feat: enhance online drive connection UI and add localization for connection status in dataset pipeline

Co-authored-by: lizb <[email protected]>

.devcontainer/Dockerfile

@@ -1,5 +1,4 @@
 FROM mcr.microsoft.com/devcontainers/python:3.12
 
-# [Optional] Uncomment this section to install additional OS packages.
-# RUN apt-get update && export DEBIAN_FRONTEND=noninteractive \
-#     && apt-get -y install --no-install-recommends <your-package-list-here>
+RUN apt-get update && export DEBIAN_FRONTEND=noninteractive \
+     && apt-get -y install libgmp-dev libmpfr-dev libmpc-dev

.devcontainer/post_create_command.sh

@@ -1,12 +1,13 @@
 #!/bin/bash
 
-npm add -g pnpm@10.8.0
+npm add -g pnpm@10.11.1
 cd web && pnpm install
 pipx install uv
 
 echo 'alias start-api="cd /workspaces/dify/api && uv run python -m flask run --host 0.0.0.0 --port=5001 --debug"' >> ~/.bashrc
 echo 'alias start-worker="cd /workspaces/dify/api && uv run python -m celery -A app.celery worker -P gevent -c 1 --loglevel INFO -Q dataset,generation,mail,ops_trace,app_deletion"' >> ~/.bashrc
 echo 'alias start-web="cd /workspaces/dify/web && pnpm dev"' >> ~/.bashrc
+echo 'alias start-web-prod="cd /workspaces/dify/web && pnpm build && pnpm start"' >> ~/.bashrc
 echo 'alias start-containers="cd /workspaces/dify/docker && docker-compose -f docker-compose.middleware.yaml -p dify --env-file middleware.env up -d"' >> ~/.bashrc
 echo 'alias stop-containers="cd /workspaces/dify/docker && docker-compose -f docker-compose.middleware.yaml -p dify --env-file middleware.env down"' >> ~/.bashrc
 

.github/actions/setup-uv/action.yml

@@ -8,7 +8,7 @@ inputs:
   uv-version:
     description: UV version to set up
     required: true
-    default: '0.6.14'
+    default: '~=0.7.11'
   uv-lockfile:
     description: Path to the UV lockfile to restore cache from
     required: true

.github/pull_request_template.md

@@ -1,25 +1,23 @@
-# Summary
+> [!IMPORTANT]
+>
+> 1. Make sure you have read our [contribution guidelines](https://github.com/langgenius/dify/blob/main/CONTRIBUTING.md)
+> 2. Ensure there is an associated issue and you have been assigned to it
+> 3. Use the correct syntax to link this PR: `Fixes #<issue number>`.
 
-Please include a summary of the change and which issue is fixed. Please also include relevant motivation and context. List any dependencies that are required for this change.
+## Summary
 
-> [!Tip]
-> Close issue syntax: `Fixes #<issue number>` or `Resolves #<issue number>`, see [documentation](https://docs.github.com/en/issues/tracking-your-work-with-issues/linking-a-pull-request-to-an-issue#linking-a-pull-request-to-an-issue-using-a-keyword) for more details.
+<!-- Please include a summary of the change and which issue is fixed. Please also include relevant motivation and context. List any dependencies that are required for this change. -->
 
-
-# Screenshots
+## Screenshots
 
 | Before | After |
 |--------|-------|
 | ...    | ...   |
 
-# Checklist
-
-> [!IMPORTANT]  
-> Please review the checklist below before submitting your pull request.
+## Checklist
 
 - [ ] This change requires a documentation update, included: [Dify Document](https://github.com/langgenius/dify-docs)
 - [x] I understand that this PR may be closed in case there was no previous discussion or issues. (This doesn't apply to typos!)
 - [x] I've added a test for each change that was introduced, and I tried as much as possible to make a single atomic change.
 - [x] I've updated the documentation accordingly.
 - [x] I ran `dev/reformat`(backend) and `cd web && npx lint-staged`(frontend) to appease the lint gods
-

.github/workflows/build-push.yml

@@ -6,6 +6,7 @@ on:
       - "main"
       - "deploy/dev"
       - "deploy/enterprise"
+      - "feat/rag-pipeline"
     tags:
       - "*"
 

.github/workflows/deploy-rag-dev.yml

@@ -0,0 +1,28 @@
+name: Deploy RAG Dev
+
+permissions:
+  contents: read
+
+on:
+  workflow_run:
+    workflows: ["Build and Push API & Web"]
+    branches:
+      - "deploy/rag-dev"
+    types:
+      - completed
+
+jobs:
+  deploy:
+    runs-on: ubuntu-latest
+    if: |
+      github.event.workflow_run.conclusion == 'success' &&
+      github.event.workflow_run.head_branch == 'deploy/rag-dev'
+    steps:
+      - name: Deploy to server
+        uses: appleboy/[email protected]
+        with:
+          host: ${{ secrets.RAG_SSH_HOST }}
+          username: ${{ secrets.SSH_USER }}
+          key: ${{ secrets.SSH_PRIVATE_KEY }}
+          script: |
+            ${{ vars.SSH_SCRIPT || secrets.SSH_SCRIPT }}

.github/workflows/expose_service_ports.sh

@@ -10,6 +10,7 @@ yq eval '.services["elasticsearch"].ports += ["9200:9200"]' -i docker/docker-com
 yq eval '.services.couchbase-server.ports += ["8091-8096:8091-8096"]' -i docker/docker-compose.yaml
 yq eval '.services.couchbase-server.ports += ["11210:11210"]' -i docker/docker-compose.yaml
 yq eval '.services.tidb.ports += ["4000:4000"]' -i docker/tidb/docker-compose.yaml
+yq eval '.services.oceanbase.ports += ["2881:2881"]' -i docker/docker-compose.yaml
 yq eval '.services.opengauss.ports += ["6600:6600"]' -i docker/docker-compose.yaml
 
 echo "Ports exposed for sandbox, weaviate, tidb, qdrant, chroma, milvus, pgvector, pgvecto-rs, elasticsearch, couchbase, opengauss"

.github/workflows/style.yml

@@ -139,6 +139,7 @@ jobs:
       - name: Checkout code
         uses: actions/checkout@v4
         with:
+          fetch-depth: 0
           persist-credentials: false
 
       - name: Check changed files

.github/workflows/translate-i18n-base-on-english.yml

@@ -31,11 +31,19 @@ jobs:
             echo "FILES_CHANGED=false" >> $GITHUB_ENV
           fi
 
+      - name: Install pnpm
+        uses: pnpm/action-setup@v4
+        with:
+          version: 10
+          run_install: false
+
       - name: Set up Node.js
         if: env.FILES_CHANGED == 'true'
         uses: actions/setup-node@v4
         with:
           node-version: 'lts/*'
+          cache: pnpm
+          cache-dependency-path: ./web/package.json
 
       - name: Install dependencies
         if: env.FILES_CHANGED == 'true'

.github/workflows/vdb-tests.yml

@@ -31,6 +31,13 @@ jobs:
         with:
           persist-credentials: false
 
+      - name: Free Disk Space
+        uses: endersonmenezes/free-disk-space@v2
+        with:
+          remove_dotnet: true
+          remove_haskell: true
+          remove_tool_cache: true
+
       - name: Setup UV and Python
         uses: ./.github/actions/setup-uv
         with:
@@ -59,7 +66,7 @@ jobs:
             tidb
             tiflash
 
-      - name: Set up Vector Stores (Weaviate, Qdrant, PGVector, Milvus, PgVecto-RS, Chroma, MyScale, ElasticSearch, Couchbase)
+      - name: Set up Vector Stores (Weaviate, Qdrant, PGVector, Milvus, PgVecto-RS, Chroma, MyScale, ElasticSearch, Couchbase, OceanBase)
         uses: hoverkraft-tech/[email protected]
         with:
           compose-file: |
@@ -75,8 +82,9 @@ jobs:
             pgvector
             chroma
             elasticsearch
+            oceanbase
 
-      - name: Check TiDB Ready
+      - name: Check VDB Ready (TiDB)
         run: uv run --project api python api/tests/integration_tests/vdb/tidb_vector/check_tiflash_ready.py
 
       - name: Test Vector Stores

.gitignore

@@ -179,6 +179,7 @@ docker/volumes/pgvecto_rs/data/*
 docker/volumes/couchbase/*
 docker/volumes/oceanbase/*
 docker/volumes/plugin_daemon/*
+docker/volumes/matrixone/*
 !docker/volumes/oceanbase/init.d
 
 docker/nginx/conf.d/default.conf
@@ -192,12 +193,12 @@ sdks/python-client/dist
 sdks/python-client/dify_client.egg-info
 
 .vscode/*
-!.vscode/launch.json
+!.vscode/launch.json.template
+!.vscode/README.md
 pyrightconfig.json
 api/.vscode
 
 .idea/
-.vscode
 
 # pnpm
 /.pnpm-store
@@ -207,3 +208,9 @@ plugins.jsonl
 
 # mise
 mise.toml
+
+# Next.js build output
+.next/
+
+# AI Assistant
+.roo/

.vscode/README.md

@@ -0,0 +1,14 @@
+# Debugging with VS Code
+
+This `launch.json.template` file provides various debug configurations for the Dify project within VS Code / Cursor. To use these configurations, you should copy the contents of this file into a new file named `launch.json` in the same `.vscode` directory.
+
+## How to Use
+
+1.  **Create `launch.json`**: If you don't have one, create a file named `launch.json` inside the `.vscode` directory.
+2.  **Copy Content**: Copy the entire content from `launch.json.template` into your newly created `launch.json` file.
+3.  **Select Debug Configuration**: Go to the Run and Debug view in VS Code / Cursor (Ctrl+Shift+D or Cmd+Shift+D).
+4.  **Start Debugging**: Select the desired configuration from the dropdown menu and click the green play button.
+
+## Tips
+
+- If you need to debug with Edge browser instead of Chrome, modify the `serverReadyAction` configuration in the "Next.js: debug full stack" section, change `"debugWithChrome"` to `"debugWithEdge"` to use Microsoft Edge for debugging.

.vscode/launch.json.template

@@ -0,0 +1,68 @@
+{
+    "version": "0.2.0",
+    "configurations": [
+        {
+            "name": "Python: Flask API",
+            "type": "debugpy",
+            "request": "launch",
+            "module": "flask",
+            "env": {
+                "FLASK_APP": "app.py",
+                "FLASK_ENV": "development",
+                "GEVENT_SUPPORT": "True"
+            },
+            "args": [
+                "run",
+                "--host=0.0.0.0",
+                "--port=5001",
+                "--no-debugger",
+                "--no-reload"
+            ],
+            "jinja": true,
+            "justMyCode": true,
+            "cwd": "${workspaceFolder}/api",
+            "python": "${workspaceFolder}/api/.venv/bin/python"
+        },
+        {
+            "name": "Python: Celery Worker (Solo)",
+            "type": "debugpy",
+            "request": "launch",
+            "module": "celery",
+            "env": {
+                "GEVENT_SUPPORT": "True"
+            },
+            "args": [
+                "-A",
+                "app.celery",
+                "worker",
+                "-P",
+                "solo",
+                "-c",
+                "1",
+                "-Q",
+                "dataset,generation,mail,ops_trace",
+                "--loglevel",
+                "INFO"
+            ],
+            "justMyCode": false,
+            "cwd": "${workspaceFolder}/api",
+            "python": "${workspaceFolder}/api/.venv/bin/python"
+        },
+        {
+            "name": "Next.js: debug full stack",
+            "type": "node",
+            "request": "launch",
+            "program": "${workspaceFolder}/web/node_modules/next/dist/bin/next",
+            "runtimeArgs": ["--inspect"],
+            "skipFiles": ["<node_internals>/**"],
+            "serverReadyAction": {
+              "action": "debugWithChrome",
+              "killOnServerStop": true,
+              "pattern": "- Local:.+(https?://.+)",
+              "uriFormat": "%s",
+              "webRoot": "${workspaceFolder}/web"
+            },
+            "cwd": "${workspaceFolder}/web"
+          }
+    ]
+}

README.md

@@ -226,6 +226,11 @@ Deploy Dify to AWS with [CDK](https://aws.amazon.com/cdk/)
 
 - [AWS CDK by @KevinZhao](https://github.com/aws-samples/solution-for-deploying-dify-on-aws)
 
+#### Using Alibaba Cloud Computing Nest
+
+Quickly deploy Dify to Alibaba cloud with [Alibaba Cloud Computing Nest](https://computenest.console.aliyun.com/service/instance/create/default?type=user&ServiceName=Dify%E7%A4%BE%E5%8C%BA%E7%89%88) 
+
+
 ## Contributing
 
 For those who'd like to contribute code, see our [Contribution Guide](https://github.com/langgenius/dify/blob/main/CONTRIBUTING.md).
@@ -235,7 +240,7 @@ At the same time, please consider supporting Dify by sharing it on social media
 
 ## Community & contact
 
-- [Github Discussion](https://github.com/langgenius/dify/discussions). Best for: sharing feedback and asking questions.
+- [GitHub Discussion](https://github.com/langgenius/dify/discussions). Best for: sharing feedback and asking questions.
 - [GitHub Issues](https://github.com/langgenius/dify/issues). Best for: bugs you encounter using Dify.AI, and feature proposals. See our [Contribution Guide](https://github.com/langgenius/dify/blob/main/CONTRIBUTING.md).
 - [Discord](https://discord.gg/FngNHpbcY7). Best for: sharing your applications and hanging out with the community.
 - [X(Twitter)](https://twitter.com/dify_ai). Best for: sharing your applications and hanging out with the community.

README_AR.md

@@ -209,6 +209,9 @@ docker compose up -d
 
 - [AWS CDK بواسطة @KevinZhao](https://github.com/aws-samples/solution-for-deploying-dify-on-aws)
 
+#### استخدام Alibaba Cloud للنشر
+ [بسرعة نشر Dify إلى سحابة علي بابا مع عش الحوسبة السحابية علي بابا](https://computenest.console.aliyun.com/service/instance/create/default?type=user&ServiceName=Dify%E7%A4%BE%E5%8C%BA%E7%89%88)
+
 ## المساهمة
 
 لأولئك الذين يرغبون في المساهمة، انظر إلى [دليل المساهمة](https://github.com/langgenius/dify/blob/main/CONTRIBUTING.md) لدينا.
@@ -223,7 +226,7 @@ docker compose up -d
 </a>
 
 ## المجتمع والاتصال
-- [مناقشة Github](https://github.com/langgenius/dify/discussions). الأفضل لـ: مشاركة التعليقات وطرح الأسئلة.
+- [مناقشة GitHub](https://github.com/langgenius/dify/discussions). الأفضل لـ: مشاركة التعليقات وطرح الأسئلة.
 - [المشكلات على GitHub](https://github.com/langgenius/dify/issues). الأفضل لـ: الأخطاء التي تواجهها في استخدام Dify.AI، واقتراحات الميزات. انظر [دليل المساهمة](https://github.com/langgenius/dify/blob/main/CONTRIBUTING.md).
 - [Discord](https://discord.gg/FngNHpbcY7). الأفضل لـ: مشاركة تطبيقاتك والترفيه مع المجتمع.
 - [تويتر](https://twitter.com/dify_ai). الأفضل لـ: مشاركة تطبيقاتك والترفيه مع المجتمع.

README_BN.md

@@ -225,6 +225,11 @@ GitHub-এ ডিফাইকে স্টার দিয়ে রাখুন
 
 - [AWS CDK by @KevinZhao](https://github.com/aws-samples/solution-for-deploying-dify-on-aws)
 
+#### Alibaba Cloud ব্যবহার করে ডিপ্লয়
+
+ [Alibaba Cloud Computing Nest](https://computenest.console.aliyun.com/service/instance/create/default?type=user&ServiceName=Dify%E7%A4%BE%E5%8C%BA%E7%89%88)
+
+
 ## Contributing
 
 যারা কোড অবদান রাখতে চান, তাদের জন্য আমাদের [অবদান নির্দেশিকা] দেখুন (https://github.com/langgenius/dify/blob/main/CONTRIBUTING.md)।
@@ -234,7 +239,7 @@ GitHub-এ ডিফাইকে স্টার দিয়ে রাখুন
 
 ## কমিউনিটি এবং যোগাযোগ
 
-- [Github Discussion](https://github.com/langgenius/dify/discussions) ফিডব্যাক এবং প্রতিক্রিয়া জানানোর মাধ্যম।
+- [GitHub Discussion](https://github.com/langgenius/dify/discussions) ফিডব্যাক এবং প্রতিক্রিয়া জানানোর মাধ্যম।
 - [GitHub Issues](https://github.com/langgenius/dify/issues). Dify.AI ব্যবহার করে আপনি যেসব বাগের সম্মুখীন হন এবং ফিচার প্রস্তাবনা।  আমাদের [অবদান নির্দেশিকা](https://github.com/langgenius/dify/blob/main/CONTRIBUTING.md) দেখুন।
 - [Discord](https://discord.gg/FngNHpbcY7) আপনার এপ্লিকেশন শেয়ার এবং কমিউনিটি আড্ডার মাধ্যম। 
 - [X(Twitter)](https://twitter.com/dify_ai) আপনার এপ্লিকেশন শেয়ার এবং কমিউনিটি আড্ডার মাধ্যম। 

README_CN.md

@@ -221,6 +221,11 @@ docker compose up -d
 ##### AWS 
 - [AWS CDK by @KevinZhao](https://github.com/aws-samples/solution-for-deploying-dify-on-aws)
 
+#### 使用 阿里云计算巢 部署
+
+使用 [阿里云计算巢](https://computenest.console.aliyun.com/service/instance/create/default?type=user&ServiceName=Dify%E7%A4%BE%E5%8C%BA%E7%89%88) 将 Dify 一键部署到 阿里云
+
+
 ## Star History
 
 [![Star History Chart](https://api.star-history.com/svg?repos=langgenius/dify&type=Date)](https://star-history.com/#langgenius/dify&Date)
@@ -243,7 +248,7 @@ docker compose up -d
 
 我们欢迎您为 Dify 做出贡献，以帮助改善 Dify。包括：提交代码、问题、新想法，或分享您基于 Dify 创建的有趣且有用的 AI 应用程序。同时，我们也欢迎您在不同的活动、会议和社交媒体上分享 Dify。
 
-- [Github Discussion](https://github.com/langgenius/dify/discussions). 👉：分享您的应用程序并与社区交流。
+- [GitHub Discussion](https://github.com/langgenius/dify/discussions). 👉：分享您的应用程序并与社区交流。
 - [GitHub Issues](https://github.com/langgenius/dify/issues)。👉：使用 Dify.AI 时遇到的错误和问题，请参阅[贡献指南](CONTRIBUTING.md)。
 - [电子邮件支持](mailto:[email protected]?subject=[GitHub]Questions%20About%20Dify)。👉：关于使用 Dify.AI 的问题。
 - [Discord](https://discord.gg/FngNHpbcY7)。👉：分享您的应用程序并与社区交流。

README_DE.md

@@ -221,6 +221,11 @@ Bereitstellung von Dify auf AWS mit [CDK](https://aws.amazon.com/cdk/)
 ##### AWS 
 - [AWS CDK by @KevinZhao](https://github.com/aws-samples/solution-for-deploying-dify-on-aws)
 
+#### Alibaba Cloud 
+
+[Alibaba Cloud Computing Nest](https://computenest.console.aliyun.com/service/instance/create/default?type=user&ServiceName=Dify%E7%A4%BE%E5%8C%BA%E7%89%88)
+
+
 ## Contributing
 
 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.
@@ -230,7 +235,7 @@ Falls Sie Code beitragen möchten, lesen Sie bitte unseren [Contribution Guide](
 
 ## Gemeinschaft & Kontakt
 
-* [Github Discussion](https://github.com/langgenius/dify/discussions). Am besten geeignet für: den Austausch von Feedback und das Stellen von Fragen.
+* [GitHub Discussion](https://github.com/langgenius/dify/discussions). Am besten geeignet für: den Austausch von Feedback und das Stellen von Fragen.
 * [GitHub Issues](https://github.com/langgenius/dify/issues). Am besten für: Fehler, auf die Sie bei der Verwendung von Dify.AI stoßen, und Funktionsvorschläge. Siehe unseren [Contribution Guide](https://github.com/langgenius/dify/blob/main/CONTRIBUTING.md).
 * [Discord](https://discord.gg/FngNHpbcY7).  Am besten geeignet für: den Austausch von Bewerbungen und den Austausch mit der Community.
 * [X(Twitter)](https://twitter.com/dify_ai). Am besten geeignet für: den Austausch von Bewerbungen und den Austausch mit der Community.

README_ES.md

@@ -221,6 +221,10 @@ Despliegue Dify en AWS usando [CDK](https://aws.amazon.com/cdk/)
 ##### AWS 
 - [AWS CDK por @KevinZhao](https://github.com/aws-samples/solution-for-deploying-dify-on-aws)
 
+#### Alibaba Cloud
+
+[Alibaba Cloud Computing Nest](https://computenest.console.aliyun.com/service/instance/create/default?type=user&ServiceName=Dify%E7%A4%BE%E5%8C%BA%E7%89%88)
+
 ## Contribuir
 
 Para aquellos que deseen contribuir con código, consulten nuestra [Guía de contribución](https://github.com/langgenius/dify/blob/main/CONTRIBUTING.md). 

README_FR.md

@@ -219,6 +219,11 @@ Déployez Dify sur AWS en utilisant [CDK](https://aws.amazon.com/cdk/)
 ##### AWS 
 - [AWS CDK par @KevinZhao](https://github.com/aws-samples/solution-for-deploying-dify-on-aws)
 
+#### Alibaba Cloud
+
+[Alibaba Cloud Computing Nest](https://computenest.console.aliyun.com/service/instance/create/default?type=user&ServiceName=Dify%E7%A4%BE%E5%8C%BA%E7%89%88)
+
+
 ## Contribuer
 
 Pour ceux qui souhaitent contribuer du code, consultez notre [Guide de contribution](https://github.com/langgenius/dify/blob/main/CONTRIBUTING.md). 

