refactor: update useNodes import to use reactflow across multiple components (#29195)

Signed-off-by: kenwoodjw <blackxin55+@gmail.com>

.cursorrules

@@ -0,0 +1,6 @@
+# Cursor Rules for Dify Project
+
+## Automated Test Generation
+
+- Use `web/testing/testing.md` as the canonical instruction set for generating frontend automated tests.
+- When proposing or saving tests, re-read that document and follow every requirement.

.devcontainer/Dockerfile

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

.devcontainer/devcontainer.json

@@ -11,7 +11,7 @@
 			"nodeGypDependencies": true,
 			"version": "lts"
 		},
-		"ghcr.io/devcontainers-contrib/features/npm-package:1": {
+		"ghcr.io/devcontainers-extra/features/npm-package:1": {
 			"package": "typescript",
 			"version": "latest"
 		},

.devcontainer/post_create_command.sh

@@ -1,15 +1,15 @@
 #!/bin/bash
+WORKSPACE_ROOT=$(pwd)
 
 corepack enable
 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,plugin,workflow_storage"' >> ~/.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
+echo "alias start-api=\"cd $WORKSPACE_ROOT/api && uv run python -m flask run --host 0.0.0.0 --port=5001 --debug\"" >> ~/.bashrc
+echo "alias start-worker=\"cd $WORKSPACE_ROOT/api && uv run python -m celery -A app.celery worker -P threads -c 1 --loglevel INFO -Q dataset,priority_dataset,priority_pipeline,pipeline,mail,ops_trace,app_deletion,plugin,workflow_storage,conversation,workflow,schedule_poller,schedule_executor,triggered_workflow_dispatcher,trigger_refresh_executor\"" >> ~/.bashrc
+echo "alias start-web=\"cd $WORKSPACE_ROOT/web && pnpm dev\"" >> ~/.bashrc
+echo "alias start-web-prod=\"cd $WORKSPACE_ROOT/web && pnpm build && pnpm start\"" >> ~/.bashrc
+echo "alias start-containers=\"cd $WORKSPACE_ROOT/docker && docker-compose -f docker-compose.middleware.yaml -p dify --env-file middleware.env up -d\"" >> ~/.bashrc
+echo "alias stop-containers=\"cd $WORKSPACE_ROOT/docker && docker-compose -f docker-compose.middleware.yaml -p dify --env-file middleware.env down\"" >> ~/.bashrc
 
 source /home/vscode/.bashrc
-

.editorconfig

@@ -29,7 +29,7 @@ trim_trailing_whitespace = false
 
 # Matches multiple files with brace expansion notation
 # Set default charset
-[*.{js,tsx}]
+[*.{js,jsx,ts,tsx,mjs}]
 indent_style = space
 indent_size = 2
 

.github/ISSUE_TEMPLATE/config.yml

@@ -1,5 +1,8 @@
 blank_issues_enabled: false
 contact_links:
+  - name: "\U0001F510 Security Vulnerabilities"
+    url: "https://github.com/langgenius/dify/security/advisories/new"
+    about: Report security vulnerabilities through GitHub Security Advisories to ensure responsible disclosure. 💡 Please do not report security vulnerabilities in public issues.
   - name: "\U0001F4A1 Model Providers & Plugins"
     url: "https://github.com/langgenius/dify-official-plugins/issues/new/choose"
     about: Report issues with official plugins or model providers, you will need to provide the plugin version and other relevant details.

.github/copilot-instructions.md

@@ -0,0 +1,12 @@
+# Copilot Instructions
+
+GitHub Copilot must follow the unified frontend testing requirements documented in `web/testing/testing.md`.
+
+Key reminders:
+
+- Generate tests using the mandated tech stack, naming, and code style (AAA pattern, `fireEvent`, descriptive test names, cleans up mocks).
+- Cover rendering, prop combinations, and edge cases by default; extend coverage for hooks, routing, async flows, and domain-specific components when applicable.
+- Target >95% line and branch coverage and 100% function/statement coverage.
+- Apply the project's mocking conventions for i18n, toast notifications, and Next.js utilities.
+
+Any suggestions from Copilot that conflict with `web/testing/testing.md` should be revised before acceptance.

.github/dependabot.yml

@@ -0,0 +1,12 @@
+version: 2
+updates:
+  - package-ecosystem: "npm"
+    directory: "/web"
+    schedule:
+      interval: "weekly"
+    open-pull-requests-limit: 2
+  - package-ecosystem: "uv"
+    directory: "/api"
+    schedule:
+      interval: "weekly"
+    open-pull-requests-limit: 2

.github/workflows/api-tests.yml

@@ -39,25 +39,11 @@ jobs:
       - name: Install dependencies
         run: uv sync --project api --dev
 
-      - name: Run Unit tests
-        run: |
-          uv run --project api bash dev/pytest/pytest_unit_tests.sh
-
       - name: Run pyrefly check
         run: |
           cd api
           uv add --dev pyrefly
           uv run pyrefly check || true
-      - name: Coverage Summary
-        run: |
-          set -x
-          # Extract coverage percentage and create a summary
-          TOTAL_COVERAGE=$(python -c 'import json; print(json.load(open("coverage.json"))["totals"]["percent_covered_display"])')
-
-          # Create a detailed coverage summary
-          echo "### Test Coverage Summary :test_tube:" >> $GITHUB_STEP_SUMMARY
-          echo "Total Coverage: ${TOTAL_COVERAGE}%" >> $GITHUB_STEP_SUMMARY
-          uv run --project api coverage report --format=markdown >> $GITHUB_STEP_SUMMARY
 
       - name: Run dify config tests
         run: uv run --project api dev/pytest/pytest_config_tests.py
@@ -76,7 +62,7 @@ jobs:
           compose-file: |
             docker/docker-compose.middleware.yaml
           services: |
-            db
+            db_postgres
             redis
             sandbox
             ssrf_proxy
@@ -93,3 +79,19 @@ jobs:
 
       - name: Run TestContainers
         run: uv run --project api bash dev/pytest/pytest_testcontainers.sh
+
+      - name: Run Unit tests
+        run: |
+          uv run --project api bash dev/pytest/pytest_unit_tests.sh
+
+      - name: Coverage Summary
+        run: |
+          set -x
+          # Extract coverage percentage and create a summary
+          TOTAL_COVERAGE=$(python -c 'import json; print(json.load(open("coverage.json"))["totals"]["percent_covered_display"])')
+
+          # Create a detailed coverage summary
+          echo "### Test Coverage Summary :test_tube:" >> $GITHUB_STEP_SUMMARY
+          echo "Total Coverage: ${TOTAL_COVERAGE}%" >> $GITHUB_STEP_SUMMARY
+          uv run --project api coverage report --format=markdown >> $GITHUB_STEP_SUMMARY
+

.github/workflows/autofix.yml

@@ -2,6 +2,8 @@ name: autofix.ci
 on:
   pull_request:
     branches: ["main"]
+  push:
+    branches: ["main"]
 permissions:
   contents: read
 
@@ -15,20 +17,49 @@ jobs:
       # Use uv to ensure we have the same ruff version in CI and locally.
       - uses: astral-sh/setup-uv@v6
         with:
-          python-version: "3.12"
+          python-version: "3.11"
       - run: |
           cd api
           uv sync --dev
+          # fmt first to avoid line too long
+          uv run ruff format ..
           # Fix lint errors
           uv run ruff check --fix .
           # Format code
-          uv run ruff format .
+          uv run ruff format ..
+
+      - name: count migration progress
+        run: |
+          cd api
+          ./cnt_base.sh
 
       - name: ast-grep
         run: |
           uvx --from ast-grep-cli sg --pattern 'db.session.query($WHATEVER).filter($HERE)' --rewrite 'db.session.query($WHATEVER).where($HERE)' -l py --update-all
           uvx --from ast-grep-cli sg --pattern 'session.query($WHATEVER).filter($HERE)' --rewrite 'session.query($WHATEVER).where($HERE)' -l py --update-all
-
+          uvx --from ast-grep-cli sg -p '$A = db.Column($$$B)' -r '$A = mapped_column($$$B)' -l py --update-all
+          uvx --from ast-grep-cli sg -p '$A : $T = db.Column($$$B)' -r '$A : $T = mapped_column($$$B)' -l py --update-all
+          # Convert Optional[T] to T | None (ignoring quoted types)
+          cat > /tmp/optional-rule.yml << 'EOF'
+          id: convert-optional-to-union
+          language: python
+          rule:
+            kind: generic_type
+            all:
+              - has:
+                  kind: identifier
+                  pattern: Optional
+              - has:
+                  kind: type_parameter
+                  has:
+                    kind: type
+                    pattern: $T
+          fix: $T | None
+          EOF
+          uvx --from ast-grep-cli sg scan --inline-rules "$(cat /tmp/optional-rule.yml)" --update-all
+          # Fix forward references that were incorrectly converted (Python doesn't support "Type" | None syntax)
+          find . -name "*.py" -type f -exec sed -i.bak -E 's/"([^"]+)" \| None/Optional["\1"]/g; s/'"'"'([^'"'"']+)'"'"' \| None/Optional['"'"'\1'"'"']/g' {} \;
+          find . -name "*.py.bak" -type f -delete
 
       - name: mdformat
         run: |

.github/workflows/build-push.yml

@@ -4,10 +4,10 @@ on:
   push:
     branches:
       - "main"
-      - "deploy/dev"
-      - "deploy/enterprise"
+      - "deploy/**"
       - "build/**"
       - "release/e-*"
+      - "hotfix/**"
     tags:
       - "*"
 

.github/workflows/db-migration-test.yml

@@ -8,7 +8,7 @@ concurrency:
   cancel-in-progress: true
 
 jobs:
-  db-migration-test:
+  db-migration-test-postgres:
     runs-on: ubuntu-latest
 
     steps:
@@ -45,7 +45,7 @@ jobs:
           compose-file: |
             docker/docker-compose.middleware.yaml
           services: |
-            db
+            db_postgres
             redis
 
       - name: Prepare configs
@@ -57,3 +57,60 @@ jobs:
         env:
           DEBUG: true
         run: uv run --directory api flask upgrade-db
+
+  db-migration-test-mysql:
+    runs-on: ubuntu-latest
+
+    steps:
+      - name: Checkout code
+        uses: actions/checkout@v4
+        with:
+          fetch-depth: 0
+          persist-credentials: false
+
+      - name: Setup UV and Python
+        uses: astral-sh/setup-uv@v6
+        with:
+          enable-cache: true
+          python-version: "3.12"
+          cache-dependency-glob: api/uv.lock
+
+      - name: Install dependencies
+        run: uv sync --project api
+      - name: Ensure Offline migration are supported
+        run: |
+          # upgrade
+          uv run --directory api flask db upgrade 'base:head' --sql
+          # downgrade
+          uv run --directory api flask db downgrade 'head:base' --sql
+
+      - name: Prepare middleware env for MySQL
+        run: |
+          cd docker
+          cp middleware.env.example middleware.env
+          sed -i 's/DB_TYPE=postgresql/DB_TYPE=mysql/' middleware.env
+          sed -i 's/DB_HOST=db_postgres/DB_HOST=db_mysql/' middleware.env
+          sed -i 's/DB_PORT=5432/DB_PORT=3306/' middleware.env
+          sed -i 's/DB_USERNAME=postgres/DB_USERNAME=mysql/' middleware.env
+
+      - name: Set up Middlewares
+        uses: hoverkraft-tech/compose-action@v2.0.2
+        with:
+          compose-file: |
+            docker/docker-compose.middleware.yaml
+          services: |
+            db_mysql
+            redis
+
+      - name: Prepare configs for MySQL
+        run: |
+          cd api
+          cp .env.example .env
+          sed -i 's/DB_TYPE=postgresql/DB_TYPE=mysql/' .env
+          sed -i 's/DB_PORT=5432/DB_PORT=3306/' .env
+          sed -i 's/DB_USERNAME=postgres/DB_USERNAME=root/' .env
+
+      - name: Run DB Migration
+        env:
+          DEBUG: true
+        run: uv run --directory api flask upgrade-db

.github/workflows/deploy-dev.yml

@@ -12,7 +12,8 @@ jobs:
   deploy:
     runs-on: ubuntu-latest
     if: |
-      github.event.workflow_run.conclusion == 'success'
+      github.event.workflow_run.conclusion == 'success' &&
+      github.event.workflow_run.head_branch == 'deploy/dev'
     steps:
       - name: Deploy to server
         uses: appleboy/ssh-action@v0.1.8

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

@@ -1,4 +1,4 @@
-name: Deploy RAG Dev
+name: Deploy Trigger Dev
 
 permissions:
   contents: read
@@ -7,7 +7,7 @@ on:
   workflow_run:
     workflows: ["Build and Push API & Web"]
     branches:
-      - "deploy/rag-dev"
+      - "deploy/trigger-dev"
     types:
       - completed
 
@@ -16,12 +16,12 @@ jobs:
     runs-on: ubuntu-latest
     if: |
       github.event.workflow_run.conclusion == 'success' &&
-      github.event.workflow_run.head_branch == 'deploy/rag-dev'
+      github.event.workflow_run.head_branch == 'deploy/trigger-dev'
     steps:
       - name: Deploy to server
         uses: appleboy/ssh-action@v0.1.8
         with:
-          host: ${{ secrets.RAG_SSH_HOST }}
+          host: ${{ secrets.TRIGGER_SSH_HOST }}
           username: ${{ secrets.SSH_USER }}
           key: ${{ secrets.SSH_PRIVATE_KEY }}
           script: |

.github/workflows/expose_service_ports.sh

@@ -1,6 +1,7 @@
 #!/bin/bash
 
 yq eval '.services.weaviate.ports += ["8080:8080"]' -i docker/docker-compose.yaml
+yq eval '.services.weaviate.ports += ["50051:50051"]' -i docker/docker-compose.yaml
 yq eval '.services.qdrant.ports += ["6333:6333"]' -i docker/docker-compose.yaml
 yq eval '.services.chroma.ports += ["8000:8000"]' -i docker/docker-compose.yaml
 yq eval '.services["milvus-standalone"].ports += ["19530:19530"]' -i docker/docker-compose.yaml
@@ -13,4 +14,4 @@ yq eval '.services.tidb.ports += ["4000:4000"]' -i docker/tidb/docker-compose.ya
 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"
+echo "Ports exposed for sandbox, weaviate (HTTP 8080, gRPC 50051), tidb, qdrant, chroma, milvus, pgvector, pgvecto-rs, elasticsearch, couchbase, opengauss"

.github/workflows/style.yml

@@ -12,7 +12,6 @@ permissions:
   statuses: write
   contents: read
 
-
 jobs:
   python-style:
     name: Python Style
@@ -44,6 +43,10 @@ jobs:
         if: steps.changed-files.outputs.any_changed == 'true'
         run: uv sync --project api --dev
 
+      - name: Run Import Linter
+        if: steps.changed-files.outputs.any_changed == 'true'
+        run: uv run --directory api --dev lint-imports
+
       - name: Run Basedpyright Checks
         if: steps.changed-files.outputs.any_changed == 'true'
         run: dev/basedpyright-check
@@ -99,7 +102,11 @@ jobs:
         working-directory: ./web
         run: |
           pnpm run lint
-          pnpm run eslint
+
+      - name: Web type check
+        if: steps.changed-files.outputs.any_changed == 'true'
+        working-directory: ./web
+        run: pnpm run type-check
 
   docker-compose-template:
     name: Docker Compose Template

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

@@ -20,22 +20,22 @@ jobs:
     steps:
       - uses: actions/checkout@v4
         with:
-          fetch-depth: 2
+          fetch-depth: 0
           token: ${{ secrets.GITHUB_TOKEN }}
 
       - name: Check for file changes in i18n/en-US
         id: check_files
         run: |
-          recent_commit_sha=$(git rev-parse HEAD)
-          second_recent_commit_sha=$(git rev-parse HEAD~1)
-          changed_files=$(git diff --name-only $recent_commit_sha $second_recent_commit_sha -- 'i18n/en-US/*.ts')
+          git fetch origin "${{ github.event.before }}" || true
+          git fetch origin "${{ github.sha }}" || true
+          changed_files=$(git diff --name-only "${{ github.event.before }}" "${{ github.sha }}" -- 'i18n/en-US/*.ts')
           echo "Changed files: $changed_files"
           if [ -n "$changed_files" ]; then
             echo "FILES_CHANGED=true" >> $GITHUB_ENV
             file_args=""
             for file in $changed_files; do
               filename=$(basename "$file" .ts)
-              file_args="$file_args --file=$filename"
+              file_args="$file_args --file $filename"
             done
             echo "FILE_ARGS=$file_args" >> $GITHUB_ENV
             echo "File arguments: $file_args"

.github/workflows/vdb-tests.yml

@@ -51,13 +51,13 @@ jobs:
       - name: Expose Service Ports
         run: sh .github/workflows/expose_service_ports.sh
 
-      - name: Set up Vector Store (TiDB)
-        uses: hoverkraft-tech/compose-action@v2.0.2
-        with:
-          compose-file: docker/tidb/docker-compose.yaml
-          services: |
-            tidb
-            tiflash
+#      - name: Set up Vector Store (TiDB)
+#        uses: hoverkraft-tech/compose-action@v2.0.2
+#        with:
+#          compose-file: docker/tidb/docker-compose.yaml
+#          services: |
+#            tidb
+#            tiflash
 
       - name: Set up Vector Stores (Weaviate, Qdrant, PGVector, Milvus, PgVecto-RS, Chroma, MyScale, ElasticSearch, Couchbase, OceanBase)
         uses: hoverkraft-tech/compose-action@v2.0.2
@@ -83,8 +83,8 @@ jobs:
           ls -lah .
           cp api/tests/integration_tests/.env.example api/tests/integration_tests/.env
 
-      - name: Check VDB Ready (TiDB)
-        run: uv run --project api python api/tests/integration_tests/vdb/tidb_vector/check_tiflash_ready.py
+#      - 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
         run: uv run --project api bash dev/pytest/pytest_vdb.sh

.gitignore

@@ -6,6 +6,9 @@ __pycache__/
 # C extensions
 *.so
 
+# *db files
+*.db
+
 # Distribution / packaging
 .Python
 build/
@@ -97,6 +100,7 @@ __pypackages__/
 
 # Celery stuff
 celerybeat-schedule
+celerybeat-schedule.db
 celerybeat.pid
 
 # SageMath parsed files
@@ -182,6 +186,8 @@ docker/volumes/couchbase/*
 docker/volumes/oceanbase/*
 docker/volumes/plugin_daemon/*
 docker/volumes/matrixone/*
+docker/volumes/mysql/*
+docker/volumes/seekdb/*
 !docker/volumes/oceanbase/init.d
 
 docker/nginx/conf.d/default.conf
@@ -230,4 +236,11 @@ api/.env.backup
 
 # Benchmark
 scripts/stress-test/setup/config/
-scripts/stress-test/reports/
+scripts/stress-test/reports/
+
+# mcp
+.playwright-mcp/
+.serena/
+
+# settings
+*.local.json

.vscode/launch.json.template

@@ -8,8 +8,7 @@
             "module": "flask",
             "env": {
                 "FLASK_APP": "app.py",
-                "FLASK_ENV": "development",
-                "GEVENT_SUPPORT": "True"
+                "FLASK_ENV": "development"
             },
             "args": [
                 "run",
@@ -28,9 +27,7 @@
             "type": "debugpy",
             "request": "launch",
             "module": "celery",
-            "env": {
-                "GEVENT_SUPPORT": "True"
-            },
+            "env": {},
             "args": [
                 "-A",
                 "app.celery",
@@ -40,7 +37,7 @@
                 "-c",
                 "1",
                 "-Q",
-                "dataset,generation,mail,ops_trace",
+                "dataset,priority_dataset,priority_pipeline,pipeline,mail,ops_trace,app_deletion,plugin,workflow_storage,conversation,workflow,schedule_poller,schedule_executor,triggered_workflow_dispatcher,trigger_refresh_executor",
                 "--loglevel",
                 "INFO"
             ],

.windsurf/rules/testing.md

@@ -0,0 +1,5 @@
+# Windsurf Testing Rules
+
+- Use `web/testing/testing.md` as the single source of truth for frontend automated testing.
+- Honor every requirement in that document when generating or accepting tests.
+- When proposing or saving tests, re-read that document and follow every requirement.

AGENTS.md

@@ -1 +0,0 @@
-CLAUDE.md

AGENTS.md

@@ -0,0 +1,54 @@
+# AGENTS.md
+
+## Project Overview
+
+Dify is an open-source platform for developing LLM applications with an intuitive interface combining agentic AI workflows, RAG pipelines, agent capabilities, and model management.
+
+The codebase is split into:
+
+- **Backend API** (`/api`): Python Flask application organized with Domain-Driven Design
+- **Frontend Web** (`/web`): Next.js 15 application using TypeScript and React 19
+- **Docker deployment** (`/docker`): Containerized deployment configurations
+
+## Backend Workflow
+
+- Run backend CLI commands through `uv run --project api <command>`.
+
+- Before submission, all backend modifications must pass local checks: `make lint`, `make type-check`, and `uv run --project api --dev dev/pytest/pytest_unit_tests.sh`.
+
+- Use Makefile targets for linting and formatting; `make lint` and `make type-check` cover the required checks.
+
+- Integration tests are CI-only and are not expected to run in the local environment.
+
+## Frontend Workflow
+
+```bash
+cd web
+pnpm lint
+pnpm lint:fix
+pnpm test
+```
+
+## Testing & Quality Practices
+
+- Follow TDD: red → green → refactor.
+- Use `pytest` for backend tests with Arrange-Act-Assert structure.
+- Enforce strong typing; avoid `Any` and prefer explicit type annotations.
+- Write self-documenting code; only add comments that explain intent.
+
+## Language Style
+
+- **Python**: Keep type hints on functions and attributes, and implement relevant special methods (e.g., `__repr__`, `__str__`).
+- **TypeScript**: Use the strict config, lean on ESLint + Prettier workflows, and avoid `any` types.
+
+## General Practices
+
+- Prefer editing existing files; add new documentation only when requested.
+- Inject dependencies through constructors and preserve clean architecture boundaries.
+- Handle errors with domain-specific exceptions at the correct layer.
+
+## Project Conventions
+
+- Backend architecture adheres to DDD and Clean Architecture principles.
+- Async work runs through Celery with Redis as the broker.
+- Frontend user-facing strings must use `web/i18n/en-US/`; avoid hardcoded text.

CLAUDE.md

@@ -1,89 +0,0 @@
-# CLAUDE.md
-
-This file provides guidance to Claude Code (claude.ai/code) when working with code in this repository.
-
-## Project Overview
-
-Dify is an open-source platform for developing LLM applications with an intuitive interface combining agentic AI workflows, RAG pipelines, agent capabilities, and model management.
-
-The codebase consists of:
-
-- **Backend API** (`/api`): Python Flask application with Domain-Driven Design architecture
-- **Frontend Web** (`/web`): Next.js 15 application with TypeScript and React 19
-- **Docker deployment** (`/docker`): Containerized deployment configurations
-
-## Development Commands
-
-### Backend (API)
-
-All Python commands must be prefixed with `uv run --project api`:
-
-```bash
-# Start development servers
-./dev/start-api                   # Start API server
-./dev/start-worker                # Start Celery worker
-
-# Run tests
-uv run --project api pytest      # Run all tests
-uv run --project api pytest tests/unit_tests/     # Unit tests only
-uv run --project api pytest tests/integration_tests/  # Integration tests
-
-# Code quality
-./dev/reformat                    # Run all formatters and linters
-uv run --project api ruff check --fix ./    # Fix linting issues
-uv run --project api ruff format ./         # Format code
-uv run --directory api basedpyright         # Type checking
-```
-
-### Frontend (Web)
-
-```bash
-cd web
-pnpm lint                         # Run ESLint
-pnpm eslint-fix                   # Fix ESLint issues
-pnpm test                         # Run Jest tests
-```
-
-## Testing Guidelines
-
-### Backend Testing
-
-- Use `pytest` for all backend tests
-- Write tests first (TDD approach)
-- Test structure: Arrange-Act-Assert
-
-## Code Style Requirements
-
-### Python
-
-- Use type hints for all functions and class attributes
-- No `Any` types unless absolutely necessary
-- Implement special methods (`__repr__`, `__str__`) appropriately
-
-### TypeScript/JavaScript
-
-- Strict TypeScript configuration
-- ESLint with Prettier integration
-- Avoid `any` type
-
-## Important Notes
-
-- **Environment Variables**: Always use UV for Python commands: `uv run --project api <command>`
-- **Comments**: Only write meaningful comments that explain "why", not "what"
-- **File Creation**: Always prefer editing existing files over creating new ones
-- **Documentation**: Don't create documentation files unless explicitly requested
-- **Code Quality**: Always run `./dev/reformat` before committing backend changes
-
-## Common Development Tasks
-
-### Adding a New API Endpoint
-
-1. Create controller in `/api/controllers/`
-1. Add service logic in `/api/services/`
-1. Update routes in controller's `__init__.py`
-1. Write tests in `/api/tests/`
-
-## Project-Specific Conventions
-
-- All async tasks use Celery with Redis as broker
-- **Internationalization**: Frontend supports multiple languages with English (`web/i18n/en-US/`) as the source. All user-facing text must use i18n keys, no hardcoded strings. Edit corresponding module files in `en-US/` directory for translations.

CLAUDE.md

@@ -0,0 +1 @@
+AGENTS.md

CONTRIBUTING.md

@@ -77,6 +77,8 @@ How we prioritize:
 
 For setting up the frontend service, please refer to our comprehensive [guide](https://github.com/langgenius/dify/blob/main/web/README.md) in the `web/README.md` file. This document provides detailed instructions to help you set up the frontend environment properly.
 
+**Testing**: All React components must have comprehensive test coverage. See [web/testing/testing.md](https://github.com/langgenius/dify/blob/main/web/testing/testing.md) for the canonical frontend testing guidelines and follow every requirement described there.
+
 #### Backend
 
 For setting up the backend service, kindly refer to our detailed [instructions](https://github.com/langgenius/dify/blob/main/api/README.md) in the `api/README.md` file. This document contains step-by-step guidance to help you get the backend up and running smoothly.

