Merge branch 'main' into feat/rag-2

# Conflicts:
#	web/app/components/workflow/hooks/use-workflow.ts

README.md

@@ -241,7 +241,7 @@ One-Click deploy Dify to Alibaba Cloud with [Alibaba Cloud Data Management](http
 For those who'd like to contribute code, see our [Contribution Guide](https://github.com/langgenius/dify/blob/main/CONTRIBUTING.md).
 At the same time, please consider supporting Dify by sharing it on social media and at events and conferences.
 
-> We are looking for contributors to help translate Dify into languages other than Mandarin or English. If you are interested in helping, please see the [i18n README](https://github.com/langgenius/dify/blob/main/web/i18n/README.md) for more information, and leave us a comment in the `global-users` channel of our [Discord Community Server](https://discord.gg/8Tpq4AcN9c).
+> We are looking for contributors to help translate Dify into languages other than Mandarin or English. If you are interested in helping, please see the [i18n README](https://github.com/langgenius/dify/blob/main/web/i18n-config/README.md) for more information, and leave us a comment in the `global-users` channel of our [Discord Community Server](https://discord.gg/8Tpq4AcN9c).
 
 ## Community & contact
 

README_AR.md

@@ -223,7 +223,7 @@ docker compose up -d
 لأولئك الذين يرغبون في المساهمة، انظر إلى [دليل المساهمة](https://github.com/langgenius/dify/blob/main/CONTRIBUTING.md) لدينا.
 في الوقت نفسه، يرجى النظر في دعم Dify عن طريق مشاركته على وسائل التواصل الاجتماعي وفي الفعاليات والمؤتمرات.
 
-> نحن نبحث عن مساهمين لمساعدة في ترجمة Dify إلى لغات أخرى غير اللغة الصينية المندرين أو الإنجليزية. إذا كنت مهتمًا بالمساعدة، يرجى الاطلاع على [README للترجمة](https://github.com/langgenius/dify/blob/main/web/i18n/README.md) لمزيد من المعلومات، واترك لنا تعليقًا في قناة `global-users` على [خادم المجتمع على Discord](https://discord.gg/8Tpq4AcN9c).
+> نحن نبحث عن مساهمين لمساعدة في ترجمة Dify إلى لغات أخرى غير اللغة الصينية المندرين أو الإنجليزية. إذا كنت مهتمًا بالمساعدة، يرجى الاطلاع على [README للترجمة](https://github.com/langgenius/dify/blob/main/web/i18n-config/README.md) لمزيد من المعلومات، واترك لنا تعليقًا في قناة `global-users` على [خادم المجتمع على Discord](https://discord.gg/8Tpq4AcN9c).
 
 **المساهمون**
 

README_BN.md

@@ -241,7 +241,7 @@ GitHub-এ ডিফাইকে স্টার দিয়ে রাখুন
 যারা কোড অবদান রাখতে চান, তাদের জন্য আমাদের [অবদান নির্দেশিকা] দেখুন (https://github.com/langgenius/dify/blob/main/CONTRIBUTING.md)।
 একই সাথে, সোশ্যাল মিডিয়া এবং ইভেন্ট এবং কনফারেন্সে এটি শেয়ার করে Dify কে সমর্থন করুন।
 
-> আমরা ম্যান্ডারিন বা ইংরেজি ছাড়া অন্য ভাষায় Dify অনুবাদ করতে সাহায্য করার জন্য অবদানকারীদের খুঁজছি। আপনি যদি সাহায্য করতে আগ্রহী হন, তাহলে আরও তথ্যের জন্য [i18n README](https://github.com/langgenius/dify/blob/main/web/i18n/README.md) দেখুন এবং আমাদের [ডিসকর্ড কমিউনিটি সার্ভার](https://discord.gg/8Tpq4AcN9c) এর `গ্লোবাল-ইউজারস` চ্যানেলে আমাদের একটি মন্তব্য করুন।
+> আমরা ম্যান্ডারিন বা ইংরেজি ছাড়া অন্য ভাষায় Dify অনুবাদ করতে সাহায্য করার জন্য অবদানকারীদের খুঁজছি। আপনি যদি সাহায্য করতে আগ্রহী হন, তাহলে আরও তথ্যের জন্য [i18n README](https://github.com/langgenius/dify/blob/main/web/i18n-config/README.md) দেখুন এবং আমাদের [ডিসকর্ড কমিউনিটি সার্ভার](https://discord.gg/8Tpq4AcN9c) এর `গ্লোবাল-ইউজারস` চ্যানেলে আমাদের একটি মন্তব্য করুন।
 
 ## কমিউনিটি এবং যোগাযোগ
 

README_CN.md

@@ -244,7 +244,7 @@ docker compose up -d
 对于那些想要贡献代码的人，请参阅我们的[贡献指南](https://github.com/langgenius/dify/blob/main/CONTRIBUTING.md)。
 同时，请考虑通过社交媒体、活动和会议来支持 Dify 的分享。
 
-> 我们正在寻找贡献者来帮助将 Dify 翻译成除了中文和英文之外的其他语言。如果您有兴趣帮助，请参阅我们的[i18n README](https://github.com/langgenius/dify/blob/main/web/i18n/README.md)获取更多信息，并在我们的[Discord 社区服务器](https://discord.gg/8Tpq4AcN9c)的`global-users`频道中留言。
+> 我们正在寻找贡献者来帮助将 Dify 翻译成除了中文和英文之外的其他语言。如果您有兴趣帮助，请参阅我们的[i18n README](https://github.com/langgenius/dify/blob/main/web/i18n-config/README.md)获取更多信息，并在我们的[Discord 社区服务器](https://discord.gg/8Tpq4AcN9c)的`global-users`频道中留言。
 
 **Contributors**
 

README_DE.md

@@ -236,7 +236,7 @@ Ein-Klick-Bereitstellung von Dify in der Alibaba Cloud mit [Alibaba Cloud Data M
 Falls Sie Code beitragen möchten, lesen Sie bitte unseren [Contribution Guide](https://github.com/langgenius/dify/blob/main/CONTRIBUTING.md). Gleichzeitig bitten wir Sie, Dify zu unterstützen, indem Sie es in den sozialen Medien teilen und auf Veranstaltungen und Konferenzen präsentieren.
 
 
-> Wir suchen Mitwirkende, die dabei helfen, Dify in weitere Sprachen zu übersetzen – außer Mandarin oder Englisch. Wenn Sie Interesse an einer Mitarbeit haben, lesen Sie bitte die [i18n README](https://github.com/langgenius/dify/blob/main/web/i18n/README.md) für weitere Informationen und hinterlassen Sie einen Kommentar im `global-users`-Kanal unseres [Discord Community Servers](https://discord.gg/8Tpq4AcN9c).
+> Wir suchen Mitwirkende, die dabei helfen, Dify in weitere Sprachen zu übersetzen – außer Mandarin oder Englisch. Wenn Sie Interesse an einer Mitarbeit haben, lesen Sie bitte die [i18n README](https://github.com/langgenius/dify/blob/main/web/i18n-config/README.md) für weitere Informationen und hinterlassen Sie einen Kommentar im `global-users`-Kanal unseres [Discord Community Servers](https://discord.gg/8Tpq4AcN9c).
 
 ## Gemeinschaft & Kontakt
 

README_ES.md

@@ -237,7 +237,7 @@ Para aquellos que deseen contribuir con código, consulten nuestra [Guía de con
 Al mismo tiempo, considera apoyar a Dify compartiéndolo en redes sociales y en eventos y conferencias.
 
 
-> Estamos buscando colaboradores para ayudar con la traducción de Dify a idiomas que no sean el mandarín o el inglés. Si estás interesado en ayudar, consulta el [README de i18n](https://github.com/langgenius/dify/blob/main/web/i18n/README.md) para obtener más información y déjanos un comentario en el canal `global-users` de nuestro [Servidor de Comunidad en Discord](https://discord.gg/8Tpq4AcN9c).
+> Estamos buscando colaboradores para ayudar con la traducción de Dify a idiomas que no sean el mandarín o el inglés. Si estás interesado en ayudar, consulta el [README de i18n](https://github.com/langgenius/dify/blob/main/web/i18n-config/README.md) para obtener más información y déjanos un comentario en el canal `global-users` de nuestro [Servidor de Comunidad en Discord](https://discord.gg/8Tpq4AcN9c).
 
 **Contribuidores**
 

README_FR.md

@@ -235,7 +235,7 @@ Pour ceux qui souhaitent contribuer du code, consultez notre [Guide de contribut
 Dans le même temps, veuillez envisager de soutenir Dify en le partageant sur les réseaux sociaux et lors d'événements et de conférences.
 
 
-> Nous recherchons des contributeurs pour aider à traduire Dify dans des langues autres que le mandarin ou l'anglais. Si vous êtes intéressé à aider, veuillez consulter le [README i18n](https://github.com/langgenius/dify/blob/main/web/i18n/README.md) pour plus d'informations, et laissez-nous un commentaire dans le canal `global-users` de notre [Serveur communautaire Discord](https://discord.gg/8Tpq4AcN9c).
+> Nous recherchons des contributeurs pour aider à traduire Dify dans des langues autres que le mandarin ou l'anglais. Si vous êtes intéressé à aider, veuillez consulter le [README i18n](https://github.com/langgenius/dify/blob/main/web/i18n-config/README.md) pour plus d'informations, et laissez-nous un commentaire dans le canal `global-users` de notre [Serveur communautaire Discord](https://discord.gg/8Tpq4AcN9c).
 
 **Contributeurs**
 

README_JA.md

@@ -234,7 +234,7 @@ docker compose up -d
 同時に、DifyをSNSやイベント、カンファレンスで共有してサポートしていただけると幸いです。
 
 
-> Difyを英語または中国語以外の言語に翻訳してくれる貢献者を募集しています。興味がある場合は、詳細については[i18n README](https://github.com/langgenius/dify/blob/main/web/i18n/README.md)を参照してください。また、[Discordコミュニティサーバー](https://discord.gg/8Tpq4AcN9c)の`global-users`チャンネルにコメントを残してください。
+> Difyを英語または中国語以外の言語に翻訳してくれる貢献者を募集しています。興味がある場合は、詳細については[i18n README](https://github.com/langgenius/dify/blob/main/web/i18n-config/README.md)を参照してください。また、[Discordコミュニティサーバー](https://discord.gg/8Tpq4AcN9c)の`global-users`チャンネルにコメントを残してください。
 
 **貢献者**
 

README_KL.md

@@ -235,7 +235,7 @@ For those who'd like to contribute code, see our [Contribution Guide](https://gi
 At the same time, please consider supporting Dify by sharing it on social media and at events and conferences.
 
 
-> We are looking for contributors to help with translating Dify to languages other than Mandarin or English. If you are interested in helping, please see the [i18n README](https://github.com/langgenius/dify/blob/main/web/i18n/README.md) for more information, and leave us a comment in the `global-users` channel of our [Discord Community Server](https://discord.gg/8Tpq4AcN9c).
+> We are looking for contributors to help with translating Dify to languages other than Mandarin or English. If you are interested in helping, please see the [i18n README](https://github.com/langgenius/dify/blob/main/web/i18n-config/README.md) for more information, and leave us a comment in the `global-users` channel of our [Discord Community Server](https://discord.gg/8Tpq4AcN9c).
 
 **Contributors**
 

README_KR.md

@@ -229,7 +229,7 @@ Dify를 Kubernetes에 배포하고 프리미엄 스케일링 설정을 구성했
 동시에 Dify를 소셜 미디어와 행사 및 컨퍼런스에 공유하여 지원하는 것을 고려해 주시기 바랍니다.
 
 
-> 우리는 Dify를 중국어나 영어 이외의 언어로 번역하는 데 도움을 줄 수 있는 기여자를 찾고 있습니다. 도움을 주고 싶으시다면 [i18n README](https://github.com/langgenius/dify/blob/main/web/i18n/README.md)에서 더 많은 정보를 확인하시고 [Discord 커뮤니티 서버](https://discord.gg/8Tpq4AcN9c)의 `global-users` 채널에 댓글을 남겨주세요. 
+> 우리는 Dify를 중국어나 영어 이외의 언어로 번역하는 데 도움을 줄 수 있는 기여자를 찾고 있습니다. 도움을 주고 싶으시다면 [i18n README](https://github.com/langgenius/dify/blob/main/web/i18n-config/README.md)에서 더 많은 정보를 확인하시고 [Discord 커뮤니티 서버](https://discord.gg/8Tpq4AcN9c)의 `global-users` 채널에 댓글을 남겨주세요. 
 
 **기여자**
 

README_PT.md

@@ -233,7 +233,7 @@ Implante o Dify na Alibaba Cloud com um clique usando o [Alibaba Cloud Data Mana
 Para aqueles que desejam contribuir com código, veja nosso [Guia de Contribuição](https://github.com/langgenius/dify/blob/main/CONTRIBUTING.md). 
 Ao mesmo tempo, considere apoiar o Dify compartilhando-o nas redes sociais e em eventos e conferências.
 
-> Estamos buscando contribuidores para ajudar na tradução do Dify para idiomas além de Mandarim e Inglês. Se você tiver interesse em ajudar, consulte o [README i18n](https://github.com/langgenius/dify/blob/main/web/i18n/README.md) para mais informações e deixe-nos um comentário no canal `global-users` em nosso [Servidor da Comunidade no Discord](https://discord.gg/8Tpq4AcN9c).
+> Estamos buscando contribuidores para ajudar na tradução do Dify para idiomas além de Mandarim e Inglês. Se você tiver interesse em ajudar, consulte o [README i18n](https://github.com/langgenius/dify/blob/main/web/i18n-config/README.md) para mais informações e deixe-nos um comentário no canal `global-users` em nosso [Servidor da Comunidade no Discord](https://discord.gg/8Tpq4AcN9c).
 
 **Contribuidores**
 

README_TR.md

@@ -227,7 +227,7 @@ Dify'ı bulut platformuna tek tıklamayla dağıtın [terraform](https://www.ter
 Kod katkısında bulunmak isteyenler için [Katkı Kılavuzumuza](https://github.com/langgenius/dify/blob/main/CONTRIBUTING.md) bakabilirsiniz.
 Aynı zamanda, lütfen Dify'ı sosyal medyada, etkinliklerde ve konferanslarda paylaşarak desteklemeyi düşünün.
 
-> Dify'ı Mandarin veya İngilizce dışındaki dillere çevirmemize yardımcı olacak katkıda bulunanlara ihtiyacımız var. Yardımcı olmakla ilgileniyorsanız, lütfen daha fazla bilgi için [i18n README](https://github.com/langgenius/dify/blob/main/web/i18n/README.md) dosyasına bakın ve [Discord Topluluk Sunucumuzdaki](https://discord.gg/8Tpq4AcN9c) `global-users` kanalında bize bir yorum bırakın.
+> Dify'ı Mandarin veya İngilizce dışındaki dillere çevirmemize yardımcı olacak katkıda bulunanlara ihtiyacımız var. Yardımcı olmakla ilgileniyorsanız, lütfen daha fazla bilgi için [i18n README](https://github.com/langgenius/dify/blob/main/web/i18n-config/README.md) dosyasına bakın ve [Discord Topluluk Sunucumuzdaki](https://discord.gg/8Tpq4AcN9c) `global-users` kanalında bize bir yorum bırakın.
 
 **Katkıda Bulunanlar**
 

README_TW.md

@@ -239,7 +239,7 @@ Dify 的所有功能都提供相應的 API，因此您可以輕鬆地將 Dify
 對於想要貢獻程式碼的開發者，請參閱我們的[貢獻指南](https://github.com/langgenius/dify/blob/main/CONTRIBUTING.md)。
 同時，也請考慮透過在社群媒體和各種活動與會議上分享 Dify 來支持我們。
 
-> 我們正在尋找貢獻者協助將 Dify 翻譯成中文和英文以外的語言。如果您有興趣幫忙，請查看 [i18n README](https://github.com/langgenius/dify/blob/main/web/i18n/README.md) 獲取更多資訊，並在我們的 [Discord 社群伺服器](https://discord.gg/8Tpq4AcN9c) 的 `global-users` 頻道留言給我們。
+> 我們正在尋找貢獻者協助將 Dify 翻譯成中文和英文以外的語言。如果您有興趣幫忙，請查看 [i18n README](https://github.com/langgenius/dify/blob/main/web/i18n-config/README.md) 獲取更多資訊，並在我們的 [Discord 社群伺服器](https://discord.gg/8Tpq4AcN9c) 的 `global-users` 頻道留言給我們。
 
 ## 社群與聯絡方式
 

README_VI.md

@@ -231,7 +231,7 @@ Triển khai Dify lên Alibaba Cloud chỉ với một cú nhấp chuột bằng
 Đồng thời, vui lòng xem xét hỗ trợ Dify bằng cách chia sẻ nó trên mạng xã hội và tại các sự kiện và hội nghị.
 
 
-> Chúng tôi đang tìm kiếm người đóng góp để giúp dịch Dify sang các ngôn ngữ khác ngoài tiếng Trung hoặc tiếng Anh. Nếu bạn quan tâm đến việc giúp đỡ, vui lòng xem [README i18n](https://github.com/langgenius/dify/blob/main/web/i18n/README.md) để biết thêm thông tin và để lại bình luận cho chúng tôi trong kênh `global-users` của [Máy chủ Cộng đồng Discord](https://discord.gg/8Tpq4AcN9c) của chúng tôi.
+> Chúng tôi đang tìm kiếm người đóng góp để giúp dịch Dify sang các ngôn ngữ khác ngoài tiếng Trung hoặc tiếng Anh. Nếu bạn quan tâm đến việc giúp đỡ, vui lòng xem [README i18n](https://github.com/langgenius/dify/blob/main/web/i18n-config/README.md) để biết thêm thông tin và để lại bình luận cho chúng tôi trong kênh `global-users` của [Máy chủ Cộng đồng Discord](https://discord.gg/8Tpq4AcN9c) của chúng tôi.
 
 **Người đóng góp**
 

api/configs/middleware/vdb/elasticsearch_config.py

@@ -1,12 +1,13 @@
 from typing import Optional
 
-from pydantic import Field, PositiveInt
+from pydantic import Field, PositiveInt, model_validator
 from pydantic_settings import BaseSettings
 
 
 class ElasticsearchConfig(BaseSettings):
     """
-    Configuration settings for Elasticsearch
+    Configuration settings for both self-managed and Elastic Cloud deployments.
+    Can load from environment variables or .env files.
     """
 
     ELASTICSEARCH_HOST: Optional[str] = Field(
@@ -28,3 +29,50 @@ class ElasticsearchConfig(BaseSettings):
         description="Password for authenticating with Elasticsearch (default is 'elastic')",
         default="elastic",
     )
+
+    # Elastic Cloud (optional)
+    ELASTICSEARCH_USE_CLOUD: Optional[bool] = Field(
+        description="Set to True to use Elastic Cloud instead of self-hosted Elasticsearch", default=False
+    )
+    ELASTICSEARCH_CLOUD_URL: Optional[str] = Field(
+        description="Full URL for Elastic Cloud deployment (e.g., 'https://example.es.region.aws.found.io:443')",
+        default=None,
+    )
+    ELASTICSEARCH_API_KEY: Optional[str] = Field(
+        description="API key for authenticating with Elastic Cloud", default=None
+    )
+
+    # Common options
+    ELASTICSEARCH_CA_CERTS: Optional[str] = Field(
+        description="Path to CA certificate file for SSL verification", default=None
+    )
+    ELASTICSEARCH_VERIFY_CERTS: bool = Field(
+        description="Whether to verify SSL certificates (default is False)", default=False
+    )
+    ELASTICSEARCH_REQUEST_TIMEOUT: int = Field(
+        description="Request timeout in milliseconds (default is 100000)", default=100000
+    )
+    ELASTICSEARCH_RETRY_ON_TIMEOUT: bool = Field(
+        description="Whether to retry requests on timeout (default is True)", default=True
+    )
+    ELASTICSEARCH_MAX_RETRIES: int = Field(
+        description="Maximum number of retry attempts (default is 10000)", default=10000
+    )
+
+    @model_validator(mode="after")
+    def validate_elasticsearch_config(self):
+        """Validate Elasticsearch configuration based on deployment type."""
+        if self.ELASTICSEARCH_USE_CLOUD:
+            if not self.ELASTICSEARCH_CLOUD_URL:
+                raise ValueError("ELASTICSEARCH_CLOUD_URL is required when using Elastic Cloud")
+            if not self.ELASTICSEARCH_API_KEY:
+                raise ValueError("ELASTICSEARCH_API_KEY is required when using Elastic Cloud")
+        else:
+            if not self.ELASTICSEARCH_HOST:
+                raise ValueError("ELASTICSEARCH_HOST is required for self-hosted Elasticsearch")
+            if not self.ELASTICSEARCH_USERNAME:
+                raise ValueError("ELASTICSEARCH_USERNAME is required for self-hosted Elasticsearch")
+            if not self.ELASTICSEARCH_PASSWORD:
+                raise ValueError("ELASTICSEARCH_PASSWORD is required for self-hosted Elasticsearch")
+
+        return self

api/controllers/console/app/annotation.py

@@ -100,7 +100,7 @@ class AnnotationReplyActionStatusApi(Resource):
         return {"job_id": job_id, "job_status": job_status, "error_msg": error_msg}, 200
 
 
-class AnnotationListApi(Resource):
+class AnnotationApi(Resource):
     @setup_required
     @login_required
     @account_initialization_required
@@ -126,46 +126,61 @@ class AnnotationListApi(Resource):
     @setup_required
     @login_required
     @account_initialization_required
-    def delete(self, app_id):
+    @cloud_edition_billing_resource_check("annotation")
+    @marshal_with(annotation_fields)
+    def post(self, app_id):
         if not current_user.is_editor:
             raise Forbidden()
 
         app_id = str(app_id)
-        AppAnnotationService.clear_all_annotations(app_id)
-        return {"result": "success"}, 204
-
+        parser = reqparse.RequestParser()
+        parser.add_argument("question", required=True, type=str, location="json")
+        parser.add_argument("answer", required=True, type=str, location="json")
+        args = parser.parse_args()
+        annotation = AppAnnotationService.insert_app_annotation_directly(args, app_id)
+        return annotation
 
-class AnnotationExportApi(Resource):
     @setup_required
     @login_required
     @account_initialization_required
-    def get(self, app_id):
+    def delete(self, app_id):
         if not current_user.is_editor:
             raise Forbidden()
 
         app_id = str(app_id)
-        annotation_list = AppAnnotationService.export_annotation_list_by_app_id(app_id)
-        response = {"data": marshal(annotation_list, annotation_fields)}
-        return response, 200
+
+        # Use request.args.getlist to get annotation_ids array directly
+        annotation_ids = request.args.getlist("annotation_id")
+
+        # If annotation_ids are provided, handle batch deletion
+        if annotation_ids:
+            # Check if any annotation_ids contain empty strings or invalid values
+            if not all(annotation_id.strip() for annotation_id in annotation_ids if annotation_id):
+                return {
+                    "code": "bad_request",
+                    "message": "annotation_ids are required if the parameter is provided.",
+                }, 400
+
+            result = AppAnnotationService.delete_app_annotations_in_batch(app_id, annotation_ids)
+            return result, 204
+        # If no annotation_ids are provided, handle clearing all annotations
+        else:
+            AppAnnotationService.clear_all_annotations(app_id)
+            return {"result": "success"}, 204
 
 
-class AnnotationCreateApi(Resource):
+class AnnotationExportApi(Resource):
     @setup_required
     @login_required
     @account_initialization_required
-    @cloud_edition_billing_resource_check("annotation")
-    @marshal_with(annotation_fields)
-    def post(self, app_id):
+    def get(self, app_id):
         if not current_user.is_editor:
             raise Forbidden()
 
         app_id = str(app_id)
-        parser = reqparse.RequestParser()
-        parser.add_argument("question", required=True, type=str, location="json")
-        parser.add_argument("answer", required=True, type=str, location="json")
-        args = parser.parse_args()
-        annotation = AppAnnotationService.insert_app_annotation_directly(args, app_id)
-        return annotation
+        annotation_list = AppAnnotationService.export_annotation_list_by_app_id(app_id)
+        response = {"data": marshal(annotation_list, annotation_fields)}
+        return response, 200
 
 
 class AnnotationUpdateDeleteApi(Resource):
@@ -276,7 +291,7 @@ api.add_resource(AnnotationReplyActionApi, "/apps/<uuid:app_id>/annotation-reply
 api.add_resource(
     AnnotationReplyActionStatusApi, "/apps/<uuid:app_id>/annotation-reply/<string:action>/status/<uuid:job_id>"
 )
-api.add_resource(AnnotationListApi, "/apps/<uuid:app_id>/annotations")
+api.add_resource(AnnotationApi, "/apps/<uuid:app_id>/annotations")
 api.add_resource(AnnotationExportApi, "/apps/<uuid:app_id>/annotations/export")
 api.add_resource(AnnotationUpdateDeleteApi, "/apps/<uuid:app_id>/annotations/<uuid:annotation_id>")
 api.add_resource(AnnotationBatchImportApi, "/apps/<uuid:app_id>/annotations/batch-import")

api/controllers/console/datasets/metadata.py

@@ -22,8 +22,8 @@ class DatasetMetadataCreateApi(Resource):
     @marshal_with(dataset_metadata_fields)
     def post(self, dataset_id):
         parser = reqparse.RequestParser()
-        parser.add_argument("type", type=str, required=True, nullable=True, location="json")
-        parser.add_argument("name", type=str, required=True, nullable=True, location="json")
+        parser.add_argument("type", type=str, required=True, nullable=False, location="json")
+        parser.add_argument("name", type=str, required=True, nullable=False, location="json")
         args = parser.parse_args()
         metadata_args = MetadataArgs(**args)
 
