensures:
+    1. Proper cancellation scope setup and cleanup
+    2. Request completion tracking
+    3. Cleanup of in-flight requests
+    """
+
+    request: ReceiveRequestT
+    _session: Any
+    _on_complete: Callable[["RequestResponder[ReceiveRequestT, SendResultT]"], Any]
+
+    def __init__(
+        self,
+        request_id: RequestId,
+        request_meta: RequestParams.Meta | None,
+        request: ReceiveRequestT,
+        session: """BaseSession[
+            SendRequestT,
+            SendNotificationT,
+            SendResultT,
+            ReceiveRequestT,
+            ReceiveNotificationT
+        ]""",
+        on_complete: Callable[["RequestResponder[ReceiveRequestT, SendResultT]"], Any],
+    ) -> None:
+        self.request_id = request_id
+        self.request_meta = request_meta
+        self.request = request
+        self._session = session
+        self._completed = False
+        self._on_complete = on_complete
+        self._entered = False  # Track if we're in a context manager
+
+    def __enter__(self) -> "RequestResponder[ReceiveRequestT, SendResultT]":
+        """Enter the context manager, enabling request cancellation tracking."""
+        self._entered = True
+        return self
+
+    def __exit__(
+        self,
+        exc_type: type[BaseException] | None,
+        exc_val: BaseException | None,
+        exc_tb: TracebackType | None,
+    ) -> None:
+        """Exit the context manager, performing cleanup and notifying completion."""
+        try:
+            if self._completed:
+                self._on_complete(self)
+        finally:
+            self._entered = False
+
+    def respond(self, response: SendResultT | ErrorData) -> None:
+        """Send a response for this request.
+
+        Must be called within a context manager block.
+        Raises:
+            RuntimeError: If not used within a context manager
+            AssertionError: If request was already responded to
+        """
+        if not self._entered:
+            raise RuntimeError("RequestResponder must be used as a context manager")
+        assert not self._completed, "Request already responded to"
+
+        self._completed = True
+
+        self._session._send_response(request_id=self.request_id, response=response)
+
+    def cancel(self) -> None:
+        """Cancel this request and mark it as completed."""
+        if not self._entered:
+            raise RuntimeError("RequestResponder must be used as a context manager")
+
+        self._completed = True  # Mark as completed so it's removed from in_flight
+        # Send an error response to indicate cancellation
+        self._session._send_response(
+            request_id=self.request_id,
+            response=ErrorData(code=0, message="Request cancelled", data=None),
+        )
+
+
+class BaseSession(
+    Generic[
+        SendRequestT,
+        SendNotificationT,
+        SendResultT,
+        ReceiveRequestT,
+        ReceiveNotificationT,
+    ],
+):
+    """
+    Implements an MCP "session" on top of read/write streams, including features
+    like request/response linking, notifications, and progress.
+
+    This class is a context manager that automatically starts processing
+    messages when entered.
+    """
+
+    _response_streams: dict[RequestId, queue.Queue[JSONRPCResponse | JSONRPCError]]
+    _request_id: int
+    _in_flight: dict[RequestId, RequestResponder[ReceiveRequestT, SendResultT]]
+    _receive_request_type: type[ReceiveRequestT]
+    _receive_notification_type: type[ReceiveNotificationT]
+
+    def __init__(
+        self,
+        read_stream: queue.Queue,
+        write_stream: queue.Queue,
+        receive_request_type: type[ReceiveRequestT],
+        receive_notification_type: type[ReceiveNotificationT],
+        # If none, reading will never time out
+        read_timeout_seconds: timedelta | None = None,
+    ) -> None:
+        self._read_stream = read_stream
+        self._write_stream = write_stream
+        self._response_streams = {}
+        self._request_id = 0
+        self._receive_request_type = receive_request_type
+        self._receive_notification_type = receive_notification_type
+        self._session_read_timeout_seconds = read_timeout_seconds
+        self._in_flight = {}
+        self._exit_stack = ExitStack()
+
+    def __enter__(self) -> Self:
+        self._executor = ThreadPoolExecutor()
+        self._receiver_future = self._executor.submit(self._receive_loop)
+        return self
+
+    def check_receiver_status(self) -> None:
+        if self._receiver_future.done():
+            self._receiver_future.result()
+
+    def __exit__(
+        self, exc_type: type[BaseException] | None, exc_val: BaseException | None, exc_tb: TracebackType | None
+    ) -> None:
+        self._exit_stack.close()
+        self._read_stream.put(None)
+        self._write_stream.put(None)
+
+    def send_request(
+        self,
+        request: SendRequestT,
+        result_type: type[ReceiveResultT],
+        request_read_timeout_seconds: timedelta | None = None,
+        metadata: MessageMetadata = None,
+    ) -> ReceiveResultT:
+        """
+        Sends a request and wait for a response. Raises an McpError if the
+        response contains an error. If a request read timeout is provided, it
+        will take precedence over the session read timeout.
+
+        Do not use this method to emit notifications! Use send_notification()
+        instead.
+        """
+        self.check_receiver_status()
+
+        request_id = self._request_id
+        self._request_id = request_id + 1
+
+        response_queue: queue.Queue[JSONRPCResponse | JSONRPCError] = queue.Queue()
+        self._response_streams[request_id] = response_queue
+
+        try:
+            jsonrpc_request = JSONRPCRequest(
+                jsonrpc="2.0",
+                id=request_id,
+                **request.model_dump(by_alias=True, mode="json", exclude_none=True),
+            )
+
+            self._write_stream.put(SessionMessage(message=JSONRPCMessage(jsonrpc_request), metadata=metadata))
+            timeout = DEFAULT_RESPONSE_READ_TIMEOUT
+            if request_read_timeout_seconds is not None:
+                timeout = float(request_read_timeout_seconds.total_seconds())
+            elif self._session_read_timeout_seconds is not None:
+                timeout = float(self._session_read_timeout_seconds.total_seconds())
+            while True:
+                try:
+                    response_or_error = response_queue.get(timeout=timeout)
+                    break
+                except queue.Empty:
+                    self.check_receiver_status()
+                    continue
+
+            if response_or_error is None:
+                raise MCPConnectionError(
+                    ErrorData(
+                        code=500,
+                        message="No response received",
+                    )
+                )
+            elif isinstance(response_or_error, JSONRPCError):
+                if response_or_error.error.code == 401:
+                    raise MCPAuthError(
+                        ErrorData(code=response_or_error.error.code, message=response_or_error.error.message)
+                    )
+                else:
+                    raise MCPConnectionError(
+                        ErrorData(code=response_or_error.error.code, message=response_or_error.error.message)
+                    )
+            else:
+                return result_type.model_validate(response_or_error.result)
+
+        finally:
+            self._response_streams.pop(request_id, None)
+
+    def send_notification(
+        self,
+        notification: SendNotificationT,
+        related_request_id: RequestId | None = None,
+    ) -> None:
+        """
+        Emits a notification, which is a one-way message that does not expect
+        a response.
+        """
+        self.check_receiver_status()
+
+        # Some transport implementations may need to set the related_request_id
+        # to attribute to the notifications to the request that triggered them.
+        jsonrpc_notification = JSONRPCNotification(
+            jsonrpc="2.0",
+            **notification.model_dump(by_alias=True, mode="json", exclude_none=True),
+        )
+        session_message = SessionMessage(
+            message=JSONRPCMessage(jsonrpc_notification),
+            metadata=ServerMessageMetadata(related_request_id=related_request_id) if related_request_id else None,
+        )
+        self._write_stream.put(session_message)
+
+    def _send_response(self, request_id: RequestId, response: SendResultT | ErrorData) -> None:
+        if isinstance(response, ErrorData):
+            jsonrpc_error = JSONRPCError(jsonrpc="2.0", id=request_id, error=response)
+            session_message = SessionMessage(message=JSONRPCMessage(jsonrpc_error))
+            self._write_stream.put(session_message)
+        else:
+            jsonrpc_response = JSONRPCResponse(
+                jsonrpc="2.0",
+                id=request_id,
+                result=response.model_dump(by_alias=True, mode="json", exclude_none=True),
+            )
+            session_message = SessionMessage(message=JSONRPCMessage(jsonrpc_response))
+            self._write_stream.put(session_message)
+
+    def _receive_loop(self) -> None:
+        """
+        Main message processing loop.
+        In a real synchronous implementation, this would likely run in a separate thread.
+        """
+        while True:
+            try:
+                # Attempt to receive a message (this would be blocking in a synchronous context)
+                message = self._read_stream.get(timeout=DEFAULT_RESPONSE_READ_TIMEOUT)
+                if message is None:
+                    break
+                if isinstance(message, HTTPStatusError):
+                    response_queue = self._response_streams.get(self._request_id - 1)
+                    if response_queue is not None:
+                        response_queue.put(
+                            JSONRPCError(
+                                jsonrpc="2.0",
+                                id=self._request_id - 1,
+                                error=ErrorData(code=message.response.status_code, message=message.args[0]),
+                            )
+                        )
+                    else:
+                        self._handle_incoming(RuntimeError(f"Received response with an unknown request ID: {message}"))
+                elif isinstance(message, Exception):
+                    self._handle_incoming(message)
+                elif isinstance(message.message.root, JSONRPCRequest):
+                    validated_request = self._receive_request_type.model_validate(
+                        message.message.root.model_dump(by_alias=True, mode="json", exclude_none=True)
+                    )
+
+                    responder = RequestResponder(
+                        request_id=message.message.root.id,
+                        request_meta=validated_request.root.params.meta if validated_request.root.params else None,
+                        request=validated_request,
+                        session=self,
+                        on_complete=lambda r: self._in_flight.pop(r.request_id, None),
+                    )
+
+                    self._in_flight[responder.request_id] = responder
+                    self._received_request(responder)
+
+                    if not responder._completed:
+                        self._handle_incoming(responder)
+
+                elif isinstance(message.message.root, JSONRPCNotification):
+                    try:
+                        notification = self._receive_notification_type.model_validate(
+                            message.message.root.model_dump(by_alias=True, mode="json", exclude_none=True)
+                        )
+                        # Handle cancellation notifications
+                        if isinstance(notification.root, CancelledNotification):
+                            cancelled_id = notification.root.params.requestId
+                            if cancelled_id in self._in_flight:
+                                self._in_flight[cancelled_id].cancel()
+                        else:
+                            self._received_notification(notification)
+                            self._handle_incoming(notification)
+                    except Exception as e:
+                        # For other validation errors, log and continue
+                        logging.warning(f"Failed to validate notification: {e}. Message was: {message.message.root}")
+                else:  # Response or error
+                    response_queue = self._response_streams.get(message.message.root.id)
+                    if response_queue is not None:
+                        response_queue.put(message.message.root)
+                    else:
+                        self._handle_incoming(RuntimeError(f"Server Error: {message}"))
+            except queue.Empty:
+                continue
+            except Exception as e:
+                logging.exception("Error in message processing loop")
+                raise
+
+    def _received_request(self, responder: RequestResponder[ReceiveRequestT, SendResultT]) -> None:
+        """
+        Can be overridden by subclasses to handle a request without needing to
+        listen on the message stream.
+
+        If the request is responded to within this method, it will not be
+        forwarded on to the message stream.
+        """
+        pass
+
+    def _received_notification(self, notification: ReceiveNotificationT) -> None:
+        """
+        Can be overridden by subclasses to handle a notification without needing
+        to listen on the message stream.
+        """
+        pass
+
+    def send_progress_notification(
+        self, progress_token: str | int, progress: float, total: float | None = None
+    ) -> None:
+        """
+        Sends a progress notification for a request that is currently being
+        processed.
+        """
+        pass
+
+    def _handle_incoming(
+        self,
+        req: RequestResponder[ReceiveRequestT, SendResultT] | ReceiveNotificationT | Exception,
+    ) -> None:
+        """A generic handler for incoming messages. Overwritten by subclasses."""
+        pass