Makefile

@@ -26,7 +26,6 @@ prepare-web:
 	@echo "🌐 Setting up web environment..."
 	@cp -n web/.env.example web/.env 2>/dev/null || echo "Web .env already exists"
 	@cd web && pnpm install
-	@cd web && pnpm build
 	@echo "✅ Web environment prepared (not started)"
 
 # Step 3: Prepare API environment
@@ -61,8 +60,9 @@ check:
 	@echo "✅ Code check complete"
 
 lint:
-	@echo "🔧 Running ruff format and check with fixes..."
-	@uv run --directory api --dev sh -c 'ruff format ./api && ruff check --fix ./api'
+	@echo "🔧 Running ruff format, check with fixes, and import linter..."
+	@uv run --project api --dev sh -c 'ruff format ./api && ruff check --fix ./api'
+	@uv run --directory api --dev lint-imports
 	@echo "✅ Linting complete"
 
 type-check:
@@ -70,6 +70,11 @@ type-check:
 	@uv run --directory api --dev basedpyright
 	@echo "✅ Type check complete"
 
+test:
+	@echo "🧪 Running backend unit tests..."
+	@uv run --project api --dev dev/pytest/pytest_unit_tests.sh
+	@echo "✅ Tests complete"
+
 # Build Docker images
 build-web:
 	@echo "Building web Docker image: $(WEB_IMAGE):$(VERSION)..."
@@ -119,6 +124,7 @@ help:
 	@echo "  make check          - Check code with ruff"
 	@echo "  make lint           - Format and fix code with ruff"
 	@echo "  make type-check     - Run type checking with basedpyright"
+	@echo "  make test           - Run backend unit tests"
 	@echo ""
 	@echo "Docker Build Targets:"
 	@echo "  make build-web      - Build web Docker image"
@@ -128,4 +134,4 @@ help:
 	@echo "  make build-push-all - Build and push all Docker images"
 
 # Phony targets
-.PHONY: build-web build-api push-web push-api build-all push-all build-push-all dev-setup prepare-docker prepare-web prepare-api dev-clean help format check lint type-check
+.PHONY: build-web build-api push-web push-api build-all push-all build-push-all dev-setup prepare-docker prepare-web prepare-api dev-clean help format check lint type-check test

README.md

@@ -40,18 +40,18 @@
 
 <p align="center">
   <a href="./README.md"><img alt="README in English" src="https://img.shields.io/badge/English-d9d9d9"></a>
-  <a href="./README_TW.md"><img alt="繁體中文文件" src="https://img.shields.io/badge/繁體中文-d9d9d9"></a>
-  <a href="./README_CN.md"><img alt="简体中文版自述文件" src="https://img.shields.io/badge/简体中文-d9d9d9"></a>
-  <a href="./README_JA.md"><img alt="日本語のREADME" src="https://img.shields.io/badge/日本語-d9d9d9"></a>
-  <a href="./README_ES.md"><img alt="README en Español" src="https://img.shields.io/badge/Español-d9d9d9"></a>
-  <a href="./README_FR.md"><img alt="README en Français" src="https://img.shields.io/badge/Français-d9d9d9"></a>
-  <a href="./README_KL.md"><img alt="README tlhIngan Hol" src="https://img.shields.io/badge/Klingon-d9d9d9"></a>
-  <a href="./README_KR.md"><img alt="README in Korean" src="https://img.shields.io/badge/한국어-d9d9d9"></a>
-  <a href="./README_AR.md"><img alt="README بالعربية" src="https://img.shields.io/badge/العربية-d9d9d9"></a>
-  <a href="./README_TR.md"><img alt="Türkçe README" src="https://img.shields.io/badge/Türkçe-d9d9d9"></a>
-  <a href="./README_VI.md"><img alt="README Tiếng Việt" src="https://img.shields.io/badge/Ti%E1%BA%BFng%20Vi%E1%BB%87t-d9d9d9"></a>
-  <a href="./README_DE.md"><img alt="README in Deutsch" src="https://img.shields.io/badge/German-d9d9d9"></a>
-  <a href="./README_BN.md"><img alt="README in বাংলা" src="https://img.shields.io/badge/বাংলা-d9d9d9"></a>
+  <a href="./docs/zh-TW/README.md"><img alt="繁體中文文件" src="https://img.shields.io/badge/繁體中文-d9d9d9"></a>
+  <a href="./docs/zh-CN/README.md"><img alt="简体中文文件" src="https://img.shields.io/badge/简体中文-d9d9d9"></a>
+  <a href="./docs/ja-JP/README.md"><img alt="日本語のREADME" src="https://img.shields.io/badge/日本語-d9d9d9"></a>
+  <a href="./docs/es-ES/README.md"><img alt="README en Español" src="https://img.shields.io/badge/Español-d9d9d9"></a>
+  <a href="./docs/fr-FR/README.md"><img alt="README en Français" src="https://img.shields.io/badge/Français-d9d9d9"></a>
+  <a href="./docs/tlh/README.md"><img alt="README tlhIngan Hol" src="https://img.shields.io/badge/Klingon-d9d9d9"></a>
+  <a href="./docs/ko-KR/README.md"><img alt="README in Korean" src="https://img.shields.io/badge/한국어-d9d9d9"></a>
+  <a href="./docs/ar-SA/README.md"><img alt="README بالعربية" src="https://img.shields.io/badge/العربية-d9d9d9"></a>
+  <a href="./docs/tr-TR/README.md"><img alt="Türkçe README" src="https://img.shields.io/badge/Türkçe-d9d9d9"></a>
+  <a href="./docs/vi-VN/README.md"><img alt="README Tiếng Việt" src="https://img.shields.io/badge/Ti%E1%BA%BFng%20Vi%E1%BB%87t-d9d9d9"></a>
+  <a href="./docs/de-DE/README.md"><img alt="README in Deutsch" src="https://img.shields.io/badge/German-d9d9d9"></a>
+  <a href="./docs/bn-BD/README.md"><img alt="README in বাংলা" src="https://img.shields.io/badge/বাংলা-d9d9d9"></a>
 </p>
 
 Dify is an open-source platform for developing LLM applications. Its intuitive interface combines agentic AI workflows, RAG pipelines, agent capabilities, model management, observability features, and more—allowing you to quickly move from prototype to production.
@@ -63,7 +63,7 @@ Dify is an open-source platform for developing LLM applications. Its intuitive i
 > - CPU >= 2 Core
 > - RAM >= 4 GiB
 
-</br>
+<br/>
 
 The easiest way to start the Dify server is through [Docker Compose](docker/docker-compose.yaml). Before running Dify with the following commands, make sure that [Docker](https://docs.docker.com/get-docker/) and [Docker Compose](https://docs.docker.com/compose/install/) are installed on your machine:
 
@@ -109,15 +109,15 @@ All of Dify's offerings come with corresponding APIs, so you could effortlessly
 
 ## Using Dify
 
-- **Cloud </br>**
+- **Cloud <br/>**
   We host a [Dify Cloud](https://dify.ai) service for anyone to try with zero setup. It provides all the capabilities of the self-deployed version, and includes 200 free GPT-4 calls in the sandbox plan.
 
-- **Self-hosting Dify Community Edition</br>**
+- **Self-hosting Dify Community Edition<br/>**
   Quickly get Dify running in your environment with this [starter guide](#quick-start).
   Use our [documentation](https://docs.dify.ai) for further references and more in-depth instructions.
 
-- **Dify for enterprise / organizations</br>**
-  We provide additional enterprise-centric features. [Log your questions for us through this chatbot](https://udify.app/chat/22L1zSxg6yW1cWQg) or [send us an email](mailto:business@dify.ai?subject=%5BGitHub%5DBusiness%20License%20Inquiry) to discuss enterprise needs. </br>
+- **Dify for enterprise / organizations<br/>**
+  We provide additional enterprise-centric features. [Send us an email](mailto:business@dify.ai?subject=%5BGitHub%5DBusiness%20License%20Inquiry) to discuss your enterprise needs. <br/>
 
   > For startups and small businesses using AWS, check out [Dify Premium on AWS Marketplace](https://aws.amazon.com/marketplace/pp/prodview-t22mebxzwjhu6) and deploy it to your own AWS VPC with one click. It's an affordable AMI offering with the option to create apps with custom logo and branding.
 
@@ -129,8 +129,18 @@ Star Dify on GitHub and be instantly notified of new releases.
 
 ## Advanced Setup
 
+### Custom configurations
+
 If you need to customize the configuration, please refer to the comments in our [.env.example](docker/.env.example) file and update the corresponding values in your `.env` file. Additionally, you might need to make adjustments to the `docker-compose.yaml` file itself, such as changing image versions, port mappings, or volume mounts, based on your specific deployment environment and requirements. After making any changes, please re-run `docker-compose up -d`. You can find the full list of available environment variables [here](https://docs.dify.ai/getting-started/install-self-hosted/environments).
 
+### Metrics Monitoring with Grafana
+
+Import the dashboard to Grafana, using Dify's PostgreSQL database as data source, to monitor metrics in granularity of apps, tenants, messages, and more.
+
+- [Grafana Dashboard by @bowenliang123](https://github.com/bowenliang123/dify-grafana-dashboard)
+
+### Deployment with Kubernetes
+
 If you'd like to configure a highly-available setup, there are community-contributed [Helm Charts](https://helm.sh/) and YAML files which allow Dify to be deployed on Kubernetes.
 
 - [Helm Chart by @LeoQuote](https://github.com/douban/charts/tree/master/charts/dify)

api/.env.example

@@ -27,6 +27,9 @@ FILES_URL=http://localhost:5001
 # Example: INTERNAL_FILES_URL=http://api:5001
 INTERNAL_FILES_URL=http://127.0.0.1:5001
 
+# TRIGGER URL
+TRIGGER_URL=http://localhost:5001
+
 # The time in seconds after the signature is rejected
 FILES_ACCESS_TIMEOUT=300
 
@@ -69,13 +72,17 @@ REDIS_CLUSTERS_PASSWORD=
 # celery configuration
 CELERY_BROKER_URL=redis://:difyai123456@localhost:${REDIS_PORT}/1
 CELERY_BACKEND=redis
-# PostgreSQL database configuration
+
+# Database configuration
+DB_TYPE=postgresql
 DB_USERNAME=postgres
 DB_PASSWORD=difyai123456
 DB_HOST=localhost
 DB_PORT=5432
 DB_DATABASE=dify
+
 SQLALCHEMY_POOL_PRE_PING=true
+SQLALCHEMY_POOL_TIMEOUT=30
 
 # Storage configuration
 # use for store upload files, private keys...
@@ -155,9 +162,11 @@ SUPABASE_URL=your-server-url
 # CORS configuration
 WEB_API_CORS_ALLOW_ORIGINS=http://localhost:3000,*
 CONSOLE_CORS_ALLOW_ORIGINS=http://localhost:3000,*
+# When the frontend and backend run on different subdomains, set COOKIE_DOMAIN to the site’s top-level domain (e.g., `example.com`). Leading dots are optional.
+COOKIE_DOMAIN=
 
 # Vector database configuration
-# Supported values are `weaviate`, `qdrant`, `milvus`, `myscale`, `relyt`, `pgvector`, `pgvecto-rs`, `chroma`, `opensearch`, `oracle`, `tencent`, `elasticsearch`, `elasticsearch-ja`, `analyticdb`, `couchbase`, `vikingdb`, `oceanbase`, `opengauss`, `tablestore`,`vastbase`,`tidb`,`tidb_on_qdrant`,`baidu`,`lindorm`,`huawei_cloud`,`upstash`, `matrixone`.
+# Supported values are `weaviate`, `oceanbase`, `qdrant`, `milvus`, `myscale`, `relyt`, `pgvector`, `pgvecto-rs`, `chroma`, `opensearch`, `oracle`, `tencent`, `elasticsearch`, `elasticsearch-ja`, `analyticdb`, `couchbase`, `vikingdb`,  `opengauss`, `tablestore`,`vastbase`,`tidb`,`tidb_on_qdrant`,`baidu`,`lindorm`,`huawei_cloud`,`upstash`, `matrixone`.
 VECTOR_STORE=weaviate
 # Prefix used to create collection name in vector database
 VECTOR_INDEX_NAME_PREFIX=Vector_index
@@ -167,6 +176,18 @@ WEAVIATE_ENDPOINT=http://localhost:8080
 WEAVIATE_API_KEY=WVF5YThaHlkYwhGUSmCRgsX3tD5ngdN8pkih
 WEAVIATE_GRPC_ENABLED=false
 WEAVIATE_BATCH_SIZE=100
+WEAVIATE_TOKENIZATION=word
+
+# OceanBase Vector configuration
+OCEANBASE_VECTOR_HOST=127.0.0.1
+OCEANBASE_VECTOR_PORT=2881
+OCEANBASE_VECTOR_USER=root@test
+OCEANBASE_VECTOR_PASSWORD=difyai123456
+OCEANBASE_VECTOR_DATABASE=test
+OCEANBASE_MEMORY_LIMIT=6G
+OCEANBASE_ENABLE_HYBRID_SEARCH=false
+OCEANBASE_FULLTEXT_PARSER=ik
+SEEKDB_MEMORY_LIMIT=2G
 
 # Qdrant configuration, use `http://localhost:6333` for local mode or `https://your-qdrant-cluster-url.qdrant.io` for remote mode
 QDRANT_URL=http://localhost:6333
@@ -303,6 +324,8 @@ BAIDU_VECTOR_DB_API_KEY=dify
 BAIDU_VECTOR_DB_DATABASE=dify
 BAIDU_VECTOR_DB_SHARD=1
 BAIDU_VECTOR_DB_REPLICAS=3
+BAIDU_VECTOR_DB_INVERTED_INDEX_ANALYZER=DEFAULT_ANALYZER
+BAIDU_VECTOR_DB_INVERTED_INDEX_PARSER_MODE=COARSE_MODE
 
 # Upstash configuration
 UPSTASH_VECTOR_URL=your-server-url
@@ -328,17 +351,17 @@ MATRIXONE_DATABASE=dify
 LINDORM_URL=http://ld-*******************-proxy-search-pub.lindorm.aliyuncs.com:30070
 LINDORM_USERNAME=admin
 LINDORM_PASSWORD=admin
-USING_UGC_INDEX=False
+LINDORM_USING_UGC=True
 LINDORM_QUERY_TIMEOUT=1
 
-# OceanBase Vector configuration
-OCEANBASE_VECTOR_HOST=127.0.0.1
-OCEANBASE_VECTOR_PORT=2881
-OCEANBASE_VECTOR_USER=root@test
-OCEANBASE_VECTOR_PASSWORD=difyai123456
-OCEANBASE_VECTOR_DATABASE=test
-OCEANBASE_MEMORY_LIMIT=6G
-OCEANBASE_ENABLE_HYBRID_SEARCH=false
+# AlibabaCloud MySQL Vector configuration
+ALIBABACLOUD_MYSQL_HOST=127.0.0.1
+ALIBABACLOUD_MYSQL_PORT=3306
+ALIBABACLOUD_MYSQL_USER=root
+ALIBABACLOUD_MYSQL_PASSWORD=root
+ALIBABACLOUD_MYSQL_DATABASE=dify
+ALIBABACLOUD_MYSQL_MAX_CONNECTION=5
+ALIBABACLOUD_MYSQL_HNSW_M=6
 
 # openGauss configuration
 OPENGAUSS_HOST=127.0.0.1
@@ -356,6 +379,12 @@ UPLOAD_IMAGE_FILE_SIZE_LIMIT=10
 UPLOAD_VIDEO_FILE_SIZE_LIMIT=100
 UPLOAD_AUDIO_FILE_SIZE_LIMIT=50
 
+# Comma-separated list of file extensions blocked from upload for security reasons.
+# Extensions should be lowercase without dots (e.g., exe,bat,sh,dll).
+# Empty by default to allow all file types.
+# Recommended: exe,bat,cmd,com,scr,vbs,ps1,msi,dll
+UPLOAD_FILE_EXTENSION_BLACKLIST=
+
 # Model configuration
 MULTIMODAL_SEND_FORMAT=base64
 PROMPT_GENERATION_MAX_TOKENS=512
@@ -405,6 +434,9 @@ SSRF_DEFAULT_TIME_OUT=5
 SSRF_DEFAULT_CONNECT_TIME_OUT=5
 SSRF_DEFAULT_READ_TIME_OUT=5
 SSRF_DEFAULT_WRITE_TIME_OUT=5
+SSRF_POOL_MAX_CONNECTIONS=100
+SSRF_POOL_MAX_KEEPALIVE_CONNECTIONS=20
+SSRF_POOL_KEEPALIVE_EXPIRY=5.0
 
 BATCH_UPLOAD_LIMIT=10
 KEYWORD_DATA_SOURCE_TYPE=database
@@ -415,10 +447,17 @@ WORKFLOW_FILE_UPLOAD_LIMIT=10
 # CODE EXECUTION CONFIGURATION
 CODE_EXECUTION_ENDPOINT=http://127.0.0.1:8194
 CODE_EXECUTION_API_KEY=dify-sandbox
+CODE_EXECUTION_SSL_VERIFY=True
+CODE_EXECUTION_POOL_MAX_CONNECTIONS=100
+CODE_EXECUTION_POOL_MAX_KEEPALIVE_CONNECTIONS=20
+CODE_EXECUTION_POOL_KEEPALIVE_EXPIRY=5.0
+CODE_EXECUTION_CONNECT_TIMEOUT=10
+CODE_EXECUTION_READ_TIMEOUT=60
+CODE_EXECUTION_WRITE_TIMEOUT=10
 CODE_MAX_NUMBER=9223372036854775807
 CODE_MIN_NUMBER=-9223372036854775808
-CODE_MAX_STRING_LENGTH=80000
-TEMPLATE_TRANSFORM_MAX_LENGTH=80000
+CODE_MAX_STRING_LENGTH=400000
+TEMPLATE_TRANSFORM_MAX_LENGTH=400000
 CODE_MAX_STRING_ARRAY_LENGTH=30
 CODE_MAX_OBJECT_ARRAY_LENGTH=30
 CODE_MAX_NUMBER_ARRAY_LENGTH=1000
@@ -435,6 +474,9 @@ HTTP_REQUEST_NODE_MAX_BINARY_SIZE=10485760
 HTTP_REQUEST_NODE_MAX_TEXT_SIZE=1048576
 HTTP_REQUEST_NODE_SSL_VERIFY=True
 
+# Webhook request configuration
+WEBHOOK_REQUEST_BODY_MAX_SIZE=10485760
+
 # Respect X-* headers to redirect clients
 RESPECT_XFORWARD_HEADERS_ENABLED=false
 
@@ -458,9 +500,18 @@ INDEXING_MAX_SEGMENTATION_TOKENS_LENGTH=4000
 WORKFLOW_MAX_EXECUTION_STEPS=500
 WORKFLOW_MAX_EXECUTION_TIME=1200
 WORKFLOW_CALL_MAX_DEPTH=5
-WORKFLOW_PARALLEL_DEPTH_LIMIT=3
 MAX_VARIABLE_SIZE=204800
 
+# GraphEngine Worker Pool Configuration
+# Minimum number of workers per GraphEngine instance (default: 1)
+GRAPH_ENGINE_MIN_WORKERS=1
+# Maximum number of workers per GraphEngine instance (default: 10)
+GRAPH_ENGINE_MAX_WORKERS=10
+# Queue depth threshold that triggers worker scale up (default: 3)
+GRAPH_ENGINE_SCALE_UP_THRESHOLD=3
+# Seconds of idle time before scaling down workers (default: 5.0)
+GRAPH_ENGINE_SCALE_DOWN_IDLE_TIME=5.0
+
 # Workflow storage configuration
 # Options: rdbms, hybrid
 # rdbms: Use only the relational database (default)
@@ -481,7 +532,7 @@ API_WORKFLOW_NODE_EXECUTION_REPOSITORY=repositories.sqlalchemy_api_workflow_node
 API_WORKFLOW_RUN_REPOSITORY=repositories.sqlalchemy_api_workflow_run_repository.DifyAPISQLAlchemyWorkflowRunRepository
 # Workflow log cleanup configuration
 # Enable automatic cleanup of workflow run logs to manage database size
-WORKFLOW_LOG_CLEANUP_ENABLED=true
+WORKFLOW_LOG_CLEANUP_ENABLED=false
 # Number of days to retain workflow run logs (default: 30 days)
 WORKFLOW_LOG_RETENTION_DAYS=30
 # Batch size for workflow log cleanup operations (default: 100)
@@ -503,6 +554,12 @@ ENABLE_CLEAN_MESSAGES=false
 ENABLE_MAIL_CLEAN_DOCUMENT_NOTIFY_TASK=false
 ENABLE_DATASETS_QUEUE_MONITOR=false
 ENABLE_CHECK_UPGRADABLE_PLUGIN_TASK=true
+ENABLE_WORKFLOW_SCHEDULE_POLLER_TASK=true
+# Interval time in minutes for polling scheduled workflows(default: 1 min)
+WORKFLOW_SCHEDULE_POLLER_INTERVAL=1
+WORKFLOW_SCHEDULE_POLLER_BATCH_SIZE=100
+# Maximum number of scheduled workflows to dispatch per tick (0 for unlimited)
+WORKFLOW_SCHEDULE_MAX_DISPATCH_PER_TICK=0
 
 # Position configuration
 POSITION_TOOL_PINS=
@@ -574,3 +631,9 @@ SWAGGER_UI_PATH=/swagger-ui.html
 # Whether to encrypt dataset IDs when exporting DSL files (default: true)
 # Set to false to export dataset IDs as plain text for easier cross-environment import
 DSL_EXPORT_ENCRYPT_DATASET_ID=true
+
+# Tenant isolated task queue configuration
+TENANT_ISOLATED_TASK_CONCURRENCY=1
+
+# Maximum number of segments for dataset segments API (0 for unlimited)
+DATASET_MAX_SEGMENTS_PER_REQUEST=0

api/.importlinter

@@ -0,0 +1,105 @@
+[importlinter]
+root_packages =
+    core
+    configs
+    controllers
+    models
+    tasks
+    services
+
+[importlinter:contract:workflow]
+name = Workflow
+type=layers
+layers =
+    graph_engine
+    graph_events
+    graph
+    nodes
+    node_events
+    entities
+containers =
+    core.workflow
+ignore_imports =
+    core.workflow.nodes.base.node -> core.workflow.graph_events
+    core.workflow.nodes.iteration.iteration_node -> core.workflow.graph_events
+    core.workflow.nodes.loop.loop_node -> core.workflow.graph_events
+
+    core.workflow.nodes.node_factory -> core.workflow.graph
+    core.workflow.nodes.iteration.iteration_node -> core.workflow.graph_engine
+    core.workflow.nodes.iteration.iteration_node -> core.workflow.graph
+    core.workflow.nodes.iteration.iteration_node -> core.workflow.graph_engine.command_channels
+    core.workflow.nodes.loop.loop_node -> core.workflow.graph_engine
+    core.workflow.nodes.loop.loop_node -> core.workflow.graph
+    core.workflow.nodes.loop.loop_node -> core.workflow.graph_engine.command_channels
+
+[importlinter:contract:rsc]
+name = RSC
+type = layers
+layers =
+    graph_engine
+    response_coordinator
+containers =
+    core.workflow.graph_engine
+
+[importlinter:contract:worker]
+name = Worker
+type = layers
+layers =
+    graph_engine
+    worker
+containers =
+    core.workflow.graph_engine
+
+[importlinter:contract:graph-engine-architecture]
+name = Graph Engine Architecture
+type = layers
+layers =
+    graph_engine
+    orchestration
+    command_processing
+    event_management
+    error_handler
+    graph_traversal
+    graph_state_manager
+    worker_management
+    domain
+containers =
+    core.workflow.graph_engine
+
+[importlinter:contract:domain-isolation]
+name = Domain Model Isolation
+type = forbidden
+source_modules =
+    core.workflow.graph_engine.domain
+forbidden_modules =
+    core.workflow.graph_engine.worker_management
+    core.workflow.graph_engine.command_channels
+    core.workflow.graph_engine.layers
+    core.workflow.graph_engine.protocols
+
+[importlinter:contract:worker-management]
+name = Worker Management
+type = forbidden
+source_modules =
+    core.workflow.graph_engine.worker_management
+forbidden_modules =
+    core.workflow.graph_engine.orchestration
+    core.workflow.graph_engine.command_processing
+    core.workflow.graph_engine.event_management
+
+
+[importlinter:contract:graph-traversal-components]
+name = Graph Traversal Components
+type = layers
+layers =
+    edge_processor
+    skip_propagator
+containers =
+    core.workflow.graph_engine.graph_traversal
+
+[importlinter:contract:command-channels]
+name = Command Channels Independence
+type = independence
+modules =
+    core.workflow.graph_engine.command_channels.in_memory_channel
+    core.workflow.graph_engine.command_channels.redis_channel

api/.ruff.toml

@@ -5,7 +5,7 @@ line-length = 120
 quote-style = "double"
 
 [lint]
-preview = false
+preview = true
 select = [
     "B",       # flake8-bugbear rules
     "C4",      # flake8-comprehensions
@@ -30,6 +30,7 @@ select = [
     "RUF022",  # unsorted-dunder-all
     "S506",    # unsafe-yaml-load
     "SIM",     # flake8-simplify rules
+    "T201",    # print-found
     "TRY400",  # error-instead-of-exception
     "TRY401",  # verbose-log-message
     "UP",      # pyupgrade rules
@@ -65,6 +66,7 @@ ignore = [
     "B006",    # mutable-argument-default
     "B007",    # unused-loop-control-variable
     "B026",    # star-arg-unpacking-after-keyword-arg
+    "B901",    # allow return in yield
     "B903",    # class-as-data-structure
     "B904",    # raise-without-from-inside-except
     "B905",    # zip-without-explicit-strict
@@ -79,7 +81,6 @@ ignore = [
     "SIM113",  # enumerate-for-loop
     "SIM117",  # multiple-with-statements
     "SIM210",  # if-expr-with-true-false
-    "UP038",   # deprecated and not recommended by Ruff, https://docs.astral.sh/ruff/rules/non-pep604-isinstance/
 ]
 
 [lint.per-file-ignores]
@@ -90,11 +91,18 @@ ignore = [
 "configs/*" = [
     "N802", # invalid-function-name
 ]
+"core/model_runtime/callbacks/base_callback.py" = [
+    "T201",
+]
+"core/workflow/callbacks/workflow_logging_callback.py" = [
+    "T201",
+]
 "libs/gmpy2_pkcs10aep_cipher.py" = [
     "N803", # invalid-argument-name
 ]
 "tests/*" = [
     "F811", # redefined-while-unused
+    "T201", # allow print in tests
 ]
 