@@ -56,7 +56,7 @@ class DatasetMetadataApi(Resource):
     @marshal_with(dataset_metadata_fields)
     def patch(self, dataset_id, metadata_id):
         parser = reqparse.RequestParser()
-        parser.add_argument("name", type=str, required=True, nullable=True, location="json")
+        parser.add_argument("name", type=str, required=True, nullable=False, location="json")
         args = parser.parse_args()
 
         dataset_id_str = str(dataset_id)
@@ -127,7 +127,7 @@ class DocumentMetadataEditApi(Resource):
         DatasetService.check_dataset_permission(dataset, current_user)
 
         parser = reqparse.RequestParser()
-        parser.add_argument("operation_data", type=list, required=True, nullable=True, location="json")
+        parser.add_argument("operation_data", type=list, required=True, nullable=False, location="json")
         args = parser.parse_args()
         metadata_args = MetadataOperationData(**args)
 

api/controllers/service_api/app/completion.py

@@ -47,6 +47,9 @@ class CompletionApi(Resource):
         parser.add_argument("retriever_from", type=str, required=False, default="dev", location="json")
 
         args = parser.parse_args()
+        external_trace_id = get_external_trace_id(request)
+        if external_trace_id:
+            args["external_trace_id"] = external_trace_id
 
         streaming = args["response_mode"] == "streaming"
 

api/controllers/service_api/dataset/metadata.py

@@ -17,8 +17,8 @@ class DatasetMetadataCreateServiceApi(DatasetApiResource):
     @cloud_edition_billing_rate_limit_check("knowledge", "dataset")
     def post(self, tenant_id, dataset_id):
         parser = reqparse.RequestParser()
-        parser.add_argument("type", type=str, required=True, nullable=True, location="json")
-        parser.add_argument("name", type=str, required=True, nullable=True, location="json")
+        parser.add_argument("type", type=str, required=True, nullable=False, location="json")
+        parser.add_argument("name", type=str, required=True, nullable=False, location="json")
         args = parser.parse_args()
         metadata_args = MetadataArgs(**args)
 
@@ -43,7 +43,7 @@ class DatasetMetadataServiceApi(DatasetApiResource):
     @cloud_edition_billing_rate_limit_check("knowledge", "dataset")
     def patch(self, tenant_id, dataset_id, metadata_id):
         parser = reqparse.RequestParser()
-        parser.add_argument("name", type=str, required=True, nullable=True, location="json")
+        parser.add_argument("name", type=str, required=True, nullable=False, location="json")
         args = parser.parse_args()
 
         dataset_id_str = str(dataset_id)
@@ -101,7 +101,7 @@ class DocumentMetadataEditServiceApi(DatasetApiResource):
         DatasetService.check_dataset_permission(dataset, current_user)
 
         parser = reqparse.RequestParser()
-        parser.add_argument("operation_data", type=list, required=True, nullable=True, location="json")
+        parser.add_argument("operation_data", type=list, required=True, nullable=False, location="json")
         args = parser.parse_args()
         metadata_args = MetadataOperationData(**args)
 

api/core/app/app_config/entities.py

@@ -159,6 +159,8 @@ SupportedComparisonOperator = Literal[
     "is not",
     "empty",
     "not empty",
+    "in",
+    "not in",
     # for number
     "=",
     "≠",

api/core/ops/aliyun_trace/aliyun_trace.py

@@ -10,6 +10,7 @@ from sqlalchemy.orm import Session, sessionmaker
 from core.ops.aliyun_trace.data_exporter.traceclient import (
     TraceClient,
     convert_datetime_to_nanoseconds,
+    convert_string_to_id,
     convert_to_span_id,
     convert_to_trace_id,
     generate_span_id,
@@ -101,8 +102,9 @@ class AliyunDataTrace(BaseTraceInstance):
             raise ValueError(f"Aliyun get run url failed: {str(e)}")
 
     def workflow_trace(self, trace_info: WorkflowTraceInfo):
-        external_trace_id = trace_info.metadata.get("external_trace_id")
-        trace_id = external_trace_id or convert_to_trace_id(trace_info.workflow_run_id)
+        trace_id = convert_to_trace_id(trace_info.workflow_run_id)
+        if trace_info.trace_id:
+            trace_id = convert_string_to_id(trace_info.trace_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)
 
@@ -130,6 +132,9 @@ class AliyunDataTrace(BaseTraceInstance):
             status = Status(StatusCode.ERROR, trace_info.error)
 
         trace_id = convert_to_trace_id(message_id)
+        if trace_info.trace_id:
+            trace_id = convert_string_to_id(trace_info.trace_id)
+
         message_span_id = convert_to_span_id(message_id, "message")
         message_span = SpanData(
             trace_id=trace_id,
@@ -186,9 +191,13 @@ class AliyunDataTrace(BaseTraceInstance):
             return
         message_id = trace_info.message_id
 
+        trace_id = convert_to_trace_id(message_id)
+        if trace_info.trace_id:
+            trace_id = convert_string_to_id(trace_info.trace_id)
+
         documents_data = extract_retrieval_documents(trace_info.documents)
         dataset_retrieval_span = SpanData(
-            trace_id=convert_to_trace_id(message_id),
+            trace_id=trace_id,
             parent_span_id=convert_to_span_id(message_id, "message"),
             span_id=generate_span_id(),
             name="dataset_retrieval",
@@ -214,8 +223,12 @@ class AliyunDataTrace(BaseTraceInstance):
         if trace_info.error:
             status = Status(StatusCode.ERROR, trace_info.error)
 
+        trace_id = convert_to_trace_id(message_id)
+        if trace_info.trace_id:
+            trace_id = convert_string_to_id(trace_info.trace_id)
+
         tool_span = SpanData(
-            trace_id=convert_to_trace_id(message_id),
+            trace_id=trace_id,
             parent_span_id=convert_to_span_id(message_id, "message"),
             span_id=generate_span_id(),
             name=trace_info.tool_name,
@@ -451,8 +464,13 @@ class AliyunDataTrace(BaseTraceInstance):
         status: Status = Status(StatusCode.OK)
         if trace_info.error:
             status = Status(StatusCode.ERROR, trace_info.error)
+
+        trace_id = convert_to_trace_id(message_id)
+        if trace_info.trace_id:
+            trace_id = convert_string_to_id(trace_info.trace_id)
+
         suggested_question_span = SpanData(
-            trace_id=convert_to_trace_id(message_id),
+            trace_id=trace_id,
             parent_span_id=convert_to_span_id(message_id, "message"),
             span_id=convert_to_span_id(message_id, "suggested_question"),
             name="suggested_question",

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

@@ -181,15 +181,21 @@ def convert_to_trace_id(uuid_v4: Optional[str]) -> int:
         raise ValueError(f"Invalid UUID input: {e}")
 
 
+def convert_string_to_id(string: Optional[str]) -> int:
+    if not string:
+        return generate_span_id()
+    hash_bytes = hashlib.sha256(string.encode("utf-8")).digest()
+    id = int.from_bytes(hash_bytes[:8], byteorder="big", signed=False)
+    return id
+
+
 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
+    return convert_string_to_id(combined_key)
 
 
 def convert_datetime_to_nanoseconds(start_time_a: Optional[datetime]) -> Optional[int]:

api/core/ops/arize_phoenix_trace/arize_phoenix_trace.py

@@ -4,6 +4,7 @@ import logging
 import os
 from datetime import datetime, timedelta
 from typing import Any, Optional, Union, cast
+from urllib.parse import urlparse
 
 from openinference.semconv.trace import OpenInferenceSpanKindValues, SpanAttributes
 from opentelemetry import trace
@@ -40,8 +41,14 @@ def setup_tracer(arize_phoenix_config: ArizeConfig | PhoenixConfig) -> tuple[tra
     try:
         # Choose the appropriate exporter based on config type
         exporter: Union[GrpcOTLPSpanExporter, HttpOTLPSpanExporter]
+
+        # Inspect the provided endpoint to determine its structure
+        parsed = urlparse(arize_phoenix_config.endpoint)
+        base_endpoint = f"{parsed.scheme}://{parsed.netloc}"
+        path = parsed.path.rstrip("/")
+
         if isinstance(arize_phoenix_config, ArizeConfig):
-            arize_endpoint = f"{arize_phoenix_config.endpoint}/v1"
+            arize_endpoint = f"{base_endpoint}/v1"
             arize_headers = {
                 "api_key": arize_phoenix_config.api_key or "",
                 "space_id": arize_phoenix_config.space_id or "",
@@ -53,7 +60,7 @@ def setup_tracer(arize_phoenix_config: ArizeConfig | PhoenixConfig) -> tuple[tra
                 timeout=30,
             )
         else:
-            phoenix_endpoint = f"{arize_phoenix_config.endpoint}/v1/traces"
+            phoenix_endpoint = f"{base_endpoint}{path}/v1/traces"
             phoenix_headers = {
                 "api_key": arize_phoenix_config.api_key or "",
                 "authorization": f"Bearer {arize_phoenix_config.api_key or ''}",
@@ -91,16 +98,21 @@ def datetime_to_nanos(dt: Optional[datetime]) -> int:
     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)."""
+def string_to_trace_id128(string: Optional[str]) -> int:
+    """
+    Convert any input string into a stable 128-bit integer trace ID.
+
+    This uses SHA-256 hashing and takes the first 16 bytes (128 bits) of the digest.
+    It's suitable for generating consistent, unique identifiers from strings.
+    """
     if string is None:
         string = ""
     hash_object = hashlib.sha256(string.encode())
 
-    # Take the first 16 bytes (128 bits) of the hash
+    # Take the first 16 bytes (128 bits) of the hash digest
     digest = hash_object.digest()[:16]
 
-    # Convert to integer (128 bits)
+    # Convert to a 128-bit integer
     return int.from_bytes(digest, byteorder="big")
 
 
@@ -153,8 +165,7 @@ class ArizePhoenixDataTrace(BaseTraceInstance):
         }
         workflow_metadata.update(trace_info.metadata)
 
-        external_trace_id = trace_info.metadata.get("external_trace_id")
-        trace_id = external_trace_id or uuid_to_trace_id(trace_info.workflow_run_id)
+        trace_id = string_to_trace_id128(trace_info.trace_id or trace_info.workflow_run_id)
         span_id = RandomIdGenerator().generate_span_id()
         context = SpanContext(
             trace_id=trace_id,
@@ -310,7 +321,7 @@ class ArizePhoenixDataTrace(BaseTraceInstance):
             SpanAttributes.SESSION_ID: trace_info.message_data.conversation_id,
         }
 
-        trace_id = uuid_to_trace_id(trace_info.message_id)
+        trace_id = string_to_trace_id128(trace_info.trace_id or trace_info.message_id)
         message_span_id = RandomIdGenerator().generate_span_id()
         span_context = SpanContext(
             trace_id=trace_id,
@@ -406,7 +417,7 @@ class ArizePhoenixDataTrace(BaseTraceInstance):
         }
         metadata.update(trace_info.metadata)
 
-        trace_id = uuid_to_trace_id(trace_info.message_id)
+        trace_id = string_to_trace_id128(trace_info.message_id)
         span_id = RandomIdGenerator().generate_span_id()
         context = SpanContext(
             trace_id=trace_id,
@@ -468,7 +479,7 @@ class ArizePhoenixDataTrace(BaseTraceInstance):
         }
         metadata.update(trace_info.metadata)
 
-        trace_id = uuid_to_trace_id(trace_info.message_id)
+        trace_id = string_to_trace_id128(trace_info.message_id)
         span_id = RandomIdGenerator().generate_span_id()
         context = SpanContext(
             trace_id=trace_id,
@@ -521,7 +532,7 @@ class ArizePhoenixDataTrace(BaseTraceInstance):
         }
         metadata.update(trace_info.metadata)
 
-        trace_id = uuid_to_trace_id(trace_info.message_id)
+        trace_id = string_to_trace_id128(trace_info.message_id)
         span_id = RandomIdGenerator().generate_span_id()
         context = SpanContext(
             trace_id=trace_id,
@@ -568,7 +579,7 @@ class ArizePhoenixDataTrace(BaseTraceInstance):
             "tool_config": json.dumps(trace_info.tool_config, ensure_ascii=False),
         }
 
-        trace_id = uuid_to_trace_id(trace_info.message_id)
+        trace_id = string_to_trace_id128(trace_info.message_id)
         tool_span_id = RandomIdGenerator().generate_span_id()
         logger.info("[Arize/Phoenix] Creating tool trace with trace_id: %s, span_id: %s", trace_id, tool_span_id)
 
@@ -629,7 +640,7 @@ class ArizePhoenixDataTrace(BaseTraceInstance):
         }
         metadata.update(trace_info.metadata)
 
-        trace_id = uuid_to_trace_id(trace_info.message_id)
+        trace_id = string_to_trace_id128(trace_info.message_id)
         span_id = RandomIdGenerator().generate_span_id()
         context = SpanContext(
             trace_id=trace_id,

api/core/ops/entities/config_entity.py

@@ -87,7 +87,7 @@ class PhoenixConfig(BaseTracingConfig):
     @field_validator("endpoint")
     @classmethod
     def endpoint_validator(cls, v, info: ValidationInfo):
-        return cls.validate_endpoint_url(v, "https://app.phoenix.arize.com")
+        return validate_url_with_path(v, "https://app.phoenix.arize.com")
 
 
 class LangfuseConfig(BaseTracingConfig):

api/core/ops/entities/trace_entity.py

@@ -14,6 +14,7 @@ class BaseTraceInfo(BaseModel):
     start_time: Optional[datetime] = None
     end_time: Optional[datetime] = None
     metadata: dict[str, Any]
+    trace_id: Optional[str] = None
 
     @field_validator("inputs", "outputs")
     @classmethod

api/core/ops/langfuse_trace/langfuse_trace.py

@@ -67,14 +67,13 @@ class LangFuseDataTrace(BaseTraceInstance):
             self.generate_name_trace(trace_info)
 
     def workflow_trace(self, trace_info: WorkflowTraceInfo):
-        external_trace_id = trace_info.metadata.get("external_trace_id")
-        trace_id = external_trace_id or trace_info.workflow_run_id
+        trace_id = trace_info.trace_id or trace_info.workflow_run_id
         user_id = trace_info.metadata.get("user_id")
         metadata = trace_info.metadata
         metadata["workflow_app_log_id"] = trace_info.workflow_app_log_id
 
         if trace_info.message_id:
-            trace_id = external_trace_id or trace_info.message_id
+            trace_id = trace_info.trace_id or trace_info.message_id
             name = TraceTaskName.MESSAGE_TRACE.value
             trace_data = LangfuseTrace(
                 id=trace_id,
@@ -250,8 +249,10 @@ class LangFuseDataTrace(BaseTraceInstance):
                 user_id = end_user_data.session_id
                 metadata["user_id"] = user_id
 
+        trace_id = trace_info.trace_id or message_id
+
         trace_data = LangfuseTrace(
-            id=message_id,
+            id=trace_id,
             user_id=user_id,
             name=TraceTaskName.MESSAGE_TRACE.value,
             input={
@@ -285,7 +286,7 @@ class LangFuseDataTrace(BaseTraceInstance):
 
         langfuse_generation_data = LangfuseGeneration(
             name="llm",
-            trace_id=message_id,
+            trace_id=trace_id,
             start_time=trace_info.start_time,
             end_time=trace_info.end_time,
             model=message_data.model_id,
@@ -311,7 +312,7 @@ class LangFuseDataTrace(BaseTraceInstance):
                 "preset_response": trace_info.preset_response,
                 "inputs": trace_info.inputs,
             },
-            trace_id=trace_info.message_id,
+            trace_id=trace_info.trace_id or trace_info.message_id,
             start_time=trace_info.start_time or trace_info.message_data.created_at,
             end_time=trace_info.end_time or trace_info.message_data.created_at,
             metadata=trace_info.metadata,
@@ -334,7 +335,7 @@ class LangFuseDataTrace(BaseTraceInstance):
             name=TraceTaskName.SUGGESTED_QUESTION_TRACE.value,
             input=trace_info.inputs,
             output=str(trace_info.suggested_question),
-            trace_id=trace_info.message_id,
+            trace_id=trace_info.trace_id or trace_info.message_id,
             start_time=trace_info.start_time,
             end_time=trace_info.end_time,
             metadata=trace_info.metadata,
@@ -352,7 +353,7 @@ class LangFuseDataTrace(BaseTraceInstance):
             name=TraceTaskName.DATASET_RETRIEVAL_TRACE.value,
             input=trace_info.inputs,
             output={"documents": trace_info.documents},
-            trace_id=trace_info.message_id,
+            trace_id=trace_info.trace_id or trace_info.message_id,
             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=trace_info.metadata,
@@ -365,7 +366,7 @@ class LangFuseDataTrace(BaseTraceInstance):
             name=trace_info.tool_name,
             input=trace_info.tool_inputs,
             output=trace_info.tool_outputs,
-            trace_id=trace_info.message_id,
+            trace_id=trace_info.trace_id or trace_info.message_id,
             start_time=trace_info.start_time,
             end_time=trace_info.end_time,
             metadata=trace_info.metadata,

api/core/ops/langsmith_trace/langsmith_trace.py

@@ -65,8 +65,7 @@ class LangSmithDataTrace(BaseTraceInstance):
             self.generate_name_trace(trace_info)
 
     def workflow_trace(self, trace_info: WorkflowTraceInfo):
-        external_trace_id = trace_info.metadata.get("external_trace_id")
-        trace_id = external_trace_id or trace_info.message_id or trace_info.workflow_run_id
+        trace_id = trace_info.trace_id or trace_info.message_id or trace_info.workflow_run_id
         if trace_info.start_time is None:
             trace_info.start_time = datetime.now()
         message_dotted_order = (
@@ -290,7 +289,7 @@ class LangSmithDataTrace(BaseTraceInstance):
             reference_example_id=None,
             input_attachments={},
             output_attachments={},
-            trace_id=None,
+            trace_id=trace_info.trace_id,
             dotted_order=None,
             parent_run_id=None,
         )
@@ -319,7 +318,7 @@ class LangSmithDataTrace(BaseTraceInstance):
             reference_example_id=None,
             input_attachments={},
             output_attachments={},
-            trace_id=None,
+            trace_id=trace_info.trace_id,
             dotted_order=None,
             id=str(uuid.uuid4()),
         )
@@ -351,7 +350,7 @@ class LangSmithDataTrace(BaseTraceInstance):
             reference_example_id=None,
             input_attachments={},
             output_attachments={},
-            trace_id=None,
+            trace_id=trace_info.trace_id,
             dotted_order=None,
             error="",
             file_list=[],
@@ -381,7 +380,7 @@ class LangSmithDataTrace(BaseTraceInstance):
             reference_example_id=None,
             input_attachments={},
             output_attachments={},
-            trace_id=None,
+            trace_id=trace_info.trace_id,
             dotted_order=None,
             error="",
             file_list=[],
@@ -410,7 +409,7 @@ class LangSmithDataTrace(BaseTraceInstance):
             reference_example_id=None,
             input_attachments={},
             output_attachments={},
-            trace_id=None,
+            trace_id=trace_info.trace_id,
             dotted_order=None,
             error="",
             file_list=[],
@@ -440,7 +439,7 @@ class LangSmithDataTrace(BaseTraceInstance):
             reference_example_id=None,
             input_attachments={},
             output_attachments={},
-            trace_id=None,
+            trace_id=trace_info.trace_id,
             dotted_order=None,
             error=trace_info.error or "",
         )
@@ -465,7 +464,7 @@ class LangSmithDataTrace(BaseTraceInstance):
             reference_example_id=None,
             input_attachments={},
             output_attachments={},
-            trace_id=None,
+            trace_id=trace_info.trace_id,
             dotted_order=None,
             error="",
             file_list=[],

api/core/ops/opik_trace/opik_trace.py

@@ -96,8 +96,7 @@ class OpikDataTrace(BaseTraceInstance):
             self.generate_name_trace(trace_info)
 
     def workflow_trace(self, trace_info: WorkflowTraceInfo):
-        external_trace_id = trace_info.metadata.get("external_trace_id")
-        dify_trace_id = external_trace_id or trace_info.workflow_run_id
+        dify_trace_id = trace_info.trace_id or trace_info.workflow_run_id
         opik_trace_id = prepare_opik_uuid(trace_info.start_time, dify_trace_id)
         workflow_metadata = wrap_metadata(
             trace_info.metadata, message_id=trace_info.message_id, workflow_app_log_id=trace_info.workflow_app_log_id
@@ -105,7 +104,7 @@ class OpikDataTrace(BaseTraceInstance):
         root_span_id = None
 
         if trace_info.message_id:
-            dify_trace_id = external_trace_id or trace_info.message_id
+            dify_trace_id = trace_info.trace_id or trace_info.message_id
             opik_trace_id = prepare_opik_uuid(trace_info.start_time, dify_trace_id)
 
             trace_data = {
@@ -276,7 +275,7 @@ class OpikDataTrace(BaseTraceInstance):
             return
 
         metadata = trace_info.metadata
-        message_id = trace_info.message_id
+        dify_trace_id = trace_info.trace_id or trace_info.message_id
 
         user_id = message_data.from_account_id
         metadata["user_id"] = user_id
@@ -291,7 +290,7 @@ class OpikDataTrace(BaseTraceInstance):
                 metadata["end_user_id"] = end_user_id
 
         trace_data = {
-            "id": prepare_opik_uuid(trace_info.start_time, message_id),
+            "id": prepare_opik_uuid(trace_info.start_time, dify_trace_id),
             "name": TraceTaskName.MESSAGE_TRACE.value,
             "start_time": trace_info.start_time,
             "end_time": trace_info.end_time,
@@ -330,7 +329,7 @@ class OpikDataTrace(BaseTraceInstance):
         start_time = trace_info.start_time or trace_info.message_data.created_at
 
         span_data = {
-            "trace_id": prepare_opik_uuid(start_time, trace_info.message_id),
+            "trace_id": prepare_opik_uuid(start_time, trace_info.trace_id or trace_info.message_id),
             "name": TraceTaskName.MODERATION_TRACE.value,
             "type": "tool",
             "start_time": start_time,
@@ -356,7 +355,7 @@ class OpikDataTrace(BaseTraceInstance):
         start_time = trace_info.start_time or message_data.created_at
 
         span_data = {
-            "trace_id": prepare_opik_uuid(start_time, trace_info.message_id),
+            "trace_id": prepare_opik_uuid(start_time, trace_info.trace_id or trace_info.message_id),
             "name": TraceTaskName.SUGGESTED_QUESTION_TRACE.value,
             "type": "tool",
             "start_time": start_time,
@@ -376,7 +375,7 @@ class OpikDataTrace(BaseTraceInstance):
         start_time = trace_info.start_time or trace_info.message_data.created_at
 
         span_data = {
-            "trace_id": prepare_opik_uuid(start_time, trace_info.message_id),
+            "trace_id": prepare_opik_uuid(start_time, trace_info.trace_id or trace_info.message_id),
             "name": TraceTaskName.DATASET_RETRIEVAL_TRACE.value,
             "type": "tool",
             "start_time": start_time,
@@ -391,7 +390,7 @@ class OpikDataTrace(BaseTraceInstance):
 
     def tool_trace(self, trace_info: ToolTraceInfo):
         span_data = {
-            "trace_id": prepare_opik_uuid(trace_info.start_time, trace_info.message_id),
+            "trace_id": prepare_opik_uuid(trace_info.start_time, trace_info.trace_id or trace_info.message_id),
             "name": trace_info.tool_name,
             "type": "tool",
             "start_time": trace_info.start_time,
@@ -406,7 +405,7 @@ class OpikDataTrace(BaseTraceInstance):
 
     def generate_name_trace(self, trace_info: GenerateNameTraceInfo):
         trace_data = {
-            "id": prepare_opik_uuid(trace_info.start_time, trace_info.message_id),
+            "id": prepare_opik_uuid(trace_info.start_time, trace_info.trace_id or trace_info.message_id),
             "name": TraceTaskName.GENERATE_NAME_TRACE.value,
             "start_time": trace_info.start_time,
             "end_time": trace_info.end_time,

api/core/ops/ops_trace_manager.py

@@ -422,8 +422,11 @@ class TraceTask:
         self.timer = timer
         self.file_base_url = os.getenv("FILES_URL", "http://127.0.0.1:5001")
         self.app_id = None
-
+        self.trace_id = None
         self.kwargs = kwargs
+        external_trace_id = kwargs.get("external_trace_id")
+        if external_trace_id:
+            self.trace_id = external_trace_id
 
     def execute(self):
         return self.preprocess()
@@ -520,11 +523,8 @@ class TraceTask:
                 "app_id": workflow_run.app_id,
             }
 
-            external_trace_id = self.kwargs.get("external_trace_id")
-            if external_trace_id:
-                metadata["external_trace_id"] = external_trace_id
-
             workflow_trace_info = WorkflowTraceInfo(
+                trace_id=self.trace_id,
                 workflow_data=workflow_run.to_dict(),
                 conversation_id=conversation_id,
                 workflow_id=workflow_id,
@@ -584,6 +584,7 @@ class TraceTask:
         message_tokens = message_data.message_tokens
 
         message_trace_info = MessageTraceInfo(
+            trace_id=self.trace_id,
             message_id=message_id,
             message_data=message_data.to_dict(),
             conversation_model=conversation_mode,
@@ -627,6 +628,7 @@ class TraceTask:
             workflow_app_log_id = str(workflow_app_log_data.id) if workflow_app_log_data else None
 
         moderation_trace_info = ModerationTraceInfo(
+            trace_id=self.trace_id,
             message_id=workflow_app_log_id or message_id,
             inputs=inputs,
             message_data=message_data.to_dict(),
@@ -667,6 +669,7 @@ class TraceTask:
             workflow_app_log_id = str(workflow_app_log_data.id) if workflow_app_log_data else None
 
         suggested_question_trace_info = SuggestedQuestionTraceInfo(
+            trace_id=self.trace_id,
             message_id=workflow_app_log_id or message_id,
             message_data=message_data.to_dict(),
             inputs=message_data.message,
@@ -708,6 +711,7 @@ class TraceTask:
         }
 
         dataset_retrieval_trace_info = DatasetRetrievalTraceInfo(
+            trace_id=self.trace_id,
             message_id=message_id,
             inputs=message_data.query or message_data.inputs,
             documents=[doc.model_dump() for doc in documents] if documents else [],
@@ -772,6 +776,7 @@ class TraceTask:
             )
 
         tool_trace_info = ToolTraceInfo(
+            trace_id=self.trace_id,
             message_id=message_id,
             message_data=message_data.to_dict(),
             tool_name=tool_name,
@@ -807,6 +812,7 @@ class TraceTask:
         }
 
         generate_name_trace_info = GenerateNameTraceInfo(
+            trace_id=self.trace_id,
             conversation_id=conversation_id,
             inputs=inputs,
             outputs=generate_conversation_name,

api/core/ops/weave_trace/weave_trace.py

@@ -87,8 +87,7 @@ class WeaveDataTrace(BaseTraceInstance):
             self.generate_name_trace(trace_info)
 
     def workflow_trace(self, trace_info: WorkflowTraceInfo):
-        external_trace_id = trace_info.metadata.get("external_trace_id")
-        trace_id = external_trace_id or trace_info.message_id or trace_info.workflow_run_id
+        trace_id = trace_info.trace_id or trace_info.message_id or trace_info.workflow_run_id
         if trace_info.start_time is None:
             trace_info.start_time = datetime.now()
 