api/core/mcp/session/client_session.py

@@ -0,0 +1,365 @@
+from datetime import timedelta
+from typing import Any, Protocol
+
+from pydantic import AnyUrl, TypeAdapter
+
+from configs import dify_config
+from core.mcp import types
+from core.mcp.entities import SUPPORTED_PROTOCOL_VERSIONS, RequestContext
+from core.mcp.session.base_session import BaseSession, RequestResponder
+
+DEFAULT_CLIENT_INFO = types.Implementation(name="Dify", version=dify_config.project.version)
+
+
+class SamplingFnT(Protocol):
+    def __call__(
+        self,
+        context: RequestContext["ClientSession", Any],
+        params: types.CreateMessageRequestParams,
+    ) -> types.CreateMessageResult | types.ErrorData: ...
+
+
+class ListRootsFnT(Protocol):
+    def __call__(self, context: RequestContext["ClientSession", Any]) -> types.ListRootsResult | types.ErrorData: ...
+
+
+class LoggingFnT(Protocol):
+    def __call__(
+        self,
+        params: types.LoggingMessageNotificationParams,
+    ) -> None: ...
+
+
+class MessageHandlerFnT(Protocol):
+    def __call__(
+        self,
+        message: RequestResponder[types.ServerRequest, types.ClientResult] | types.ServerNotification | Exception,
+    ) -> None: ...
+
+
+def _default_message_handler(
+    message: RequestResponder[types.ServerRequest, types.ClientResult] | types.ServerNotification | Exception,
+) -> None:
+    if isinstance(message, Exception):
+        raise ValueError(str(message))
+    elif isinstance(message, (types.ServerNotification | RequestResponder)):
+        pass
+
+
+def _default_sampling_callback(
+    context: RequestContext["ClientSession", Any],
+    params: types.CreateMessageRequestParams,
+) -> types.CreateMessageResult | types.ErrorData:
+    return types.ErrorData(
+        code=types.INVALID_REQUEST,
+        message="Sampling not supported",
+    )
+
+
+def _default_list_roots_callback(
+    context: RequestContext["ClientSession", Any],
+) -> types.ListRootsResult | types.ErrorData:
+    return types.ErrorData(
+        code=types.INVALID_REQUEST,
+        message="List roots not supported",
+    )
+
+
+def _default_logging_callback(
+    params: types.LoggingMessageNotificationParams,
+) -> None:
+    pass
+
+
+ClientResponse: TypeAdapter[types.ClientResult | types.ErrorData] = TypeAdapter(types.ClientResult | types.ErrorData)
+
+
+class ClientSession(
+    BaseSession[
+        types.ClientRequest,
+        types.ClientNotification,
+        types.ClientResult,
+        types.ServerRequest,
+        types.ServerNotification,
+    ]
+):
+    def __init__(
+        self,
+        read_stream,
+        write_stream,
+        read_timeout_seconds: timedelta | None = None,
+        sampling_callback: SamplingFnT | None = None,
+        list_roots_callback: ListRootsFnT | None = None,
+        logging_callback: LoggingFnT | None = None,
+        message_handler: MessageHandlerFnT | None = None,
+        client_info: types.Implementation | None = None,
+    ) -> None:
+        super().__init__(
+            read_stream,
+            write_stream,
+            types.ServerRequest,
+            types.ServerNotification,
+            read_timeout_seconds=read_timeout_seconds,
+        )
+        self._client_info = client_info or DEFAULT_CLIENT_INFO
+        self._sampling_callback = sampling_callback or _default_sampling_callback
+        self._list_roots_callback = list_roots_callback or _default_list_roots_callback
+        self._logging_callback = logging_callback or _default_logging_callback
+        self._message_handler = message_handler or _default_message_handler
+
+    def initialize(self) -> types.InitializeResult:
+        sampling = types.SamplingCapability()
+        roots = types.RootsCapability(
+            # TODO: Should this be based on whether we
+            # _will_ send notifications, or only whether
+            # they're supported?
+            listChanged=True,
+        )
+
+        result = self.send_request(
+            types.ClientRequest(
+                types.InitializeRequest(
+                    method="initialize",
+                    params=types.InitializeRequestParams(
+                        protocolVersion=types.LATEST_PROTOCOL_VERSION,
+                        capabilities=types.ClientCapabilities(
+                            sampling=sampling,
+                            experimental=None,
+                            roots=roots,
+                        ),
+                        clientInfo=self._client_info,
+                    ),
+                )
+            ),
+            types.InitializeResult,
+        )
+
+        if result.protocolVersion not in SUPPORTED_PROTOCOL_VERSIONS:
+            raise RuntimeError(f"Unsupported protocol version from the server: {result.protocolVersion}")
+
+        self.send_notification(
+            types.ClientNotification(types.InitializedNotification(method="notifications/initialized"))
+        )
+
+        return result
+
+    def send_ping(self) -> types.EmptyResult:
+        """Send a ping request."""
+        return self.send_request(
+            types.ClientRequest(
+                types.PingRequest(
+                    method="ping",
+                )
+            ),
+            types.EmptyResult,
+        )
+
+    def send_progress_notification(
+        self, progress_token: str | int, progress: float, total: float | None = None
+    ) -> None:
+        """Send a progress notification."""
+        self.send_notification(
+            types.ClientNotification(
+                types.ProgressNotification(
+                    method="notifications/progress",
+                    params=types.ProgressNotificationParams(
+                        progressToken=progress_token,
+                        progress=progress,
+                        total=total,
+                    ),
+                ),
+            )
+        )
+
+    def set_logging_level(self, level: types.LoggingLevel) -> types.EmptyResult:
+        """Send a logging/setLevel request."""
+        return self.send_request(
+            types.ClientRequest(
+                types.SetLevelRequest(
+                    method="logging/setLevel",
+                    params=types.SetLevelRequestParams(level=level),
+                )
+            ),
+            types.EmptyResult,
+        )
+
+    def list_resources(self) -> types.ListResourcesResult:
+        """Send a resources/list request."""
+        return self.send_request(
+            types.ClientRequest(
+                types.ListResourcesRequest(
+                    method="resources/list",
+                )
+            ),
+            types.ListResourcesResult,
+        )
+
+    def list_resource_templates(self) -> types.ListResourceTemplatesResult:
+        """Send a resources/templates/list request."""
+        return self.send_request(
+            types.ClientRequest(
+                types.ListResourceTemplatesRequest(
+                    method="resources/templates/list",
+                )
+            ),
+            types.ListResourceTemplatesResult,
+        )
+
+    def read_resource(self, uri: AnyUrl) -> types.ReadResourceResult:
+        """Send a resources/read request."""
+        return self.send_request(
+            types.ClientRequest(
+                types.ReadResourceRequest(
+                    method="resources/read",
+                    params=types.ReadResourceRequestParams(uri=uri),
+                )
+            ),
+            types.ReadResourceResult,
+        )
+
+    def subscribe_resource(self, uri: AnyUrl) -> types.EmptyResult:
+        """Send a resources/subscribe request."""
+        return self.send_request(
+            types.ClientRequest(
+                types.SubscribeRequest(
+                    method="resources/subscribe",
+                    params=types.SubscribeRequestParams(uri=uri),
+                )
+            ),
+            types.EmptyResult,
+        )
+
+    def unsubscribe_resource(self, uri: AnyUrl) -> types.EmptyResult:
+        """Send a resources/unsubscribe request."""
+        return self.send_request(
+            types.ClientRequest(
+                types.UnsubscribeRequest(
+                    method="resources/unsubscribe",
+                    params=types.UnsubscribeRequestParams(uri=uri),
+                )
+            ),
+            types.EmptyResult,
+        )
+
+    def call_tool(
+        self,
+        name: str,
+        arguments: dict[str, Any] | None = None,
+        read_timeout_seconds: timedelta | None = None,
+    ) -> types.CallToolResult:
+        """Send a tools/call request."""
+
+        return self.send_request(
+            types.ClientRequest(
+                types.CallToolRequest(
+                    method="tools/call",
+                    params=types.CallToolRequestParams(name=name, arguments=arguments),
+                )
+            ),
+            types.CallToolResult,
+            request_read_timeout_seconds=read_timeout_seconds,
+        )
+
+    def list_prompts(self) -> types.ListPromptsResult:
+        """Send a prompts/list request."""
+        return self.send_request(
+            types.ClientRequest(
+                types.ListPromptsRequest(
+                    method="prompts/list",
+                )
+            ),
+            types.ListPromptsResult,
+        )
+
+    def get_prompt(self, name: str, arguments: dict[str, str] | None = None) -> types.GetPromptResult:
+        """Send a prompts/get request."""
+        return self.send_request(
+            types.ClientRequest(
+                types.GetPromptRequest(
+                    method="prompts/get",
+                    params=types.GetPromptRequestParams(name=name, arguments=arguments),
+                )
+            ),
+            types.GetPromptResult,
+        )
+
+    def complete(
+        self,
+        ref: types.ResourceReference | types.PromptReference,
+        argument: dict[str, str],
+    ) -> types.CompleteResult:
+        """Send a completion/complete request."""
+        return self.send_request(
+            types.ClientRequest(
+                types.CompleteRequest(
+                    method="completion/complete",
+                    params=types.CompleteRequestParams(
+                        ref=ref,
+                        argument=types.CompletionArgument(**argument),
+                    ),
+                )
+            ),
+            types.CompleteResult,
+        )
+
+    def list_tools(self) -> types.ListToolsResult:
+        """Send a tools/list request."""
+        return self.send_request(
+            types.ClientRequest(
+                types.ListToolsRequest(
+                    method="tools/list",
+                )
+            ),
+            types.ListToolsResult,
+        )
+
+    def send_roots_list_changed(self) -> None:
+        """Send a roots/list_changed notification."""
+        self.send_notification(
+            types.ClientNotification(
+                types.RootsListChangedNotification(
+                    method="notifications/roots/list_changed",
+                )
+            )
+        )
+
+    def _received_request(self, responder: RequestResponder[types.ServerRequest, types.ClientResult]) -> None:
+        ctx = RequestContext[ClientSession, Any](
+            request_id=responder.request_id,
+            meta=responder.request_meta,
+            session=self,
+            lifespan_context=None,
+        )
+
+        match responder.request.root:
+            case types.CreateMessageRequest(params=params):
+                with responder:
+                    response = self._sampling_callback(ctx, params)
+                    client_response = ClientResponse.validate_python(response)
+                    responder.respond(client_response)
+
+            case types.ListRootsRequest():
+                with responder:
+                    list_roots_response = self._list_roots_callback(ctx)
+                    client_response = ClientResponse.validate_python(list_roots_response)
+                    responder.respond(client_response)
+
+            case types.PingRequest():
+                with responder:
+                    return responder.respond(types.ClientResult(root=types.EmptyResult()))
+
+    def _handle_incoming(
+        self,
+        req: RequestResponder[types.ServerRequest, types.ClientResult] | types.ServerNotification | Exception,
+    ) -> None:
+        """Handle incoming messages by forwarding to the message handler."""
+        self._message_handler(req)
+
+    def _received_notification(self, notification: types.ServerNotification) -> None:
+        """Handle notifications from the server."""
+        # Process specific notification types
+        match notification.root:
+            case types.LoggingMessageNotification(params=params):
+                self._logging_callback(params)
+            case _:
+                pass

api/core/mcp/utils.py

@@ -0,0 +1,114 @@
+import json
+
+import httpx
+
+from configs import dify_config
+from core.mcp.types import ErrorData, JSONRPCError
+from core.model_runtime.utils.encoders import jsonable_encoder
+
+HTTP_REQUEST_NODE_SSL_VERIFY = dify_config.HTTP_REQUEST_NODE_SSL_VERIFY
+
+STATUS_FORCELIST = [429, 500, 502, 503, 504]
+
+
+def create_ssrf_proxy_mcp_http_client(
+    headers: dict[str, str] | None = None,
+    timeout: httpx.Timeout | None = None,
+) -> httpx.Client:
+    """Create an HTTPX client with SSRF proxy configuration for MCP connections.
+
+    Args:
+        headers: Optional headers to include in the client
+        timeout: Optional timeout configuration
+
+    Returns:
+        Configured httpx.Client with proxy settings
+    """
+    if dify_config.SSRF_PROXY_ALL_URL:
+        return httpx.Client(
+            verify=HTTP_REQUEST_NODE_SSL_VERIFY,
+            headers=headers or {},
+            timeout=timeout,
+            follow_redirects=True,
+            proxy=dify_config.SSRF_PROXY_ALL_URL,
+        )
+    elif dify_config.SSRF_PROXY_HTTP_URL and dify_config.SSRF_PROXY_HTTPS_URL:
+        proxy_mounts = {
+            "http://": httpx.HTTPTransport(proxy=dify_config.SSRF_PROXY_HTTP_URL, verify=HTTP_REQUEST_NODE_SSL_VERIFY),
+            "https://": httpx.HTTPTransport(
+                proxy=dify_config.SSRF_PROXY_HTTPS_URL, verify=HTTP_REQUEST_NODE_SSL_VERIFY
+            ),
+        }
+        return httpx.Client(
+            verify=HTTP_REQUEST_NODE_SSL_VERIFY,
+            headers=headers or {},
+            timeout=timeout,
+            follow_redirects=True,
+            mounts=proxy_mounts,
+        )
+    else:
+        return httpx.Client(
+            verify=HTTP_REQUEST_NODE_SSL_VERIFY,
+            headers=headers or {},
+            timeout=timeout,
+            follow_redirects=True,
+        )
+
+
+def ssrf_proxy_sse_connect(url, **kwargs):
+    """Connect to SSE endpoint with SSRF proxy protection.
+
+    This function creates an SSE connection using the configured proxy settings
+    to prevent SSRF attacks when connecting to external endpoints.
+
+    Args:
+        url: The SSE endpoint URL
+        **kwargs: Additional arguments passed to the SSE connection
+
+    Returns:
+        EventSource object for SSE streaming
+    """
+    from httpx_sse import connect_sse
+
+    # Extract client if provided, otherwise create one
+    client = kwargs.pop("client", None)
+    if client is None:
+        # Create client with SSRF proxy configuration
+        timeout = kwargs.pop(
+            "timeout",
+            httpx.Timeout(
+                timeout=dify_config.SSRF_DEFAULT_TIME_OUT,
+                connect=dify_config.SSRF_DEFAULT_CONNECT_TIME_OUT,
+                read=dify_config.SSRF_DEFAULT_READ_TIME_OUT,
+                write=dify_config.SSRF_DEFAULT_WRITE_TIME_OUT,
+            ),
+        )
+        headers = kwargs.pop("headers", {})
+        client = create_ssrf_proxy_mcp_http_client(headers=headers, timeout=timeout)
+        client_provided = False
+    else:
+        client_provided = True
+
+    # Extract method if provided, default to GET
+    method = kwargs.pop("method", "GET")
+
+    try:
+        return connect_sse(client, method, url, **kwargs)
+    except Exception:
+        # If we created the client, we need to clean it up on error
+        if not client_provided:
+            client.close()
+        raise
+
+
+def create_mcp_error_response(request_id: int | str | None, code: int, message: str, data=None):
+    """Create MCP error response"""
+    error_data = ErrorData(code=code, message=message, data=data)
+    json_response = JSONRPCError(
+        jsonrpc="2.0",
+        id=request_id or 1,
+        error=error_data,
+    )
+    json_data = json.dumps(jsonable_encoder(json_response))
+    sse_content = f"event: message\ndata: {json_data}\n\n".encode()
+    yield sse_content

api/core/memory/token_buffer_memory.py

@@ -1,6 +1,8 @@
 from collections.abc import Sequence
 from typing import Optional
 
+from sqlalchemy import select
+
 from core.app.app_config.features.file_upload.manager import FileUploadConfigManager
 from core.file import file_manager
 from core.model_manager import ModelInstance
@@ -17,11 +19,15 @@ from core.prompt.utils.extract_thread_messages import extract_thread_messages
 from extensions.ext_database import db
 from factories import file_factory
 from models.model import AppMode, Conversation, Message, MessageFile
-from models.workflow import WorkflowRun
+from models.workflow import Workflow, WorkflowRun
 
 
 class TokenBufferMemory:
-    def __init__(self, conversation: Conversation, model_instance: ModelInstance) -> None:
+    def __init__(
+        self,
+        conversation: Conversation,
+        model_instance: ModelInstance,
+    ) -> None:
         self.conversation = conversation
         self.model_instance = model_instance
 
@@ -36,20 +42,8 @@ class TokenBufferMemory:
         app_record = self.conversation.app
 
         # fetch limited messages, and return reversed
-        query = (
-            db.session.query(
-                Message.id,
-                Message.query,
-                Message.answer,
-                Message.created_at,
-                Message.workflow_run_id,
-                Message.parent_message_id,
-                Message.answer_tokens,
-            )
-            .filter(
-                Message.conversation_id == self.conversation.id,
-            )
-            .order_by(Message.created_at.desc())
+        stmt = (
+            select(Message).where(Message.conversation_id == self.conversation.id).order_by(Message.created_at.desc())
         )
 
         if message_limit and message_limit > 0:
@@ -57,7 +51,9 @@ class TokenBufferMemory:
         else:
             message_limit = 500
 
-        messages = query.limit(message_limit).all()
+        stmt = stmt.limit(message_limit)
+
+        messages = db.session.scalars(stmt).all()
 
         # instead of all messages from the conversation, we only need to extract messages
         # that belong to the thread of last message
@@ -74,18 +70,20 @@ class TokenBufferMemory:
             files = db.session.query(MessageFile).filter(MessageFile.message_id == message.id).all()
             if files:
                 file_extra_config = None
-                if self.conversation.mode not in {AppMode.ADVANCED_CHAT, AppMode.WORKFLOW}:
+                if self.conversation.mode in {AppMode.AGENT_CHAT, AppMode.COMPLETION, AppMode.CHAT}:
                     file_extra_config = FileUploadConfigManager.convert(self.conversation.model_config)
+                elif self.conversation.mode in {AppMode.ADVANCED_CHAT, AppMode.WORKFLOW}:
+                    workflow_run = db.session.scalar(
+                        select(WorkflowRun).where(WorkflowRun.id == message.workflow_run_id)
+                    )
+                    if not workflow_run:
+                        raise ValueError(f"Workflow run not found: {message.workflow_run_id}")
+                    workflow = db.session.scalar(select(Workflow).where(Workflow.id == workflow_run.workflow_id))
+                    if not workflow:
+                        raise ValueError(f"Workflow not found: {workflow_run.workflow_id}")
+                    file_extra_config = FileUploadConfigManager.convert(workflow.features_dict, is_vision=False)
                 else:
-                    if message.workflow_run_id:
-                        workflow_run = (
-                            db.session.query(WorkflowRun).filter(WorkflowRun.id == message.workflow_run_id).first()
-                        )
-
-                        if workflow_run and workflow_run.workflow:
-                            file_extra_config = FileUploadConfigManager.convert(
-                                workflow_run.workflow.features_dict, is_vision=False
-                            )
+                    raise AssertionError(f"Invalid app mode: {self.conversation.mode}")
 
                 detail = ImagePromptMessageContent.DETAIL.LOW
                 if file_extra_config and app_record:

api/core/model_runtime/entities/llm_entities.py

@@ -53,6 +53,37 @@ class LLMUsage(ModelUsage):
             latency=0.0,
         )
 
+    @classmethod
+    def from_metadata(cls, metadata: dict) -> "LLMUsage":
+        """
+        Create LLMUsage instance from metadata dictionary with default values.
+
+        Args:
+            metadata: Dictionary containing usage metadata
+
+        Returns:
+            LLMUsage instance with values from metadata or defaults
+        """
+        total_tokens = metadata.get("total_tokens", 0)
+        completion_tokens = metadata.get("completion_tokens", 0)
+        if total_tokens > 0 and completion_tokens == 0:
+            completion_tokens = total_tokens
+
+        return cls(
+            prompt_tokens=metadata.get("prompt_tokens", 0),
+            completion_tokens=completion_tokens,
+            total_tokens=total_tokens,
+            prompt_unit_price=Decimal(str(metadata.get("prompt_unit_price", 0))),
+            completion_unit_price=Decimal(str(metadata.get("completion_unit_price", 0))),
+            total_price=Decimal(str(metadata.get("total_price", 0))),
+            currency=metadata.get("currency", "USD"),
+            prompt_price_unit=Decimal(str(metadata.get("prompt_price_unit", 0))),
+            completion_price_unit=Decimal(str(metadata.get("completion_price_unit", 0))),
+            prompt_price=Decimal(str(metadata.get("prompt_price", 0))),
+            completion_price=Decimal(str(metadata.get("completion_price", 0))),
+            latency=metadata.get("latency", 0.0),
+        )
+
     def plus(self, other: "LLMUsage") -> "LLMUsage":
         """
         Add two LLMUsage instances together.