 [lint.pyflakes]

api/.vscode/launch.json.example

@@ -54,7 +54,7 @@
                 "--loglevel",
                 "DEBUG",
                 "-Q",
-                "dataset,generation,mail,ops_trace,app_deletion"
+                "dataset,priority_pipeline,pipeline,mail,ops_trace,app_deletion,plugin,workflow_storage,conversation,workflow,schedule_poller,schedule_executor,triggered_workflow_dispatcher,trigger_refresh_executor"
             ]
         }
     ]

api/AGENTS.md

@@ -0,0 +1,62 @@
+# Agent Skill Index
+
+Start with the section that best matches your need. Each entry lists the problems it solves plus key files/concepts so you know what to expect before opening it.
+
+______________________________________________________________________
+
+## Platform Foundations
+
+- **[Infrastructure Overview](agent_skills/infra.md)**\
+  When to read this:
+
+  - You need to understand where a feature belongs in the architecture.
+  - You’re wiring storage, Redis, vector stores, or OTEL.
+  - You’re about to add CLI commands or async jobs.\
+    What it covers: configuration stack (`configs/app_config.py`, remote settings), storage entry points (`extensions/ext_storage.py`, `core/file/file_manager.py`), Redis conventions (`extensions/ext_redis.py`), plugin runtime topology, vector-store factory (`core/rag/datasource/vdb/*`), observability hooks, SSRF proxy usage, and core CLI commands.
+
+- **[Coding Style](agent_skills/coding_style.md)**\
+  When to read this:
+
+  - You’re writing or reviewing backend code and need the authoritative checklist.
+  - You’re unsure about Pydantic validators, SQLAlchemy session usage, or logging patterns.
+  - You want the exact lint/type/test commands used in PRs.\
+    Includes: Ruff & BasedPyright commands, no-annotation policy, session examples (`with Session(db.engine, ...)`), `@field_validator` usage, logging expectations, and the rule set for file size, helpers, and package management.
+
+______________________________________________________________________
+
+## Plugin & Extension Development
+
+- **[Plugin Systems](agent_skills/plugin.md)**\
+  When to read this:
+
+  - You’re building or debugging a marketplace plugin.
+  - You need to know how manifests, providers, daemons, and migrations fit together.\
+    What it covers: plugin manifests (`core/plugin/entities/plugin.py`), installation/upgrade flows (`services/plugin/plugin_service.py`, CLI commands), runtime adapters (`core/plugin/impl/*` for tool/model/datasource/trigger/endpoint/agent), daemon coordination (`core/plugin/entities/plugin_daemon.py`), and how provider registries surface capabilities to the rest of the platform.
+
+- **[Plugin OAuth](agent_skills/plugin_oauth.md)**\
+  When to read this:
+
+  - You must integrate OAuth for a plugin or datasource.
+  - You’re handling credential encryption or refresh flows.\
+    Topics: credential storage, encryption helpers (`core/helper/provider_encryption.py`), OAuth client bootstrap (`services/plugin/oauth_service.py`, `services/plugin/plugin_parameter_service.py`), and how console/API layers expose the flows.
+
+______________________________________________________________________
+
+## Workflow Entry & Execution
+
+- **[Trigger Concepts](agent_skills/trigger.md)**\
+  When to read this:
+  - You’re debugging why a workflow didn’t start.
+  - You’re adding a new trigger type or hook.
+  - You need to trace async execution, draft debugging, or webhook/schedule pipelines.\
+    Details: Start-node taxonomy, webhook & schedule internals (`core/workflow/nodes/trigger_*`, `services/trigger/*`), async orchestration (`services/async_workflow_service.py`, Celery queues), debug event bus, and storage/logging interactions.
+
+______________________________________________________________________
+
+## Additional Notes for Agents
+
+- All skill docs assume you follow the coding style guide—run Ruff/BasedPyright/tests listed there before submitting changes.
+- When you cannot find an answer in these briefs, search the codebase using the paths referenced (e.g., `core/plugin/impl/tool.py`, `services/dataset_service.py`).
+- If you run into cross-cutting concerns (tenancy, configuration, storage), check the infrastructure guide first; it links to most supporting modules.
+- Keep multi-tenancy and configuration central: everything flows through `configs.dify_config` and `tenant_id`.
+- When touching plugins or triggers, consult both the system overview and the specialised doc to ensure you adjust lifecycle, storage, and observability consistently.

api/Dockerfile

@@ -15,7 +15,11 @@ FROM base AS packages
 # RUN sed -i 's@deb.debian.org@mirrors.aliyun.com@g' /etc/apt/sources.list.d/debian.sources
 
 RUN apt-get update \
-    && apt-get install -y --no-install-recommends gcc g++ libc-dev libffi-dev libgmp-dev libmpfr-dev libmpc-dev
+    && apt-get install -y --no-install-recommends \
+          # basic environment
+          g++ \
+          # for building gmpy2
+          libmpfr-dev libmpc-dev
 
 # Install Python dependencies
 COPY pyproject.toml uv.lock ./
@@ -49,9 +53,11 @@ RUN \
     # Install dependencies
     && apt-get install -y --no-install-recommends \
         # basic environment
-        curl nodejs libgmp-dev libmpfr-dev libmpc-dev \
+        curl nodejs \
+        # for gmpy2 \
+        libgmp-dev libmpfr-dev libmpc-dev \
         # For Security
-        expat libldap-2.5-0 perl libsqlite3-0 zlib1g \
+        expat libldap-2.5-0=2.5.13+dfsg-5 perl libsqlite3-0=3.40.1-2+deb12u2 zlib1g=1:1.2.13.dfsg-1 \
         # install fonts to support the use of tools like pypdfium2
         fonts-noto-cjk \
         # install a package to improve the accuracy of guessing mime type and file extension
@@ -67,7 +73,8 @@ COPY --from=packages ${VIRTUAL_ENV} ${VIRTUAL_ENV}
 ENV PATH="${VIRTUAL_ENV}/bin:${PATH}"
 
 # Download nltk data
-RUN python -c "import nltk; nltk.download('punkt'); nltk.download('averaged_perceptron_tagger')"
+RUN mkdir -p /usr/local/share/nltk_data && NLTK_DATA=/usr/local/share/nltk_data python -c "import nltk; nltk.download('punkt'); nltk.download('averaged_perceptron_tagger'); nltk.download('stopwords')" \
+    && chmod -R 755 /usr/local/share/nltk_data
 
 ENV TIKTOKEN_CACHE_DIR=/app/api/.tiktoken_cache
 
@@ -80,7 +87,15 @@ COPY . /app/api/
 COPY docker/entrypoint.sh /entrypoint.sh
 RUN chmod +x /entrypoint.sh
 
+# Create non-root user and set permissions
+RUN groupadd -r -g 1001 dify && \
+    useradd -r -u 1001 -g 1001 -s /bin/bash dify && \
+    mkdir -p /home/dify && \
+    chown -R 1001:1001 /app /home/dify ${TIKTOKEN_CACHE_DIR} /entrypoint.sh
+
 ARG COMMIT_SHA
 ENV COMMIT_SHA=${COMMIT_SHA}
+ENV NLTK_DATA=/usr/local/share/nltk_data
+USER 1001
 
 ENTRYPOINT ["/bin/bash", "/entrypoint.sh"]

api/README.md

@@ -15,8 +15,8 @@
    ```bash
    cd ../docker
    cp middleware.env.example middleware.env
-   # change the profile to other vector database if you are not using weaviate
-   docker compose -f docker-compose.middleware.yaml --profile weaviate -p dify up -d
+   # change the profile to mysql if you are not using postgres,change the profile to other vector database if you are not using weaviate
+   docker compose -f docker-compose.middleware.yaml --profile postgresql --profile weaviate -p dify up -d
    cd ../api
    ```
 
@@ -26,6 +26,10 @@
    cp .env.example .env
    ```
 
+> [!IMPORTANT]
+>
+> When the frontend and backend run on different subdomains, set COOKIE_DOMAIN to the site’s top-level domain (e.g., `example.com`). The frontend and backend must be under the same top-level domain in order to share authentication cookies.
+
 1. Generate a `SECRET_KEY` in the `.env` file.
 
    bash for Linux
@@ -80,10 +84,10 @@
 1. If you need to handle and debug the async tasks (e.g. dataset importing and documents indexing), please start the worker service.
 
 ```bash
-uv run celery -A app.celery worker -P gevent -c 1 --loglevel INFO -Q dataset,generation,mail,ops_trace,app_deletion,plugin,workflow_storage,conversation
+uv run celery -A app.celery worker -P threads -c 2 --loglevel INFO -Q dataset,priority_dataset,priority_pipeline,pipeline,mail,ops_trace,app_deletion,plugin,workflow_storage,conversation,workflow,schedule_poller,schedule_executor,triggered_workflow_dispatcher,trigger_refresh_executor
 ```
 