README_JA.md

@@ -220,6 +220,10 @@ docker compose up -d
 ##### AWS
 - [@KevinZhaoによるAWS CDK](https://github.com/aws-samples/solution-for-deploying-dify-on-aws)
 
+#### Alibaba Cloud
+[Alibaba Cloud Computing Nest](https://computenest.console.aliyun.com/service/instance/create/default?type=user&ServiceName=Dify%E7%A4%BE%E5%8C%BA%E7%89%88)
+
+
 ## 貢献
 
 コードに貢献したい方は、[Contribution Guide](https://github.com/langgenius/dify/blob/main/CONTRIBUTING.md)を参照してください。
@@ -236,7 +240,7 @@ docker compose up -d
 
 ## コミュニティ & お問い合わせ
 
-* [Github Discussion](https://github.com/langgenius/dify/discussions). 主に: フィードバックの共有や質問。
+* [GitHub Discussion](https://github.com/langgenius/dify/discussions). 主に: フィードバックの共有や質問。
 * [GitHub Issues](https://github.com/langgenius/dify/issues). 主に: Dify.AIを使用する際に発生するエラーや問題については、[貢献ガイド](CONTRIBUTING_JA.md)を参照してください
 * [Discord](https://discord.gg/FngNHpbcY7). 主に: アプリケーションの共有やコミュニティとの交流。
 * [X(Twitter)](https://twitter.com/dify_ai). 主に: アプリケーションの共有やコミュニティとの交流。

README_KL.md

@@ -219,6 +219,11 @@ wa'logh nIqHom neH ghun deployment toy'wI' [CDK](https://aws.amazon.com/cdk/) lo
 ##### AWS 
 - [AWS CDK qachlot @KevinZhao](https://github.com/aws-samples/solution-for-deploying-dify-on-aws)
 
+#### Alibaba Cloud
+
+[Alibaba Cloud Computing Nest](https://computenest.console.aliyun.com/service/instance/create/default?type=user&ServiceName=Dify%E7%A4%BE%E5%8C%BA%E7%89%88)
+
+
 ## Contributing
 
 For those who'd like to contribute code, see our [Contribution Guide](https://github.com/langgenius/dify/blob/main/CONTRIBUTING.md). 
@@ -235,7 +240,7 @@ At the same time, please consider supporting Dify by sharing it on social media
 
 ## Community & Contact
 
-* [Github Discussion](https://github.com/langgenius/dify/discussions
+* [GitHub Discussion](https://github.com/langgenius/dify/discussions
 
 ). Best for: sharing feedback and asking questions.
 * [GitHub Issues](https://github.com/langgenius/dify/issues). Best for: bugs you encounter using Dify.AI, and feature proposals. See our [Contribution Guide](https://github.com/langgenius/dify/blob/main/CONTRIBUTING.md).

README_KR.md

@@ -213,6 +213,11 @@ Dify를 Kubernetes에 배포하고 프리미엄 스케일링 설정을 구성했
 ##### AWS 
 - [KevinZhao의 AWS CDK](https://github.com/aws-samples/solution-for-deploying-dify-on-aws)
 
+#### Alibaba Cloud
+
+[Alibaba Cloud Computing Nest](https://computenest.console.aliyun.com/service/instance/create/default?type=user&ServiceName=Dify%E7%A4%BE%E5%8C%BA%E7%89%88)
+
+
 ## 기여
 
 코드에 기여하고 싶은 분들은 [기여 가이드](https://github.com/langgenius/dify/blob/main/CONTRIBUTING.md)를 참조하세요.
@@ -229,7 +234,7 @@ Dify를 Kubernetes에 배포하고 프리미엄 스케일링 설정을 구성했
 
 ## 커뮤니티 & 연락처
 
-* [Github 토론](https://github.com/langgenius/dify/discussions). 피드백 공유 및 질문하기에 적합합니다.
+* [GitHub 토론](https://github.com/langgenius/dify/discussions). 피드백 공유 및 질문하기에 적합합니다.
 * [GitHub 이슈](https://github.com/langgenius/dify/issues). Dify.AI 사용 중 발견한 버그와 기능 제안에 적합합니다. [기여 가이드](https://github.com/langgenius/dify/blob/main/CONTRIBUTING.md)를 참조하세요. 
 * [디스코드](https://discord.gg/FngNHpbcY7). 애플리케이션 공유 및 커뮤니티와 소통하기에 적합합니다.
 * [트위터](https://twitter.com/dify_ai). 애플리케이션 공유 및 커뮤니티와 소통하기에 적합합니다.

README_PT.md

@@ -218,6 +218,11 @@ Implante o Dify na AWS usando [CDK](https://aws.amazon.com/cdk/)
 ##### AWS 
 - [AWS CDK por @KevinZhao](https://github.com/aws-samples/solution-for-deploying-dify-on-aws)
 
+#### Alibaba Cloud
+
+[Alibaba Cloud Computing Nest](https://computenest.console.aliyun.com/service/instance/create/default?type=user&ServiceName=Dify%E7%A4%BE%E5%8C%BA%E7%89%88)
+
+
 ## Contribuindo
 
 Para aqueles que desejam contribuir com código, veja nosso [Guia de Contribuição](https://github.com/langgenius/dify/blob/main/CONTRIBUTING.md). 

README_SI.md

@@ -219,6 +219,11 @@ Uvedite Dify v AWS z uporabo [CDK](https://aws.amazon.com/cdk/)
 ##### AWS 
 - [AWS CDK by @KevinZhao](https://github.com/aws-samples/solution-for-deploying-dify-on-aws)
 
+#### Alibaba Cloud
+
+[Alibaba Cloud Computing Nest](https://computenest.console.aliyun.com/service/instance/create/default?type=user&ServiceName=Dify%E7%A4%BE%E5%8C%BA%E7%89%88)
+
+
 ## Prispevam
 
 Za tiste, ki bi radi prispevali kodo, si oglejte naš vodnik za prispevke . Hkrati vas prosimo, da podprete Dify tako, da ga delite na družbenih medijih ter na dogodkih in konferencah. 
@@ -229,7 +234,7 @@ Za tiste, ki bi radi prispevali kodo, si oglejte naš vodnik za prispevke . Hkra
 
 ## Skupnost in stik
 
-* [Github Discussion](https://github.com/langgenius/dify/discussions). Najboljše za: izmenjavo povratnih informacij in postavljanje vprašanj.
+* [GitHub Discussion](https://github.com/langgenius/dify/discussions). Najboljše za: izmenjavo povratnih informacij in postavljanje vprašanj.
 * [GitHub Issues](https://github.com/langgenius/dify/issues). Najboljše za: hrošče, na katere naletite pri uporabi Dify.AI, in predloge funkcij. Oglejte si naš [vodnik za prispevke](https://github.com/langgenius/dify/blob/main/CONTRIBUTING.md).
 * [Discord](https://discord.gg/FngNHpbcY7). Najboljše za: deljenje vaših aplikacij in druženje s skupnostjo.
 * [X(Twitter)](https://twitter.com/dify_ai). Najboljše za: deljenje vaših aplikacij in druženje s skupnostjo.

README_TR.md

@@ -212,6 +212,11 @@ Dify'ı bulut platformuna tek tıklamayla dağıtın [terraform](https://www.ter
 ##### AWS 
 - [AWS CDK tarafından @KevinZhao](https://github.com/aws-samples/solution-for-deploying-dify-on-aws)
 
+#### Alibaba Cloud
+
+[Alibaba Cloud Computing Nest](https://computenest.console.aliyun.com/service/instance/create/default?type=user&ServiceName=Dify%E7%A4%BE%E5%8C%BA%E7%89%88)
+
+
 ## Katkıda Bulunma
 
 Kod katkısında bulunmak isteyenler için [Katkı Kılavuzumuza](https://github.com/langgenius/dify/blob/main/CONTRIBUTING.md) bakabilirsiniz.
@@ -227,7 +232,7 @@ Aynı zamanda, lütfen Dify'ı sosyal medyada, etkinliklerde ve konferanslarda p
 
 ## Topluluk & iletişim
 
-* [Github Tartışmaları](https://github.com/langgenius/dify/discussions). En uygun: geri bildirim paylaşmak ve soru sormak için.
+* [GitHub Tartışmaları](https://github.com/langgenius/dify/discussions). En uygun: geri bildirim paylaşmak ve soru sormak için.
 * [GitHub Sorunları](https://github.com/langgenius/dify/issues). En uygun: Dify.AI kullanırken karşılaştığınız hatalar ve özellik önerileri için. [Katkı Kılavuzumuza](https://github.com/langgenius/dify/blob/main/CONTRIBUTING.md) bakın.
 * [Discord](https://discord.gg/FngNHpbcY7). En uygun: uygulamalarınızı paylaşmak ve toplulukla vakit geçirmek için.
 * [X(Twitter)](https://twitter.com/dify_ai). En uygun: uygulamalarınızı paylaşmak ve toplulukla vakit geçirmek için.

README_TW.md

@@ -224,6 +224,11 @@ Dify 的所有功能都提供相應的 API，因此您可以輕鬆地將 Dify
 
 - [由 @KevinZhao 提供的 AWS CDK](https://github.com/aws-samples/solution-for-deploying-dify-on-aws)
 
+#### 使用 阿里云计算巢進行部署
+
+[阿里云](https://computenest.console.aliyun.com/service/instance/create/default?type=user&ServiceName=Dify%E7%A4%BE%E5%8C%BA%E7%89%88)
+
+
 ## 貢獻
 
 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)。
@@ -233,7 +238,7 @@ Dify 的所有功能都提供相應的 API，因此您可以輕鬆地將 Dify
 
 ## 社群與聯絡方式
 
-- [Github Discussion](https://github.com/langgenius/dify/discussions)：最適合分享反饋和提問。
+- [GitHub Discussion](https://github.com/langgenius/dify/discussions)：最適合分享反饋和提問。
 - [GitHub Issues](https://github.com/langgenius/dify/issues)：最適合報告使用 Dify.AI 時遇到的問題和提出功能建議。請參閱我們的[貢獻指南](https://github.com/langgenius/dify/blob/main/CONTRIBUTING.md)。
 - [Discord](https://discord.gg/FngNHpbcY7)：最適合分享您的應用程式並與社群互動。
 - [X(Twitter)](https://twitter.com/dify_ai)：最適合分享您的應用程式並與社群互動。

README_VI.md

@@ -214,6 +214,12 @@ Triển khai Dify trên AWS bằng [CDK](https://aws.amazon.com/cdk/)
 ##### AWS 
 - [AWS CDK bởi @KevinZhao](https://github.com/aws-samples/solution-for-deploying-dify-on-aws)
 
+
+#### Alibaba Cloud
+
+[Alibaba Cloud Computing Nest](https://computenest.console.aliyun.com/service/instance/create/default?type=user&ServiceName=Dify%E7%A4%BE%E5%8C%BA%E7%89%88)
+
+
 ## Đóng góp
 
 Đối với những người muốn đóng góp mã, xem [Hướng dẫn Đóng góp](https://github.com/langgenius/dify/blob/main/CONTRIBUTING.md) của chúng tôi. 

api/.env.example

@@ -137,7 +137,7 @@ WEB_API_CORS_ALLOW_ORIGINS=http://127.0.0.1:3000,*
 CONSOLE_CORS_ALLOW_ORIGINS=http://127.0.0.1:3000,*
 
 # Vector database configuration
-# support: weaviate, qdrant, milvus, myscale, relyt, pgvecto_rs, pgvector, pgvector, chroma, opensearch, tidb_vector, couchbase, vikingdb, upstash, lindorm, oceanbase, opengauss, tablestore
+# support: weaviate, qdrant, milvus, myscale, relyt, pgvecto_rs, pgvector, pgvector, chroma, opensearch, tidb_vector, couchbase, vikingdb, upstash, lindorm, oceanbase, opengauss, tablestore, matrixone
 VECTOR_STORE=weaviate
 
 # Weaviate configuration
@@ -152,6 +152,7 @@ QDRANT_API_KEY=difyai123456
 QDRANT_CLIENT_TIMEOUT=20
 QDRANT_GRPC_ENABLED=false
 QDRANT_GRPC_PORT=6334
+QDRANT_REPLICATION_FACTOR=1
 
 #Couchbase configuration
 COUCHBASE_CONNECTION_STRING=127.0.0.1
@@ -269,6 +270,7 @@ OPENSEARCH_PORT=9200
 OPENSEARCH_USER=admin
 OPENSEARCH_PASSWORD=admin
 OPENSEARCH_SECURE=true
+OPENSEARCH_VERIFY_CERTS=true
 
 # Baidu configuration
 BAIDU_VECTOR_DB_ENDPOINT=http://127.0.0.1:5287
@@ -292,6 +294,13 @@ VIKINGDB_SCHEMA=http
 VIKINGDB_CONNECTION_TIMEOUT=30
 VIKINGDB_SOCKET_TIMEOUT=30
 
+# Matrixone configration
+MATRIXONE_HOST=127.0.0.1
+MATRIXONE_PORT=6001
+MATRIXONE_USER=dump
+MATRIXONE_PASSWORD=111
+MATRIXONE_DATABASE=dify
+
 # Lindorm configuration
 LINDORM_URL=http://ld-*******************-proxy-search-pub.lindorm.aliyuncs.com:30070
 LINDORM_USERNAME=admin
@@ -330,9 +339,11 @@ PROMPT_GENERATION_MAX_TOKENS=512
 CODE_GENERATION_MAX_TOKENS=1024
 PLUGIN_BASED_TOKEN_COUNTING_ENABLED=false
 
-# Mail configuration, support: resend, smtp
+# Mail configuration, support: resend, smtp, sendgrid
 MAIL_TYPE=
+# If using SendGrid, use the 'from' field for authentication if necessary.
 MAIL_DEFAULT_SEND_FROM=no-reply <[email protected]>
+# resend configuration
 RESEND_API_KEY=
 RESEND_API_URL=https://api.resend.com
 # smtp configuration
@@ -342,12 +353,14 @@ SMTP_USERNAME=123
 SMTP_PASSWORD=abc
 SMTP_USE_TLS=true
 SMTP_OPPORTUNISTIC_TLS=false
-
+# Sendgid configuration
+SENDGRID_API_KEY=
 # Sentry configuration
 SENTRY_DSN=
 
 # DEBUG
 DEBUG=false
+ENABLE_REQUEST_LOGGING=False
 SQLALCHEMY_ECHO=false
 
 # Notion import configuration, support public and internal
@@ -488,3 +501,10 @@ OTEL_METRIC_EXPORT_TIMEOUT=30000
 
 # Prevent Clickjacking
 ALLOW_EMBED=false
+
+# Dataset queue monitor configuration
+QUEUE_MONITOR_THRESHOLD=200
+# You can configure multiple ones, separated by commas. eg: [email protected],[email protected]
+QUEUE_MONITOR_ALERT_EMAILS=
+# Monitor interval in minutes, default is 30 minutes
+QUEUE_MONITOR_INTERVAL=30

api/.ruff.toml

@@ -43,6 +43,7 @@ select = [
     "S307", # suspicious-eval-usage, disallow use of `eval` and `ast.literal_eval`
     "S301", # suspicious-pickle-usage, disallow use of `pickle` and its wrappers.
     "S302", # suspicious-marshal-usage, disallow use of `marshal` module
+    "S311", # suspicious-non-cryptographic-random-usage
 ]
 
 ignore = [

api/Dockerfile

@@ -4,7 +4,7 @@ FROM python:3.12-slim-bookworm AS base
 WORKDIR /app/api
 
 # Install uv
-ENV UV_VERSION=0.6.14
+ENV UV_VERSION=0.7.11
 
 RUN pip install --no-cache-dir uv==${UV_VERSION}
 

api/app_factory.py

@@ -54,6 +54,7 @@ def initialize_extensions(app: DifyApp):
         ext_otel,
         ext_proxy_fix,
         ext_redis,
+        ext_request_logging,
         ext_sentry,
         ext_set_secretkey,
         ext_storage,
@@ -83,6 +84,7 @@ def initialize_extensions(app: DifyApp):
         ext_blueprints,
         ext_commands,
         ext_otel,
+        ext_request_logging,
     ]
     for ext in extensions:
         short_name = ext.__name__.split(".")[-1]

api/commands.py

@@ -27,7 +27,7 @@ from models.dataset import Dataset, DatasetCollectionBinding, DatasetMetadata, D
 from models.dataset import Document as DatasetDocument
 from models.model import Account, App, AppAnnotationSetting, AppMode, Conversation, MessageAnnotation
 from models.provider import Provider, ProviderModel
-from services.account_service import RegisterService, TenantService
+from services.account_service import AccountService, RegisterService, TenantService
 from services.clear_free_plan_tenant_expired_logs import ClearFreePlanTenantExpiredLogs
 from services.plugin.data_migration import PluginDataMigration
 from services.plugin.plugin_migration import PluginMigration
@@ -68,6 +68,7 @@ def reset_password(email, new_password, password_confirm):
     account.password = base64_password_hashed
     account.password_salt = base64_salt
     db.session.commit()
+    AccountService.reset_login_error_rate_limit(email)
     click.echo(click.style("Password reset successfully.", fg="green"))
 
 
@@ -280,6 +281,7 @@ def migrate_knowledge_vector_database():
         VectorType.ELASTICSEARCH,
         VectorType.OPENGAUSS,
         VectorType.TABLESTORE,
+        VectorType.MATRIXONE,
     }
     lower_collection_vector_types = {
         VectorType.ANALYTICDB,
@@ -846,6 +848,9 @@ def clear_orphaned_file_records(force: bool):
         {"type": "text", "table": "workflow_node_executions", "column": "outputs"},
         {"type": "text", "table": "conversations", "column": "introduction"},
         {"type": "text", "table": "conversations", "column": "system_instruction"},
+        {"type": "text", "table": "accounts", "column": "avatar"},
+        {"type": "text", "table": "apps", "column": "icon"},
+        {"type": "text", "table": "sites", "column": "icon"},
         {"type": "json", "table": "messages", "column": "inputs"},
         {"type": "json", "table": "messages", "column": "message"},
     ]

api/configs/deploy/__init__.py

@@ -17,6 +17,12 @@ class DeploymentConfig(BaseSettings):
         default=False,
     )
 
+    # Request logging configuration
+    ENABLE_REQUEST_LOGGING: bool = Field(
+        description="Enable request and response body logging",
+        default=False,
+    )
+
     EDITION: str = Field(
         description="Deployment edition of the application (e.g., 'SELF_HOSTED', 'CLOUD')",
         default="SELF_HOSTED",

api/configs/feature/__init__.py

@@ -609,7 +609,7 @@ class MailConfig(BaseSettings):
     """
 
     MAIL_TYPE: Optional[str] = Field(
-        description="Email service provider type ('smtp' or 'resend'), default to None.",
+        description="Email service provider type ('smtp' or 'resend' or 'sendGrid), default to None.",
         default=None,
     )
 
@@ -663,6 +663,11 @@ class MailConfig(BaseSettings):
         default=50,
     )
 
+    SENDGRID_API_KEY: Optional[str] = Field(
+        description="API key for SendGrid service",
+        default=None,
+    )
+
 
 class RagEtlConfig(BaseSettings):
     """

api/configs/middleware/__init__.py

@@ -2,7 +2,7 @@ import os
 from typing import Any, Literal, Optional
 from urllib.parse import parse_qsl, quote_plus
 
-from pydantic import Field, NonNegativeInt, PositiveFloat, PositiveInt, computed_field
+from pydantic import Field, NonNegativeFloat, NonNegativeInt, PositiveFloat, PositiveInt, computed_field
 from pydantic_settings import BaseSettings
 
 from .cache.redis_config import RedisConfig
@@ -24,6 +24,7 @@ from .vdb.couchbase_config import CouchbaseConfig
 from .vdb.elasticsearch_config import ElasticsearchConfig
 from .vdb.huawei_cloud_config import HuaweiCloudConfig
 from .vdb.lindorm_config import LindormConfig
+from .vdb.matrixone_config import MatrixoneConfig
 from .vdb.milvus_config import MilvusConfig
 from .vdb.myscale_config import MyScaleConfig
 from .vdb.oceanbase_config import OceanBaseVectorConfig
@@ -256,6 +257,25 @@ class InternalTestConfig(BaseSettings):
     )
 
 
+class DatasetQueueMonitorConfig(BaseSettings):
+    """
+    Configuration settings for Dataset Queue Monitor
+    """
+
+    QUEUE_MONITOR_THRESHOLD: Optional[NonNegativeInt] = Field(
+        description="Threshold for dataset queue monitor",
+        default=200,
+    )
+    QUEUE_MONITOR_ALERT_EMAILS: Optional[str] = Field(
+        description="Emails for dataset queue monitor alert, separated by commas",
+        default=None,
+    )
+    QUEUE_MONITOR_INTERVAL: Optional[NonNegativeFloat] = Field(
+        description="Interval for dataset queue monitor in minutes",
+        default=30,
+    )
+
+
 class MiddlewareConfig(
     # place the configs in alphabet order
     CeleryConfig,
@@ -303,5 +323,7 @@ class MiddlewareConfig(
     BaiduVectorDBConfig,
     OpenGaussConfig,
     TableStoreConfig,
+    DatasetQueueMonitorConfig,
+    MatrixoneConfig,
 ):
     pass

api/configs/middleware/storage/amazon_s3_storage_config.py

@@ -1,4 +1,4 @@
-from typing import Optional
+from typing import Literal, Optional
 
 from pydantic import Field
 from pydantic_settings import BaseSettings
@@ -34,7 +34,7 @@ class S3StorageConfig(BaseSettings):
         default=None,
     )
 
-    S3_ADDRESS_STYLE: str = Field(
+    S3_ADDRESS_STYLE: Literal["auto", "virtual", "path"] = Field(
         description="S3 addressing style: 'auto', 'path', or 'virtual'",
         default="auto",
     )

api/configs/middleware/vdb/matrixone_config.py

@@ -0,0 +1,14 @@
+from pydantic import BaseModel, Field
+
+
+class MatrixoneConfig(BaseModel):
+    """Matrixone vector database configuration."""
+
+    MATRIXONE_HOST: str = Field(default="localhost", description="Host address of the Matrixone server")
+    MATRIXONE_PORT: int = Field(default=6001, description="Port number of the Matrixone server")
+    MATRIXONE_USER: str = Field(default="dump", description="Username for authenticating with Matrixone")
+    MATRIXONE_PASSWORD: str = Field(default="111", description="Password for authenticating with Matrixone")
+    MATRIXONE_DATABASE: str = Field(default="dify", description="Name of the Matrixone database to connect to")
+    MATRIXONE_METRIC: str = Field(
+        default="l2", description="Distance metric type for vector similarity search (cosine or l2)"
+    )

api/configs/middleware/vdb/opensearch_config.py

@@ -33,6 +33,11 @@ class OpenSearchConfig(BaseSettings):
         default=False,
     )
 
+    OPENSEARCH_VERIFY_CERTS: bool = Field(
+        description="Whether to verify SSL certificates for HTTPS connections (recommended to set True in production)",
+        default=True,
+    )
+
     OPENSEARCH_AUTH_METHOD: AuthMethod = Field(
         description="Authentication method for OpenSearch connection (default is 'basic')",
         default=AuthMethod.BASIC,

api/configs/middleware/vdb/qdrant_config.py

@@ -33,3 +33,8 @@ class QdrantConfig(BaseSettings):
         description="Port number for gRPC connection to Qdrant server (default is 6334)",
         default=6334,
     )
+
+    QDRANT_REPLICATION_FACTOR: PositiveInt = Field(
+        description="Replication factor for Qdrant collections (default is 1)",
+        default=1,
+    )

api/configs/packaging/__init__.py

@@ -9,7 +9,7 @@ class PackagingInfo(BaseSettings):
 
     CURRENT_VERSION: str = Field(
         description="Dify version",
-        default="1.4.0",
+        default="1.4.3",
     )
 
     COMMIT_SHA: str = Field(

api/configs/remote_settings_sources/nacos/http_request.py

@@ -60,8 +60,7 @@ class NacosHttpClient:
             sign_str = tenant + "+"
         if group:
             sign_str = sign_str + group + "+"
-        if sign_str:
-            sign_str += ts
+        sign_str += ts  # Directly concatenate ts without conditional checks, because the nacos auth header forced it.
         return sign_str
 
     def get_access_token(self, force_refresh=False):

api/contexts/__init__.py

@@ -11,10 +11,6 @@ if TYPE_CHECKING:
     from core.workflow.entities.variable_pool import VariablePool
 