api/core/model_runtime/entities/provider_entities.py

@@ -123,6 +123,8 @@ class ProviderEntity(BaseModel):
     description: Optional[I18nObject] = None
     icon_small: Optional[I18nObject] = None
     icon_large: Optional[I18nObject] = None
+    icon_small_dark: Optional[I18nObject] = None
+    icon_large_dark: Optional[I18nObject] = None
     background: Optional[str] = None
     help: Optional[ProviderHelpEntity] = None
     supported_model_types: Sequence[ModelType]

api/core/ops/aliyun_trace/aliyun_trace.py

@@ -0,0 +1,487 @@
+import json
+import logging
+from collections.abc import Sequence
+from typing import Optional
+from urllib.parse import urljoin
+
+from opentelemetry.trace import Status, StatusCode
+from sqlalchemy.orm import Session, sessionmaker
+
+from core.ops.aliyun_trace.data_exporter.traceclient import (
+    TraceClient,
+    convert_datetime_to_nanoseconds,
+    convert_to_span_id,
+    convert_to_trace_id,
+    generate_span_id,
+)
+from core.ops.aliyun_trace.entities.aliyun_trace_entity import SpanData
+from core.ops.aliyun_trace.entities.semconv import (
+    GEN_AI_COMPLETION,
+    GEN_AI_FRAMEWORK,
+    GEN_AI_MODEL_NAME,
+    GEN_AI_PROMPT,
+    GEN_AI_PROMPT_TEMPLATE_TEMPLATE,
+    GEN_AI_PROMPT_TEMPLATE_VARIABLE,
+    GEN_AI_RESPONSE_FINISH_REASON,
+    GEN_AI_SESSION_ID,
+    GEN_AI_SPAN_KIND,
+    GEN_AI_SYSTEM,
+    GEN_AI_USAGE_INPUT_TOKENS,
+    GEN_AI_USAGE_OUTPUT_TOKENS,
+    GEN_AI_USAGE_TOTAL_TOKENS,
+    GEN_AI_USER_ID,
+    INPUT_VALUE,
+    OUTPUT_VALUE,
+    RETRIEVAL_DOCUMENT,
+    RETRIEVAL_QUERY,
+    TOOL_DESCRIPTION,
+    TOOL_NAME,
+    TOOL_PARAMETERS,
+    GenAISpanKind,
+)
+from core.ops.base_trace_instance import BaseTraceInstance
+from core.ops.entities.config_entity import AliyunConfig
+from core.ops.entities.trace_entity import (
+    BaseTraceInfo,
+    DatasetRetrievalTraceInfo,
+    GenerateNameTraceInfo,
+    MessageTraceInfo,
+    ModerationTraceInfo,
+    SuggestedQuestionTraceInfo,
+    ToolTraceInfo,
+    WorkflowTraceInfo,
+)
+from core.rag.models.document import Document
+from core.repositories import SQLAlchemyWorkflowNodeExecutionRepository
+from core.workflow.entities.workflow_node_execution import (
+    WorkflowNodeExecution,
+    WorkflowNodeExecutionMetadataKey,
+    WorkflowNodeExecutionStatus,
+)
+from core.workflow.nodes import NodeType
+from models import Account, App, EndUser, TenantAccountJoin, WorkflowNodeExecutionTriggeredFrom, db
+
+logger = logging.getLogger(__name__)
+
+
+class AliyunDataTrace(BaseTraceInstance):
+    def __init__(
+        self,
+        aliyun_config: AliyunConfig,
+    ):
+        super().__init__(aliyun_config)
+        base_url = aliyun_config.endpoint.rstrip("/")
+        endpoint = urljoin(base_url, f"adapt_{aliyun_config.license_key}/api/otlp/traces")
+        self.trace_client = TraceClient(service_name=aliyun_config.app_name, endpoint=endpoint)
+
+    def trace(self, trace_info: BaseTraceInfo):
+        if isinstance(trace_info, WorkflowTraceInfo):
+            self.workflow_trace(trace_info)
+        if isinstance(trace_info, MessageTraceInfo):
+            self.message_trace(trace_info)
+        if isinstance(trace_info, ModerationTraceInfo):
+            pass
+        if isinstance(trace_info, SuggestedQuestionTraceInfo):
+            self.suggested_question_trace(trace_info)
+        if isinstance(trace_info, DatasetRetrievalTraceInfo):
+            self.dataset_retrieval_trace(trace_info)
+        if isinstance(trace_info, ToolTraceInfo):
+            self.tool_trace(trace_info)
+        if isinstance(trace_info, GenerateNameTraceInfo):
+            pass
+
+    def api_check(self):
+        return self.trace_client.api_check()
+
+    def get_project_url(self):
+        try:
+            return self.trace_client.get_project_url()
+        except Exception as e:
+            logger.info(f"Aliyun get run url failed: {str(e)}", exc_info=True)
+            raise ValueError(f"Aliyun get run url failed: {str(e)}")
+
+    def workflow_trace(self, trace_info: WorkflowTraceInfo):
+        trace_id = convert_to_trace_id(trace_info.workflow_run_id)
+        workflow_span_id = convert_to_span_id(trace_info.workflow_run_id, "workflow")
+        self.add_workflow_span(trace_id, workflow_span_id, trace_info)
+
+        workflow_node_executions = self.get_workflow_node_executions(trace_info)
+        for node_execution in workflow_node_executions:
+            node_span = self.build_workflow_node_span(node_execution, trace_id, trace_info, workflow_span_id)
+            self.trace_client.add_span(node_span)
+
+    def message_trace(self, trace_info: MessageTraceInfo):
+        message_data = trace_info.message_data
+        if message_data is None:
+            return
+        message_id = trace_info.message_id
+
+        user_id = message_data.from_account_id
+        if message_data.from_end_user_id:
+            end_user_data: Optional[EndUser] = (
+                db.session.query(EndUser).filter(EndUser.id == message_data.from_end_user_id).first()
+            )
+            if end_user_data is not None:
+                user_id = end_user_data.session_id
+
+        status: Status = Status(StatusCode.OK)
+        if trace_info.error:
+            status = Status(StatusCode.ERROR, trace_info.error)
+
+        trace_id = convert_to_trace_id(message_id)
+        message_span_id = convert_to_span_id(message_id, "message")
+        message_span = SpanData(
+            trace_id=trace_id,
+            parent_span_id=None,
+            span_id=message_span_id,
+            name="message",
+            start_time=convert_datetime_to_nanoseconds(trace_info.start_time),
+            end_time=convert_datetime_to_nanoseconds(trace_info.end_time),
+            attributes={
+                GEN_AI_SESSION_ID: trace_info.metadata.get("conversation_id", ""),
+                GEN_AI_USER_ID: str(user_id),
+                GEN_AI_SPAN_KIND: GenAISpanKind.CHAIN.value,
+                GEN_AI_FRAMEWORK: "dify",
+                INPUT_VALUE: json.dumps(trace_info.inputs, ensure_ascii=False),
+                OUTPUT_VALUE: str(trace_info.outputs),
+            },
+            status=status,
+        )
+        self.trace_client.add_span(message_span)
+
+        app_model_config = getattr(trace_info.message_data, "app_model_config", {})
+        pre_prompt = getattr(app_model_config, "pre_prompt", "")
+        inputs_data = getattr(trace_info.message_data, "inputs", {})
+        llm_span = SpanData(
+            trace_id=trace_id,
+            parent_span_id=message_span_id,
+            span_id=convert_to_span_id(message_id, "llm"),
+            name="llm",
+            start_time=convert_datetime_to_nanoseconds(trace_info.start_time),
+            end_time=convert_datetime_to_nanoseconds(trace_info.end_time),
+            attributes={
+                GEN_AI_SESSION_ID: trace_info.metadata.get("conversation_id", ""),
+                GEN_AI_USER_ID: str(user_id),
+                GEN_AI_SPAN_KIND: GenAISpanKind.LLM.value,
+                GEN_AI_FRAMEWORK: "dify",
+                GEN_AI_MODEL_NAME: trace_info.metadata.get("ls_model_name", ""),
+                GEN_AI_SYSTEM: trace_info.metadata.get("ls_provider", ""),
+                GEN_AI_USAGE_INPUT_TOKENS: str(trace_info.message_tokens),
+                GEN_AI_USAGE_OUTPUT_TOKENS: str(trace_info.answer_tokens),
+                GEN_AI_USAGE_TOTAL_TOKENS: str(trace_info.total_tokens),
+                GEN_AI_PROMPT_TEMPLATE_VARIABLE: json.dumps(inputs_data, ensure_ascii=False),
+                GEN_AI_PROMPT_TEMPLATE_TEMPLATE: pre_prompt,
+                GEN_AI_PROMPT: json.dumps(trace_info.inputs, ensure_ascii=False),
+                GEN_AI_COMPLETION: str(trace_info.outputs),
+                INPUT_VALUE: json.dumps(trace_info.inputs, ensure_ascii=False),
+                OUTPUT_VALUE: str(trace_info.outputs),
+            },
+            status=status,
+        )
+        self.trace_client.add_span(llm_span)
+
+    def dataset_retrieval_trace(self, trace_info: DatasetRetrievalTraceInfo):
+        if trace_info.message_data is None:
+            return
+        message_id = trace_info.message_id
+
+        documents_data = extract_retrieval_documents(trace_info.documents)
+        dataset_retrieval_span = SpanData(
+            trace_id=convert_to_trace_id(message_id),
+            parent_span_id=convert_to_span_id(message_id, "message"),
+            span_id=generate_span_id(),
+            name="dataset_retrieval",
+            start_time=convert_datetime_to_nanoseconds(trace_info.start_time),
+            end_time=convert_datetime_to_nanoseconds(trace_info.end_time),
+            attributes={
+                GEN_AI_SPAN_KIND: GenAISpanKind.RETRIEVER.value,
+                GEN_AI_FRAMEWORK: "dify",
+                RETRIEVAL_QUERY: str(trace_info.inputs),
+                RETRIEVAL_DOCUMENT: json.dumps(documents_data, ensure_ascii=False),
+                INPUT_VALUE: str(trace_info.inputs),
+                OUTPUT_VALUE: json.dumps(documents_data, ensure_ascii=False),
+            },
+        )
+        self.trace_client.add_span(dataset_retrieval_span)
+
+    def tool_trace(self, trace_info: ToolTraceInfo):
+        if trace_info.message_data is None:
+            return
+        message_id = trace_info.message_id
+
+        status: Status = Status(StatusCode.OK)
+        if trace_info.error:
+            status = Status(StatusCode.ERROR, trace_info.error)
+
+        tool_span = SpanData(
+            trace_id=convert_to_trace_id(message_id),
+            parent_span_id=convert_to_span_id(message_id, "message"),
+            span_id=generate_span_id(),
+            name=trace_info.tool_name,
+            start_time=convert_datetime_to_nanoseconds(trace_info.start_time),
+            end_time=convert_datetime_to_nanoseconds(trace_info.end_time),
+            attributes={
+                GEN_AI_SPAN_KIND: GenAISpanKind.TOOL.value,
+                GEN_AI_FRAMEWORK: "dify",
+                TOOL_NAME: trace_info.tool_name,
+                TOOL_DESCRIPTION: json.dumps(trace_info.tool_config, ensure_ascii=False),
+                TOOL_PARAMETERS: json.dumps(trace_info.tool_inputs, ensure_ascii=False),
+                INPUT_VALUE: json.dumps(trace_info.inputs, ensure_ascii=False),
+                OUTPUT_VALUE: str(trace_info.tool_outputs),
+            },
+            status=status,
+        )
+        self.trace_client.add_span(tool_span)
+
+    def get_workflow_node_executions(self, trace_info: WorkflowTraceInfo) -> Sequence[WorkflowNodeExecution]:
+        # through workflow_run_id get all_nodes_execution using repository
+        session_factory = sessionmaker(bind=db.engine)
+        # Find the app's creator account
+        with Session(db.engine, expire_on_commit=False) as session:
+            # Get the app to find its creator
+            app_id = trace_info.metadata.get("app_id")
+            if not app_id:
+                raise ValueError("No app_id found in trace_info metadata")
+
+            app = session.query(App).filter(App.id == app_id).first()
+            if not app:
+                raise ValueError(f"App with id {app_id} not found")
+
+            if not app.created_by:
+                raise ValueError(f"App with id {app_id} has no creator (created_by is None)")
+
+            service_account = session.query(Account).filter(Account.id == app.created_by).first()
+            if not service_account:
+                raise ValueError(f"Creator account with id {app.created_by} not found for app {app_id}")
+            current_tenant = (
+                session.query(TenantAccountJoin).filter_by(account_id=service_account.id, current=True).first()
+            )
+            if not current_tenant:
+                raise ValueError(f"Current tenant not found for account {service_account.id}")
+            service_account.set_tenant_id(current_tenant.tenant_id)
+        workflow_node_execution_repository = SQLAlchemyWorkflowNodeExecutionRepository(
+            session_factory=session_factory,
+            user=service_account,
+            app_id=trace_info.metadata.get("app_id"),
+            triggered_from=WorkflowNodeExecutionTriggeredFrom.WORKFLOW_RUN,
+        )
+        # Get all executions for this workflow run
+        workflow_node_executions = workflow_node_execution_repository.get_by_workflow_run(
+            workflow_run_id=trace_info.workflow_run_id
+        )
+        return workflow_node_executions
+
+    def build_workflow_node_span(
+        self, node_execution: WorkflowNodeExecution, trace_id: int, trace_info: WorkflowTraceInfo, workflow_span_id: int
+    ):
+        try:
+            if node_execution.node_type == NodeType.LLM:
+                node_span = self.build_workflow_llm_span(trace_id, workflow_span_id, trace_info, node_execution)
+            elif node_execution.node_type == NodeType.KNOWLEDGE_RETRIEVAL:
+                node_span = self.build_workflow_retrieval_span(trace_id, workflow_span_id, trace_info, node_execution)
+            elif node_execution.node_type == NodeType.TOOL:
+                node_span = self.build_workflow_tool_span(trace_id, workflow_span_id, trace_info, node_execution)
+            else:
+                node_span = self.build_workflow_task_span(trace_id, workflow_span_id, trace_info, node_execution)
+            return node_span
+        except Exception:
+            return None
+
+    def get_workflow_node_status(self, node_execution: WorkflowNodeExecution) -> Status:
+        span_status: Status = Status(StatusCode.UNSET)
+        if node_execution.status == WorkflowNodeExecutionStatus.SUCCEEDED:
+            span_status = Status(StatusCode.OK)
+        elif node_execution.status in [WorkflowNodeExecutionStatus.FAILED, WorkflowNodeExecutionStatus.EXCEPTION]:
+            span_status = Status(StatusCode.ERROR, str(node_execution.error))
+        return span_status
+
+    def build_workflow_task_span(
+        self, trace_id: int, workflow_span_id: int, trace_info: WorkflowTraceInfo, node_execution: WorkflowNodeExecution
+    ) -> SpanData:
+        return SpanData(
+            trace_id=trace_id,
+            parent_span_id=workflow_span_id,
+            span_id=convert_to_span_id(node_execution.id, "node"),
+            name=node_execution.title,
+            start_time=convert_datetime_to_nanoseconds(node_execution.created_at),
+            end_time=convert_datetime_to_nanoseconds(node_execution.finished_at),
+            attributes={
+                GEN_AI_SESSION_ID: trace_info.metadata.get("conversation_id", ""),
+                GEN_AI_SPAN_KIND: GenAISpanKind.TASK.value,
+                GEN_AI_FRAMEWORK: "dify",
+                INPUT_VALUE: json.dumps(node_execution.inputs, ensure_ascii=False),
+                OUTPUT_VALUE: json.dumps(node_execution.outputs, ensure_ascii=False),
+            },
+            status=self.get_workflow_node_status(node_execution),
+        )
+
+    def build_workflow_tool_span(
+        self, trace_id: int, workflow_span_id: int, trace_info: WorkflowTraceInfo, node_execution: WorkflowNodeExecution
+    ) -> SpanData:
+        tool_des = {}
+        if node_execution.metadata:
+            tool_des = node_execution.metadata.get(WorkflowNodeExecutionMetadataKey.TOOL_INFO, {})
+        return SpanData(
+            trace_id=trace_id,
+            parent_span_id=workflow_span_id,
+            span_id=convert_to_span_id(node_execution.id, "node"),
+            name=node_execution.title,
+            start_time=convert_datetime_to_nanoseconds(node_execution.created_at),
+            end_time=convert_datetime_to_nanoseconds(node_execution.finished_at),
+            attributes={
+                GEN_AI_SPAN_KIND: GenAISpanKind.TOOL.value,
+                GEN_AI_FRAMEWORK: "dify",
+                TOOL_NAME: node_execution.title,
+                TOOL_DESCRIPTION: json.dumps(tool_des, ensure_ascii=False),
+                TOOL_PARAMETERS: json.dumps(node_execution.inputs if node_execution.inputs else {}, ensure_ascii=False),
+                INPUT_VALUE: json.dumps(node_execution.inputs if node_execution.inputs else {}, ensure_ascii=False),
+                OUTPUT_VALUE: json.dumps(node_execution.outputs, ensure_ascii=False),
+            },
+            status=self.get_workflow_node_status(node_execution),
+        )
+
+    def build_workflow_retrieval_span(
+        self, trace_id: int, workflow_span_id: int, trace_info: WorkflowTraceInfo, node_execution: WorkflowNodeExecution
+    ) -> SpanData:
+        input_value = ""
+        if node_execution.inputs:
+            input_value = str(node_execution.inputs.get("query", ""))
+        output_value = ""
+        if node_execution.outputs:
+            output_value = json.dumps(node_execution.outputs.get("result", []), ensure_ascii=False)
+        return SpanData(
+            trace_id=trace_id,
+            parent_span_id=workflow_span_id,
+            span_id=convert_to_span_id(node_execution.id, "node"),
+            name=node_execution.title,
+            start_time=convert_datetime_to_nanoseconds(node_execution.created_at),
+            end_time=convert_datetime_to_nanoseconds(node_execution.finished_at),
+            attributes={
+                GEN_AI_SPAN_KIND: GenAISpanKind.RETRIEVER.value,
+                GEN_AI_FRAMEWORK: "dify",
+                RETRIEVAL_QUERY: input_value,
+                RETRIEVAL_DOCUMENT: output_value,
+                INPUT_VALUE: input_value,
+                OUTPUT_VALUE: output_value,
+            },
+            status=self.get_workflow_node_status(node_execution),
+        )
+
+    def build_workflow_llm_span(
+        self, trace_id: int, workflow_span_id: int, trace_info: WorkflowTraceInfo, node_execution: WorkflowNodeExecution
+    ) -> SpanData:
+        process_data = node_execution.process_data or {}
+        outputs = node_execution.outputs or {}
+        usage_data = process_data.get("usage", {}) if "usage" in process_data else outputs.get("usage", {})
+        return SpanData(
+            trace_id=trace_id,
+            parent_span_id=workflow_span_id,
+            span_id=convert_to_span_id(node_execution.id, "node"),
+            name=node_execution.title,
+            start_time=convert_datetime_to_nanoseconds(node_execution.created_at),
+            end_time=convert_datetime_to_nanoseconds(node_execution.finished_at),
+            attributes={
+                GEN_AI_SESSION_ID: trace_info.metadata.get("conversation_id", ""),
+                GEN_AI_SPAN_KIND: GenAISpanKind.LLM.value,
+                GEN_AI_FRAMEWORK: "dify",
+                GEN_AI_MODEL_NAME: process_data.get("model_name", ""),
+                GEN_AI_SYSTEM: process_data.get("model_provider", ""),
+                GEN_AI_USAGE_INPUT_TOKENS: str(usage_data.get("prompt_tokens", 0)),
+                GEN_AI_USAGE_OUTPUT_TOKENS: str(usage_data.get("completion_tokens", 0)),
+                GEN_AI_USAGE_TOTAL_TOKENS: str(usage_data.get("total_tokens", 0)),
+                GEN_AI_PROMPT: json.dumps(process_data.get("prompts", []), ensure_ascii=False),
+                GEN_AI_COMPLETION: str(outputs.get("text", "")),
+                GEN_AI_RESPONSE_FINISH_REASON: outputs.get("finish_reason", ""),
+                INPUT_VALUE: json.dumps(process_data.get("prompts", []), ensure_ascii=False),
+                OUTPUT_VALUE: str(outputs.get("text", "")),
+            },
+            status=self.get_workflow_node_status(node_execution),
+        )
+
+    def add_workflow_span(self, trace_id: int, workflow_span_id: int, trace_info: WorkflowTraceInfo):
+        message_span_id = None
+        if trace_info.message_id:
+            message_span_id = convert_to_span_id(trace_info.message_id, "message")
+        user_id = trace_info.metadata.get("user_id")
+        status: Status = Status(StatusCode.OK)
+        if trace_info.error:
+            status = Status(StatusCode.ERROR, trace_info.error)
+        if message_span_id:  # chatflow
+            message_span = SpanData(
+                trace_id=trace_id,
+                parent_span_id=None,
+                span_id=message_span_id,
+                name="message",
+                start_time=convert_datetime_to_nanoseconds(trace_info.start_time),
+                end_time=convert_datetime_to_nanoseconds(trace_info.end_time),
+                attributes={
+                    GEN_AI_SESSION_ID: trace_info.metadata.get("conversation_id", ""),
+                    GEN_AI_USER_ID: str(user_id),
+                    GEN_AI_SPAN_KIND: GenAISpanKind.CHAIN.value,
+                    GEN_AI_FRAMEWORK: "dify",
+                    INPUT_VALUE: trace_info.workflow_run_inputs.get("sys.query", ""),
+                    OUTPUT_VALUE: json.dumps(trace_info.workflow_run_outputs, ensure_ascii=False),
+                },
+                status=status,
+            )
+            self.trace_client.add_span(message_span)
+
+        workflow_span = SpanData(
+            trace_id=trace_id,
+            parent_span_id=message_span_id,
+            span_id=workflow_span_id,
+            name="workflow",
+            start_time=convert_datetime_to_nanoseconds(trace_info.start_time),
+            end_time=convert_datetime_to_nanoseconds(trace_info.end_time),
+            attributes={
+                GEN_AI_USER_ID: str(user_id),
+                GEN_AI_SPAN_KIND: GenAISpanKind.CHAIN.value,
+                GEN_AI_FRAMEWORK: "dify",
+                INPUT_VALUE: json.dumps(trace_info.workflow_run_inputs, ensure_ascii=False),
+                OUTPUT_VALUE: json.dumps(trace_info.workflow_run_outputs, ensure_ascii=False),
+            },
+            status=status,
+        )
+        self.trace_client.add_span(workflow_span)
+
+    def suggested_question_trace(self, trace_info: SuggestedQuestionTraceInfo):
+        message_id = trace_info.message_id
+        status: Status = Status(StatusCode.OK)
+        if trace_info.error:
+            status = Status(StatusCode.ERROR, trace_info.error)
+        suggested_question_span = SpanData(
+            trace_id=convert_to_trace_id(message_id),
+            parent_span_id=convert_to_span_id(message_id, "message"),
+            span_id=convert_to_span_id(message_id, "suggested_question"),
+            name="suggested_question",
+            start_time=convert_datetime_to_nanoseconds(trace_info.start_time),
+            end_time=convert_datetime_to_nanoseconds(trace_info.end_time),
+            attributes={
+                GEN_AI_SPAN_KIND: GenAISpanKind.LLM.value,
+                GEN_AI_FRAMEWORK: "dify",
+                GEN_AI_MODEL_NAME: trace_info.metadata.get("ls_model_name", ""),
+                GEN_AI_SYSTEM: trace_info.metadata.get("ls_provider", ""),
+                GEN_AI_PROMPT: json.dumps(trace_info.inputs, ensure_ascii=False),
+                GEN_AI_COMPLETION: json.dumps(trace_info.suggested_question, ensure_ascii=False),
+                INPUT_VALUE: json.dumps(trace_info.inputs, ensure_ascii=False),
+                OUTPUT_VALUE: json.dumps(trace_info.suggested_question, ensure_ascii=False),
+            },
+            status=status,
+        )
+        self.trace_client.add_span(suggested_question_span)
+
+
+def extract_retrieval_documents(documents: list[Document]):
+    documents_data = []
+    for document in documents:
+        document_data = {
+            "content": document.page_content,
+            "metadata": {
+                "dataset_id": document.metadata.get("dataset_id"),
+                "doc_id": document.metadata.get("doc_id"),
+                "document_id": document.metadata.get("document_id"),
+            },
+            "score": document.metadata.get("score"),
+        }
+        documents_data.append(document_data)
+    return documents_data