-Addition, if you want to debug the celery scheduled tasks, you can use the following command in another terminal:
+Additionally, if you want to debug the celery scheduled tasks, you can run the following command in another terminal to start the beat service:
 
 ```bash
 uv run celery -A app.celery beat

api/agent_skills/coding_style.md

@@ -0,0 +1,115 @@
+## Linter
+
+- Always follow `.ruff.toml`.
+- Run `uv run ruff check --fix --unsafe-fixes`.
+- Keep each line under 100 characters (including spaces).
+
+## Code Style
+
+- `snake_case` for variables and functions.
+- `PascalCase` for classes.
+- `UPPER_CASE` for constants.
+
+## Rules
+
+- Use Pydantic v2 standard.
+- Use `uv` for package management.
+- Do not override dunder methods like `__init__`, `__iadd__`, etc.
+- Never launch services (`uv run app.py`, `flask run`, etc.); running tests under `tests/` is allowed.
+- Prefer simple functions over classes for lightweight helpers.
+- Keep files below 800 lines; split when necessary.
+- Keep code readable—no clever hacks.
+- Never use `print`; log with `logger = logging.getLogger(__name__)`.
+
+## Guiding Principles
+
+- Mirror the project’s layered architecture: controller → service → core/domain.
+- Reuse existing helpers in `core/`, `services/`, and `libs/` before creating new abstractions.
+- Optimise for observability: deterministic control flow, clear logging, actionable errors.
+
+## SQLAlchemy Patterns
+
+- Models inherit from `models.base.Base`; never create ad-hoc metadata or engines.
+
+- Open sessions with context managers:
+
+  ```python
+  from sqlalchemy.orm import Session
+
+  with Session(db.engine, expire_on_commit=False) as session:
+      stmt = select(Workflow).where(
+          Workflow.id == workflow_id,
+          Workflow.tenant_id == tenant_id,
+      )
+      workflow = session.execute(stmt).scalar_one_or_none()
+  ```
+
+- Use SQLAlchemy expressions; avoid raw SQL unless necessary.
+
+- Introduce repository abstractions only for very large tables (e.g., workflow executions) to support alternative storage strategies.
+
+- Always scope queries by `tenant_id` and protect write paths with safeguards (`FOR UPDATE`, row counts, etc.).
+
+## Storage & External IO
+
+- Access storage via `extensions.ext_storage.storage`.
+- Use `core.helper.ssrf_proxy` for outbound HTTP fetches.
+- Background tasks that touch storage must be idempotent and log the relevant object identifiers.
+
+## Pydantic Usage
+
+- Define DTOs with Pydantic v2 models and forbid extras by default.
+
+- Use `@field_validator` / `@model_validator` for domain rules.
+
+- Example:
+
+  ```python
+  from pydantic import BaseModel, ConfigDict, HttpUrl, field_validator
+
+  class TriggerConfig(BaseModel):
+      endpoint: HttpUrl
+      secret: str
+
+      model_config = ConfigDict(extra="forbid")
+
+      @field_validator("secret")
+      def ensure_secret_prefix(cls, value: str) -> str:
+          if not value.startswith("dify_"):
+              raise ValueError("secret must start with dify_")
+          return value
+  ```
+
+## Generics & Protocols
+
+- Use `typing.Protocol` to define behavioural contracts (e.g., cache interfaces).
+- Apply generics (`TypeVar`, `Generic`) for reusable utilities like caches or providers.
+- Validate dynamic inputs at runtime when generics cannot enforce safety alone.
+
+## Error Handling & Logging
+
+- Raise domain-specific exceptions (`services/errors`, `core/errors`) and translate to HTTP responses in controllers.
+- Declare `logger = logging.getLogger(__name__)` at module top.
+- Include tenant/app/workflow identifiers in log context.
+- Log retryable events at `warning`, terminal failures at `error`.
+
+## Tooling & Checks
+
+- Format/lint: `uv run --project api --dev ruff format ./api` and `uv run --project api --dev ruff check --fix --unsafe-fixes ./api`.
+- Type checks: `uv run --directory api --dev basedpyright`.
+- Tests: `uv run --project api --dev dev/pytest/pytest_unit_tests.sh`.
+- Run all of the above before submitting your work.
+
+## Controllers & Services
+
+- Controllers: parse input via Pydantic, invoke services, return serialised responses; no business logic.
+- Services: coordinate repositories, providers, background tasks; keep side effects explicit.
+- Avoid repositories unless necessary; direct SQLAlchemy usage is preferred for typical tables.
+- Document non-obvious behaviour with concise comments.
+
+## Miscellaneous
+
+- Use `configs.dify_config` for configuration—never read environment variables directly.
+- Maintain tenant awareness end-to-end; `tenant_id` must flow through every layer touching shared resources.
+- Queue async work through `services/async_workflow_service`; implement tasks under `tasks/` with explicit queue selection.
+- Keep experimental scripts under `dev/`; do not ship them in production builds.

api/agent_skills/infra.md

@@ -0,0 +1,96 @@
+## Configuration
+
+- Import `configs.dify_config` for every runtime toggle. Do not read environment variables directly.
+- Add new settings to the proper mixin inside `configs/` (deployment, feature, middleware, etc.) so they load through `DifyConfig`.
+- Remote overrides come from the optional providers in `configs/remote_settings_sources`; keep defaults in code safe when the value is missing.
+- Example: logging pulls targets from `extensions/ext_logging.py`, and model provider URLs are assembled in `services/entities/model_provider_entities.py`.
+
+## Dependencies
+
+- Runtime dependencies live in `[project].dependencies` inside `pyproject.toml`. Optional clients go into the `storage`, `tools`, or `vdb` groups under `[dependency-groups]`.
+- Always pin versions and keep the list alphabetised. Shared tooling (lint, typing, pytest) belongs in the `dev` group.
+- When code needs a new package, explain why in the PR and run `uv lock` so the lockfile stays current.
+
+## Storage & Files
+
+- Use `extensions.ext_storage.storage` for all blob IO; it already respects the configured backend.
+- Convert files for workflows with helpers in `core/file/file_manager.py`; they handle signed URLs and multimodal payloads.
+- When writing controller logic, delegate upload quotas and metadata to `services/file_service.py` instead of touching storage directly.
+- All outbound HTTP fetches (webhooks, remote files) must go through the SSRF-safe client in `core/helper/ssrf_proxy.py`; it wraps `httpx` with the allow/deny rules configured for the platform.
+
+## Redis & Shared State
+
+- Access Redis through `extensions.ext_redis.redis_client`. For locking, reuse `redis_client.lock`.
+- Prefer higher-level helpers when available: rate limits use `libs.helper.RateLimiter`, provider metadata uses caches in `core/helper/provider_cache.py`.
+
+## Models
+
+- SQLAlchemy models sit in `models/` and inherit from the shared declarative `Base` defined in `models/base.py` (metadata configured via `models/engine.py`).
+- `models/__init__.py` exposes grouped aggregates: account/tenant models, app and conversation tables, datasets, providers, workflow runs, triggers, etc. Import from there to avoid deep path churn.
+- Follow the DDD boundary: persistence objects live in `models/`, repositories under `repositories/` translate them into domain entities, and services consume those repositories.
+- When adding a table, create the model class, register it in `models/__init__.py`, wire a repository if needed, and generate an Alembic migration as described below.
+
+## Vector Stores
+
+- Vector client implementations live in `core/rag/datasource/vdb/<provider>`, with a common factory in `core/rag/datasource/vdb/vector_factory.py` and enums in `core/rag/datasource/vdb/vector_type.py`.
+- Retrieval pipelines call these providers through `core/rag/datasource/retrieval_service.py` and dataset ingestion flows in `services/dataset_service.py`.
+- The CLI helper `flask vdb-migrate` orchestrates bulk migrations using routines in `commands.py`; reuse that pattern when adding new backend transitions.
+- To add another store, mirror the provider layout, register it with the factory, and include any schema changes in Alembic migrations.
+
+## Observability & OTEL
+
+- OpenTelemetry settings live under the observability mixin in `configs/observability`. Toggle exporters and sampling via `dify_config`, not ad-hoc env reads.
+- HTTP, Celery, Redis, SQLAlchemy, and httpx instrumentation is initialised in `extensions/ext_app_metrics.py` and `extensions/ext_request_logging.py`; reuse these hooks when adding new workers or entrypoints.
+- When creating background tasks or external calls, propagate tracing context with helpers in the existing instrumented clients (e.g. use the shared `httpx` session from `core/helper/http_client_pooling.py`).
+- If you add a new external integration, ensure spans and metrics are emitted by wiring the appropriate OTEL instrumentation package in `pyproject.toml` and configuring it in `extensions/`.
+
+## Ops Integrations
+
+- Langfuse support and other tracing bridges live under `core/ops/opik_trace`. Config toggles sit in `configs/observability`, while exporters are initialised in the OTEL extensions mentioned above.
+- External monitoring services should follow this pattern: keep client code in `core/ops`, expose switches via `dify_config`, and hook initialisation in `extensions/ext_app_metrics.py` or sibling modules.
+- Before instrumenting new code paths, check whether existing context helpers (e.g. `extensions/ext_request_logging.py`) already capture the necessary metadata.
+
+## Controllers, Services, Core
+
+- Controllers only parse HTTP input and call a service method. Keep business rules in `services/`.
+- Services enforce tenant rules, quotas, and orchestration, then call into `core/` engines (workflow execution, tools, LLMs).
+- When adding a new endpoint, search for an existing service to extend before introducing a new layer. Example: workflow APIs pipe through `services/workflow_service.py` into `core/workflow`.
+
+## Plugins, Tools, Providers
+
+- In Dify a plugin is a tenant-installable bundle that declares one or more providers (tool, model, datasource, trigger, endpoint, agent strategy) plus its resource needs and version metadata. The manifest (`core/plugin/entities/plugin.py`) mirrors what you see in the marketplace documentation.
+- Installation, upgrades, and migrations are orchestrated by `services/plugin/plugin_service.py` together with helpers such as `services/plugin/plugin_migration.py`.
+- Runtime loading happens through the implementations under `core/plugin/impl/*` (tool/model/datasource/trigger/endpoint/agent). These modules normalise plugin providers so that downstream systems (`core/tools/tool_manager.py`, `services/model_provider_service.py`, `services/trigger/*`) can treat builtin and plugin capabilities the same way.
+- For remote execution, plugin daemons (`core/plugin/entities/plugin_daemon.py`, `core/plugin/impl/plugin.py`) manage lifecycle hooks, credential forwarding, and background workers that keep plugin processes in sync with the main application.
+- Acquire tool implementations through `core/tools/tool_manager.py`; it resolves builtin, plugin, and workflow-as-tool providers uniformly, injecting the right context (tenant, credentials, runtime config).
+- To add a new plugin capability, extend the relevant `core/plugin/entities` schema and register the implementation in the matching `core/plugin/impl` module rather than importing the provider directly.
+
+## Async Workloads
+
+see `agent_skills/trigger.md` for more detailed documentation.
+
+- Enqueue background work through `services/async_workflow_service.py`. It routes jobs to the tiered Celery queues defined in `tasks/`.
+- Workers boot from `celery_entrypoint.py` and execute functions in `tasks/workflow_execution_tasks.py`, `tasks/trigger_processing_tasks.py`, etc.
+- Scheduled workflows poll from `schedule/workflow_schedule_tasks.py`. Follow the same pattern if you need new periodic jobs.
+
+## Database & Migrations
+
+- SQLAlchemy models live under `models/` and map directly to migration files in `migrations/versions`.
+- Generate migrations with `uv run --project api flask db revision --autogenerate -m "<summary>"`, then review the diff; never hand-edit the database outside Alembic.
+- Apply migrations locally using `uv run --project api flask db upgrade`; production deploys expect the same history.
+- If you add tenant-scoped data, confirm the upgrade includes tenant filters or defaults consistent with the service logic touching those tables.
+
+## CLI Commands
+
+- Maintenance commands from `commands.py` are registered on the Flask CLI. Run them via `uv run --project api flask <command>`.
+- Use the built-in `db` commands from Flask-Migrate for schema operations (`flask db upgrade`, `flask db stamp`, etc.). Only fall back to custom helpers if you need their extra behaviour.
+- Custom entries such as `flask reset-password`, `flask reset-email`, and `flask vdb-migrate` handle self-hosted account recovery and vector database migrations.
+- Before adding a new command, check whether an existing service can be reused and ensure the command guards edition-specific behaviour (many enforce `SELF_HOSTED`). Document any additions in the PR.
+- Ruff helpers are run directly with `uv`: `uv run --project api --dev ruff format ./api` for formatting and `uv run --project api --dev ruff check ./api` (add `--fix` if you want automatic fixes).
+
+## When You Add Features
+
+- Check for an existing helper or service before writing a new util.
+- Uphold tenancy: every service method should receive the tenant ID from controller wrappers such as `controllers/console/wraps.py`.
+- Update or create tests alongside behaviour changes (`tests/unit_tests` for fast coverage, `tests/integration_tests` when touching orchestrations).
+- Run `uv run --project api --dev ruff check ./api`, `uv run --directory api --dev basedpyright`, and `uv run --project api --dev dev/pytest/pytest_unit_tests.sh` before submitting changes.

api/agent_skills/plugin.md

@@ -0,0 +1 @@
+// TBD

api/agent_skills/plugin_oauth.md

@@ -0,0 +1 @@
+// TBD

api/agent_skills/trigger.md

@@ -0,0 +1,53 @@
+## Overview
+
+Trigger is a collection of nodes that we called `Start` nodes, also, the concept of `Start` is the same as `RootNode` in the workflow engine `core/workflow/graph_engine`, On the other hand, `Start` node is the entry point of workflows, every workflow run always starts from a `Start` node.
+
+## Trigger nodes
+
+- `UserInput`
+- `Trigger Webhook`
+- `Trigger Schedule`
+- `Trigger Plugin`
+
+### UserInput
+
+Before `Trigger` concept is introduced, it's what we called `Start` node, but now, to avoid confusion, it was renamed to `UserInput` node, has a strong relation with `ServiceAPI` in `controllers/service_api/app`
+
+1. `UserInput` node introduces a list of arguments that need to be provided by the user, finally it will be converted into variables in the workflow variable pool.
+1. `ServiceAPI` accept those arguments, and pass through them into `UserInput` node.
+1. For its detailed implementation, please refer to `core/workflow/nodes/start`
+
+### Trigger Webhook
+
+Inside Webhook Node, Dify provided a UI panel that allows user define a HTTP manifest `core/workflow/nodes/trigger_webhook/entities.py`.`WebhookData`, also, Dify generates a random webhook id for each `Trigger Webhook` node, the implementation was implemented in `core/trigger/utils/endpoint.py`, as you can see, `webhook-debug` is a debug mode for webhook, you may find it in `controllers/trigger/webhook.py`.
+
+Finally, requests to `webhook` endpoint will be converted into variables in workflow variable pool during workflow execution.
+
+### Trigger Schedule
+
+`Trigger Schedule` node is a node that allows user define a schedule to trigger the workflow, detailed manifest is here `core/workflow/nodes/trigger_schedule/entities.py`, we have a poller and executor to handle millions of schedules, see `docker/entrypoint.sh` / `schedule/workflow_schedule_task.py` for help.
+
+To Achieve this, a `WorkflowSchedulePlan` model was introduced in `models/trigger.py`, and a `events/event_handlers/sync_workflow_schedule_when_app_published.py` was used to sync workflow schedule plans when app is published.
+
+### Trigger Plugin
+
+`Trigger Plugin` node allows user define there own distributed trigger plugin, whenever a request was received, Dify forwards it to the plugin and wait for parsed variables from it.
+
+1. Requests were saved in storage by `services/trigger/trigger_request_service.py`, referenced by `services/trigger/trigger_service.py`.`TriggerService`.`process_endpoint`
+1. Plugins accept those requests and parse variables from it, see `core/plugin/impl/trigger.py` for details.
+
+A `subscription` concept was out here by Dify, it means an endpoint address from Dify was bound to thirdparty webhook service like `Github` `Slack` `Linear` `GoogleDrive` `Gmail` etc. Once a subscription was created, Dify continually receives requests from the platforms and handle them one by one.
+
+## Worker Pool / Async Task
+
+All the events that triggered a new workflow run is always in async mode, a unified entrypoint can be found here `services/async_workflow_service.py`.`AsyncWorkflowService`.`trigger_workflow_async`.
+
+The infrastructure we used is `celery`, we've already configured it in `docker/entrypoint.sh`, and the consumers are in `tasks/async_workflow_tasks.py`, 3 queues were used to handle different tiers of users, `PROFESSIONAL_QUEUE` `TEAM_QUEUE` `SANDBOX_QUEUE`.
+
+## Debug Strategy
+
+Dify divided users into 2 groups: builders / end users.
+
+Builders are the users who create workflows, in this stage, debugging a workflow becomes a critical part of the workflow development process, as the start node in workflows, trigger nodes can `listen` to the events from `WebhookDebug` `Schedule` `Plugin`, debugging process was created in `controllers/console/app/workflow.py`.`DraftWorkflowTriggerNodeApi`.
+
+A polling process can be considered as combine of few single `poll` operations, each `poll` operation fetches events cached in `Redis`, returns `None` if no event was found, more detailed implemented: `core/trigger/debug/event_bus.py` was used to handle the polling process, and `core/trigger/debug/event_selectors.py` was used to select the event poller based on the trigger type.

api/app.py

@@ -1,8 +1,7 @@
-import os
 import sys
 
 
-def is_db_command():
+def is_db_command() -> bool:
     if len(sys.argv) > 1 and sys.argv[0].endswith("flask") and sys.argv[1] == "db":
         return True
     return False
@@ -14,23 +13,12 @@ if is_db_command():
 
     app = create_migrations_app()
 else:
-    # It seems that JetBrains Python debugger does not work well with gevent,
-    # so we need to disable gevent in debug mode.
-    # If you are using debugpy and set GEVENT_SUPPORT=True, you can debug with gevent.
-    if (flask_debug := os.environ.get("FLASK_DEBUG", "0")) and flask_debug.lower() in {"false", "0", "no"}:
-        from gevent import monkey
-
-        # gevent
-        monkey.patch_all()
-
-        from grpc.experimental import gevent as grpc_gevent  # type: ignore
-
-        # grpc gevent
-        grpc_gevent.init_gevent()
-
-        import psycogreen.gevent  # type: ignore
-
-        psycogreen.gevent.patch_psycopg()
+    # Gunicorn and Celery handle monkey patching automatically in production by
+    # specifying the `gevent` worker class. Manual monkey patching is not required here.
+    #
+    # See `api/docker/entrypoint.sh` (lines 33 and 47) for details.
+    #
+    # For third-party library patching, refer to `gunicorn.conf.py` and `celery_entrypoint.py`.
 
     from app_factory import create_app
 

api/app_factory.py

@@ -18,6 +18,7 @@ def create_flask_app_with_configs() -> DifyApp:
     """
     dify_app = DifyApp(__name__)
     dify_app.config.from_mapping(dify_config.model_dump())
+    dify_app.config["RESTX_INCLUDE_ALL_MODELS"] = True
 
     # add before request hook
     @dify_app.before_request

api/celery_entrypoint.py

@@ -0,0 +1,13 @@
+import psycogreen.gevent as pscycogreen_gevent  # type: ignore
+from grpc.experimental import gevent as grpc_gevent  # type: ignore
+
+# grpc gevent
+grpc_gevent.init_gevent()
+print("gRPC patched with gevent.", flush=True)  # noqa: T201
+pscycogreen_gevent.patch_psycopg()
+print("psycopg2 patched with gevent.", flush=True)  # noqa: T201
+
+
+from app import app, celery
+
+__all__ = ["app", "celery"]

api/cnt_base.sh

@@ -0,0 +1,7 @@
+#!/bin/bash
+set -euxo pipefail
+
+for pattern in "Base" "TypeBase"; do
+    printf "%s " "$pattern"
+    grep "($pattern):" -r --include='*.py' --exclude-dir=".venv" --exclude-dir="tests" . | wc -l
+done

api/commands.py

@@ -2,7 +2,7 @@ import base64
 import json
 import logging
 import secrets
-from typing import Any, Optional
+from typing import Any
 
 import click
 import sqlalchemy as sa
@@ -10,10 +10,13 @@ from flask import current_app
 from pydantic import TypeAdapter
 from sqlalchemy import select
 from sqlalchemy.exc import SQLAlchemyError
+from sqlalchemy.orm import sessionmaker
 
 from configs import dify_config
 from constants.languages import languages
-from core.plugin.entities.plugin import ToolProviderID
+from core.helper import encrypter
+from core.plugin.entities.plugin_daemon import CredentialType
+from core.plugin.impl.plugin import PluginInstaller
 from core.rag.datasource.vdb.vector_factory import Vector
 from core.rag.datasource.vdb.vector_type import VectorType
 from core.rag.index_processor.constant.built_in_field import BuiltInField
@@ -23,19 +26,25 @@ from events.app_event import app_was_created
 from extensions.ext_database import db
 from extensions.ext_redis import redis_client
 from extensions.ext_storage import storage
+from extensions.storage.opendal_storage import OpenDALStorage
+from extensions.storage.storage_type import StorageType
 from libs.helper import email as email_validate
 from libs.password import hash_password, password_pattern, valid_password
 from libs.rsa import generate_key_pair
 from models import Tenant
 from models.dataset import Dataset, DatasetCollectionBinding, DatasetMetadata, DatasetMetadataBinding, DocumentSegment
 from models.dataset import Document as DatasetDocument
-from models.model import Account, App, AppAnnotationSetting, AppMode, Conversation, MessageAnnotation
+from models.model import Account, App, AppAnnotationSetting, AppMode, Conversation, MessageAnnotation, UploadFile
+from models.oauth import DatasourceOauthParamConfig, DatasourceProvider
 from models.provider import Provider, ProviderModel
+from models.provider_ids import DatasourceProviderID, ToolProviderID
+from models.source import DataSourceApiKeyAuthBinding, DataSourceOauthBinding
 from models.tools import ToolOAuthSystemClient
 from services.account_service import AccountService, RegisterService, TenantService
 from services.clear_free_plan_tenant_expired_logs import ClearFreePlanTenantExpiredLogs
 from services.plugin.data_migration import PluginDataMigration
 from services.plugin.plugin_migration import PluginMigration
+from services.plugin.plugin_service import PluginService
 from tasks.remove_app_and_related_data_task import delete_draft_variables_batch
 
 logger = logging.getLogger(__name__)
@@ -53,31 +62,30 @@ def reset_password(email, new_password, password_confirm):
     if str(new_password).strip() != str(password_confirm).strip():
         click.echo(click.style("Passwords do not match.", fg="red"))
         return
+    with sessionmaker(db.engine, expire_on_commit=False).begin() as session:
+        account = session.query(Account).where(Account.email == email).one_or_none()
 
-    account = db.session.query(Account).where(Account.email == email).one_or_none()
+        if not account:
+            click.echo(click.style(f"Account not found for email: {email}", fg="red"))
+            return
 
-    if not account:
-        click.echo(click.style(f"Account not found for email: {email}", fg="red"))
-        return
+        try:
+            valid_password(new_password)
+        except:
+            click.echo(click.style(f"Invalid password. Must match {password_pattern}", fg="red"))
+            return
 
-    try:
-        valid_password(new_password)
-    except:
-        click.echo(click.style(f"Invalid password. Must match {password_pattern}", fg="red"))
-        return
+        # generate password salt
+        salt = secrets.token_bytes(16)
+        base64_salt = base64.b64encode(salt).decode()
 
-    # generate password salt
-    salt = secrets.token_bytes(16)
-    base64_salt = base64.b64encode(salt).decode()
-
-    # encrypt password with salt
-    password_hashed = hash_password(new_password, salt)
-    base64_password_hashed = base64.b64encode(password_hashed).decode()
-    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"))
+        # encrypt password with salt
+        password_hashed = hash_password(new_password, salt)
+        base64_password_hashed = base64.b64encode(password_hashed).decode()
+        account.password = base64_password_hashed
+        account.password_salt = base64_salt
+        AccountService.reset_login_error_rate_limit(email)
+        click.echo(click.style("Password reset successfully.", fg="green"))
 
 
 @click.command("reset-email", help="Reset the account email.")
@@ -92,22 +100,21 @@ def reset_email(email, new_email, email_confirm):
     if str(new_email).strip() != str(email_confirm).strip():
         click.echo(click.style("New emails do not match.", fg="red"))
         return
+    with sessionmaker(db.engine, expire_on_commit=False).begin() as session:
+        account = session.query(Account).where(Account.email == email).one_or_none()
 
-    account = db.session.query(Account).where(Account.email == email).one_or_none()
+        if not account:
+            click.echo(click.style(f"Account not found for email: {email}", fg="red"))
+            return
 
-    if not account:
-        click.echo(click.style(f"Account not found for email: {email}", fg="red"))
-        return
+        try:
+            email_validate(new_email)
+        except:
+            click.echo(click.style(f"Invalid email: {new_email}", fg="red"))
+            return
 
-    try:
-        email_validate(new_email)
-    except:
-        click.echo(click.style(f"Invalid email: {new_email}", fg="red"))
-        return
-
-    account.email = new_email
-    db.session.commit()
-    click.echo(click.style("Email updated successfully.", fg="green"))
+        account.email = new_email
+        click.echo(click.style("Email updated successfully.", fg="green"))
 
 
 @click.command(
@@ -131,25 +138,24 @@ def reset_encrypt_key_pair():
     if dify_config.EDITION != "SELF_HOSTED":
         click.echo(click.style("This command is only for SELF_HOSTED installations.", fg="red"))
         return
+    with sessionmaker(db.engine, expire_on_commit=False).begin() as session:
+        tenants = session.query(Tenant).all()
+        for tenant in tenants:
+            if not tenant:
+                click.echo(click.style("No workspaces found. Run /install first.", fg="red"))
+                return
 
-    tenants = db.session.query(Tenant).all()
-    for tenant in tenants:
-        if not tenant:
-            click.echo(click.style("No workspaces found. Run /install first.", fg="red"))
-            return
+            tenant.encrypt_public_key = generate_key_pair(tenant.id)
 
-        tenant.encrypt_public_key = generate_key_pair(tenant.id)
+            session.query(Provider).where(Provider.provider_type == "custom", Provider.tenant_id == tenant.id).delete()
+            session.query(ProviderModel).where(ProviderModel.tenant_id == tenant.id).delete()
 
-        db.session.query(Provider).where(Provider.provider_type == "custom", Provider.tenant_id == tenant.id).delete()
-        db.session.query(ProviderModel).where(ProviderModel.tenant_id == tenant.id).delete()
-        db.session.commit()
-
-        click.echo(
-            click.style(
-                f"Congratulations! The asymmetric key pair of workspace {tenant.id} has been reset.",
-                fg="green",
+            click.echo(
+                click.style(
+                    f"Congratulations! The asymmetric key pair of workspace {tenant.id} has been reset.",
+                    fg="green",
+                )
             )
-        )
 
 
 @click.command("vdb-migrate", help="Migrate vector db.")
@@ -174,14 +180,15 @@ def migrate_annotation_vector_database():
         try:
             # get apps info
             per_page = 50
-            apps = (
-                db.session.query(App)
-                .where(App.status == "normal")
-                .order_by(App.created_at.desc())
-                .limit(per_page)
-                .offset((page - 1) * per_page)
-                .all()
-            )
+            with sessionmaker(db.engine, expire_on_commit=False).begin() as session:
+                apps = (
+                    session.query(App)
+                    .where(App.status == "normal")
+                    .order_by(App.created_at.desc())
+                    .limit(per_page)
+                    .offset((page - 1) * per_page)
+                    .all()
+                )
             if not apps:
                 break
         except SQLAlchemyError:
@@ -195,26 +202,27 @@ def migrate_annotation_vector_database():
             )
             try:
                 click.echo(f"Creating app annotation index: {app.id}")
-                app_annotation_setting = (
-                    db.session.query(AppAnnotationSetting).where(AppAnnotationSetting.app_id == app.id).first()
-                )
+                with sessionmaker(db.engine, expire_on_commit=False).begin() as session:
+                    app_annotation_setting = (