 
-tenant_id: ContextVar[str] = ContextVar("tenant_id")
-
-workflow_variable_pool: ContextVar["VariablePool"] = ContextVar("workflow_variable_pool")
-
 """
 To avoid race-conditions caused by gunicorn thread recycling, using RecyclableContextVar to replace with
 """

api/controllers/console/admin.py

@@ -56,8 +56,7 @@ class InsertExploreAppListApi(Resource):
         parser.add_argument("position", type=int, required=True, nullable=False, location="json")
         args = parser.parse_args()
 
-        with Session(db.engine) as session:
-            app = session.execute(select(App).filter(App.id == args["app_id"])).scalar_one_or_none()
+        app = db.session.execute(select(App).filter(App.id == args["app_id"])).scalar_one_or_none()
         if not app:
             raise NotFound(f"App '{args['app_id']}' is not found")
 
@@ -78,38 +77,38 @@ class InsertExploreAppListApi(Resource):
                 select(RecommendedApp).filter(RecommendedApp.app_id == args["app_id"])
             ).scalar_one_or_none()
 
-        if not recommended_app:
-            recommended_app = RecommendedApp(
-                app_id=app.id,
-                description=desc,
-                copyright=copy_right,
-                privacy_policy=privacy_policy,
-                custom_disclaimer=custom_disclaimer,
-                language=args["language"],
-                category=args["category"],
-                position=args["position"],
-            )
+            if not recommended_app:
+                recommended_app = RecommendedApp(
+                    app_id=app.id,
+                    description=desc,
+                    copyright=copy_right,
+                    privacy_policy=privacy_policy,
+                    custom_disclaimer=custom_disclaimer,
+                    language=args["language"],
+                    category=args["category"],
+                    position=args["position"],
+                )
 
-            db.session.add(recommended_app)
+                db.session.add(recommended_app)
 
-            app.is_public = True
-            db.session.commit()
+                app.is_public = True
+                db.session.commit()
 
-            return {"result": "success"}, 201
-        else:
-            recommended_app.description = desc
-            recommended_app.copyright = copy_right
-            recommended_app.privacy_policy = privacy_policy
-            recommended_app.custom_disclaimer = custom_disclaimer
-            recommended_app.language = args["language"]
-            recommended_app.category = args["category"]
-            recommended_app.position = args["position"]
+                return {"result": "success"}, 201
+            else:
+                recommended_app.description = desc
+                recommended_app.copyright = copy_right
+                recommended_app.privacy_policy = privacy_policy
+                recommended_app.custom_disclaimer = custom_disclaimer
+                recommended_app.language = args["language"]
+                recommended_app.category = args["category"]
+                recommended_app.position = args["position"]
 
-            app.is_public = True
+                app.is_public = True
 
-            db.session.commit()
+                db.session.commit()
 
-            return {"result": "success"}, 200
+                return {"result": "success"}, 200
 
 
 class InsertExploreAppApi(Resource):

api/controllers/console/app/annotation.py

@@ -208,7 +208,7 @@ class AnnotationBatchImportApi(Resource):
         if len(request.files) > 1:
             raise TooManyFilesError()
         # check file type
-        if not file.filename.endswith(".csv"):
+        if not file.filename or not file.filename.lower().endswith(".csv"):
             raise ValueError("Invalid file type. Only CSV files are allowed")
         return AppAnnotationService.batch_import_app_annotations(app_id, file)
 

api/controllers/console/app/app.py

@@ -17,15 +17,13 @@ from controllers.console.wraps import (
 )
 from core.ops.ops_trace_manager import OpsTraceManager
 from extensions.ext_database import db
-from fields.app_fields import (
-    app_detail_fields,
-    app_detail_fields_with_site,
-    app_pagination_fields,
-)
+from fields.app_fields import app_detail_fields, app_detail_fields_with_site, app_pagination_fields
 from libs.login import login_required
 from models import Account, App
 from services.app_dsl_service import AppDslService, ImportMode
 from services.app_service import AppService
+from services.enterprise.enterprise_service import EnterpriseService
+from services.feature_service import FeatureService
 
 ALLOW_CREATE_APP_MODES = ["chat", "agent-chat", "advanced-chat", "workflow", "completion"]
 
@@ -75,7 +73,17 @@ class AppListApi(Resource):
         if not app_pagination:
             return {"data": [], "total": 0, "page": 1, "limit": 20, "has_more": False}
 
-        return marshal(app_pagination, app_pagination_fields)
+        if FeatureService.get_system_features().webapp_auth.enabled:
+            app_ids = [str(app.id) for app in app_pagination.items]
+            res = EnterpriseService.WebAppAuth.batch_get_app_access_mode_by_id(app_ids=app_ids)
+            if len(res) != len(app_ids):
+                raise BadRequest("Invalid app id in webapp auth")
+
+            for app in app_pagination.items:
+                if str(app.id) in res:
+                    app.access_mode = res[str(app.id)].access_mode
+
+        return marshal(app_pagination, app_pagination_fields), 200
 
     @setup_required
     @login_required
@@ -119,6 +127,10 @@ class AppApi(Resource):
 
         app_model = app_service.get_app(app_model)
 
+        if FeatureService.get_system_features().webapp_auth.enabled:
+            app_setting = EnterpriseService.WebAppAuth.get_app_access_mode_by_id(app_id=str(app_model.id))
+            app_model.access_mode = app_setting.access_mode
+
         return app_model
 
     @setup_required

api/controllers/console/app/app_import.py

@@ -17,6 +17,8 @@ from libs.login import login_required
 from models import Account
 from models.model import App
 from services.app_dsl_service import AppDslService, ImportStatus
+from services.enterprise.enterprise_service import EnterpriseService
+from services.feature_service import FeatureService
 
 
 class AppImportApi(Resource):
@@ -60,7 +62,9 @@ class AppImportApi(Resource):
                 app_id=args.get("app_id"),
             )
             session.commit()
-
+        if result.app_id and FeatureService.get_system_features().webapp_auth.enabled:
+            # update web app setting as private
+            EnterpriseService.WebAppAuth.update_app_access_mode(result.app_id, "private")
         # Return appropriate status code based on result
         status = result.status
         if status == ImportStatus.FAILED.value:

api/controllers/console/app/workflow.py

@@ -81,8 +81,7 @@ class DraftWorkflowApi(Resource):
             parser.add_argument("graph", type=dict, required=True, nullable=False, location="json")
             parser.add_argument("features", type=dict, required=True, nullable=False, location="json")
             parser.add_argument("hash", type=str, required=False, location="json")
-            # TODO: set this to required=True after frontend is updated
-            parser.add_argument("environment_variables", type=list, required=False, location="json")
+            parser.add_argument("environment_variables", type=list, required=True, location="json")
             parser.add_argument("conversation_variables", type=list, required=False, location="json")
             args = parser.parse_args()
         elif "text/plain" in content_type:

api/controllers/console/app/workflow_app_log.py

@@ -6,12 +6,12 @@ from sqlalchemy.orm import Session
 from controllers.console import api
 from controllers.console.app.wraps import get_app_model
 from controllers.console.wraps import account_initialization_required, setup_required
+from core.workflow.entities.workflow_execution import WorkflowExecutionStatus
 from extensions.ext_database import db
 from fields.workflow_app_log_fields import workflow_app_log_pagination_fields
 from libs.login import login_required
 from models import App
 from models.model import AppMode
-from models.workflow import WorkflowRunStatus
 from services.workflow_app_service import WorkflowAppService
 
 
@@ -34,11 +34,25 @@ class WorkflowAppLogApi(Resource):
         parser.add_argument(
             "created_at__after", type=str, location="args", help="Filter logs created after this timestamp"
         )
+        parser.add_argument(
+            "created_by_end_user_session_id",
+            type=str,
+            location="args",
+            required=False,
+            default=None,
+        )
+        parser.add_argument(
+            "created_by_account",
+            type=str,
+            location="args",
+            required=False,
+            default=None,
+        )
         parser.add_argument("page", type=int_range(1, 99999), default=1, location="args")
         parser.add_argument("limit", type=int_range(1, 100), default=20, location="args")
         args = parser.parse_args()
 
-        args.status = WorkflowRunStatus(args.status) if args.status else None
+        args.status = WorkflowExecutionStatus(args.status) if args.status else None
         if args.created_at__before:
             args.created_at__before = isoparse(args.created_at__before)
 
@@ -57,6 +71,8 @@ class WorkflowAppLogApi(Resource):
                 created_at_after=args.created_at__after,
                 page=args.page,
                 limit=args.limit,
+                created_by_end_user_session_id=args.created_by_end_user_session_id,
+                created_by_account=args.created_by_account,
             )
 
             return workflow_app_log_pagination

api/controllers/console/app/workflow_run.py

@@ -1,3 +1,6 @@
+from typing import cast
+
+from flask_login import current_user
 from flask_restful import Resource, marshal_with, reqparse
 from flask_restful.inputs import int_range
 
@@ -12,8 +15,7 @@ from fields.workflow_run_fields import (
 )
 from libs.helper import uuid_value
 from libs.login import login_required
-from models import App
-from models.model import AppMode
+from models import Account, App, AppMode, EndUser
 from services.workflow_run_service import WorkflowRunService
 
 
@@ -90,7 +92,12 @@ class WorkflowRunNodeExecutionListApi(Resource):
         run_id = str(run_id)
 
         workflow_run_service = WorkflowRunService()
-        node_executions = workflow_run_service.get_workflow_run_node_executions(app_model=app_model, run_id=run_id)
+        user = cast("Account | EndUser", current_user)
+        node_executions = workflow_run_service.get_workflow_run_node_executions(
+            app_model=app_model,
+            run_id=run_id,
+            user=user,
+        )
 
         return {"data": node_executions}
 

api/controllers/console/auth/forgot_password.py

@@ -24,7 +24,7 @@ from libs.password import hash_password, valid_password
 from models.account import Account
 from services.account_service import AccountService, TenantService
 from services.errors.account import AccountRegisterError
-from services.errors.workspace import WorkSpaceNotAllowedCreateError
+from services.errors.workspace import WorkSpaceNotAllowedCreateError, WorkspacesLimitExceededError
 from services.feature_service import FeatureService
 
 
@@ -168,6 +168,8 @@ class ForgotPasswordResetApi(Resource):
             )
         except WorkSpaceNotAllowedCreateError:
             pass
+        except WorkspacesLimitExceededError:
+            pass
         except AccountRegisterError:
             raise AccountInFreezeError()
 

api/controllers/console/auth/login.py

@@ -21,6 +21,7 @@ from controllers.console.error import (
     AccountNotFound,
     EmailSendIpLimitError,
     NotAllowedCreateWorkspace,
+    WorkspacesLimitExceeded,
 )
 from controllers.console.wraps import email_password_login_enabled, setup_required
 from events.tenant_event import tenant_was_created
@@ -30,7 +31,7 @@ from models.account import Account
 from services.account_service import AccountService, RegisterService, TenantService
 from services.billing_service import BillingService
 from services.errors.account import AccountRegisterError
-from services.errors.workspace import WorkSpaceNotAllowedCreateError
+from services.errors.workspace import WorkSpaceNotAllowedCreateError, WorkspacesLimitExceededError
 from services.feature_service import FeatureService
 
 
@@ -88,10 +89,15 @@ class LoginApi(Resource):
         # SELF_HOSTED only have one workspace
         tenants = TenantService.get_join_tenants(account)
         if len(tenants) == 0:
-            return {
-                "result": "fail",
-                "data": "workspace not found, please contact system admin to invite you to join in a workspace",
-            }
+            system_features = FeatureService.get_system_features()
+
+            if system_features.is_allow_create_workspace and not system_features.license.workspaces.is_available():
+                raise WorkspacesLimitExceeded()
+            else:
+                return {
+                    "result": "fail",
+                    "data": "workspace not found, please contact system admin to invite you to join in a workspace",
+                }
 
         token_pair = AccountService.login(account=account, ip_address=extract_remote_ip(request))
         AccountService.reset_login_error_rate_limit(args["email"])
@@ -196,15 +202,18 @@ class EmailCodeLoginApi(Resource):
         except AccountRegisterError as are:
             raise AccountInFreezeError()
         if account:
-            tenant = TenantService.get_join_tenants(account)
-            if not tenant:
+            tenants = TenantService.get_join_tenants(account)
+            if not tenants:
+                workspaces = FeatureService.get_system_features().license.workspaces
+                if not workspaces.is_available():
+                    raise WorkspacesLimitExceeded()
                 if not FeatureService.get_system_features().is_allow_create_workspace:
                     raise NotAllowedCreateWorkspace()
                 else:
-                    tenant = TenantService.create_tenant(f"{account.name}'s Workspace")
-                    TenantService.create_tenant_member(tenant, account, role="owner")
-                    account.current_tenant = tenant
-                    tenant_was_created.send(tenant)
+                    new_tenant = TenantService.create_tenant(f"{account.name}'s Workspace")
+                    TenantService.create_tenant_member(new_tenant, account, role="owner")
+                    account.current_tenant = new_tenant
+                    tenant_was_created.send(new_tenant)
 
         if account is None:
             try:
@@ -215,6 +224,8 @@ class EmailCodeLoginApi(Resource):
                 return NotAllowedCreateWorkspace()
             except AccountRegisterError as are:
                 raise AccountInFreezeError()
+            except WorkspacesLimitExceededError:
+                raise WorkspacesLimitExceeded()
         token_pair = AccountService.login(account, ip_address=extract_remote_ip(request))
         AccountService.reset_login_error_rate_limit(args["email"])
         return {"result": "success", "data": token_pair.model_dump()}

api/controllers/console/auth/oauth.py

@@ -148,15 +148,15 @@ def _generate_account(provider: str, user_info: OAuthUserInfo):
     account = _get_account_by_openid_or_email(provider, user_info)
 
     if account:
-        tenant = TenantService.get_join_tenants(account)
-        if not tenant:
+        tenants = TenantService.get_join_tenants(account)
+        if not tenants:
             if not FeatureService.get_system_features().is_allow_create_workspace:
                 raise WorkSpaceNotAllowedCreateError()
             else:
-                tenant = TenantService.create_tenant(f"{account.name}'s Workspace")
-                TenantService.create_tenant_member(tenant, account, role="owner")
-                account.current_tenant = tenant
-                tenant_was_created.send(tenant)
+                new_tenant = TenantService.create_tenant(f"{account.name}'s Workspace")
+                TenantService.create_tenant_member(new_tenant, account, role="owner")
+                account.current_tenant = new_tenant
+                tenant_was_created.send(new_tenant)
 
     if not account:
         if not FeatureService.get_system_features().is_allow_register:

api/controllers/console/datasets/datasets.py

@@ -540,9 +540,22 @@ class DatasetIndexingStatusApi(Resource):
                 .filter(DocumentSegment.document_id == str(document.id), DocumentSegment.status != "re_segment")
                 .count()
             )
-            document.completed_segments = completed_segments
-            document.total_segments = total_segments
-            documents_status.append(marshal(document, document_status_fields))
+            # Create a dictionary with document attributes and additional fields
+            document_dict = {
+                "id": document.id,
+                "indexing_status": document.indexing_status,
+                "processing_started_at": document.processing_started_at,
+                "parsing_completed_at": document.parsing_completed_at,
+                "cleaning_completed_at": document.cleaning_completed_at,
+                "splitting_completed_at": document.splitting_completed_at,
+                "completed_at": document.completed_at,
+                "paused_at": document.paused_at,
+                "error": document.error,
+                "stopped_at": document.stopped_at,
+                "completed_segments": completed_segments,
+                "total_segments": total_segments,
+            }
+            documents_status.append(marshal(document_dict, document_status_fields))
         data = {"data": documents_status}
         return data
 
@@ -673,6 +686,7 @@ class DatasetRetrievalSettingApi(Resource):
                 | VectorType.TABLESTORE
                 | VectorType.HUAWEI_CLOUD
                 | VectorType.TENCENT
+                | VectorType.MATRIXONE
             ):
                 return {
                     "retrieval_method": [
@@ -720,6 +734,7 @@ class DatasetRetrievalSettingMockApi(Resource):
                 | VectorType.TABLESTORE
                 | VectorType.TENCENT
                 | VectorType.HUAWEI_CLOUD
+                | VectorType.MATRIXONE
             ):
                 return {
                     "retrieval_method": [

api/controllers/console/datasets/datasets_document.py

@@ -43,7 +43,6 @@ from core.model_runtime.errors.invoke import InvokeAuthorizationError
 from core.plugin.impl.exc import PluginDaemonClientSideError
 from core.rag.extractor.entity.extract_setting import ExtractSetting
 from extensions.ext_database import db
-from extensions.ext_redis import redis_client
 from fields.document_fields import (
     dataset_and_document_fields,
     document_fields,
@@ -54,8 +53,6 @@ from libs.login import login_required
 from models import Dataset, DatasetProcessRule, Document, DocumentSegment, UploadFile
 from services.dataset_service import DatasetService, DocumentService
 from services.entities.knowledge_entities.knowledge_entities import KnowledgeConfig
-from tasks.add_document_to_index_task import add_document_to_index_task
-from tasks.remove_document_from_index_task import remove_document_from_index_task
 
 
 class DocumentResource(Resource):
@@ -583,11 +580,22 @@ class DocumentBatchIndexingStatusApi(DocumentResource):
                 .filter(DocumentSegment.document_id == str(document.id), DocumentSegment.status != "re_segment")
                 .count()
             )
-            document.completed_segments = completed_segments
-            document.total_segments = total_segments
-            if document.is_paused:
-                document.indexing_status = "paused"
-            documents_status.append(marshal(document, document_status_fields))
+            # Create a dictionary with document attributes and additional fields
+            document_dict = {
+                "id": document.id,
+                "indexing_status": "paused" if document.is_paused else document.indexing_status,
+                "processing_started_at": document.processing_started_at,
+                "parsing_completed_at": document.parsing_completed_at,
+                "cleaning_completed_at": document.cleaning_completed_at,
+                "splitting_completed_at": document.splitting_completed_at,
+                "completed_at": document.completed_at,
+                "paused_at": document.paused_at,
+                "error": document.error,
+                "stopped_at": document.stopped_at,
+                "completed_segments": completed_segments,
+                "total_segments": total_segments,
+            }
+            documents_status.append(marshal(document_dict, document_status_fields))
         data = {"data": documents_status}
         return data
 
@@ -616,11 +624,22 @@ class DocumentIndexingStatusApi(DocumentResource):
             .count()
         )
 
-        document.completed_segments = completed_segments
-        document.total_segments = total_segments
-        if document.is_paused:
-            document.indexing_status = "paused"
-        return marshal(document, document_status_fields)
+        # Create a dictionary with document attributes and additional fields
+        document_dict = {
+            "id": document.id,
+            "indexing_status": "paused" if document.is_paused else document.indexing_status,
+            "processing_started_at": document.processing_started_at,
+            "parsing_completed_at": document.parsing_completed_at,
+            "cleaning_completed_at": document.cleaning_completed_at,
+            "splitting_completed_at": document.splitting_completed_at,
+            "completed_at": document.completed_at,
+            "paused_at": document.paused_at,
+            "error": document.error,
+            "stopped_at": document.stopped_at,
+            "completed_segments": completed_segments,
+            "total_segments": total_segments,
+        }
+        return marshal(document_dict, document_status_fields)
 
 
 class DocumentDetailApi(DocumentResource):
@@ -840,77 +859,16 @@ class DocumentStatusApi(DocumentResource):
         DatasetService.check_dataset_permission(dataset, current_user)
 
         document_ids = request.args.getlist("document_id")
-        for document_id in document_ids:
-            document = self.get_document(dataset_id, document_id)
 
-            indexing_cache_key = "document_{}_indexing".format(document.id)
-            cache_result = redis_client.get(indexing_cache_key)
-            if cache_result is not None:
-                raise InvalidActionError(f"Document:{document.name} is being indexed, please try again later")
+        try:
+            DocumentService.batch_update_document_status(dataset, document_ids, action, current_user)
+        except services.errors.document.DocumentIndexingError as e:
+            raise InvalidActionError(str(e))
+        except ValueError as e:
+            raise InvalidActionError(str(e))
+        except NotFound as e:
+            raise NotFound(str(e))
 
-            if action == "enable":
-                if document.enabled:
-                    continue
-                document.enabled = True
-                document.disabled_at = None
-                document.disabled_by = None
-                document.updated_at = datetime.now(UTC).replace(tzinfo=None)
-                db.session.commit()
-
-                # Set cache to prevent indexing the same document multiple times
-                redis_client.setex(indexing_cache_key, 600, 1)
-
-                add_document_to_index_task.delay(document_id)
-
-            elif action == "disable":
-                if not document.completed_at or document.indexing_status != "completed":
-                    raise InvalidActionError(f"Document: {document.name} is not completed.")
-                if not document.enabled:
-                    continue
-
-                document.enabled = False
-                document.disabled_at = datetime.now(UTC).replace(tzinfo=None)
-                document.disabled_by = current_user.id
-                document.updated_at = datetime.now(UTC).replace(tzinfo=None)
-                db.session.commit()
-
-                # Set cache to prevent indexing the same document multiple times
-                redis_client.setex(indexing_cache_key, 600, 1)
-
-                remove_document_from_index_task.delay(document_id)
-
-            elif action == "archive":
-                if document.archived:
-                    continue
-
-                document.archived = True
-                document.archived_at = datetime.now(UTC).replace(tzinfo=None)
-                document.archived_by = current_user.id
-                document.updated_at = datetime.now(UTC).replace(tzinfo=None)
-                db.session.commit()
-
-                if document.enabled:
-                    # Set cache to prevent indexing the same document multiple times
-                    redis_client.setex(indexing_cache_key, 600, 1)
-
-                    remove_document_from_index_task.delay(document_id)
-
-            elif action == "un_archive":
-                if not document.archived:
-                    continue
-                document.archived = False
-                document.archived_at = None
-                document.archived_by = None
-                document.updated_at = datetime.now(UTC).replace(tzinfo=None)
-                db.session.commit()
-
-                # Set cache to prevent indexing the same document multiple times
-                redis_client.setex(indexing_cache_key, 600, 1)
-
-                add_document_to_index_task.delay(document_id)
-
-            else:
-                raise InvalidActionError()
         return {"result": "success"}, 200
 
 

api/controllers/console/datasets/datasets_segments.py

@@ -374,7 +374,7 @@ class DatasetDocumentSegmentBatchImportApi(Resource):
         if len(request.files) > 1:
             raise TooManyFilesError()
         # check file type
-        if not file.filename.endswith(".csv"):
+        if not file.filename or not file.filename.lower().endswith(".csv"):
             raise ValueError("Invalid file type. Only CSV files are allowed")
 
         try:

api/controllers/console/error.py

@@ -46,6 +46,18 @@ class NotAllowedCreateWorkspace(BaseHTTPException):
     code = 400
 