@@ -245,8 +244,12 @@ class WeaveDataTrace(BaseTraceInstance):
         attributes["start_time"] = trace_info.start_time
         attributes["end_time"] = trace_info.end_time
         attributes["tags"] = ["message", str(trace_info.conversation_mode)]
+
+        trace_id = trace_info.trace_id or message_id
+        attributes["trace_id"] = trace_id
+
         message_run = WeaveTraceModel(
-            id=message_id,
+            id=trace_id,
             op=str(TraceTaskName.MESSAGE_TRACE.value),
             input_tokens=trace_info.message_tokens,
             output_tokens=trace_info.answer_tokens,
@@ -274,7 +277,7 @@ class WeaveDataTrace(BaseTraceInstance):
         )
         self.start_call(
             llm_run,
-            parent_run_id=message_id,
+            parent_run_id=trace_id,
         )
         self.finish_call(llm_run)
         self.finish_call(message_run)
@@ -289,6 +292,9 @@ class WeaveDataTrace(BaseTraceInstance):
         attributes["start_time"] = trace_info.start_time or trace_info.message_data.created_at
         attributes["end_time"] = trace_info.end_time or trace_info.message_data.updated_at
 
+        trace_id = trace_info.trace_id or trace_info.message_id
+        attributes["trace_id"] = trace_id
+
         moderation_run = WeaveTraceModel(
             id=str(uuid.uuid4()),
             op=str(TraceTaskName.MODERATION_TRACE.value),
@@ -303,7 +309,7 @@ class WeaveDataTrace(BaseTraceInstance):
             exception=getattr(trace_info, "error", None),
             file_list=[],
         )
-        self.start_call(moderation_run, parent_run_id=trace_info.message_id)
+        self.start_call(moderation_run, parent_run_id=trace_id)
         self.finish_call(moderation_run)
 
     def suggested_question_trace(self, trace_info: SuggestedQuestionTraceInfo):
@@ -316,6 +322,9 @@ class WeaveDataTrace(BaseTraceInstance):
         attributes["start_time"] = (trace_info.start_time or message_data.created_at,)
         attributes["end_time"] = (trace_info.end_time or message_data.updated_at,)
 
+        trace_id = trace_info.trace_id or trace_info.message_id
+        attributes["trace_id"] = trace_id
+
         suggested_question_run = WeaveTraceModel(
             id=str(uuid.uuid4()),
             op=str(TraceTaskName.SUGGESTED_QUESTION_TRACE.value),
@@ -326,7 +335,7 @@ class WeaveDataTrace(BaseTraceInstance):
             file_list=[],
         )
 
-        self.start_call(suggested_question_run, parent_run_id=trace_info.message_id)
+        self.start_call(suggested_question_run, parent_run_id=trace_id)
         self.finish_call(suggested_question_run)
 
     def dataset_retrieval_trace(self, trace_info: DatasetRetrievalTraceInfo):
@@ -338,6 +347,9 @@ class WeaveDataTrace(BaseTraceInstance):
         attributes["start_time"] = (trace_info.start_time or trace_info.message_data.created_at,)
         attributes["end_time"] = (trace_info.end_time or trace_info.message_data.updated_at,)
 
+        trace_id = trace_info.trace_id or trace_info.message_id
+        attributes["trace_id"] = trace_id
+
         dataset_retrieval_run = WeaveTraceModel(
             id=str(uuid.uuid4()),
             op=str(TraceTaskName.DATASET_RETRIEVAL_TRACE.value),
@@ -348,7 +360,7 @@ class WeaveDataTrace(BaseTraceInstance):
             file_list=[],
         )
 
-        self.start_call(dataset_retrieval_run, parent_run_id=trace_info.message_id)
+        self.start_call(dataset_retrieval_run, parent_run_id=trace_id)
         self.finish_call(dataset_retrieval_run)
 
     def tool_trace(self, trace_info: ToolTraceInfo):
@@ -357,6 +369,11 @@ class WeaveDataTrace(BaseTraceInstance):
         attributes["start_time"] = trace_info.start_time
         attributes["end_time"] = trace_info.end_time
 
+        message_id = trace_info.message_id or getattr(trace_info, "conversation_id", None)
+        message_id = message_id or None
+        trace_id = trace_info.trace_id or message_id
+        attributes["trace_id"] = trace_id
+
         tool_run = WeaveTraceModel(
             id=str(uuid.uuid4()),
             op=trace_info.tool_name,
@@ -366,9 +383,7 @@ class WeaveDataTrace(BaseTraceInstance):
             attributes=attributes,
             exception=trace_info.error,
         )
-        message_id = trace_info.message_id or getattr(trace_info, "conversation_id", None)
-        message_id = message_id or None
-        self.start_call(tool_run, parent_run_id=message_id)
+        self.start_call(tool_run, parent_run_id=trace_id)
         self.finish_call(tool_run)
 
     def generate_name_trace(self, trace_info: GenerateNameTraceInfo):

api/core/rag/datasource/vdb/elasticsearch/elasticsearch_vector.py

@@ -22,22 +22,50 @@ logger = logging.getLogger(__name__)
 
 
 class ElasticSearchConfig(BaseModel):
-    host: str
-    port: int
-    username: str
-    password: str
+    # Regular Elasticsearch config
+    host: Optional[str] = None
+    port: Optional[int] = None
+    username: Optional[str] = None
+    password: Optional[str] = None
+
+    # Elastic Cloud specific config
+    cloud_url: Optional[str] = None  # Cloud URL for Elasticsearch Cloud
+    api_key: Optional[str] = None
+
+    # Common config
+    use_cloud: bool = False
+    ca_certs: Optional[str] = None
+    verify_certs: bool = False
+    request_timeout: int = 100000
+    retry_on_timeout: bool = True
+    max_retries: int = 10000
 
     @model_validator(mode="before")
     @classmethod
     def validate_config(cls, values: dict) -> dict:
-        if not values["host"]:
-            raise ValueError("config HOST is required")
-        if not values["port"]:
-            raise ValueError("config PORT is required")
-        if not values["username"]:
-            raise ValueError("config USERNAME is required")
-        if not values["password"]:
-            raise ValueError("config PASSWORD is required")
+        use_cloud = values.get("use_cloud", False)
+        cloud_url = values.get("cloud_url")
+
+        if use_cloud:
+            # Cloud configuration validation - requires cloud_url and api_key
+            if not cloud_url:
+                raise ValueError("cloud_url is required for Elastic Cloud")
+
+            api_key = values.get("api_key")
+            if not api_key:
+                raise ValueError("api_key is required for Elastic Cloud")
+
+        else:
+            # Regular Elasticsearch validation
+            if not values.get("host"):
+                raise ValueError("config HOST is required for regular Elasticsearch")
+            if not values.get("port"):
+                raise ValueError("config PORT is required for regular Elasticsearch")
+            if not values.get("username"):
+                raise ValueError("config USERNAME is required for regular Elasticsearch")
+            if not values.get("password"):
+                raise ValueError("config PASSWORD is required for regular Elasticsearch")
+
         return values
 
 
@@ -50,21 +78,69 @@ class ElasticSearchVector(BaseVector):
         self._attributes = attributes
 
     def _init_client(self, config: ElasticSearchConfig) -> Elasticsearch:
+        """
+        Initialize Elasticsearch client for both regular Elasticsearch and Elastic Cloud.
+        """
         try:
-            parsed_url = urlparse(config.host)
-            if parsed_url.scheme in {"http", "https"}:
-                hosts = f"{config.host}:{config.port}"
+            # Check if using Elastic Cloud
+            client_config: dict[str, Any]
+            if config.use_cloud and config.cloud_url:
+                client_config = {
+                    "request_timeout": config.request_timeout,
+                    "retry_on_timeout": config.retry_on_timeout,
+                    "max_retries": config.max_retries,
+                    "verify_certs": config.verify_certs,
+                }
+
+                # Parse cloud URL and configure hosts
+                parsed_url = urlparse(config.cloud_url)
+                host = f"{parsed_url.scheme}://{parsed_url.hostname}"
+                if parsed_url.port:
+                    host += f":{parsed_url.port}"
+
+                client_config["hosts"] = [host]
+
+                # API key authentication for cloud
+                client_config["api_key"] = config.api_key
+
+                # SSL settings
+                if config.ca_certs:
+                    client_config["ca_certs"] = config.ca_certs
+
             else:
-                hosts = f"http://{config.host}:{config.port}"
-            client = Elasticsearch(
-                hosts=hosts,
-                basic_auth=(config.username, config.password),
-                request_timeout=100000,
-                retry_on_timeout=True,
-                max_retries=10000,
-            )
-        except requests.exceptions.ConnectionError:
-            raise ConnectionError("Vector database connection error")
+                # Regular Elasticsearch configuration
+                parsed_url = urlparse(config.host or "")
+                if parsed_url.scheme in {"http", "https"}:
+                    hosts = f"{config.host}:{config.port}"
+                    use_https = parsed_url.scheme == "https"
+                else:
+                    hosts = f"http://{config.host}:{config.port}"
+                    use_https = False
+
+                client_config = {
+                    "hosts": [hosts],
+                    "basic_auth": (config.username, config.password),
+                    "request_timeout": config.request_timeout,
+                    "retry_on_timeout": config.retry_on_timeout,
+                    "max_retries": config.max_retries,
+                }
+
+                # Only add SSL settings if using HTTPS
+                if use_https:
+                    client_config["verify_certs"] = config.verify_certs
+                    if config.ca_certs:
+                        client_config["ca_certs"] = config.ca_certs
+
+            client = Elasticsearch(**client_config)
+
+            # Test connection
+            if not client.ping():
+                raise ConnectionError("Failed to connect to Elasticsearch")
+
+        except requests.exceptions.ConnectionError as e:
+            raise ConnectionError(f"Vector database connection error: {str(e)}")
+        except Exception as e:
+            raise ConnectionError(f"Elasticsearch client initialization failed: {str(e)}")
 
         return client
 
@@ -209,7 +285,11 @@ class ElasticSearchVector(BaseVector):
                         },
                     }
                 }
+
                 self._client.indices.create(index=self._collection_name, mappings=mappings)
+                logger.info("Created index %s with dimension %s", self._collection_name, dim)
+            else:
+                logger.info("Collection %s already exists.", self._collection_name)
 
             redis_client.set(collection_exist_cache_key, 1, ex=3600)
 
@@ -225,13 +305,51 @@ class ElasticSearchVectorFactory(AbstractVectorFactory):
             dataset.index_struct = json.dumps(self.gen_index_struct_dict(VectorType.ELASTICSEARCH, collection_name))
 
         config = current_app.config
+
+        # Check if ELASTICSEARCH_USE_CLOUD is explicitly set to false (boolean)
+        use_cloud_env = config.get("ELASTICSEARCH_USE_CLOUD", False)
+
+        if use_cloud_env is False:
+            # Use regular Elasticsearch with config values
+            config_dict = {
+                "use_cloud": False,
+                "host": config.get("ELASTICSEARCH_HOST", "elasticsearch"),
+                "port": config.get("ELASTICSEARCH_PORT", 9200),
+                "username": config.get("ELASTICSEARCH_USERNAME", "elastic"),
+                "password": config.get("ELASTICSEARCH_PASSWORD", "elastic"),
+            }
+        else:
+            # Check for cloud configuration
+            cloud_url = config.get("ELASTICSEARCH_CLOUD_URL")
+            if cloud_url:
+                config_dict = {
+                    "use_cloud": True,
+                    "cloud_url": cloud_url,
+                    "api_key": config.get("ELASTICSEARCH_API_KEY"),
+                }
+            else:
+                # Fallback to regular Elasticsearch
+                config_dict = {
+                    "use_cloud": False,
+                    "host": config.get("ELASTICSEARCH_HOST", "localhost"),
+                    "port": config.get("ELASTICSEARCH_PORT", 9200),
+                    "username": config.get("ELASTICSEARCH_USERNAME", "elastic"),
+                    "password": config.get("ELASTICSEARCH_PASSWORD", ""),
+                }
+
+        # Common configuration
+        config_dict.update(
+            {
+                "ca_certs": str(config.get("ELASTICSEARCH_CA_CERTS")) if config.get("ELASTICSEARCH_CA_CERTS") else None,
+                "verify_certs": bool(config.get("ELASTICSEARCH_VERIFY_CERTS", False)),
+                "request_timeout": int(config.get("ELASTICSEARCH_REQUEST_TIMEOUT", 100000)),
+                "retry_on_timeout": bool(config.get("ELASTICSEARCH_RETRY_ON_TIMEOUT", True)),
+                "max_retries": int(config.get("ELASTICSEARCH_MAX_RETRIES", 10000)),
+            }
+        )
+
         return ElasticSearchVector(
             index_name=collection_name,
-            config=ElasticSearchConfig(
-                host=config.get("ELASTICSEARCH_HOST", "localhost"),
-                port=config.get("ELASTICSEARCH_PORT", 9200),
-                username=config.get("ELASTICSEARCH_USERNAME", ""),
-                password=config.get("ELASTICSEARCH_PASSWORD", ""),
-            ),
+            config=ElasticSearchConfig(**config_dict),
             attributes=[],
         )

api/core/rag/entities/metadata_entities.py

@@ -13,6 +13,8 @@ SupportedComparisonOperator = Literal[
     "is not",
     "empty",
     "not empty",
+    "in",
+    "not in",
     # for number
     "=",
     "≠",

api/core/rag/extractor/notion_extractor.py

@@ -1,5 +1,6 @@
 import json
 import logging
+import operator
 from typing import Any, Optional, cast
 
 import requests
@@ -132,13 +133,15 @@ class NotionExtractor(BaseExtractor):
                     data[property_name] = value
                 row_dict = {k: v for k, v in data.items() if v}
                 row_content = ""
-                for key, value in row_dict.items():
+                for key, value in sorted(row_dict.items(), key=operator.itemgetter(0)):
                     if isinstance(value, dict):
                         value_dict = {k: v for k, v in value.items() if v}
                         value_content = "".join(f"{k}:{v} " for k, v in value_dict.items())
                         row_content = row_content + f"{key}:{value_content}\n"
                     else:
                         row_content = row_content + f"{key}:{value}\n"
+                if "url" in result:
+                    row_content = row_content + f"Row Page URL:{result.get('url', '')}\n"
                 database_content.append(row_content)
 
             has_more = response_data.get("has_more", False)

api/core/tools/workflow_as_tool/tool.py

@@ -142,7 +142,7 @@ class WorkflowTool(Tool):
         if not version:
             workflow = (
                 db.session.query(Workflow)
-                .where(Workflow.app_id == app_id, Workflow.version != "draft")
+                .where(Workflow.app_id == app_id, Workflow.version != Workflow.VERSION_DRAFT)
                 .order_by(Workflow.created_at.desc())
                 .first()
             )

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

@@ -265,9 +265,9 @@ class Executor:
             if not authorization.config.header:
                 authorization.config.header = "Authorization"
 
-            if self.auth.config.type == "bearer":
+            if self.auth.config.type == "bearer" and authorization.config.api_key:
                 headers[authorization.config.header] = f"Bearer {authorization.config.api_key}"
-            elif self.auth.config.type == "basic":
+            elif self.auth.config.type == "basic" and authorization.config.api_key:
                 credentials = authorization.config.api_key
                 if ":" in credentials:
                     encoded_credentials = base64.b64encode(credentials.encode("utf-8")).decode("utf-8")

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

@@ -74,6 +74,8 @@ SupportedComparisonOperator = Literal[
     "is not",
     "empty",
     "not empty",
+    "in",
+    "not in",
     # for number
     "=",
     "≠",

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

@@ -602,6 +602,28 @@ class KnowledgeRetrievalNode(BaseNode):
                         **{key: metadata_name, key_value: f"%{value}"}
                     )
                 )
+            case "in":
+                if isinstance(value, str):
+                    escaped_values = [v.strip().replace("'", "''") for v in str(value).split(",")]
+                    escaped_value_str = ",".join(escaped_values)
+                else:
+                    escaped_value_str = str(value)
+                filters.append(
+                    (text(f"documents.doc_metadata ->> :{key} = any(string_to_array(:{key_value},','))")).params(
+                        **{key: metadata_name, key_value: escaped_value_str}
+                    )
+                )
+            case "not in":
+                if isinstance(value, str):
+                    escaped_values = [v.strip().replace("'", "''") for v in str(value).split(",")]
+                    escaped_value_str = ",".join(escaped_values)
+                else:
+                    escaped_value_str = str(value)
+                filters.append(
+                    (text(f"documents.doc_metadata ->> :{key} != all(string_to_array(:{key_value},','))")).params(
+                        **{key: metadata_name, key_value: escaped_value_str}
+                    )
+                )
             case "=" | "is":
                 if isinstance(value, str):
                     filters.append(Document.doc_metadata[metadata_name] == f'"{value}"')

api/schedule/queue_monitor_task.py

@@ -1,8 +1,8 @@
 import logging
 from datetime import datetime
-from urllib.parse import urlparse
 
 import click
+from kombu.utils.url import parse_url  # type: ignore
 from redis import Redis
 
 import app
@@ -10,16 +10,13 @@ from configs import dify_config
 from extensions.ext_database import db
 from libs.email_i18n import EmailType, get_email_i18n_service
 
-# Create a dedicated Redis connection (using the same configuration as Celery)
-celery_broker_url = dify_config.CELERY_BROKER_URL
-
-parsed = urlparse(celery_broker_url)
-host = parsed.hostname or "localhost"
-port = parsed.port or 6379
-password = parsed.password or None
-redis_db = parsed.path.strip("/") or "1"  # type: ignore
-
-celery_redis = Redis(host=host, port=port, password=password, db=redis_db)
+redis_config = parse_url(dify_config.CELERY_BROKER_URL)
+celery_redis = Redis(
+    host=redis_config["hostname"],
+    port=redis_config["port"],
+    password=redis_config["password"],
+    db=int(redis_config["virtual_host"]) if redis_config["virtual_host"] else 1,
+)
 
 
 @app.celery.task(queue="monitor")

api/services/annotation_service.py

@@ -266,6 +266,54 @@ class AppAnnotationService:
                 annotation.id, app_id, current_user.current_tenant_id, app_annotation_setting.collection_binding_id
             )
 
+    @classmethod
+    def delete_app_annotations_in_batch(cls, app_id: str, annotation_ids: list[str]):
+        # get app info
+        app = (
+            db.session.query(App)
+            .where(App.id == app_id, App.tenant_id == current_user.current_tenant_id, App.status == "normal")
+            .first()
+        )
+
+        if not app:
+            raise NotFound("App not found")
+
+        # Fetch annotations and their settings in a single query
+        annotations_to_delete = (
+            db.session.query(MessageAnnotation, AppAnnotationSetting)
+            .outerjoin(AppAnnotationSetting, MessageAnnotation.app_id == AppAnnotationSetting.app_id)
+            .filter(MessageAnnotation.id.in_(annotation_ids))
+            .all()
+        )
+
+        if not annotations_to_delete:
+            return {"deleted_count": 0}
+
+        # Step 1: Extract IDs for bulk operations
+        annotation_ids_to_delete = [annotation.id for annotation, _ in annotations_to_delete]
+
+        # Step 2: Bulk delete hit histories in a single query
+        db.session.query(AppAnnotationHitHistory).filter(
+            AppAnnotationHitHistory.annotation_id.in_(annotation_ids_to_delete)
+        ).delete(synchronize_session=False)
+
+        # Step 3: Trigger async tasks for search index deletion
+        for annotation, annotation_setting in annotations_to_delete:
+            if annotation_setting:
+                delete_annotation_index_task.delay(
+                    annotation.id, app_id, current_user.current_tenant_id, annotation_setting.collection_binding_id
+                )
+
+        # Step 4: Bulk delete annotations in a single query
+        deleted_count = (
+            db.session.query(MessageAnnotation)
+            .filter(MessageAnnotation.id.in_(annotation_ids_to_delete))
+            .delete(synchronize_session=False)
+        )
+
+        db.session.commit()
+        return {"deleted_count": deleted_count}
+
     @classmethod
     def batch_import_app_annotations(cls, app_id, file: FileStorage) -> dict:
         # get app info
@@ -280,7 +328,7 @@ class AppAnnotationService:
 
         try:
             # Skip the first row
-            df = pd.read_csv(file)
+            df = pd.read_csv(file, dtype=str)
             result = []
             for index, row in df.iterrows():
                 content = {"question": row.iloc[0], "answer": row.iloc[1]}
@@ -452,6 +500,11 @@ class AppAnnotationService:
         if not app:
             raise NotFound("App not found")
 
+        # if annotation reply is enabled, delete annotation index
+        app_annotation_setting = (
+            db.session.query(AppAnnotationSetting).where(AppAnnotationSetting.app_id == app_id).first()
+        )
+
         annotations_query = db.session.query(MessageAnnotation).filter(MessageAnnotation.app_id == app_id)
         for annotation in annotations_query.yield_per(100):
             annotation_hit_histories_query = db.session.query(AppAnnotationHitHistory).filter(
@@ -460,6 +513,12 @@ class AppAnnotationService:
             for annotation_hit_history in annotation_hit_histories_query.yield_per(100):
                 db.session.delete(annotation_hit_history)
 
+            # if annotation reply is enabled, delete annotation index
+            if app_annotation_setting:
+                delete_annotation_index_task.delay(
+                    annotation.id, app_id, current_user.current_tenant_id, app_annotation_setting.collection_binding_id
+                )
+
             db.session.delete(annotation)
 
         db.session.commit()

api/services/external_knowledge_service.py

@@ -46,9 +46,9 @@ class ExternalDatasetService:
     def validate_api_list(cls, api_settings: dict):
         if not api_settings:
             raise ValueError("api list is empty")
-        if "endpoint" not in api_settings and not api_settings["endpoint"]:
+        if not api_settings.get("endpoint"):
             raise ValueError("endpoint is required")
-        if "api_key" not in api_settings and not api_settings["api_key"]:
+        if not api_settings.get("api_key"):
             raise ValueError("api_key is required")
 
     @staticmethod

api/services/workflow/workflow_converter.py

@@ -185,7 +185,7 @@ class WorkflowConverter:
             tenant_id=app_model.tenant_id,
             app_id=app_model.id,
             type=WorkflowType.from_app_mode(new_app_mode).value,
-            version="draft",
+            version=Workflow.VERSION_DRAFT,
             graph=json.dumps(graph),
             features=json.dumps(features),
             created_by=account_id,

api/services/workflow_service.py

@@ -105,7 +105,9 @@ class WorkflowService:
         workflow = (
             db.session.query(Workflow)
             .where(
-                Workflow.tenant_id == app_model.tenant_id, Workflow.app_id == app_model.id, Workflow.version == "draft"
+                Workflow.tenant_id == app_model.tenant_id,
+                Workflow.app_id == app_model.id,
+                Workflow.version == Workflow.VERSION_DRAFT,
             )
             .first()
         )
@@ -219,7 +221,7 @@ class WorkflowService:
                 tenant_id=app_model.tenant_id,
                 app_id=app_model.id,
                 type=WorkflowType.from_app_mode(app_model.mode).value,
-                version="draft",
+                version=Workflow.VERSION_DRAFT,
                 graph=json.dumps(graph),
                 features=json.dumps(features),
                 created_by=account.id,
@@ -257,7 +259,7 @@ class WorkflowService:
         draft_workflow_stmt = select(Workflow).where(
             Workflow.tenant_id == app_model.tenant_id,
             Workflow.app_id == app_model.id,
-            Workflow.version == "draft",
+            Workflow.version == Workflow.VERSION_DRAFT,
         )
         draft_workflow = session.scalar(draft_workflow_stmt)
         if not draft_workflow:
@@ -383,9 +385,9 @@ class WorkflowService:
             tenant_id=app_model.tenant_id,
         )
 
-        eclosing_node_type_and_id = draft_workflow.get_enclosing_node_type_and_id(node_config)
-        if eclosing_node_type_and_id:
-            _, enclosing_node_id = eclosing_node_type_and_id
+        enclosing_node_type_and_id = draft_workflow.get_enclosing_node_type_and_id(node_config)
+        if enclosing_node_type_and_id:
+            _, enclosing_node_id = enclosing_node_type_and_id
         else:
             enclosing_node_id = None
 
@@ -645,7 +647,7 @@ class WorkflowService:
             raise ValueError(f"Workflow with ID {workflow_id} not found")
 
         # Check if workflow is a draft version
-        if workflow.version == "draft":
+        if workflow.version == Workflow.VERSION_DRAFT:
             raise DraftWorkflowDeletionError("Cannot delete draft workflow versions")
 