+                        session.query(AppAnnotationSetting).where(AppAnnotationSetting.app_id == app.id).first()
+                    )
 
-                if not app_annotation_setting:
-                    skipped_count = skipped_count + 1
-                    click.echo(f"App annotation setting disabled: {app.id}")
-                    continue
-                # get dataset_collection_binding info
-                dataset_collection_binding = (
-                    db.session.query(DatasetCollectionBinding)
-                    .where(DatasetCollectionBinding.id == app_annotation_setting.collection_binding_id)
-                    .first()
-                )
-                if not dataset_collection_binding:
-                    click.echo(f"App annotation collection binding not found: {app.id}")
-                    continue
-                annotations = db.session.scalars(
-                    select(MessageAnnotation).where(MessageAnnotation.app_id == app.id)
-                ).all()
+                    if not app_annotation_setting:
+                        skipped_count = skipped_count + 1
+                        click.echo(f"App annotation setting disabled: {app.id}")
+                        continue
+                    # get dataset_collection_binding info
+                    dataset_collection_binding = (
+                        session.query(DatasetCollectionBinding)
+                        .where(DatasetCollectionBinding.id == app_annotation_setting.collection_binding_id)
+                        .first()
+                    )
+                    if not dataset_collection_binding:
+                        click.echo(f"App annotation collection binding not found: {app.id}")
+                        continue
+                    annotations = session.scalars(
+                        select(MessageAnnotation).where(MessageAnnotation.app_id == app.id)
+                    ).all()
                 dataset = Dataset(
                     id=app.id,
                     tenant_id=app.tenant_id,
@@ -313,6 +321,8 @@ def migrate_knowledge_vector_database():
             )
 
             datasets = db.paginate(select=stmt, page=page, per_page=50, max_per_page=50, error_out=False)
+            if not datasets.items:
+                break
         except SQLAlchemyError:
             raise
 
@@ -639,7 +649,7 @@ def old_metadata_migration():
 @click.option("--email", prompt=True, help="Tenant account email.")
 @click.option("--name", prompt=True, help="Workspace name.")
 @click.option("--language", prompt=True, help="Account language, default: en-US.")
-def create_tenant(email: str, language: Optional[str] = None, name: Optional[str] = None):
+def create_tenant(email: str, language: str | None = None, name: str | None = None):
     """
     Create tenant account
     """
@@ -731,18 +741,18 @@ where sites.id is null limit 1000"""
                 try:
                     app = db.session.query(App).where(App.id == app_id).first()
                     if not app:
-                        print(f"App {app_id} not found")
+                        logger.info("App %s not found", app_id)
                         continue
 
                     tenant = app.tenant
                     if tenant:
                         accounts = tenant.get_accounts()
                         if not accounts:
-                            print(f"Fix failed for app {app.id}")
+                            logger.info("Fix failed for app %s", app.id)
                             continue
 
                         account = accounts[0]
-                        print(f"Fixing missing site for app {app.id}")
+                        logger.info("Fixing missing site for app %s", app.id)
                         app_was_created.send(app, account=account)
                 except Exception:
                     failed_app_ids.append(app_id)
@@ -953,7 +963,7 @@ def clear_orphaned_file_records(force: bool):
             click.echo(click.style("- Deleting orphaned message_files records", fg="white"))
             query = "DELETE FROM message_files WHERE id IN :ids"
             with db.engine.begin() as conn:
-                conn.execute(sa.text(query), {"ids": tuple([record["id"] for record in orphaned_message_files])})
+                conn.execute(sa.text(query), {"ids": tuple(record["id"] for record in orphaned_message_files)})
             click.echo(
                 click.style(f"Removed {len(orphaned_message_files)} orphaned message_files records.", fg="green")
             )
@@ -1219,6 +1229,55 @@ def setup_system_tool_oauth_client(provider, client_params):
     click.echo(click.style(f"OAuth client params setup successfully. id: {oauth_client.id}", fg="green"))
 
 
+@click.command("setup-system-trigger-oauth-client", help="Setup system trigger oauth client.")
+@click.option("--provider", prompt=True, help="Provider name")
+@click.option("--client-params", prompt=True, help="Client Params")
+def setup_system_trigger_oauth_client(provider, client_params):
+    """
+    Setup system trigger oauth client
+    """
+    from models.provider_ids import TriggerProviderID
+    from models.trigger import TriggerOAuthSystemClient
+
+    provider_id = TriggerProviderID(provider)
+    provider_name = provider_id.provider_name
+    plugin_id = provider_id.plugin_id
+
+    try:
+        # json validate
+        click.echo(click.style(f"Validating client params: {client_params}", fg="yellow"))
+        client_params_dict = TypeAdapter(dict[str, Any]).validate_json(client_params)
+        click.echo(click.style("Client params validated successfully.", fg="green"))
+
+        click.echo(click.style(f"Encrypting client params: {client_params}", fg="yellow"))
+        click.echo(click.style(f"Using SECRET_KEY: `{dify_config.SECRET_KEY}`", fg="yellow"))
+        oauth_client_params = encrypt_system_oauth_params(client_params_dict)
+        click.echo(click.style("Client params encrypted successfully.", fg="green"))
+    except Exception as e:
+        click.echo(click.style(f"Error parsing client params: {str(e)}", fg="red"))
+        return
+
+    deleted_count = (
+        db.session.query(TriggerOAuthSystemClient)
+        .filter_by(
+            provider=provider_name,
+            plugin_id=plugin_id,
+        )
+        .delete()
+    )
+    if deleted_count > 0:
+        click.echo(click.style(f"Deleted {deleted_count} existing oauth client params.", fg="yellow"))
+
+    oauth_client = TriggerOAuthSystemClient(
+        provider=provider_name,
+        plugin_id=plugin_id,
+        encrypted_oauth_params=oauth_client_params,
+    )
+    db.session.add(oauth_client)
+    db.session.commit()
+    click.echo(click.style(f"OAuth client params setup successfully. id: {oauth_client.id}", fg="green"))
+
+
 def _find_orphaned_draft_variables(batch_size: int = 1000) -> list[str]:
     """
     Find draft variables that reference non-existent apps.
@@ -1245,15 +1304,17 @@ def _find_orphaned_draft_variables(batch_size: int = 1000) -> list[str]:
 
 def _count_orphaned_draft_variables() -> dict[str, Any]:
     """
-    Count orphaned draft variables by app.
+    Count orphaned draft variables by app, including associated file counts.
 
     Returns:
-        Dictionary with statistics about orphaned variables
+        Dictionary with statistics about orphaned variables and files
     """
-    query = """
+    # Count orphaned variables by app
+    variables_query = """
         SELECT
             wdv.app_id,
-            COUNT(*) as variable_count
+            COUNT(*) as variable_count,
+            COUNT(wdv.file_id) as file_count
         FROM workflow_draft_variables AS wdv
         WHERE NOT EXISTS(
             SELECT 1 FROM apps WHERE apps.id = wdv.app_id
@@ -1263,14 +1324,21 @@ def _count_orphaned_draft_variables() -> dict[str, Any]:
     """
 
     with db.engine.connect() as conn:
-        result = conn.execute(sa.text(query))
-        orphaned_by_app = {row[0]: row[1] for row in result}
+        result = conn.execute(sa.text(variables_query))
+        orphaned_by_app = {}
+        total_files = 0
 
-        total_orphaned = sum(orphaned_by_app.values())
+        for row in result:
+            app_id, variable_count, file_count = row
+            orphaned_by_app[app_id] = {"variables": variable_count, "files": file_count}
+            total_files += file_count
+
+        total_orphaned = sum(app_data["variables"] for app_data in orphaned_by_app.values())
         app_count = len(orphaned_by_app)
 
         return {
             "total_orphaned_variables": total_orphaned,
+            "total_orphaned_files": total_files,
             "orphaned_app_count": app_count,
             "orphaned_by_app": orphaned_by_app,
         }
@@ -1299,6 +1367,7 @@ def cleanup_orphaned_draft_variables(
     stats = _count_orphaned_draft_variables()
 
     logger.info("Found %s orphaned draft variables", stats["total_orphaned_variables"])
+    logger.info("Found %s associated offload files", stats["total_orphaned_files"])
     logger.info("Across %s non-existent apps", stats["orphaned_app_count"])
 
     if stats["total_orphaned_variables"] == 0:
@@ -1307,10 +1376,10 @@ def cleanup_orphaned_draft_variables(
 
     if dry_run:
         logger.info("DRY RUN: Would delete the following:")
-        for app_id, count in sorted(stats["orphaned_by_app"].items(), key=lambda x: x[1], reverse=True)[
+        for app_id, data in sorted(stats["orphaned_by_app"].items(), key=lambda x: x[1]["variables"], reverse=True)[
             :10
         ]:  # Show top 10
-            logger.info("  App %s: %s variables", app_id, count)
+            logger.info("  App %s: %s variables, %s files", app_id, data["variables"], data["files"])
         if len(stats["orphaned_by_app"]) > 10:
             logger.info("  ... and %s more apps", len(stats["orphaned_by_app"]) - 10)
         return
@@ -1319,7 +1388,8 @@ def cleanup_orphaned_draft_variables(
     if not force:
         click.confirm(
             f"Are you sure you want to delete {stats['total_orphaned_variables']} "
-            f"orphaned draft variables from {stats['orphaned_app_count']} apps?",
+            f"orphaned draft variables and {stats['total_orphaned_files']} associated files "
+            f"from {stats['orphaned_app_count']} apps?",
             abort=True,
         )
 
@@ -1352,3 +1422,480 @@ def cleanup_orphaned_draft_variables(
                 continue
 
     logger.info("Cleanup completed. Total deleted: %s variables across %s apps", total_deleted, processed_apps)
+
+
+@click.command("setup-datasource-oauth-client", help="Setup datasource oauth client.")
+@click.option("--provider", prompt=True, help="Provider name")
+@click.option("--client-params", prompt=True, help="Client Params")
+def setup_datasource_oauth_client(provider, client_params):
+    """
+    Setup datasource oauth client
+    """
+    provider_id = DatasourceProviderID(provider)
+    provider_name = provider_id.provider_name
+    plugin_id = provider_id.plugin_id
+
+    try:
+        # json validate
+        click.echo(click.style(f"Validating client params: {client_params}", fg="yellow"))
+        client_params_dict = TypeAdapter(dict[str, Any]).validate_json(client_params)
+        click.echo(click.style("Client params validated successfully.", fg="green"))
+    except Exception as e:
+        click.echo(click.style(f"Error parsing client params: {str(e)}", fg="red"))
+        return
+
+    click.echo(click.style(f"Ready to delete existing oauth client params: {provider_name}", fg="yellow"))
+    deleted_count = (
+        db.session.query(DatasourceOauthParamConfig)
+        .filter_by(
+            provider=provider_name,
+            plugin_id=plugin_id,
+        )
+        .delete()
+    )
+    if deleted_count > 0:
+        click.echo(click.style(f"Deleted {deleted_count} existing oauth client params.", fg="yellow"))
+
+    click.echo(click.style(f"Ready to setup datasource oauth client: {provider_name}", fg="yellow"))
+    oauth_client = DatasourceOauthParamConfig(
+        provider=provider_name,
+        plugin_id=plugin_id,
+        system_credentials=client_params_dict,
+    )
+    db.session.add(oauth_client)
+    db.session.commit()
+    click.echo(click.style(f"provider: {provider_name}", fg="green"))
+    click.echo(click.style(f"plugin_id: {plugin_id}", fg="green"))
+    click.echo(click.style(f"params: {json.dumps(client_params_dict, indent=2, ensure_ascii=False)}", fg="green"))
+    click.echo(click.style(f"Datasource oauth client setup successfully. id: {oauth_client.id}", fg="green"))
+
+
+@click.command("transform-datasource-credentials", help="Transform datasource credentials.")
+@click.option(
+    "--environment", prompt=True, help="the environment to transform datasource credentials", default="online"
+)
+def transform_datasource_credentials(environment: str):
+    """
+    Transform datasource credentials
+    """
+    try:
+        installer_manager = PluginInstaller()
+        plugin_migration = PluginMigration()
+
+        notion_plugin_id = "langgenius/notion_datasource"
+        firecrawl_plugin_id = "langgenius/firecrawl_datasource"
+        jina_plugin_id = "langgenius/jina_datasource"
+        if environment == "online":
+            notion_plugin_unique_identifier = plugin_migration._fetch_plugin_unique_identifier(notion_plugin_id)  # pyright: ignore[reportPrivateUsage]
+            firecrawl_plugin_unique_identifier = plugin_migration._fetch_plugin_unique_identifier(firecrawl_plugin_id)  # pyright: ignore[reportPrivateUsage]
+            jina_plugin_unique_identifier = plugin_migration._fetch_plugin_unique_identifier(jina_plugin_id)  # pyright: ignore[reportPrivateUsage]
+        else:
+            notion_plugin_unique_identifier = None
+            firecrawl_plugin_unique_identifier = None
+            jina_plugin_unique_identifier = None
+        oauth_credential_type = CredentialType.OAUTH2
+        api_key_credential_type = CredentialType.API_KEY
+
+        # deal notion credentials
+        deal_notion_count = 0
+        notion_credentials = db.session.query(DataSourceOauthBinding).filter_by(provider="notion").all()
+        if notion_credentials:
+            notion_credentials_tenant_mapping: dict[str, list[DataSourceOauthBinding]] = {}
+            for notion_credential in notion_credentials:
+                tenant_id = notion_credential.tenant_id
+                if tenant_id not in notion_credentials_tenant_mapping:
+                    notion_credentials_tenant_mapping[tenant_id] = []
+                notion_credentials_tenant_mapping[tenant_id].append(notion_credential)
+            for tenant_id, notion_tenant_credentials in notion_credentials_tenant_mapping.items():
+                tenant = db.session.query(Tenant).filter_by(id=tenant_id).first()
+                if not tenant:
+                    continue
+                try:
+                    # check notion plugin is installed
+                    installed_plugins = installer_manager.list_plugins(tenant_id)
+                    installed_plugins_ids = [plugin.plugin_id for plugin in installed_plugins]
+                    if notion_plugin_id not in installed_plugins_ids:
+                        if notion_plugin_unique_identifier:
+                            # install notion plugin
+                            PluginService.install_from_marketplace_pkg(tenant_id, [notion_plugin_unique_identifier])
+                    auth_count = 0
+                    for notion_tenant_credential in notion_tenant_credentials:
+                        auth_count += 1
+                        # get credential oauth params
+                        access_token = notion_tenant_credential.access_token
+                        # notion info
+                        notion_info = notion_tenant_credential.source_info
+                        workspace_id = notion_info.get("workspace_id")
+                        workspace_name = notion_info.get("workspace_name")
+                        workspace_icon = notion_info.get("workspace_icon")
+                        new_credentials = {
+                            "integration_secret": encrypter.encrypt_token(tenant_id, access_token),
+                            "workspace_id": workspace_id,
+                            "workspace_name": workspace_name,
+                            "workspace_icon": workspace_icon,
+                        }
+                        datasource_provider = DatasourceProvider(
+                            provider="notion_datasource",
+                            tenant_id=tenant_id,
+                            plugin_id=notion_plugin_id,
+                            auth_type=oauth_credential_type.value,
+                            encrypted_credentials=new_credentials,
+                            name=f"Auth {auth_count}",
+                            avatar_url=workspace_icon or "default",
+                            is_default=False,
+                        )
+                        db.session.add(datasource_provider)
+                        deal_notion_count += 1
+                except Exception as e:
+                    click.echo(
+                        click.style(
+                            f"Error transforming notion credentials: {str(e)}, tenant_id: {tenant_id}", fg="red"
+                        )
+                    )
+                    continue
+                db.session.commit()
+        # deal firecrawl credentials
+        deal_firecrawl_count = 0
+        firecrawl_credentials = db.session.query(DataSourceApiKeyAuthBinding).filter_by(provider="firecrawl").all()
+        if firecrawl_credentials:
+            firecrawl_credentials_tenant_mapping: dict[str, list[DataSourceApiKeyAuthBinding]] = {}
+            for firecrawl_credential in firecrawl_credentials:
+                tenant_id = firecrawl_credential.tenant_id
+                if tenant_id not in firecrawl_credentials_tenant_mapping:
+                    firecrawl_credentials_tenant_mapping[tenant_id] = []
+                firecrawl_credentials_tenant_mapping[tenant_id].append(firecrawl_credential)
+            for tenant_id, firecrawl_tenant_credentials in firecrawl_credentials_tenant_mapping.items():
+                tenant = db.session.query(Tenant).filter_by(id=tenant_id).first()
+                if not tenant:
+                    continue
+                try:
+                    # check firecrawl plugin is installed
+                    installed_plugins = installer_manager.list_plugins(tenant_id)
+                    installed_plugins_ids = [plugin.plugin_id for plugin in installed_plugins]
+                    if firecrawl_plugin_id not in installed_plugins_ids:
+                        if firecrawl_plugin_unique_identifier:
+                            # install firecrawl plugin
+                            PluginService.install_from_marketplace_pkg(tenant_id, [firecrawl_plugin_unique_identifier])
+
+                    auth_count = 0
+                    for firecrawl_tenant_credential in firecrawl_tenant_credentials:
+                        auth_count += 1
+                        if not firecrawl_tenant_credential.credentials:
+                            click.echo(
+                                click.style(
+                                    f"Skipping firecrawl credential for tenant {tenant_id} due to missing credentials.",
+                                    fg="yellow",
+                                )
+                            )
+                            continue
+                        # get credential api key
+                        credentials_json = json.loads(firecrawl_tenant_credential.credentials)
+                        api_key = credentials_json.get("config", {}).get("api_key")
+                        base_url = credentials_json.get("config", {}).get("base_url")
+                        new_credentials = {
+                            "firecrawl_api_key": api_key,
+                            "base_url": base_url,
+                        }
+                        datasource_provider = DatasourceProvider(
+                            provider="firecrawl",
+                            tenant_id=tenant_id,
+                            plugin_id=firecrawl_plugin_id,
+                            auth_type=api_key_credential_type.value,
+                            encrypted_credentials=new_credentials,
+                            name=f"Auth {auth_count}",
+                            avatar_url="default",
+                            is_default=False,
+                        )
+                        db.session.add(datasource_provider)
+                        deal_firecrawl_count += 1
+                except Exception as e:
+                    click.echo(
+                        click.style(
+                            f"Error transforming firecrawl credentials: {str(e)}, tenant_id: {tenant_id}", fg="red"
+                        )
+                    )
+                    continue
+                db.session.commit()
+        # deal jina credentials
+        deal_jina_count = 0
+        jina_credentials = db.session.query(DataSourceApiKeyAuthBinding).filter_by(provider="jinareader").all()
+        if jina_credentials:
+            jina_credentials_tenant_mapping: dict[str, list[DataSourceApiKeyAuthBinding]] = {}
+            for jina_credential in jina_credentials:
+                tenant_id = jina_credential.tenant_id
+                if tenant_id not in jina_credentials_tenant_mapping:
+                    jina_credentials_tenant_mapping[tenant_id] = []
+                jina_credentials_tenant_mapping[tenant_id].append(jina_credential)
+            for tenant_id, jina_tenant_credentials in jina_credentials_tenant_mapping.items():
+                tenant = db.session.query(Tenant).filter_by(id=tenant_id).first()
+                if not tenant:
+                    continue
+                try:
+                    # check jina plugin is installed
+                    installed_plugins = installer_manager.list_plugins(tenant_id)
+                    installed_plugins_ids = [plugin.plugin_id for plugin in installed_plugins]
+                    if jina_plugin_id not in installed_plugins_ids:
+                        if jina_plugin_unique_identifier:
+                            # install jina plugin
+                            logger.debug("Installing Jina plugin %s", jina_plugin_unique_identifier)
+                            PluginService.install_from_marketplace_pkg(tenant_id, [jina_plugin_unique_identifier])
+
+                    auth_count = 0
+                    for jina_tenant_credential in jina_tenant_credentials:
+                        auth_count += 1
+                        if not jina_tenant_credential.credentials:
+                            click.echo(
+                                click.style(
+                                    f"Skipping jina credential for tenant {tenant_id} due to missing credentials.",
+                                    fg="yellow",
+                                )
+                            )
+                            continue
+                        # get credential api key
+                        credentials_json = json.loads(jina_tenant_credential.credentials)
+                        api_key = credentials_json.get("config", {}).get("api_key")
+                        new_credentials = {
+                            "integration_secret": api_key,
+                        }
+                        datasource_provider = DatasourceProvider(
+                            provider="jinareader",
+                            tenant_id=tenant_id,
+                            plugin_id=jina_plugin_id,
+                            auth_type=api_key_credential_type.value,
+                            encrypted_credentials=new_credentials,
+                            name=f"Auth {auth_count}",
+                            avatar_url="default",
+                            is_default=False,
+                        )
+                        db.session.add(datasource_provider)
+                        deal_jina_count += 1
+                except Exception as e:
+                    click.echo(
+                        click.style(f"Error transforming jina credentials: {str(e)}, tenant_id: {tenant_id}", fg="red")
+                    )
+                    continue
+                db.session.commit()
+    except Exception as e:
+        click.echo(click.style(f"Error parsing client params: {str(e)}", fg="red"))
+        return
+    click.echo(click.style(f"Transforming notion successfully. deal_notion_count: {deal_notion_count}", fg="green"))
+    click.echo(
+        click.style(f"Transforming firecrawl successfully. deal_firecrawl_count: {deal_firecrawl_count}", fg="green")
+    )
+    click.echo(click.style(f"Transforming jina successfully. deal_jina_count: {deal_jina_count}", fg="green"))
+
+
+@click.command("install-rag-pipeline-plugins", help="Install rag pipeline plugins.")
+@click.option(
+    "--input_file", prompt=True, help="The file to store the extracted unique identifiers.", default="plugins.jsonl"
+)
+@click.option(
+    "--output_file", prompt=True, help="The file to store the installed plugins.", default="installed_plugins.jsonl"
+)
+@click.option("--workers", prompt=True, help="The number of workers to install plugins.", default=100)
+def install_rag_pipeline_plugins(input_file, output_file, workers):
+    """
+    Install rag pipeline plugins
+    """
+    click.echo(click.style("Installing rag pipeline plugins", fg="yellow"))
+    plugin_migration = PluginMigration()
+    plugin_migration.install_rag_pipeline_plugins(
+        input_file,
+        output_file,
+        workers,
+    )
+    click.echo(click.style("Installing rag pipeline plugins successfully", fg="green"))
+
+
+@click.command(
+    "migrate-oss",
+    help="Migrate files from Local or OpenDAL source to a cloud OSS storage (destination must NOT be local/opendal).",
+)
+@click.option(
+    "--path",
+    "paths",
+    multiple=True,
+    help="Storage path prefixes to migrate (repeatable). Defaults: privkeys, upload_files, image_files,"
+    " tools, website_files, keyword_files, ops_trace",
+)
+@click.option(
+    "--source",
+    type=click.Choice(["local", "opendal"], case_sensitive=False),
+    default="opendal",
+    show_default=True,
+    help="Source storage type to read from",
+)
+@click.option("--overwrite", is_flag=True, default=False, help="Overwrite destination if file already exists")
+@click.option("--dry-run", is_flag=True, default=False, help="Show what would be migrated without uploading")
+@click.option("-f", "--force", is_flag=True, help="Skip confirmation and run without prompts")
+@click.option(
+    "--update-db/--no-update-db",
+    default=True,
+    help="Update upload_files.storage_type from source type to current storage after migration",
+)
+def migrate_oss(
+    paths: tuple[str, ...],
+    source: str,
+    overwrite: bool,
+    dry_run: bool,
+    force: bool,
+    update_db: bool,
+):
+    """
+    Copy all files under selected prefixes from a source storage
+    (Local filesystem or OpenDAL-backed) into the currently configured
+    destination storage backend, then optionally update DB records.
+
+    Expected usage: set STORAGE_TYPE (and its credentials) to your target backend.
+    """
+    # Ensure target storage is not local/opendal
+    if dify_config.STORAGE_TYPE in (StorageType.LOCAL, StorageType.OPENDAL):
+        click.echo(
+            click.style(
+                "Target STORAGE_TYPE must be a cloud OSS (not 'local' or 'opendal').\n"
+                "Please set STORAGE_TYPE to one of: s3, aliyun-oss, azure-blob, google-storage, tencent-cos, \n"
+                "volcengine-tos, supabase, oci-storage, huawei-obs, baidu-obs, clickzetta-volume.",
+                fg="red",
+            )
+        )
+        return
+
+    # Default paths if none specified
+    default_paths = ("privkeys", "upload_files", "image_files", "tools", "website_files", "keyword_files", "ops_trace")
+    path_list = list(paths) if paths else list(default_paths)
+    is_source_local = source.lower() == "local"
+
+    click.echo(click.style("Preparing migration to target storage.", fg="yellow"))
+    click.echo(click.style(f"Target storage type: {dify_config.STORAGE_TYPE}", fg="white"))
+    if is_source_local:
+        src_root = dify_config.STORAGE_LOCAL_PATH
+        click.echo(click.style(f"Source: local fs, root: {src_root}", fg="white"))
+    else:
+        click.echo(click.style(f"Source: opendal scheme={dify_config.OPENDAL_SCHEME}", fg="white"))
+    click.echo(click.style(f"Paths to migrate: {', '.join(path_list)}", fg="white"))
+    click.echo("")
+
+    if not force:
+        click.confirm("Proceed with migration?", abort=True)
+
+    # Instantiate source storage
+    try:
+        if is_source_local:
+            src_root = dify_config.STORAGE_LOCAL_PATH
+            source_storage = OpenDALStorage(scheme="fs", root=src_root)
+        else:
+            source_storage = OpenDALStorage(scheme=dify_config.OPENDAL_SCHEME)
+    except Exception as e:
+        click.echo(click.style(f"Failed to initialize source storage: {str(e)}", fg="red"))
+        return
+
+    total_files = 0
+    copied_files = 0
+    skipped_files = 0
+    errored_files = 0
+    copied_upload_file_keys: list[str] = []
+
+    for prefix in path_list:
+        click.echo(click.style(f"Scanning source path: {prefix}", fg="white"))
+        try:
+            keys = source_storage.scan(path=prefix, files=True, directories=False)
+        except FileNotFoundError:
+            click.echo(click.style(f"  -> Skipping missing path: {prefix}", fg="yellow"))
+            continue
+        except NotImplementedError:
+            click.echo(click.style("  -> Source storage does not support scanning.", fg="red"))