 
+class WorkspaceMembersLimitExceeded(BaseHTTPException):
+    error_code = "limit_exceeded"
+    description = "Unable to add member because the maximum workspace's member limit was exceeded"
+    code = 400
+
+
+class WorkspacesLimitExceeded(BaseHTTPException):
+    error_code = "limit_exceeded"
+    description = "Unable to create workspace because the maximum workspace limit was exceeded"
+    code = 400
+
+
 class AccountBannedError(BaseHTTPException):
     error_code = "account_banned"
     description = "Account is banned."

api/controllers/console/explore/error.py

@@ -23,3 +23,9 @@ class AppSuggestedQuestionsAfterAnswerDisabledError(BaseHTTPException):
     error_code = "app_suggested_questions_after_answer_disabled"
     description = "Function Suggested questions after answer disabled."
     code = 403
+
+
+class AppAccessDeniedError(BaseHTTPException):
+    error_code = "access_denied"
+    description = "App access denied."
+    code = 403

api/controllers/console/explore/installed_app.py

@@ -1,3 +1,4 @@
+import logging
 from datetime import UTC, datetime
 from typing import Any
 
@@ -15,6 +16,11 @@ from fields.installed_app_fields import installed_app_list_fields
 from libs.login import login_required
 from models import App, InstalledApp, RecommendedApp
 from services.account_service import TenantService
+from services.app_service import AppService
+from services.enterprise.enterprise_service import EnterpriseService
+from services.feature_service import FeatureService
+
+logger = logging.getLogger(__name__)
 
 
 class InstalledAppsListApi(Resource):
@@ -48,6 +54,28 @@ class InstalledAppsListApi(Resource):
             for installed_app in installed_apps
             if installed_app.app is not None
         ]
+
+        # filter out apps that user doesn't have access to
+        if FeatureService.get_system_features().webapp_auth.enabled:
+            user_id = current_user.id
+            res = []
+            app_ids = [installed_app["app"].id for installed_app in installed_app_list]
+            webapp_settings = EnterpriseService.WebAppAuth.batch_get_app_access_mode_by_id(app_ids)
+            for installed_app in installed_app_list:
+                webapp_setting = webapp_settings.get(installed_app["app"].id)
+                if not webapp_setting:
+                    continue
+                if webapp_setting.access_mode == "sso_verified":
+                    continue
+                app_code = AppService.get_app_code_by_id(str(installed_app["app"].id))
+                if EnterpriseService.WebAppAuth.is_user_allowed_to_access_webapp(
+                    user_id=user_id,
+                    app_code=app_code,
+                ):
+                    res.append(installed_app)
+            installed_app_list = res
+            logger.debug(f"installed_app_list: {installed_app_list}, user_id: {user_id}")
+
         installed_app_list.sort(
             key=lambda app: (
                 -app["is_pinned"],

api/controllers/console/explore/wraps.py

@@ -4,10 +4,14 @@ from flask_login import current_user
 from flask_restful import Resource
 from werkzeug.exceptions import NotFound
 
+from controllers.console.explore.error import AppAccessDeniedError
 from controllers.console.wraps import account_initialization_required
 from extensions.ext_database import db
 from libs.login import login_required
 from models import InstalledApp
+from services.app_service import AppService
+from services.enterprise.enterprise_service import EnterpriseService
+from services.feature_service import FeatureService
 
 
 def installed_app_required(view=None):
@@ -48,6 +52,36 @@ def installed_app_required(view=None):
     return decorator
 
 
+def user_allowed_to_access_app(view=None):
+    def decorator(view):
+        @wraps(view)
+        def decorated(installed_app: InstalledApp, *args, **kwargs):
+            feature = FeatureService.get_system_features()
+            if feature.webapp_auth.enabled:
+                app_id = installed_app.app_id
+                app_code = AppService.get_app_code_by_id(app_id)
+                res = EnterpriseService.WebAppAuth.is_user_allowed_to_access_webapp(
+                    user_id=str(current_user.id),
+                    app_code=app_code,
+                )
+                if not res:
+                    raise AppAccessDeniedError()
+
+            return view(installed_app, *args, **kwargs)
+
+        return decorated
+
+    if view:
+        return decorator(view)
+    return decorator
+
+
 class InstalledAppResource(Resource):
     # must be reversed if there are multiple decorators
-    method_decorators = [installed_app_required, account_initialization_required, login_required]
+
+    method_decorators = [
+        user_allowed_to_access_app,
+        installed_app_required,
+        account_initialization_required,
+        login_required,
+    ]

api/controllers/console/workspace/load_balancing_config.py

@@ -15,7 +15,7 @@ class LoadBalancingCredentialsValidateApi(Resource):
     @login_required
     @account_initialization_required
     def post(self, provider: str):
-        if not TenantAccountRole.is_privileged_role(current_user.current_tenant.current_role):
+        if not TenantAccountRole.is_privileged_role(current_user.current_role):
             raise Forbidden()
 
         tenant_id = current_user.current_tenant_id
@@ -64,7 +64,7 @@ class LoadBalancingConfigCredentialsValidateApi(Resource):
     @login_required
     @account_initialization_required
     def post(self, provider: str, config_id: str):
-        if not TenantAccountRole.is_privileged_role(current_user.current_tenant.current_role):
+        if not TenantAccountRole.is_privileged_role(current_user.current_role):
             raise Forbidden()
 
         tenant_id = current_user.current_tenant_id

api/controllers/console/workspace/members.py

@@ -6,6 +6,7 @@ from flask_restful import Resource, abort, marshal_with, reqparse
 import services
 from configs import dify_config
 from controllers.console import api
+from controllers.console.error import WorkspaceMembersLimitExceeded
 from controllers.console.wraps import (
     account_initialization_required,
     cloud_edition_billing_resource_check,
@@ -17,6 +18,7 @@ from libs.login import login_required
 from models.account import Account, TenantAccountRole
 from services.account_service import RegisterService, TenantService
 from services.errors.account import AccountAlreadyInTenantError
+from services.feature_service import FeatureService
 
 
 class MemberListApi(Resource):
@@ -54,6 +56,12 @@ class MemberInviteEmailApi(Resource):
         inviter = current_user
         invitation_results = []
         console_web_url = dify_config.CONSOLE_WEB_URL
+
+        workspace_members = FeatureService.get_features(tenant_id=inviter.current_tenant.id).workspace_members
+
+        if not workspace_members.is_available(len(invitee_emails)):
+            raise WorkspaceMembersLimitExceeded()
+
         for invitee_email in invitee_emails:
             try:
                 token = RegisterService.invite_new_member(

api/controllers/console/workspace/plugin.py

@@ -41,12 +41,16 @@ class PluginListApi(Resource):
     @account_initialization_required
     def get(self):
         tenant_id = current_user.current_tenant_id
+        parser = reqparse.RequestParser()
+        parser.add_argument("page", type=int, required=False, location="args", default=1)
+        parser.add_argument("page_size", type=int, required=False, location="args", default=256)
+        args = parser.parse_args()
         try:
-            plugins = PluginService.list(tenant_id)
+            plugins_with_total = PluginService.list_with_total(tenant_id, args["page"], args["page_size"])
         except PluginDaemonClientSideError as e:
             raise ValueError(e)
 
-        return jsonable_encoder({"plugins": plugins})
+        return jsonable_encoder({"plugins": plugins_with_total.list, "total": plugins_with_total.total})
 
 
 class PluginListLatestVersionsApi(Resource):

api/controllers/console/workspace/workspace.py

@@ -68,16 +68,24 @@ class TenantListApi(Resource):
     @account_initialization_required
     def get(self):
         tenants = TenantService.get_join_tenants(current_user)
+        tenant_dicts = []
 
         for tenant in tenants:
             features = FeatureService.get_features(tenant.id)
-            if features.billing.enabled:
-                tenant.plan = features.billing.subscription.plan
-            else:
-                tenant.plan = "sandbox"
-            if tenant.id == current_user.current_tenant_id:
-                tenant.current = True  # Set current=True for current tenant
-        return {"workspaces": marshal(tenants, tenants_fields)}, 200
+
+            # Create a dictionary with tenant attributes
+            tenant_dict = {
+                "id": tenant.id,
+                "name": tenant.name,
+                "status": tenant.status,
+                "created_at": tenant.created_at,
+                "plan": features.billing.subscription.plan if features.billing.enabled else "sandbox",
+                "current": tenant.id == current_user.current_tenant_id,
+            }
+
+            tenant_dicts.append(tenant_dict)
+
+        return {"workspaces": marshal(tenant_dicts, tenants_fields)}, 200
 
 
 class WorkspaceListApi(Resource):

api/controllers/console/wraps.py

@@ -44,6 +44,17 @@ def only_edition_cloud(view):
     return decorated
 
 
+def only_edition_enterprise(view):
+    @wraps(view)
+    def decorated(*args, **kwargs):
+        if not dify_config.ENTERPRISE_ENABLED:
+            abort(404)
+
+        return view(*args, **kwargs)
+
+    return decorated
+
+
 def only_edition_self_hosted(view):
     @wraps(view)
     def decorated(*args, **kwargs):

api/controllers/files/upload.py

@@ -64,9 +64,24 @@ class PluginUploadFileApi(Resource):
 
             extension = guess_extension(tool_file.mimetype) or ".bin"
             preview_url = ToolFileManager.sign_file(tool_file_id=tool_file.id, extension=extension)
-            tool_file.mime_type = mimetype
-            tool_file.extension = extension
-            tool_file.preview_url = preview_url
+
+            # Create a dictionary with all the necessary attributes
+            result = {
+                "id": tool_file.id,
+                "user_id": tool_file.user_id,
+                "tenant_id": tool_file.tenant_id,
+                "conversation_id": tool_file.conversation_id,
+                "file_key": tool_file.file_key,
+                "mimetype": tool_file.mimetype,
+                "original_url": tool_file.original_url,
+                "name": tool_file.name,
+                "size": tool_file.size,
+                "mime_type": mimetype,
+                "extension": extension,
+                "preview_url": preview_url,
+            }
+
+            return result, 201
         except services.errors.file.FileTooLargeError as file_too_large_error:
             raise FileTooLargeError(file_too_large_error.description)
         except services.errors.file.UnsupportedFileTypeError:

api/controllers/inner_api/__init__.py

@@ -5,5 +5,6 @@ from libs.external_api import ExternalApi
 bp = Blueprint("inner_api", __name__, url_prefix="/inner/api")
 api = ExternalApi(bp)
 
+from . import mail
 from .plugin import plugin
 from .workspace import workspace

api/controllers/inner_api/mail.py

@@ -0,0 +1,27 @@
+from flask_restful import (
+    Resource,  # type: ignore
+    reqparse,
+)
+
+from controllers.console.wraps import setup_required
+from controllers.inner_api import api
+from controllers.inner_api.wraps import enterprise_inner_api_only
+from services.enterprise.mail_service import DifyMail, EnterpriseMailService
+
+
+class EnterpriseMail(Resource):
+    @setup_required
+    @enterprise_inner_api_only
+    def post(self):
+        parser = reqparse.RequestParser()
+        parser.add_argument("to", type=str, action="append", required=True)
+        parser.add_argument("subject", type=str, required=True)
+        parser.add_argument("body", type=str, required=True)
+        parser.add_argument("substitutions", type=dict, required=False)
+        args = parser.parse_args()
+
+        EnterpriseMailService.send_mail(DifyMail(**args))
+        return {"message": "success"}, 200
+
+
+api.add_resource(EnterpriseMail, "/enterprise/mail")

api/controllers/inner_api/plugin/plugin.py

@@ -29,7 +29,7 @@ from core.plugin.entities.request import (
     RequestRequestUploadFile,
 )
 from core.tools.entities.tool_entities import ToolProviderType
-from libs.helper import compact_generate_response
+from libs.helper import length_prefixed_response
 from models.account import Account, Tenant
 from models.model import EndUser
 
@@ -44,7 +44,7 @@ class PluginInvokeLLMApi(Resource):
             response = PluginModelBackwardsInvocation.invoke_llm(user_model.id, tenant_model, payload)
             return PluginModelBackwardsInvocation.convert_to_event_stream(response)
 
-        return compact_generate_response(generator())
+        return length_prefixed_response(0xF, generator())
 
 
 class PluginInvokeTextEmbeddingApi(Resource):
@@ -101,7 +101,7 @@ class PluginInvokeTTSApi(Resource):
             )
             return PluginModelBackwardsInvocation.convert_to_event_stream(response)
 
-        return compact_generate_response(generator())
+        return length_prefixed_response(0xF, generator())
 
 
 class PluginInvokeSpeech2TextApi(Resource):
@@ -162,7 +162,7 @@ class PluginInvokeToolApi(Resource):
                 ),
             )
 
-        return compact_generate_response(generator())
+        return length_prefixed_response(0xF, generator())
 
 
 class PluginInvokeParameterExtractorNodeApi(Resource):
@@ -228,7 +228,7 @@ class PluginInvokeAppApi(Resource):
             files=payload.files,
         )
 
-        return compact_generate_response(PluginAppBackwardsInvocation.convert_to_event_stream(response))
+        return length_prefixed_response(0xF, PluginAppBackwardsInvocation.convert_to_event_stream(response))
 
 
 class PluginInvokeEncryptApi(Resource):

api/controllers/inner_api/plugin/wraps.py

@@ -2,12 +2,14 @@ from collections.abc import Callable
 from functools import wraps
 from typing import Optional
 
-from flask import request
+from flask import current_app, request
+from flask_login import user_logged_in
 from flask_restful import reqparse
 from pydantic import BaseModel
 from sqlalchemy.orm import Session
 
 from extensions.ext_database import db
+from libs.login import _get_user
 from models.account import Account, Tenant
 from models.model import EndUser
 from services.account_service import AccountService
@@ -30,6 +32,7 @@ def get_user(tenant_id: str, user_id: str | None) -> Account | EndUser:
                     )
                     session.add(user_model)
                     session.commit()
+                    session.refresh(user_model)
             else:
                 user_model = AccountService.load_user(user_id)
                 if not user_model:
@@ -80,7 +83,12 @@ def get_user_tenant(view: Optional[Callable] = None):
                 raise ValueError("tenant not found")
 
             kwargs["tenant_model"] = tenant_model
-            kwargs["user_model"] = get_user(tenant_id, user_id)
+
+            user = get_user(tenant_id, user_id)
+            kwargs["user_model"] = user
+
+            current_app.login_manager._update_request_context_with_user(user)  # type: ignore
+            user_logged_in.send(current_app._get_current_object(), user=_get_user())  # type: ignore
 
             return view_func(*args, **kwargs)
 

api/controllers/service_api/app/annotation.py

@@ -3,19 +3,19 @@ from flask_restful import Resource, marshal, marshal_with, reqparse
 from werkzeug.exceptions import Forbidden
 
 from controllers.service_api import api
-from controllers.service_api.wraps import FetchUserArg, WhereisUserArg, validate_app_token
+from controllers.service_api.wraps import validate_app_token
 from extensions.ext_redis import redis_client
 from fields.annotation_fields import (
     annotation_fields,
 )
 from libs.login import current_user
-from models.model import App, EndUser
+from models.model import App
 from services.annotation_service import AppAnnotationService
 
 
 class AnnotationReplyActionApi(Resource):
-    @validate_app_token(fetch_user_arg=FetchUserArg(fetch_from=WhereisUserArg.JSON))
-    def post(self, app_model: App, end_user: EndUser, action):
+    @validate_app_token
+    def post(self, app_model: App, action):
         parser = reqparse.RequestParser()
         parser.add_argument("score_threshold", required=True, type=float, location="json")
         parser.add_argument("embedding_provider_name", required=True, type=str, location="json")
@@ -31,8 +31,8 @@ class AnnotationReplyActionApi(Resource):
 
 
 class AnnotationReplyActionStatusApi(Resource):
-    @validate_app_token(fetch_user_arg=FetchUserArg(fetch_from=WhereisUserArg.QUERY))
-    def get(self, app_model: App, end_user: EndUser, job_id, action):
+    @validate_app_token
+    def get(self, app_model: App, job_id, action):
         job_id = str(job_id)
         app_annotation_job_key = "{}_app_annotation_job_{}".format(action, str(job_id))
         cache_result = redis_client.get(app_annotation_job_key)
@@ -49,8 +49,8 @@ class AnnotationReplyActionStatusApi(Resource):
 
 
 class AnnotationListApi(Resource):
-    @validate_app_token(fetch_user_arg=FetchUserArg(fetch_from=WhereisUserArg.QUERY))
-    def get(self, app_model: App, end_user: EndUser):
+    @validate_app_token
+    def get(self, app_model: App):
         page = request.args.get("page", default=1, type=int)
         limit = request.args.get("limit", default=20, type=int)
         keyword = request.args.get("keyword", default="", type=str)
@@ -65,9 +65,9 @@ class AnnotationListApi(Resource):
         }
         return response, 200
 
-    @validate_app_token(fetch_user_arg=FetchUserArg(fetch_from=WhereisUserArg.JSON))
+    @validate_app_token
     @marshal_with(annotation_fields)
-    def post(self, app_model: App, end_user: EndUser):
+    def post(self, app_model: App):
         parser = reqparse.RequestParser()
         parser.add_argument("question", required=True, type=str, location="json")
         parser.add_argument("answer", required=True, type=str, location="json")
@@ -77,9 +77,9 @@ class AnnotationListApi(Resource):
 
 
 class AnnotationUpdateDeleteApi(Resource):
-    @validate_app_token(fetch_user_arg=FetchUserArg(fetch_from=WhereisUserArg.JSON))
+    @validate_app_token
     @marshal_with(annotation_fields)
-    def put(self, app_model: App, end_user: EndUser, annotation_id):
+    def put(self, app_model: App, annotation_id):
         if not current_user.is_editor:
             raise Forbidden()
 
@@ -91,8 +91,8 @@ class AnnotationUpdateDeleteApi(Resource):
         annotation = AppAnnotationService.update_app_annotation_directly(args, app_model.id, annotation_id)
         return annotation
 
-    @validate_app_token(fetch_user_arg=FetchUserArg(fetch_from=WhereisUserArg.QUERY))
-    def delete(self, app_model: App, end_user: EndUser, annotation_id):
+    @validate_app_token
+    def delete(self, app_model: App, annotation_id):
         if not current_user.is_editor:
             raise Forbidden()
 

api/controllers/service_api/app/app.py

@@ -47,7 +47,13 @@ class AppInfoApi(Resource):
     def get(self, app_model: App):
         """Get app information"""
         tags = [tag.name for tag in app_model.tags]
-        return {"name": app_model.name, "description": app_model.description, "tags": tags, "mode": app_model.mode}
+        return {
+            "name": app_model.name,
+            "description": app_model.description,
+            "tags": tags,
+            "mode": app_model.mode,
+            "author_name": app_model.author_name,
+        }
 
 
 api.add_resource(AppParameterApi, "/parameters")

api/controllers/service_api/app/workflow.py

@@ -24,12 +24,13 @@ from core.errors.error import (
     QuotaExceededError,
 )
 from core.model_runtime.errors.invoke import InvokeError
+from core.workflow.entities.workflow_execution import WorkflowExecutionStatus
 from extensions.ext_database import db
 from fields.workflow_app_log_fields import workflow_app_log_pagination_fields
 from libs import helper
 from libs.helper import TimestampField
 from models.model import App, AppMode, EndUser
-from models.workflow import WorkflowRun, WorkflowRunStatus
+from models.workflow import WorkflowRun
 from services.app_generate_service import AppGenerateService
 from services.errors.llm import InvokeRateLimitError
 from services.workflow_app_service import WorkflowAppService
@@ -134,11 +135,25 @@ class WorkflowAppLogApi(Resource):
         parser.add_argument("status", type=str, choices=["succeeded", "failed", "stopped"], location="args")
         parser.add_argument("created_at__before", type=str, location="args")
         parser.add_argument("created_at__after", type=str, location="args")
+        parser.add_argument(
+            "created_by_end_user_session_id",
+            type=str,
+            location="args",
+            required=False,
+            default=None,
+        )
+        parser.add_argument(
+            "created_by_account",
+            type=str,
+            location="args",
+            required=False,
+            default=None,
+        )
         parser.add_argument("page", type=int_range(1, 99999), default=1, location="args")
         parser.add_argument("limit", type=int_range(1, 100), default=20, location="args")
         args = parser.parse_args()
 
-        args.status = WorkflowRunStatus(args.status) if args.status else None
+        args.status = WorkflowExecutionStatus(args.status) if args.status else None
         if args.created_at__before:
             args.created_at__before = isoparse(args.created_at__before)
 
@@ -157,6 +172,8 @@ class WorkflowAppLogApi(Resource):
                 created_at_after=args.created_at__after,
                 page=args.page,
                 limit=args.limit,
+                created_by_end_user_session_id=args.created_by_end_user_session_id,
+                created_by_account=args.created_by_account,
             )
 
             return workflow_app_log_pagination

api/controllers/service_api/dataset/dataset.py

@@ -1,19 +1,25 @@
 from flask import request
-from flask_restful import marshal, reqparse
+from flask_restful import marshal, marshal_with, reqparse
 from werkzeug.exceptions import Forbidden, NotFound
 
 import services.dataset_service
 from controllers.service_api import api
-from controllers.service_api.dataset.error import DatasetInUseError, DatasetNameDuplicateError
-from controllers.service_api.wraps import DatasetApiResource
+from controllers.service_api.dataset.error import DatasetInUseError, DatasetNameDuplicateError, InvalidActionError
+from controllers.service_api.wraps import (
+    DatasetApiResource,
+    cloud_edition_billing_rate_limit_check,
+    validate_dataset_token,
+)
 from core.model_runtime.entities.model_entities import ModelType
 from core.plugin.entities.plugin import ModelProviderID
 from core.provider_manager import ProviderManager
 from fields.dataset_fields import dataset_detail_fields
+from fields.tag_fields import tag_fields
 from libs.login import current_user
 from models.dataset import Dataset, DatasetPermissionEnum
-from services.dataset_service import DatasetPermissionService, DatasetService
+from services.dataset_service import DatasetPermissionService, DatasetService, DocumentService
 from services.entities.knowledge_entities.knowledge_entities import RetrievalModel
+from services.tag_service import TagService
 
 
 def _validate_name(name):
@@ -68,6 +74,7 @@ class DatasetListApi(DatasetApiResource):
         response = {"data": data, "has_more": len(datasets) == limit, "limit": limit, "total": total, "page": page}
         return response, 200
 
+    @cloud_edition_billing_rate_limit_check("knowledge", "dataset")
     def post(self, tenant_id):
         """Resource for creating datasets."""
         parser = reqparse.RequestParser()
@@ -191,6 +198,7 @@ class DatasetApi(DatasetApiResource):
 
         return data, 200
 
+    @cloud_edition_billing_rate_limit_check("knowledge", "dataset")
     def patch(self, _, dataset_id):
         dataset_id_str = str(dataset_id)
         dataset = DatasetService.get_dataset(dataset_id_str)
@@ -291,6 +299,7 @@ class DatasetApi(DatasetApiResource):
 
         return result_data, 200
 
+    @cloud_edition_billing_rate_limit_check("knowledge", "dataset")
     def delete(self, _, dataset_id):
         """
         Deletes a dataset given its ID.
@@ -320,5 +329,186 @@ class DatasetApi(DatasetApiResource):
             raise DatasetInUseError()
 