         # Check if this workflow is currently referenced by an app

api/tasks/add_document_to_index_task.py

@@ -32,6 +32,7 @@ def add_document_to_index_task(dataset_document_id: str):
         return
 
     if dataset_document.indexing_status != "completed":
+        db.session.close()
         return
 
     indexing_cache_key = f"document_{dataset_document.id}_indexing"
@@ -112,3 +113,4 @@ def add_document_to_index_task(dataset_document_id: str):
         db.session.commit()
     finally:
         redis_client.delete(indexing_cache_key)
+        db.session.close()

api/tasks/create_segment_to_index_task.py

@@ -31,6 +31,7 @@ def create_segment_to_index_task(segment_id: str, keywords: Optional[list[str]]
         return
 
     if segment.status != "waiting":
+        db.session.close()
         return
 
     indexing_cache_key = f"segment_{segment.id}_indexing"

api/tasks/document_indexing_sync_task.py

@@ -113,3 +113,5 @@ def document_indexing_sync_task(dataset_id: str, document_id: str):
                 logging.info(click.style(str(ex), fg="yellow"))
             except Exception:
                 logging.exception("document_indexing_sync_task failed, document_id: %s", document_id)
+            finally:
+                db.session.close()

api/tasks/retry_document_indexing_task.py

@@ -95,8 +95,8 @@ def retry_document_indexing_task(dataset_id: str, document_ids: list[str]):
                 logging.info(click.style(str(ex), fg="yellow"))
                 redis_client.delete(retry_indexing_cache_key)
                 logging.exception("retry_document_indexing_task failed, document_id: %s", document_id)
-            end_at = time.perf_counter()
-            logging.info(click.style(f"Retry dataset: {dataset_id} latency: {end_at - start_at}", fg="green"))
+        end_at = time.perf_counter()
+        logging.info(click.style(f"Retry dataset: {dataset_id} latency: {end_at - start_at}", fg="green"))
     except Exception as e:
         logging.exception(
             "retry_document_indexing_task failed, dataset_id: %s, document_ids: %s", dataset_id, document_ids

api/tests/integration_tests/vdb/elasticsearch/test_elasticsearch.py

@@ -11,7 +11,9 @@ class ElasticSearchVectorTest(AbstractVectorTest):
         self.attributes = ["doc_id", "dataset_id", "document_id", "doc_hash"]
         self.vector = ElasticSearchVector(
             index_name=self.collection_name.lower(),
-            config=ElasticSearchConfig(host="http://localhost", port="9200", username="elastic", password="elastic"),
+            config=ElasticSearchConfig(
+                use_cloud=False, host="http://localhost", port="9200", username="elastic", password="elastic"
+            ),
             attributes=self.attributes,
         )
 

api/tests/unit_tests/configs/test_dify_config.py

@@ -1,5 +1,6 @@
 import os
 
+import pytest
 from flask import Flask
 from packaging.version import Version
 from yarl import URL
@@ -137,3 +138,61 @@ def test_db_extras_options_merging(monkeypatch):
     options = engine_options["connect_args"]["options"]
     assert "search_path=myschema" in options
     assert "timezone=UTC" in options
+
+
+@pytest.mark.parametrize(
+    ("broker_url", "expected_host", "expected_port", "expected_username", "expected_password", "expected_db"),
+    [
+        ("redis://localhost:6379/1", "localhost", 6379, None, None, "1"),
+        ("redis://:password@localhost:6379/1", "localhost", 6379, None, "password", "1"),
+        ("redis://:mypass%23123@localhost:6379/1", "localhost", 6379, None, "mypass#123", "1"),
+        ("redis://user:pass%40word@redis-host:6380/2", "redis-host", 6380, "user", "pass@word", "2"),
+        ("redis://admin:complex%23pass%40word@127.0.0.1:6379/0", "127.0.0.1", 6379, "admin", "complex#pass@word", "0"),
+        (
+            "redis://user%40domain:secret%23123@redis.example.com:6380/3",
+            "redis.example.com",
+            6380,
+            "user@domain",
+            "secret#123",
+            "3",
+        ),
+        # Password containing %23 substring (double encoding scenario)
+        ("redis://:mypass%2523@localhost:6379/1", "localhost", 6379, None, "mypass%23", "1"),
+        # Username and password both containing encoded characters
+        ("redis://user%2525%40:pass%2523@localhost:6379/1", "localhost", 6379, "user%25@", "pass%23", "1"),
+    ],
+)
+def test_celery_broker_url_with_special_chars_password(
+    monkeypatch, broker_url, expected_host, expected_port, expected_username, expected_password, expected_db
+):
+    """Test that CELERY_BROKER_URL with various formats are handled correctly."""
+    from kombu.utils.url import parse_url
+
+    # clear system environment variables
+    os.environ.clear()
+
+    # Set up basic required environment variables (following existing pattern)
+    monkeypatch.setenv("CONSOLE_API_URL", "https://example.com")
+    monkeypatch.setenv("CONSOLE_WEB_URL", "https://example.com")
+    monkeypatch.setenv("DB_USERNAME", "postgres")
+    monkeypatch.setenv("DB_PASSWORD", "postgres")
+    monkeypatch.setenv("DB_HOST", "localhost")
+    monkeypatch.setenv("DB_PORT", "5432")
+    monkeypatch.setenv("DB_DATABASE", "dify")
+
+    # Set the CELERY_BROKER_URL to test
+    monkeypatch.setenv("CELERY_BROKER_URL", broker_url)
+
+    # Create config and verify the URL is stored correctly
+    config = DifyConfig()
+    assert broker_url == config.CELERY_BROKER_URL
+
+    # Test actual parsing behavior using kombu's parse_url (same as production)
+    redis_config = parse_url(config.CELERY_BROKER_URL)
+
+    # Verify the parsing results match expectations (using kombu's field names)
+    assert redis_config["hostname"] == expected_host
+    assert redis_config["port"] == expected_port
+    assert redis_config["userid"] == expected_username  # kombu uses 'userid' not 'username'
+    assert redis_config["password"] == expected_password
+    assert redis_config["virtual_host"] == expected_db  # kombu uses 'virtual_host' not 'db'

api/tests/unit_tests/core/ops/test_config_entity.py

@@ -102,9 +102,14 @@ class TestPhoenixConfig:
         assert config.project == "default"
 
     def test_endpoint_validation_with_path(self):
-        """Test endpoint validation normalizes URL by removing path"""
-        config = PhoenixConfig(endpoint="https://custom.phoenix.com/api/v1")
-        assert config.endpoint == "https://custom.phoenix.com"
+        """Test endpoint validation with path"""
+        config = PhoenixConfig(endpoint="https://app.phoenix.arize.com/s/dify-integration")
+        assert config.endpoint == "https://app.phoenix.arize.com/s/dify-integration"
+
+    def test_endpoint_validation_without_path(self):
+        """Test endpoint validation without path"""
+        config = PhoenixConfig(endpoint="https://app.phoenix.arize.com")
+        assert config.endpoint == "https://app.phoenix.arize.com"
 
 
 class TestLangfuseConfig:
@@ -118,7 +123,7 @@ class TestLangfuseConfig:
         assert config.host == "https://custom.langfuse.com"
 
     def test_valid_config_with_path(self):
-        host = host = "https://custom.langfuse.com/api/v1"
+        host = "https://custom.langfuse.com/api/v1"
         config = LangfuseConfig(public_key="public_key", secret_key="secret_key", host=host)
         assert config.public_key == "public_key"
         assert config.secret_key == "secret_key"
@@ -368,13 +373,15 @@ class TestConfigIntegration:
         """Test that URL normalization works consistently across configs"""
         # Test that paths are removed from endpoints
         arize_config = ArizeConfig(endpoint="https://arize.com/api/v1/test")
-        phoenix_config = PhoenixConfig(endpoint="https://phoenix.com/api/v2/")
+        phoenix_with_path_config = PhoenixConfig(endpoint="https://app.phoenix.arize.com/s/dify-integration")
+        phoenix_without_path_config = PhoenixConfig(endpoint="https://app.phoenix.arize.com")
         aliyun_config = AliyunConfig(
             license_key="test_license", endpoint="https://tracing-analysis-dc-hz.aliyuncs.com/api/v1/traces"
         )
 
         assert arize_config.endpoint == "https://arize.com"
-        assert phoenix_config.endpoint == "https://phoenix.com"
+        assert phoenix_with_path_config.endpoint == "https://app.phoenix.arize.com/s/dify-integration"
+        assert phoenix_without_path_config.endpoint == "https://app.phoenix.arize.com"
         assert aliyun_config.endpoint == "https://tracing-analysis-dc-hz.aliyuncs.com"
 
     def test_project_default_values(self):

api/tests/unit_tests/services/test_metadata_bug_complete.py

@@ -0,0 +1,189 @@
+from unittest.mock import Mock, patch
+
+import pytest
+from flask_restful import reqparse
+from werkzeug.exceptions import BadRequest
+
+from services.entities.knowledge_entities.knowledge_entities import MetadataArgs
+from services.metadata_service import MetadataService
+
+
+class TestMetadataBugCompleteValidation:
+    """Complete test suite to verify the metadata nullable bug and its fix."""
+
+    def test_1_pydantic_layer_validation(self):
+        """Test Layer 1: Pydantic model validation correctly rejects None values."""
+        # Pydantic should reject None values for required fields
+        with pytest.raises((ValueError, TypeError)):
+            MetadataArgs(type=None, name=None)
+
+        with pytest.raises((ValueError, TypeError)):
+            MetadataArgs(type="string", name=None)
+
+        with pytest.raises((ValueError, TypeError)):
+            MetadataArgs(type=None, name="test")
+
+        # Valid values should work
+        valid_args = MetadataArgs(type="string", name="test_name")
+        assert valid_args.type == "string"
+        assert valid_args.name == "test_name"
+
+    def test_2_business_logic_layer_crashes_on_none(self):
+        """Test Layer 2: Business logic crashes when None values slip through."""
+        # Create mock that bypasses Pydantic validation
+        mock_metadata_args = Mock()
+        mock_metadata_args.name = None
+        mock_metadata_args.type = "string"
+
+        with patch("services.metadata_service.current_user") as mock_user:
+            mock_user.current_tenant_id = "tenant-123"
+            mock_user.id = "user-456"
+
+            # Should crash with TypeError
+            with pytest.raises(TypeError, match="object of type 'NoneType' has no len"):
+                MetadataService.create_metadata("dataset-123", mock_metadata_args)
+
+        # Test update method as well
+        with patch("services.metadata_service.current_user") as mock_user:
+            mock_user.current_tenant_id = "tenant-123"
+            mock_user.id = "user-456"
+
+            with pytest.raises(TypeError, match="object of type 'NoneType' has no len"):
+                MetadataService.update_metadata_name("dataset-123", "metadata-456", None)
+
+    def test_3_database_constraints_verification(self):
+        """Test Layer 3: Verify database model has nullable=False constraints."""
+        from sqlalchemy import inspect
+
+        from models.dataset import DatasetMetadata
+
+        # Get table info
+        mapper = inspect(DatasetMetadata)
+
+        # Check that type and name columns are not nullable
+        type_column = mapper.columns["type"]
+        name_column = mapper.columns["name"]
+
+        assert type_column.nullable is False, "type column should be nullable=False"
+        assert name_column.nullable is False, "name column should be nullable=False"
+
+    def test_4_fixed_api_layer_rejects_null(self, app):
+        """Test Layer 4: Fixed API configuration properly rejects null values."""
+        # Test Console API create endpoint (fixed)
+        parser = reqparse.RequestParser()
+        parser.add_argument("type", type=str, required=True, nullable=False, location="json")
+        parser.add_argument("name", type=str, required=True, nullable=False, location="json")
+
+        with app.test_request_context(json={"type": None, "name": None}, content_type="application/json"):
+            with pytest.raises(BadRequest):
+                parser.parse_args()
+
+        # Test with just name being null
+        with app.test_request_context(json={"type": "string", "name": None}, content_type="application/json"):
+            with pytest.raises(BadRequest):
+                parser.parse_args()
+
+        # Test with just type being null
+        with app.test_request_context(json={"type": None, "name": "test"}, content_type="application/json"):
+            with pytest.raises(BadRequest):
+                parser.parse_args()
+
+    def test_5_fixed_api_accepts_valid_values(self, app):
+        """Test that fixed API still accepts valid non-null values."""
+        parser = reqparse.RequestParser()
+        parser.add_argument("type", type=str, required=True, nullable=False, location="json")
+        parser.add_argument("name", type=str, required=True, nullable=False, location="json")
+
+        with app.test_request_context(json={"type": "string", "name": "valid_name"}, content_type="application/json"):
+            args = parser.parse_args()
+            assert args["type"] == "string"
+            assert args["name"] == "valid_name"
+
+    def test_6_simulated_buggy_behavior(self, app):
+        """Test simulating the original buggy behavior with nullable=True."""
+        # Simulate the old buggy configuration
+        buggy_parser = reqparse.RequestParser()
+        buggy_parser.add_argument("type", type=str, required=True, nullable=True, location="json")
+        buggy_parser.add_argument("name", type=str, required=True, nullable=True, location="json")
+
+        with app.test_request_context(json={"type": None, "name": None}, content_type="application/json"):
+            # This would pass in the buggy version
+            args = buggy_parser.parse_args()
+            assert args["type"] is None
+            assert args["name"] is None
+
+            # But would crash when trying to create MetadataArgs
+            with pytest.raises((ValueError, TypeError)):
+                MetadataArgs(**args)
+
+    def test_7_end_to_end_validation_layers(self):
+        """Test all validation layers work together correctly."""
+        # Layer 1: API should reject null at parameter level (with fix)
+        # Layer 2: Pydantic should reject null at model level
+        # Layer 3: Business logic expects non-null
+        # Layer 4: Database enforces non-null
+
+        # Test that valid data flows through all layers
+        valid_data = {"type": "string", "name": "test_metadata"}
+
+        # Should create valid Pydantic object
+        metadata_args = MetadataArgs(**valid_data)
+        assert metadata_args.type == "string"
+        assert metadata_args.name == "test_metadata"
+
+        # Should not crash in business logic length check
+        assert len(metadata_args.name) <= 255  # This should not crash
+        assert len(metadata_args.type) > 0  # This should not crash
+
+    def test_8_verify_specific_fix_locations(self):
+        """Verify that the specific locations mentioned in bug report are fixed."""
+        # Read the actual files to verify fixes
+        import os
+
+        # Console API create
+        console_create_file = "api/controllers/console/datasets/metadata.py"
+        if os.path.exists(console_create_file):
+            with open(console_create_file) as f:
+                content = f.read()
+                # Should contain nullable=False, not nullable=True
+                assert "nullable=True" not in content.split("class DatasetMetadataCreateApi")[1].split("class")[0]
+
+        # Service API create
+        service_create_file = "api/controllers/service_api/dataset/metadata.py"
+        if os.path.exists(service_create_file):
+            with open(service_create_file) as f:
+                content = f.read()
+                # Should contain nullable=False, not nullable=True
+                create_api_section = content.split("class DatasetMetadataCreateServiceApi")[1].split("class")[0]
+                assert "nullable=True" not in create_api_section
+
+
+class TestMetadataValidationSummary:
+    """Summary tests that demonstrate the complete validation architecture."""
+
+    def test_validation_layer_architecture(self):
+        """Document and test the 4-layer validation architecture."""
+        # Layer 1: API Parameter Validation (Flask-RESTful reqparse)
+        # - Role: First line of defense, validates HTTP request parameters
+        # - Fixed: nullable=False ensures null values are rejected at API boundary
+
+        # Layer 2: Pydantic Model Validation
+        # - Role: Validates data structure and types before business logic
+        # - Working: Required fields without Optional[] reject None values
+
+        # Layer 3: Business Logic Validation
+        # - Role: Domain-specific validation (length checks, uniqueness, etc.)
+        # - Vulnerable: Direct len() calls crash on None values
+
+        # Layer 4: Database Constraints
+        # - Role: Final data integrity enforcement
+        # - Working: nullable=False prevents None values in database
+
+        # The bug was: Layer 1 allowed None, but Layers 2-4 expected non-None
+        # The fix: Make Layer 1 consistent with Layers 2-4
+
+        assert True  # This test documents the architecture
+
+
+if __name__ == "__main__":
+    pytest.main([__file__, "-v"])

api/tests/unit_tests/services/test_metadata_nullable_bug.py

@@ -0,0 +1,108 @@
+from unittest.mock import Mock, patch
+
+import pytest
+from flask_restful import reqparse
+
+from services.entities.knowledge_entities.knowledge_entities import MetadataArgs
+from services.metadata_service import MetadataService
+
+
+class TestMetadataNullableBug:
+    """Test case to reproduce the metadata nullable validation bug."""
+
+    def test_metadata_args_with_none_values_should_fail(self):
+        """Test that MetadataArgs validation should reject None values."""
+        # This test demonstrates the expected behavior - should fail validation
+        with pytest.raises((ValueError, TypeError)):
+            # This should fail because Pydantic expects non-None values
+            MetadataArgs(type=None, name=None)
+
+    def test_metadata_service_create_with_none_name_crashes(self):
+        """Test that MetadataService.create_metadata crashes when name is None."""
+        # Mock the MetadataArgs to bypass Pydantic validation
+        mock_metadata_args = Mock()
+        mock_metadata_args.name = None  # This will cause len() to crash
+        mock_metadata_args.type = "string"
+
+        with patch("services.metadata_service.current_user") as mock_user:
+            mock_user.current_tenant_id = "tenant-123"
+            mock_user.id = "user-456"
+
+            # This should crash with TypeError when calling len(None)
+            with pytest.raises(TypeError, match="object of type 'NoneType' has no len"):
+                MetadataService.create_metadata("dataset-123", mock_metadata_args)
+
+    def test_metadata_service_update_with_none_name_crashes(self):
+        """Test that MetadataService.update_metadata_name crashes when name is None."""
+        with patch("services.metadata_service.current_user") as mock_user:
+            mock_user.current_tenant_id = "tenant-123"
+            mock_user.id = "user-456"
+
+            # This should crash with TypeError when calling len(None)
+            with pytest.raises(TypeError, match="object of type 'NoneType' has no len"):
+                MetadataService.update_metadata_name("dataset-123", "metadata-456", None)
+
+    def test_api_parser_accepts_null_values(self, app):
+        """Test that API parser configuration incorrectly accepts null values."""
+        # Simulate the current API parser configuration
+        parser = reqparse.RequestParser()
+        parser.add_argument("type", type=str, required=True, nullable=True, location="json")
+        parser.add_argument("name", type=str, required=True, nullable=True, location="json")
+
+        # Simulate request data with null values
+        with app.test_request_context(json={"type": None, "name": None}, content_type="application/json"):
+            # This should parse successfully due to nullable=True
+            args = parser.parse_args()
+
+            # Verify that null values are accepted
+            assert args["type"] is None
+            assert args["name"] is None
+
+            # This demonstrates the bug: API accepts None but business logic will crash
+
+    def test_integration_bug_scenario(self, app):
+        """Test the complete bug scenario from API to service layer."""
+        # Step 1: API parser accepts null values (current buggy behavior)
+        parser = reqparse.RequestParser()
+        parser.add_argument("type", type=str, required=True, nullable=True, location="json")
+        parser.add_argument("name", type=str, required=True, nullable=True, location="json")
+
+        with app.test_request_context(json={"type": None, "name": None}, content_type="application/json"):
+            args = parser.parse_args()
+
+            # Step 2: Try to create MetadataArgs with None values
+            # This should fail at Pydantic validation level
+            with pytest.raises((ValueError, TypeError)):
+                metadata_args = MetadataArgs(**args)
+
+        # Step 3: If we bypass Pydantic (simulating the bug scenario)
+        # Move this outside the request context to avoid Flask-Login issues
+        mock_metadata_args = Mock()
+        mock_metadata_args.name = None  # From args["name"]
+        mock_metadata_args.type = None  # From args["type"]
+
+        with patch("services.metadata_service.current_user") as mock_user:
+            mock_user.current_tenant_id = "tenant-123"
+            mock_user.id = "user-456"
+
+            # Step 4: Service layer crashes on len(None)
+            with pytest.raises(TypeError, match="object of type 'NoneType' has no len"):
+                MetadataService.create_metadata("dataset-123", mock_metadata_args)
+
+    def test_correct_nullable_false_configuration_works(self, app):
+        """Test that the correct nullable=False configuration works as expected."""
+        # This tests the FIXED configuration
+        parser = reqparse.RequestParser()
+        parser.add_argument("type", type=str, required=True, nullable=False, location="json")
+        parser.add_argument("name", type=str, required=True, nullable=False, location="json")
+
+        with app.test_request_context(json={"type": None, "name": None}, content_type="application/json"):
+            # This should fail with BadRequest due to nullable=False
+            from werkzeug.exceptions import BadRequest
+
+            with pytest.raises(BadRequest):
+                parser.parse_args()
+
+
+if __name__ == "__main__":
+    pytest.main([__file__, "-v"])

docker/.env.example

@@ -583,6 +583,17 @@ ELASTICSEARCH_USERNAME=elastic
 ELASTICSEARCH_PASSWORD=elastic
 KIBANA_PORT=5601
 
+# Using ElasticSearch Cloud Serverless, or not.
+ELASTICSEARCH_USE_CLOUD=false
+ELASTICSEARCH_CLOUD_URL=YOUR-ELASTICSEARCH_CLOUD_URL
+ELASTICSEARCH_API_KEY=YOUR-ELASTICSEARCH_API_KEY
+
+ELASTICSEARCH_VERIFY_CERTS=False
+ELASTICSEARCH_CA_CERTS=
+ELASTICSEARCH_REQUEST_TIMEOUT=100000
+ELASTICSEARCH_RETRY_ON_TIMEOUT=True
+ELASTICSEARCH_MAX_RETRIES=10
+
 # baidu vector configurations, only available when VECTOR_STORE is `baidu`
 BAIDU_VECTOR_DB_ENDPOINT=http://127.0.0.1:5287
 BAIDU_VECTOR_DB_CONNECTION_TIMEOUT_MS=30000

docker/docker-compose.yaml

@@ -261,6 +261,14 @@ x-shared-env: &shared-api-worker-env
   ELASTICSEARCH_USERNAME: ${ELASTICSEARCH_USERNAME:-elastic}
   ELASTICSEARCH_PASSWORD: ${ELASTICSEARCH_PASSWORD:-elastic}
   KIBANA_PORT: ${KIBANA_PORT:-5601}
+  ELASTICSEARCH_USE_CLOUD: ${ELASTICSEARCH_USE_CLOUD:-false}
+  ELASTICSEARCH_CLOUD_URL: ${ELASTICSEARCH_CLOUD_URL:-YOUR-ELASTICSEARCH_CLOUD_URL}
+  ELASTICSEARCH_API_KEY: ${ELASTICSEARCH_API_KEY:-YOUR-ELASTICSEARCH_API_KEY}
+  ELASTICSEARCH_VERIFY_CERTS: ${ELASTICSEARCH_VERIFY_CERTS:-False}
+  ELASTICSEARCH_CA_CERTS: ${ELASTICSEARCH_CA_CERTS:-}
+  ELASTICSEARCH_REQUEST_TIMEOUT: ${ELASTICSEARCH_REQUEST_TIMEOUT:-100000}
+  ELASTICSEARCH_RETRY_ON_TIMEOUT: ${ELASTICSEARCH_RETRY_ON_TIMEOUT:-True}
+  ELASTICSEARCH_MAX_RETRIES: ${ELASTICSEARCH_MAX_RETRIES:-10}
   BAIDU_VECTOR_DB_ENDPOINT: ${BAIDU_VECTOR_DB_ENDPOINT:-http://127.0.0.1:5287}
   BAIDU_VECTOR_DB_CONNECTION_TIMEOUT_MS: ${BAIDU_VECTOR_DB_CONNECTION_TIMEOUT_MS:-30000}
   BAIDU_VECTOR_DB_ACCOUNT: ${BAIDU_VECTOR_DB_ACCOUNT:-root}