+            return
+        except Exception as e:
+            click.echo(click.style(f"  -> Error scanning '{prefix}': {str(e)}", fg="red"))
+            continue
+
+        click.echo(click.style(f"Found {len(keys)} files under {prefix}", fg="white"))
+
+        for key in keys:
+            total_files += 1
+
+            # check destination existence
+            if not overwrite:
+                try:
+                    if storage.exists(key):
+                        skipped_files += 1
+                        continue
+                except Exception as e:
+                    # existence check failures should not block migration attempt
+                    # but should be surfaced to user as a warning for visibility
+                    click.echo(
+                        click.style(
+                            f"  -> Warning: failed target existence check for {key}: {str(e)}",
+                            fg="yellow",
+                        )
+                    )
+
+            if dry_run:
+                copied_files += 1
+                continue
+
+            # read from source and write to destination
+            try:
+                data = source_storage.load_once(key)
+            except FileNotFoundError:
+                errored_files += 1
+                click.echo(click.style(f"  -> Missing on source: {key}", fg="yellow"))
+                continue
+            except Exception as e:
+                errored_files += 1
+                click.echo(click.style(f"  -> Error reading {key}: {str(e)}", fg="red"))
+                continue
+
+            try:
+                storage.save(key, data)
+                copied_files += 1
+                if prefix == "upload_files":
+                    copied_upload_file_keys.append(key)
+            except Exception as e:
+                errored_files += 1
+                click.echo(click.style(f"  -> Error writing {key} to target: {str(e)}", fg="red"))
+                continue
+
+    click.echo("")
+    click.echo(click.style("Migration summary:", fg="yellow"))
+    click.echo(click.style(f"  Total:   {total_files}", fg="white"))
+    click.echo(click.style(f"  Copied:  {copied_files}", fg="green"))
+    click.echo(click.style(f"  Skipped: {skipped_files}", fg="white"))
+    if errored_files:
+        click.echo(click.style(f"  Errors:  {errored_files}", fg="red"))
+
+    if dry_run:
+        click.echo(click.style("Dry-run complete. No changes were made.", fg="green"))
+        return
+
+    if errored_files:
+        click.echo(
+            click.style(
+                "Some files failed to migrate. Review errors above before updating DB records.",
+                fg="yellow",
+            )
+        )
+        if update_db and not force:
+            if not click.confirm("Proceed to update DB storage_type despite errors?", default=False):
+                update_db = False
+
+    # Optionally update DB records for upload_files.storage_type (only for successfully copied upload_files)
+    if update_db:
+        if not copied_upload_file_keys:
+            click.echo(click.style("No upload_files copied. Skipping DB storage_type update.", fg="yellow"))
+        else:
+            try:
+                source_storage_type = StorageType.LOCAL if is_source_local else StorageType.OPENDAL
+                updated = (
+                    db.session.query(UploadFile)
+                    .where(
+                        UploadFile.storage_type == source_storage_type,
+                        UploadFile.key.in_(copied_upload_file_keys),
+                    )
+                    .update({UploadFile.storage_type: dify_config.STORAGE_TYPE}, synchronize_session=False)
+                )
+                db.session.commit()
+                click.echo(click.style(f"Updated storage_type for {updated} upload_files records.", fg="green"))
+            except Exception as e:
+                db.session.rollback()
+                click.echo(click.style(f"Failed to update DB storage_type: {str(e)}", fg="red"))

api/configs/__init__.py

@@ -1,3 +1,3 @@
 from .app_config import DifyConfig
 
-dify_config = DifyConfig()
+dify_config = DifyConfig()  # type: ignore

api/configs/extra/notion_config.py

@@ -1,5 +1,3 @@
-from typing import Optional
-
 from pydantic import Field
 from pydantic_settings import BaseSettings
 
@@ -9,28 +7,28 @@ class NotionConfig(BaseSettings):
     Configuration settings for Notion integration
     """
 
-    NOTION_CLIENT_ID: Optional[str] = Field(
+    NOTION_CLIENT_ID: str | None = Field(
         description="Client ID for Notion API authentication. Required for OAuth 2.0 flow.",
         default=None,
     )
 
-    NOTION_CLIENT_SECRET: Optional[str] = Field(
+    NOTION_CLIENT_SECRET: str | None = Field(
         description="Client secret for Notion API authentication. Required for OAuth 2.0 flow.",
         default=None,
     )
 
-    NOTION_INTEGRATION_TYPE: Optional[str] = Field(
+    NOTION_INTEGRATION_TYPE: str | None = Field(
         description="Type of Notion integration."
         " Set to 'internal' for internal integrations, or None for public integrations.",
         default=None,
     )
 
-    NOTION_INTERNAL_SECRET: Optional[str] = Field(
+    NOTION_INTERNAL_SECRET: str | None = Field(
         description="Secret key for internal Notion integrations. Required when NOTION_INTEGRATION_TYPE is 'internal'.",
         default=None,
     )
 
-    NOTION_INTEGRATION_TOKEN: Optional[str] = Field(
+    NOTION_INTEGRATION_TOKEN: str | None = Field(
         description="Integration token for Notion API access. Used for direct API calls without OAuth flow.",
         default=None,
     )

api/configs/extra/sentry_config.py

@@ -1,5 +1,3 @@
-from typing import Optional
-
 from pydantic import Field, NonNegativeFloat
 from pydantic_settings import BaseSettings
 
@@ -9,7 +7,7 @@ class SentryConfig(BaseSettings):
     Configuration settings for Sentry error tracking and performance monitoring
     """
 
-    SENTRY_DSN: Optional[str] = Field(
+    SENTRY_DSN: str | None = Field(
         description="Sentry Data Source Name (DSN)."
         " This is the unique identifier of your Sentry project, used to send events to the correct project.",
         default=None,

api/configs/feature/__init__.py

@@ -1,4 +1,5 @@
-from typing import Literal, Optional
+from enum import StrEnum
+from typing import Literal
 
 from pydantic import (
     AliasChoices,
@@ -57,7 +58,7 @@ class SecurityConfig(BaseSettings):
         default=False,
     )
 
-    ADMIN_API_KEY: Optional[str] = Field(
+    ADMIN_API_KEY: str | None = Field(
         description="admin api key for authentication",
         default=None,
     )
@@ -76,10 +77,6 @@ class AppExecutionConfig(BaseSettings):
         description="Maximum number of concurrent active requests per app (0 for unlimited)",
         default=0,
     )
-    APP_DAILY_RATE_LIMIT: NonNegativeInt = Field(
-        description="Maximum number of requests per app per day",
-        default=5000,
-    )
 
 
 class CodeExecutionSandboxConfig(BaseSettings):
@@ -97,21 +94,36 @@ class CodeExecutionSandboxConfig(BaseSettings):
         default="dify-sandbox",
     )
 
-    CODE_EXECUTION_CONNECT_TIMEOUT: Optional[float] = Field(
+    CODE_EXECUTION_CONNECT_TIMEOUT: float | None = Field(
         description="Connection timeout in seconds for code execution requests",
         default=10.0,
     )
 
-    CODE_EXECUTION_READ_TIMEOUT: Optional[float] = Field(
+    CODE_EXECUTION_READ_TIMEOUT: float | None = Field(
         description="Read timeout in seconds for code execution requests",
         default=60.0,
     )
 
-    CODE_EXECUTION_WRITE_TIMEOUT: Optional[float] = Field(
+    CODE_EXECUTION_WRITE_TIMEOUT: float | None = Field(
         description="Write timeout in seconds for code execution request",
         default=10.0,
     )
 
+    CODE_EXECUTION_POOL_MAX_CONNECTIONS: PositiveInt = Field(
+        description="Maximum number of concurrent connections for the code execution HTTP client",
+        default=100,
+    )
+
+    CODE_EXECUTION_POOL_MAX_KEEPALIVE_CONNECTIONS: PositiveInt = Field(
+        description="Maximum number of persistent keep-alive connections for the code execution HTTP client",
+        default=20,
+    )
+
+    CODE_EXECUTION_POOL_KEEPALIVE_EXPIRY: PositiveFloat | None = Field(
+        description="Keep-alive expiry in seconds for idle connections (set to None to disable)",
+        default=5.0,
+    )
+
     CODE_MAX_NUMBER: PositiveInt = Field(
         description="Maximum allowed numeric value in code execution",
         default=9223372036854775807,
@@ -134,7 +146,7 @@ class CodeExecutionSandboxConfig(BaseSettings):
 
     CODE_MAX_STRING_LENGTH: PositiveInt = Field(
         description="Maximum allowed length for strings in code execution",
-        default=80000,
+        default=400_000,
     )
 
     CODE_MAX_STRING_ARRAY_LENGTH: PositiveInt = Field(
@@ -152,6 +164,38 @@ class CodeExecutionSandboxConfig(BaseSettings):
         default=1000,
     )
 
+    CODE_EXECUTION_SSL_VERIFY: bool = Field(
+        description="Enable or disable SSL verification for code execution requests",
+        default=True,
+    )
+
+
+class TriggerConfig(BaseSettings):
+    """
+    Configuration for trigger
+    """
+
+    WEBHOOK_REQUEST_BODY_MAX_SIZE: PositiveInt = Field(
+        description="Maximum allowed size for webhook request bodies in bytes",
+        default=10485760,
+    )
+
+
+class AsyncWorkflowConfig(BaseSettings):
+    """
+    Configuration for async workflow
+    """
+
+    ASYNC_WORKFLOW_SCHEDULER_GRANULARITY: int = Field(
+        description="Granularity for async workflow scheduler, "
+        "sometime, few users could block the queue due to some time-consuming tasks, "
+        "to avoid this, workflow can be suspended if needed, to achieve"
+        "this, a time-based checker is required, every granularity seconds, "
+        "the checker will check the workflow queue and suspend the workflow",
+        default=120,
+        ge=1,
+    )
+
 
 class PluginConfig(BaseSettings):
     """
@@ -168,6 +212,11 @@ class PluginConfig(BaseSettings):
         default="plugin-api-key",
     )
 
+    PLUGIN_DAEMON_TIMEOUT: PositiveFloat | None = Field(
+        description="Timeout in seconds for requests to the plugin daemon (set to None to disable)",
+        default=300.0,
+    )
+
     INNER_API_KEY_FOR_PLUGIN: str = Field(description="Inner api key for plugin", default="inner-api-key")
 
     PLUGIN_REMOTE_INSTALL_HOST: str = Field(
@@ -237,6 +286,8 @@ class EndpointConfig(BaseSettings):
         description="Template url for endpoint plugin", default="http://localhost:5002/e/{hook_id}"
     )
 
+    TRIGGER_URL: str = Field(description="Template url for triggers", default="http://localhost:5001")
+
 
 class FileAccessConfig(BaseSettings):
     """
@@ -305,12 +356,42 @@ class FileUploadConfig(BaseSettings):
         default=10,
     )
 
+    inner_UPLOAD_FILE_EXTENSION_BLACKLIST: str = Field(
+        description=(
+            "Comma-separated list of file extensions that are blocked from upload. "
+            "Extensions should be lowercase without dots (e.g., 'exe,bat,sh,dll'). "
+            "Empty by default to allow all file types."
+        ),
+        validation_alias=AliasChoices("UPLOAD_FILE_EXTENSION_BLACKLIST"),
+        default="",
+    )
+
+    @computed_field  # type: ignore[misc]
+    @property
+    def UPLOAD_FILE_EXTENSION_BLACKLIST(self) -> set[str]:
+        """
+        Parse and return the blacklist as a set of lowercase extensions.
+        Returns an empty set if no blacklist is configured.
+        """
+        if not self.inner_UPLOAD_FILE_EXTENSION_BLACKLIST:
+            return set()
+        return {
+            ext.strip().lower().strip(".")
+            for ext in self.inner_UPLOAD_FILE_EXTENSION_BLACKLIST.split(",")
+            if ext.strip()
+        }
+
 
 class HttpConfig(BaseSettings):
     """
     HTTP-related configurations for the application
     """
 
+    COOKIE_DOMAIN: str = Field(
+        description="Explicit cookie domain for console/service cookies when sharing across subdomains",
+        default="",
+    )
+
     API_COMPRESSION_ENABLED: bool = Field(
         description="Enable or disable gzip compression for HTTP responses",
         default=False,
@@ -341,11 +422,11 @@ class HttpConfig(BaseSettings):
     )
 
     HTTP_REQUEST_MAX_READ_TIMEOUT: int = Field(
-        ge=1, description="Maximum read timeout in seconds for HTTP requests", default=60
+        ge=1, description="Maximum read timeout in seconds for HTTP requests", default=600
     )
 
     HTTP_REQUEST_MAX_WRITE_TIMEOUT: int = Field(
-        ge=1, description="Maximum write timeout in seconds for HTTP requests", default=20
+        ge=1, description="Maximum write timeout in seconds for HTTP requests", default=600
     )
 
     HTTP_REQUEST_NODE_MAX_BINARY_SIZE: PositiveInt = Field(
@@ -368,17 +449,17 @@ class HttpConfig(BaseSettings):
         default=3,
     )
 
-    SSRF_PROXY_ALL_URL: Optional[str] = Field(
+    SSRF_PROXY_ALL_URL: str | None = Field(
         description="Proxy URL for HTTP or HTTPS requests to prevent Server-Side Request Forgery (SSRF)",
         default=None,
     )
 
-    SSRF_PROXY_HTTP_URL: Optional[str] = Field(
+    SSRF_PROXY_HTTP_URL: str | None = Field(
         description="Proxy URL for HTTP requests to prevent Server-Side Request Forgery (SSRF)",
         default=None,
     )
 
-    SSRF_PROXY_HTTPS_URL: Optional[str] = Field(
+    SSRF_PROXY_HTTPS_URL: str | None = Field(
         description="Proxy URL for HTTPS requests to prevent Server-Side Request Forgery (SSRF)",
         default=None,
     )
@@ -403,6 +484,21 @@ class HttpConfig(BaseSettings):
         default=5,
     )
 
+    SSRF_POOL_MAX_CONNECTIONS: PositiveInt = Field(
+        description="Maximum number of concurrent connections for the SSRF HTTP client",
+        default=100,
+    )
+
+    SSRF_POOL_MAX_KEEPALIVE_CONNECTIONS: PositiveInt = Field(
+        description="Maximum number of persistent keep-alive connections for the SSRF HTTP client",
+        default=20,
+    )
+
+    SSRF_POOL_KEEPALIVE_EXPIRY: PositiveFloat | None = Field(
+        description="Keep-alive expiry in seconds for idle SSRF connections (set to None to disable)",
+        default=5.0,
+    )
+
     RESPECT_XFORWARD_HEADERS_ENABLED: bool = Field(
         description="Enable handling of X-Forwarded-For, X-Forwarded-Proto, and X-Forwarded-Port headers"
         " when the app is behind a single trusted reverse proxy.",
@@ -420,7 +516,7 @@ class InnerAPIConfig(BaseSettings):
         default=False,
     )
 
-    INNER_API_KEY: Optional[str] = Field(
+    INNER_API_KEY: str | None = Field(
         description="API key for accessing the internal API",
         default=None,
     )
@@ -436,7 +532,7 @@ class LoggingConfig(BaseSettings):
         default="INFO",
     )
 
-    LOG_FILE: Optional[str] = Field(
+    LOG_FILE: str | None = Field(
         description="File path for log output.",
         default=None,
     )
@@ -456,12 +552,12 @@ class LoggingConfig(BaseSettings):
         default="%(asctime)s.%(msecs)03d %(levelname)s [%(threadName)s] [%(filename)s:%(lineno)d] - %(message)s",
     )
 
-    LOG_DATEFORMAT: Optional[str] = Field(
+    LOG_DATEFORMAT: str | None = Field(
         description="Date format string for log timestamps",
         default=None,
     )
 
-    LOG_TZ: Optional[str] = Field(
+    LOG_TZ: str | None = Field(
         description="Timezone for log timestamps (e.g., 'America/New_York')",
         default="UTC",
     )
@@ -505,6 +601,22 @@ class UpdateConfig(BaseSettings):
     )
 
 
+class WorkflowVariableTruncationConfig(BaseSettings):
+    WORKFLOW_VARIABLE_TRUNCATION_MAX_SIZE: PositiveInt = Field(
+        # 1000 KiB
+        1024_000,
+        description="Maximum size for variable to trigger final truncation.",
+    )
+    WORKFLOW_VARIABLE_TRUNCATION_STRING_LENGTH: PositiveInt = Field(
+        100000,
+        description="maximum length for string to trigger tuncation, measure in number of characters",
+    )
+    WORKFLOW_VARIABLE_TRUNCATION_ARRAY_LENGTH: PositiveInt = Field(
+        1000,
+        description="maximum length for array to trigger truncation.",
+    )
+
+
 class WorkflowConfig(BaseSettings):
     """
     Configuration for workflow execution
@@ -525,16 +637,38 @@ class WorkflowConfig(BaseSettings):
         default=5,
     )
 
-    WORKFLOW_PARALLEL_DEPTH_LIMIT: PositiveInt = Field(
-        description="Maximum allowed depth for nested parallel executions",
-        default=3,
-    )
-
     MAX_VARIABLE_SIZE: PositiveInt = Field(
         description="Maximum size in bytes for a single variable in workflows. Default to 200 KB.",
         default=200 * 1024,
     )
 
+    TEMPLATE_TRANSFORM_MAX_LENGTH: PositiveInt = Field(
+        description="Maximum number of characters allowed in Template Transform node output",
+        default=400_000,
+    )
+
+    # GraphEngine Worker Pool Configuration
+    GRAPH_ENGINE_MIN_WORKERS: PositiveInt = Field(
+        description="Minimum number of workers per GraphEngine instance",
+        default=1,
+    )
+
+    GRAPH_ENGINE_MAX_WORKERS: PositiveInt = Field(
+        description="Maximum number of workers per GraphEngine instance",
+        default=10,
+    )
+
+    GRAPH_ENGINE_SCALE_UP_THRESHOLD: PositiveInt = Field(
+        description="Queue depth threshold that triggers worker scale up",
+        default=3,
+    )
+
+    GRAPH_ENGINE_SCALE_DOWN_IDLE_TIME: float = Field(
+        description="Seconds of idle time before scaling down workers",
+        default=5.0,
+        ge=0.1,
+    )
+
 
 class WorkflowNodeExecutionConfig(BaseSettings):
     """
@@ -595,22 +729,22 @@ class AuthConfig(BaseSettings):
         default="/console/api/oauth/authorize",
     )
 
-    GITHUB_CLIENT_ID: Optional[str] = Field(
+    GITHUB_CLIENT_ID: str | None = Field(
         description="GitHub OAuth client ID",
         default=None,
     )
 
-    GITHUB_CLIENT_SECRET: Optional[str] = Field(
+    GITHUB_CLIENT_SECRET: str | None = Field(
         description="GitHub OAuth client secret",
         default=None,
     )
 
-    GOOGLE_CLIENT_ID: Optional[str] = Field(
+    GOOGLE_CLIENT_ID: str | None = Field(
         description="Google OAuth client ID",
         default=None,
     )
 
-    GOOGLE_CLIENT_SECRET: Optional[str] = Field(
+    GOOGLE_CLIENT_SECRET: str | None = Field(
         description="Google OAuth client secret",
         default=None,
     )
@@ -673,47 +807,71 @@ class ToolConfig(BaseSettings):
     )
 
 
+class TemplateMode(StrEnum):
+    # unsafe mode allows flexible operations in templates, but may cause security vulnerabilities
+    UNSAFE = "unsafe"
+
+    # sandbox mode restricts some unsafe operations like accessing __class__.
+    # however, it is still not 100% safe, for example, cpu exploitation can happen.
+    SANDBOX = "sandbox"
+
+    # templating is disabled
+    DISABLED = "disabled"
+
+
 class MailConfig(BaseSettings):
     """
     Configuration for email services
     """
 
-    MAIL_TYPE: Optional[str] = Field(
+    MAIL_TEMPLATING_MODE: TemplateMode = Field(
+        description="Template mode for email services",
+        default=TemplateMode.SANDBOX,
+    )
+
+    MAIL_TEMPLATING_TIMEOUT: int = Field(
+        description="""
+        Timeout for email templating in seconds. Used to prevent infinite loops in malicious templates.
+        Only available in sandbox mode.""",
+        default=3,
+    )
+
+    MAIL_TYPE: str | None = Field(
         description="Email service provider type ('smtp' or 'resend' or 'sendGrid), default to None.",
         default=None,
     )
 
-    MAIL_DEFAULT_SEND_FROM: Optional[str] = Field(
+    MAIL_DEFAULT_SEND_FROM: str | None = Field(
         description="Default email address to use as the sender",
         default=None,
     )
 
-    RESEND_API_KEY: Optional[str] = Field(
+    RESEND_API_KEY: str | None = Field(
         description="API key for Resend email service",
         default=None,
     )
 
-    RESEND_API_URL: Optional[str] = Field(
+    RESEND_API_URL: str | None = Field(
         description="API URL for Resend email service",
         default=None,
     )
 
-    SMTP_SERVER: Optional[str] = Field(
+    SMTP_SERVER: str | None = Field(
         description="SMTP server hostname",
         default=None,
     )
 
-    SMTP_PORT: Optional[int] = Field(
+    SMTP_PORT: int | None = Field(
         description="SMTP server port number",
         default=465,
     )
 
-    SMTP_USERNAME: Optional[str] = Field(
+    SMTP_USERNAME: str | None = Field(
         description="Username for SMTP authentication",
         default=None,
     )
 
-    SMTP_PASSWORD: Optional[str] = Field(
+    SMTP_PASSWORD: str | None = Field(
         description="Password for SMTP authentication",
         default=None,
     )
@@ -733,7 +891,7 @@ class MailConfig(BaseSettings):
         default=50,
     )
 
-    SENDGRID_API_KEY: Optional[str] = Field(
+    SENDGRID_API_KEY: str | None = Field(
         description="API key for SendGrid service",
         default=None,
     )
@@ -756,17 +914,17 @@ class RagEtlConfig(BaseSettings):
         default="database",
     )
 
-    UNSTRUCTURED_API_URL: Optional[str] = Field(
+    UNSTRUCTURED_API_URL: str | None = Field(
         description="API URL for Unstructured.io service",
         default=None,
     )
 
-    UNSTRUCTURED_API_KEY: Optional[str] = Field(
+    UNSTRUCTURED_API_KEY: str | None = Field(
         description="API key for Unstructured.io service",
         default="",
     )
 
-    SCARF_NO_ANALYTICS: Optional[str] = Field(
+    SCARF_NO_ANALYTICS: str | None = Field(
         description="This is about whether to disable Scarf analytics in Unstructured library.",
         default="false",
     )
@@ -812,6 +970,11 @@ class DataSetConfig(BaseSettings):
         default=True,
     )
 
+    DATASET_MAX_SEGMENTS_PER_REQUEST: NonNegativeInt = Field(
+        description="Maximum number of segments for dataset segments API (0 for unlimited)",
+        default=0,
+    )
+
 
 class WorkspaceConfig(BaseSettings):
     """
@@ -887,6 +1050,44 @@ class CeleryScheduleTasksConfig(BaseSettings):
         description="Enable check upgradable plugin task",
         default=True,
     )
+    ENABLE_WORKFLOW_SCHEDULE_POLLER_TASK: bool = Field(
+        description="Enable workflow schedule poller task",
+        default=True,
+    )
+    WORKFLOW_SCHEDULE_POLLER_INTERVAL: int = Field(
+        description="Workflow schedule poller interval in minutes",
+        default=1,
+    )
+    WORKFLOW_SCHEDULE_POLLER_BATCH_SIZE: int = Field(
+        description="Maximum number of schedules to process in each poll batch",
+        default=100,
+    )
+    WORKFLOW_SCHEDULE_MAX_DISPATCH_PER_TICK: int = Field(
+        description="Maximum schedules to dispatch per tick (0=unlimited, circuit breaker)",
+        default=0,
+    )
+
+    # Trigger provider refresh (simple version)
+    ENABLE_TRIGGER_PROVIDER_REFRESH_TASK: bool = Field(
+        description="Enable trigger provider refresh poller",
+        default=True,
+    )
+    TRIGGER_PROVIDER_REFRESH_INTERVAL: int = Field(
+        description="Trigger provider refresh poller interval in minutes",
+        default=1,
+    )
+    TRIGGER_PROVIDER_REFRESH_BATCH_SIZE: int = Field(
+        description="Max trigger subscriptions to process per tick",
+        default=200,
+    )
+    TRIGGER_PROVIDER_CREDENTIAL_THRESHOLD_SECONDS: int = Field(
+        description="Proactive credential refresh threshold in seconds",
+        default=60 * 60,
+    )
+    TRIGGER_PROVIDER_SUBSCRIPTION_THRESHOLD_SECONDS: int = Field(
+        description="Proactive subscription refresh threshold in seconds",
+        default=60 * 60,
+    )
 
 
 class PositionConfig(BaseSettings):
@@ -985,7 +1186,7 @@ class AccountConfig(BaseSettings):
 
 
 class WorkflowLogConfig(BaseSettings):
-    WORKFLOW_LOG_CLEANUP_ENABLED: bool = Field(default=True, description="Enable workflow run log cleanup")
+    WORKFLOW_LOG_CLEANUP_ENABLED: bool = Field(default=False, description="Enable workflow run log cleanup")
     WORKFLOW_LOG_RETENTION_DAYS: int = Field(default=30, description="Retention days for workflow run logs")
     WORKFLOW_LOG_CLEANUP_BATCH_SIZE: int = Field(
         default=100, description="Batch size for workflow run log cleanup operations"
@@ -1004,12 +1205,21 @@ class SwaggerUIConfig(BaseSettings):
     )
 
 
+class TenantIsolatedTaskQueueConfig(BaseSettings):
+    TENANT_ISOLATED_TASK_CONCURRENCY: int = Field(
+        description="Number of tasks allowed to be delivered concurrently from isolated queue per tenant",
+        default=1,
+    )
+
+
 class FeatureConfig(
     # place the configs in alphabet order
     AppExecutionConfig,
     AuthConfig,  # Changed from OAuthConfig to AuthConfig
     BillingConfig,
     CodeExecutionSandboxConfig,
+    TriggerConfig,
+    AsyncWorkflowConfig,
     PluginConfig,
     MarketplaceConfig,
     DataSetConfig,
@@ -1028,6 +1238,7 @@ class FeatureConfig(
     RagEtlConfig,
     RepositoryConfig,
     SecurityConfig,
+    TenantIsolatedTaskQueueConfig,
     ToolConfig,
     UpdateConfig,
     WorkflowConfig,
@@ -1041,5 +1252,6 @@ class FeatureConfig(
     CeleryBeatConfig,
     CeleryScheduleTasksConfig,
     WorkflowLogConfig,
+    WorkflowVariableTruncationConfig,
 ):
     pass

api/configs/feature/hosted_service/__init__.py

@@ -1,5 +1,3 @@
-from typing import Optional
-
 from pydantic import Field, NonNegativeInt
 from pydantic_settings import BaseSettings
 
@@ -40,17 +38,17 @@ class HostedOpenAiConfig(BaseSettings):
     Configuration for hosted OpenAI service
     """
 
-    HOSTED_OPENAI_API_KEY: Optional[str] = Field(
+    HOSTED_OPENAI_API_KEY: str | None = Field(
         description="API key for hosted OpenAI service",
         default=None,
     )
 
-    HOSTED_OPENAI_API_BASE: Optional[str] = Field(
+    HOSTED_OPENAI_API_BASE: str | None = Field(
         description="Base URL for hosted OpenAI API",
         default=None,
     )
 
-    HOSTED_OPENAI_API_ORGANIZATION: Optional[str] = Field(
+    HOSTED_OPENAI_API_ORGANIZATION: str | None = Field(
         description="Organization ID for hosted OpenAI service",
         default=None,
     )
@@ -110,12 +108,12 @@ class HostedAzureOpenAiConfig(BaseSettings):
         default=False,
     )
 
-    HOSTED_AZURE_OPENAI_API_KEY: Optional[str] = Field(
+    HOSTED_AZURE_OPENAI_API_KEY: str | None = Field(
         description="API key for hosted Azure OpenAI service",
         default=None,
     )
 
-    HOSTED_AZURE_OPENAI_API_BASE: Optional[str] = Field(
+    HOSTED_AZURE_OPENAI_API_BASE: str | None = Field(
         description="Base URL for hosted Azure OpenAI API",
         default=None,
     )
@@ -131,12 +129,12 @@ class HostedAnthropicConfig(BaseSettings):
     Configuration for hosted Anthropic service
     """
 
-    HOSTED_ANTHROPIC_API_BASE: Optional[str] = Field(
+    HOSTED_ANTHROPIC_API_BASE: str | None = Field(
         description="Base URL for hosted Anthropic API",
         default=None,
     )
 
-    HOSTED_ANTHROPIC_API_KEY: Optional[str] = Field(
+    HOSTED_ANTHROPIC_API_KEY: str | None = Field(
         description="API key for hosted Anthropic service",
         default=None,
     )
@@ -222,11 +220,28 @@ class HostedFetchAppTemplateConfig(BaseSettings):
     )
 
 
+class HostedFetchPipelineTemplateConfig(BaseSettings):
+    """
+    Configuration for fetching pipeline templates
+    """
+
+    HOSTED_FETCH_PIPELINE_TEMPLATES_MODE: str = Field(
+        description="Mode for fetching pipeline templates: remote, db, or builtin default to remote,",
+        default="remote",
+    )
+
+    HOSTED_FETCH_PIPELINE_TEMPLATES_REMOTE_DOMAIN: str = Field(
+        description="Domain for fetching remote pipeline templates",
+        default="https://tmpl.dify.ai",
+    )
+
+
 class HostedServiceConfig(
     # place the configs in alphabet order
     HostedAnthropicConfig,
     HostedAzureOpenAiConfig,
     HostedFetchAppTemplateConfig,
+    HostedFetchPipelineTemplateConfig,
     HostedMinmaxConfig,
     HostedOpenAiConfig,
     HostedSparkConfig,

api/configs/middleware/__init__.py

@@ -1,5 +1,5 @@
 import os
-from typing import Any, Literal, Optional
+from typing import Any, Literal
 from urllib.parse import parse_qsl, quote_plus
 
 from pydantic import Field, NonNegativeFloat, NonNegativeInt, PositiveFloat, PositiveInt, computed_field
@@ -18,6 +18,7 @@ from .storage.opendal_storage_config import OpenDALStorageConfig
 from .storage.supabase_storage_config import SupabaseStorageConfig
 from .storage.tencent_cos_storage_config import TencentCloudCOSStorageConfig
 from .storage.volcengine_tos_storage_config import VolcengineTOSStorageConfig
+from .vdb.alibabacloud_mysql_config import AlibabaCloudMySQLConfig
 from .vdb.analyticdb_config import AnalyticdbConfig
 from .vdb.baidu_vector_config import BaiduVectorDBConfig
 from .vdb.chroma_config import ChromaConfig
@@ -78,18 +79,18 @@ class StorageConfig(BaseSettings):
 
 
 class VectorStoreConfig(BaseSettings):
-    VECTOR_STORE: Optional[str] = Field(
+    VECTOR_STORE: str | None = Field(
         description="Type of vector store to use for efficient similarity search."
         " Set to None if not using a vector store.",
         default=None,
     )
 
-    VECTOR_STORE_WHITELIST_ENABLE: Optional[bool] = Field(
+    VECTOR_STORE_WHITELIST_ENABLE: bool | None = Field(
         description="Enable whitelist for vector store.",
         default=False,
     )
 
-    VECTOR_INDEX_NAME_PREFIX: Optional[str] = Field(
+    VECTOR_INDEX_NAME_PREFIX: str | None = Field(
         description="Prefix used to create collection name in vector database",