 
+class DocumentStatusApi(DatasetApiResource):
+    """Resource for batch document status operations."""
+
+    def patch(self, tenant_id, dataset_id, action):
+        """
+        Batch update document status.
+
+        Args:
+            tenant_id: tenant id
+            dataset_id: dataset id
+            action: action to perform (enable, disable, archive, un_archive)
+
+        Returns:
+            dict: A dictionary with a key 'result' and a value 'success'
+            int: HTTP status code 200 indicating that the operation was successful.
+
+        Raises:
+            NotFound: If the dataset with the given ID does not exist.
+            Forbidden: If the user does not have permission.
+            InvalidActionError: If the action is invalid or cannot be performed.
+        """
+        dataset_id_str = str(dataset_id)
+        dataset = DatasetService.get_dataset(dataset_id_str)
+
+        if dataset is None:
+            raise NotFound("Dataset not found.")
+
+        # Check user's permission
+        try:
+            DatasetService.check_dataset_permission(dataset, current_user)
+        except services.errors.account.NoPermissionError as e:
+            raise Forbidden(str(e))
+
+        # Check dataset model setting
+        DatasetService.check_dataset_model_setting(dataset)
+
+        # Get document IDs from request body
+        data = request.get_json()
+        document_ids = data.get("document_ids", [])
+
+        try:
+            DocumentService.batch_update_document_status(dataset, document_ids, action, current_user)
+        except services.errors.document.DocumentIndexingError as e:
+            raise InvalidActionError(str(e))
+        except ValueError as e:
+            raise InvalidActionError(str(e))
+
+        return {"result": "success"}, 200
+
+
+class DatasetTagsApi(DatasetApiResource):
+    @validate_dataset_token
+    @marshal_with(tag_fields)
+    def get(self, _, dataset_id):
+        """Get all knowledge type tags."""
+        tags = TagService.get_tags("knowledge", current_user.current_tenant_id)
+
+        return tags, 200
+
+    @validate_dataset_token
+    def post(self, _, dataset_id):
+        """Add a knowledge type tag."""
+        if not (current_user.is_editor or current_user.is_dataset_editor):
+            raise Forbidden()
+
+        parser = reqparse.RequestParser()
+        parser.add_argument(
+            "name",
+            nullable=False,
+            required=True,
+            help="Name must be between 1 to 50 characters.",
+            type=DatasetTagsApi._validate_tag_name,
+        )
+
+        args = parser.parse_args()
+        args["type"] = "knowledge"
+        tag = TagService.save_tags(args)
+
+        response = {"id": tag.id, "name": tag.name, "type": tag.type, "binding_count": 0}
+
+        return response, 200
+
+    @validate_dataset_token
+    def patch(self, _, dataset_id):
+        if not (current_user.is_editor or current_user.is_dataset_editor):
+            raise Forbidden()
+
+        parser = reqparse.RequestParser()
+        parser.add_argument(
+            "name",
+            nullable=False,
+            required=True,
+            help="Name must be between 1 to 50 characters.",
+            type=DatasetTagsApi._validate_tag_name,
+        )
+        parser.add_argument("tag_id", nullable=False, required=True, help="Id of a tag.", type=str)
+        args = parser.parse_args()
+        args["type"] = "knowledge"
+        tag = TagService.update_tags(args, args.get("tag_id"))
+
+        binding_count = TagService.get_tag_binding_count(args.get("tag_id"))
+
+        response = {"id": tag.id, "name": tag.name, "type": tag.type, "binding_count": binding_count}
+
+        return response, 200
+
+    @validate_dataset_token
+    def delete(self, _, dataset_id):
+        """Delete a knowledge type tag."""
+        if not current_user.is_editor:
+            raise Forbidden()
+        parser = reqparse.RequestParser()
+        parser.add_argument("tag_id", nullable=False, required=True, help="Id of a tag.", type=str)
+        args = parser.parse_args()
+        TagService.delete_tag(args.get("tag_id"))
+
+        return 204
+
+    @staticmethod
+    def _validate_tag_name(name):
+        if not name or len(name) < 1 or len(name) > 50:
+            raise ValueError("Name must be between 1 to 50 characters.")
+        return name
+
+
+class DatasetTagBindingApi(DatasetApiResource):
+    @validate_dataset_token
+    def post(self, _, dataset_id):
+        # The role of the current user in the ta table must be admin, owner, editor, or dataset_operator
+        if not (current_user.is_editor or current_user.is_dataset_editor):
+            raise Forbidden()
+
+        parser = reqparse.RequestParser()
+        parser.add_argument(
+            "tag_ids", type=list, nullable=False, required=True, location="json", help="Tag IDs is required."
+        )
+        parser.add_argument(
+            "target_id", type=str, nullable=False, required=True, location="json", help="Target Dataset ID is required."
+        )
+
+        args = parser.parse_args()
+        args["type"] = "knowledge"
+        TagService.save_tag_binding(args)
+
+        return 204
+
+
+class DatasetTagUnbindingApi(DatasetApiResource):
+    @validate_dataset_token
+    def post(self, _, dataset_id):
+        # The role of the current user in the ta table must be admin, owner, editor, or dataset_operator
+        if not (current_user.is_editor or current_user.is_dataset_editor):
+            raise Forbidden()
+
+        parser = reqparse.RequestParser()
+        parser.add_argument("tag_id", type=str, nullable=False, required=True, help="Tag ID is required.")
+        parser.add_argument("target_id", type=str, nullable=False, required=True, help="Target ID is required.")
+
+        args = parser.parse_args()
+        args["type"] = "knowledge"
+        TagService.delete_tag_binding(args)
+
+        return 204
+
+
+class DatasetTagsBindingStatusApi(DatasetApiResource):
+    @validate_dataset_token
+    def get(self, _, *args, **kwargs):
+        """Get all knowledge type tags."""
+        dataset_id = kwargs.get("dataset_id")
+        tags = TagService.get_tags_by_target_id("knowledge", current_user.current_tenant_id, str(dataset_id))
+        tags_list = [{"id": tag.id, "name": tag.name} for tag in tags]
+        response = {"data": tags_list, "total": len(tags)}
+        return response, 200
+
+
 api.add_resource(DatasetListApi, "/datasets")
 api.add_resource(DatasetApi, "/datasets/<uuid:dataset_id>")
+api.add_resource(DocumentStatusApi, "/datasets/<uuid:dataset_id>/documents/status/<string:action>")
+api.add_resource(DatasetTagsApi, "/datasets/tags")
+api.add_resource(DatasetTagBindingApi, "/datasets/tags/binding")
+api.add_resource(DatasetTagUnbindingApi, "/datasets/tags/unbinding")
+api.add_resource(DatasetTagsBindingStatusApi, "/datasets/<uuid:dataset_id>/tags")

api/controllers/service_api/dataset/document.py

@@ -19,7 +19,11 @@ from controllers.service_api.dataset.error import (
     ArchivedDocumentImmutableError,
     DocumentIndexingError,
 )
-from controllers.service_api.wraps import DatasetApiResource, cloud_edition_billing_resource_check
+from controllers.service_api.wraps import (
+    DatasetApiResource,
+    cloud_edition_billing_rate_limit_check,
+    cloud_edition_billing_resource_check,
+)
 from core.errors.error import ProviderTokenNotInitError
 from extensions.ext_database import db
 from fields.document_fields import document_fields, document_status_fields
@@ -35,6 +39,7 @@ class DocumentAddByTextApi(DatasetApiResource):
 
     @cloud_edition_billing_resource_check("vector_space", "dataset")
     @cloud_edition_billing_resource_check("documents", "dataset")
+    @cloud_edition_billing_rate_limit_check("knowledge", "dataset")
     def post(self, tenant_id, dataset_id):
         """Create document by text."""
         parser = reqparse.RequestParser()
@@ -99,6 +104,7 @@ class DocumentUpdateByTextApi(DatasetApiResource):
     """Resource for update documents."""
 
     @cloud_edition_billing_resource_check("vector_space", "dataset")
+    @cloud_edition_billing_rate_limit_check("knowledge", "dataset")
     def post(self, tenant_id, dataset_id, document_id):
         """Update document by text."""
         parser = reqparse.RequestParser()
@@ -158,6 +164,7 @@ class DocumentAddByFileApi(DatasetApiResource):
 
     @cloud_edition_billing_resource_check("vector_space", "dataset")
     @cloud_edition_billing_resource_check("documents", "dataset")
+    @cloud_edition_billing_rate_limit_check("knowledge", "dataset")
     def post(self, tenant_id, dataset_id):
         """Create document by upload file."""
         args = {}
@@ -175,8 +182,11 @@ class DocumentAddByFileApi(DatasetApiResource):
 
         if not dataset:
             raise ValueError("Dataset does not exist.")
-        if not dataset.indexing_technique and not args.get("indexing_technique"):
+
+        indexing_technique = args.get("indexing_technique") or dataset.indexing_technique
+        if not indexing_technique:
             raise ValueError("indexing_technique is required.")
+        args["indexing_technique"] = indexing_technique
 
         # save file info
         file = request.files["file"]
@@ -206,12 +216,16 @@ class DocumentAddByFileApi(DatasetApiResource):
         knowledge_config = KnowledgeConfig(**args)
         DocumentService.document_create_args_validate(knowledge_config)
 
+        dataset_process_rule = dataset.latest_process_rule if "process_rule" not in args else None
+        if not knowledge_config.original_document_id and not dataset_process_rule and not knowledge_config.process_rule:
+            raise ValueError("process_rule is required.")
+
         try:
             documents, batch = DocumentService.save_document_with_dataset_id(
                 dataset=dataset,
                 knowledge_config=knowledge_config,
                 account=dataset.created_by_account,
-                dataset_process_rule=dataset.latest_process_rule if "process_rule" not in args else None,
+                dataset_process_rule=dataset_process_rule,
                 created_from="api",
             )
         except ProviderTokenNotInitError as ex:
@@ -225,6 +239,7 @@ class DocumentUpdateByFileApi(DatasetApiResource):
     """Resource for update documents."""
 
     @cloud_edition_billing_resource_check("vector_space", "dataset")
+    @cloud_edition_billing_rate_limit_check("knowledge", "dataset")
     def post(self, tenant_id, dataset_id, document_id):
         """Update document by upload file."""
         args = {}
@@ -295,6 +310,7 @@ class DocumentUpdateByFileApi(DatasetApiResource):
 
 
 class DocumentDeleteApi(DatasetApiResource):
+    @cloud_edition_billing_rate_limit_check("knowledge", "dataset")
     def delete(self, tenant_id, dataset_id, document_id):
         """Delete document."""
         document_id = str(document_id)
@@ -388,11 +404,22 @@ class DocumentIndexingStatusApi(DatasetApiResource):
                 .filter(DocumentSegment.document_id == str(document.id), DocumentSegment.status != "re_segment")
                 .count()
             )
-            document.completed_segments = completed_segments
-            document.total_segments = total_segments
-            if document.is_paused:
-                document.indexing_status = "paused"
-            documents_status.append(marshal(document, document_status_fields))
+            # Create a dictionary with document attributes and additional fields
+            document_dict = {
+                "id": document.id,
+                "indexing_status": "paused" if document.is_paused else document.indexing_status,
+                "processing_started_at": document.processing_started_at,
+                "parsing_completed_at": document.parsing_completed_at,
+                "cleaning_completed_at": document.cleaning_completed_at,
+                "splitting_completed_at": document.splitting_completed_at,
+                "completed_at": document.completed_at,
+                "paused_at": document.paused_at,
+                "error": document.error,
+                "stopped_at": document.stopped_at,
+                "completed_segments": completed_segments,
+                "total_segments": total_segments,
+            }
+            documents_status.append(marshal(document_dict, document_status_fields))
         data = {"data": documents_status}
         return data
 

api/controllers/service_api/dataset/hit_testing.py

@@ -1,9 +1,10 @@
 from controllers.console.datasets.hit_testing_base import DatasetsHitTestingBase
 from controllers.service_api import api
-from controllers.service_api.wraps import DatasetApiResource
+from controllers.service_api.wraps import DatasetApiResource, cloud_edition_billing_rate_limit_check
 
 
 class HitTestingApi(DatasetApiResource, DatasetsHitTestingBase):
+    @cloud_edition_billing_rate_limit_check("knowledge", "dataset")
     def post(self, tenant_id, dataset_id):
         dataset_id_str = str(dataset_id)
 

api/controllers/service_api/dataset/metadata.py

@@ -3,7 +3,7 @@ from flask_restful import marshal, reqparse
 from werkzeug.exceptions import NotFound
 
 from controllers.service_api import api
-from controllers.service_api.wraps import DatasetApiResource
+from controllers.service_api.wraps import DatasetApiResource, cloud_edition_billing_rate_limit_check
 from fields.dataset_fields import dataset_metadata_fields
 from services.dataset_service import DatasetService
 from services.entities.knowledge_entities.knowledge_entities import (
@@ -14,6 +14,7 @@ from services.metadata_service import MetadataService
 
 
 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")
@@ -39,6 +40,7 @@ class DatasetMetadataCreateServiceApi(DatasetApiResource):
 
 
 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")
@@ -54,6 +56,7 @@ class DatasetMetadataServiceApi(DatasetApiResource):
         metadata = MetadataService.update_metadata_name(dataset_id_str, metadata_id_str, args.get("name"))
         return marshal(metadata, dataset_metadata_fields), 200
 
+    @cloud_edition_billing_rate_limit_check("knowledge", "dataset")
     def delete(self, tenant_id, dataset_id, metadata_id):
         dataset_id_str = str(dataset_id)
         metadata_id_str = str(metadata_id)
@@ -73,6 +76,7 @@ class DatasetMetadataBuiltInFieldServiceApi(DatasetApiResource):
 
 
 class DatasetMetadataBuiltInFieldActionServiceApi(DatasetApiResource):
+    @cloud_edition_billing_rate_limit_check("knowledge", "dataset")
     def post(self, tenant_id, dataset_id, action):
         dataset_id_str = str(dataset_id)
         dataset = DatasetService.get_dataset(dataset_id_str)
@@ -88,6 +92,7 @@ class DatasetMetadataBuiltInFieldActionServiceApi(DatasetApiResource):
 
 
 class DocumentMetadataEditServiceApi(DatasetApiResource):
+    @cloud_edition_billing_rate_limit_check("knowledge", "dataset")
     def post(self, tenant_id, dataset_id):
         dataset_id_str = str(dataset_id)
         dataset = DatasetService.get_dataset(dataset_id_str)

api/controllers/service_api/dataset/segment.py

@@ -8,6 +8,7 @@ from controllers.service_api.app.error import ProviderNotInitializeError
 from controllers.service_api.wraps import (
     DatasetApiResource,
     cloud_edition_billing_knowledge_limit_check,
+    cloud_edition_billing_rate_limit_check,
     cloud_edition_billing_resource_check,
 )
 from core.errors.error import LLMBadRequestError, ProviderTokenNotInitError
@@ -35,6 +36,7 @@ class SegmentApi(DatasetApiResource):
 
     @cloud_edition_billing_resource_check("vector_space", "dataset")
     @cloud_edition_billing_knowledge_limit_check("add_segment", "dataset")
+    @cloud_edition_billing_rate_limit_check("knowledge", "dataset")
     def post(self, tenant_id, dataset_id, document_id):
         """Create single segment."""
         # check dataset
@@ -139,6 +141,7 @@ class SegmentApi(DatasetApiResource):
 
 
 class DatasetSegmentApi(DatasetApiResource):
+    @cloud_edition_billing_rate_limit_check("knowledge", "dataset")
     def delete(self, tenant_id, dataset_id, document_id, segment_id):
         # check dataset
         dataset_id = str(dataset_id)
@@ -162,6 +165,7 @@ class DatasetSegmentApi(DatasetApiResource):
         return 204
 
     @cloud_edition_billing_resource_check("vector_space", "dataset")
+    @cloud_edition_billing_rate_limit_check("knowledge", "dataset")
     def post(self, tenant_id, dataset_id, document_id, segment_id):
         # check dataset
         dataset_id = str(dataset_id)
@@ -208,12 +212,35 @@ class DatasetSegmentApi(DatasetApiResource):
         )
         return {"data": marshal(updated_segment, segment_fields), "doc_form": document.doc_form}, 200
 
+    def get(self, tenant_id, dataset_id, document_id, segment_id):
+        # check dataset
+        dataset_id = str(dataset_id)
+        tenant_id = str(tenant_id)
+        dataset = db.session.query(Dataset).filter(Dataset.tenant_id == tenant_id, Dataset.id == dataset_id).first()
+        if not dataset:
+            raise NotFound("Dataset not found.")
+        # check user's model setting
+        DatasetService.check_dataset_model_setting(dataset)
+        # check document
+        document_id = str(document_id)
+        document = DocumentService.get_document(dataset_id, document_id)
+        if not document:
+            raise NotFound("Document not found.")
+        # check segment
+        segment_id = str(segment_id)
+        segment = SegmentService.get_segment_by_id(segment_id=segment_id, tenant_id=current_user.current_tenant_id)
+        if not segment:
+            raise NotFound("Segment not found.")
+
+        return {"data": marshal(segment, segment_fields), "doc_form": document.doc_form}, 200
+
 
 class ChildChunkApi(DatasetApiResource):
     """Resource for child chunks."""
 
     @cloud_edition_billing_resource_check("vector_space", "dataset")
     @cloud_edition_billing_knowledge_limit_check("add_segment", "dataset")
+    @cloud_edition_billing_rate_limit_check("knowledge", "dataset")
     def post(self, tenant_id, dataset_id, document_id, segment_id):
         """Create child chunk."""
         # check dataset
@@ -310,6 +337,7 @@ class DatasetChildChunkApi(DatasetApiResource):
     """Resource for updating child chunks."""
 
     @cloud_edition_billing_knowledge_limit_check("add_segment", "dataset")
+    @cloud_edition_billing_rate_limit_check("knowledge", "dataset")
     def delete(self, tenant_id, dataset_id, document_id, segment_id, child_chunk_id):
         """Delete child chunk."""
         # check dataset
@@ -348,6 +376,7 @@ class DatasetChildChunkApi(DatasetApiResource):
 
     @cloud_edition_billing_resource_check("vector_space", "dataset")
     @cloud_edition_billing_knowledge_limit_check("add_segment", "dataset")
+    @cloud_edition_billing_rate_limit_check("knowledge", "dataset")
     def patch(self, tenant_id, dataset_id, document_id, segment_id, child_chunk_id):
         """Update child chunk."""
         # check dataset

api/controllers/service_api/wraps.py

@@ -99,7 +99,12 @@ def validate_app_token(view: Optional[Callable] = None, *, fetch_user_arg: Optio
                 if user_id:
                     user_id = str(user_id)
 
-                kwargs["end_user"] = create_or_update_end_user_for_user_id(app_model, user_id)
+                end_user = create_or_update_end_user_for_user_id(app_model, user_id)
+                kwargs["end_user"] = end_user
+
+                # Set EndUser as current logged-in user for flask_login.current_user
+                current_app.login_manager._update_request_context_with_user(end_user)  # type: ignore
+                user_logged_in.send(current_app._get_current_object(), user=end_user)  # type: ignore
 
             return view_func(*args, **kwargs)
 

api/controllers/web/__init__.py

@@ -15,4 +15,17 @@ api.add_resource(FileApi, "/files/upload")
 api.add_resource(RemoteFileInfoApi, "/remote-files/<path:url>")
 api.add_resource(RemoteFileUploadApi, "/remote-files/upload")
 
-from . import app, audio, completion, conversation, feature, message, passport, saved_message, site, workflow
+from . import (
+    app,
+    audio,
+    completion,
+    conversation,
+    feature,
+    forgot_password,
+    login,
+    message,
+    passport,
+    saved_message,
+    site,
+    workflow,
+)

api/controllers/web/app.py

@@ -1,12 +1,17 @@
-from flask_restful import marshal_with
+from flask import request
+from flask_restful import Resource, marshal_with, reqparse
 
 from controllers.common import fields
 from controllers.web import api
 from controllers.web.error import AppUnavailableError
 from controllers.web.wraps import WebApiResource
 from core.app.app_config.common.parameters_mapping import get_parameters_from_feature_dict
+from libs.passport import PassportService
 from models.model import App, AppMode
 from services.app_service import AppService
+from services.enterprise.enterprise_service import EnterpriseService
+from services.feature_service import FeatureService
+from services.webapp_auth_service import WebAppAuthService
 
 
 class AppParameterApi(WebApiResource):
@@ -40,5 +45,69 @@ class AppMeta(WebApiResource):
         return AppService().get_app_meta(app_model)
 
 
+class AppAccessMode(Resource):
+    def get(self):
+        parser = reqparse.RequestParser()
+        parser.add_argument("appId", type=str, required=False, location="args")
+        parser.add_argument("appCode", type=str, required=False, location="args")
+        args = parser.parse_args()
+
+        features = FeatureService.get_system_features()
+        if not features.webapp_auth.enabled:
+            return {"accessMode": "public"}
+
+        app_id = args.get("appId")
+        if args.get("appCode"):
+            app_code = args["appCode"]
+            app_id = AppService.get_app_id_by_code(app_code)
+
+        if not app_id:
+            raise ValueError("appId or appCode must be provided")
+
+        res = EnterpriseService.WebAppAuth.get_app_access_mode_by_id(app_id)
+
+        return {"accessMode": res.access_mode}
+
+
+class AppWebAuthPermission(Resource):
+    def get(self):
+        user_id = "visitor"
+        try:
+            auth_header = request.headers.get("Authorization")
+            if auth_header is None:
+                raise
+            if " " not in auth_header:
+                raise
+
+            auth_scheme, tk = auth_header.split(None, 1)
+            auth_scheme = auth_scheme.lower()
+            if auth_scheme != "bearer":
+                raise
+
+            decoded = PassportService().verify(tk)
+            user_id = decoded.get("user_id", "visitor")
+        except Exception as e:
+            pass
+
+        features = FeatureService.get_system_features()
+        if not features.webapp_auth.enabled:
+            return {"result": True}
+
+        parser = reqparse.RequestParser()
+        parser.add_argument("appId", type=str, required=True, location="args")
+        args = parser.parse_args()
+
+        app_id = args["appId"]
+        app_code = AppService.get_app_code_by_id(app_id)
+
+        res = True
+        if WebAppAuthService.is_app_require_permission_check(app_id=app_id):
+            res = EnterpriseService.WebAppAuth.is_user_allowed_to_access_webapp(str(user_id), app_code)
+        return {"result": res}
+
+
 api.add_resource(AppParameterApi, "/parameters")
 api.add_resource(AppMeta, "/meta")
+# webapp auth apis
+api.add_resource(AppAccessMode, "/webapp/access-mode")
+api.add_resource(AppWebAuthPermission, "/webapp/permission")

api/controllers/web/error.py

@@ -121,9 +121,15 @@ class UnsupportedFileTypeError(BaseHTTPException):
     code = 415
 