web/__tests__/check-i18n.test.ts

@@ -0,0 +1,566 @@
+import fs from 'node:fs'
+import path from 'node:path'
+
+// Mock functions to simulate the check-i18n functionality
+const vm = require('node:vm')
+const transpile = require('typescript').transpile
+
+describe('check-i18n script functionality', () => {
+  const testDir = path.join(__dirname, '../i18n-test')
+  const testEnDir = path.join(testDir, 'en-US')
+  const testZhDir = path.join(testDir, 'zh-Hans')
+
+  // Helper function that replicates the getKeysFromLanguage logic
+  async function getKeysFromLanguage(language: string, testPath = testDir): Promise<string[]> {
+    return new Promise((resolve, reject) => {
+      const folderPath = path.resolve(testPath, language)
+      const allKeys: string[] = []
+
+      if (!fs.existsSync(folderPath)) {
+        resolve([])
+        return
+      }
+
+      fs.readdir(folderPath, (err, files) => {
+        if (err) {
+          reject(err)
+          return
+        }
+
+        const translationFiles = files.filter(file => /\.(ts|js)$/.test(file))
+
+        translationFiles.forEach((file) => {
+          const filePath = path.join(folderPath, file)
+          const fileName = file.replace(/\.[^/.]+$/, '')
+          const camelCaseFileName = fileName.replace(/[-_](.)/g, (_, c) =>
+            c.toUpperCase(),
+          )
+
+          try {
+            const content = fs.readFileSync(filePath, 'utf8')
+            const moduleExports = {}
+            const context = {
+              exports: moduleExports,
+              module: { exports: moduleExports },
+              require,
+              console,
+              __filename: filePath,
+              __dirname: folderPath,
+            }
+
+            vm.runInNewContext(transpile(content), context)
+            const translationObj = (context.module.exports as any).default || context.module.exports
+
+            if (!translationObj || typeof translationObj !== 'object')
+              throw new Error(`Error parsing file: ${filePath}`)
+
+            const nestedKeys: string[] = []
+            const iterateKeys = (obj: any, prefix = '') => {
+              for (const key in obj) {
+                const nestedKey = prefix ? `${prefix}.${key}` : key
+                if (typeof obj[key] === 'object' && obj[key] !== null && !Array.isArray(obj[key])) {
+                  // This is an object (but not array), recurse into it but don't add it as a key
+                  iterateKeys(obj[key], nestedKey)
+                }
+                else {
+                  // This is a leaf node (string, number, boolean, array, etc.), add it as a key
+                  nestedKeys.push(nestedKey)
+                }
+              }
+            }
+            iterateKeys(translationObj)
+
+            const fileKeys = nestedKeys.map(key => `${camelCaseFileName}.${key}`)
+            allKeys.push(...fileKeys)
+          }
+          catch (error) {
+            reject(error)
+          }
+        })
+        resolve(allKeys)
+      })
+    })
+  }
+
+  beforeEach(() => {
+    // Clean up and create test directories
+    if (fs.existsSync(testDir))
+      fs.rmSync(testDir, { recursive: true })
+
+    fs.mkdirSync(testDir, { recursive: true })
+    fs.mkdirSync(testEnDir, { recursive: true })
+    fs.mkdirSync(testZhDir, { recursive: true })
+  })
+
+  afterEach(() => {
+    // Clean up test files
+    if (fs.existsSync(testDir))
+      fs.rmSync(testDir, { recursive: true })
+  })
+
+  describe('Key extraction logic', () => {
+    it('should extract only leaf node keys, not intermediate objects', async () => {
+      const testContent = `const translation = {
+  simple: 'Simple Value',
+  nested: {
+    level1: 'Level 1 Value',
+    deep: {
+      level2: 'Level 2 Value'
+    }
+  },
+  array: ['not extracted'],
+  number: 42,
+  boolean: true
+}
+
+export default translation
+`
+
+      fs.writeFileSync(path.join(testEnDir, 'test.ts'), testContent)
+
+      const keys = await getKeysFromLanguage('en-US')
+
+      expect(keys).toEqual([
+        'test.simple',
+        'test.nested.level1',
+        'test.nested.deep.level2',
+        'test.array',
+        'test.number',
+        'test.boolean',
+      ])
+
+      // Should not include intermediate object keys
+      expect(keys).not.toContain('test.nested')
+      expect(keys).not.toContain('test.nested.deep')
+    })
+
+    it('should handle camelCase file name conversion correctly', async () => {
+      const testContent = `const translation = {
+  key: 'value'
+}
+
+export default translation
+`
+
+      fs.writeFileSync(path.join(testEnDir, 'app-debug.ts'), testContent)
+      fs.writeFileSync(path.join(testEnDir, 'user_profile.ts'), testContent)
+
+      const keys = await getKeysFromLanguage('en-US')
+
+      expect(keys).toContain('appDebug.key')
+      expect(keys).toContain('userProfile.key')
+    })
+  })
+
+  describe('Missing keys detection', () => {
+    it('should detect missing keys in target language', async () => {
+      const enContent = `const translation = {
+  common: {
+    save: 'Save',
+    cancel: 'Cancel',
+    delete: 'Delete'
+  },
+  app: {
+    title: 'My App',
+    version: '1.0'
+  }
+}
+
+export default translation
+`
+
+      const zhContent = `const translation = {
+  common: {
+    save: '保存',
+    cancel: '取消'
+    // missing 'delete'
+  },
+  app: {
+    title: '我的应用'
+    // missing 'version'
+  }
+}
+
+export default translation
+`
+
+      fs.writeFileSync(path.join(testEnDir, 'test.ts'), enContent)
+      fs.writeFileSync(path.join(testZhDir, 'test.ts'), zhContent)
+
+      const enKeys = await getKeysFromLanguage('en-US')
+      const zhKeys = await getKeysFromLanguage('zh-Hans')
+
+      const missingKeys = enKeys.filter(key => !zhKeys.includes(key))
+
+      expect(missingKeys).toContain('test.common.delete')
+      expect(missingKeys).toContain('test.app.version')
+      expect(missingKeys).toHaveLength(2)
+    })
+  })
+
+  describe('Extra keys detection', () => {
+    it('should detect extra keys in target language', async () => {
+      const enContent = `const translation = {
+  common: {
+    save: 'Save',
+    cancel: 'Cancel'
+  }
+}
+
+export default translation
+`
+
+      const zhContent = `const translation = {
+  common: {
+    save: '保存',
+    cancel: '取消',
+    delete: '删除', // extra key
+    extra: '额外的' // another extra key
+  },
+  newSection: {
+    someKey: '某个值' // extra section
+  }
+}
+
+export default translation
+`
+
+      fs.writeFileSync(path.join(testEnDir, 'test.ts'), enContent)
+      fs.writeFileSync(path.join(testZhDir, 'test.ts'), zhContent)
+
+      const enKeys = await getKeysFromLanguage('en-US')
+      const zhKeys = await getKeysFromLanguage('zh-Hans')
+
+      const extraKeys = zhKeys.filter(key => !enKeys.includes(key))
+
+      expect(extraKeys).toContain('test.common.delete')
+      expect(extraKeys).toContain('test.common.extra')
+      expect(extraKeys).toContain('test.newSection.someKey')
+      expect(extraKeys).toHaveLength(3)
+    })
+  })
+
+  describe('File filtering logic', () => {
+    it('should filter keys by specific file correctly', async () => {
+      // Create multiple files
+      const file1Content = `const translation = {
+  button: 'Button',
+  text: 'Text'
+}
+
+export default translation
+`
+
+      const file2Content = `const translation = {
+  title: 'Title',
+  description: 'Description'
+}
+
+export default translation
+`
+
+      fs.writeFileSync(path.join(testEnDir, 'components.ts'), file1Content)
+      fs.writeFileSync(path.join(testEnDir, 'pages.ts'), file2Content)
+      fs.writeFileSync(path.join(testZhDir, 'components.ts'), file1Content)
+      fs.writeFileSync(path.join(testZhDir, 'pages.ts'), file2Content)
+
+      const allEnKeys = await getKeysFromLanguage('en-US')
+      const allZhKeys = await getKeysFromLanguage('zh-Hans')
+
+      // Test file filtering logic
+      const targetFile = 'components'
+      const filteredEnKeys = allEnKeys.filter(key =>
+        key.startsWith(targetFile.replace(/[-_](.)/g, (_, c) => c.toUpperCase())),
+      )
+
+      expect(allEnKeys).toHaveLength(4) // 2 keys from each file
+      expect(filteredEnKeys).toHaveLength(2) // only components keys
+      expect(filteredEnKeys).toContain('components.button')
+      expect(filteredEnKeys).toContain('components.text')
+      expect(filteredEnKeys).not.toContain('pages.title')
+      expect(filteredEnKeys).not.toContain('pages.description')
+    })
+  })
+
+  describe('Complex nested structure handling', () => {
+    it('should handle deeply nested objects correctly', async () => {
+      const complexContent = `const translation = {
+  level1: {
+    level2: {
+      level3: {
+        level4: {
+          deepValue: 'Deep Value'
+        },
+        anotherValue: 'Another Value'
+      },
+      simpleValue: 'Simple Value'
+    },
+    directValue: 'Direct Value'
+  },
+  rootValue: 'Root Value'
+}
+
+export default translation
+`
+
+      fs.writeFileSync(path.join(testEnDir, 'complex.ts'), complexContent)
+
+      const keys = await getKeysFromLanguage('en-US')
+
+      expect(keys).toContain('complex.level1.level2.level3.level4.deepValue')
+      expect(keys).toContain('complex.level1.level2.level3.anotherValue')
+      expect(keys).toContain('complex.level1.level2.simpleValue')
+      expect(keys).toContain('complex.level1.directValue')
+      expect(keys).toContain('complex.rootValue')
+
+      // Should not include intermediate objects
+      expect(keys).not.toContain('complex.level1')
+      expect(keys).not.toContain('complex.level1.level2')
+      expect(keys).not.toContain('complex.level1.level2.level3')
+      expect(keys).not.toContain('complex.level1.level2.level3.level4')
+    })
+  })
+
+  describe('Edge cases', () => {
+    it('should handle empty objects', async () => {
+      const emptyContent = `const translation = {
+  empty: {},
+  withValue: 'value'
+}
+
+export default translation
+`
+
+      fs.writeFileSync(path.join(testEnDir, 'empty.ts'), emptyContent)
+
+      const keys = await getKeysFromLanguage('en-US')
+
+      expect(keys).toContain('empty.withValue')
+      expect(keys).not.toContain('empty.empty')
+    })
+
+    it('should handle special characters in keys', async () => {
+      const specialContent = `const translation = {
+  'key-with-dash': 'value1',
+  'key_with_underscore': 'value2',
+  'key.with.dots': 'value3',
+  normalKey: 'value4'
+}
+
+export default translation
+`
+
+      fs.writeFileSync(path.join(testEnDir, 'special.ts'), specialContent)
+
+      const keys = await getKeysFromLanguage('en-US')
+
+      expect(keys).toContain('special.key-with-dash')
+      expect(keys).toContain('special.key_with_underscore')
+      expect(keys).toContain('special.key.with.dots')
+      expect(keys).toContain('special.normalKey')
+    })
+
+    it('should handle different value types', async () => {
+      const typesContent = `const translation = {
+  stringValue: 'string',
+  numberValue: 42,
+  booleanValue: true,
+  nullValue: null,
+  undefinedValue: undefined,
+  arrayValue: ['array', 'values'],
+  objectValue: {
+    nested: 'nested value'
+  }
+}
+
+export default translation
+`
+
+      fs.writeFileSync(path.join(testEnDir, 'types.ts'), typesContent)
+
+      const keys = await getKeysFromLanguage('en-US')
+
+      expect(keys).toContain('types.stringValue')
+      expect(keys).toContain('types.numberValue')
+      expect(keys).toContain('types.booleanValue')
+      expect(keys).toContain('types.nullValue')
+      expect(keys).toContain('types.undefinedValue')
+      expect(keys).toContain('types.arrayValue')
+      expect(keys).toContain('types.objectValue.nested')
+      expect(keys).not.toContain('types.objectValue')
+    })
+  })
+
+  describe('Real-world scenario tests', () => {
+    it('should handle app-debug structure like real files', async () => {
+      const appDebugEn = `const translation = {
+  pageTitle: {
+    line1: 'Prompt',
+    line2: 'Engineering'
+  },
+  operation: {
+    applyConfig: 'Publish',
+    resetConfig: 'Reset',
+    debugConfig: 'Debug'
+  },
+  generate: {
+    instruction: 'Instructions',
+    generate: 'Generate',
+    resTitle: 'Generated Prompt',
+    noDataLine1: 'Describe your use case on the left,',
+    noDataLine2: 'the orchestration preview will show here.'
+  }
+}
+
+export default translation
+`
+
+      const appDebugZh = `const translation = {
+  pageTitle: {
+    line1: '提示词',
+    line2: '编排'
+  },
+  operation: {
+    applyConfig: '发布',
+    resetConfig: '重置',
+    debugConfig: '调试'
+  },
+  generate: {
+    instruction: '指令',
+    generate: '生成',
+    resTitle: '生成的提示词',
+    noData: '在左侧描述您的用例，编排预览将在此处显示。' // This is extra
+  }
+}
+
+export default translation
+`
+
+      fs.writeFileSync(path.join(testEnDir, 'app-debug.ts'), appDebugEn)
+      fs.writeFileSync(path.join(testZhDir, 'app-debug.ts'), appDebugZh)
+
+      const enKeys = await getKeysFromLanguage('en-US')
+      const zhKeys = await getKeysFromLanguage('zh-Hans')
+
+      const missingKeys = enKeys.filter(key => !zhKeys.includes(key))
+      const extraKeys = zhKeys.filter(key => !enKeys.includes(key))
+
+      expect(missingKeys).toContain('appDebug.generate.noDataLine1')
+      expect(missingKeys).toContain('appDebug.generate.noDataLine2')
+      expect(extraKeys).toContain('appDebug.generate.noData')
+
+      expect(missingKeys).toHaveLength(2)
+      expect(extraKeys).toHaveLength(1)
+    })
+
+    it('should handle time structure with operation nested keys', async () => {
+      const timeEn = `const translation = {
+  months: {
+    January: 'January',
+    February: 'February'
+  },
+  operation: {
+    now: 'Now',
+    ok: 'OK',
+    cancel: 'Cancel',
+    pickDate: 'Pick Date'
+  },
+  title: {
+    pickTime: 'Pick Time'
+  },
+  defaultPlaceholder: 'Pick a time...'
+}
+
+export default translation
+`
+
+      const timeZh = `const translation = {
+  months: {
+    January: '一月',
+    February: '二月'
+  },
+  operation: {
+    now: '此刻',
+    ok: '确定',
+    cancel: '取消',
+    pickDate: '选择日期'
+  },
+  title: {
+    pickTime: '选择时间'
+  },
+  pickDate: '选择日期', // This is extra - duplicates operation.pickDate
+  defaultPlaceholder: '请选择时间...'
+}
+
+export default translation
+`
+
+      fs.writeFileSync(path.join(testEnDir, 'time.ts'), timeEn)
+      fs.writeFileSync(path.join(testZhDir, 'time.ts'), timeZh)
+
+      const enKeys = await getKeysFromLanguage('en-US')
+      const zhKeys = await getKeysFromLanguage('zh-Hans')
+
+      const missingKeys = enKeys.filter(key => !zhKeys.includes(key))
+      const extraKeys = zhKeys.filter(key => !enKeys.includes(key))
+
+      expect(missingKeys).toHaveLength(0) // No missing keys
+      expect(extraKeys).toContain('time.pickDate') // Extra root-level pickDate
+      expect(extraKeys).toHaveLength(1)
+
+      // Should have both keys available
+      expect(zhKeys).toContain('time.operation.pickDate') // Correct nested key
+      expect(zhKeys).toContain('time.pickDate') // Extra duplicate key
+    })
+  })
+
+  describe('Statistics calculation', () => {
+    it('should calculate correct difference statistics', async () => {
+      const enContent = `const translation = {
+  key1: 'value1',
+  key2: 'value2',
+  key3: 'value3'
+}
+
+export default translation
+`
+
+      const zhContentMissing = `const translation = {
+  key1: 'value1',
+  key2: 'value2'
+  // missing key3
+}
+
+export default translation
+`
+
+      const zhContentExtra = `const translation = {
+  key1: 'value1',
+  key2: 'value2', 
+  key3: 'value3',
+  key4: 'extra',
+  key5: 'extra2'
+}
+
+export default translation
+`
+
+      fs.writeFileSync(path.join(testEnDir, 'stats.ts'), enContent)
+
+      // Test missing keys scenario
+      fs.writeFileSync(path.join(testZhDir, 'stats.ts'), zhContentMissing)
+
+      const enKeys = await getKeysFromLanguage('en-US')
+      const zhKeysMissing = await getKeysFromLanguage('zh-Hans')
+
+      expect(enKeys.length - zhKeysMissing.length).toBe(1) // +1 means 1 missing key
+
+      // Test extra keys scenario
+      fs.writeFileSync(path.join(testZhDir, 'stats.ts'), zhContentExtra)
+
+      const zhKeysExtra = await getKeysFromLanguage('zh-Hans')
+
+      expect(enKeys.length - zhKeysExtra.length).toBe(-2) // -2 means 2 extra keys
+    })
+  })
+})

web/__tests__/plugin-tool-workflow-error.test.tsx

@@ -0,0 +1,207 @@
+/**
+ * Test cases to reproduce the plugin tool workflow error
+ * Issue: #23154 - Application error when loading plugin tools in workflow
+ * Root cause: split() operation called on null/undefined values
+ */
+
+describe('Plugin Tool Workflow Error Reproduction', () => {
+  /**
+   * Mock function to simulate the problematic code in switch-plugin-version.tsx:29
+   * const [pluginId] = uniqueIdentifier.split(':')
+   */
+  const mockSwitchPluginVersionLogic = (uniqueIdentifier: string | null | undefined) => {
+    // This directly reproduces the problematic line from switch-plugin-version.tsx:29
+    const [pluginId] = uniqueIdentifier!.split(':')
+    return pluginId
+  }
+
+  /**
+   * Test case 1: Simulate null uniqueIdentifier
+   * This should reproduce the error mentioned in the issue
+   */
+  it('should reproduce error when uniqueIdentifier is null', () => {
+    expect(() => {
+      mockSwitchPluginVersionLogic(null)
+    }).toThrow('Cannot read properties of null (reading \'split\')')
+  })
+
+  /**
+   * Test case 2: Simulate undefined uniqueIdentifier
+   */
+  it('should reproduce error when uniqueIdentifier is undefined', () => {
+    expect(() => {
+      mockSwitchPluginVersionLogic(undefined)
+    }).toThrow('Cannot read properties of undefined (reading \'split\')')
+  })
+
+  /**
+   * Test case 3: Simulate empty string uniqueIdentifier
+   */
+  it('should handle empty string uniqueIdentifier', () => {
+    expect(() => {
+      const result = mockSwitchPluginVersionLogic('')
+      expect(result).toBe('') // Empty string split by ':' returns ['']
+    }).not.toThrow()
+  })
+
+  /**
+   * Test case 4: Simulate malformed uniqueIdentifier without colon separator
+   */
+  it('should handle malformed uniqueIdentifier without colon separator', () => {
+    expect(() => {
+      const result = mockSwitchPluginVersionLogic('malformed-identifier-without-colon')
+      expect(result).toBe('malformed-identifier-without-colon') // No colon means full string returned
+    }).not.toThrow()
+  })
+
+  /**
+   * Test case 5: Simulate valid uniqueIdentifier
+   */
+  it('should work correctly with valid uniqueIdentifier', () => {
+    expect(() => {
+      const result = mockSwitchPluginVersionLogic('valid-plugin-id:1.0.0')
+      expect(result).toBe('valid-plugin-id')
+    }).not.toThrow()
+  })
+})
+
+/**
+ * Test for the variable processing split error in use-single-run-form-params
+ */
+describe('Variable Processing Split Error', () => {
+  /**
+   * Mock function to simulate the problematic code in use-single-run-form-params.ts:91
+   * const getDependentVars = () => {
+   *   return varInputs.map(item => item.variable.slice(1, -1).split('.'))
+   * }
+   */
+  const mockGetDependentVars = (varInputs: Array<{ variable: string | null | undefined }>) => {
+    return varInputs.map((item) => {
+      // Guard against null/undefined variable to prevent app crash
+      if (!item.variable || typeof item.variable !== 'string')
+        return []
+
+      return item.variable.slice(1, -1).split('.')
+    }).filter(arr => arr.length > 0) // Filter out empty arrays
+  }
+
+  /**
+   * Test case 1: Variable processing with null variable
+   */
+  it('should handle null variable safely', () => {
+    const varInputs = [{ variable: null }]
+
+    expect(() => {
+      mockGetDependentVars(varInputs)
+    }).not.toThrow()
+
+    const result = mockGetDependentVars(varInputs)
+    expect(result).toEqual([]) // null variables are filtered out
+  })
+
+  /**
+   * Test case 2: Variable processing with undefined variable
+   */
+  it('should handle undefined variable safely', () => {
+    const varInputs = [{ variable: undefined }]
+
+    expect(() => {
+      mockGetDependentVars(varInputs)
+    }).not.toThrow()
+
+    const result = mockGetDependentVars(varInputs)
+    expect(result).toEqual([]) // undefined variables are filtered out
+  })
+
+  /**
+   * Test case 3: Variable processing with empty string
+   */
+  it('should handle empty string variable', () => {
+    const varInputs = [{ variable: '' }]
+
+    expect(() => {
+      mockGetDependentVars(varInputs)
+    }).not.toThrow()
+
+    const result = mockGetDependentVars(varInputs)
+    expect(result).toEqual([]) // Empty string is filtered out, so result is empty array
+  })
+
+  /**
+   * Test case 4: Variable processing with valid variable format
+   */
+  it('should work correctly with valid variable format', () => {
+    const varInputs = [{ variable: '{{workflow.node.output}}' }]
+
+    expect(() => {
+      mockGetDependentVars(varInputs)
+    }).not.toThrow()
+
+    const result = mockGetDependentVars(varInputs)
+    expect(result[0]).toEqual(['{workflow', 'node', 'output}'])
+  })
+})
+
+/**
+ * Integration test to simulate the complete workflow scenario
+ */
+describe('Plugin Tool Workflow Integration', () => {
+  /**
+   * Simulate the scenario where plugin metadata is incomplete or corrupted
+   * This can happen when:
+   * 1. Plugin is being loaded from marketplace but metadata request fails
+   * 2. Plugin configuration is corrupted in database
+   * 3. Network issues during plugin loading
+   */
+  it('should reproduce the client-side exception scenario', () => {
+    // Mock incomplete plugin data that could cause the error
+    const incompletePluginData = {
+      // Missing or null uniqueIdentifier
+      uniqueIdentifier: null,
+      meta: null,
+      minimum_dify_version: undefined,
+    }
+
+    // This simulates the error path that leads to the white screen
+    expect(() => {
+      // Simulate the code path in switch-plugin-version.tsx:29
+      // The actual problematic code doesn't use optional chaining
+      const _pluginId = (incompletePluginData.uniqueIdentifier as any).split(':')[0]
+    }).toThrow('Cannot read properties of null (reading \'split\')')
+  })
+
+  /**
+   * Test the scenario mentioned in the issue where plugin tools are loaded in workflow
+   */
+  it('should simulate plugin tool loading in workflow context', () => {
+    // Mock the workflow context where plugin tools are being loaded
+    const workflowPluginTools = [
+      {
+        provider_name: 'test-plugin',
+        uniqueIdentifier: null, // This is the problematic case
+        tool_name: 'test-tool',
+      },
+      {
+        provider_name: 'valid-plugin',
+        uniqueIdentifier: 'valid-plugin:1.0.0',
+        tool_name: 'valid-tool',
+      },
+    ]
+
+    // Process each plugin tool
+    workflowPluginTools.forEach((tool, _index) => {
+      if (tool.uniqueIdentifier === null) {
+        // This reproduces the exact error scenario
+        expect(() => {
+          const _pluginId = (tool.uniqueIdentifier as any).split(':')[0]
+        }).toThrow()
+      }
+ else {
+        // Valid tools should work fine
+        expect(() => {
+          const _pluginId = tool.uniqueIdentifier.split(':')[0]
+        }).not.toThrow()
+      }
+    })
+  })
+})