         default="Vector_index",
     )
@@ -104,6 +105,12 @@ class KeywordStoreConfig(BaseSettings):
 
 
 class DatabaseConfig(BaseSettings):
+    # Database type selector
+    DB_TYPE: Literal["postgresql", "mysql", "oceanbase"] = Field(
+        description="Database type to use. OceanBase is MySQL-compatible.",
+        default="postgresql",
+    )
+
     DB_HOST: str = Field(
         description="Hostname or IP address of the database server.",
         default="localhost",
@@ -139,12 +146,12 @@ class DatabaseConfig(BaseSettings):
         default="",
     )
 
-    SQLALCHEMY_DATABASE_URI_SCHEME: str = Field(
-        description="Database URI scheme for SQLAlchemy connection.",
-        default="postgresql",
-    )
+    @computed_field  # type: ignore[prop-decorator]
+    @property
+    def SQLALCHEMY_DATABASE_URI_SCHEME(self) -> str:
+        return "postgresql" if self.DB_TYPE == "postgresql" else "mysql+pymysql"
 
-    @computed_field  # type: ignore[misc]
+    @computed_field  # type: ignore[prop-decorator]
     @property
     def SQLALCHEMY_DATABASE_URI(self) -> str:
         db_extras = (
@@ -187,26 +194,31 @@ class DatabaseConfig(BaseSettings):
         default=False,
     )
 
+    SQLALCHEMY_POOL_TIMEOUT: NonNegativeInt = Field(
+        description="Number of seconds to wait for a connection from the pool before raising a timeout error.",
+        default=30,
+    )
+
     RETRIEVAL_SERVICE_EXECUTORS: NonNegativeInt = Field(
         description="Number of processes for the retrieval service, default to CPU cores.",
         default=os.cpu_count() or 1,
     )
 
-    @computed_field  # type: ignore[misc]
+    @computed_field  # type: ignore[prop-decorator]
     @property
     def SQLALCHEMY_ENGINE_OPTIONS(self) -> dict[str, Any]:
         # Parse DB_EXTRAS for 'options'
         db_extras_dict = dict(parse_qsl(self.DB_EXTRAS))
         options = db_extras_dict.get("options", "")
-        # Always include timezone
-        timezone_opt = "-c timezone=UTC"
-        if options:
-            # Merge user options and timezone
-            merged_options = f"{options} {timezone_opt}"
-        else:
-            merged_options = timezone_opt
-
-        connect_args = {"options": merged_options}
+        connect_args = {}
+        # Use the dynamic SQLALCHEMY_DATABASE_URI_SCHEME property
+        if self.SQLALCHEMY_DATABASE_URI_SCHEME.startswith("postgresql"):
+            timezone_opt = "-c timezone=UTC"
+            if options:
+                merged_options = f"{options} {timezone_opt}"
+            else:
+                merged_options = timezone_opt
+            connect_args = {"options": merged_options}
 
         return {
             "pool_size": self.SQLALCHEMY_POOL_SIZE,
@@ -216,6 +228,7 @@ class DatabaseConfig(BaseSettings):
             "connect_args": connect_args,
             "pool_use_lifo": self.SQLALCHEMY_POOL_USE_LIFO,
             "pool_reset_on_return": None,
+            "pool_timeout": self.SQLALCHEMY_POOL_TIMEOUT,
         }
 
 
@@ -225,26 +238,26 @@ class CeleryConfig(DatabaseConfig):
         default="redis",
     )
 
-    CELERY_BROKER_URL: Optional[str] = Field(
+    CELERY_BROKER_URL: str | None = Field(
         description="URL of the message broker for Celery tasks.",
         default=None,
     )
 
-    CELERY_USE_SENTINEL: Optional[bool] = Field(
+    CELERY_USE_SENTINEL: bool | None = Field(
         description="Whether to use Redis Sentinel for high availability.",
         default=False,
     )
 
-    CELERY_SENTINEL_MASTER_NAME: Optional[str] = Field(
+    CELERY_SENTINEL_MASTER_NAME: str | None = Field(
         description="Name of the Redis Sentinel master.",
         default=None,
     )
 
-    CELERY_SENTINEL_PASSWORD: Optional[str] = Field(
+    CELERY_SENTINEL_PASSWORD: str | None = Field(
         description="Password of the Redis Sentinel master.",
         default=None,
     )
-    CELERY_SENTINEL_SOCKET_TIMEOUT: Optional[PositiveFloat] = Field(
+    CELERY_SENTINEL_SOCKET_TIMEOUT: PositiveFloat | None = Field(
         description="Timeout for Redis Sentinel socket operations in seconds.",
         default=0.1,
     )
@@ -268,12 +281,12 @@ class InternalTestConfig(BaseSettings):
     Configuration settings for Internal Test
     """
 
-    AWS_SECRET_ACCESS_KEY: Optional[str] = Field(
+    AWS_SECRET_ACCESS_KEY: str | None = Field(
         description="Internal test AWS secret access key",
         default=None,
     )
 
-    AWS_ACCESS_KEY_ID: Optional[str] = Field(
+    AWS_ACCESS_KEY_ID: str | None = Field(
         description="Internal test AWS access key ID",
         default=None,
     )
@@ -284,15 +297,15 @@ class DatasetQueueMonitorConfig(BaseSettings):
     Configuration settings for Dataset Queue Monitor
     """
 
-    QUEUE_MONITOR_THRESHOLD: Optional[NonNegativeInt] = Field(
+    QUEUE_MONITOR_THRESHOLD: NonNegativeInt | None = Field(
         description="Threshold for dataset queue monitor",
         default=200,
     )
-    QUEUE_MONITOR_ALERT_EMAILS: Optional[str] = Field(
+    QUEUE_MONITOR_ALERT_EMAILS: str | None = Field(
         description="Emails for dataset queue monitor alert, separated by commas",
         default=None,
     )
-    QUEUE_MONITOR_INTERVAL: Optional[NonNegativeFloat] = Field(
+    QUEUE_MONITOR_INTERVAL: NonNegativeFloat | None = Field(
         description="Interval for dataset queue monitor in minutes",
         default=30,
     )
@@ -324,6 +337,7 @@ class MiddlewareConfig(
     ClickzettaConfig,
     HuaweiCloudConfig,
     MilvusConfig,
+    AlibabaCloudMySQLConfig,
     MyScaleConfig,
     OpenSearchConfig,
     OracleConfig,

api/configs/middleware/cache/redis_config.py

@@ -1,5 +1,3 @@
-from typing import Optional
-
 from pydantic import Field, NonNegativeInt, PositiveFloat, PositiveInt
 from pydantic_settings import BaseSettings
 
@@ -19,12 +17,12 @@ class RedisConfig(BaseSettings):
         default=6379,
     )
 
-    REDIS_USERNAME: Optional[str] = Field(
+    REDIS_USERNAME: str | None = Field(
         description="Username for Redis authentication (if required)",
         default=None,
     )
 
-    REDIS_PASSWORD: Optional[str] = Field(
+    REDIS_PASSWORD: str | None = Field(
         description="Password for Redis authentication (if required)",
         default=None,
     )
@@ -44,47 +42,47 @@ class RedisConfig(BaseSettings):
         default="CERT_NONE",
     )
 
-    REDIS_SSL_CA_CERTS: Optional[str] = Field(
+    REDIS_SSL_CA_CERTS: str | None = Field(
         description="Path to the CA certificate file for SSL verification",
         default=None,
     )
 
-    REDIS_SSL_CERTFILE: Optional[str] = Field(
+    REDIS_SSL_CERTFILE: str | None = Field(
         description="Path to the client certificate file for SSL authentication",
         default=None,
     )
 
-    REDIS_SSL_KEYFILE: Optional[str] = Field(
+    REDIS_SSL_KEYFILE: str | None = Field(
         description="Path to the client private key file for SSL authentication",
         default=None,
     )
 
-    REDIS_USE_SENTINEL: Optional[bool] = Field(
+    REDIS_USE_SENTINEL: bool | None = Field(
         description="Enable Redis Sentinel mode for high availability",
         default=False,
     )
 
-    REDIS_SENTINELS: Optional[str] = Field(
+    REDIS_SENTINELS: str | None = Field(
         description="Comma-separated list of Redis Sentinel nodes (host:port)",
         default=None,
     )
 
-    REDIS_SENTINEL_SERVICE_NAME: Optional[str] = Field(
+    REDIS_SENTINEL_SERVICE_NAME: str | None = Field(
         description="Name of the Redis Sentinel service to monitor",
         default=None,
     )
 
-    REDIS_SENTINEL_USERNAME: Optional[str] = Field(
+    REDIS_SENTINEL_USERNAME: str | None = Field(
         description="Username for Redis Sentinel authentication (if required)",
         default=None,
     )
 
-    REDIS_SENTINEL_PASSWORD: Optional[str] = Field(
+    REDIS_SENTINEL_PASSWORD: str | None = Field(
         description="Password for Redis Sentinel authentication (if required)",
         default=None,
     )
 
-    REDIS_SENTINEL_SOCKET_TIMEOUT: Optional[PositiveFloat] = Field(
+    REDIS_SENTINEL_SOCKET_TIMEOUT: PositiveFloat | None = Field(
         description="Socket timeout in seconds for Redis Sentinel connections",
         default=0.1,
     )
@@ -94,12 +92,12 @@ class RedisConfig(BaseSettings):
         default=False,
     )
 
-    REDIS_CLUSTERS: Optional[str] = Field(
+    REDIS_CLUSTERS: str | None = Field(
         description="Comma-separated list of Redis Clusters nodes (host:port)",
         default=None,
     )
 
-    REDIS_CLUSTERS_PASSWORD: Optional[str] = Field(
+    REDIS_CLUSTERS_PASSWORD: str | None = Field(
         description="Password for Redis Clusters authentication (if required)",
         default=None,
     )

api/configs/middleware/storage/aliyun_oss_storage_config.py

@@ -1,5 +1,3 @@
-from typing import Optional
-
 from pydantic import Field
 from pydantic_settings import BaseSettings
 
@@ -9,37 +7,37 @@ class AliyunOSSStorageConfig(BaseSettings):
     Configuration settings for Aliyun Object Storage Service (OSS)
     """
 
-    ALIYUN_OSS_BUCKET_NAME: Optional[str] = Field(
+    ALIYUN_OSS_BUCKET_NAME: str | None = Field(
         description="Name of the Aliyun OSS bucket to store and retrieve objects",
         default=None,
     )
 
-    ALIYUN_OSS_ACCESS_KEY: Optional[str] = Field(
+    ALIYUN_OSS_ACCESS_KEY: str | None = Field(
         description="Access key ID for authenticating with Aliyun OSS",
         default=None,
     )
 
-    ALIYUN_OSS_SECRET_KEY: Optional[str] = Field(
+    ALIYUN_OSS_SECRET_KEY: str | None = Field(
         description="Secret access key for authenticating with Aliyun OSS",
         default=None,
     )
 
-    ALIYUN_OSS_ENDPOINT: Optional[str] = Field(
+    ALIYUN_OSS_ENDPOINT: str | None = Field(
         description="URL of the Aliyun OSS endpoint for your chosen region",
         default=None,
     )
 
-    ALIYUN_OSS_REGION: Optional[str] = Field(
+    ALIYUN_OSS_REGION: str | None = Field(
         description="Aliyun OSS region where your bucket is located (e.g., 'oss-cn-hangzhou')",
         default=None,
     )
 
-    ALIYUN_OSS_AUTH_VERSION: Optional[str] = Field(
+    ALIYUN_OSS_AUTH_VERSION: str | None = Field(
         description="Version of the authentication protocol to use with Aliyun OSS (e.g., 'v4')",
         default=None,
     )
 
-    ALIYUN_OSS_PATH: Optional[str] = Field(
+    ALIYUN_OSS_PATH: str | None = Field(
         description="Base path within the bucket to store objects (e.g., 'my-app-data/')",
         default=None,
     )

api/configs/middleware/storage/amazon_s3_storage_config.py

@@ -1,4 +1,4 @@
-from typing import Literal, Optional
+from typing import Literal
 
 from pydantic import Field
 from pydantic_settings import BaseSettings
@@ -9,27 +9,27 @@ class S3StorageConfig(BaseSettings):
     Configuration settings for S3-compatible object storage
     """
 
-    S3_ENDPOINT: Optional[str] = Field(
+    S3_ENDPOINT: str | None = Field(
         description="URL of the S3-compatible storage endpoint (e.g., 'https://s3.amazonaws.com')",
         default=None,
     )
 
-    S3_REGION: Optional[str] = Field(
+    S3_REGION: str | None = Field(
         description="Region where the S3 bucket is located (e.g., 'us-east-1')",
         default=None,
     )
 
-    S3_BUCKET_NAME: Optional[str] = Field(
+    S3_BUCKET_NAME: str | None = Field(
         description="Name of the S3 bucket to store and retrieve objects",
         default=None,
     )
 
-    S3_ACCESS_KEY: Optional[str] = Field(
+    S3_ACCESS_KEY: str | None = Field(
         description="Access key ID for authenticating with the S3 service",
         default=None,
     )
 
-    S3_SECRET_KEY: Optional[str] = Field(
+    S3_SECRET_KEY: str | None = Field(
         description="Secret access key for authenticating with the S3 service",
         default=None,
     )

api/configs/middleware/storage/azure_blob_storage_config.py

@@ -1,5 +1,3 @@
-from typing import Optional
-
 from pydantic import Field
 from pydantic_settings import BaseSettings
 
@@ -9,22 +7,22 @@ class AzureBlobStorageConfig(BaseSettings):
     Configuration settings for Azure Blob Storage
     """
 
-    AZURE_BLOB_ACCOUNT_NAME: Optional[str] = Field(
+    AZURE_BLOB_ACCOUNT_NAME: str | None = Field(
         description="Name of the Azure Storage account (e.g., 'mystorageaccount')",
         default=None,
     )
 
-    AZURE_BLOB_ACCOUNT_KEY: Optional[str] = Field(
+    AZURE_BLOB_ACCOUNT_KEY: str | None = Field(
         description="Access key for authenticating with the Azure Storage account",
         default=None,
     )
 
-    AZURE_BLOB_CONTAINER_NAME: Optional[str] = Field(
+    AZURE_BLOB_CONTAINER_NAME: str | None = Field(
         description="Name of the Azure Blob container to store and retrieve objects",
         default=None,
     )
 
-    AZURE_BLOB_ACCOUNT_URL: Optional[str] = Field(
+    AZURE_BLOB_ACCOUNT_URL: str | None = Field(
         description="URL of the Azure Blob storage endpoint (e.g., 'https://mystorageaccount.blob.core.windows.net')",
         default=None,
     )

api/configs/middleware/storage/baidu_obs_storage_config.py

@@ -1,5 +1,3 @@
-from typing import Optional
-
 from pydantic import Field
 from pydantic_settings import BaseSettings
 
@@ -9,22 +7,22 @@ class BaiduOBSStorageConfig(BaseSettings):
     Configuration settings for Baidu Object Storage Service (OBS)
     """
 
-    BAIDU_OBS_BUCKET_NAME: Optional[str] = Field(
+    BAIDU_OBS_BUCKET_NAME: str | None = Field(
         description="Name of the Baidu OBS bucket to store and retrieve objects (e.g., 'my-obs-bucket')",
         default=None,
     )
 
-    BAIDU_OBS_ACCESS_KEY: Optional[str] = Field(
+    BAIDU_OBS_ACCESS_KEY: str | None = Field(
         description="Access Key ID for authenticating with Baidu OBS",
         default=None,
     )
 
-    BAIDU_OBS_SECRET_KEY: Optional[str] = Field(
+    BAIDU_OBS_SECRET_KEY: str | None = Field(
         description="Secret Access Key for authenticating with Baidu OBS",
         default=None,
     )
 
-    BAIDU_OBS_ENDPOINT: Optional[str] = Field(
+    BAIDU_OBS_ENDPOINT: str | None = Field(
         description="URL of the Baidu OSS endpoint for your chosen region (e.g., 'https://.bj.bcebos.com')",
         default=None,
     )

api/configs/middleware/storage/clickzetta_volume_storage_config.py

@@ -1,7 +1,5 @@
 """ClickZetta Volume Storage Configuration"""
 
-from typing import Optional
-
 from pydantic import Field
 from pydantic_settings import BaseSettings
 
@@ -9,17 +7,17 @@ from pydantic_settings import BaseSettings
 class ClickZettaVolumeStorageConfig(BaseSettings):
     """Configuration for ClickZetta Volume storage."""
 
-    CLICKZETTA_VOLUME_USERNAME: Optional[str] = Field(
+    CLICKZETTA_VOLUME_USERNAME: str | None = Field(
         description="Username for ClickZetta Volume authentication",
         default=None,
     )
 
-    CLICKZETTA_VOLUME_PASSWORD: Optional[str] = Field(
+    CLICKZETTA_VOLUME_PASSWORD: str | None = Field(
         description="Password for ClickZetta Volume authentication",
         default=None,
     )
 
-    CLICKZETTA_VOLUME_INSTANCE: Optional[str] = Field(
+    CLICKZETTA_VOLUME_INSTANCE: str | None = Field(
         description="ClickZetta instance identifier",
         default=None,
     )
@@ -49,7 +47,7 @@ class ClickZettaVolumeStorageConfig(BaseSettings):
         default="user",
     )
 
-    CLICKZETTA_VOLUME_NAME: Optional[str] = Field(
+    CLICKZETTA_VOLUME_NAME: str | None = Field(
         description="ClickZetta volume name for external volumes",
         default=None,
     )

api/configs/middleware/storage/google_cloud_storage_config.py

@@ -1,5 +1,3 @@
-from typing import Optional
-
 from pydantic import Field
 from pydantic_settings import BaseSettings
 
@@ -9,12 +7,12 @@ class GoogleCloudStorageConfig(BaseSettings):
     Configuration settings for Google Cloud Storage
     """
 
-    GOOGLE_STORAGE_BUCKET_NAME: Optional[str] = Field(
+    GOOGLE_STORAGE_BUCKET_NAME: str | None = Field(
         description="Name of the Google Cloud Storage bucket to store and retrieve objects (e.g., 'my-gcs-bucket')",
         default=None,
     )
 
-    GOOGLE_STORAGE_SERVICE_ACCOUNT_JSON_BASE64: Optional[str] = Field(
+    GOOGLE_STORAGE_SERVICE_ACCOUNT_JSON_BASE64: str | None = Field(
         description="Base64-encoded JSON key file for Google Cloud service account authentication",
         default=None,
     )

api/configs/middleware/storage/huawei_obs_storage_config.py

@@ -1,5 +1,3 @@
-from typing import Optional
-
 from pydantic import Field
 from pydantic_settings import BaseSettings
 
@@ -9,22 +7,22 @@ class HuaweiCloudOBSStorageConfig(BaseSettings):
     Configuration settings for Huawei Cloud Object Storage Service (OBS)
     """
 
-    HUAWEI_OBS_BUCKET_NAME: Optional[str] = Field(
+    HUAWEI_OBS_BUCKET_NAME: str | None = Field(
         description="Name of the Huawei Cloud OBS bucket to store and retrieve objects (e.g., 'my-obs-bucket')",
         default=None,
     )
 
-    HUAWEI_OBS_ACCESS_KEY: Optional[str] = Field(
+    HUAWEI_OBS_ACCESS_KEY: str | None = Field(
         description="Access Key ID for authenticating with Huawei Cloud OBS",
         default=None,
     )
 
-    HUAWEI_OBS_SECRET_KEY: Optional[str] = Field(
+    HUAWEI_OBS_SECRET_KEY: str | None = Field(
         description="Secret Access Key for authenticating with Huawei Cloud OBS",
         default=None,
     )
 
-    HUAWEI_OBS_SERVER: Optional[str] = Field(
+    HUAWEI_OBS_SERVER: str | None = Field(
         description="Endpoint URL for Huawei Cloud OBS (e.g., 'https://obs.cn-north-4.myhuaweicloud.com')",
         default=None,
     )

api/configs/middleware/storage/oci_storage_config.py

@@ -1,5 +1,3 @@
-from typing import Optional
-
 from pydantic import Field
 from pydantic_settings import BaseSettings
 
@@ -9,27 +7,27 @@ class OCIStorageConfig(BaseSettings):
     Configuration settings for Oracle Cloud Infrastructure (OCI) Object Storage
     """
 
-    OCI_ENDPOINT: Optional[str] = Field(
+    OCI_ENDPOINT: str | None = Field(
         description="URL of the OCI Object Storage endpoint (e.g., 'https://objectstorage.us-phoenix-1.oraclecloud.com')",
         default=None,
     )
 
-    OCI_REGION: Optional[str] = Field(
+    OCI_REGION: str | None = Field(
         description="OCI region where the bucket is located (e.g., 'us-phoenix-1')",
         default=None,
     )
 
-    OCI_BUCKET_NAME: Optional[str] = Field(
+    OCI_BUCKET_NAME: str | None = Field(
         description="Name of the OCI Object Storage bucket to store and retrieve objects (e.g., 'my-oci-bucket')",
         default=None,
     )
 
-    OCI_ACCESS_KEY: Optional[str] = Field(
+    OCI_ACCESS_KEY: str | None = Field(
         description="Access key (also known as API key) for authenticating with OCI Object Storage",
         default=None,
     )
 
-    OCI_SECRET_KEY: Optional[str] = Field(
+    OCI_SECRET_KEY: str | None = Field(
         description="Secret key associated with the access key for authenticating with OCI Object Storage",
         default=None,
     )

api/configs/middleware/storage/supabase_storage_config.py

@@ -1,5 +1,3 @@
-from typing import Optional
-
 from pydantic import Field
 from pydantic_settings import BaseSettings
 
@@ -9,17 +7,17 @@ class SupabaseStorageConfig(BaseSettings):
     Configuration settings for Supabase Object Storage Service
     """
 
-    SUPABASE_BUCKET_NAME: Optional[str] = Field(
+    SUPABASE_BUCKET_NAME: str | None = Field(
         description="Name of the Supabase bucket to store and retrieve objects (e.g., 'dify-bucket')",
         default=None,
     )
 
-    SUPABASE_API_KEY: Optional[str] = Field(
+    SUPABASE_API_KEY: str | None = Field(
         description="API KEY for authenticating with Supabase",
         default=None,
     )
 
-    SUPABASE_URL: Optional[str] = Field(
+    SUPABASE_URL: str | None = Field(
         description="URL of the Supabase",
         default=None,
     )

api/configs/middleware/storage/tencent_cos_storage_config.py

@@ -1,5 +1,3 @@
-from typing import Optional
-
 from pydantic import Field
 from pydantic_settings import BaseSettings
 
@@ -9,27 +7,27 @@ class TencentCloudCOSStorageConfig(BaseSettings):
     Configuration settings for Tencent Cloud Object Storage (COS)
     """
 
-    TENCENT_COS_BUCKET_NAME: Optional[str] = Field(
+    TENCENT_COS_BUCKET_NAME: str | None = Field(
         description="Name of the Tencent Cloud COS bucket to store and retrieve objects",
         default=None,
     )
 
-    TENCENT_COS_REGION: Optional[str] = Field(
+    TENCENT_COS_REGION: str | None = Field(
         description="Tencent Cloud region where the COS bucket is located (e.g., 'ap-guangzhou')",
         default=None,
     )
 
-    TENCENT_COS_SECRET_ID: Optional[str] = Field(
+    TENCENT_COS_SECRET_ID: str | None = Field(
         description="SecretId for authenticating with Tencent Cloud COS (part of API credentials)",
         default=None,
     )
 
-    TENCENT_COS_SECRET_KEY: Optional[str] = Field(
+    TENCENT_COS_SECRET_KEY: str | None = Field(
         description="SecretKey for authenticating with Tencent Cloud COS (part of API credentials)",
         default=None,
     )
 
-    TENCENT_COS_SCHEME: Optional[str] = Field(
+    TENCENT_COS_SCHEME: str | None = Field(
         description="Protocol scheme for COS requests: 'https' (recommended) or 'http'",
         default=None,
     )

api/configs/middleware/storage/volcengine_tos_storage_config.py

@@ -1,5 +1,3 @@
-from typing import Optional
-
 from pydantic import Field
 from pydantic_settings import BaseSettings
 
@@ -9,27 +7,27 @@ class VolcengineTOSStorageConfig(BaseSettings):
     Configuration settings for Volcengine Tinder Object Storage (TOS)
     """
 
-    VOLCENGINE_TOS_BUCKET_NAME: Optional[str] = Field(
+    VOLCENGINE_TOS_BUCKET_NAME: str | None = Field(
         description="Name of the Volcengine TOS bucket to store and retrieve objects (e.g., 'my-tos-bucket')",
         default=None,
     )
 
-    VOLCENGINE_TOS_ACCESS_KEY: Optional[str] = Field(
+    VOLCENGINE_TOS_ACCESS_KEY: str | None = Field(
         description="Access Key ID for authenticating with Volcengine TOS",
         default=None,
     )
 
-    VOLCENGINE_TOS_SECRET_KEY: Optional[str] = Field(
+    VOLCENGINE_TOS_SECRET_KEY: str | None = Field(
         description="Secret Access Key for authenticating with Volcengine TOS",
         default=None,
     )
 
-    VOLCENGINE_TOS_ENDPOINT: Optional[str] = Field(
+    VOLCENGINE_TOS_ENDPOINT: str | None = Field(
         description="URL of the Volcengine TOS endpoint (e.g., 'https://tos-cn-beijing.volces.com')",
         default=None,
     )
 
-    VOLCENGINE_TOS_REGION: Optional[str] = Field(
+    VOLCENGINE_TOS_REGION: str | None = Field(
         description="Volcengine region where the TOS bucket is located (e.g., 'cn-beijing')",
         default=None,
     )

api/configs/middleware/vdb/alibabacloud_mysql_config.py

@@ -0,0 +1,54 @@
+from pydantic import Field, PositiveInt
+from pydantic_settings import BaseSettings
+
+
+class AlibabaCloudMySQLConfig(BaseSettings):
+    """
+    Configuration settings for AlibabaCloud MySQL vector database
+    """
+
+    ALIBABACLOUD_MYSQL_HOST: str = Field(
+        description="Hostname or IP address of the AlibabaCloud MySQL server (e.g., 'localhost' or 'mysql.aliyun.com')",
+        default="localhost",
+    )
+
+    ALIBABACLOUD_MYSQL_PORT: PositiveInt = Field(
+        description="Port number on which the AlibabaCloud MySQL server is listening (default is 3306)",
+        default=3306,
+    )
+
+    ALIBABACLOUD_MYSQL_USER: str = Field(
+        description="Username for authenticating with AlibabaCloud MySQL (default is 'root')",
+        default="root",
+    )
+
+    ALIBABACLOUD_MYSQL_PASSWORD: str = Field(
+        description="Password for authenticating with AlibabaCloud MySQL (default is an empty string)",
+        default="",
+    )
+
+    ALIBABACLOUD_MYSQL_DATABASE: str = Field(
+        description="Name of the AlibabaCloud MySQL database to connect to (default is 'dify')",
+        default="dify",
+    )
+
+    ALIBABACLOUD_MYSQL_MAX_CONNECTION: PositiveInt = Field(
+        description="Maximum number of connections in the connection pool",
+        default=5,
+    )
+
+    ALIBABACLOUD_MYSQL_CHARSET: str = Field(
+        description="Character set for AlibabaCloud MySQL connection (default is 'utf8mb4')",
+        default="utf8mb4",
+    )
+
+    ALIBABACLOUD_MYSQL_DISTANCE_FUNCTION: str = Field(
+        description="Distance function used for vector similarity search in AlibabaCloud MySQL "
+        "(e.g., 'cosine', 'euclidean')",
+        default="cosine",
+    )
+
+    ALIBABACLOUD_MYSQL_HNSW_M: PositiveInt = Field(
+        description="Maximum number of connections per layer for HNSW vector index (default is 6, range: 3-200)",
+        default=6,
+    )

api/configs/middleware/vdb/analyticdb_config.py

@@ -1,5 +1,3 @@
-from typing import Optional
-
 from pydantic import Field, PositiveInt
 from pydantic_settings import BaseSettings
 
@@ -11,37 +9,37 @@ class AnalyticdbConfig(BaseSettings):
     https://www.alibabacloud.com/help/en/analyticdb-for-postgresql/getting-started/create-an-instance-instances-with-vector-engine-optimization-enabled
     """
 
-    ANALYTICDB_KEY_ID: Optional[str] = Field(
+    ANALYTICDB_KEY_ID: str | None = Field(
         default=None, description="The Access Key ID provided by Alibaba Cloud for API authentication."
     )
-    ANALYTICDB_KEY_SECRET: Optional[str] = Field(
+    ANALYTICDB_KEY_SECRET: str | None = Field(
         default=None, description="The Secret Access Key corresponding to the Access Key ID for secure API access."
     )
-    ANALYTICDB_REGION_ID: Optional[str] = Field(
+    ANALYTICDB_REGION_ID: str | None = Field(
         default=None,
         description="The region where the AnalyticDB instance is deployed (e.g., 'cn-hangzhou', 'ap-southeast-1').",
     )
-    ANALYTICDB_INSTANCE_ID: Optional[str] = Field(
+    ANALYTICDB_INSTANCE_ID: str | None = Field(
         default=None,
         description="The unique identifier of the AnalyticDB instance you want to connect to.",
     )
-    ANALYTICDB_ACCOUNT: Optional[str] = Field(
+    ANALYTICDB_ACCOUNT: str | None = Field(
         default=None,
         description="The account name used to log in to the AnalyticDB instance"
         " (usually the initial account created with the instance).",
     )
-    ANALYTICDB_PASSWORD: Optional[str] = Field(
+    ANALYTICDB_PASSWORD: str | None = Field(
         default=None, description="The password associated with the AnalyticDB account for database authentication."
     )
-    ANALYTICDB_NAMESPACE: Optional[str] = Field(
+    ANALYTICDB_NAMESPACE: str | None = Field(
         default=None, description="The namespace within AnalyticDB for schema isolation (if using namespace feature)."
     )
-    ANALYTICDB_NAMESPACE_PASSWORD: Optional[str] = Field(
+    ANALYTICDB_NAMESPACE_PASSWORD: str | None = Field(
         default=None,
         description="The password for accessing the specified namespace within the AnalyticDB instance"
         " (if namespace feature is enabled).",
     )
-    ANALYTICDB_HOST: Optional[str] = Field(
+    ANALYTICDB_HOST: str | None = Field(
         default=None, description="The host of the AnalyticDB instance you want to connect to."
     )
     ANALYTICDB_PORT: PositiveInt = Field(

api/configs/middleware/vdb/baidu_vector_config.py

@@ -1,5 +1,3 @@
-from typing import Optional
-
 from pydantic import Field, NonNegativeInt, PositiveInt
 from pydantic_settings import BaseSettings
 
@@ -9,7 +7,7 @@ class BaiduVectorDBConfig(BaseSettings):
     Configuration settings for Baidu Vector Database
     """
 
-    BAIDU_VECTOR_DB_ENDPOINT: Optional[str] = Field(
+    BAIDU_VECTOR_DB_ENDPOINT: str | None = Field(
         description="URL of the Baidu Vector Database service (e.g., 'http://vdb.bj.baidubce.com')",
         default=None,
     )
@@ -19,17 +17,17 @@ class BaiduVectorDBConfig(BaseSettings):
         default=30000,
     )
 
-    BAIDU_VECTOR_DB_ACCOUNT: Optional[str] = Field(
+    BAIDU_VECTOR_DB_ACCOUNT: str | None = Field(
         description="Account for authenticating with the Baidu Vector Database",
         default=None,
     )
 
-    BAIDU_VECTOR_DB_API_KEY: Optional[str] = Field(
+    BAIDU_VECTOR_DB_API_KEY: str | None = Field(
         description="API key for authenticating with the Baidu Vector Database service",
         default=None,
     )
 
-    BAIDU_VECTOR_DB_DATABASE: Optional[str] = Field(
+    BAIDU_VECTOR_DB_DATABASE: str | None = Field(
         description="Name of the specific Baidu Vector Database to connect to",
         default=None,
     )
@@ -43,3 +41,13 @@ class BaiduVectorDBConfig(BaseSettings):
         description="Number of replicas for the Baidu Vector Database (default is 3)",
         default=3,
     )
+
+    BAIDU_VECTOR_DB_INVERTED_INDEX_ANALYZER: str = Field(
+        description="Analyzer type for inverted index in Baidu Vector Database (default is DEFAULT_ANALYZER)",
+        default="DEFAULT_ANALYZER",
+    )
+
+    BAIDU_VECTOR_DB_INVERTED_INDEX_PARSER_MODE: str = Field(
+        description="Parser mode for inverted index in Baidu Vector Database (default is COARSE_MODE)",
+        default="COARSE_MODE",
+    )

api/configs/middleware/vdb/chroma_config.py

@@ -1,5 +1,3 @@
-from typing import Optional
-
 from pydantic import Field, PositiveInt
 from pydantic_settings import BaseSettings
 
@@ -9,7 +7,7 @@ class ChromaConfig(BaseSettings):
     Configuration settings for Chroma vector database
     """
 
-    CHROMA_HOST: Optional[str] = Field(
+    CHROMA_HOST: str | None = Field(