 
-class WebSSOAuthRequiredError(BaseHTTPException):
+class WebAppAuthRequiredError(BaseHTTPException):
     error_code = "web_sso_auth_required"
-    description = "Web SSO authentication required."
+    description = "Web app authentication required."
+    code = 401
+
+
+class WebAppAuthAccessDeniedError(BaseHTTPException):
+    error_code = "web_app_access_denied"
+    description = "You do not have permission to access this web app."
     code = 401
 
 

api/controllers/web/forgot_password.py

@@ -0,0 +1,147 @@
+import base64
+import secrets
+
+from flask import request
+from flask_restful import Resource, reqparse
+from sqlalchemy import select
+from sqlalchemy.orm import Session
+
+from controllers.console.auth.error import (
+    EmailCodeError,
+    EmailPasswordResetLimitError,
+    InvalidEmailError,
+    InvalidTokenError,
+    PasswordMismatchError,
+)
+from controllers.console.error import AccountNotFound, EmailSendIpLimitError
+from controllers.console.wraps import email_password_login_enabled, only_edition_enterprise, setup_required
+from controllers.web import api
+from extensions.ext_database import db
+from libs.helper import email, extract_remote_ip
+from libs.password import hash_password, valid_password
+from models.account import Account
+from services.account_service import AccountService
+
+
+class ForgotPasswordSendEmailApi(Resource):
+    @only_edition_enterprise
+    @setup_required
+    @email_password_login_enabled
+    def post(self):
+        parser = reqparse.RequestParser()
+        parser.add_argument("email", type=email, required=True, location="json")
+        parser.add_argument("language", type=str, required=False, location="json")
+        args = parser.parse_args()
+
+        ip_address = extract_remote_ip(request)
+        if AccountService.is_email_send_ip_limit(ip_address):
+            raise EmailSendIpLimitError()
+
+        if args["language"] is not None and args["language"] == "zh-Hans":
+            language = "zh-Hans"
+        else:
+            language = "en-US"
+
+        with Session(db.engine) as session:
+            account = session.execute(select(Account).filter_by(email=args["email"])).scalar_one_or_none()
+        token = None
+        if account is None:
+            raise AccountNotFound()
+        else:
+            token = AccountService.send_reset_password_email(account=account, email=args["email"], language=language)
+
+        return {"result": "success", "data": token}
+
+
+class ForgotPasswordCheckApi(Resource):
+    @only_edition_enterprise
+    @setup_required
+    @email_password_login_enabled
+    def post(self):
+        parser = reqparse.RequestParser()
+        parser.add_argument("email", type=str, required=True, location="json")
+        parser.add_argument("code", type=str, required=True, location="json")
+        parser.add_argument("token", type=str, required=True, nullable=False, location="json")
+        args = parser.parse_args()
+
+        user_email = args["email"]
+
+        is_forgot_password_error_rate_limit = AccountService.is_forgot_password_error_rate_limit(args["email"])
+        if is_forgot_password_error_rate_limit:
+            raise EmailPasswordResetLimitError()
+
+        token_data = AccountService.get_reset_password_data(args["token"])
+        if token_data is None:
+            raise InvalidTokenError()
+
+        if user_email != token_data.get("email"):
+            raise InvalidEmailError()
+
+        if args["code"] != token_data.get("code"):
+            AccountService.add_forgot_password_error_rate_limit(args["email"])
+            raise EmailCodeError()
+
+        # Verified, revoke the first token
+        AccountService.revoke_reset_password_token(args["token"])
+
+        # Refresh token data by generating a new token
+        _, new_token = AccountService.generate_reset_password_token(
+            user_email, code=args["code"], additional_data={"phase": "reset"}
+        )
+
+        AccountService.reset_forgot_password_error_rate_limit(args["email"])
+        return {"is_valid": True, "email": token_data.get("email"), "token": new_token}
+
+
+class ForgotPasswordResetApi(Resource):
+    @only_edition_enterprise
+    @setup_required
+    @email_password_login_enabled
+    def post(self):
+        parser = reqparse.RequestParser()
+        parser.add_argument("token", type=str, required=True, nullable=False, location="json")
+        parser.add_argument("new_password", type=valid_password, required=True, nullable=False, location="json")
+        parser.add_argument("password_confirm", type=valid_password, required=True, nullable=False, location="json")
+        args = parser.parse_args()
+
+        # Validate passwords match
+        if args["new_password"] != args["password_confirm"]:
+            raise PasswordMismatchError()
+
+        # Validate token and get reset data
+        reset_data = AccountService.get_reset_password_data(args["token"])
+        if not reset_data:
+            raise InvalidTokenError()
+        # Must use token in reset phase
+        if reset_data.get("phase", "") != "reset":
+            raise InvalidTokenError()
+
+        # Revoke token to prevent reuse
+        AccountService.revoke_reset_password_token(args["token"])
+
+        # Generate secure salt and hash password
+        salt = secrets.token_bytes(16)
+        password_hashed = hash_password(args["new_password"], salt)
+
+        email = reset_data.get("email", "")
+
+        with Session(db.engine) as session:
+            account = session.execute(select(Account).filter_by(email=email)).scalar_one_or_none()
+
+            if account:
+                self._update_existing_account(account, password_hashed, salt, session)
+            else:
+                raise AccountNotFound()
+
+        return {"result": "success"}
+
+    def _update_existing_account(self, account, password_hashed, salt, session):
+        # Update existing account credentials
+        account.password = base64.b64encode(password_hashed).decode()
+        account.password_salt = base64.b64encode(salt).decode()
+        session.commit()
+
+
+api.add_resource(ForgotPasswordSendEmailApi, "/forgot-password")
+api.add_resource(ForgotPasswordCheckApi, "/forgot-password/validity")
+api.add_resource(ForgotPasswordResetApi, "/forgot-password/resets")

api/controllers/web/login.py

@@ -0,0 +1,108 @@
+from flask_restful import Resource, reqparse
+from jwt import InvalidTokenError  # type: ignore
+
+import services
+from controllers.console.auth.error import EmailCodeError, EmailOrPasswordMismatchError, InvalidEmailError
+from controllers.console.error import AccountBannedError, AccountNotFound
+from controllers.console.wraps import only_edition_enterprise, setup_required
+from controllers.web import api
+from libs.helper import email
+from libs.password import valid_password
+from services.account_service import AccountService
+from services.webapp_auth_service import WebAppAuthService
+
+
+class LoginApi(Resource):
+    """Resource for web app email/password login."""
+
+    @setup_required
+    @only_edition_enterprise
+    def post(self):
+        """Authenticate user and login."""
+        parser = reqparse.RequestParser()
+        parser.add_argument("email", type=email, required=True, location="json")
+        parser.add_argument("password", type=valid_password, required=True, location="json")
+        args = parser.parse_args()
+
+        try:
+            account = WebAppAuthService.authenticate(args["email"], args["password"])
+        except services.errors.account.AccountLoginError:
+            raise AccountBannedError()
+        except services.errors.account.AccountPasswordError:
+            raise EmailOrPasswordMismatchError()
+        except services.errors.account.AccountNotFoundError:
+            raise AccountNotFound()
+
+        token = WebAppAuthService.login(account=account)
+        return {"result": "success", "data": {"access_token": token}}
+
+
+# class LogoutApi(Resource):
+#     @setup_required
+#     def get(self):
+#         account = cast(Account, flask_login.current_user)
+#         if isinstance(account, flask_login.AnonymousUserMixin):
+#             return {"result": "success"}
+#         flask_login.logout_user()
+#         return {"result": "success"}
+
+
+class EmailCodeLoginSendEmailApi(Resource):
+    @setup_required
+    @only_edition_enterprise
+    def post(self):
+        parser = reqparse.RequestParser()
+        parser.add_argument("email", type=email, required=True, location="json")
+        parser.add_argument("language", type=str, required=False, location="json")
+        args = parser.parse_args()
+
+        if args["language"] is not None and args["language"] == "zh-Hans":
+            language = "zh-Hans"
+        else:
+            language = "en-US"
+
+        account = WebAppAuthService.get_user_through_email(args["email"])
+        if account is None:
+            raise AccountNotFound()
+        else:
+            token = WebAppAuthService.send_email_code_login_email(account=account, language=language)
+
+        return {"result": "success", "data": token}
+
+
+class EmailCodeLoginApi(Resource):
+    @setup_required
+    @only_edition_enterprise
+    def post(self):
+        parser = reqparse.RequestParser()
+        parser.add_argument("email", type=str, required=True, location="json")
+        parser.add_argument("code", type=str, required=True, location="json")
+        parser.add_argument("token", type=str, required=True, location="json")
+        args = parser.parse_args()
+
+        user_email = args["email"]
+
+        token_data = WebAppAuthService.get_email_code_login_data(args["token"])
+        if token_data is None:
+            raise InvalidTokenError()
+
+        if token_data["email"] != args["email"]:
+            raise InvalidEmailError()
+
+        if token_data["code"] != args["code"]:
+            raise EmailCodeError()
+
+        WebAppAuthService.revoke_email_code_login_token(args["token"])
+        account = WebAppAuthService.get_user_through_email(user_email)
+        if not account:
+            raise AccountNotFound()
+
+        token = WebAppAuthService.login(account=account)
+        AccountService.reset_login_error_rate_limit(args["email"])
+        return {"result": "success", "data": {"access_token": token}}
+
+
+api.add_resource(LoginApi, "/login")
+# api.add_resource(LogoutApi, "/logout")
+api.add_resource(EmailCodeLoginSendEmailApi, "/email-code-login")
+api.add_resource(EmailCodeLoginApi, "/email-code-login/validity")

api/controllers/web/passport.py

@@ -1,16 +1,19 @@
 import uuid
+from datetime import UTC, datetime, timedelta
 
 from flask import request
 from flask_restful import Resource
 from werkzeug.exceptions import NotFound, Unauthorized
 
+from configs import dify_config
 from controllers.web import api
-from controllers.web.error import WebSSOAuthRequiredError
+from controllers.web.error import WebAppAuthRequiredError
 from extensions.ext_database import db
 from libs.passport import PassportService
 from models.model import App, EndUser, Site
 from services.enterprise.enterprise_service import EnterpriseService
 from services.feature_service import FeatureService
+from services.webapp_auth_service import WebAppAuthService, WebAppAuthType
 
 
 class PassportResource(Resource):
@@ -20,14 +23,23 @@ class PassportResource(Resource):
         system_features = FeatureService.get_system_features()
         app_code = request.headers.get("X-App-Code")
         user_id = request.args.get("user_id")
+        web_app_access_token = request.args.get("web_app_access_token")
 
         if app_code is None:
             raise Unauthorized("X-App-Code header is missing.")
 
-        if system_features.sso_enforced_for_web:
-            app_web_sso_enabled = EnterpriseService.get_app_web_sso_enabled(app_code).get("enabled", False)
-            if app_web_sso_enabled:
-                raise WebSSOAuthRequiredError()
+        # exchange token for enterprise logined web user
+        enterprise_user_decoded = decode_enterprise_webapp_user_id(web_app_access_token)
+        if enterprise_user_decoded:
+            # a web user has already logged in, exchange a token for this app without redirecting to the login page
+            return exchange_token_for_existing_web_user(
+                app_code=app_code, enterprise_user_decoded=enterprise_user_decoded
+            )
+
+        if system_features.webapp_auth.enabled:
+            app_settings = EnterpriseService.WebAppAuth.get_app_access_mode_by_code(app_code=app_code)
+            if not app_settings or not app_settings.access_mode == "public":
+                raise WebAppAuthRequiredError()
 
         # get site from db and check if it is normal
         site = db.session.query(Site).filter(Site.code == app_code, Site.status == "normal").first()
@@ -84,6 +96,128 @@ class PassportResource(Resource):
 api.add_resource(PassportResource, "/passport")
 
 
+def decode_enterprise_webapp_user_id(jwt_token: str | None):
+    """
+    Decode the enterprise user session from the Authorization header.
+    """
+    if not jwt_token:
+        return None
+
+    decoded = PassportService().verify(jwt_token)
+    source = decoded.get("token_source")
+    if not source or source != "webapp_login_token":
+        raise Unauthorized("Invalid token source. Expected 'webapp_login_token'.")
+    return decoded
+
+
+def exchange_token_for_existing_web_user(app_code: str, enterprise_user_decoded: dict):
+    """
+    Exchange a token for an existing web user session.
+    """
+    user_id = enterprise_user_decoded.get("user_id")
+    end_user_id = enterprise_user_decoded.get("end_user_id")
+    session_id = enterprise_user_decoded.get("session_id")
+    user_auth_type = enterprise_user_decoded.get("auth_type")
+    if not user_auth_type:
+        raise Unauthorized("Missing auth_type in the token.")
+
+    site = db.session.query(Site).filter(Site.code == app_code, Site.status == "normal").first()
+    if not site:
+        raise NotFound()
+
+    app_model = db.session.query(App).filter(App.id == site.app_id).first()
+    if not app_model or app_model.status != "normal" or not app_model.enable_site:
+        raise NotFound()
+
+    app_auth_type = WebAppAuthService.get_app_auth_type(app_code=app_code)
+
+    if app_auth_type == WebAppAuthType.PUBLIC:
+        return _exchange_for_public_app_token(app_model, site, enterprise_user_decoded)
+    elif app_auth_type == WebAppAuthType.EXTERNAL and user_auth_type != "external":
+        raise WebAppAuthRequiredError("Please login as external user.")
+    elif app_auth_type == WebAppAuthType.INTERNAL and user_auth_type != "internal":
+        raise WebAppAuthRequiredError("Please login as internal user.")
+
+    end_user = None
+    if end_user_id:
+        end_user = db.session.query(EndUser).filter(EndUser.id == end_user_id).first()
+    if session_id:
+        end_user = (
+            db.session.query(EndUser)
+            .filter(
+                EndUser.session_id == session_id,
+                EndUser.tenant_id == app_model.tenant_id,
+                EndUser.app_id == app_model.id,
+            )
+            .first()
+        )
+    if not end_user:
+        if not session_id:
+            raise NotFound("Missing session_id for existing web user.")
+        end_user = EndUser(
+            tenant_id=app_model.tenant_id,
+            app_id=app_model.id,
+            type="browser",
+            is_anonymous=True,
+            session_id=session_id,
+        )
+        db.session.add(end_user)
+        db.session.commit()
+    exp_dt = datetime.now(UTC) + timedelta(minutes=dify_config.ACCESS_TOKEN_EXPIRE_MINUTES)
+    exp = int(exp_dt.timestamp())
+    payload = {
+        "iss": site.id,
+        "sub": "Web API Passport",
+        "app_id": site.app_id,
+        "app_code": site.code,
+        "user_id": user_id,
+        "end_user_id": end_user.id,
+        "auth_type": user_auth_type,
+        "granted_at": int(datetime.now(UTC).timestamp()),
+        "token_source": "webapp",
+        "exp": exp,
+    }
+    token: str = PassportService().issue(payload)
+    return {
+        "access_token": token,
+    }
+
+
+def _exchange_for_public_app_token(app_model, site, token_decoded):
+    user_id = token_decoded.get("user_id")
+    end_user = None
+    if user_id:
+        end_user = (
+            db.session.query(EndUser).filter(EndUser.app_id == app_model.id, EndUser.session_id == user_id).first()
+        )
+
+    if not end_user:
+        end_user = EndUser(
+            tenant_id=app_model.tenant_id,
+            app_id=app_model.id,
+            type="browser",
+            is_anonymous=True,
+            session_id=generate_session_id(),
+        )
+
+        db.session.add(end_user)
+        db.session.commit()
+
+    payload = {
+        "iss": site.app_id,
+        "sub": "Web API Passport",
+        "app_id": site.app_id,
+        "app_code": site.code,
+        "end_user_id": end_user.id,
+    }
+
+    tk = PassportService().issue(payload)
+
+    return {
+        "access_token": tk,
+    }
+
+
 def generate_session_id():
     """
     Generate a unique session ID.

api/controllers/web/wraps.py

@@ -1,15 +1,17 @@
+from datetime import UTC, datetime
 from functools import wraps
 
 from flask import request
 from flask_restful import Resource
 from werkzeug.exceptions import BadRequest, NotFound, Unauthorized
 
-from controllers.web.error import WebSSOAuthRequiredError
+from controllers.web.error import WebAppAuthAccessDeniedError, WebAppAuthRequiredError
 from extensions.ext_database import db
 from libs.passport import PassportService
 from models.model import App, EndUser, Site
-from services.enterprise.enterprise_service import EnterpriseService
+from services.enterprise.enterprise_service import EnterpriseService, WebAppSettings
 from services.feature_service import FeatureService
+from services.webapp_auth_service import WebAppAuthService
 
 
 def validate_jwt_token(view=None):
@@ -29,7 +31,7 @@ def validate_jwt_token(view=None):
 
 def decode_jwt_token():
     system_features = FeatureService.get_system_features()
-    app_code = request.headers.get("X-App-Code")
+    app_code = str(request.headers.get("X-App-Code"))
     try:
         auth_header = request.headers.get("Authorization")
         if auth_header is None:
@@ -45,7 +47,8 @@ def decode_jwt_token():
             raise Unauthorized("Invalid Authorization header format. Expected 'Bearer <api-key>' format.")
         decoded = PassportService().verify(tk)
         app_code = decoded.get("app_code")
-        app_model = db.session.query(App).filter(App.id == decoded["app_id"]).first()
+        app_id = decoded.get("app_id")
+        app_model = db.session.query(App).filter(App.id == app_id).first()
         site = db.session.query(Site).filter(Site.code == app_code).first()
         if not app_model:
             raise NotFound()
@@ -53,39 +56,90 @@ def decode_jwt_token():
             raise BadRequest("Site URL is no longer valid.")
         if app_model.enable_site is False:
             raise BadRequest("Site is disabled.")
-        end_user = db.session.query(EndUser).filter(EndUser.id == decoded["end_user_id"]).first()
+        end_user_id = decoded.get("end_user_id")
+        end_user = db.session.query(EndUser).filter(EndUser.id == end_user_id).first()
         if not end_user:
             raise NotFound()
 
-        _validate_web_sso_token(decoded, system_features, app_code)
+        # for enterprise webapp auth
+        app_web_auth_enabled = False
+        webapp_settings = None
+        if system_features.webapp_auth.enabled:
+            webapp_settings = EnterpriseService.WebAppAuth.get_app_access_mode_by_code(app_code=app_code)
+            if not webapp_settings:
+                raise NotFound("Web app settings not found.")
+            app_web_auth_enabled = webapp_settings.access_mode != "public"
+
+        _validate_webapp_token(decoded, app_web_auth_enabled, system_features.webapp_auth.enabled)
+        _validate_user_accessibility(
+            decoded, app_code, app_web_auth_enabled, system_features.webapp_auth.enabled, webapp_settings
+        )
 
         return app_model, end_user
     except Unauthorized as e:
-        if system_features.sso_enforced_for_web:
-            app_web_sso_enabled = EnterpriseService.get_app_web_sso_enabled(app_code).get("enabled", False)
-            if app_web_sso_enabled:
-                raise WebSSOAuthRequiredError()
+        if system_features.webapp_auth.enabled:
+            if not app_code:
+                raise Unauthorized("Please re-login to access the web app.")
+            app_web_auth_enabled = (
+                EnterpriseService.WebAppAuth.get_app_access_mode_by_code(app_code=str(app_code)).access_mode != "public"
+            )
+            if app_web_auth_enabled:
+                raise WebAppAuthRequiredError()
 
         raise Unauthorized(e.description)
 
 
-def _validate_web_sso_token(decoded, system_features, app_code):
-    app_web_sso_enabled = False
-
-    # Check if SSO is enforced for web, and if the token source is not SSO, raise an error and redirect to SSO login
-    if system_features.sso_enforced_for_web:
-        app_web_sso_enabled = EnterpriseService.get_app_web_sso_enabled(app_code).get("enabled", False)
-        if app_web_sso_enabled:
-            source = decoded.get("token_source")
-            if not source or source != "sso":
-                raise WebSSOAuthRequiredError()
-
-    # Check if SSO is not enforced for web, and if the token source is SSO,
-    # raise an error and redirect to normal passport login
-    if not system_features.sso_enforced_for_web or not app_web_sso_enabled:
+def _validate_webapp_token(decoded, app_web_auth_enabled: bool, system_webapp_auth_enabled: bool):
+    # Check if authentication is enforced for web app, and if the token source is not webapp,
+    # raise an error and redirect to login
+    if system_webapp_auth_enabled and app_web_auth_enabled:
         source = decoded.get("token_source")
-        if source and source == "sso":
-            raise Unauthorized("sso token expired.")
+        if not source or source != "webapp":
+            raise WebAppAuthRequiredError()
+
+    # Check if authentication is not enforced for web, and if the token source is webapp,
+    # raise an error and redirect to normal passport login
+    if not system_webapp_auth_enabled or not app_web_auth_enabled:
+        source = decoded.get("token_source")
+        if source and source == "webapp":
+            raise Unauthorized("webapp token expired.")
+
+
+def _validate_user_accessibility(
+    decoded,
+    app_code,
+    app_web_auth_enabled: bool,
+    system_webapp_auth_enabled: bool,
+    webapp_settings: WebAppSettings | None,
+):
+    if system_webapp_auth_enabled and app_web_auth_enabled:
+        # Check if the user is allowed to access the web app
+        user_id = decoded.get("user_id")
+        if not user_id:
+            raise WebAppAuthRequiredError()
+
+        if not webapp_settings:
+            raise WebAppAuthRequiredError("Web app settings not found.")
+
+        if WebAppAuthService.is_app_require_permission_check(access_mode=webapp_settings.access_mode):
+            if not EnterpriseService.WebAppAuth.is_user_allowed_to_access_webapp(user_id, app_code=app_code):
+                raise WebAppAuthAccessDeniedError()
+
+        auth_type = decoded.get("auth_type")
+        granted_at = decoded.get("granted_at")
+        if not auth_type:
+            raise WebAppAuthAccessDeniedError("Missing auth_type in the token.")
+        if not granted_at:
+            raise WebAppAuthAccessDeniedError("Missing granted_at in the token.")
+        # check if sso has been updated
+        if auth_type == "external":
+            last_update_time = EnterpriseService.get_app_sso_settings_last_update_time()
+            if granted_at and datetime.fromtimestamp(granted_at, tz=UTC) < last_update_time:
+                raise WebAppAuthAccessDeniedError("SSO settings have been updated. Please re-login.")
+        elif auth_type == "internal":
+            last_update_time = EnterpriseService.get_workspace_sso_settings_last_update_time()
+            if granted_at and datetime.fromtimestamp(granted_at, tz=UTC) < last_update_time:
+                raise WebAppAuthAccessDeniedError("SSO settings have been updated. Please re-login.")
 
 
 class WebApiResource(Resource):

api/core/agent/cot_agent_runner.py

@@ -63,7 +63,7 @@ class CotAgentRunner(BaseAgentRunner, ABC):
         self._instruction = self._fill_in_inputs_from_external_data_tools(instruction, inputs)
 
         iteration_step = 1
-        max_iteration_steps = min(app_config.agent.max_iteration if app_config.agent else 5, 5) + 1
+        max_iteration_steps = min(app_config.agent.max_iteration, 99) + 1
 