web/__tests__/workflow-parallel-limit.test.tsx

@@ -0,0 +1,301 @@
+/**
+ * MAX_PARALLEL_LIMIT Configuration Bug Test
+ *
+ * This test reproduces and verifies the fix for issue #23083:
+ * MAX_PARALLEL_LIMIT environment variable does not take effect in iteration panel
+ */
+
+import { render, screen } from '@testing-library/react'
+import React from 'react'
+
+// Mock environment variables before importing constants
+const originalEnv = process.env.NEXT_PUBLIC_MAX_PARALLEL_LIMIT
+
+// Test with different environment values
+function setupEnvironment(value?: string) {
+  if (value)
+    process.env.NEXT_PUBLIC_MAX_PARALLEL_LIMIT = value
+   else
+    delete process.env.NEXT_PUBLIC_MAX_PARALLEL_LIMIT
+
+  // Clear module cache to force re-evaluation
+  jest.resetModules()
+}
+
+function restoreEnvironment() {
+  if (originalEnv)
+    process.env.NEXT_PUBLIC_MAX_PARALLEL_LIMIT = originalEnv
+   else
+    delete process.env.NEXT_PUBLIC_MAX_PARALLEL_LIMIT
+
+  jest.resetModules()
+}
+
+// Mock i18next with proper implementation
+jest.mock('react-i18next', () => ({
+  useTranslation: () => ({
+    t: (key: string) => {
+      if (key.includes('MaxParallelismTitle')) return 'Max Parallelism'
+      if (key.includes('MaxParallelismDesc')) return 'Maximum number of parallel executions'
+      if (key.includes('parallelMode')) return 'Parallel Mode'
+      if (key.includes('parallelPanelDesc')) return 'Enable parallel execution'
+      if (key.includes('errorResponseMethod')) return 'Error Response Method'
+      return key
+    },
+  }),
+  initReactI18next: {
+    type: '3rdParty',
+    init: jest.fn(),
+  },
+}))
+
+// Mock i18next module completely to prevent initialization issues
+jest.mock('i18next', () => ({
+  use: jest.fn().mockReturnThis(),
+  init: jest.fn().mockReturnThis(),
+  t: jest.fn(key => key),
+  isInitialized: true,
+}))
+
+// Mock the useConfig hook
+jest.mock('@/app/components/workflow/nodes/iteration/use-config', () => ({
+  __esModule: true,
+  default: () => ({
+    inputs: {
+      is_parallel: true,
+      parallel_nums: 5,
+      error_handle_mode: 'terminated',
+    },
+    changeParallel: jest.fn(),
+    changeParallelNums: jest.fn(),
+    changeErrorHandleMode: jest.fn(),
+  }),
+}))
+
+// Mock other components
+jest.mock('@/app/components/workflow/nodes/_base/components/variable/var-reference-picker', () => {
+  return function MockVarReferencePicker() {
+    return <div data-testid="var-reference-picker">VarReferencePicker</div>
+  }
+})
+
+jest.mock('@/app/components/workflow/nodes/_base/components/split', () => {
+  return function MockSplit() {
+    return <div data-testid="split">Split</div>
+  }
+})
+
+jest.mock('@/app/components/workflow/nodes/_base/components/field', () => {
+  return function MockField({ title, children }: { title: string, children: React.ReactNode }) {
+    return (
+      <div data-testid="field">
+        <label>{title}</label>
+        {children}
+      </div>
+    )
+  }
+})
+
+jest.mock('@/app/components/base/switch', () => {
+  return function MockSwitch({ defaultValue }: { defaultValue: boolean }) {
+    return <input type="checkbox" defaultChecked={defaultValue} data-testid="switch" />
+  }
+})
+
+jest.mock('@/app/components/base/select', () => {
+  return function MockSelect() {
+    return <select data-testid="select">Select</select>
+  }
+})
+
+// Use defaultValue to avoid controlled input warnings
+jest.mock('@/app/components/base/slider', () => {
+  return function MockSlider({ value, max, min }: { value: number, max: number, min: number }) {
+    return (
+      <input
+        type="range"
+        defaultValue={value}
+        max={max}
+        min={min}
+        data-testid="slider"
+        data-max={max}
+        data-min={min}
+        readOnly
+      />
+    )
+  }
+})
+
+// Use defaultValue to avoid controlled input warnings
+jest.mock('@/app/components/base/input', () => {
+  return function MockInput({ type, max, min, value }: { type: string, max: number, min: number, value: number }) {
+    return (
+      <input
+        type={type}
+        defaultValue={value}
+        max={max}
+        min={min}
+        data-testid="number-input"
+        data-max={max}
+        data-min={min}
+        readOnly
+      />
+    )
+  }
+})
+
+describe('MAX_PARALLEL_LIMIT Configuration Bug', () => {
+  const mockNodeData = {
+    id: 'test-iteration-node',
+    type: 'iteration' as const,
+    data: {
+      title: 'Test Iteration',
+      desc: 'Test iteration node',
+      iterator_selector: ['test'],
+      output_selector: ['output'],
+      is_parallel: true,
+      parallel_nums: 5,
+      error_handle_mode: 'terminated' as const,
+    },
+  }
+
+  beforeEach(() => {
+    jest.clearAllMocks()
+  })
+
+  afterEach(() => {
+    restoreEnvironment()
+  })
+
+  afterAll(() => {
+    restoreEnvironment()
+  })
+
+  describe('Environment Variable Parsing', () => {
+    it('should parse MAX_PARALLEL_LIMIT from NEXT_PUBLIC_MAX_PARALLEL_LIMIT environment variable', () => {
+      setupEnvironment('25')
+      const { MAX_PARALLEL_LIMIT } = require('@/config')
+      expect(MAX_PARALLEL_LIMIT).toBe(25)
+    })
+
+    it('should fallback to default when environment variable is not set', () => {
+      setupEnvironment() // No environment variable
+      const { MAX_PARALLEL_LIMIT } = require('@/config')
+      expect(MAX_PARALLEL_LIMIT).toBe(10)
+    })
+
+    it('should handle invalid environment variable values', () => {
+      setupEnvironment('invalid')
+      const { MAX_PARALLEL_LIMIT } = require('@/config')
+
+      // Should fall back to default when parsing fails
+      expect(MAX_PARALLEL_LIMIT).toBe(10)
+    })
+
+    it('should handle empty environment variable', () => {
+      setupEnvironment('')
+      const { MAX_PARALLEL_LIMIT } = require('@/config')
+
+      // Should fall back to default when empty
+      expect(MAX_PARALLEL_LIMIT).toBe(10)
+    })
+
+    // Edge cases for boundary values
+    it('should clamp MAX_PARALLEL_LIMIT to MIN when env is 0 or negative', () => {
+      setupEnvironment('0')
+      let { MAX_PARALLEL_LIMIT } = require('@/config')
+      expect(MAX_PARALLEL_LIMIT).toBe(10) // Falls back to default
+
+      setupEnvironment('-5')
+      ;({ MAX_PARALLEL_LIMIT } = require('@/config'))
+      expect(MAX_PARALLEL_LIMIT).toBe(10) // Falls back to default
+    })
+
+    it('should handle float numbers by parseInt behavior', () => {
+      setupEnvironment('12.7')
+      const { MAX_PARALLEL_LIMIT } = require('@/config')
+      // parseInt truncates to integer
+      expect(MAX_PARALLEL_LIMIT).toBe(12)
+    })
+  })
+
+  describe('UI Component Integration (Main Fix Verification)', () => {
+    it('should render iteration panel with environment-configured max value', () => {
+      // Set environment variable to a different value
+      setupEnvironment('30')
+
+      // Import Panel after setting environment
+      const Panel = require('@/app/components/workflow/nodes/iteration/panel').default
+      const { MAX_PARALLEL_LIMIT } = require('@/config')
+
+      render(
+        <Panel
+          id="test-node"
+          data={mockNodeData.data}
+        />,
+      )
+
+      // Behavior-focused assertion: UI max should equal MAX_PARALLEL_LIMIT
+      const numberInput = screen.getByTestId('number-input')
+      expect(numberInput).toHaveAttribute('data-max', String(MAX_PARALLEL_LIMIT))
+
+      const slider = screen.getByTestId('slider')
+      expect(slider).toHaveAttribute('data-max', String(MAX_PARALLEL_LIMIT))
+
+      // Verify the actual values
+      expect(MAX_PARALLEL_LIMIT).toBe(30)
+      expect(numberInput.getAttribute('data-max')).toBe('30')
+      expect(slider.getAttribute('data-max')).toBe('30')
+    })
+
+    it('should maintain UI consistency with different environment values', () => {
+      setupEnvironment('15')
+      const Panel = require('@/app/components/workflow/nodes/iteration/panel').default
+      const { MAX_PARALLEL_LIMIT } = require('@/config')
+
+      render(
+        <Panel
+          id="test-node"
+          data={mockNodeData.data}
+        />,
+      )
+
+      // Both input and slider should use the same max value from MAX_PARALLEL_LIMIT
+      const numberInput = screen.getByTestId('number-input')
+      const slider = screen.getByTestId('slider')
+
+      expect(numberInput.getAttribute('data-max')).toBe(slider.getAttribute('data-max'))
+      expect(numberInput.getAttribute('data-max')).toBe(String(MAX_PARALLEL_LIMIT))
+    })
+  })
+
+  describe('Legacy Constant Verification (For Transition Period)', () => {
+    // Marked as transition/deprecation tests
+    it('should maintain MAX_ITERATION_PARALLEL_NUM for backward compatibility', () => {
+      const { MAX_ITERATION_PARALLEL_NUM } = require('@/app/components/workflow/constants')
+      expect(typeof MAX_ITERATION_PARALLEL_NUM).toBe('number')
+      expect(MAX_ITERATION_PARALLEL_NUM).toBe(10) // Hardcoded legacy value
+    })
+
+    it('should demonstrate MAX_PARALLEL_LIMIT vs legacy constant difference', () => {
+      setupEnvironment('50')
+      const { MAX_PARALLEL_LIMIT } = require('@/config')
+      const { MAX_ITERATION_PARALLEL_NUM } = require('@/app/components/workflow/constants')
+
+      // MAX_PARALLEL_LIMIT is configurable, MAX_ITERATION_PARALLEL_NUM is not
+      expect(MAX_PARALLEL_LIMIT).toBe(50)
+      expect(MAX_ITERATION_PARALLEL_NUM).toBe(10)
+      expect(MAX_PARALLEL_LIMIT).not.toBe(MAX_ITERATION_PARALLEL_NUM)
+    })
+  })
+
+  describe('Constants Validation', () => {
+    it('should validate that required constants exist and have correct types', () => {
+      const { MAX_PARALLEL_LIMIT } = require('@/config')
+      const { MIN_ITERATION_PARALLEL_NUM } = require('@/app/components/workflow/constants')
+      expect(typeof MAX_PARALLEL_LIMIT).toBe('number')
+      expect(typeof MIN_ITERATION_PARALLEL_NUM).toBe('number')
+      expect(MAX_PARALLEL_LIMIT).toBeGreaterThanOrEqual(MIN_ITERATION_PARALLEL_NUM)
+    })
+  })
+})

web/app/components/app/annotation/batch-action.tsx

@@ -0,0 +1,79 @@
+import React, { type FC } from 'react'
+import { RiDeleteBinLine } from '@remixicon/react'
+import { useTranslation } from 'react-i18next'
+import { useBoolean } from 'ahooks'
+import Divider from '@/app/components/base/divider'
+import classNames from '@/utils/classnames'
+import Confirm from '@/app/components/base/confirm'
+
+const i18nPrefix = 'appAnnotation.batchAction'
+
+type IBatchActionProps = {
+  className?: string
+  selectedIds: string[]
+  onBatchDelete: () => Promise<void>
+  onCancel: () => void
+}
+
+const BatchAction: FC<IBatchActionProps> = ({
+  className,
+  selectedIds,
+  onBatchDelete,
+  onCancel,
+}) => {
+  const { t } = useTranslation()
+  const [isShowDeleteConfirm, {
+    setTrue: showDeleteConfirm,
+    setFalse: hideDeleteConfirm,
+  }] = useBoolean(false)
+  const [isDeleting, {
+    setTrue: setIsDeleting,
+    setFalse: setIsNotDeleting,
+  }] = useBoolean(false)
+
+  const handleBatchDelete = async () => {
+    setIsDeleting()
+    await onBatchDelete()
+    hideDeleteConfirm()
+    setIsNotDeleting()
+  }
+  return (
+    <div className={classNames('pointer-events-none flex w-full justify-center', className)}>
+      <div className='pointer-events-auto flex items-center gap-x-1 rounded-[10px] border border-components-actionbar-border-accent bg-components-actionbar-bg-accent p-1 shadow-xl shadow-shadow-shadow-5 backdrop-blur-[5px]'>
+        <div className='inline-flex items-center gap-x-2 py-1 pl-2 pr-3'>
+          <span className='flex h-5 w-5 items-center justify-center rounded-md bg-text-accent px-1 py-0.5 text-xs font-medium text-text-primary-on-surface'>
+            {selectedIds.length}
+          </span>
+          <span className='text-[13px] font-semibold leading-[16px] text-text-accent'>{t(`${i18nPrefix}.selected`)}</span>
+        </div>
+        <Divider type='vertical' className='mx-0.5 h-3.5 bg-divider-regular' />
+        <div className='flex cursor-pointer items-center gap-x-0.5 px-3 py-2' onClick={showDeleteConfirm}>
+          <RiDeleteBinLine className='h-4 w-4 text-components-button-destructive-ghost-text' />
+          <button type='button' className='px-0.5 text-[13px] font-medium leading-[16px] text-components-button-destructive-ghost-text' >
+            {t('common.operation.delete')}
+          </button>
+        </div>
+
+        <Divider type='vertical' className='mx-0.5 h-3.5 bg-divider-regular' />
+        <button type='button' className='px-3.5 py-2 text-[13px] font-medium leading-[16px] text-components-button-ghost-text' onClick={onCancel}>
+          {t('common.operation.cancel')}
+        </button>
+      </div>
+      {
+        isShowDeleteConfirm && (
+          <Confirm
+            isShow
+            title={t('appAnnotation.list.delete.title')}
+            confirmText={t('common.operation.delete')}
+            onConfirm={handleBatchDelete}
+            onCancel={hideDeleteConfirm}
+            isLoading={isDeleting}
+            isDisabled={isDeleting}
+          />
+        )
+      }
+    </div>
+  )
+}
+
+export default React.memo(BatchAction)

web/app/components/app/annotation/index.tsx

@@ -26,6 +26,7 @@ import { useProviderContext } from '@/context/provider-context'
 import AnnotationFullModal from '@/app/components/billing/annotation-full/modal'
 import type { App } from '@/types/app'
 import cn from '@/utils/classnames'
+import { delAnnotations } from '@/service/annotation'
 
 type Props = {
   appDetail: App
@@ -50,7 +51,9 @@ const Annotation: FC<Props> = (props) => {
   const [controlUpdateList, setControlUpdateList] = useState(Date.now())
   const [currItem, setCurrItem] = useState<AnnotationItem | null>(null)
   const [isShowViewModal, setIsShowViewModal] = useState(false)
+  const [selectedIds, setSelectedIds] = useState<string[]>([])
   const debouncedQueryParams = useDebounce(queryParams, { wait: 500 })
+  const [isBatchDeleting, setIsBatchDeleting] = useState(false)
 
   const fetchAnnotationConfig = async () => {
     const res = await doFetchAnnotationConfig(appDetail.id)
@@ -60,7 +63,6 @@ const Annotation: FC<Props> = (props) => {
 
   useEffect(() => {
     if (isChatApp) fetchAnnotationConfig()
-    // eslint-disable-next-line react-hooks/exhaustive-deps
   }, [])
 
   const ensureJobCompleted = async (jobId: string, status: AnnotationEnableStatus) => {
@@ -89,7 +91,6 @@ const Annotation: FC<Props> = (props) => {
 
   useEffect(() => {
     fetchList(currPage + 1)
-    // eslint-disable-next-line react-hooks/exhaustive-deps
   }, [currPage, limit, debouncedQueryParams])
 
   const handleAdd = async (payload: AnnotationItemBasic) => {
@@ -106,6 +107,25 @@ const Annotation: FC<Props> = (props) => {
     setControlUpdateList(Date.now())
   }
 
+  const handleBatchDelete = async () => {
+    if (isBatchDeleting)
+      return
+    setIsBatchDeleting(true)
+    try {
+      await delAnnotations(appDetail.id, selectedIds)
+      Toast.notify({ message: t('common.api.actionSuccess'), type: 'success' })
+      fetchList()
+      setControlUpdateList(Date.now())
+      setSelectedIds([])
+    }
+    catch (e: any) {
+      Toast.notify({ type: 'error', message: e.message || t('common.api.actionFailed') })
+    }
+    finally {
+      setIsBatchDeleting(false)
+    }
+  }
+
   const handleView = (item: AnnotationItem) => {
     setCurrItem(item)
     setIsShowViewModal(true)
@@ -189,6 +209,11 @@ const Annotation: FC<Props> = (props) => {
               list={list}
               onRemove={handleRemove}
               onView={handleView}
+              selectedIds={selectedIds}
+              onSelectedIdsChange={setSelectedIds}
+              onBatchDelete={handleBatchDelete}
+              onCancel={() => setSelectedIds([])}
+              isBatchDeleting={isBatchDeleting}
             />
             : <div className='flex h-full grow items-center justify-center'><EmptyElement /></div>
         }

web/app/components/app/annotation/list.tsx

@@ -1,6 +1,6 @@
 'use client'
 import type { FC } from 'react'
-import React from 'react'
+import React, { useCallback, useMemo } from 'react'
 import { useTranslation } from 'react-i18next'
 import { RiDeleteBinLine, RiEditLine } from '@remixicon/react'
 import type { AnnotationItem } from './type'
@@ -8,28 +8,67 @@ import RemoveAnnotationConfirmModal from './remove-annotation-confirm-modal'
 import ActionButton from '@/app/components/base/action-button'
 import useTimestamp from '@/hooks/use-timestamp'
 import cn from '@/utils/classnames'
+import Checkbox from '@/app/components/base/checkbox'
+import BatchAction from './batch-action'
 
 type Props = {
   list: AnnotationItem[]
-  onRemove: (id: string) => void
   onView: (item: AnnotationItem) => void
+  onRemove: (id: string) => void
+  selectedIds: string[]
+  onSelectedIdsChange: (selectedIds: string[]) => void
+  onBatchDelete: () => Promise<void>
+  onCancel: () => void
+  isBatchDeleting?: boolean
 }
 
 const List: FC<Props> = ({
   list,
   onView,
   onRemove,
+  selectedIds,
+  onSelectedIdsChange,
+  onBatchDelete,
+  onCancel,
+  isBatchDeleting,
 }) => {
   const { t } = useTranslation()
   const { formatTime } = useTimestamp()
   const [currId, setCurrId] = React.useState<string | null>(null)
   const [showConfirmDelete, setShowConfirmDelete] = React.useState(false)
+
+  const isAllSelected = useMemo(() => {
+    return list.length > 0 && list.every(item => selectedIds.includes(item.id))
+  }, [list, selectedIds])
+
+  const isSomeSelected = useMemo(() => {
+    return list.some(item => selectedIds.includes(item.id))
+  }, [list, selectedIds])
+
+  const handleSelectAll = useCallback(() => {
+    const currentPageIds = list.map(item => item.id)
+    const otherPageIds = selectedIds.filter(id => !currentPageIds.includes(id))
+
+    if (isAllSelected)
+      onSelectedIdsChange(otherPageIds)
+    else
+      onSelectedIdsChange([...otherPageIds, ...currentPageIds])
+  }, [isAllSelected, list, selectedIds, onSelectedIdsChange])
+
   return (
-    <div className='overflow-x-auto'>
+    <div className='relative grow overflow-x-auto'>
       <table className={cn('mt-2 w-full min-w-[440px] border-collapse border-0')}>
         <thead className='system-xs-medium-uppercase text-text-tertiary'>
           <tr>
-            <td className='w-5 whitespace-nowrap rounded-l-lg bg-background-section-burn pl-2 pr-1'>{t('appAnnotation.table.header.question')}</td>
+            <td className='w-12 whitespace-nowrap rounded-l-lg bg-background-section-burn px-2'>
+              <Checkbox
+                className='mr-2'
+                checked={isAllSelected}
+                indeterminate={!isAllSelected && isSomeSelected}
+                onCheck={handleSelectAll}
+              />
+            </td>
+            <td className='w-5 whitespace-nowrap bg-background-section-burn pl-2 pr-1'>{t('appAnnotation.table.header.question')}</td>
             <td className='whitespace-nowrap bg-background-section-burn py-1.5 pl-3'>{t('appAnnotation.table.header.answer')}</td>
             <td className='whitespace-nowrap bg-background-section-burn py-1.5 pl-3'>{t('appAnnotation.table.header.createdAt')}</td>
             <td className='whitespace-nowrap bg-background-section-burn py-1.5 pl-3'>{t('appAnnotation.table.header.hits')}</td>
@@ -47,6 +86,18 @@ const List: FC<Props> = ({
                 }
               }
             >
+              <td className='w-12 px-2' onClick={e => e.stopPropagation()}>
+                <Checkbox
+                  className='mr-2'
+                  checked={selectedIds.includes(item.id)}
+                  onCheck={() => {
+                    if (selectedIds.includes(item.id))
+                      onSelectedIdsChange(selectedIds.filter(id => id !== item.id))
+                    else
+                      onSelectedIdsChange([...selectedIds, item.id])
+                  }}
+                />
+              </td>
               <td
                 className='max-w-[250px] overflow-hidden text-ellipsis whitespace-nowrap p-3 pr-2'
                 title={item.question}
@@ -85,6 +136,15 @@ const List: FC<Props> = ({
           setShowConfirmDelete(false)
         }}
       />
+      {selectedIds.length > 0 && (
+        <BatchAction
+          className='absolute bottom-6 left-1/2 z-20 -translate-x-1/2'
+          selectedIds={selectedIds}
+          onBatchDelete={onBatchDelete}
+          onCancel={onCancel}
+          isBatchDeleting={isBatchDeleting}
+        />
+      )}
     </div>
   )
 }

web/app/components/plugins/plugin-detail-panel/detail-header.tsx

@@ -124,6 +124,8 @@ const DetailHeader = ({
   const isAutoUpgradeEnabled = useMemo(() => {
     if (!autoUpgradeInfo || !isFromMarketplace)
       return false
+    if(autoUpgradeInfo.strategy_setting === 'disabled')
+      return false
     if(autoUpgradeInfo.upgrade_mode === AUTO_UPDATE_MODE.update_all)
       return true
     if(autoUpgradeInfo.upgrade_mode === AUTO_UPDATE_MODE.partial && autoUpgradeInfo.include_plugins.includes(plugin_id))

web/app/components/workflow/constants.ts

@@ -35,14 +35,6 @@ export const NODE_LAYOUT_HORIZONTAL_PADDING = 60
 export const NODE_LAYOUT_VERTICAL_PADDING = 60
 export const NODE_LAYOUT_MIN_DISTANCE = 100
 
-let maxParallelLimit = 10
-
-if (process.env.NEXT_PUBLIC_MAX_PARALLEL_LIMIT && process.env.NEXT_PUBLIC_MAX_PARALLEL_LIMIT !== '')
-  maxParallelLimit = Number.parseInt(process.env.NEXT_PUBLIC_MAX_PARALLEL_LIMIT)
-else if (globalThis.document?.body?.getAttribute('data-public-max-parallel-limit') && globalThis.document.body.getAttribute('data-public-max-parallel-limit') !== '')
-  maxParallelLimit = Number.parseInt(globalThis.document.body.getAttribute('data-public-max-parallel-limit') as string)
-
-export const PARALLEL_LIMIT = maxParallelLimit
 export const PARALLEL_DEPTH_LIMIT = 3
 
 export const RETRIEVAL_OUTPUT_STRUCT = `{

web/app/components/workflow/hooks/use-workflow.ts

@@ -27,7 +27,6 @@ import {
 import { getParallelInfo } from '../utils'
 import {
   PARALLEL_DEPTH_LIMIT,
-  PARALLEL_LIMIT,
   SUPPORT_OUTPUT_VARS_NODE,
 } from '../constants'
 import type { IterationNodeType } from '../nodes/iteration/types'
@@ -45,6 +44,8 @@ import {
 import { CUSTOM_ITERATION_START_NODE } from '@/app/components/workflow/nodes/iteration-start/constants'
 import { CUSTOM_LOOP_START_NODE } from '@/app/components/workflow/nodes/loop-start/constants'
 import { basePath } from '@/utils/var'
+import { canFindTool } from '@/utils'
+import { MAX_PARALLEL_LIMIT } from '@/config'
 import { useNodesMetaData } from '.'
 
 export const useIsChatMode = () => {
@@ -257,8 +258,6 @@ export const useWorkflow = () => {
       })
       setNodes(newNodes)
     }
-
-    // eslint-disable-next-line react-hooks/exhaustive-deps
   }, [store])
 
   const isVarUsedInNodes = useCallback((varSelector: ValueSelector) => {
@@ -297,9 +296,9 @@ export const useWorkflow = () => {
       edges,
     } = store.getState()
     const connectedEdges = edges.filter(edge => edge.source === nodeId && edge.sourceHandle === nodeHandle)
-    if (connectedEdges.length > PARALLEL_LIMIT - 1) {
+    if (connectedEdges.length > MAX_PARALLEL_LIMIT - 1) {
       const { setShowTips } = workflowStore.getState()
-      setShowTips(t('workflow.common.parallelTip.limit', { num: PARALLEL_LIMIT }))
+      setShowTips(t('workflow.common.parallelTip.limit', { num: MAX_PARALLEL_LIMIT }))
       return false
     }
 

web/app/components/workflow/nodes/_base/components/switch-plugin-version.tsx

@@ -26,7 +26,8 @@ export type SwitchPluginVersionProps = {
 
 export const SwitchPluginVersion: FC<SwitchPluginVersionProps> = (props) => {
   const { uniqueIdentifier, tooltip, onChange, className } = props
-  const [pluginId] = uniqueIdentifier.split(':')
+
+  const [pluginId] = uniqueIdentifier?.split(':') || ['']
   const [isShow, setIsShow] = useState(false)
   const [isShowUpdateModal, { setTrue: showUpdateModal, setFalse: hideUpdateModal }] = useBoolean(false)
   const [target, setTarget] = useState<{
@@ -60,6 +61,11 @@ export const SwitchPluginVersion: FC<SwitchPluginVersionProps> = (props) => {
       })
   }
   const { t } = useTranslation()
+
+  // Guard against null/undefined uniqueIdentifier to prevent app crash
+  if (!uniqueIdentifier || !pluginId)
+    return null
+
   return <Tooltip popupContent={!isShow && !isShowUpdateModal && tooltip} triggerMethod='hover'>
     <div className={cn('flex w-fit items-center justify-center', className)} onClick={e => e.stopPropagation()}>
       {isShowUpdateModal && pluginDetail && <PluginMutationModel

web/app/components/workflow/nodes/agent/use-single-run-form-params.ts

@@ -77,7 +77,13 @@ const useSingleRunFormParams = ({
   }, [runResult, t])
 
     const getDependentVars = () => {
-    return varInputs.map(item => item.variable.slice(1, -1).split('.'))
+    return varInputs.map((item) => {
+      // Guard against null/undefined variable to prevent app crash
+      if (!item.variable || typeof item.variable !== 'string')
+        return []
+
+      return item.variable.slice(1, -1).split('.')
+    }).filter(arr => arr.length > 0)
   }
 
   return {

web/app/components/workflow/nodes/http/components/timeout/index.tsx

@@ -20,7 +20,7 @@ const InputField: FC<{
   description: string
   placeholder: string
   value?: number
-  onChange: (value: number) => void
+  onChange: (value: number | undefined) => void
   readOnly?: boolean
   min: number
   max: number
@@ -35,8 +35,18 @@ const InputField: FC<{
         type='number'
         value={value}
         onChange={(e) => {
-          const value = Math.max(min, Math.min(max, Number.parseInt(e.target.value, 10)))
-          onChange(value)
+          const inputValue = e.target.value
+          if (inputValue === '') {
+            // When user clears the input, set to undefined to let backend use default values
+            onChange(undefined)
+          }
+          else {
+            const parsedValue = Number.parseInt(inputValue, 10)
+            if (!Number.isNaN(parsedValue)) {
+              const value = Math.max(min, Math.min(max, parsedValue))
+              onChange(value)
+            }
+          }
         }}
         placeholder={placeholder}
         readOnly={readOnly}

web/app/components/workflow/nodes/http/use-single-run-form-params.ts

@@ -62,7 +62,13 @@ const useSingleRunFormParams = ({
   }, [inputVarValues, setInputVarValues, varInputs])
 
   const getDependentVars = () => {
-    return varInputs.map(item => item.variable.slice(1, -1).split('.'))
+    return varInputs.map((item) => {
+      // Guard against null/undefined variable to prevent app crash
+      if (!item.variable || typeof item.variable !== 'string')
+        return []
+
+      return item.variable.slice(1, -1).split('.')
+    }).filter(arr => arr.length > 0)
   }
 
   return {

web/app/components/workflow/nodes/iteration/panel.tsx

@@ -3,7 +3,7 @@ import React from 'react'
 import { useTranslation } from 'react-i18next'
 import VarReferencePicker from '../_base/components/variable/var-reference-picker'
 import Split from '../_base/components/split'
-import { MAX_ITERATION_PARALLEL_NUM, MIN_ITERATION_PARALLEL_NUM } from '../../constants'
+import { MIN_ITERATION_PARALLEL_NUM } from '../../constants'
 import type { IterationNodeType } from './types'
 import useConfig from './use-config'
 import { ErrorHandleMode, type NodePanelProps } from '@/app/components/workflow/types'
@@ -12,6 +12,7 @@ import Switch from '@/app/components/base/switch'
 import Select from '@/app/components/base/select'
 import Slider from '@/app/components/base/slider'
 import Input from '@/app/components/base/input'
+import { MAX_PARALLEL_LIMIT } from '@/config'
 
 const i18nPrefix = 'workflow.nodes.iteration'
 
@@ -96,11 +97,11 @@ const Panel: FC<NodePanelProps<IterationNodeType>> = ({
         inputs.is_parallel && (<div className='px-4 pb-2'>
           <Field title={t(`${i18nPrefix}.MaxParallelismTitle`)} isSubTitle tooltip={<div className='w-[230px]'>{t(`${i18nPrefix}.MaxParallelismDesc`)}</div>}>
             <div className='row flex'>
-              <Input type='number' wrapperClassName='w-18 mr-4 ' max={MAX_ITERATION_PARALLEL_NUM} min={MIN_ITERATION_PARALLEL_NUM} value={inputs.parallel_nums} onChange={(e) => { changeParallelNums(Number(e.target.value)) }} />
+              <Input type='number' wrapperClassName='w-18 mr-4 ' max={MAX_PARALLEL_LIMIT} min={MIN_ITERATION_PARALLEL_NUM} value={inputs.parallel_nums} onChange={(e) => { changeParallelNums(Number(e.target.value)) }} />
               <Slider
                 value={inputs.parallel_nums}
                 onChange={changeParallelNums}
-                max={MAX_ITERATION_PARALLEL_NUM}
+                max={MAX_PARALLEL_LIMIT}
                 min={MIN_ITERATION_PARALLEL_NUM}
                 className=' mt-4 flex-1 shrink-0'
               />

web/app/components/workflow/nodes/knowledge-retrieval/components/metadata/condition-list/utils.ts