api/core/ops/aliyun_trace/data_exporter/traceclient.py

@@ -0,0 +1,200 @@
+import hashlib
+import logging
+import random
+import socket
+import threading
+import uuid
+from collections import deque
+from collections.abc import Sequence
+from datetime import datetime
+from typing import Optional
+
+import requests
+from opentelemetry import trace as trace_api
+from opentelemetry.exporter.otlp.proto.http.trace_exporter import OTLPSpanExporter
+from opentelemetry.sdk.resources import Resource
+from opentelemetry.sdk.trace import ReadableSpan
+from opentelemetry.sdk.util.instrumentation import InstrumentationScope
+from opentelemetry.semconv.resource import ResourceAttributes
+
+from configs import dify_config
+from core.ops.aliyun_trace.entities.aliyun_trace_entity import SpanData
+
+INVALID_SPAN_ID = 0x0000000000000000
+INVALID_TRACE_ID = 0x00000000000000000000000000000000
+
+logger = logging.getLogger(__name__)
+
+
+class TraceClient:
+    def __init__(
+        self,
+        service_name: str,
+        endpoint: str,
+        max_queue_size: int = 1000,
+        schedule_delay_sec: int = 5,
+        max_export_batch_size: int = 50,
+    ):
+        self.endpoint = endpoint
+        self.resource = Resource(
+            attributes={
+                ResourceAttributes.SERVICE_NAME: service_name,
+                ResourceAttributes.SERVICE_VERSION: f"dify-{dify_config.project.version}-{dify_config.COMMIT_SHA}",
+                ResourceAttributes.DEPLOYMENT_ENVIRONMENT: f"{dify_config.DEPLOY_ENV}-{dify_config.EDITION}",
+                ResourceAttributes.HOST_NAME: socket.gethostname(),
+            }
+        )
+        self.span_builder = SpanBuilder(self.resource)
+        self.exporter = OTLPSpanExporter(endpoint=endpoint)
+
+        self.max_queue_size = max_queue_size
+        self.schedule_delay_sec = schedule_delay_sec
+        self.max_export_batch_size = max_export_batch_size
+
+        self.queue: deque = deque(maxlen=max_queue_size)
+        self.condition = threading.Condition(threading.Lock())
+        self.done = False
+
+        self.worker_thread = threading.Thread(target=self._worker, daemon=True)
+        self.worker_thread.start()
+
+        self._spans_dropped = False
+
+    def export(self, spans: Sequence[ReadableSpan]):
+        self.exporter.export(spans)
+
+    def api_check(self):
+        try:
+            response = requests.head(self.endpoint, timeout=5)
+            if response.status_code == 405:
+                return True
+            else:
+                logger.debug(f"AliyunTrace API check failed: Unexpected status code: {response.status_code}")
+                return False
+        except requests.exceptions.RequestException as e:
+            logger.debug(f"AliyunTrace API check failed: {str(e)}")
+            raise ValueError(f"AliyunTrace API check failed: {str(e)}")
+
+    def get_project_url(self):
+        return "https://arms.console.aliyun.com/#/llm"
+
+    def add_span(self, span_data: SpanData):
+        if span_data is None:
+            return
+        span: ReadableSpan = self.span_builder.build_span(span_data)
+        with self.condition:
+            if len(self.queue) == self.max_queue_size:
+                if not self._spans_dropped:
+                    logger.warning("Queue is full, likely spans will be dropped.")
+                    self._spans_dropped = True
+
+            self.queue.appendleft(span)
+            if len(self.queue) >= self.max_export_batch_size:
+                self.condition.notify()
+
+    def _worker(self):
+        while not self.done:
+            with self.condition:
+                if len(self.queue) < self.max_export_batch_size and not self.done:
+                    self.condition.wait(timeout=self.schedule_delay_sec)
+            self._export_batch()
+
+    def _export_batch(self):
+        spans_to_export: list[ReadableSpan] = []
+        with self.condition:
+            while len(spans_to_export) < self.max_export_batch_size and self.queue:
+                spans_to_export.append(self.queue.pop())
+
+        if spans_to_export:
+            try:
+                self.exporter.export(spans_to_export)
+            except Exception as e:
+                logger.debug(f"Error exporting spans: {e}")
+
+    def shutdown(self):
+        with self.condition:
+            self.done = True
+            self.condition.notify_all()
+        self.worker_thread.join()
+        self._export_batch()
+        self.exporter.shutdown()
+
+
+class SpanBuilder:
+    def __init__(self, resource):
+        self.resource = resource
+        self.instrumentation_scope = InstrumentationScope(
+            __name__,
+            "",
+            None,
+            None,
+        )
+
+    def build_span(self, span_data: SpanData) -> ReadableSpan:
+        span_context = trace_api.SpanContext(
+            trace_id=span_data.trace_id,
+            span_id=span_data.span_id,
+            is_remote=False,
+            trace_flags=trace_api.TraceFlags(trace_api.TraceFlags.SAMPLED),
+            trace_state=None,
+        )
+
+        parent_span_context = None
+        if span_data.parent_span_id is not None:
+            parent_span_context = trace_api.SpanContext(
+                trace_id=span_data.trace_id,
+                span_id=span_data.parent_span_id,
+                is_remote=False,
+                trace_flags=trace_api.TraceFlags(trace_api.TraceFlags.SAMPLED),
+                trace_state=None,
+            )
+
+        span = ReadableSpan(
+            name=span_data.name,
+            context=span_context,
+            parent=parent_span_context,
+            resource=self.resource,
+            attributes=span_data.attributes,
+            events=span_data.events,
+            links=span_data.links,
+            kind=trace_api.SpanKind.INTERNAL,
+            status=span_data.status,
+            start_time=span_data.start_time,
+            end_time=span_data.end_time,
+            instrumentation_scope=self.instrumentation_scope,
+        )
+        return span
+
+
+def generate_span_id() -> int:
+    span_id = random.getrandbits(64)
+    while span_id == INVALID_SPAN_ID:
+        span_id = random.getrandbits(64)
+    return span_id
+
+
+def convert_to_trace_id(uuid_v4: Optional[str]) -> int:
+    try:
+        uuid_obj = uuid.UUID(uuid_v4)
+        return uuid_obj.int
+    except Exception as e:
+        raise ValueError(f"Invalid UUID input: {e}")
+
+
+def convert_to_span_id(uuid_v4: Optional[str], span_type: str) -> int:
+    try:
+        uuid_obj = uuid.UUID(uuid_v4)
+    except Exception as e:
+        raise ValueError(f"Invalid UUID input: {e}")
+    combined_key = f"{uuid_obj.hex}-{span_type}"
+    hash_bytes = hashlib.sha256(combined_key.encode("utf-8")).digest()
+    span_id = int.from_bytes(hash_bytes[:8], byteorder="big", signed=False)
+    return span_id
+
+
+def convert_datetime_to_nanoseconds(start_time_a: Optional[datetime]) -> Optional[int]:
+    if start_time_a is None:
+        return None
+    timestamp_in_seconds = start_time_a.timestamp()
+    timestamp_in_nanoseconds = int(timestamp_in_seconds * 1e9)
+    return timestamp_in_nanoseconds

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

@@ -0,0 +1,21 @@
+from collections.abc import Sequence
+from typing import Optional
+
+from opentelemetry import trace as trace_api
+from opentelemetry.sdk.trace import Event, Status, StatusCode
+from pydantic import BaseModel, Field
+
+
+class SpanData(BaseModel):
+    model_config = {"arbitrary_types_allowed": True}
+
+    trace_id: int = Field(..., description="The unique identifier for the trace.")
+    parent_span_id: Optional[int] = Field(None, description="The ID of the parent span, if any.")
+    span_id: int = Field(..., description="The unique identifier for this span.")
+    name: str = Field(..., description="The name of the span.")
+    attributes: dict[str, str] = Field(default_factory=dict, description="Attributes associated with the span.")
+    events: Sequence[Event] = Field(default_factory=list, description="Events recorded in the span.")
+    links: Sequence[trace_api.Link] = Field(default_factory=list, description="Links to other spans.")
+    status: Status = Field(default=Status(StatusCode.UNSET), description="The status of the span.")
+    start_time: Optional[int] = Field(..., description="The start time of the span in nanoseconds.")
+    end_time: Optional[int] = Field(..., description="The end time of the span in nanoseconds.")