         # convert tools into ModelRuntime Tool format
         tool_instances, prompt_messages_tools = self._init_prompt_tools()

api/core/agent/entities.py

@@ -82,7 +82,7 @@ class AgentEntity(BaseModel):
     strategy: Strategy
     prompt: Optional[AgentPromptEntity] = None
     tools: Optional[list[AgentToolEntity]] = None
-    max_iteration: int = 5
+    max_iteration: int = 10
 
 
 class AgentInvokeMessage(ToolInvokeMessage):

api/core/agent/fc_agent_runner.py

@@ -48,7 +48,7 @@ class FunctionCallAgentRunner(BaseAgentRunner):
         assert app_config.agent
 
         iteration_step = 1
-        max_iteration_steps = min(app_config.agent.max_iteration, 5) + 1
+        max_iteration_steps = min(app_config.agent.max_iteration, 99) + 1
 
         # continue to run until there is not any tool call
         function_call_state = True

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

@@ -75,7 +75,7 @@ class AgentConfigManager:
                     strategy=strategy,
                     prompt=agent_prompt_entity,
                     tools=agent_tools,
-                    max_iteration=agent_dict.get("max_iteration", 5),
+                    max_iteration=agent_dict.get("max_iteration", 10),
                 )
 
         return None

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

@@ -138,15 +138,12 @@ class DatasetConfigManager:
         if not config.get("dataset_configs"):
             config["dataset_configs"] = {"retrieval_model": "single"}
 
+        if not isinstance(config["dataset_configs"], dict):
+            raise ValueError("dataset_configs must be of object type")
+
         if not config["dataset_configs"].get("datasets"):
             config["dataset_configs"]["datasets"] = {"strategy": "router", "datasets": []}
 
-        if not isinstance(config["dataset_configs"], dict):
-            raise ValueError("dataset_configs must be of object type")
-
-        if not isinstance(config["dataset_configs"], dict):
-            raise ValueError("dataset_configs must be of object type")
-
         need_manual_query_datasets = config.get("dataset_configs") and config["dataset_configs"].get(
             "datasets", {}
         ).get("datasets")

api/core/app/app_config/easy_ui_based_app/model_config/converter.py

@@ -70,7 +70,7 @@ class ModelConfigConverter:
         if not model_mode:
             model_mode = LLMMode.CHAT.value
             if model_schema and model_schema.model_properties.get(ModelPropertyKey.MODE):
-                model_mode = LLMMode.value_of(model_schema.model_properties[ModelPropertyKey.MODE]).value
+                model_mode = LLMMode(model_schema.model_properties[ModelPropertyKey.MODE]).value
 
         if not model_schema:
             raise ValueError(f"Model {model_name} not exist.")

api/core/app/app_config/entities.py

@@ -109,6 +109,7 @@ class VariableEntity(BaseModel):
     description: str = ""
     type: VariableEntityType
     required: bool = False
+    hide: bool = False
     max_length: Optional[int] = None
     options: Sequence[str] = Field(default_factory=list)
     allowed_file_types: Sequence[FileType] = Field(default_factory=list)

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

@@ -26,12 +26,14 @@ from core.model_runtime.errors.invoke import InvokeAuthorizationError
 from core.ops.ops_trace_manager import TraceQueueManager
 from core.prompt.utils.get_thread_messages_length import get_thread_messages_length
 from core.repositories import SQLAlchemyWorkflowNodeExecutionRepository
-from core.workflow.repository.workflow_node_execution_repository import WorkflowNodeExecutionRepository
+from core.repositories.sqlalchemy_workflow_execution_repository import SQLAlchemyWorkflowExecutionRepository
+from core.workflow.repositories.workflow_execution_repository import WorkflowExecutionRepository
+from core.workflow.repositories.workflow_node_execution_repository import WorkflowNodeExecutionRepository
 from extensions.ext_database import db
 from factories import file_factory
-from models.account import Account
-from models.model import App, Conversation, EndUser, Message
-from models.workflow import Workflow
+from libs.flask_utils import preserve_flask_contexts
+from models import Account, App, Conversation, EndUser, Message, Workflow, WorkflowNodeExecutionTriggeredFrom
+from models.enums import WorkflowRunTriggeredFrom
 from services.conversation_service import ConversationService
 from services.errors.message import MessageNotExistsError
 
@@ -157,16 +159,30 @@ class AdvancedChatAppGenerator(MessageBasedAppGenerator):
             trace_manager=trace_manager,
             workflow_run_id=workflow_run_id,
         )
-        contexts.tenant_id.set(application_generate_entity.app_config.tenant_id)
         contexts.plugin_tool_providers.set({})
         contexts.plugin_tool_providers_lock.set(threading.Lock())
 
-        # Create workflow node execution repository
+        # Create repositories
+        #
+        # Create session factory
         session_factory = sessionmaker(bind=db.engine, expire_on_commit=False)
+        # Create workflow execution(aka workflow run) repository
+        if invoke_from == InvokeFrom.DEBUGGER:
+            workflow_triggered_from = WorkflowRunTriggeredFrom.DEBUGGING
+        else:
+            workflow_triggered_from = WorkflowRunTriggeredFrom.APP_RUN
+        workflow_execution_repository = SQLAlchemyWorkflowExecutionRepository(
+            session_factory=session_factory,
+            user=user,
+            app_id=application_generate_entity.app_config.app_id,
+            triggered_from=workflow_triggered_from,
+        )
+        # Create workflow node execution repository
         workflow_node_execution_repository = SQLAlchemyWorkflowNodeExecutionRepository(
             session_factory=session_factory,
-            tenant_id=application_generate_entity.app_config.tenant_id,
+            user=user,
             app_id=application_generate_entity.app_config.app_id,
+            triggered_from=WorkflowNodeExecutionTriggeredFrom.WORKFLOW_RUN,
         )
 
         return self._generate(
@@ -174,6 +190,7 @@ class AdvancedChatAppGenerator(MessageBasedAppGenerator):
             user=user,
             invoke_from=invoke_from,
             application_generate_entity=application_generate_entity,
+            workflow_execution_repository=workflow_execution_repository,
             workflow_node_execution_repository=workflow_node_execution_repository,
             conversation=conversation,
             stream=streaming,
@@ -223,16 +240,26 @@ class AdvancedChatAppGenerator(MessageBasedAppGenerator):
                 node_id=node_id, inputs=args["inputs"]
             ),
         )
-        contexts.tenant_id.set(application_generate_entity.app_config.tenant_id)
         contexts.plugin_tool_providers.set({})
         contexts.plugin_tool_providers_lock.set(threading.Lock())
 
-        # Create workflow node execution repository
+        # Create repositories
+        #
+        # Create session factory
         session_factory = sessionmaker(bind=db.engine, expire_on_commit=False)
+        # Create workflow execution(aka workflow run) repository
+        workflow_execution_repository = SQLAlchemyWorkflowExecutionRepository(
+            session_factory=session_factory,
+            user=user,
+            app_id=application_generate_entity.app_config.app_id,
+            triggered_from=WorkflowRunTriggeredFrom.DEBUGGING,
+        )
+        # Create workflow node execution repository
         workflow_node_execution_repository = SQLAlchemyWorkflowNodeExecutionRepository(
             session_factory=session_factory,
-            tenant_id=application_generate_entity.app_config.tenant_id,
+            user=user,
             app_id=application_generate_entity.app_config.app_id,
+            triggered_from=WorkflowNodeExecutionTriggeredFrom.SINGLE_STEP,
         )
 
         return self._generate(
@@ -240,6 +267,7 @@ class AdvancedChatAppGenerator(MessageBasedAppGenerator):
             user=user,
             invoke_from=InvokeFrom.DEBUGGER,
             application_generate_entity=application_generate_entity,
+            workflow_execution_repository=workflow_execution_repository,
             workflow_node_execution_repository=workflow_node_execution_repository,
             conversation=None,
             stream=streaming,
@@ -287,16 +315,26 @@ class AdvancedChatAppGenerator(MessageBasedAppGenerator):
             extras={"auto_generate_conversation_name": False},
             single_loop_run=AdvancedChatAppGenerateEntity.SingleLoopRunEntity(node_id=node_id, inputs=args["inputs"]),
         )
-        contexts.tenant_id.set(application_generate_entity.app_config.tenant_id)
         contexts.plugin_tool_providers.set({})
         contexts.plugin_tool_providers_lock.set(threading.Lock())
 
-        # Create workflow node execution repository
+        # Create repositories
+        #
+        # Create session factory
         session_factory = sessionmaker(bind=db.engine, expire_on_commit=False)
+        # Create workflow execution(aka workflow run) repository
+        workflow_execution_repository = SQLAlchemyWorkflowExecutionRepository(
+            session_factory=session_factory,
+            user=user,
+            app_id=application_generate_entity.app_config.app_id,
+            triggered_from=WorkflowRunTriggeredFrom.DEBUGGING,
+        )
+        # Create workflow node execution repository
         workflow_node_execution_repository = SQLAlchemyWorkflowNodeExecutionRepository(
             session_factory=session_factory,
-            tenant_id=application_generate_entity.app_config.tenant_id,
+            user=user,
             app_id=application_generate_entity.app_config.app_id,
+            triggered_from=WorkflowNodeExecutionTriggeredFrom.SINGLE_STEP,
         )
 
         return self._generate(
@@ -304,6 +342,7 @@ class AdvancedChatAppGenerator(MessageBasedAppGenerator):
             user=user,
             invoke_from=InvokeFrom.DEBUGGER,
             application_generate_entity=application_generate_entity,
+            workflow_execution_repository=workflow_execution_repository,
             workflow_node_execution_repository=workflow_node_execution_repository,
             conversation=None,
             stream=streaming,
@@ -316,6 +355,7 @@ class AdvancedChatAppGenerator(MessageBasedAppGenerator):
         user: Union[Account, EndUser],
         invoke_from: InvokeFrom,
         application_generate_entity: AdvancedChatAppGenerateEntity,
+        workflow_execution_repository: WorkflowExecutionRepository,
         workflow_node_execution_repository: WorkflowNodeExecutionRepository,
         conversation: Optional[Conversation] = None,
         stream: bool = True,
@@ -327,6 +367,7 @@ class AdvancedChatAppGenerator(MessageBasedAppGenerator):
         :param user: account or end user
         :param invoke_from: invoke from source
         :param application_generate_entity: application generate entity
+        :param workflow_execution_repository: repository for workflow execution
         :param workflow_node_execution_repository: repository for workflow node execution
         :param conversation: conversation
         :param stream: is stream
@@ -357,7 +398,9 @@ class AdvancedChatAppGenerator(MessageBasedAppGenerator):
             message_id=message.id,
         )
 
-        # new thread
+        # new thread with request context and contextvars
+        context = contextvars.copy_context()
+
         worker_thread = threading.Thread(
             target=self._generate_worker,
             kwargs={
@@ -366,7 +409,7 @@ class AdvancedChatAppGenerator(MessageBasedAppGenerator):
                 "queue_manager": queue_manager,
                 "conversation_id": conversation.id,
                 "message_id": message.id,
-                "context": contextvars.copy_context(),
+                "context": context,
             },
         )
 
@@ -380,6 +423,7 @@ class AdvancedChatAppGenerator(MessageBasedAppGenerator):
             conversation=conversation,
             message=message,
             user=user,
+            workflow_execution_repository=workflow_execution_repository,
             workflow_node_execution_repository=workflow_node_execution_repository,
             stream=stream,
         )
@@ -404,9 +448,8 @@ class AdvancedChatAppGenerator(MessageBasedAppGenerator):
         :param message_id: message ID
         :return:
         """
-        for var, val in context.items():
-            var.set(val)
-        with flask_app.app_context():
+
+        with preserve_flask_contexts(flask_app, context_vars=context):
             try:
                 # get conversation and message
                 conversation = self._get_conversation(conversation_id)
@@ -452,6 +495,7 @@ class AdvancedChatAppGenerator(MessageBasedAppGenerator):
         conversation: Conversation,
         message: Message,
         user: Union[Account, EndUser],
+        workflow_execution_repository: WorkflowExecutionRepository,
         workflow_node_execution_repository: WorkflowNodeExecutionRepository,
         stream: bool = False,
     ) -> Union[ChatbotAppBlockingResponse, Generator[ChatbotAppStreamResponse, None, None]]:
@@ -475,9 +519,10 @@ class AdvancedChatAppGenerator(MessageBasedAppGenerator):
             conversation=conversation,
             message=message,
             user=user,
-            stream=stream,
             dialogue_count=self._dialogue_count,
+            workflow_execution_repository=workflow_execution_repository,
             workflow_node_execution_repository=workflow_node_execution_repository,
+            stream=stream,
         )
 
         try:

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

@@ -140,7 +140,7 @@ class AdvancedChatAppRunner(WorkflowBasedAppRunner):
                 SystemVariableKey.DIALOGUE_COUNT: self._dialogue_count,
                 SystemVariableKey.APP_ID: app_config.app_id,
                 SystemVariableKey.WORKFLOW_ID: app_config.workflow_id,
-                SystemVariableKey.WORKFLOW_RUN_ID: self.application_generate_entity.workflow_run_id,
+                SystemVariableKey.WORKFLOW_EXECUTION_ID: self.application_generate_entity.workflow_run_id,
             }
 
             # init variable pool

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

@@ -1,4 +1,3 @@
-import json
 import logging
 import time
 from collections.abc import Generator, Mapping
@@ -10,6 +9,7 @@ from sqlalchemy.orm import Session
 
 from constants.tts_auto_play_timeout import TTS_AUTO_PLAY_TIMEOUT, TTS_AUTO_PLAY_YIELD_CPU_TIME
 from core.app.apps.base_app_queue_manager import AppQueueManager, PublishFrom
+from core.app.apps.common.workflow_response_converter import WorkflowResponseConverter
 from core.app.entities.app_invoke_entities import (
     AdvancedChatAppGenerateEntity,
     InvokeFrom,
@@ -56,25 +56,23 @@ from core.app.entities.task_entities import (
     WorkflowTaskState,
 )
 from core.app.task_pipeline.based_generate_task_pipeline import BasedGenerateTaskPipeline
-from core.app.task_pipeline.message_cycle_manage import MessageCycleManage
+from core.app.task_pipeline.message_cycle_manager import MessageCycleManager
 from core.base.tts import AppGeneratorTTSPublisher, AudioTrunk
 from core.model_runtime.entities.llm_entities import LLMUsage
-from core.model_runtime.utils.encoders import jsonable_encoder
 from core.ops.ops_trace_manager import TraceQueueManager
+from core.workflow.entities.workflow_execution import WorkflowExecutionStatus, WorkflowType
 from core.workflow.enums import SystemVariableKey
 from core.workflow.graph_engine.entities.graph_runtime_state import GraphRuntimeState
 from core.workflow.nodes import NodeType
-from core.workflow.repository.workflow_node_execution_repository import WorkflowNodeExecutionRepository
-from core.workflow.workflow_cycle_manager import WorkflowCycleManager
+from core.workflow.repositories.workflow_execution_repository import WorkflowExecutionRepository
+from core.workflow.repositories.workflow_node_execution_repository import WorkflowNodeExecutionRepository
+from core.workflow.workflow_cycle_manager import CycleManagerWorkflowInfo, WorkflowCycleManager
 from events.message_event import message_was_created
 from extensions.ext_database import db
 from models import Conversation, EndUser, Message, MessageFile
 from models.account import Account
-from models.enums import CreatedByRole
-from models.workflow import (
-    Workflow,
-    WorkflowRunStatus,
-)
+from models.enums import CreatorUserRole
+from models.workflow import Workflow
 
 logger = logging.getLogger(__name__)
 
@@ -94,6 +92,7 @@ class AdvancedChatAppGenerateTaskPipeline:
         user: Union[Account, EndUser],
         stream: bool,
         dialogue_count: int,
+        workflow_execution_repository: WorkflowExecutionRepository,
         workflow_node_execution_repository: WorkflowNodeExecutionRepository,
     ) -> None:
         self._base_task_pipeline = BasedGenerateTaskPipeline(
@@ -105,11 +104,11 @@ class AdvancedChatAppGenerateTaskPipeline:
         if isinstance(user, EndUser):
             self._user_id = user.id
             user_session_id = user.session_id
-            self._created_by_role = CreatedByRole.END_USER
+            self._created_by_role = CreatorUserRole.END_USER
         elif isinstance(user, Account):
             self._user_id = user.id
             user_session_id = user.id
-            self._created_by_role = CreatedByRole.ACCOUNT
+            self._created_by_role = CreatorUserRole.ACCOUNT
         else:
             raise NotImplementedError(f"User type not supported: {type(user)}")
 
@@ -123,13 +122,24 @@ class AdvancedChatAppGenerateTaskPipeline:
                 SystemVariableKey.DIALOGUE_COUNT: dialogue_count,
                 SystemVariableKey.APP_ID: application_generate_entity.app_config.app_id,
                 SystemVariableKey.WORKFLOW_ID: workflow.id,
-                SystemVariableKey.WORKFLOW_RUN_ID: application_generate_entity.workflow_run_id,
+                SystemVariableKey.WORKFLOW_EXECUTION_ID: application_generate_entity.workflow_run_id,
             },
+            workflow_info=CycleManagerWorkflowInfo(
+                workflow_id=workflow.id,
+                workflow_type=WorkflowType(workflow.type),
+                version=workflow.version,
+                graph_data=workflow.graph_dict,
+            ),
+            workflow_execution_repository=workflow_execution_repository,
             workflow_node_execution_repository=workflow_node_execution_repository,
         )
 
+        self._workflow_response_converter = WorkflowResponseConverter(
+            application_generate_entity=application_generate_entity,
+        )
+
         self._task_state = WorkflowTaskState()
-        self._message_cycle_manager = MessageCycleManage(
+        self._message_cycle_manager = MessageCycleManager(
             application_generate_entity=application_generate_entity, task_state=self._task_state
         )
 
@@ -150,7 +160,7 @@ class AdvancedChatAppGenerateTaskPipeline:
         :return:
         """
         # start generate conversation name thread
-        self._conversation_name_generate_thread = self._message_cycle_manager._generate_conversation_name(
+        self._conversation_name_generate_thread = self._message_cycle_manager.generate_conversation_name(
             conversation_id=self._conversation_id, query=self._application_generate_entity.query
         )
 
@@ -294,19 +304,15 @@ class AdvancedChatAppGenerateTaskPipeline:
 
                 with Session(db.engine, expire_on_commit=False) as session:
                     # init workflow run
-                    workflow_run = self._workflow_cycle_manager._handle_workflow_run_start(
-                        session=session,
-                        workflow_id=self._workflow_id,
-                        user_id=self._user_id,
-                        created_by_role=self._created_by_role,
-                    )
-                    self._workflow_run_id = workflow_run.id
+                    workflow_execution = self._workflow_cycle_manager.handle_workflow_run_start()
+                    self._workflow_run_id = workflow_execution.id_
                     message = self._get_message(session=session)
                     if not message:
                         raise ValueError(f"Message not found: {self._message_id}")
-                    message.workflow_run_id = workflow_run.id
-                    workflow_start_resp = self._workflow_cycle_manager._workflow_start_to_stream_response(
-                        session=session, task_id=self._application_generate_entity.task_id, workflow_run=workflow_run
+                    message.workflow_run_id = workflow_execution.id_
+                    workflow_start_resp = self._workflow_response_converter.workflow_start_to_stream_response(
+                        task_id=self._application_generate_entity.task_id,
+                        workflow_execution=workflow_execution,
                     )
                     session.commit()
 
@@ -319,13 +325,10 @@ class AdvancedChatAppGenerateTaskPipeline:
                     raise ValueError("workflow run not initialized.")
 
                 with Session(db.engine, expire_on_commit=False) as session:
-                    workflow_run = self._workflow_cycle_manager._get_workflow_run(
-                        session=session, workflow_run_id=self._workflow_run_id
+                    workflow_node_execution = self._workflow_cycle_manager.handle_workflow_node_execution_retried(
+                        workflow_execution_id=self._workflow_run_id, event=event
                     )
-                    workflow_node_execution = self._workflow_cycle_manager._handle_workflow_node_execution_retried(
-                        workflow_run=workflow_run, event=event
-                    )
-                    node_retry_resp = self._workflow_cycle_manager._workflow_node_retry_to_stream_response(
+                    node_retry_resp = self._workflow_response_converter.workflow_node_retry_to_stream_response(
                         event=event,
                         task_id=self._application_generate_entity.task_id,
                         workflow_node_execution=workflow_node_execution,
@@ -338,20 +341,15 @@ class AdvancedChatAppGenerateTaskPipeline:
                 if not self._workflow_run_id:
                     raise ValueError("workflow run not initialized.")
 
-                with Session(db.engine, expire_on_commit=False) as session:
-                    workflow_run = self._workflow_cycle_manager._get_workflow_run(
-                        session=session, workflow_run_id=self._workflow_run_id
-                    )
-                    workflow_node_execution = self._workflow_cycle_manager._handle_node_execution_start(
-                        workflow_run=workflow_run, event=event
-                    )
+                workflow_node_execution = self._workflow_cycle_manager.handle_node_execution_start(
+                    workflow_execution_id=self._workflow_run_id, event=event
+                )
 
-                    node_start_resp = self._workflow_cycle_manager._workflow_node_start_to_stream_response(
-                        event=event,
-                        task_id=self._application_generate_entity.task_id,
-                        workflow_node_execution=workflow_node_execution,
-                    )
-                    session.commit()
+                node_start_resp = self._workflow_response_converter.workflow_node_start_to_stream_response(
+                    event=event,
+                    task_id=self._application_generate_entity.task_id,
+                    workflow_node_execution=workflow_node_execution,
+                )
 
                 if node_start_resp:
                     yield node_start_resp
@@ -359,15 +357,15 @@ class AdvancedChatAppGenerateTaskPipeline:
                 # Record files if it's an answer node or end node
                 if event.node_type in [NodeType.ANSWER, NodeType.END]:
                     self._recorded_files.extend(
-                        self._workflow_cycle_manager._fetch_files_from_node_outputs(event.outputs or {})
+                        self._workflow_response_converter.fetch_files_from_node_outputs(event.outputs or {})
                     )
 
                 with Session(db.engine, expire_on_commit=False) as session:
-                    workflow_node_execution = self._workflow_cycle_manager._handle_workflow_node_execution_success(
+                    workflow_node_execution = self._workflow_cycle_manager.handle_workflow_node_execution_success(
                         event=event
                     )
 
-                    node_finish_resp = self._workflow_cycle_manager._workflow_node_finish_to_stream_response(
+                    node_finish_resp = self._workflow_response_converter.workflow_node_finish_to_stream_response(
                         event=event,
                         task_id=self._application_generate_entity.task_id,
                         workflow_node_execution=workflow_node_execution,
@@ -383,11 +381,11 @@ class AdvancedChatAppGenerateTaskPipeline:
                 | QueueNodeInLoopFailedEvent
                 | QueueNodeExceptionEvent,
             ):
-                workflow_node_execution = self._workflow_cycle_manager._handle_workflow_node_execution_failed(
+                workflow_node_execution = self._workflow_cycle_manager.handle_workflow_node_execution_failed(
                     event=event
                 )
 
-                node_finish_resp = self._workflow_cycle_manager._workflow_node_finish_to_stream_response(
+                node_finish_resp = self._workflow_response_converter.workflow_node_finish_to_stream_response(
                     event=event,
                     task_id=self._application_generate_entity.task_id,
                     workflow_node_execution=workflow_node_execution,
@@ -399,132 +397,92 @@ class AdvancedChatAppGenerateTaskPipeline:
                 if not self._workflow_run_id:
                     raise ValueError("workflow run not initialized.")
 