@@ -32,6 +32,8 @@ export const getOperators = (type?: MetadataFilteringVariableType) => {
         ComparisonOperator.endWith,
         ComparisonOperator.empty,
         ComparisonOperator.notEmpty,
+        ComparisonOperator.in,
+        ComparisonOperator.notIn,
       ]
     case MetadataFilteringVariableType.number:
       return [

web/app/components/workflow/nodes/list-operator/components/filter-condition.tsx

@@ -15,18 +15,21 @@ import cn from '@/utils/classnames'
 import { VarType } from '../../../types'
 
 const optionNameI18NPrefix = 'workflow.nodes.ifElse.optionName'
+import { getConditionValueAsString } from '@/app/components/workflow/nodes/utils'
 
 const VAR_INPUT_SUPPORTED_KEYS: Record<string, VarType> = {
   name: VarType.string,
   url: VarType.string,
   extension: VarType.string,
   mime_type: VarType.string,
-  related_id: VarType.number,
+  related_id: VarType.string,
+  size: VarType.number,
 }
 
 type Props = {
   condition: Condition
   onChange: (condition: Condition) => void
+  varType: VarType
   hasSubVariable: boolean
   readOnly: boolean
   nodeId: string
@@ -34,6 +37,7 @@ type Props = {
 
 const FilterCondition: FC<Props> = ({
   condition = { key: '', comparison_operator: ComparisonOperator.equal, value: '' },
+  varType,
   onChange,
   hasSubVariable,
   readOnly,
@@ -42,7 +46,7 @@ const FilterCondition: FC<Props> = ({
   const { t } = useTranslation()
   const [isFocus, setIsFocus] = useState(false)
 
-  const expectedVarType = VAR_INPUT_SUPPORTED_KEYS[condition.key]
+  const expectedVarType = condition.key ? VAR_INPUT_SUPPORTED_KEYS[condition.key] : varType
   const supportVariableInput = !!expectedVarType
 
   const { availableVars, availableNodesWithParent } = useAvailableVarList(nodeId, {
@@ -93,6 +97,59 @@ const FilterCondition: FC<Props> = ({
     })
   }, [onChange, expectedVarType])
 
+  // Extract input rendering logic to avoid nested ternary
+  let inputElement: React.ReactNode = null
+  if (!comparisonOperatorNotRequireValue(condition.comparison_operator)) {
+    if (isSelect) {
+      inputElement = (
+        <Select
+          items={selectOptions}
+          defaultValue={isArrayValue ? (condition.value as string[])[0] : condition.value as string}
+          onSelect={item => handleChange('value')(item.value)}
+          className='!text-[13px]'
+          wrapperClassName='grow h-8'
+          placeholder='Select value'
+        />
+      )
+    }
+    else if (supportVariableInput) {
+      inputElement = (
+        <Input
+          instanceId='filter-condition-input'
+          className={cn(
+            isFocus
+              ? 'border-components-input-border-active bg-components-input-bg-active shadow-xs'
+              : 'border-components-input-border-hover bg-components-input-bg-normal',
+            'w-0 grow rounded-lg border px-3 py-[6px]',
+          )}
+          value={
+            getConditionValueAsString(condition)
+          }
+          onChange={handleChange('value')}
+          readOnly={readOnly}
+          nodesOutputVars={availableVars}
+          availableNodes={availableNodesWithParent}
+          onFocusChange={setIsFocus}
+          placeholder={!readOnly ? t('workflow.nodes.http.insertVarPlaceholder')! : ''}
+          placeholderClassName='!leading-[21px]'
+        />
+      )
+    }
+    else {
+      inputElement = (
+        <input
+          type={((hasSubVariable && condition.key === 'size') || (!hasSubVariable && varType === VarType.number)) ? 'number' : 'text'}
+          className='grow rounded-lg border border-components-input-border-hover bg-components-input-bg-normal px-3 py-[6px]'
+          value={
+            getConditionValueAsString(condition)
+          }
+          onChange={e => handleChange('value')(e.target.value)}
+          readOnly={readOnly}
+        />
+      )
+    }
+  }
+
   return (
     <div>
       {hasSubVariable && (
@@ -111,46 +168,7 @@ const FilterCondition: FC<Props> = ({
           file={hasSubVariable ? { key: condition.key } : undefined}
           disabled={readOnly}
         />
-        {!comparisonOperatorNotRequireValue(condition.comparison_operator) && (
-          <>
-            {isSelect ? (
-              <Select
-                items={selectOptions}
-                defaultValue={isArrayValue ? (condition.value as string[])[0] : condition.value as string}
-                onSelect={item => handleChange('value')(item.value)}
-                className='!text-[13px]'
-                wrapperClassName='grow h-8'
-                placeholder='Select value'
-              />
-            ) : supportVariableInput ? (
-              <Input
-                instanceId='filter-condition-input'
-                className={cn(
-                  isFocus
-                    ? 'border-components-input-border-active bg-components-input-bg-active shadow-xs'
-                    : 'border-components-input-border-hover bg-components-input-bg-normal',
-                  'w-0 grow rounded-lg border px-3 py-[6px]',
-                )}
-                value={condition.value}
-                onChange={handleChange('value')}
-                readOnly={readOnly}
-                nodesOutputVars={availableVars}
-                availableNodes={availableNodesWithParent}
-                onFocusChange={setIsFocus}
-                placeholder={!readOnly ? t('workflow.nodes.http.extractListPlaceholder')! : ''}
-                placeholderClassName='!leading-[21px]'
-              />
-            ) : (
-              <input
-                type={(condition.key === 'size' || expectedVarType === VarType.number) ? 'number' : 'text'}
-                className='grow rounded-lg border border-components-input-border-hover bg-components-input-bg-normal px-3 py-[6px]'
-                value={condition.value}
-                onChange={e => handleChange('value')(e.target.value)}
-                readOnly={readOnly}
-              />
-            )}
-          </>
-        )}
+        {inputElement}
       </div>
     </div>
   )

web/app/components/workflow/nodes/llm/use-single-run-form-params.ts

@@ -168,7 +168,13 @@ const useSingleRunFormParams = ({
   })()
 
   const getDependentVars = () => {
-    const promptVars = varInputs.map(item => item.variable.slice(1, -1).split('.'))
+    const promptVars = varInputs.map((item) => {
+      // Guard against null/undefined variable to prevent app crash
+      if (!item.variable || typeof item.variable !== 'string')
+        return []
+
+      return item.variable.slice(1, -1).split('.')
+    }).filter(arr => arr.length > 0)
     const contextVar = payload.context.variable_selector
     const vars = [...promptVars, contextVar]
     if (isVisionModel && payload.vision?.enabled && payload.vision?.configs?.variable_selector) {

web/app/components/workflow/nodes/parameter-extractor/use-single-run-form-params.ts

@@ -120,7 +120,13 @@ const useSingleRunFormParams = ({
   })()
 
   const getDependentVars = () => {
-    const promptVars = varInputs.map(item => item.variable.slice(1, -1).split('.'))
+    const promptVars = varInputs.map((item) => {
+      // Guard against null/undefined variable to prevent app crash
+      if (!item.variable || typeof item.variable !== 'string')
+        return []
+
+      return item.variable.slice(1, -1).split('.')
+    }).filter(arr => arr.length > 0)
     const vars = [payload.query, ...promptVars]
     if (isVisionModel && payload.vision?.enabled && payload.vision?.configs?.variable_selector) {
       const visionVar = payload.vision.configs.variable_selector

web/app/components/workflow/nodes/question-classifier/use-single-run-form-params.ts

@@ -118,7 +118,13 @@ const useSingleRunFormParams = ({
   })()
 
   const getDependentVars = () => {
-    const promptVars = varInputs.map(item => item.variable.slice(1, -1).split('.'))
+    const promptVars = varInputs.map((item) => {
+      // Guard against null/undefined variable to prevent app crash
+      if (!item.variable || typeof item.variable !== 'string')
+        return []
+
+      return item.variable.slice(1, -1).split('.')
+    }).filter(arr => arr.length > 0)
     const vars = [payload.query_variable_selector, ...promptVars]
     if (isVisionModel && payload.vision?.enabled && payload.vision?.configs?.variable_selector) {
       const visionVar = payload.vision.configs.variable_selector

web/app/components/workflow/nodes/tool/use-single-run-form-params.ts

@@ -88,7 +88,13 @@ const useSingleRunFormParams = ({
   const toolIcon = useToolIcon(payload)
 
   const getDependentVars = () => {
-    return varInputs.map(item => item.variable.slice(1, -1).split('.'))
+    return varInputs.map((item) => {
+      // Guard against null/undefined variable to prevent app crash
+      if (!item.variable || typeof item.variable !== 'string')
+        return []
+
+      return item.variable.slice(1, -1).split('.')
+    }).filter(arr => arr.length > 0)
   }
 
   return {

web/app/components/workflow/nodes/utils.ts

@@ -28,3 +28,13 @@ export const findVariableWhenOnLLMVision = (valueSelector: ValueSelector, availa
     formType,
   }
 }
+
+export const getConditionValueAsString = (condition: { value: any }) => {
+  if (Array.isArray(condition.value))
+    return condition.value[0] ?? ''
+
+  if (typeof condition.value === 'number')
+    return String(condition.value)
+
+  return condition.value ?? ''
+}

web/config/index.ts

@@ -14,12 +14,18 @@ const getBooleanConfig = (envVar: string | undefined, dataAttrKey: DatasetAttr,
 }
 
 const getNumberConfig = (envVar: string | undefined, dataAttrKey: DatasetAttr, defaultValue: number) => {
-  if (envVar)
-    return Number.parseInt(envVar)
+  if (envVar) {
+    const parsed = Number.parseInt(envVar)
+    if (!Number.isNaN(parsed) && parsed > 0)
+      return parsed
+  }
 
   const attrValue = globalThis.document?.body?.getAttribute(dataAttrKey)
-  if (attrValue)
-    return Number.parseInt(attrValue)
+  if (attrValue) {
+    const parsed = Number.parseInt(attrValue)
+    if (!Number.isNaN(parsed) && parsed > 0)
+      return parsed
+  }
   return defaultValue
 }
 
@@ -275,6 +281,7 @@ export const FULL_DOC_PREVIEW_LENGTH = 50
 export const JSON_SCHEMA_MAX_DEPTH = 10
 
 export const MAX_TOOLS_NUM = getNumberConfig(process.env.NEXT_PUBLIC_MAX_TOOLS_NUM, DatasetAttr.DATA_PUBLIC_MAX_TOOLS_NUM, 10)
+export const MAX_PARALLEL_LIMIT = getNumberConfig(process.env.NEXT_PUBLIC_MAX_PARALLEL_LIMIT, DatasetAttr.DATA_PUBLIC_MAX_PARALLEL_LIMIT, 10)
 export const TEXT_GENERATION_TIMEOUT_MS = getNumberConfig(process.env.NEXT_PUBLIC_TEXT_GENERATION_TIMEOUT_MS, DatasetAttr.DATA_PUBLIC_TEXT_GENERATION_TIMEOUT_MS, 60000)
 export const LOOP_NODE_MAX_COUNT = getNumberConfig(process.env.NEXT_PUBLIC_LOOP_NODE_MAX_COUNT, DatasetAttr.DATA_PUBLIC_LOOP_NODE_MAX_COUNT, 100)
 export const MAX_ITERATIONS_NUM = getNumberConfig(process.env.NEXT_PUBLIC_MAX_ITERATIONS_NUM, DatasetAttr.DATA_PUBLIC_MAX_ITERATIONS_NUM, 99)

web/i18n-config/README.md

@@ -8,7 +8,6 @@ This directory contains the internationalization (i18n) files for this project.
 
 ```
 ├── [  24]  README.md
-├── [   0]  README_CN.md
 ├── [ 704]  en-US
 │   ├── [2.4K]  app-annotation.ts
 │   ├── [5.2K]  app-api.ts
@@ -37,7 +36,7 @@ This directory contains the internationalization (i18n) files for this project.
 
 We use English as the default language. The i18n files are organized by language and then by module. For example, the English translation for the `app` module is in `en-US/app.ts`.
 
-If you want to add a new language or modify an existing translation, you can create a new file for the language or modify the existing file. The file name should be the language code (e.g., `zh-CN` for Chinese) and the file extension should be `.ts`.
+If you want to add a new language or modify an existing translation, you can create a new file for the language or modify the existing file. The file name should be the language code (e.g., `zh-Hans` for Chinese) and the file extension should be `.ts`.
 
 For example, if you want to add french translation, you can create a new folder `fr-FR` and add the translation files in it.
 
@@ -48,6 +47,7 @@ By default we will use `LanguagesSupported` to determine which languages are sup
 1. Create a new folder for the new language.
 