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

@@ -0,0 +1,64 @@
+from enum import Enum
+
+# public
+GEN_AI_SESSION_ID = "gen_ai.session.id"
+
+GEN_AI_USER_ID = "gen_ai.user.id"
+
+GEN_AI_USER_NAME = "gen_ai.user.name"
+
+GEN_AI_SPAN_KIND = "gen_ai.span.kind"
+
+GEN_AI_FRAMEWORK = "gen_ai.framework"
+
+
+# Chain
+INPUT_VALUE = "input.value"
+
+OUTPUT_VALUE = "output.value"
+
+
+# Retriever
+RETRIEVAL_QUERY = "retrieval.query"
+
+RETRIEVAL_DOCUMENT = "retrieval.document"
+
+
+# LLM
+GEN_AI_MODEL_NAME = "gen_ai.model_name"
+
+GEN_AI_SYSTEM = "gen_ai.system"
+
+GEN_AI_USAGE_INPUT_TOKENS = "gen_ai.usage.input_tokens"
+
+GEN_AI_USAGE_OUTPUT_TOKENS = "gen_ai.usage.output_tokens"
+
+GEN_AI_USAGE_TOTAL_TOKENS = "gen_ai.usage.total_tokens"
+
+GEN_AI_PROMPT_TEMPLATE_TEMPLATE = "gen_ai.prompt_template.template"
+
+GEN_AI_PROMPT_TEMPLATE_VARIABLE = "gen_ai.prompt_template.variable"
+
+GEN_AI_PROMPT = "gen_ai.prompt"
+
+GEN_AI_COMPLETION = "gen_ai.completion"
+
+GEN_AI_RESPONSE_FINISH_REASON = "gen_ai.response.finish_reason"
+
+# Tool
+TOOL_NAME = "tool.name"
+
+TOOL_DESCRIPTION = "tool.description"
+
+TOOL_PARAMETERS = "tool.parameters"
+
+
+class GenAISpanKind(Enum):
+    CHAIN = "CHAIN"
+    RETRIEVER = "RETRIEVER"
+    RERANKER = "RERANKER"
+    LLM = "LLM"
+    EMBEDDING = "EMBEDDING"
+    TOOL = "TOOL"
+    AGENT = "AGENT"
+    TASK = "TASK"

api/core/ops/arize_phoenix_trace/arize_phoenix_trace.py

@@ -0,0 +1,726 @@
+import hashlib
+import json
+import logging
+import os
+from datetime import datetime, timedelta
+from typing import Optional, Union, cast
+
+from openinference.semconv.trace import OpenInferenceSpanKindValues, SpanAttributes
+from opentelemetry import trace
+from opentelemetry.exporter.otlp.proto.grpc.trace_exporter import OTLPSpanExporter as GrpcOTLPSpanExporter
+from opentelemetry.exporter.otlp.proto.http.trace_exporter import OTLPSpanExporter as HttpOTLPSpanExporter
+from opentelemetry.sdk import trace as trace_sdk
+from opentelemetry.sdk.resources import Resource
+from opentelemetry.sdk.trace.export import SimpleSpanProcessor
+from opentelemetry.sdk.trace.id_generator import RandomIdGenerator
+from opentelemetry.trace import SpanContext, TraceFlags, TraceState
+
+from core.ops.base_trace_instance import BaseTraceInstance
+from core.ops.entities.config_entity import ArizeConfig, PhoenixConfig
+from core.ops.entities.trace_entity import (
+    BaseTraceInfo,
+    DatasetRetrievalTraceInfo,
+    GenerateNameTraceInfo,
+    MessageTraceInfo,
+    ModerationTraceInfo,
+    SuggestedQuestionTraceInfo,
+    ToolTraceInfo,
+    TraceTaskName,
+    WorkflowTraceInfo,
+)
+from extensions.ext_database import db
+from models.model import EndUser, MessageFile
+from models.workflow import WorkflowNodeExecutionModel
+
+logger = logging.getLogger(__name__)
+
+
+def setup_tracer(arize_phoenix_config: ArizeConfig | PhoenixConfig) -> tuple[trace_sdk.Tracer, SimpleSpanProcessor]:
+    """Configure OpenTelemetry tracer with OTLP exporter for Arize/Phoenix."""
+    try:
+        # Choose the appropriate exporter based on config type
+        exporter: Union[GrpcOTLPSpanExporter, HttpOTLPSpanExporter]
+        if isinstance(arize_phoenix_config, ArizeConfig):
+            arize_endpoint = f"{arize_phoenix_config.endpoint}/v1"
+            arize_headers = {
+                "api_key": arize_phoenix_config.api_key or "",
+                "space_id": arize_phoenix_config.space_id or "",
+                "authorization": f"Bearer {arize_phoenix_config.api_key or ''}",
+            }
+            exporter = GrpcOTLPSpanExporter(
+                endpoint=arize_endpoint,
+                headers=arize_headers,
+                timeout=30,
+            )
+        else:
+            phoenix_endpoint = f"{arize_phoenix_config.endpoint}/v1/traces"
+            phoenix_headers = {
+                "api_key": arize_phoenix_config.api_key or "",
+                "authorization": f"Bearer {arize_phoenix_config.api_key or ''}",
+            }
+            exporter = HttpOTLPSpanExporter(
+                endpoint=phoenix_endpoint,
+                headers=phoenix_headers,
+                timeout=30,
+            )
+
+        attributes = {
+            "openinference.project.name": arize_phoenix_config.project or "",
+            "model_id": arize_phoenix_config.project or "",
+        }
+        resource = Resource(attributes=attributes)
+        provider = trace_sdk.TracerProvider(resource=resource)
+        processor = SimpleSpanProcessor(
+            exporter,
+        )
+        provider.add_span_processor(processor)
+
+        # Create a named tracer instead of setting the global provider
+        tracer_name = f"arize_phoenix_tracer_{arize_phoenix_config.project}"
+        logger.info(f"[Arize/Phoenix] Created tracer with name: {tracer_name}")
+        return cast(trace_sdk.Tracer, provider.get_tracer(tracer_name)), processor
+    except Exception as e:
+        logger.error(f"[Arize/Phoenix] Failed to setup the tracer: {str(e)}", exc_info=True)
+        raise
+
+
+def datetime_to_nanos(dt: Optional[datetime]) -> int:
+    """Convert datetime to nanoseconds since epoch. If None, use current time."""
+    if dt is None:
+        dt = datetime.now()
+    return int(dt.timestamp() * 1_000_000_000)
+
+
+def uuid_to_trace_id(string: Optional[str]) -> int:
+    """Convert UUID string to a valid trace ID (16-byte integer)."""
+    if string is None:
+        string = ""
+    hash_object = hashlib.sha256(string.encode())
+
+    # Take the first 16 bytes (128 bits) of the hash
+    digest = hash_object.digest()[:16]
+
+    # Convert to integer (128 bits)
+    return int.from_bytes(digest, byteorder="big")
+
+
+class ArizePhoenixDataTrace(BaseTraceInstance):
+    def __init__(
+        self,
+        arize_phoenix_config: ArizeConfig | PhoenixConfig,
+    ):
+        super().__init__(arize_phoenix_config)
+        import logging
+
+        logging.basicConfig()
+        logging.getLogger().setLevel(logging.DEBUG)
+        self.arize_phoenix_config = arize_phoenix_config
+        self.tracer, self.processor = setup_tracer(arize_phoenix_config)
+        self.project = arize_phoenix_config.project
+        self.file_base_url = os.getenv("FILES_URL", "http://127.0.0.1:5001")
+
+    def trace(self, trace_info: BaseTraceInfo):
+        logger.info(f"[Arize/Phoenix] Trace: {trace_info}")
+        try:
+            if isinstance(trace_info, WorkflowTraceInfo):
+                self.workflow_trace(trace_info)
+            if isinstance(trace_info, MessageTraceInfo):
+                self.message_trace(trace_info)
+            if isinstance(trace_info, ModerationTraceInfo):
+                self.moderation_trace(trace_info)
+            if isinstance(trace_info, SuggestedQuestionTraceInfo):
+                self.suggested_question_trace(trace_info)
+            if isinstance(trace_info, DatasetRetrievalTraceInfo):
+                self.dataset_retrieval_trace(trace_info)
+            if isinstance(trace_info, ToolTraceInfo):
+                self.tool_trace(trace_info)
+            if isinstance(trace_info, GenerateNameTraceInfo):
+                self.generate_name_trace(trace_info)
+
+        except Exception as e:
+            logger.error(f"[Arize/Phoenix] Error in the trace: {str(e)}", exc_info=True)
+            raise
+
+    def workflow_trace(self, trace_info: WorkflowTraceInfo):
+        if trace_info.message_data is None:
+            return
+
+        workflow_metadata = {
+            "workflow_id": trace_info.workflow_run_id or "",
+            "message_id": trace_info.message_id or "",
+            "workflow_app_log_id": trace_info.workflow_app_log_id or "",
+            "status": trace_info.workflow_run_status or "",
+            "status_message": trace_info.error or "",
+            "level": "ERROR" if trace_info.error else "DEFAULT",
+            "total_tokens": trace_info.total_tokens or 0,
+        }
+        workflow_metadata.update(trace_info.metadata)
+
+        trace_id = uuid_to_trace_id(trace_info.message_id)
+        span_id = RandomIdGenerator().generate_span_id()
+        context = SpanContext(
+            trace_id=trace_id,
+            span_id=span_id,
+            is_remote=False,
+            trace_flags=TraceFlags(TraceFlags.SAMPLED),
+            trace_state=TraceState(),
+        )
+
+        workflow_span = self.tracer.start_span(
+            name=TraceTaskName.WORKFLOW_TRACE.value,
+            attributes={
+                SpanAttributes.INPUT_VALUE: json.dumps(trace_info.workflow_run_inputs, ensure_ascii=False),
+                SpanAttributes.OUTPUT_VALUE: json.dumps(trace_info.workflow_run_outputs, ensure_ascii=False),
+                SpanAttributes.OPENINFERENCE_SPAN_KIND: OpenInferenceSpanKindValues.CHAIN.value,
+                SpanAttributes.METADATA: json.dumps(workflow_metadata, ensure_ascii=False),
+                SpanAttributes.SESSION_ID: trace_info.conversation_id or "",
+            },
+            start_time=datetime_to_nanos(trace_info.start_time),
+            context=trace.set_span_in_context(trace.NonRecordingSpan(context)),
+        )
+
+        try:
+            # Process workflow nodes
+            for node_execution in self._get_workflow_nodes(trace_info.workflow_run_id):
+                created_at = node_execution.created_at or datetime.now()
+                elapsed_time = node_execution.elapsed_time
+                finished_at = created_at + timedelta(seconds=elapsed_time)
+
+                process_data = json.loads(node_execution.process_data) if node_execution.process_data else {}
+
+                node_metadata = {
+                    "node_id": node_execution.id,
+                    "node_type": node_execution.node_type,
+                    "node_status": node_execution.status,
+                    "tenant_id": node_execution.tenant_id,
+                    "app_id": node_execution.app_id,
+                    "app_name": node_execution.title,
+                    "status": node_execution.status,
+                    "level": "ERROR" if node_execution.status != "succeeded" else "DEFAULT",
+                }
+
+                if node_execution.execution_metadata:
+                    node_metadata.update(json.loads(node_execution.execution_metadata))
+
+                # Determine the correct span kind based on node type
+                span_kind = OpenInferenceSpanKindValues.CHAIN.value
+                if node_execution.node_type == "llm":
+                    span_kind = OpenInferenceSpanKindValues.LLM.value
+                    provider = process_data.get("model_provider")
+                    model = process_data.get("model_name")
+                    if provider:
+                        node_metadata["ls_provider"] = provider
+                    if model:
+                        node_metadata["ls_model_name"] = model
+
+                    outputs = json.loads(node_execution.outputs).get("usage", {})
+                    usage_data = process_data.get("usage", {}) if "usage" in process_data else outputs.get("usage", {})
+                    if usage_data:
+                        node_metadata["total_tokens"] = usage_data.get("total_tokens", 0)
+                        node_metadata["prompt_tokens"] = usage_data.get("prompt_tokens", 0)
+                        node_metadata["completion_tokens"] = usage_data.get("completion_tokens", 0)
+                elif node_execution.node_type == "dataset_retrieval":
+                    span_kind = OpenInferenceSpanKindValues.RETRIEVER.value
+                elif node_execution.node_type == "tool":
+                    span_kind = OpenInferenceSpanKindValues.TOOL.value
+                else:
+                    span_kind = OpenInferenceSpanKindValues.CHAIN.value
+
+                node_span = self.tracer.start_span(
+                    name=node_execution.node_type,
+                    attributes={
+                        SpanAttributes.INPUT_VALUE: node_execution.inputs or "{}",
+                        SpanAttributes.OUTPUT_VALUE: node_execution.outputs or "{}",
+                        SpanAttributes.OPENINFERENCE_SPAN_KIND: span_kind,
+                        SpanAttributes.METADATA: json.dumps(node_metadata, ensure_ascii=False),
+                        SpanAttributes.SESSION_ID: trace_info.conversation_id or "",
+                    },
+                    start_time=datetime_to_nanos(created_at),
+                )
+
+                try:
+                    if node_execution.node_type == "llm":
+                        provider = process_data.get("model_provider")
+                        model = process_data.get("model_name")
+                        if provider:
+                            node_span.set_attribute(SpanAttributes.LLM_PROVIDER, provider)
+                        if model:
+                            node_span.set_attribute(SpanAttributes.LLM_MODEL_NAME, model)
+
+                        outputs = json.loads(node_execution.outputs).get("usage", {})
+                        usage_data = (
+                            process_data.get("usage", {}) if "usage" in process_data else outputs.get("usage", {})
+                        )
+                        if usage_data:
+                            node_span.set_attribute(
+                                SpanAttributes.LLM_TOKEN_COUNT_TOTAL, usage_data.get("total_tokens", 0)
+                            )
+                            node_span.set_attribute(
+                                SpanAttributes.LLM_TOKEN_COUNT_PROMPT, usage_data.get("prompt_tokens", 0)
+                            )
+                            node_span.set_attribute(
+                                SpanAttributes.LLM_TOKEN_COUNT_COMPLETION, usage_data.get("completion_tokens", 0)
+                            )
+                finally:
+                    node_span.end(end_time=datetime_to_nanos(finished_at))
+        finally:
+            workflow_span.end(end_time=datetime_to_nanos(trace_info.end_time))
+
+    def message_trace(self, trace_info: MessageTraceInfo):
+        if trace_info.message_data is None:
+            return
+
+        file_list = cast(list[str], trace_info.file_list) or []
+        message_file_data: Optional[MessageFile] = trace_info.message_file_data
+
+        if message_file_data is not None:
+            file_url = f"{self.file_base_url}/{message_file_data.url}" if message_file_data else ""
+            file_list.append(file_url)
+
+        message_metadata = {
+            "message_id": trace_info.message_id or "",
+            "conversation_mode": str(trace_info.conversation_mode or ""),
+            "user_id": trace_info.message_data.from_account_id or "",
+            "file_list": json.dumps(file_list),
+            "status": trace_info.message_data.status or "",
+            "status_message": trace_info.error or "",
+            "level": "ERROR" if trace_info.error else "DEFAULT",
+            "total_tokens": trace_info.total_tokens or 0,
+            "prompt_tokens": trace_info.message_tokens or 0,
+            "completion_tokens": trace_info.answer_tokens or 0,
+            "ls_provider": trace_info.message_data.model_provider or "",
+            "ls_model_name": trace_info.message_data.model_id or "",
+        }
+        message_metadata.update(trace_info.metadata)
+
+        # Add end user data if available
+        if trace_info.message_data.from_end_user_id:
+            end_user_data: Optional[EndUser] = (
+                db.session.query(EndUser).filter(EndUser.id == trace_info.message_data.from_end_user_id).first()
+            )
+            if end_user_data is not None:
+                message_metadata["end_user_id"] = end_user_data.session_id
+
+        attributes = {
+            SpanAttributes.INPUT_VALUE: trace_info.message_data.query,
+            SpanAttributes.OUTPUT_VALUE: trace_info.message_data.answer,
+            SpanAttributes.OPENINFERENCE_SPAN_KIND: OpenInferenceSpanKindValues.CHAIN.value,
+            SpanAttributes.METADATA: json.dumps(message_metadata, ensure_ascii=False),
+            SpanAttributes.SESSION_ID: trace_info.message_data.conversation_id,
+        }
+
+        trace_id = uuid_to_trace_id(trace_info.message_id)
+        message_span_id = RandomIdGenerator().generate_span_id()
+        span_context = SpanContext(
+            trace_id=trace_id,
+            span_id=message_span_id,
+            is_remote=False,
+            trace_flags=TraceFlags(TraceFlags.SAMPLED),
+            trace_state=TraceState(),
+        )
+
+        message_span = self.tracer.start_span(
+            name=TraceTaskName.MESSAGE_TRACE.value,
+            attributes=attributes,
+            start_time=datetime_to_nanos(trace_info.start_time),
+            context=trace.set_span_in_context(trace.NonRecordingSpan(span_context)),
+        )
+
+        try:
+            if trace_info.error:
+                message_span.add_event(
+                    "exception",
+                    attributes={
+                        "exception.message": trace_info.error,
+                        "exception.type": "Error",
+                        "exception.stacktrace": trace_info.error,
+                    },
+                )
+
+            # Convert outputs to string based on type
+            if isinstance(trace_info.outputs, dict | list):
+                outputs_str = json.dumps(trace_info.outputs, ensure_ascii=False)
+            elif isinstance(trace_info.outputs, str):
+                outputs_str = trace_info.outputs
+            else:
+                outputs_str = str(trace_info.outputs)
+
+            llm_attributes = {
+                SpanAttributes.OPENINFERENCE_SPAN_KIND: OpenInferenceSpanKindValues.LLM.value,