-                with Session(db.engine, expire_on_commit=False) as session:
-                    workflow_run = self._workflow_cycle_manager._get_workflow_run(
-                        session=session, workflow_run_id=self._workflow_run_id
-                    )
-                    parallel_start_resp = (
-                        self._workflow_cycle_manager._workflow_parallel_branch_start_to_stream_response(
-                            session=session,
-                            task_id=self._application_generate_entity.task_id,
-                            workflow_run=workflow_run,
-                            event=event,
-                        )
+                parallel_start_resp = (
+                    self._workflow_response_converter.workflow_parallel_branch_start_to_stream_response(
+                        task_id=self._application_generate_entity.task_id,
+                        workflow_execution_id=self._workflow_run_id,
+                        event=event,
                     )
+                )
 
                 yield parallel_start_resp
             elif isinstance(event, QueueParallelBranchRunSucceededEvent | QueueParallelBranchRunFailedEvent):
                 if not self._workflow_run_id:
                     raise ValueError("workflow run not initialized.")
 
-                with Session(db.engine, expire_on_commit=False) as session:
-                    workflow_run = self._workflow_cycle_manager._get_workflow_run(
-                        session=session, workflow_run_id=self._workflow_run_id
-                    )
-                    parallel_finish_resp = (
-                        self._workflow_cycle_manager._workflow_parallel_branch_finished_to_stream_response(
-                            session=session,
-                            task_id=self._application_generate_entity.task_id,
-                            workflow_run=workflow_run,
-                            event=event,
-                        )
+                parallel_finish_resp = (
+                    self._workflow_response_converter.workflow_parallel_branch_finished_to_stream_response(
+                        task_id=self._application_generate_entity.task_id,
+                        workflow_execution_id=self._workflow_run_id,
+                        event=event,
                     )
+                )
 
                 yield parallel_finish_resp
             elif isinstance(event, QueueIterationStartEvent):
                 if not self._workflow_run_id:
                     raise ValueError("workflow run not initialized.")
 
-                with Session(db.engine, expire_on_commit=False) as session:
-                    workflow_run = self._workflow_cycle_manager._get_workflow_run(
-                        session=session, workflow_run_id=self._workflow_run_id
-                    )
-                    iter_start_resp = self._workflow_cycle_manager._workflow_iteration_start_to_stream_response(
-                        session=session,
-                        task_id=self._application_generate_entity.task_id,
-                        workflow_run=workflow_run,
-                        event=event,
-                    )
+                iter_start_resp = self._workflow_response_converter.workflow_iteration_start_to_stream_response(
+                    task_id=self._application_generate_entity.task_id,
+                    workflow_execution_id=self._workflow_run_id,
+                    event=event,
+                )
 
                 yield iter_start_resp
             elif isinstance(event, QueueIterationNextEvent):
                 if not self._workflow_run_id:
                     raise ValueError("workflow run not initialized.")
 
-                with Session(db.engine, expire_on_commit=False) as session:
-                    workflow_run = self._workflow_cycle_manager._get_workflow_run(
-                        session=session, workflow_run_id=self._workflow_run_id
-                    )
-                    iter_next_resp = self._workflow_cycle_manager._workflow_iteration_next_to_stream_response(
-                        session=session,
-                        task_id=self._application_generate_entity.task_id,
-                        workflow_run=workflow_run,
-                        event=event,
-                    )
+                iter_next_resp = self._workflow_response_converter.workflow_iteration_next_to_stream_response(
+                    task_id=self._application_generate_entity.task_id,
+                    workflow_execution_id=self._workflow_run_id,
+                    event=event,
+                )
 
                 yield iter_next_resp
             elif isinstance(event, QueueIterationCompletedEvent):
                 if not self._workflow_run_id:
                     raise ValueError("workflow run not initialized.")
 
-                with Session(db.engine, expire_on_commit=False) as session:
-                    workflow_run = self._workflow_cycle_manager._get_workflow_run(
-                        session=session, workflow_run_id=self._workflow_run_id
-                    )
-                    iter_finish_resp = self._workflow_cycle_manager._workflow_iteration_completed_to_stream_response(
-                        session=session,
-                        task_id=self._application_generate_entity.task_id,
-                        workflow_run=workflow_run,
-                        event=event,
-                    )
+                iter_finish_resp = self._workflow_response_converter.workflow_iteration_completed_to_stream_response(
+                    task_id=self._application_generate_entity.task_id,
+                    workflow_execution_id=self._workflow_run_id,
+                    event=event,
+                )
 
                 yield iter_finish_resp
             elif isinstance(event, QueueLoopStartEvent):
                 if not self._workflow_run_id:
                     raise ValueError("workflow run not initialized.")
 
-                with Session(db.engine, expire_on_commit=False) as session:
-                    workflow_run = self._workflow_cycle_manager._get_workflow_run(
-                        session=session, workflow_run_id=self._workflow_run_id
-                    )
-                    loop_start_resp = self._workflow_cycle_manager._workflow_loop_start_to_stream_response(
-                        session=session,
-                        task_id=self._application_generate_entity.task_id,
-                        workflow_run=workflow_run,
-                        event=event,
-                    )
+                loop_start_resp = self._workflow_response_converter.workflow_loop_start_to_stream_response(
+                    task_id=self._application_generate_entity.task_id,
+                    workflow_execution_id=self._workflow_run_id,
+                    event=event,
+                )
 
                 yield loop_start_resp
             elif isinstance(event, QueueLoopNextEvent):
                 if not self._workflow_run_id:
                     raise ValueError("workflow run not initialized.")
 
-                with Session(db.engine, expire_on_commit=False) as session:
-                    workflow_run = self._workflow_cycle_manager._get_workflow_run(
-                        session=session, workflow_run_id=self._workflow_run_id
-                    )
-                    loop_next_resp = self._workflow_cycle_manager._workflow_loop_next_to_stream_response(
-                        session=session,
-                        task_id=self._application_generate_entity.task_id,
-                        workflow_run=workflow_run,
-                        event=event,
-                    )
+                loop_next_resp = self._workflow_response_converter.workflow_loop_next_to_stream_response(
+                    task_id=self._application_generate_entity.task_id,
+                    workflow_execution_id=self._workflow_run_id,
+                    event=event,
+                )
 
                 yield loop_next_resp
             elif isinstance(event, QueueLoopCompletedEvent):
                 if not self._workflow_run_id:
                     raise ValueError("workflow run not initialized.")
 
-                with Session(db.engine, expire_on_commit=False) as session:
-                    workflow_run = self._workflow_cycle_manager._get_workflow_run(
-                        session=session, workflow_run_id=self._workflow_run_id
-                    )
-                    loop_finish_resp = self._workflow_cycle_manager._workflow_loop_completed_to_stream_response(
-                        session=session,
-                        task_id=self._application_generate_entity.task_id,
-                        workflow_run=workflow_run,
-                        event=event,
-                    )
+                loop_finish_resp = self._workflow_response_converter.workflow_loop_completed_to_stream_response(
+                    task_id=self._application_generate_entity.task_id,
+                    workflow_execution_id=self._workflow_run_id,
+                    event=event,
+                )
 
                 yield loop_finish_resp
             elif isinstance(event, QueueWorkflowSucceededEvent):
@@ -535,10 +493,8 @@ class AdvancedChatAppGenerateTaskPipeline:
                     raise ValueError("workflow run not initialized.")
 
                 with Session(db.engine, expire_on_commit=False) as session:
-                    workflow_run = self._workflow_cycle_manager._handle_workflow_run_success(
-                        session=session,
+                    workflow_execution = self._workflow_cycle_manager.handle_workflow_run_success(
                         workflow_run_id=self._workflow_run_id,
-                        start_at=graph_runtime_state.start_at,
                         total_tokens=graph_runtime_state.total_tokens,
                         total_steps=graph_runtime_state.node_run_steps,
                         outputs=event.outputs,
@@ -546,10 +502,11 @@ class AdvancedChatAppGenerateTaskPipeline:
                         trace_manager=trace_manager,
                     )
 
-                    workflow_finish_resp = self._workflow_cycle_manager._workflow_finish_to_stream_response(
-                        session=session, task_id=self._application_generate_entity.task_id, workflow_run=workflow_run
+                    workflow_finish_resp = self._workflow_response_converter.workflow_finish_to_stream_response(
+                        session=session,
+                        task_id=self._application_generate_entity.task_id,
+                        workflow_execution=workflow_execution,
                     )
-                    session.commit()
 
                 yield workflow_finish_resp
                 self._base_task_pipeline._queue_manager.publish(
@@ -562,10 +519,8 @@ class AdvancedChatAppGenerateTaskPipeline:
                     raise ValueError("graph runtime state not initialized.")
 
                 with Session(db.engine, expire_on_commit=False) as session:
-                    workflow_run = self._workflow_cycle_manager._handle_workflow_run_partial_success(
-                        session=session,
+                    workflow_execution = self._workflow_cycle_manager.handle_workflow_run_partial_success(
                         workflow_run_id=self._workflow_run_id,
-                        start_at=graph_runtime_state.start_at,
                         total_tokens=graph_runtime_state.total_tokens,
                         total_steps=graph_runtime_state.node_run_steps,
                         outputs=event.outputs,
@@ -573,10 +528,11 @@ class AdvancedChatAppGenerateTaskPipeline:
                         conversation_id=None,
                         trace_manager=trace_manager,
                     )
-                    workflow_finish_resp = self._workflow_cycle_manager._workflow_finish_to_stream_response(
-                        session=session, task_id=self._application_generate_entity.task_id, workflow_run=workflow_run
+                    workflow_finish_resp = self._workflow_response_converter.workflow_finish_to_stream_response(
+                        session=session,
+                        task_id=self._application_generate_entity.task_id,
+                        workflow_execution=workflow_execution,
                     )
-                    session.commit()
 
                 yield workflow_finish_resp
                 self._base_task_pipeline._queue_manager.publish(
@@ -589,26 +545,25 @@ class AdvancedChatAppGenerateTaskPipeline:
                     raise ValueError("graph runtime state not initialized.")
 
                 with Session(db.engine, expire_on_commit=False) as session:
-                    workflow_run = self._workflow_cycle_manager._handle_workflow_run_failed(
-                        session=session,
+                    workflow_execution = self._workflow_cycle_manager.handle_workflow_run_failed(
                         workflow_run_id=self._workflow_run_id,
-                        start_at=graph_runtime_state.start_at,
                         total_tokens=graph_runtime_state.total_tokens,
                         total_steps=graph_runtime_state.node_run_steps,
-                        status=WorkflowRunStatus.FAILED,
-                        error=event.error,
+                        status=WorkflowExecutionStatus.FAILED,
+                        error_message=event.error,
                         conversation_id=self._conversation_id,
                         trace_manager=trace_manager,
                         exceptions_count=event.exceptions_count,
                     )
-                    workflow_finish_resp = self._workflow_cycle_manager._workflow_finish_to_stream_response(
-                        session=session, task_id=self._application_generate_entity.task_id, workflow_run=workflow_run
+                    workflow_finish_resp = self._workflow_response_converter.workflow_finish_to_stream_response(
+                        session=session,
+                        task_id=self._application_generate_entity.task_id,
+                        workflow_execution=workflow_execution,
                     )
-                    err_event = QueueErrorEvent(error=ValueError(f"Run failed: {workflow_run.error}"))
+                    err_event = QueueErrorEvent(error=ValueError(f"Run failed: {workflow_execution.error_message}"))
                     err = self._base_task_pipeline._handle_error(
                         event=err_event, session=session, message_id=self._message_id
                     )
-                    session.commit()
 
                 yield workflow_finish_resp
                 yield self._base_task_pipeline._error_to_stream_response(err)
@@ -616,21 +571,19 @@ class AdvancedChatAppGenerateTaskPipeline:
             elif isinstance(event, QueueStopEvent):
                 if self._workflow_run_id and graph_runtime_state:
                     with Session(db.engine, expire_on_commit=False) as session:
-                        workflow_run = self._workflow_cycle_manager._handle_workflow_run_failed(
-                            session=session,
+                        workflow_execution = self._workflow_cycle_manager.handle_workflow_run_failed(
                             workflow_run_id=self._workflow_run_id,
-                            start_at=graph_runtime_state.start_at,
                             total_tokens=graph_runtime_state.total_tokens,
                             total_steps=graph_runtime_state.node_run_steps,
-                            status=WorkflowRunStatus.STOPPED,
-                            error=event.get_stop_reason(),
+                            status=WorkflowExecutionStatus.STOPPED,
+                            error_message=event.get_stop_reason(),
                             conversation_id=self._conversation_id,
                             trace_manager=trace_manager,
                         )
-                        workflow_finish_resp = self._workflow_cycle_manager._workflow_finish_to_stream_response(
+                        workflow_finish_resp = self._workflow_response_converter.workflow_finish_to_stream_response(
                             session=session,
                             task_id=self._application_generate_entity.task_id,
-                            workflow_run=workflow_run,
+                            workflow_execution=workflow_execution,
                         )
                         # Save message
                         self._save_message(session=session, graph_runtime_state=graph_runtime_state)
@@ -650,22 +603,18 @@ class AdvancedChatAppGenerateTaskPipeline:
                 yield self._message_end_to_stream_response()
                 break
             elif isinstance(event, QueueRetrieverResourcesEvent):
-                self._message_cycle_manager._handle_retriever_resources(event)
+                self._message_cycle_manager.handle_retriever_resources(event)
 
                 with Session(db.engine, expire_on_commit=False) as session:
                     message = self._get_message(session=session)
-                    message.message_metadata = (
-                        json.dumps(jsonable_encoder(self._task_state.metadata)) if self._task_state.metadata else None
-                    )
+                    message.message_metadata = self._task_state.metadata.model_dump_json()
                     session.commit()
             elif isinstance(event, QueueAnnotationReplyEvent):
-                self._message_cycle_manager._handle_annotation_reply(event)
+                self._message_cycle_manager.handle_annotation_reply(event)
 
                 with Session(db.engine, expire_on_commit=False) as session:
                     message = self._get_message(session=session)
-                    message.message_metadata = (
-                        json.dumps(jsonable_encoder(self._task_state.metadata)) if self._task_state.metadata else None
-                    )
+                    message.message_metadata = self._task_state.metadata.model_dump_json()
                     session.commit()
             elif isinstance(event, QueueTextChunkEvent):
                 delta_text = event.text
@@ -682,12 +631,12 @@ class AdvancedChatAppGenerateTaskPipeline:
                     tts_publisher.publish(queue_message)
 
                 self._task_state.answer += delta_text
-                yield self._message_cycle_manager._message_to_stream_response(
+                yield self._message_cycle_manager.message_to_stream_response(
                     answer=delta_text, message_id=self._message_id, from_variable_selector=event.from_variable_selector
                 )
             elif isinstance(event, QueueMessageReplaceEvent):
                 # published by moderation
-                yield self._message_cycle_manager._message_replace_to_stream_response(
+                yield self._message_cycle_manager.message_replace_to_stream_response(
                     answer=event.text, reason=event.reason
                 )
             elif isinstance(event, QueueAdvancedChatMessageEndEvent):
@@ -699,7 +648,7 @@ class AdvancedChatAppGenerateTaskPipeline:
                 )
                 if output_moderation_answer:
                     self._task_state.answer = output_moderation_answer
-                    yield self._message_cycle_manager._message_replace_to_stream_response(
+                    yield self._message_cycle_manager.message_replace_to_stream_response(
                         answer=output_moderation_answer,
                         reason=QueueMessageReplaceEvent.MessageReplaceReason.OUTPUT_MODERATION,
                     )
@@ -711,7 +660,7 @@ class AdvancedChatAppGenerateTaskPipeline:
 
                 yield self._message_end_to_stream_response()
             elif isinstance(event, QueueAgentLogEvent):
-                yield self._workflow_cycle_manager._handle_agent_log(
+                yield self._workflow_response_converter.handle_agent_log(
                     task_id=self._application_generate_entity.task_id, event=event
                 )
             else:
@@ -728,9 +677,7 @@ class AdvancedChatAppGenerateTaskPipeline:
         message = self._get_message(session=session)
         message.answer = self._task_state.answer
         message.provider_response_latency = time.perf_counter() - self._base_task_pipeline._start_at
-        message.message_metadata = (
-            json.dumps(jsonable_encoder(self._task_state.metadata)) if self._task_state.metadata else None
-        )
+        message.message_metadata = self._task_state.metadata.model_dump_json()
         message_files = [
             MessageFile(
                 message_id=message.id,
@@ -739,9 +686,9 @@ class AdvancedChatAppGenerateTaskPipeline:
                 url=file["remote_url"],
                 belongs_to="assistant",
                 upload_file_id=file["related_id"],
-                created_by_role=CreatedByRole.ACCOUNT
+                created_by_role=CreatorUserRole.ACCOUNT
                 if message.invoke_from in {InvokeFrom.EXPLORE, InvokeFrom.DEBUGGER}
-                else CreatedByRole.END_USER,
+                else CreatorUserRole.END_USER,
                 created_by=message.from_account_id or message.from_end_user_id or "",
             )
             for file in self._recorded_files
@@ -758,9 +705,9 @@ class AdvancedChatAppGenerateTaskPipeline:
             message.answer_price_unit = usage.completion_price_unit
             message.total_price = usage.total_price
             message.currency = usage.currency
-            self._task_state.metadata["usage"] = jsonable_encoder(usage)
+            self._task_state.metadata.usage = usage
         else:
-            self._task_state.metadata["usage"] = jsonable_encoder(LLMUsage.empty_usage())
+            self._task_state.metadata.usage = LLMUsage.empty_usage()
         message_was_created.send(
             message,
             application_generate_entity=self._application_generate_entity,
@@ -771,18 +718,16 @@ class AdvancedChatAppGenerateTaskPipeline:
         Message end to stream response.
         :return:
         """
-        extras = {}
-        if self._task_state.metadata:
-            extras["metadata"] = self._task_state.metadata.copy()
+        extras = self._task_state.metadata.model_dump()
 
-            if "annotation_reply" in extras["metadata"]:
-                del extras["metadata"]["annotation_reply"]
+        if self._task_state.metadata.annotation_reply:
+            del extras["annotation_reply"]
 
         return MessageEndStreamResponse(
             task_id=self._application_generate_entity.task_id,
             id=self._message_id,
             files=self._recorded_files,
-            metadata=extras.get("metadata", {}),
+            metadata=extras,
         )
 
     def _handle_output_moderation_chunk(self, text: str) -> bool:

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

@@ -23,6 +23,7 @@ from core.model_runtime.errors.invoke import InvokeAuthorizationError
 from core.ops.ops_trace_manager import TraceQueueManager
 from extensions.ext_database import db
 from factories import file_factory
+from libs.flask_utils import preserve_flask_contexts
 from models import Account, App, EndUser
 from services.conversation_service import ConversationService
 from services.errors.message import MessageNotExistsError
@@ -179,12 +180,14 @@ class AgentChatAppGenerator(MessageBasedAppGenerator):
             message_id=message.id,
         )
 
-        # new thread
+        # new thread with request context and contextvars
+        context = contextvars.copy_context()
+
         worker_thread = threading.Thread(
             target=self._generate_worker,
             kwargs={
                 "flask_app": current_app._get_current_object(),  # type: ignore
-                "context": contextvars.copy_context(),
+                "context": context,
                 "application_generate_entity": application_generate_entity,
                 "queue_manager": queue_manager,
                 "conversation_id": conversation.id,
@@ -224,10 +227,8 @@ class AgentChatAppGenerator(MessageBasedAppGenerator):
         :param message_id: message ID
         :return:
         """
-        for var, val in context.items():
-            var.set(val)
 
-        with flask_app.app_context():
+        with preserve_flask_contexts(flask_app, context_vars=context):
             try:
                 # get conversation and message
                 conversation = self._get_conversation(conversation_id)

api/core/app/apps/base_app_runner.py

@@ -1,3 +1,4 @@
+import logging
 import time
 from collections.abc import Generator, Mapping, Sequence
 from typing import TYPE_CHECKING, Any, Optional, Union
@@ -33,6 +34,8 @@ from models.model import App, AppMode, Message, MessageAnnotation
 if TYPE_CHECKING:
     from core.file.models import File
 
+_logger = logging.getLogger(__name__)
+
 
 class AppRunner:
     def get_pre_calculate_rest_tokens(
@@ -298,7 +301,7 @@ class AppRunner:
         )
 
     def _handle_invoke_result_stream(
-        self, invoke_result: Generator, queue_manager: AppQueueManager, agent: bool
+        self, invoke_result: Generator[LLMResultChunk, None, None], queue_manager: AppQueueManager, agent: bool
     ) -> None:
         """
         Handle invoke result
@@ -317,18 +320,28 @@ class AppRunner:
             else:
                 queue_manager.publish(QueueAgentMessageEvent(chunk=result), PublishFrom.APPLICATION_MANAGER)
 
-            text += result.delta.message.content
+            message = result.delta.message
+            if isinstance(message.content, str):
+                text += message.content
+            elif isinstance(message.content, list):
+                for content in message.content:
+                    if not isinstance(content, str):
+                        # TODO(QuantumGhost): Add multimodal output support for easy ui.
+                        _logger.warning("received multimodal output, type=%s", type(content))
+                        text += content.data
+                    else:
+                        text += content  # failback to str
 
             if not model:
                 model = result.model
 
             if not prompt_messages:
-                prompt_messages = result.prompt_messages
+                prompt_messages = list(result.prompt_messages)
 
             if result.delta.usage:
                 usage = result.delta.usage
 
-        if not usage:
+        if usage is None:
             usage = LLMUsage.empty_usage()
 
         llm_result = LLMResult(

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

@@ -4,7 +4,7 @@ import uuid
 from collections.abc import Generator, Mapping
 from typing import Any, Literal, Union, overload
 
-from flask import Flask, current_app
+from flask import Flask, copy_current_request_context, current_app
 from pydantic import ValidationError
 
 from configs import dify_config
@@ -170,17 +170,18 @@ class ChatAppGenerator(MessageBasedAppGenerator):
             message_id=message.id,
         )
 
-        # new thread
-        worker_thread = threading.Thread(
-            target=self._generate_worker,
-            kwargs={
-                "flask_app": current_app._get_current_object(),  # type: ignore
-                "application_generate_entity": application_generate_entity,
-                "queue_manager": queue_manager,
-                "conversation_id": conversation.id,
-                "message_id": message.id,
-            },
-        )
+        # new thread with request context
+        @copy_current_request_context
+        def worker_with_context():
+            return self._generate_worker(
+                flask_app=current_app._get_current_object(),  # type: ignore
+                application_generate_entity=application_generate_entity,
+                queue_manager=queue_manager,
+                conversation_id=conversation.id,
+                message_id=message.id,
+            )
+
+        worker_thread = threading.Thread(target=worker_with_context)
 
         worker_thread.start()