 ```
+cd web/i18n
 cp -r en-US fr-FR
 ```
 

web/i18n-config/check-i18n.js

@@ -58,9 +58,14 @@ async function getKeysFromLanguage(language) {
           const iterateKeys = (obj, prefix = '') => {
             for (const key in obj) {
               const nestedKey = prefix ? `${prefix}.${key}` : key
-              nestedKeys.push(nestedKey)
-              if (typeof obj[key] === 'object' && obj[key] !== null)
+              if (typeof obj[key] === 'object' && obj[key] !== null && !Array.isArray(obj[key])) {
+                // This is an object (but not array), recurse into it but don't add it as a key
                 iterateKeys(obj[key], nestedKey)
+              }
+ else {
+                // This is a leaf node (string, number, boolean, array, etc.), add it as a key
+                nestedKeys.push(nestedKey)
+              }
             }
           }
           iterateKeys(translationObj)
@@ -79,15 +84,176 @@ async function getKeysFromLanguage(language) {
   })
 }
 
+function removeKeysFromObject(obj, keysToRemove, prefix = '') {
+  let modified = false
+  for (const key in obj) {
+    const fullKey = prefix ? `${prefix}.${key}` : key
+
+    if (keysToRemove.includes(fullKey)) {
+      delete obj[key]
+      modified = true
+      console.log(`🗑️  Removed key: ${fullKey}`)
+    }
+ else if (typeof obj[key] === 'object' && obj[key] !== null) {
+      const subModified = removeKeysFromObject(obj[key], keysToRemove, fullKey)
+      modified = modified || subModified
+    }
+  }
+  return modified
+}
+
+async function removeExtraKeysFromFile(language, fileName, extraKeys) {
+  const filePath = path.resolve(__dirname, '../i18n', language, `${fileName}.ts`)
+
+  if (!fs.existsSync(filePath)) {
+    console.log(`⚠️  File not found: ${filePath}`)
+    return false
+  }
+
+  try {
+    // Filter keys that belong to this file
+    const camelCaseFileName = fileName.replace(/[-_](.)/g, (_, c) => c.toUpperCase())
+    const fileSpecificKeys = extraKeys
+      .filter(key => key.startsWith(`${camelCaseFileName}.`))
+      .map(key => key.substring(camelCaseFileName.length + 1)) // Remove file prefix
+
+    if (fileSpecificKeys.length === 0)
+      return false
+
+    console.log(`🔄 Processing file: ${filePath}`)
+
+    // Read the original file content
+    const content = fs.readFileSync(filePath, 'utf8')
+    const lines = content.split('\n')
+
+    let modified = false
+    const linesToRemove = []
+
+    // Find lines to remove for each key
+    for (const keyToRemove of fileSpecificKeys) {
+      const keyParts = keyToRemove.split('.')
+      let targetLineIndex = -1
+
+      // Build regex pattern for the exact key path
+      if (keyParts.length === 1) {
+        // Simple key at root level like "pickDate: 'value'"
+        for (let i = 0; i < lines.length; i++) {
+          const line = lines[i]
+          const simpleKeyPattern = new RegExp(`^\\s*${keyParts[0]}\\s*:`)
+          if (simpleKeyPattern.test(line)) {
+            targetLineIndex = i
+            break
+          }
+        }
+      }
+ else {
+        // Nested key - need to find the exact path
+        const currentPath = []
+        let braceDepth = 0
+
+        for (let i = 0; i < lines.length; i++) {
+          const line = lines[i]
+          const trimmedLine = line.trim()
+
+          // Track current object path
+          const keyMatch = trimmedLine.match(/^(\w+)\s*:\s*{/)
+          if (keyMatch) {
+            currentPath.push(keyMatch[1])
+            braceDepth++
+          }
+ else if (trimmedLine === '},' || trimmedLine === '}') {
+            if (braceDepth > 0) {
+              braceDepth--
+              currentPath.pop()
+            }
+          }
+
+          // Check if this line matches our target key
+          const leafKeyMatch = trimmedLine.match(/^(\w+)\s*:/)
+          if (leafKeyMatch) {
+            const fullPath = [...currentPath, leafKeyMatch[1]]
+            const fullPathString = fullPath.join('.')
+
+            if (fullPathString === keyToRemove) {
+              targetLineIndex = i
+              break
+            }
+          }
+        }
+      }
+
+      if (targetLineIndex !== -1) {
+        linesToRemove.push(targetLineIndex)
+        console.log(`🗑️  Found key to remove: ${keyToRemove} at line ${targetLineIndex + 1}`)
+        modified = true
+      }
+ else {
+        console.log(`⚠️  Could not find key: ${keyToRemove}`)
+      }
+    }
+
+    if (modified) {
+      // Remove lines in reverse order to maintain correct indices
+      linesToRemove.sort((a, b) => b - a)
+
+      for (const lineIndex of linesToRemove) {
+        const line = lines[lineIndex]
+        console.log(`🗑️  Removing line ${lineIndex + 1}: ${line.trim()}`)
+        lines.splice(lineIndex, 1)
+
+        // Also remove trailing comma from previous line if it exists and the next line is a closing brace
+        if (lineIndex > 0 && lineIndex < lines.length) {
+          const prevLine = lines[lineIndex - 1]
+          const nextLine = lines[lineIndex] ? lines[lineIndex].trim() : ''
+
+          if (prevLine.trim().endsWith(',') && (nextLine.startsWith('}') || nextLine === ''))
+            lines[lineIndex - 1] = prevLine.replace(/,\s*$/, '')
+        }
+      }
+
+      // Write back to file
+      const newContent = lines.join('\n')
+      fs.writeFileSync(filePath, newContent)
+      console.log(`💾 Updated file: ${filePath}`)
+      return true
+    }
+
+    return false
+  }
+ catch (error) {
+    console.error(`Error processing file ${filePath}:`, error.message)
+    return false
+  }
+}
+
+// Add command line argument support
+const targetFile = process.argv.find(arg => arg.startsWith('--file='))?.split('=')[1]
+const targetLang = process.argv.find(arg => arg.startsWith('--lang='))?.split('=')[1]
+const autoRemove = process.argv.includes('--auto-remove')
+
 async function main() {
   const compareKeysCount = async () => {
-    const targetKeys = await getKeysFromLanguage(targetLanguage)
-    const languagesKeys = await Promise.all(languages.map(language => getKeysFromLanguage(language)))
+    const allTargetKeys = await getKeysFromLanguage(targetLanguage)
+
+    // Filter target keys by file if specified
+    const targetKeys = targetFile
+      ? allTargetKeys.filter(key => key.startsWith(targetFile.replace(/[-_](.)/g, (_, c) => c.toUpperCase())))
+      : allTargetKeys
+
+    // Filter languages by target language if specified
+    const languagesToProcess = targetLang ? [targetLang] : languages
+
+    const allLanguagesKeys = await Promise.all(languagesToProcess.map(language => getKeysFromLanguage(language)))
+
+    // Filter language keys by file if specified
+    const languagesKeys = targetFile
+      ? allLanguagesKeys.map(keys => keys.filter(key => key.startsWith(targetFile.replace(/[-_](.)/g, (_, c) => c.toUpperCase()))))
+      : allLanguagesKeys
 
     const keysCount = languagesKeys.map(keys => keys.length)
     const targetKeysCount = targetKeys.length
 
-    const comparison = languages.reduce((result, language, index) => {
+    const comparison = languagesToProcess.reduce((result, language, index) => {
       const languageKeysCount = keysCount[index]
       const difference = targetKeysCount - languageKeysCount
       result[language] = difference
@@ -96,13 +262,52 @@ async function main() {
 
     console.log(comparison)
 
-    // Print missing keys
-    languages.forEach((language, index) => {
-      const missingKeys = targetKeys.filter(key => !languagesKeys[index].includes(key))
+    // Print missing keys and extra keys
+    for (let index = 0; index < languagesToProcess.length; index++) {
+      const language = languagesToProcess[index]
+      const languageKeys = languagesKeys[index]
+      const missingKeys = targetKeys.filter(key => !languageKeys.includes(key))
+      const extraKeys = languageKeys.filter(key => !targetKeys.includes(key))
+
       console.log(`Missing keys in ${language}:`, missingKeys)
-    })
+
+      // Show extra keys only when there are extra keys (negative difference)
+      if (extraKeys.length > 0) {
+        console.log(`Extra keys in ${language} (not in ${targetLanguage}):`, extraKeys)
+
+        // Auto-remove extra keys if flag is set
+        if (autoRemove) {
+          console.log(`\n🤖 Auto-removing extra keys from ${language}...`)
+
+          // Get all translation files
+          const i18nFolder = path.resolve(__dirname, '../i18n', language)
+          const files = fs.readdirSync(i18nFolder)
+            .filter(file => /\.ts$/.test(file))
+            .map(file => file.replace(/\.ts$/, ''))
+            .filter(f => !targetFile || f === targetFile) // Filter by target file if specified
+
+          let totalRemoved = 0
+          for (const fileName of files) {
+            const removed = await removeExtraKeysFromFile(language, fileName, extraKeys)
+            if (removed) totalRemoved++
+          }
+
+          console.log(`✅ Auto-removal completed for ${language}. Modified ${totalRemoved} files.`)
+        }
+      }
+    }
   }
 
+  console.log('🚀 Starting check-i18n script...')
+  if (targetFile)
+    console.log(`📁 Checking file: ${targetFile}`)
+
+  if (targetLang)
+    console.log(`🌍 Checking language: ${targetLang}`)
+
+  if (autoRemove)
+    console.log('🤖 Auto-remove mode: ENABLED')
+
   compareKeysCount()
 }
 

web/i18n/de-DE/app-debug.ts

@@ -276,7 +276,6 @@ const translation = {
     queryNoBeEmpty: 'Anfrage muss im Prompt gesetzt sein',
   },
   variableConfig: {
-    modalTitle: 'Feldeinstellungen',
     description: 'Einstellung für Variable {{varName}}',
     fieldType: 'Feldtyp',
     string: 'Kurztext',

web/i18n/de-DE/app.ts

@@ -2,7 +2,6 @@ const translation = {
   createApp: 'Neue App erstellen',
   types: {
     all: 'Alle',
-    assistant: 'Assistent',
     completion: 'Vervollständigung',
     workflow: 'Arbeitsablauf',
     agent: 'Agent',
@@ -11,8 +10,6 @@ const translation = {
     advanced: 'Chatflow',
   },
   modes: {
-    completion: 'Textgenerator',
-    chat: 'Basisassistent',
   },
   createFromConfigFile: 'App aus Konfigurationsdatei erstellen',
   deleteAppConfirmTitle: 'Diese App löschen?',
@@ -24,11 +21,8 @@ const translation = {
   communityIntro:
     'Diskutieren Sie mit Teammitgliedern, Mitwirkenden und Entwicklern auf verschiedenen Kanälen.',
   roadmap: 'Sehen Sie unseren Fahrplan',
-  appNamePlaceholder: 'Bitte geben Sie den Namen der App ein',
   newApp: {
-    startToCreate: 'Lassen Sie uns mit Ihrer neuen App beginnen',
     captionName: 'App-Symbol & Name',
-    captionAppType: 'Welchen Typ von App möchten Sie erstellen?',
     previewDemo: 'Vorschau-Demo',
     chatApp: 'Assistent',
     chatAppIntro:
@@ -46,25 +40,12 @@ const translation = {
     appTypeRequired: 'Bitte wählen Sie einen App-Typ',
     appCreated: 'App erstellt',
     appCreateFailed: 'Erstellen der App fehlgeschlagen',
-    basic: 'Grundlegend',
-    chatbotType: 'Chatbot-Orchestrierungsmethode',
-    workflowDescription: 'Erstellen Sie eine Anwendung, die qualitativ hochwertigen Text auf der Grundlage von Workflow-Orchestrierungen mit einem hohen Maß an Anpassung generiert. Es ist für erfahrene Benutzer geeignet.',
-    advancedFor: 'Für Fortgeschrittene',
     startFromTemplate: 'Aus Vorlage erstellen',
     appNamePlaceholder: 'Geben Sie Ihrer App einen Namen',
     startFromBlank: 'Aus Leer erstellen',
-    basicTip: 'Für Anfänger können Sie später zu Chatflow wechseln',
-    basicDescription: 'Basic Orchestrate ermöglicht die Orchestrierung einer Chatbot-App mit einfachen Einstellungen, ohne die Möglichkeit, integrierte Eingabeaufforderungen zu ändern. Es ist für Anfänger geeignet.',
     workflowWarning: 'Derzeit in der Beta-Phase',
-    advancedDescription: 'Workflow Orchestrate orchestriert Chatbots in Form von Workflows und bietet ein hohes Maß an Individualisierung, einschließlich der Möglichkeit, integrierte Eingabeaufforderungen zu bearbeiten. Es ist für erfahrene Benutzer geeignet.',
-    basicFor: 'FÜR ANFÄNGER',
-    completionWarning: 'Diese Art von App wird nicht mehr unterstützt.',
-    chatbotDescription: 'Erstellen Sie eine chatbasierte Anwendung. Diese App verwendet ein Frage-und-Antwort-Format, das mehrere Runden kontinuierlicher Konversation ermöglicht.',
     captionDescription: 'Beschreibung',
-    advanced: 'Chatflow',
     useTemplate: 'Diese Vorlage verwenden',
-    agentDescription: 'Erstellen Sie einen intelligenten Agenten, der autonom Werkzeuge auswählen kann, um die Aufgaben zu erledigen',
-    completionDescription: 'Erstellen Sie eine Anwendung, die qualitativ hochwertigen Text auf der Grundlage von Eingabeaufforderungen generiert, z. B. zum Generieren von Artikeln, Zusammenfassungen, Übersetzungen und mehr.',
     appDescriptionPlaceholder: 'Geben Sie die Beschreibung der App ein',
     caution: 'Vorsicht',
     Confirm: 'Bestätigen',

web/i18n/de-DE/billing.ts

@@ -23,18 +23,13 @@ const translation = {
     contractSales: 'Vertrieb kontaktieren',
     contractOwner: 'Teammanager kontaktieren',
     startForFree: 'Kostenlos starten',
-    getStartedWith: 'Beginnen Sie mit ',
     contactSales: 'Vertrieb kontaktieren',
     talkToSales: 'Mit dem Vertrieb sprechen',
     modelProviders: 'Modellanbieter',
-    teamMembers: 'Teammitglieder',
     buildApps: 'Apps bauen',
     vectorSpace: 'Vektorraum',
-    vectorSpaceBillingTooltip: 'Jedes 1MB kann ungefähr 1,2 Millionen Zeichen an vektorisierten Daten speichern (geschätzt mit OpenAI Embeddings, variiert je nach Modell).',
     vectorSpaceTooltip: 'Vektorraum ist das Langzeitspeichersystem, das erforderlich ist, damit LLMs Ihre Daten verstehen können.',
-    documentsUploadQuota: 'Dokumenten-Upload-Kontingent',
     documentProcessingPriority: 'Priorität der Dokumentenverarbeitung',
-    documentProcessingPriorityTip: 'Für eine höhere Dokumentenverarbeitungspriorität, bitte Ihren Tarif upgraden.',
     documentProcessingPriorityUpgrade: 'Mehr Daten mit höherer Genauigkeit bei schnelleren Geschwindigkeiten verarbeiten.',
     priority: {
       'standard': 'Standard',
@@ -103,61 +98,52 @@ const translation = {
     sandbox: {
       name: 'Sandbox',
       description: '200 mal GPT kostenlos testen',
-      includesTitle: 'Beinhaltet:',
       for: 'Kostenlose Testversion der Kernfunktionen',
     },
     professional: {
       name: 'Professionell',
       description: 'Für Einzelpersonen und kleine Teams, um mehr Leistung erschwinglich freizuschalten.',
-      includesTitle: 'Alles im kostenlosen Tarif, plus:',
       for: 'Für unabhängige Entwickler/kleine Teams',
     },
     team: {
       name: 'Team',
       description: 'Zusammenarbeiten ohne Grenzen und Top-Leistung genießen.',
-      includesTitle: 'Alles im Professionell-Tarif, plus:',
       for: 'Für mittelgroße Teams',
     },
     enterprise: {
       name: 'Unternehmen',
       description: 'Erhalten Sie volle Fähigkeiten und Unterstützung für großangelegte, missionskritische Systeme.',
       includesTitle: 'Alles im Team-Tarif, plus:',
-      features: {
-        2: 'Exklusive Unternehmensfunktionen',
-        8: 'Professioneller technischer Support',
-        6: 'Erweiterte Sicherheits- und Kontrollsysteme',
-        4: 'SSO',
-        0: 'Enterprise-Grade Skalierbare Bereitstellungslösungen',
-        3: 'Mehrere Arbeitsbereiche und Unternehmensverwaltung',
-        1: 'Kommerzielle Lizenzgenehmigung',
-        5: 'Verhandelte SLAs durch Dify-Partner',
-        7: 'Updates und Wartung von Dify offiziell',
-      },
       btnText: 'Vertrieb kontaktieren',
       price: 'Benutzerdefiniert',
       priceTip: 'Jährliche Abrechnung nur',
       for: 'Für große Teams',
+      features: [
+        'Skalierbare Bereitstellungslösungen in Unternehmensqualität',
+        'Kommerzielle Lizenzierung',
+        'Exklusive Enterprise-Funktionen',
+        'Mehrere Arbeitsbereiche und Unternehmensverwaltung',
+        'SSO (Single Sign-On)',
+        'Vereinbarte SLAs mit Dify-Partnern',
+        'Erweiterte Sicherheitsfunktionen und Kontrollen',
+        'Offizielle Updates und Wartung durch Dify',
+        'Professioneller technischer Support',
+      ],
     },
     community: {
-      features: {
-        2: 'Entspricht der Dify Open Source Lizenz',
-        1: 'Einzelner Arbeitsbereich',
-        0: 'Alle Kernfunktionen wurden im öffentlichen Repository veröffentlicht.',
-      },
       description: 'Für Einzelbenutzer, kleine Teams oder nicht-kommerzielle Projekte',
       for: 'Für Einzelbenutzer, kleine Teams oder nicht-kommerzielle Projekte',
       btnText: 'Beginnen Sie mit der Gemeinschaft',
       price: 'Kostenlos',
       includesTitle: 'Kostenlose Funktionen:',
       name: 'Gemeinschaft',
+      features: [
+        'Alle Kernfunktionen im öffentlichen Repository veröffentlicht',
+        'Einzelner Arbeitsbereich',
+        'Entspricht der Dify Open-Source-Lizenz',
+      ],
     },
     premium: {
-      features: {
-        2: 'WebApp-Logo und Branding-Anpassung',
-        0: 'Selbstverwaltete Zuverlässigkeit durch verschiedene Cloud-Anbieter',
-        3: 'Priorisierte E-Mail- und Chat-Unterstützung',
-        1: 'Einzelner Arbeitsbereich',
-      },
       includesTitle: 'Alles aus der Community, plus:',
       name: 'Premium',
       priceTip: 'Basierend auf dem Cloud-Marktplatz',
@@ -166,6 +152,12 @@ const translation = {
       comingSoon: 'Microsoft Azure- und Google Cloud-Support demnächst verfügbar',
       description: 'Für mittelgroße Organisationen und Teams',
       price: 'Skalierbar',
+      features: [
+        'Selbstverwaltete Zuverlässigkeit durch verschiedene Cloud-Anbieter',
+        'Einzelner Arbeitsbereich',
+        'Anpassung von WebApp-Logo und Branding',
+        'Bevorzugter E-Mail- und Chat-Support',
+      ],
     },
   },
   vectorSpace: {
@@ -173,8 +165,6 @@ const translation = {
     fullSolution: 'Upgraden Sie Ihren Tarif, um mehr Speicherplatz zu erhalten.',
   },
   apps: {
-    fullTipLine1: 'Upgraden Sie Ihren Tarif, um',
-    fullTipLine2: 'mehr Apps zu bauen.',
     contactUs: 'Kontaktieren Sie uns',
     fullTip1: 'Upgrade, um mehr Apps zu erstellen',
     fullTip2des: 'Es wird empfohlen, inaktive Anwendungen zu bereinigen, um Speicherplatz freizugeben, oder uns zu kontaktieren.',

web/i18n/de-DE/common.ts

@@ -197,7 +197,6 @@ const translation = {
     showAppLength: '{{length}} Apps anzeigen',
     delete: 'Konto löschen',
     deleteTip: 'Wenn Sie Ihr Konto löschen, werden alle Ihre Daten dauerhaft gelöscht und können nicht wiederhergestellt werden.',
-    deleteConfirmTip: 'Zur Bestätigung senden Sie bitte Folgendes von Ihrer registrierten E-Mail-Adresse an ',
     myAccount: 'Mein Konto',
     studio: 'Dify Studio',
     account: 'Konto',

web/i18n/de-DE/dataset-creation.ts

@@ -1,8 +1,6 @@
 const translation = {
   steps: {
     header: {
-      creation: 'Wissen erstellen',
-      update: 'Daten hinzufügen',
       fallbackRoute: 'Wissen',
     },
     one: 'Datenquelle wählen',

web/i18n/de-DE/dataset-documents.ts

@@ -146,7 +146,6 @@ const translation = {
         journalConferenceName: 'Zeitschrift/Konferenzname',
         volumeIssuePage: 'Band/Ausgabe/Seite',
         DOI: 'DOI',
-        topicKeywords: 'Themen/Schlüsselwörter',
         abstract: 'Zusammenfassung',
         topicsKeywords: 'Themen/Stichworte',
       },
@@ -343,7 +342,6 @@ const translation = {
     keywords: 'Schlüsselwörter',
     addKeyWord: 'Schlüsselwort hinzufügen',
     keywordError: 'Die maximale Länge des Schlüsselworts beträgt 20',
-    characters: 'Zeichen',
     hitCount: 'Abrufanzahl',
     vectorHash: 'Vektor-Hash: ',
     questionPlaceholder: 'Frage hier hinzufügen',

web/i18n/de-DE/dataset-hit-testing.ts

@@ -2,7 +2,6 @@ const translation = {
   title: 'Abruf-Test',
   desc: 'Testen Sie die Treffereffektivität des Wissens anhand des gegebenen Abfragetextes.',
   dateTimeFormat: 'MM/DD/YYYY hh:mm A',
-  recents: 'Kürzlich',
   table: {
     header: {
       source: 'Quelle',

web/i18n/de-DE/login.ts

@@ -70,7 +70,6 @@ const translation = {
   activated: 'Jetzt anmelden',
   adminInitPassword: 'Admin-Initialpasswort',
   validate: 'Validieren',
-  sso: 'Mit SSO fortfahren',
   checkCode: {
     didNotReceiveCode: 'Sie haben den Code nicht erhalten?',
     verificationCodePlaceholder: 'Geben Sie den 6-stelligen Code ein',

web/i18n/de-DE/run-log.ts

@@ -21,7 +21,6 @@ const translation = {
   resultEmpty: {
     title: 'Dieser Lauf gibt nur das JSON-Format aus',
     tipLeft: 'Bitte gehen Sie zum ',
-    Link: 'Detailpanel',
     tipRight: 'ansehen.',
     link: 'Gruppe Detail',
   },

web/i18n/de-DE/tools.ts

@@ -54,7 +54,6 @@ const translation = {
       keyTooltip: 'Http Header Key, Sie können es bei "Authorization" belassen, wenn Sie nicht wissen, was es ist, oder auf einen benutzerdefinierten Wert setzen',
       types: {
         none: 'Keine',
-        api_key: 'API-Key',
         apiKeyPlaceholder: 'HTTP-Headername für API-Key',
         apiValuePlaceholder: 'API-Key eingeben',
         api_key_header: 'Kopfzeile',

web/i18n/de-DE/workflow.ts

@@ -104,10 +104,8 @@ const translation = {
     loadMore: 'Weitere Workflows laden',
     noHistory: 'Keine Geschichte',
     exportSVG: 'Als SVG exportieren',
-    noExist: 'Keine solche Variable',
     versionHistory: 'Versionsverlauf',
     publishUpdate: 'Update veröffentlichen',
-    referenceVar: 'Referenzvariable',
     exportImage: 'Bild exportieren',
     exportJPEG: 'Als JPEG exportieren',
     exitVersions: 'Ausgangsversionen',
@@ -222,7 +220,6 @@ const translation = {
   tabs: {
     'tools': 'Werkzeuge',
     'allTool': 'Alle',
-    'builtInTool': 'Eingebaut',
     'customTool': 'Benutzerdefiniert',
     'workflowTool': 'Arbeitsablauf',
     'question-understand': 'Fragen verstehen',
@@ -587,7 +584,6 @@ const translation = {
         'not empty': 'ist nicht leer',
         'null': 'ist null',
         'not null': 'ist nicht null',
-        'regex match': 'Regex-Übereinstimmung',
         'not exists': 'existiert nicht',
         'in': 'in',
         'all of': 'alle',
@@ -610,7 +606,6 @@ const translation = {
       },
       select: 'Auswählen',
       addSubVariable: 'Untervariable',
-      condition: 'Bedingung',
     },
     variableAssigner: {
       title: 'Variablen zuweisen',

web/i18n/en-US/app-annotation.ts

@@ -57,6 +57,16 @@ const translation = {
     error: 'Import Error',
     ok: 'OK',
   },
+  list: {
+    delete: {
+      title: 'Are you sure Delete?',
+    },
+  },
+  batchAction: {
+    selected: 'Selected',
+    delete: 'Delete',
+    cancel: 'Cancel',
+  },
   errorMessage: {
     answerRequired: 'Answer is required',
     queryRequired: 'Question is required',

web/i18n/es-ES/app-debug.ts

@@ -227,21 +227,6 @@ const translation = {
     },
   },
   automatic: {
-    title: 'Orquestación automatizada de aplicaciones',
-    description: 'Describe tu escenario, Dify orquestará una aplicación para ti.',
-    intendedAudience: '¿Quién es el público objetivo?',
-    intendedAudiencePlaceHolder: 'p.ej. Estudiante',
-    solveProblem: '¿Qué problemas esperan que la IA pueda resolver para ellos?',
-    solveProblemPlaceHolder: 'p.ej. Extraer ideas y resumir información de informes y artículos largos',
-    generate: 'Generar',
-    audiencesRequired: 'Audiencia requerida',
-    problemRequired: 'Problema requerido',
-    resTitle: 'Hemos orquestado la siguiente aplicación para ti.',
-    apply: 'Aplicar esta orquestación',
-    noData: 'Describe tu caso de uso a la izquierda, la vista previa de la orquestación se mostrará aquí.',
-    loading: 'Orquestando la aplicación para ti...',
-    overwriteTitle: '¿Sobrescribir configuración existente?',
-    overwriteMessage: 'Aplicar esta orquestación sobrescribirá la configuración existente.',
   },
   resetConfig: {
     title: '¿Confirmar restablecimiento?',

web/i18n/es-ES/app.ts

@@ -27,21 +27,7 @@ const translation = {
   newApp: {
     startFromBlank: 'Crear desde cero',
     startFromTemplate: 'Crear desde plantilla',
-    captionAppType: '¿Qué tipo de app quieres crear?',
-    chatbotDescription: 'Crea una aplicación basada en chat. Esta app utiliza un formato de pregunta y respuesta, permitiendo múltiples rondas de conversación continua.',
-    completionDescription: 'Crea una aplicación que genera texto de alta calidad basado en prompts, como la generación de artículos, resúmenes, traducciones y más.',
-    completionWarning: 'Este tipo de app ya no será compatible.',
-    agentDescription: 'Crea un Agente inteligente que puede elegir herramientas de forma autónoma para completar tareas',
-    workflowDescription: 'Crea una aplicación que genera texto de alta calidad basado en flujos de trabajo con un alto grado de personalización. Es adecuado para usuarios experimentados.',
     workflowWarning: 'Actualmente en beta',
-    chatbotType: 'Método de orquestación del Chatbot',
-    basic: 'Básico',
-    basicTip: 'Para principiantes, se puede cambiar a Chatflow más adelante',
-    basicFor: 'PARA PRINCIPIANTES',
-    basicDescription: 'La Orquestación Básica permite la orquestación de una app de Chatbot utilizando configuraciones simples, sin la capacidad de modificar los prompts incorporados. Es adecuado para principiantes.',
-    advanced: 'Chatflow',
-    advancedFor: 'Para usuarios avanzados',
-    advancedDescription: 'La Orquestación de Flujo de Trabajo orquesta Chatbots en forma de flujos de trabajo, ofreciendo un alto grado de personalización, incluida la capacidad de editar los prompts incorporados. Es adecuado para usuarios experimentados.',
     captionName: 'Icono y nombre de la app',
     appNamePlaceholder: 'Asigna un nombre a tu app',
     captionDescription: 'Descripción',

web/i18n/es-ES/billing.ts

@@ -23,19 +23,14 @@ const translation = {
     contractSales: 'Contactar ventas',
     contractOwner: 'Contactar al administrador del equipo',
     startForFree: 'Empezar gratis',
-    getStartedWith: 'Empezar con ',
     contactSales: 'Contactar Ventas',
     talkToSales: 'Hablar con Ventas',
     modelProviders: 'Proveedores de Modelos',
-    teamMembers: 'Miembros del Equipo',
     annotationQuota: 'Cuota de Anotación',
     buildApps: 'Crear Aplicaciones',
     vectorSpace: 'Espacio Vectorial',
-    vectorSpaceBillingTooltip: 'Cada 1MB puede almacenar aproximadamente 1.2 millones de caracteres de datos vectorizados (estimado utilizando OpenAI Embeddings, varía según los modelos).',
     vectorSpaceTooltip: 'El Espacio Vectorial es el sistema de memoria a largo plazo necesario para que los LLMs comprendan tus datos.',
-    documentsUploadQuota: 'Cuota de Carga de Documentos',
     documentProcessingPriority: 'Prioridad de Procesamiento de Documentos',
-    documentProcessingPriorityTip: 'Para una mayor prioridad de procesamiento de documentos, por favor actualiza tu plan.',
     documentProcessingPriorityUpgrade: 'Procesa más datos con mayor precisión y velocidad.',
     priority: {
       'standard': 'Estándar',
@@ -103,61 +98,52 @@ const translation = {
     sandbox: {
       name: 'Sandbox',
       description: 'Prueba gratuita de 200 veces GPT',
-      includesTitle: 'Incluye:',
       for: 'Prueba gratuita de capacidades básicas',
     },
     professional: {
       name: 'Profesional',
       description: 'Para individuos y pequeños equipos que desean desbloquear más poder de manera asequible.',
-      includesTitle: 'Todo en el plan gratuito, más:',
       for: 'Para desarrolladores independientes/equipos pequeños',
     },
     team: {
       name: 'Equipo',
       description: 'Colabora sin límites y disfruta de un rendimiento de primera categoría.',
-      includesTitle: 'Todo en el plan Profesional, más:',
       for: 'Para equipos de tamaño mediano',
     },
     enterprise: {
       name: 'Empresa',
       description: 'Obtén capacidades completas y soporte para sistemas críticos a gran escala.',
       includesTitle: 'Todo en el plan Equipo, más:',
-      features: {
-        0: 'Soluciones de implementación escalables de nivel empresarial',
-        7: 'Actualizaciones y Mantenimiento por Dify Oficialmente',
-        8: 'Soporte Técnico Profesional',
-        3: 'Múltiples Espacios de Trabajo y Gestión Empresarial',
-        1: 'Autorización de Licencia Comercial',
-        2: 'Características Exclusivas de la Empresa',
-        5: 'SLA negociados por Dify Partners',
-        4: 'SSO',
-        6: 'Seguridad y Controles Avanzados',
-      },
       btnText: 'Contactar ventas',
       for: 'Para equipos de gran tamaño',
       price: 'Personalizado',
       priceTip: 'Facturación Anual Solo',
+      features: [
+        'Soluciones de implementación escalables a nivel empresarial',
+        'Autorización de licencia comercial',
+        'Funciones exclusivas para empresas',
+        'Múltiples espacios de trabajo y gestión empresarial',
+        'SSO (inicio de sesión único)',
+        'SLAs negociados con socios de Dify',
+        'Seguridad y controles avanzados',
+        'Actualizaciones y mantenimiento oficiales por parte de Dify',
+        'Soporte técnico profesional',
+      ],
     },
     community: {
-      features: {
-        0: 'Todas las características principales se lanzaron bajo el repositorio público',
-        2: 'Cumple con la Licencia de Código Abierto de Dify',
-        1: 'Espacio de trabajo único',
-      },
       includesTitle: 'Características gratuitas:',
       for: 'Para usuarios individuales, pequeños equipos o proyectos no comerciales',
       price: 'Gratis',
       btnText: 'Comienza con la Comunidad',
       name: 'Comunidad',
       description: 'Para usuarios individuales, pequeños equipos o proyectos no comerciales',
+      features: [
+        'Todas las funciones principales publicadas en el repositorio público',
+        'Espacio de trabajo único',
+        'Cumple con la licencia de código abierto de Dify',
+      ],
     },
     premium: {
-      features: {
-        0: 'Confiabilidad autogestionada por varios proveedores de nube',
-        1: 'Espacio de trabajo único',
-        3: 'Soporte prioritario por correo electrónico y chat',
-        2: 'Personalización de logotipos y marcas de WebApp',
-      },
       description: 'Para organizaciones y equipos de tamaño mediano',
       comingSoon: 'Soporte de Microsoft Azure y Google Cloud disponible próximamente',
       btnText: 'Obtén Premium en',
@@ -166,6 +152,12 @@ const translation = {
       includesTitle: 'Todo de Community, además:',
       name: 'Premium',
       for: 'Para organizaciones y equipos de tamaño mediano',
+      features: [
+        'Fiabilidad autogestionada mediante varios proveedores de nube',
+        'Espacio de trabajo único',
+        'Personalización del logotipo y la marca de la aplicación web',
+        'Soporte prioritario por correo electrónico y chat',
+      ],
     },
   },
   vectorSpace: {
@@ -173,8 +165,6 @@ const translation = {
     fullSolution: 'Actualiza tu plan para obtener más espacio.',
   },
   apps: {
-    fullTipLine1: 'Actualiza tu plan para',
-    fullTipLine2: 'crear más aplicaciones.',
     fullTip1des: 'Has alcanzado el límite de aplicaciones de construcción en este plan',
     fullTip2des: 'Se recomienda limpiar las aplicaciones inactivas para liberar espacio de uso, o contactarnos.',
     fullTip1: 'Actualiza para crear más aplicaciones',

web/i18n/es-ES/common.ts

@@ -201,7 +201,6 @@ const translation = {
     showAppLength: 'Mostrar {{length}} apps',
     delete: 'Eliminar cuenta',
     deleteTip: 'Eliminar tu cuenta borrará permanentemente todos tus datos y no se podrán recuperar.',
-    deleteConfirmTip: 'Para confirmar, por favor envía lo siguiente desde tu correo electrónico registrado a ',
     account: 'Cuenta',
     myAccount: 'Mi Cuenta',
     studio: 'Estudio Dify',

web/i18n/es-ES/dataset-creation.ts

@@ -1,8 +1,6 @@
 const translation = {
   steps: {
     header: {
-      creation: 'Crear conocimiento',
-      update: 'Agregar datos',
       fallbackRoute: 'Conocimiento',
     },
     one: 'Elegir fuente de datos',

web/i18n/es-ES/dataset-documents.ts

@@ -342,7 +342,6 @@ const translation = {
     keywords: 'Palabras clave',
     addKeyWord: 'Agregar palabra clave',
     keywordError: 'La longitud máxima de la palabra clave es 20',
-    characters: 'caracteres',
     hitCount: 'Cantidad de recuperación',
     vectorHash: 'Hash de vector: ',
     questionPlaceholder: 'agregar pregunta aquí',

web/i18n/es-ES/dataset-hit-testing.ts

@@ -2,7 +2,6 @@ const translation = {
   title: 'Prueba de recuperación',
   desc: 'Prueba del efecto de impacto del conocimiento basado en el texto de consulta proporcionado.',
   dateTimeFormat: 'MM/DD/YYYY hh:mm A',
-  recents: 'Recientes',
   table: {
     header: {
       source: 'Fuente',

web/i18n/es-ES/login.ts

@@ -9,7 +9,6 @@ const translation = {
   namePlaceholder: 'Tu nombre de usuario',
   forget: '¿Olvidaste tu contraseña?',
   signBtn: 'Iniciar sesión',
-  sso: 'Continuar con SSO',
   installBtn: 'Configurar',
   setAdminAccount: 'Configurando una cuenta de administrador',
   setAdminAccountDesc: 'Privilegios máximos para la cuenta de administrador, que se puede utilizar para crear aplicaciones y administrar proveedores de LLM, etc.',

web/i18n/es-ES/tools.ts

@@ -82,7 +82,6 @@ const translation = {
       keyTooltip: 'Clave del encabezado HTTP, puedes dejarla como "Authorization" si no tienes idea de qué es o configurarla con un valor personalizado',
       types: {
         none: 'Ninguno',
-        api_key: 'Clave API',
         apiKeyPlaceholder: 'Nombre del encabezado HTTP para la Clave API',
         apiValuePlaceholder: 'Ingresa la Clave API',
         api_key_header: 'Encabezado',

web/i18n/es-ES/workflow.ts

@@ -108,9 +108,7 @@ const translation = {
     exitVersions: 'Versiones de salida',
     exportJPEG: 'Exportar como JPEG',
     exportPNG: 'Exportar como PNG',
-    referenceVar: 'Variable de referencia',
     publishUpdate: 'Publicar actualización',
-    noExist: 'No existe tal variable',
     exportImage: 'Exportar imagen',
     needAnswerNode: 'Se debe agregar el nodo de respuesta',
     needEndNode: 'Se debe agregar el nodo Final',
@@ -222,7 +220,6 @@ const translation = {
   tabs: {
     'tools': 'Herramientas',
     'allTool': 'Todos',
-    'builtInTool': 'Incorporadas',
     'customTool': 'Personalizadas',
     'workflowTool': 'Flujo de trabajo',
     'question-understand': 'Entender pregunta',
@@ -587,7 +584,6 @@ const translation = {
         'not empty': 'no está vacío',
         'null': 'es nulo',
         'not null': 'no es nulo',
-        'regex match': 'Coincidencia de expresiones regulares',
         'not in': 'no en',
         'in': 'en',
         'exists': 'Existe',
@@ -610,7 +606,6 @@ const translation = {
       },
       select: 'Escoger',
       addSubVariable: 'Sub Variable',
-      condition: 'Condición',
     },
     variableAssigner: {
       title: 'Asignar variables',
@@ -771,9 +766,6 @@ const translation = {
         showAuthor: 'Mostrar autor',
       },
     },
-    tracing: {
-      stopBy: 'Detenido por {{user}}',
-    },
     docExtractor: {
       outputVars: {
         text: 'Texto extraído',
@@ -905,7 +897,7 @@ const translation = {
     },
   },
   tracing: {
-    stopBy: 'Pásate por {{usuario}}',
+    stopBy: 'Pásate por {{user}}',
   },
   variableReference: {
     noAvailableVars: 'No hay variables disponibles',