+                SpanAttributes.INPUT_VALUE: json.dumps(trace_info.inputs, ensure_ascii=False),
+                SpanAttributes.OUTPUT_VALUE: outputs_str,
+                SpanAttributes.METADATA: json.dumps(message_metadata, ensure_ascii=False),
+                SpanAttributes.SESSION_ID: trace_info.message_data.conversation_id,
+            }
+
+            if isinstance(trace_info.inputs, list):
+                for i, msg in enumerate(trace_info.inputs):
+                    if isinstance(msg, dict):
+                        llm_attributes[f"{SpanAttributes.LLM_INPUT_MESSAGES}.{i}.message.content"] = msg.get("text", "")
+                        llm_attributes[f"{SpanAttributes.LLM_INPUT_MESSAGES}.{i}.message.role"] = msg.get(
+                            "role", "user"
+                        )
+                        # todo: handle assistant and tool role messages, as they don't always
+                        # have a text field, but may have a tool_calls field instead
+                        # e.g. 'tool_calls': [{'id': '98af3a29-b066-45a5-b4b1-46c74ddafc58',
+                        # 'type': 'function', 'function': {'name': 'current_time', 'arguments': '{}'}}]}
+            elif isinstance(trace_info.inputs, dict):
+                llm_attributes[f"{SpanAttributes.LLM_INPUT_MESSAGES}.0.message.content"] = json.dumps(trace_info.inputs)
+                llm_attributes[f"{SpanAttributes.LLM_INPUT_MESSAGES}.0.message.role"] = "user"
+            elif isinstance(trace_info.inputs, str):
+                llm_attributes[f"{SpanAttributes.LLM_INPUT_MESSAGES}.0.message.content"] = trace_info.inputs
+                llm_attributes[f"{SpanAttributes.LLM_INPUT_MESSAGES}.0.message.role"] = "user"
+
+            if trace_info.total_tokens is not None and trace_info.total_tokens > 0:
+                llm_attributes[SpanAttributes.LLM_TOKEN_COUNT_TOTAL] = trace_info.total_tokens
+            if trace_info.message_tokens is not None and trace_info.message_tokens > 0:
+                llm_attributes[SpanAttributes.LLM_TOKEN_COUNT_PROMPT] = trace_info.message_tokens
+            if trace_info.answer_tokens is not None and trace_info.answer_tokens > 0:
+                llm_attributes[SpanAttributes.LLM_TOKEN_COUNT_COMPLETION] = trace_info.answer_tokens
+
+            if trace_info.message_data.model_id is not None:
+                llm_attributes[SpanAttributes.LLM_MODEL_NAME] = trace_info.message_data.model_id
+            if trace_info.message_data.model_provider is not None:
+                llm_attributes[SpanAttributes.LLM_PROVIDER] = trace_info.message_data.model_provider
+
+            if trace_info.message_data and trace_info.message_data.message_metadata:
+                metadata_dict = json.loads(trace_info.message_data.message_metadata)
+                if model_params := metadata_dict.get("model_parameters"):
+                    llm_attributes[SpanAttributes.LLM_INVOCATION_PARAMETERS] = json.dumps(model_params)
+
+            llm_span = self.tracer.start_span(
+                name="llm",
+                attributes=llm_attributes,
+                start_time=datetime_to_nanos(trace_info.start_time),
+                context=trace.set_span_in_context(trace.NonRecordingSpan(span_context)),
+            )
+
+            try:
+                if trace_info.error:
+                    llm_span.add_event(
+                        "exception",
+                        attributes={
+                            "exception.message": trace_info.error,
+                            "exception.type": "Error",
+                            "exception.stacktrace": trace_info.error,
+                        },
+                    )
+            finally:
+                llm_span.end(end_time=datetime_to_nanos(trace_info.end_time))
+        finally:
+            message_span.end(end_time=datetime_to_nanos(trace_info.end_time))
+
+    def moderation_trace(self, trace_info: ModerationTraceInfo):
+        if trace_info.message_data is None:
+            return
+
+        metadata = {
+            "message_id": trace_info.message_id,
+            "tool_name": "moderation",
+            "status": trace_info.message_data.status,
+            "status_message": trace_info.message_data.error or "",
+            "level": "ERROR" if trace_info.message_data.error else "DEFAULT",
+        }
+        metadata.update(trace_info.metadata)
+
+        trace_id = uuid_to_trace_id(trace_info.message_id)
+        span_id = RandomIdGenerator().generate_span_id()
+        context = SpanContext(
+            trace_id=trace_id,
+            span_id=span_id,
+            is_remote=False,
+            trace_flags=TraceFlags(TraceFlags.SAMPLED),
+            trace_state=TraceState(),
+        )
+
+        span = self.tracer.start_span(
+            name=TraceTaskName.MODERATION_TRACE.value,
+            attributes={
+                SpanAttributes.INPUT_VALUE: json.dumps(trace_info.inputs, ensure_ascii=False),
+                SpanAttributes.OUTPUT_VALUE: json.dumps(
+                    {
+                        "action": trace_info.action,
+                        "flagged": trace_info.flagged,
+                        "preset_response": trace_info.preset_response,
+                        "inputs": trace_info.inputs,
+                    },
+                    ensure_ascii=False,
+                ),
+                SpanAttributes.OPENINFERENCE_SPAN_KIND: OpenInferenceSpanKindValues.CHAIN.value,
+                SpanAttributes.METADATA: json.dumps(metadata, ensure_ascii=False),
+            },
+            start_time=datetime_to_nanos(trace_info.start_time),
+            context=trace.set_span_in_context(trace.NonRecordingSpan(context)),
+        )
+
+        try:
+            if trace_info.message_data.error:
+                span.add_event(
+                    "exception",
+                    attributes={
+                        "exception.message": trace_info.message_data.error,
+                        "exception.type": "Error",
+                        "exception.stacktrace": trace_info.message_data.error,
+                    },
+                )
+        finally:
+            span.end(end_time=datetime_to_nanos(trace_info.end_time))
+
+    def suggested_question_trace(self, trace_info: SuggestedQuestionTraceInfo):
+        if trace_info.message_data is None:
+            return
+
+        start_time = trace_info.start_time or trace_info.message_data.created_at
+        end_time = trace_info.end_time or trace_info.message_data.updated_at
+
+        metadata = {
+            "message_id": trace_info.message_id,
+            "tool_name": "suggested_question",
+            "status": trace_info.status,
+            "status_message": trace_info.error or "",
+            "level": "ERROR" if trace_info.error else "DEFAULT",
+            "total_tokens": trace_info.total_tokens,
+            "ls_provider": trace_info.model_provider or "",
+            "ls_model_name": trace_info.model_id or "",
+        }
+        metadata.update(trace_info.metadata)
+
+        trace_id = uuid_to_trace_id(trace_info.message_id)
+        span_id = RandomIdGenerator().generate_span_id()
+        context = SpanContext(
+            trace_id=trace_id,
+            span_id=span_id,
+            is_remote=False,
+            trace_flags=TraceFlags(TraceFlags.SAMPLED),
+            trace_state=TraceState(),
+        )
+
+        span = self.tracer.start_span(
+            name=TraceTaskName.SUGGESTED_QUESTION_TRACE.value,
+            attributes={
+                SpanAttributes.INPUT_VALUE: json.dumps(trace_info.inputs, ensure_ascii=False),
+                SpanAttributes.OUTPUT_VALUE: json.dumps(trace_info.suggested_question, ensure_ascii=False),
+                SpanAttributes.OPENINFERENCE_SPAN_KIND: OpenInferenceSpanKindValues.CHAIN.value,
+                SpanAttributes.METADATA: json.dumps(metadata, ensure_ascii=False),
+            },
+            start_time=datetime_to_nanos(start_time),
+            context=trace.set_span_in_context(trace.NonRecordingSpan(context)),
+        )
+
+        try:
+            if trace_info.error:
+                span.add_event(
+                    "exception",
+                    attributes={
+                        "exception.message": trace_info.error,
+                        "exception.type": "Error",
+                        "exception.stacktrace": trace_info.error,
+                    },
+                )
+        finally:
+            span.end(end_time=datetime_to_nanos(end_time))
+
+    def dataset_retrieval_trace(self, trace_info: DatasetRetrievalTraceInfo):
+        if trace_info.message_data is None:
+            return
+
+        start_time = trace_info.start_time or trace_info.message_data.created_at
+        end_time = trace_info.end_time or trace_info.message_data.updated_at
+
+        metadata = {
+            "message_id": trace_info.message_id,
+            "tool_name": "dataset_retrieval",
+            "status": trace_info.message_data.status,
+            "status_message": trace_info.message_data.error or "",
+            "level": "ERROR" if trace_info.message_data.error else "DEFAULT",
+            "ls_provider": trace_info.message_data.model_provider or "",
+            "ls_model_name": trace_info.message_data.model_id or "",
+        }
+        metadata.update(trace_info.metadata)
+
+        trace_id = uuid_to_trace_id(trace_info.message_id)
+        span_id = RandomIdGenerator().generate_span_id()
+        context = SpanContext(
+            trace_id=trace_id,
+            span_id=span_id,
+            is_remote=False,
+            trace_flags=TraceFlags(TraceFlags.SAMPLED),
+            trace_state=TraceState(),
+        )
+
+        span = self.tracer.start_span(
+            name=TraceTaskName.DATASET_RETRIEVAL_TRACE.value,
+            attributes={
+                SpanAttributes.INPUT_VALUE: json.dumps(trace_info.inputs, ensure_ascii=False),
+                SpanAttributes.OUTPUT_VALUE: json.dumps({"documents": trace_info.documents}, ensure_ascii=False),
+                SpanAttributes.OPENINFERENCE_SPAN_KIND: OpenInferenceSpanKindValues.RETRIEVER.value,
+                SpanAttributes.METADATA: json.dumps(metadata, ensure_ascii=False),
+                "start_time": start_time.isoformat() if start_time else "",
+                "end_time": end_time.isoformat() if end_time else "",
+            },
+            start_time=datetime_to_nanos(start_time),
+            context=trace.set_span_in_context(trace.NonRecordingSpan(context)),
+        )
+
+        try:
+            if trace_info.message_data.error:
+                span.add_event(
+                    "exception",
+                    attributes={
+                        "exception.message": trace_info.message_data.error,
+                        "exception.type": "Error",
+                        "exception.stacktrace": trace_info.message_data.error,
+                    },
+                )
+        finally:
+            span.end(end_time=datetime_to_nanos(end_time))
+
+    def tool_trace(self, trace_info: ToolTraceInfo):
+        if trace_info.message_data is None:
+            logger.warning("[Arize/Phoenix] Message data is None, skipping tool trace.")
+            return
+
+        metadata = {
+            "message_id": trace_info.message_id,
+            "tool_config": json.dumps(trace_info.tool_config, ensure_ascii=False),
+        }
+
+        trace_id = uuid_to_trace_id(trace_info.message_id)
+        tool_span_id = RandomIdGenerator().generate_span_id()
+        logger.info(f"[Arize/Phoenix] Creating tool trace with trace_id: {trace_id}, span_id: {tool_span_id}")
+
+        # Create span context with the same trace_id as the parent
+        # todo: Create with the appropriate parent span context, so that the tool span is
+        # a child of the appropriate span (e.g. message span)
+        span_context = SpanContext(
+            trace_id=trace_id,
+            span_id=tool_span_id,
+            is_remote=False,
+            trace_flags=TraceFlags(TraceFlags.SAMPLED),
+            trace_state=TraceState(),
+        )
+
+        tool_params_str = (
+            json.dumps(trace_info.tool_parameters, ensure_ascii=False)
+            if isinstance(trace_info.tool_parameters, dict)
+            else str(trace_info.tool_parameters)
+        )
+
+        span = self.tracer.start_span(
+            name=trace_info.tool_name,
+            attributes={
+                SpanAttributes.INPUT_VALUE: json.dumps(trace_info.tool_inputs, ensure_ascii=False),
+                SpanAttributes.OUTPUT_VALUE: trace_info.tool_outputs,
+                SpanAttributes.OPENINFERENCE_SPAN_KIND: OpenInferenceSpanKindValues.TOOL.value,
+                SpanAttributes.METADATA: json.dumps(metadata, ensure_ascii=False),
+                SpanAttributes.TOOL_NAME: trace_info.tool_name,
+                SpanAttributes.TOOL_PARAMETERS: tool_params_str,
+            },
+            start_time=datetime_to_nanos(trace_info.start_time),
+            context=trace.set_span_in_context(trace.NonRecordingSpan(span_context)),
+        )
+
+        try:
+            if trace_info.error:
+                span.add_event(
+                    "exception",
+                    attributes={
+                        "exception.message": trace_info.error,
+                        "exception.type": "Error",
+                        "exception.stacktrace": trace_info.error,
+                    },
+                )
+        finally:
+            span.end(end_time=datetime_to_nanos(trace_info.end_time))
+
+    def generate_name_trace(self, trace_info: GenerateNameTraceInfo):
+        if trace_info.message_data is None:
+            return
+
+        metadata = {
+            "project_name": self.project,
+            "message_id": trace_info.message_id,
+            "status": trace_info.message_data.status,
+            "status_message": trace_info.message_data.error or "",
+            "level": "ERROR" if trace_info.message_data.error else "DEFAULT",
+        }
+        metadata.update(trace_info.metadata)
+
+        trace_id = uuid_to_trace_id(trace_info.message_id)
+        span_id = RandomIdGenerator().generate_span_id()
+        context = SpanContext(
+            trace_id=trace_id,
+            span_id=span_id,
+            is_remote=False,
+            trace_flags=TraceFlags(TraceFlags.SAMPLED),
+            trace_state=TraceState(),
+        )
+
+        span = self.tracer.start_span(
+            name=TraceTaskName.GENERATE_NAME_TRACE.value,
+            attributes={
+                SpanAttributes.INPUT_VALUE: json.dumps(trace_info.inputs, ensure_ascii=False),
+                SpanAttributes.OUTPUT_VALUE: json.dumps(trace_info.outputs, ensure_ascii=False),
+                SpanAttributes.OPENINFERENCE_SPAN_KIND: OpenInferenceSpanKindValues.CHAIN.value,
+                SpanAttributes.METADATA: json.dumps(metadata, ensure_ascii=False),
+                SpanAttributes.SESSION_ID: trace_info.message_data.conversation_id,
+                "start_time": trace_info.start_time.isoformat() if trace_info.start_time else "",
+                "end_time": trace_info.end_time.isoformat() if trace_info.end_time else "",
+            },
+            start_time=datetime_to_nanos(trace_info.start_time),
+            context=trace.set_span_in_context(trace.NonRecordingSpan(context)),
+        )
+
+        try:
+            if trace_info.message_data.error:
+                span.add_event(
+                    "exception",
+                    attributes={
+                        "exception.message": trace_info.message_data.error,
+                        "exception.type": "Error",
+                        "exception.stacktrace": trace_info.message_data.error,
+                    },
+                )
+        finally:
+            span.end(end_time=datetime_to_nanos(trace_info.end_time))
+
+    def api_check(self):
+        try:
+            with self.tracer.start_span("api_check") as span:
+                span.set_attribute("test", "true")
+            return True
+        except Exception as e:
+            logger.info(f"[Arize/Phoenix] API check failed: {str(e)}", exc_info=True)
+            raise ValueError(f"[Arize/Phoenix] API check failed: {str(e)}")
+
+    def get_project_url(self):
+        try:
+            if self.arize_phoenix_config.endpoint == "https://otlp.arize.com":
+                return "https://app.arize.com/"
+            else:
+                return f"{self.arize_phoenix_config.endpoint}/projects/"
+        except Exception as e:
+            logger.info(f"[Arize/Phoenix] Get run url failed: {str(e)}", exc_info=True)
+            raise ValueError(f"[Arize/Phoenix] Get run url failed: {str(e)}")
+
+    def _get_workflow_nodes(self, workflow_run_id: str):
+        """Helper method to get workflow nodes"""
+        workflow_nodes = (
+            db.session.query(
+                WorkflowNodeExecutionModel.id,
+                WorkflowNodeExecutionModel.tenant_id,
+                WorkflowNodeExecutionModel.app_id,
+                WorkflowNodeExecutionModel.title,
+                WorkflowNodeExecutionModel.node_type,
+                WorkflowNodeExecutionModel.status,
+                WorkflowNodeExecutionModel.inputs,
+                WorkflowNodeExecutionModel.outputs,
+                WorkflowNodeExecutionModel.created_at,
+                WorkflowNodeExecutionModel.elapsed_time,
+                WorkflowNodeExecutionModel.process_data,
+                WorkflowNodeExecutionModel.execution_metadata,
+            )
+            .filter(WorkflowNodeExecutionModel.workflow_run_id == workflow_run_id)
+            .all()
+        )
+        return workflow_nodes

api/core/ops/entities/config_entity.py

@@ -2,20 +2,92 @@ from enum import StrEnum
 
 from pydantic import BaseModel, ValidationInfo, field_validator
 
+from core.ops.utils import validate_project_name, validate_url, validate_url_with_path
+
 
 class TracingProviderEnum(StrEnum):
+    ARIZE = "arize"
+    PHOENIX = "phoenix"
     LANGFUSE = "langfuse"
     LANGSMITH = "langsmith"
     OPIK = "opik"
     WEAVE = "weave"
+    ALIYUN = "aliyun"
 
 
 class BaseTracingConfig(BaseModel):
     """
-    Base model class for tracing
+    Base model class for tracing configurations
     """
 
-    ...
+    @classmethod
+    def validate_endpoint_url(cls, v: str, default_url: str) -> str:
+        """
+        Common endpoint URL validation logic
+
+        Args:
+            v: URL value to validate
+            default_url: Default URL to use if input is None or empty
+
+        Returns:
+            Validated and normalized URL
+        """
+        return validate_url(v, default_url)
+
+    @classmethod
+    def validate_project_field(cls, v: str, default_name: str) -> str:
+        """
+        Common project name validation logic
+
+        Args:
+            v: Project name to validate
+            default_name: Default name to use if input is None or empty
+
+        Returns:
+            Validated project name
+        """
+        return validate_project_name(v, default_name)
+
+
+class ArizeConfig(BaseTracingConfig):
+    """
+    Model class for Arize tracing config.
+    """
+
+    api_key: str | None = None
+    space_id: str | None = None
+    project: str | None = None
+    endpoint: str = "https://otlp.arize.com"
+
+    @field_validator("project")
+    @classmethod
+    def project_validator(cls, v, info: ValidationInfo):
+        return cls.validate_project_field(v, "default")
+
+    @field_validator("endpoint")
+    @classmethod
+    def endpoint_validator(cls, v, info: ValidationInfo):
+        return cls.validate_endpoint_url(v, "https://otlp.arize.com")
+
+
+class PhoenixConfig(BaseTracingConfig):
+    """
+    Model class for Phoenix tracing config.
+    """
+
+    api_key: str | None = None
+    project: str | None = None
+    endpoint: str = "https://app.phoenix.arize.com"
+
+    @field_validator("project")
+    @classmethod
+    def project_validator(cls, v, info: ValidationInfo):
+        return cls.validate_project_field(v, "default")
+
+    @field_validator("endpoint")
+    @classmethod
+    def endpoint_validator(cls, v, info: ValidationInfo):
+        return cls.validate_endpoint_url(v, "https://app.phoenix.arize.com")
 
 
 class LangfuseConfig(BaseTracingConfig):
@@ -29,13 +101,8 @@ class LangfuseConfig(BaseTracingConfig):
 
     @field_validator("host")
     @classmethod
-    def set_value(cls, v, info: ValidationInfo):
-        if v is None or v == "":
-            v = "https://api.langfuse.com"
-        if not v.startswith("https://") and not v.startswith("http://"):
-            raise ValueError("host must start with https:// or http://")
-
-        return v
+    def host_validator(cls, v, info: ValidationInfo):
+        return cls.validate_endpoint_url(v, "https://api.langfuse.com")
 
 
 class LangSmithConfig(BaseTracingConfig):
@@ -49,13 +116,9 @@ class LangSmithConfig(BaseTracingConfig):
 
     @field_validator("endpoint")
     @classmethod
-    def set_value(cls, v, info: ValidationInfo):
-        if v is None or v == "":
-            v = "https://api.smith.langchain.com"
-        if not v.startswith("https://"):
-            raise ValueError("endpoint must start with https://")
-
-        return v
+    def endpoint_validator(cls, v, info: ValidationInfo):
+        # LangSmith only allows HTTPS
+        return validate_url(v, "https://api.smith.langchain.com", allowed_schemes=("https",))
 
 
 class OpikConfig(BaseTracingConfig):
@@ -71,22 +134,12 @@ class OpikConfig(BaseTracingConfig):
     @field_validator("project")
     @classmethod
     def project_validator(cls, v, info: ValidationInfo):
-        if v is None or v == "":
-            v = "Default Project"
-
-        return v
+        return cls.validate_project_field(v, "Default Project")
 
     @field_validator("url")
     @classmethod
     def url_validator(cls, v, info: ValidationInfo):
-        if v is None or v == "":
-            v = "https://www.comet.com/opik/api/"
-        if not v.startswith(("https://", "http://")):
-            raise ValueError("url must start with https:// or http://")
-        if not v.endswith("/api/"):
-            raise ValueError("url should ends with /api/")
-
-        return v
+        return validate_url_with_path(v, "https://www.comet.com/opik/api/", required_suffix="/api/")
 
 
 class WeaveConfig(BaseTracingConfig):
@@ -102,22 +155,44 @@ class WeaveConfig(BaseTracingConfig):
 
     @field_validator("endpoint")
     @classmethod
-    def set_value(cls, v, info: ValidationInfo):
-        if v is None or v == "":
-            v = "https://trace.wandb.ai"
-        if not v.startswith("https://"):
-            raise ValueError("endpoint must start with https://")
-
-        return v
+    def endpoint_validator(cls, v, info: ValidationInfo):
+        # Weave only allows HTTPS for endpoint
+        return validate_url(v, "https://trace.wandb.ai", allowed_schemes=("https",))
 
     @field_validator("host")
     @classmethod
-    def validate_host(cls, v, info: ValidationInfo):
-        if v is not None and v != "":
-            if not v.startswith(("https://", "http://")):
-                raise ValueError("host must start with https:// or http://")
+    def host_validator(cls, v, info: ValidationInfo):
+        if v is not None and v.strip() != "":
+            return validate_url(v, v, allowed_schemes=("https", "http"))
         return v
 
 
+class AliyunConfig(BaseTracingConfig):
+    """
+    Model class for Aliyun tracing config.
+    """
+
+    app_name: str = "dify_app"
+    license_key: str
+    endpoint: str
+
+    @field_validator("app_name")
+    @classmethod
+    def app_name_validator(cls, v, info: ValidationInfo):
+        return cls.validate_project_field(v, "dify_app")
+
+    @field_validator("license_key")
+    @classmethod
+    def license_key_validator(cls, v, info: ValidationInfo):
+        if not v or v.strip() == "":
+            raise ValueError("License key cannot be empty")
+        return v
+
+    @field_validator("endpoint")
+    @classmethod
+    def endpoint_validator(cls, v, info: ValidationInfo):
+        return cls.validate_endpoint_url(v, "https://tracing-analysis-dc-hz.aliyuncs.com")
+
+
 OPS_FILE_PATH = "ops_trace/"
 OPS_TRACE_FAILED_KEY = "FAILED_OPS_TRACE"

api/core/ops/langfuse_trace/langfuse_trace.py

@@ -28,10 +28,11 @@ from core.ops.langfuse_trace.entities.langfuse_trace_entity import (
     UnitEnum,
 )
 from core.ops.utils import filter_none_values
-from core.repositories import SQLAlchemyWorkflowNodeExecutionRepository
+from core.repositories import DifyCoreRepositoryFactory
 from core.workflow.nodes.enums import NodeType
 from extensions.ext_database import db
 from models import EndUser, WorkflowNodeExecutionTriggeredFrom
+from models.enums import MessageStatus
 
 logger = logging.getLogger(__name__)
 
@@ -122,10 +123,10 @@ class LangFuseDataTrace(BaseTraceInstance):
 
         service_account = self.get_service_account_with_tenant(app_id)
 
-        workflow_node_execution_repository = SQLAlchemyWorkflowNodeExecutionRepository(
+        workflow_node_execution_repository = DifyCoreRepositoryFactory.create_workflow_node_execution_repository(
             session_factory=session_factory,
             user=service_account,
-            app_id=trace_info.metadata.get("app_id"),
+            app_id=app_id,
             triggered_from=WorkflowNodeExecutionTriggeredFrom.WORKFLOW_RUN,
         )
 
@@ -180,12 +181,9 @@ class LangFuseDataTrace(BaseTraceInstance):
                 prompt_tokens = 0
                 completion_tokens = 0
                 try:
-                    if outputs.get("usage"):
-                        prompt_tokens = outputs.get("usage", {}).get("prompt_tokens", 0)
-                        completion_tokens = outputs.get("usage", {}).get("completion_tokens", 0)
-                    else:
-                        prompt_tokens = process_data.get("usage", {}).get("prompt_tokens", 0)
-                        completion_tokens = process_data.get("usage", {}).get("completion_tokens", 0)
+                    usage_data = process_data.get("usage", {}) if "usage" in process_data else outputs.get("usage", {})
+                    prompt_tokens = usage_data.get("prompt_tokens", 0)
+                    completion_tokens = usage_data.get("completion_tokens", 0)
                 except Exception:
                     logger.error("Failed to extract usage", exc_info=True)
 
@@ -293,7 +291,7 @@ class LangFuseDataTrace(BaseTraceInstance):
             input=trace_info.inputs,
             output=message_data.answer,
             metadata=metadata,
-            level=(LevelEnum.DEFAULT if message_data.status != "error" else LevelEnum.ERROR),
+            level=(LevelEnum.DEFAULT if message_data.status != MessageStatus.ERROR else LevelEnum.ERROR),
             status_message=message_data.error or "",
             usage=generation_usage,
         )
@@ -339,7 +337,7 @@ class LangFuseDataTrace(BaseTraceInstance):
             start_time=trace_info.start_time,
             end_time=trace_info.end_time,
             metadata=trace_info.metadata,
-            level=(LevelEnum.DEFAULT if message_data.status != "error" else LevelEnum.ERROR),
+            level=(LevelEnum.DEFAULT if message_data.status != MessageStatus.ERROR else LevelEnum.ERROR),
             status_message=message_data.error or "",
             usage=generation_usage,
         )

api/core/ops/langsmith_trace/langsmith_trace.py

@@ -27,7 +27,7 @@ from core.ops.langsmith_trace.entities.langsmith_trace_entity import (
     LangSmithRunUpdateModel,
 )
 from core.ops.utils import filter_none_values, generate_dotted_order
-from core.repositories import SQLAlchemyWorkflowNodeExecutionRepository
+from core.repositories import DifyCoreRepositoryFactory
 from core.workflow.entities.workflow_node_execution import WorkflowNodeExecutionMetadataKey
 from core.workflow.nodes.enums import NodeType
 from extensions.ext_database import db
@@ -145,10 +145,10 @@ class LangSmithDataTrace(BaseTraceInstance):
 
         service_account = self.get_service_account_with_tenant(app_id)
 
-        workflow_node_execution_repository = SQLAlchemyWorkflowNodeExecutionRepository(
+        workflow_node_execution_repository = DifyCoreRepositoryFactory.create_workflow_node_execution_repository(
             session_factory=session_factory,
             user=service_account,
-            app_id=trace_info.metadata.get("app_id"),
+            app_id=app_id,
             triggered_from=WorkflowNodeExecutionTriggeredFrom.WORKFLOW_RUN,
         )
 
@@ -206,12 +206,9 @@ class LangSmithDataTrace(BaseTraceInstance):
             prompt_tokens = 0
             completion_tokens = 0
             try:
-                if outputs.get("usage"):
-                    prompt_tokens = outputs.get("usage", {}).get("prompt_tokens", 0)
-                    completion_tokens = outputs.get("usage", {}).get("completion_tokens", 0)
-                else:
-                    prompt_tokens = process_data.get("usage", {}).get("prompt_tokens", 0)
-                    completion_tokens = process_data.get("usage", {}).get("completion_tokens", 0)
+                usage_data = process_data.get("usage", {}) if "usage" in process_data else outputs.get("usage", {})
+                prompt_tokens = usage_data.get("prompt_tokens", 0)
+                completion_tokens = usage_data.get("completion_tokens", 0)
             except Exception:
                 logger.error("Failed to extract usage", exc_info=True)
 

api/core/ops/opik_trace/opik_trace.py

@@ -21,7 +21,7 @@ from core.ops.entities.trace_entity import (
     TraceTaskName,
     WorkflowTraceInfo,
 )
-from core.repositories import SQLAlchemyWorkflowNodeExecutionRepository
+from core.repositories import DifyCoreRepositoryFactory
 from core.workflow.entities.workflow_node_execution import WorkflowNodeExecutionMetadataKey
 from core.workflow.nodes.enums import NodeType
 from extensions.ext_database import db
@@ -160,10 +160,10 @@ class OpikDataTrace(BaseTraceInstance):
 
         service_account = self.get_service_account_with_tenant(app_id)
 
-        workflow_node_execution_repository = SQLAlchemyWorkflowNodeExecutionRepository(
+        workflow_node_execution_repository = DifyCoreRepositoryFactory.create_workflow_node_execution_repository(
             session_factory=session_factory,
             user=service_account,
-            app_id=trace_info.metadata.get("app_id"),
+            app_id=app_id,
             triggered_from=WorkflowNodeExecutionTriggeredFrom.WORKFLOW_RUN,
         )
 
@@ -222,10 +222,10 @@ class OpikDataTrace(BaseTraceInstance):
                 )
 
                 try:
-                    if outputs.get("usage"):
-                        total_tokens = outputs["usage"].get("total_tokens", 0)
-                        prompt_tokens = outputs["usage"].get("prompt_tokens", 0)
-                        completion_tokens = outputs["usage"].get("completion_tokens", 0)
+                    usage_data = process_data.get("usage", {}) if "usage" in process_data else outputs.get("usage", {})
+                    total_tokens = usage_data.get("total_tokens", 0)
+                    prompt_tokens = usage_data.get("prompt_tokens", 0)
+                    completion_tokens = usage_data.get("completion_tokens", 0)
                 except Exception:
                     logger.error("Failed to extract usage", exc_info=True)
 
@@ -241,7 +241,7 @@ class OpikDataTrace(BaseTraceInstance):
                 "trace_id": opik_trace_id,
                 "id": prepare_opik_uuid(created_at, node_execution_id),
                 "parent_span_id": prepare_opik_uuid(trace_info.start_time, parent_span_id),
-                "name": node_type,
+                "name": node_name,
                 "type": run_type,
                 "start_time": created_at,
                 "end_time": finished_at,

api/core/ops/ops_trace_manager.py

@@ -84,6 +84,36 @@ class OpsTraceProviderConfigMap(dict[str, dict[str, Any]]):
                     "other_keys": ["project", "entity", "endpoint", "host"],
                     "trace_instance": WeaveDataTrace,
                 }
+            case TracingProviderEnum.ARIZE:
+                from core.ops.arize_phoenix_trace.arize_phoenix_trace import ArizePhoenixDataTrace
+                from core.ops.entities.config_entity import ArizeConfig
+
+                return {
+                    "config_class": ArizeConfig,
+                    "secret_keys": ["api_key", "space_id"],
+                    "other_keys": ["project", "endpoint"],
+                    "trace_instance": ArizePhoenixDataTrace,
+                }
+            case TracingProviderEnum.PHOENIX:
+                from core.ops.arize_phoenix_trace.arize_phoenix_trace import ArizePhoenixDataTrace
+                from core.ops.entities.config_entity import PhoenixConfig
+
+                return {
+                    "config_class": PhoenixConfig,
+                    "secret_keys": ["api_key"],
+                    "other_keys": ["project", "endpoint"],
+                    "trace_instance": ArizePhoenixDataTrace,
+                }
+            case TracingProviderEnum.ALIYUN:
+                from core.ops.aliyun_trace.aliyun_trace import AliyunDataTrace
+                from core.ops.entities.config_entity import AliyunConfig
+
+                return {
+                    "config_class": AliyunConfig,
+                    "secret_keys": ["license_key"],
+                    "other_keys": ["endpoint", "app_name"],
+                    "trace_instance": AliyunDataTrace,
+                }
 
             case _:
                 raise KeyError(f"Unsupported tracing provider: {provider}")

api/core/ops/utils.py

@@ -1,6 +1,7 @@
 from contextlib import contextmanager
 from datetime import datetime
 from typing import Optional, Union
+from urllib.parse import urlparse
 
 from extensions.ext_database import db
 from models.model import Message
@@ -60,3 +61,83 @@ def generate_dotted_order(
         return current_segment
 
     return f"{parent_dotted_order}.{current_segment}"
+
+
+def validate_url(url: str, default_url: str, allowed_schemes: tuple = ("https", "http")) -> str:
+    """
+    Validate and normalize URL with proper error handling
+
+    Args:
+        url: The URL to validate
+        default_url: Default URL to use if input is None or empty
+        allowed_schemes: Tuple of allowed URL schemes (default: https, http)
+
+    Returns:
+        Normalized URL string
+
+    Raises:
+        ValueError: If URL format is invalid or scheme not allowed
+    """
+    if not url or url.strip() == "":
+        return default_url
+
+    # Parse URL to validate format
+    parsed = urlparse(url)
+
+    # Check if scheme is allowed
+    if parsed.scheme not in allowed_schemes:
+        raise ValueError(f"URL scheme must be one of: {', '.join(allowed_schemes)}")
+
+    # Reconstruct URL with only scheme, netloc (removing path, query, fragment)
+    normalized_url = f"{parsed.scheme}://{parsed.netloc}"
+
+    return normalized_url
+
+
+def validate_url_with_path(url: str, default_url: str, required_suffix: str | None = None) -> str:
+    """
+    Validate URL that may include path components
+
+    Args:
+        url: The URL to validate
+        default_url: Default URL to use if input is None or empty
+        required_suffix: Optional suffix that URL must end with
+
+    Returns:
+        Validated URL string
+
+    Raises:
+        ValueError: If URL format is invalid or doesn't match required suffix
+    """
+    if not url or url.strip() == "":
+        return default_url
+
+    # Parse URL to validate format
+    parsed = urlparse(url)
+
+    # Check if scheme is allowed
+    if parsed.scheme not in ("https", "http"):
+        raise ValueError("URL must start with https:// or http://")
+
+    # Check required suffix if specified
+    if required_suffix and not url.endswith(required_suffix):
+        raise ValueError(f"URL should end with {required_suffix}")
+
+    return url
+
+
+def validate_project_name(project: str, default_name: str) -> str:
+    """
+    Validate and normalize project name
+
+    Args:
+        project: Project name to validate
+        default_name: Default name to use if input is None or empty
+
+    Returns:
+        Normalized project name
+    """
+    if not project or project.strip() == "":
+        return default_name
+
+    return project.strip()

api/core/ops/weave_trace/weave_trace.py

@@ -22,7 +22,7 @@ from core.ops.entities.trace_entity import (
     WorkflowTraceInfo,
 )
 from core.ops.weave_trace.entities.weave_trace_entity import WeaveTraceModel
-from core.repositories import SQLAlchemyWorkflowNodeExecutionRepository
+from core.repositories import DifyCoreRepositoryFactory
 from core.workflow.entities.workflow_node_execution import WorkflowNodeExecutionMetadataKey
 from core.workflow.nodes.enums import NodeType
 from extensions.ext_database import db
@@ -144,10 +144,10 @@ class WeaveDataTrace(BaseTraceInstance):
 
         service_account = self.get_service_account_with_tenant(app_id)
 
-        workflow_node_execution_repository = SQLAlchemyWorkflowNodeExecutionRepository(
+        workflow_node_execution_repository = DifyCoreRepositoryFactory.create_workflow_node_execution_repository(
             session_factory=session_factory,
             user=service_account,
-            app_id=trace_info.metadata.get("app_id"),
+            app_id=app_id,
             triggered_from=WorkflowNodeExecutionTriggeredFrom.WORKFLOW_RUN,
         )
 

api/core/plugin/backwards_invocation/encrypt.py

@@ -1,16 +1,20 @@
+from core.helper.provider_cache import SingletonProviderCredentialsCache
 from core.plugin.entities.request import RequestInvokeEncrypt
-from core.tools.utils.configuration import ProviderConfigEncrypter
+from core.tools.utils.encryption import create_provider_encrypter
 from models.account import Tenant
 
 
 class PluginEncrypter:
     @classmethod
     def invoke_encrypt(cls, tenant: Tenant, payload: RequestInvokeEncrypt) -> dict:
-        encrypter = ProviderConfigEncrypter(
+        encrypter, cache = create_provider_encrypter(
             tenant_id=tenant.id,
             config=payload.config,
-            provider_type=payload.namespace,
-            provider_identity=payload.identity,
+            cache=SingletonProviderCredentialsCache(
+                tenant_id=tenant.id,
+                provider_type=payload.namespace,
+                provider_identity=payload.identity,
+            ),
         )
 
         if payload.opt == "encrypt":
@@ -22,7 +26,7 @@ class PluginEncrypter:
                 "data": encrypter.decrypt(payload.data),
             }
         elif payload.opt == "clear":
-            encrypter.delete_tool_credentials_cache()
+            cache.delete()
             return {
                 "data": {},
             }

api/core/plugin/backwards_invocation/tool.py

@@ -1,5 +1,5 @@
 from collections.abc import Generator
-from typing import Any
+from typing import Any, Optional
 
 from core.callback_handler.workflow_tool_callback_handler import DifyWorkflowCallbackHandler
 from core.plugin.backwards_invocation.base import BaseBackwardsInvocation
@@ -23,6 +23,7 @@ class PluginToolBackwardsInvocation(BaseBackwardsInvocation):
         provider: str,
         tool_name: str,
         tool_parameters: dict[str, Any],
+        credential_id: Optional[str] = None,
     ) -> Generator[ToolInvokeMessage, None, None]:
         """
         invoke tool
@@ -30,7 +31,7 @@ class PluginToolBackwardsInvocation(BaseBackwardsInvocation):
         # get tool runtime
         try:
             tool_runtime = ToolManager.get_tool_runtime_from_plugin(
-                tool_type, tenant_id, provider, tool_name, tool_parameters
+                tool_type, tenant_id, provider, tool_name, tool_parameters, credential_id
             )
             response = ToolEngine.generic_invoke(
                 tool_runtime, tool_parameters, user_id, DifyWorkflowCallbackHandler(), workflow_call_depth=1

api/core/plugin/entities/parameters.py

@@ -43,6 +43,19 @@ class PluginParameterType(enum.StrEnum):
     # deprecated, should not use.
     SYSTEM_FILES = CommonParameterType.SYSTEM_FILES.value
 
+    # MCP object and array type parameters
+    ARRAY = CommonParameterType.ARRAY.value
+    OBJECT = CommonParameterType.OBJECT.value
+
+
+class MCPServerParameterType(enum.StrEnum):
+    """
+    MCP server got complex parameter types
+    """
+
+    ARRAY = "array"
+    OBJECT = "object"
+
 
 class PluginParameterAutoGenerate(BaseModel):
     class Type(enum.StrEnum):
@@ -138,6 +151,34 @@ def cast_parameter_value(typ: enum.StrEnum, value: Any, /):
                 if value and not isinstance(value, list):
                     raise ValueError("The tools selector must be a list.")
                 return value
+            case PluginParameterType.ARRAY:
+                if not isinstance(value, list):
+                    # Try to parse JSON string for arrays
+                    if isinstance(value, str):
+                        try:
+                            import json
+
+                            parsed_value = json.loads(value)
+                            if isinstance(parsed_value, list):
+                                return parsed_value
+                        except (json.JSONDecodeError, ValueError):
+                            pass
+                    return [value]
+                return value
+            case PluginParameterType.OBJECT:
+                if not isinstance(value, dict):
+                    # Try to parse JSON string for objects
+                    if isinstance(value, str):
+                        try:
+                            import json
+
+                            parsed_value = json.loads(value)
+                            if isinstance(parsed_value, dict):
+                                return parsed_value
+                        except (json.JSONDecodeError, ValueError):
+                            pass
+                    return {}
+                return value
             case _:
                 return str(value)
     except ValueError:

api/core/plugin/entities/plugin.py

@@ -72,12 +72,14 @@ class PluginDeclaration(BaseModel):
 
     class Meta(BaseModel):
         minimum_dify_version: Optional[str] = Field(default=None, pattern=r"^\d{1,4}(\.\d{1,4}){1,3}(-\w{1,16})?$")
+        version: Optional[str] = Field(default=None)
 
     version: str = Field(..., pattern=r"^\d{1,4}(\.\d{1,4}){1,3}(-\w{1,16})?$")
     author: Optional[str] = Field(..., pattern=r"^[a-zA-Z0-9_-]{1,64}$")
     name: str = Field(..., pattern=r"^[a-z0-9_-]{1,128}$")
     description: I18nObject
     icon: str
+    icon_dark: Optional[str] = Field(default=None)
     label: I18nObject
     category: PluginCategory
     created_at: datetime.datetime

api/core/plugin/entities/plugin_daemon.py

@@ -53,6 +53,7 @@ class PluginAgentProviderEntity(BaseModel):
     plugin_unique_identifier: str
     plugin_id: str
     declaration: AgentProviderEntityWithPlugin
+    meta: PluginDeclaration.Meta
 
 
 class PluginBasicBooleanResponse(BaseModel):

api/core/plugin/entities/request.py

@@ -27,15 +27,30 @@ from core.workflow.nodes.question_classifier.entities import (
 )
 
 
+class InvokeCredentials(BaseModel):
+    tool_credentials: dict[str, str] = Field(
+        default_factory=dict,
+        description="Map of tool provider to credential id, used to store the credential id for the tool provider.",
+    )
+
+
+class PluginInvokeContext(BaseModel):
+    credentials: Optional[InvokeCredentials] = Field(
+        default_factory=InvokeCredentials,
+        description="Credentials context for the plugin invocation or backward invocation.",
+    )
+
+
 class RequestInvokeTool(BaseModel):
     """
     Request to invoke a tool
     """
 
-    tool_type: Literal["builtin", "workflow", "api"]
+    tool_type: Literal["builtin", "workflow", "api", "mcp"]
     provider: str
     tool: str
     tool_parameters: dict
+    credential_id: Optional[str] = None
 
 
 class BaseRequestInvokeModel(BaseModel):

api/core/plugin/impl/agent.py

@@ -6,6 +6,7 @@ from core.plugin.entities.plugin import GenericProviderID
 from core.plugin.entities.plugin_daemon import (
     PluginAgentProviderEntity,
 )
+from core.plugin.entities.request import PluginInvokeContext
 from core.plugin.impl.base import BasePluginClient
 
 
@@ -83,6 +84,7 @@ class PluginAgentClient(BasePluginClient):
         conversation_id: Optional[str] = None,
         app_id: Optional[str] = None,
         message_id: Optional[str] = None,
+        context: Optional[PluginInvokeContext] = None,
     ) -> Generator[AgentInvokeMessage, None, None]:
         """
         Invoke the agent with the given tenant, user, plugin, provider, name and parameters.
@@ -99,6 +101,7 @@ class PluginAgentClient(BasePluginClient):
                 "conversation_id": conversation_id,
                 "app_id": app_id,
                 "message_id": message_id,
+                "context": context.model_dump() if context else {},
                 "data": {
                     "agent_strategy_provider": agent_provider_id.provider_name,
                     "agent_strategy": agent_strategy,

api/core/plugin/impl/oauth.py

@@ -15,27 +15,32 @@ class OAuthHandler(BasePluginClient):
         user_id: str,
         plugin_id: str,
         provider: str,
+        redirect_uri: str,
         system_credentials: Mapping[str, Any],
     ) -> PluginOAuthAuthorizationUrlResponse:
-        response = self._request_with_plugin_daemon_response_stream(
-            "POST",
-            f"plugin/{tenant_id}/dispatch/oauth/get_authorization_url",
-            PluginOAuthAuthorizationUrlResponse,
-            data={
-                "user_id": user_id,
-                "data": {
-                    "provider": provider,
-                    "system_credentials": system_credentials,
+        try:
+            response = self._request_with_plugin_daemon_response_stream(
+                "POST",
+                f"plugin/{tenant_id}/dispatch/oauth/get_authorization_url",
+                PluginOAuthAuthorizationUrlResponse,
+                data={
+                    "user_id": user_id,
+                    "data": {
+                        "provider": provider,
+                        "redirect_uri": redirect_uri,
+                        "system_credentials": system_credentials,
+                    },
                 },
-            },
-            headers={
-                "X-Plugin-ID": plugin_id,
-                "Content-Type": "application/json",
-            },
-        )
-        for resp in response:
-            return resp
-        raise ValueError("No response received from plugin daemon for authorization URL request.")
+                headers={
+                    "X-Plugin-ID": plugin_id,
+                    "Content-Type": "application/json",
+                },
+            )
+            for resp in response:
+                return resp
+            raise ValueError("No response received from plugin daemon for authorization URL request.")
+        except Exception as e:
+            raise ValueError(f"Error getting authorization URL: {e}")
 
     def get_credentials(
         self,
@@ -43,6 +48,7 @@ class OAuthHandler(BasePluginClient):
         user_id: str,
         plugin_id: str,
         provider: str,
+        redirect_uri: str,
         system_credentials: Mapping[str, Any],
         request: Request,
     ) -> PluginOAuthCredentialsResponse:
@@ -50,30 +56,34 @@ class OAuthHandler(BasePluginClient):
         Get credentials from the given request.
         """
 
-        # encode request to raw http request
-        raw_request_bytes = self._convert_request_to_raw_data(request)
 
-        response = self._request_with_plugin_daemon_response_stream(
-            "POST",
-            f"plugin/{tenant_id}/dispatch/oauth/get_credentials",
-            PluginOAuthCredentialsResponse,
-            data={
-                "user_id": user_id,
-                "data": {
-                    "provider": provider,
-                    "system_credentials": system_credentials,
-                    # for json serialization
-                    "raw_http_request": binascii.hexlify(raw_request_bytes).decode(),
+        try:
+            # encode request to raw http request
+            raw_request_bytes = self._convert_request_to_raw_data(request)
+            response = self._request_with_plugin_daemon_response_stream(
+                "POST",
+                f"plugin/{tenant_id}/dispatch/oauth/get_credentials",
+                PluginOAuthCredentialsResponse,
+                data={
+                    "user_id": user_id,
+                    "data": {
+                        "provider": provider,
+                        "redirect_uri": redirect_uri,
+                        "system_credentials": system_credentials,
+                        # for json serialization
+                        "raw_http_request": binascii.hexlify(raw_request_bytes).decode(),
+                    },
                 },
-            },
-            headers={
-                "X-Plugin-ID": plugin_id,
-                "Content-Type": "application/json",
-            },
-        )
-        for resp in response:
-            return resp
-        raise ValueError("No response received from plugin daemon for authorization URL request.")
+                headers={
+                    "X-Plugin-ID": plugin_id,
+                    "Content-Type": "application/json",
+                },
+            )
+            for resp in response:
+                return resp
+            raise ValueError("No response received from plugin daemon for authorization URL request.")
+        except Exception as e:
+            raise ValueError(f"Error getting credentials: {e}")
 
     def _convert_request_to_raw_data(self, request: Request) -> bytes:
         """

api/core/plugin/impl/plugin.py

@@ -36,7 +36,7 @@ class PluginInstaller(BasePluginClient):
             "GET",
             f"plugin/{tenant_id}/management/list",
             PluginListResponse,
-            params={"page": 1, "page_size": 256},
+            params={"page": 1, "page_size": 256, "response_type": "paged"},
         )
         return result.list
 
@@ -45,7 +45,7 @@ class PluginInstaller(BasePluginClient):
             "GET",
             f"plugin/{tenant_id}/management/list",
             PluginListResponse,
-            params={"page": page, "page_size": page_size},
+            params={"page": page, "page_size": page_size, "response_type": "paged"},
         )
 
     def upload_pkg(

api/core/plugin/impl/tool.py

@@ -6,7 +6,7 @@ from pydantic import BaseModel
 from core.plugin.entities.plugin import GenericProviderID, ToolProviderID
 from core.plugin.entities.plugin_daemon import PluginBasicBooleanResponse, PluginToolProviderEntity
 from core.plugin.impl.base import BasePluginClient
-from core.tools.entities.tool_entities import ToolInvokeMessage, ToolParameter
+from core.tools.entities.tool_entities import CredentialType, ToolInvokeMessage, ToolParameter
 
 
 class PluginToolManager(BasePluginClient):
@@ -78,6 +78,7 @@ class PluginToolManager(BasePluginClient):
         tool_provider: str,
         tool_name: str,
         credentials: dict[str, Any],
+        credential_type: CredentialType,
         tool_parameters: dict[str, Any],
         conversation_id: Optional[str] = None,
         app_id: Optional[str] = None,
@@ -102,6 +103,7 @@ class PluginToolManager(BasePluginClient):
                     "provider": tool_provider_id.provider_name,
                     "tool": tool_name,
                     "credentials": credentials,
+                    "credential_type": credential_type,
                     "tool_parameters": tool_parameters,
                 },
             },

api/core/prompt/utils/extract_thread_messages.py

@@ -1,10 +1,11 @@
-from typing import Any
+from collections.abc import Sequence
 
 from constants import UUID_NIL
+from models import Message
 
 
-def extract_thread_messages(messages: list[Any]):
-    thread_messages = []
+def extract_thread_messages(messages: Sequence[Message]):
+    thread_messages: list[Message] = []
     next_message = None
 
     for message in messages:

api/core/prompt/utils/get_thread_messages_length.py

@@ -1,3 +1,5 @@
+from sqlalchemy import select
+
 from core.prompt.utils.extract_thread_messages import extract_thread_messages
 from extensions.ext_database import db
 from models.model import Message
@@ -8,19 +10,9 @@ def get_thread_messages_length(conversation_id: str) -> int:
     Get the number of thread messages based on the parent message id.
     """
     # Fetch all messages related to the conversation
-    query = (
-        db.session.query(
-            Message.id,
-            Message.parent_message_id,
-            Message.answer,
-        )
-        .filter(
-            Message.conversation_id == conversation_id,
-        )
-        .order_by(Message.created_at.desc())
-    )
+    stmt = select(Message).where(Message.conversation_id == conversation_id).order_by(Message.created_at.desc())
 
-    messages = query.all()
+    messages = db.session.scalars(stmt).all()
 
     # Extract thread messages
     thread_messages = extract_thread_messages(messages)

api/core/rag/datasource/retrieval_service.py

@@ -3,7 +3,7 @@ from concurrent.futures import ThreadPoolExecutor
 from typing import Optional
 
 from flask import Flask, current_app
-from sqlalchemy.orm import load_only
+from sqlalchemy.orm import Session, load_only
 
 from configs import dify_config
 from core.rag.data_post_processor.data_post_processor import DataPostProcessor
@@ -144,7 +144,8 @@ class RetrievalService:
 
     @classmethod
     def _get_dataset(cls, dataset_id: str) -> Optional[Dataset]:
-        return db.session.query(Dataset).filter(Dataset.id == dataset_id).first()
+        with Session(db.engine) as session:
+            return session.query(Dataset).filter(Dataset.id == dataset_id).first()
 
     @classmethod
     def keyword_search(