         description="Hostname or IP address of the Chroma server (e.g., 'localhost' or '192.168.1.100')",
         default=None,
     )
@@ -19,22 +17,22 @@ class ChromaConfig(BaseSettings):
         default=8000,
     )
 
-    CHROMA_TENANT: Optional[str] = Field(
+    CHROMA_TENANT: str | None = Field(
         description="Tenant identifier for multi-tenancy support in Chroma",
         default=None,
     )
 
-    CHROMA_DATABASE: Optional[str] = Field(
+    CHROMA_DATABASE: str | None = Field(
         description="Name of the Chroma database to connect to",
         default=None,
     )
 
-    CHROMA_AUTH_PROVIDER: Optional[str] = Field(
+    CHROMA_AUTH_PROVIDER: str | None = Field(
         description="Authentication provider for Chroma (e.g., 'basic', 'token', or a custom provider)",
         default=None,
     )
 
-    CHROMA_AUTH_CREDENTIALS: Optional[str] = Field(
+    CHROMA_AUTH_CREDENTIALS: str | None = Field(
         description="Authentication credentials for Chroma (format depends on the auth provider)",
         default=None,
     )

api/configs/middleware/vdb/clickzetta_config.py

@@ -1,5 +1,3 @@
-from typing import Optional
-
 from pydantic import Field
 from pydantic_settings import BaseSettings
 
@@ -9,62 +7,62 @@ class ClickzettaConfig(BaseSettings):
     Clickzetta Lakehouse vector database configuration
     """
 
-    CLICKZETTA_USERNAME: Optional[str] = Field(
+    CLICKZETTA_USERNAME: str | None = Field(
         description="Username for authenticating with Clickzetta Lakehouse",
         default=None,
     )
 
-    CLICKZETTA_PASSWORD: Optional[str] = Field(
+    CLICKZETTA_PASSWORD: str | None = Field(
         description="Password for authenticating with Clickzetta Lakehouse",
         default=None,
     )
 
-    CLICKZETTA_INSTANCE: Optional[str] = Field(
+    CLICKZETTA_INSTANCE: str | None = Field(
         description="Clickzetta Lakehouse instance ID",
         default=None,
     )
 
-    CLICKZETTA_SERVICE: Optional[str] = Field(
+    CLICKZETTA_SERVICE: str | None = Field(
         description="Clickzetta API service endpoint (e.g., 'api.clickzetta.com')",
         default="api.clickzetta.com",
     )
 
-    CLICKZETTA_WORKSPACE: Optional[str] = Field(
+    CLICKZETTA_WORKSPACE: str | None = Field(
         description="Clickzetta workspace name",
         default="default",
     )
 
-    CLICKZETTA_VCLUSTER: Optional[str] = Field(
+    CLICKZETTA_VCLUSTER: str | None = Field(
         description="Clickzetta virtual cluster name",
         default="default_ap",
     )
 
-    CLICKZETTA_SCHEMA: Optional[str] = Field(
+    CLICKZETTA_SCHEMA: str | None = Field(
         description="Database schema name in Clickzetta",
         default="public",
     )
 
-    CLICKZETTA_BATCH_SIZE: Optional[int] = Field(
+    CLICKZETTA_BATCH_SIZE: int | None = Field(
         description="Batch size for bulk insert operations",
         default=100,
     )
 
-    CLICKZETTA_ENABLE_INVERTED_INDEX: Optional[bool] = Field(
+    CLICKZETTA_ENABLE_INVERTED_INDEX: bool | None = Field(
         description="Enable inverted index for full-text search capabilities",
         default=True,
     )
 
-    CLICKZETTA_ANALYZER_TYPE: Optional[str] = Field(
+    CLICKZETTA_ANALYZER_TYPE: str | None = Field(
         description="Analyzer type for full-text search: keyword, english, chinese, unicode",
         default="chinese",
     )
 
-    CLICKZETTA_ANALYZER_MODE: Optional[str] = Field(
+    CLICKZETTA_ANALYZER_MODE: str | None = Field(
         description="Analyzer mode for tokenization: max_word (fine-grained) or smart (intelligent)",
         default="smart",
     )
 
-    CLICKZETTA_VECTOR_DISTANCE_FUNCTION: Optional[str] = Field(
+    CLICKZETTA_VECTOR_DISTANCE_FUNCTION: str | None = Field(
         description="Distance function for vector similarity: l2_distance or cosine_distance",
         default="cosine_distance",
     )

api/configs/middleware/vdb/couchbase_config.py

@@ -1,5 +1,3 @@
-from typing import Optional
-
 from pydantic import Field
 from pydantic_settings import BaseSettings
 
@@ -9,27 +7,27 @@ class CouchbaseConfig(BaseSettings):
     Couchbase configs
     """
 
-    COUCHBASE_CONNECTION_STRING: Optional[str] = Field(
+    COUCHBASE_CONNECTION_STRING: str | None = Field(
         description="COUCHBASE connection string",
         default=None,
     )
 
-    COUCHBASE_USER: Optional[str] = Field(
+    COUCHBASE_USER: str | None = Field(
         description="COUCHBASE user",
         default=None,
     )
 
-    COUCHBASE_PASSWORD: Optional[str] = Field(
+    COUCHBASE_PASSWORD: str | None = Field(
         description="COUCHBASE password",
         default=None,
     )
 
-    COUCHBASE_BUCKET_NAME: Optional[str] = Field(
+    COUCHBASE_BUCKET_NAME: str | None = Field(
         description="COUCHBASE bucket name",
         default=None,
     )
 
-    COUCHBASE_SCOPE_NAME: Optional[str] = Field(
+    COUCHBASE_SCOPE_NAME: str | None = Field(
         description="COUCHBASE scope name",
         default=None,
     )

api/configs/middleware/vdb/elasticsearch_config.py

@@ -1,5 +1,3 @@
-from typing import Optional
-
 from pydantic import Field, PositiveInt, model_validator
 from pydantic_settings import BaseSettings
 
@@ -10,7 +8,7 @@ class ElasticsearchConfig(BaseSettings):
     Can load from environment variables or .env files.
     """
 
-    ELASTICSEARCH_HOST: Optional[str] = Field(
+    ELASTICSEARCH_HOST: str | None = Field(
         description="Hostname or IP address of the Elasticsearch server (e.g., 'localhost' or '192.168.1.100')",
         default="127.0.0.1",
     )
@@ -20,30 +18,28 @@ class ElasticsearchConfig(BaseSettings):
         default=9200,
     )
 
-    ELASTICSEARCH_USERNAME: Optional[str] = Field(
+    ELASTICSEARCH_USERNAME: str | None = Field(
         description="Username for authenticating with Elasticsearch (default is 'elastic')",
         default="elastic",
     )
 
-    ELASTICSEARCH_PASSWORD: Optional[str] = Field(
+    ELASTICSEARCH_PASSWORD: str | None = Field(
         description="Password for authenticating with Elasticsearch (default is 'elastic')",
         default="elastic",
     )
 
     # Elastic Cloud (optional)
-    ELASTICSEARCH_USE_CLOUD: Optional[bool] = Field(
+    ELASTICSEARCH_USE_CLOUD: bool | None = Field(
         description="Set to True to use Elastic Cloud instead of self-hosted Elasticsearch", default=False
     )
-    ELASTICSEARCH_CLOUD_URL: Optional[str] = Field(
+    ELASTICSEARCH_CLOUD_URL: str | None = Field(
         description="Full URL for Elastic Cloud deployment (e.g., 'https://example.es.region.aws.found.io:443')",
         default=None,
     )
-    ELASTICSEARCH_API_KEY: Optional[str] = Field(
-        description="API key for authenticating with Elastic Cloud", default=None
-    )
+    ELASTICSEARCH_API_KEY: str | None = Field(description="API key for authenticating with Elastic Cloud", default=None)
 
     # Common options
-    ELASTICSEARCH_CA_CERTS: Optional[str] = Field(
+    ELASTICSEARCH_CA_CERTS: str | None = Field(
         description="Path to CA certificate file for SSL verification", default=None
     )
     ELASTICSEARCH_VERIFY_CERTS: bool = Field(

api/configs/middleware/vdb/huawei_cloud_config.py

@@ -1,5 +1,3 @@
-from typing import Optional
-
 from pydantic import Field
 from pydantic_settings import BaseSettings
 
@@ -9,17 +7,17 @@ class HuaweiCloudConfig(BaseSettings):
     Configuration settings for Huawei cloud search service
     """
 
-    HUAWEI_CLOUD_HOSTS: Optional[str] = Field(
+    HUAWEI_CLOUD_HOSTS: str | None = Field(
         description="Hostname or IP address of the Huawei cloud search service instance",
         default=None,
     )
 
-    HUAWEI_CLOUD_USER: Optional[str] = Field(
+    HUAWEI_CLOUD_USER: str | None = Field(
         description="Username for authenticating with Huawei cloud search service",
         default=None,
     )
 
-    HUAWEI_CLOUD_PASSWORD: Optional[str] = Field(
+    HUAWEI_CLOUD_PASSWORD: str | None = Field(
         description="Password for authenticating with Huawei cloud search service",
         default=None,
     )

api/configs/middleware/vdb/lindorm_config.py

@@ -1,5 +1,3 @@
-from typing import Optional
-
 from pydantic import Field
 from pydantic_settings import BaseSettings
 
@@ -9,27 +7,27 @@ class LindormConfig(BaseSettings):
     Lindorm configs
     """
 
-    LINDORM_URL: Optional[str] = Field(
+    LINDORM_URL: str | None = Field(
         description="Lindorm url",
         default=None,
     )
-    LINDORM_USERNAME: Optional[str] = Field(
+    LINDORM_USERNAME: str | None = Field(
         description="Lindorm user",
         default=None,
     )
-    LINDORM_PASSWORD: Optional[str] = Field(
+    LINDORM_PASSWORD: str | None = Field(
         description="Lindorm password",
         default=None,
     )
-    DEFAULT_INDEX_TYPE: Optional[str] = Field(
+    LINDORM_INDEX_TYPE: str | None = Field(
         description="Lindorm Vector Index Type, hnsw or flat is available in dify",
         default="hnsw",
     )
-    DEFAULT_DISTANCE_TYPE: Optional[str] = Field(
+    LINDORM_DISTANCE_TYPE: str | None = Field(
         description="Vector Distance Type, support l2, cosinesimil, innerproduct", default="l2"
     )
-    USING_UGC_INDEX: Optional[bool] = Field(
-        description="Using UGC index will store the same type of Index in a single index but can retrieve separately.",
-        default=False,
+    LINDORM_USING_UGC: bool | None = Field(
+        description="Using UGC index will store indexes with the same IndexType/Dimension in a single big index.",
+        default=True,
     )
-    LINDORM_QUERY_TIMEOUT: Optional[float] = Field(description="The lindorm search request timeout (s)", default=2.0)
+    LINDORM_QUERY_TIMEOUT: float | None = Field(description="The lindorm search request timeout (s)", default=2.0)

api/configs/middleware/vdb/milvus_config.py

@@ -1,5 +1,3 @@
-from typing import Optional
-
 from pydantic import Field
 from pydantic_settings import BaseSettings
 
@@ -9,22 +7,22 @@ class MilvusConfig(BaseSettings):
     Configuration settings for Milvus vector database
     """
 
-    MILVUS_URI: Optional[str] = Field(
+    MILVUS_URI: str | None = Field(
         description="URI for connecting to the Milvus server (e.g., 'http://localhost:19530' or 'https://milvus-instance.example.com:19530')",
         default="http://127.0.0.1:19530",
     )
 
-    MILVUS_TOKEN: Optional[str] = Field(
+    MILVUS_TOKEN: str | None = Field(
         description="Authentication token for Milvus, if token-based authentication is enabled",
         default=None,
     )
 
-    MILVUS_USER: Optional[str] = Field(
+    MILVUS_USER: str | None = Field(
         description="Username for authenticating with Milvus, if username/password authentication is enabled",
         default=None,
     )
 
-    MILVUS_PASSWORD: Optional[str] = Field(
+    MILVUS_PASSWORD: str | None = Field(
         description="Password for authenticating with Milvus, if username/password authentication is enabled",
         default=None,
     )
@@ -40,7 +38,7 @@ class MilvusConfig(BaseSettings):
         default=True,
     )
 
-    MILVUS_ANALYZER_PARAMS: Optional[str] = Field(
+    MILVUS_ANALYZER_PARAMS: str | None = Field(
         description='Milvus text analyzer parameters, e.g., {"type": "chinese"} for Chinese segmentation support.',
         default=None,
     )

api/configs/middleware/vdb/oceanbase_config.py

@@ -1,5 +1,3 @@
-from typing import Optional
-
 from pydantic import Field, PositiveInt
 from pydantic_settings import BaseSettings
 
@@ -9,27 +7,27 @@ class OceanBaseVectorConfig(BaseSettings):
     Configuration settings for OceanBase Vector database
     """
 
-    OCEANBASE_VECTOR_HOST: Optional[str] = Field(
+    OCEANBASE_VECTOR_HOST: str | None = Field(
         description="Hostname or IP address of the OceanBase Vector server (e.g. 'localhost')",
         default=None,
     )
 
-    OCEANBASE_VECTOR_PORT: Optional[PositiveInt] = Field(
+    OCEANBASE_VECTOR_PORT: PositiveInt | None = Field(
         description="Port number on which the OceanBase Vector server is listening (default is 2881)",
         default=2881,
     )
 
-    OCEANBASE_VECTOR_USER: Optional[str] = Field(
+    OCEANBASE_VECTOR_USER: str | None = Field(
         description="Username for authenticating with the OceanBase Vector database",
         default=None,
     )
 
-    OCEANBASE_VECTOR_PASSWORD: Optional[str] = Field(
+    OCEANBASE_VECTOR_PASSWORD: str | None = Field(
         description="Password for authenticating with the OceanBase Vector database",
         default=None,
     )
 
-    OCEANBASE_VECTOR_DATABASE: Optional[str] = Field(
+    OCEANBASE_VECTOR_DATABASE: str | None = Field(
         description="Name of the OceanBase Vector database to connect to",
         default=None,
     )
@@ -39,3 +37,15 @@ class OceanBaseVectorConfig(BaseSettings):
         "with older versions",
         default=False,
     )
+
+    OCEANBASE_FULLTEXT_PARSER: str | None = Field(
+        description=(
+            "Fulltext parser to use for text indexing. "
+            "Built-in options: 'ngram' (N-gram tokenizer for English/numbers), "
+            "'beng' (Basic English tokenizer), 'space' (Space-based tokenizer), "
+            "'ngram2' (Improved N-gram tokenizer), 'ik' (Chinese tokenizer). "
+            "External plugins (require installation): 'japanese_ftparser' (Japanese tokenizer), "
+            "'thai_ftparser' (Thai tokenizer). Default is 'ik'"
+        ),
+        default="ik",
+    )

api/configs/middleware/vdb/opengauss_config.py

@@ -1,5 +1,3 @@
-from typing import Optional
-
 from pydantic import Field, PositiveInt
 from pydantic_settings import BaseSettings
 
@@ -9,7 +7,7 @@ class OpenGaussConfig(BaseSettings):
     Configuration settings for OpenGauss
     """
 
-    OPENGAUSS_HOST: Optional[str] = Field(
+    OPENGAUSS_HOST: str | None = Field(
         description="Hostname or IP address of the OpenGauss server(e.g., 'localhost')",
         default=None,
     )
@@ -19,17 +17,17 @@ class OpenGaussConfig(BaseSettings):
         default=6600,
     )
 
-    OPENGAUSS_USER: Optional[str] = Field(
+    OPENGAUSS_USER: str | None = Field(
         description="Username for authenticating with the OpenGauss database",
         default=None,
     )
 
-    OPENGAUSS_PASSWORD: Optional[str] = Field(
+    OPENGAUSS_PASSWORD: str | None = Field(
         description="Password for authenticating with the OpenGauss database",
         default=None,
     )
 
-    OPENGAUSS_DATABASE: Optional[str] = Field(
+    OPENGAUSS_DATABASE: str | None = Field(
         description="Name of the OpenGauss database to connect to",
         default=None,
     )

api/configs/middleware/vdb/opensearch_config.py

@@ -1,24 +1,25 @@
-from enum import Enum
-from typing import Literal, Optional
+from enum import StrEnum
+from typing import Literal
 
 from pydantic import Field, PositiveInt
 from pydantic_settings import BaseSettings
 
 
+class AuthMethod(StrEnum):
+    """
+    Authentication method for OpenSearch
+    """
+
+    BASIC = "basic"
+    AWS_MANAGED_IAM = "aws_managed_iam"
+
+
 class OpenSearchConfig(BaseSettings):
     """
     Configuration settings for OpenSearch
     """
 
-    class AuthMethod(Enum):
-        """
-        Authentication method for OpenSearch
-        """
-
-        BASIC = "basic"
-        AWS_MANAGED_IAM = "aws_managed_iam"
-
-    OPENSEARCH_HOST: Optional[str] = Field(
+    OPENSEARCH_HOST: str | None = Field(
         description="Hostname or IP address of the OpenSearch server (e.g., 'localhost' or 'opensearch.example.com')",
         default=None,
     )
@@ -43,21 +44,21 @@ class OpenSearchConfig(BaseSettings):
         default=AuthMethod.BASIC,
     )
 
-    OPENSEARCH_USER: Optional[str] = Field(
+    OPENSEARCH_USER: str | None = Field(
         description="Username for authenticating with OpenSearch",
         default=None,
     )
 
-    OPENSEARCH_PASSWORD: Optional[str] = Field(
+    OPENSEARCH_PASSWORD: str | None = Field(
         description="Password for authenticating with OpenSearch",
         default=None,
     )
 
-    OPENSEARCH_AWS_REGION: Optional[str] = Field(
+    OPENSEARCH_AWS_REGION: str | None = Field(
         description="AWS region for OpenSearch (e.g. 'us-west-2')",
         default=None,
     )
 
-    OPENSEARCH_AWS_SERVICE: Optional[Literal["es", "aoss"]] = Field(
+    OPENSEARCH_AWS_SERVICE: Literal["es", "aoss"] | None = Field(
         description="AWS service for OpenSearch (e.g. 'aoss' for OpenSearch Serverless)", default=None
     )

api/configs/middleware/vdb/oracle_config.py

@@ -1,5 +1,3 @@
-from typing import Optional
-
 from pydantic import Field
 from pydantic_settings import BaseSettings
 
@@ -9,33 +7,33 @@ class OracleConfig(BaseSettings):
     Configuration settings for Oracle database
     """
 
-    ORACLE_USER: Optional[str] = Field(
+    ORACLE_USER: str | None = Field(
         description="Username for authenticating with the Oracle database",
         default=None,
     )
 
-    ORACLE_PASSWORD: Optional[str] = Field(
+    ORACLE_PASSWORD: str | None = Field(
         description="Password for authenticating with the Oracle database",
         default=None,
     )
 
-    ORACLE_DSN: Optional[str] = Field(
+    ORACLE_DSN: str | None = Field(
         description="Oracle database connection string. For traditional database, use format 'host:port/service_name'. "
         "For autonomous database, use the service name from tnsnames.ora in the wallet",
         default=None,
     )
 
-    ORACLE_CONFIG_DIR: Optional[str] = Field(
+    ORACLE_CONFIG_DIR: str | None = Field(
         description="Directory containing the tnsnames.ora configuration file. Only used in thin mode connection",
         default=None,
     )
 
-    ORACLE_WALLET_LOCATION: Optional[str] = Field(
+    ORACLE_WALLET_LOCATION: str | None = Field(
         description="Oracle wallet directory path containing the wallet files for secure connection",
         default=None,
     )
 
-    ORACLE_WALLET_PASSWORD: Optional[str] = Field(
+    ORACLE_WALLET_PASSWORD: str | None = Field(
         description="Password to decrypt the Oracle wallet, if it is encrypted",
         default=None,
     )

api/configs/middleware/vdb/pgvector_config.py

@@ -1,5 +1,3 @@
-from typing import Optional
-
 from pydantic import Field, PositiveInt
 from pydantic_settings import BaseSettings
 
@@ -9,7 +7,7 @@ class PGVectorConfig(BaseSettings):
     Configuration settings for PGVector (PostgreSQL with vector extension)
     """
 
-    PGVECTOR_HOST: Optional[str] = Field(
+    PGVECTOR_HOST: str | None = Field(
         description="Hostname or IP address of the PostgreSQL server with PGVector extension (e.g., 'localhost')",
         default=None,
     )
@@ -19,17 +17,17 @@ class PGVectorConfig(BaseSettings):
         default=5433,
     )
 
-    PGVECTOR_USER: Optional[str] = Field(
+    PGVECTOR_USER: str | None = Field(
         description="Username for authenticating with the PostgreSQL database",
         default=None,
     )
 
-    PGVECTOR_PASSWORD: Optional[str] = Field(
+    PGVECTOR_PASSWORD: str | None = Field(
         description="Password for authenticating with the PostgreSQL database",
         default=None,
     )
 
-    PGVECTOR_DATABASE: Optional[str] = Field(
+    PGVECTOR_DATABASE: str | None = Field(
         description="Name of the PostgreSQL database to connect to",
         default=None,
     )

api/configs/middleware/vdb/pgvectors_config.py

@@ -1,5 +1,3 @@
-from typing import Optional
-
 from pydantic import Field, PositiveInt
 from pydantic_settings import BaseSettings
 
@@ -9,7 +7,7 @@ class PGVectoRSConfig(BaseSettings):
     Configuration settings for PGVecto.RS (Rust-based vector extension for PostgreSQL)
     """
 
-    PGVECTO_RS_HOST: Optional[str] = Field(
+    PGVECTO_RS_HOST: str | None = Field(
         description="Hostname or IP address of the PostgreSQL server with PGVecto.RS extension (e.g., 'localhost')",
         default=None,
     )
@@ -19,17 +17,17 @@ class PGVectoRSConfig(BaseSettings):
         default=5431,
     )
 
-    PGVECTO_RS_USER: Optional[str] = Field(
+    PGVECTO_RS_USER: str | None = Field(
         description="Username for authenticating with the PostgreSQL database using PGVecto.RS",
         default=None,
     )
 
-    PGVECTO_RS_PASSWORD: Optional[str] = Field(
+    PGVECTO_RS_PASSWORD: str | None = Field(
         description="Password for authenticating with the PostgreSQL database using PGVecto.RS",
         default=None,
     )
 
-    PGVECTO_RS_DATABASE: Optional[str] = Field(
+    PGVECTO_RS_DATABASE: str | None = Field(
         description="Name of the PostgreSQL database with PGVecto.RS extension to connect to",
         default=None,
     )

api/configs/middleware/vdb/qdrant_config.py

@@ -1,5 +1,3 @@
-from typing import Optional
-
 from pydantic import Field, NonNegativeInt, PositiveInt
 from pydantic_settings import BaseSettings
 
@@ -9,12 +7,12 @@ class QdrantConfig(BaseSettings):
     Configuration settings for Qdrant vector database
     """
 
-    QDRANT_URL: Optional[str] = Field(
+    QDRANT_URL: str | None = Field(
         description="URL of the Qdrant server (e.g., 'http://localhost:6333' or 'https://qdrant.example.com')",
         default=None,
     )
 
-    QDRANT_API_KEY: Optional[str] = Field(
+    QDRANT_API_KEY: str | None = Field(
         description="API key for authenticating with the Qdrant server",
         default=None,
     )

api/configs/middleware/vdb/relyt_config.py

@@ -1,5 +1,3 @@
-from typing import Optional
-
 from pydantic import Field, PositiveInt
 from pydantic_settings import BaseSettings
 
@@ -9,7 +7,7 @@ class RelytConfig(BaseSettings):
     Configuration settings for Relyt database
     """
 
-    RELYT_HOST: Optional[str] = Field(
+    RELYT_HOST: str | None = Field(
         description="Hostname or IP address of the Relyt server (e.g., 'localhost' or 'relyt.example.com')",
         default=None,
     )
@@ -19,17 +17,17 @@ class RelytConfig(BaseSettings):
         default=9200,
     )
 
-    RELYT_USER: Optional[str] = Field(
+    RELYT_USER: str | None = Field(
         description="Username for authenticating with the Relyt database",
         default=None,
     )
 
-    RELYT_PASSWORD: Optional[str] = Field(
+    RELYT_PASSWORD: str | None = Field(
         description="Password for authenticating with the Relyt database",
         default=None,
     )
 
-    RELYT_DATABASE: Optional[str] = Field(
+    RELYT_DATABASE: str | None = Field(
         description="Name of the Relyt database to connect to (default is 'default')",
         default="default",
     )

api/configs/middleware/vdb/tablestore_config.py

@@ -1,5 +1,3 @@
-from typing import Optional
-
 from pydantic import Field
 from pydantic_settings import BaseSettings
 
@@ -9,22 +7,22 @@ class TableStoreConfig(BaseSettings):
     Configuration settings for TableStore.
     """
 
-    TABLESTORE_ENDPOINT: Optional[str] = Field(
+    TABLESTORE_ENDPOINT: str | None = Field(
         description="Endpoint address of the TableStore server (e.g. 'https://instance-name.cn-hangzhou.ots.aliyuncs.com')",
         default=None,
     )
 
-    TABLESTORE_INSTANCE_NAME: Optional[str] = Field(
+    TABLESTORE_INSTANCE_NAME: str | None = Field(
         description="Instance name to access TableStore server (eg. 'instance-name')",
         default=None,
     )
 
-    TABLESTORE_ACCESS_KEY_ID: Optional[str] = Field(
+    TABLESTORE_ACCESS_KEY_ID: str | None = Field(
         description="AccessKey id for the instance name",
         default=None,
     )
 
-    TABLESTORE_ACCESS_KEY_SECRET: Optional[str] = Field(
+    TABLESTORE_ACCESS_KEY_SECRET: str | None = Field(
         description="AccessKey secret for the instance name",
         default=None,
     )

api/configs/middleware/vdb/tencent_vector_config.py

@@ -1,5 +1,3 @@
-from typing import Optional
-
 from pydantic import Field, NonNegativeInt, PositiveInt
 from pydantic_settings import BaseSettings
 
@@ -9,12 +7,12 @@ class TencentVectorDBConfig(BaseSettings):
     Configuration settings for Tencent Vector Database
     """
 
-    TENCENT_VECTOR_DB_URL: Optional[str] = Field(
+    TENCENT_VECTOR_DB_URL: str | None = Field(
         description="URL of the Tencent Vector Database service (e.g., 'https://vectordb.tencentcloudapi.com')",
         default=None,
     )
 
-    TENCENT_VECTOR_DB_API_KEY: Optional[str] = Field(
+    TENCENT_VECTOR_DB_API_KEY: str | None = Field(
         description="API key for authenticating with the Tencent Vector Database service",
         default=None,
     )
@@ -24,12 +22,12 @@ class TencentVectorDBConfig(BaseSettings):
         default=30,
     )
 
-    TENCENT_VECTOR_DB_USERNAME: Optional[str] = Field(
+    TENCENT_VECTOR_DB_USERNAME: str | None = Field(
         description="Username for authenticating with the Tencent Vector Database (if required)",
         default=None,
     )
 
-    TENCENT_VECTOR_DB_PASSWORD: Optional[str] = Field(
+    TENCENT_VECTOR_DB_PASSWORD: str | None = Field(
         description="Password for authenticating with the Tencent Vector Database (if required)",
         default=None,
     )
@@ -44,7 +42,7 @@ class TencentVectorDBConfig(BaseSettings):
         default=2,
     )
 
-    TENCENT_VECTOR_DB_DATABASE: Optional[str] = Field(
+    TENCENT_VECTOR_DB_DATABASE: str | None = Field(
         description="Name of the specific Tencent Vector Database to connect to",
         default=None,
     )

api/configs/middleware/vdb/tidb_on_qdrant_config.py

@@ -1,5 +1,3 @@
-from typing import Optional
-
 from pydantic import Field, NonNegativeInt, PositiveInt
 from pydantic_settings import BaseSettings
 
@@ -9,12 +7,12 @@ class TidbOnQdrantConfig(BaseSettings):
     Tidb on Qdrant configs
     """
 
-    TIDB_ON_QDRANT_URL: Optional[str] = Field(
+    TIDB_ON_QDRANT_URL: str | None = Field(
         description="Tidb on Qdrant url",
         default=None,
     )
 
-    TIDB_ON_QDRANT_API_KEY: Optional[str] = Field(
+    TIDB_ON_QDRANT_API_KEY: str | None = Field(
         description="Tidb on Qdrant api key",
         default=None,
     )
@@ -34,37 +32,37 @@ class TidbOnQdrantConfig(BaseSettings):
         default=6334,
     )
 
-    TIDB_PUBLIC_KEY: Optional[str] = Field(
+    TIDB_PUBLIC_KEY: str | None = Field(
         description="Tidb account public key",
         default=None,
     )
 
-    TIDB_PRIVATE_KEY: Optional[str] = Field(
+    TIDB_PRIVATE_KEY: str | None = Field(
         description="Tidb account private key",
         default=None,
     )
 
-    TIDB_API_URL: Optional[str] = Field(
+    TIDB_API_URL: str | None = Field(
         description="Tidb API url",
         default=None,
     )
 
-    TIDB_IAM_API_URL: Optional[str] = Field(
+    TIDB_IAM_API_URL: str | None = Field(
         description="Tidb IAM API url",
         default=None,
     )
 
-    TIDB_REGION: Optional[str] = Field(
+    TIDB_REGION: str | None = Field(
         description="Tidb serverless region",
         default="regions/aws-us-east-1",
     )
 
-    TIDB_PROJECT_ID: Optional[str] = Field(
+    TIDB_PROJECT_ID: str | None = Field(
         description="Tidb project id",
         default=None,
     )
 
-    TIDB_SPEND_LIMIT: Optional[int] = Field(
+    TIDB_SPEND_LIMIT: int | None = Field(
         description="Tidb spend limit",
         default=100,
     )

api/configs/middleware/vdb/tidb_vector_config.py

@@ -1,5 +1,3 @@
-from typing import Optional
-
 from pydantic import Field, PositiveInt
 from pydantic_settings import BaseSettings
 
@@ -9,27 +7,27 @@ class TiDBVectorConfig(BaseSettings):
     Configuration settings for TiDB Vector database
     """
 
-    TIDB_VECTOR_HOST: Optional[str] = Field(
+    TIDB_VECTOR_HOST: str | None = Field(
         description="Hostname or IP address of the TiDB Vector server (e.g., 'localhost' or 'tidb.example.com')",
         default=None,
     )
 
-    TIDB_VECTOR_PORT: Optional[PositiveInt] = Field(
+    TIDB_VECTOR_PORT: PositiveInt | None = Field(
         description="Port number on which the TiDB Vector server is listening (default is 4000)",
         default=4000,
     )
 
-    TIDB_VECTOR_USER: Optional[str] = Field(
+    TIDB_VECTOR_USER: str | None = Field(
         description="Username for authenticating with the TiDB Vector database",
         default=None,
     )
 
-    TIDB_VECTOR_PASSWORD: Optional[str] = Field(
+    TIDB_VECTOR_PASSWORD: str | None = Field(
         description="Password for authenticating with the TiDB Vector database",
         default=None,
     )
 
-    TIDB_VECTOR_DATABASE: Optional[str] = Field(
+    TIDB_VECTOR_DATABASE: str | None = Field(
         description="Name of the TiDB Vector database to connect to",
         default=None,
     )

api/configs/middleware/vdb/upstash_config.py

@@ -1,5 +1,3 @@
-from typing import Optional
-
 from pydantic import Field
 from pydantic_settings import BaseSettings
 
@@ -9,12 +7,12 @@ class UpstashConfig(BaseSettings):
     Configuration settings for Upstash vector database
     """
 
-    UPSTASH_VECTOR_URL: Optional[str] = Field(
+    UPSTASH_VECTOR_URL: str | None = Field(
         description="URL of the upstash server (e.g., 'https://vector.upstash.io')",
         default=None,
     )
 
-    UPSTASH_VECTOR_TOKEN: Optional[str] = Field(
+    UPSTASH_VECTOR_TOKEN: str | None = Field(
         description="Token for authenticating with the upstash server",
         default=None,
     )

api/configs/middleware/vdb/vastbase_vector_config.py

@@ -1,5 +1,3 @@
-from typing import Optional
-
 from pydantic import Field, PositiveInt
 from pydantic_settings import BaseSettings
 
@@ -9,7 +7,7 @@ class VastbaseVectorConfig(BaseSettings):
     Configuration settings for Vector (Vastbase with vector extension)
     """
 
-    VASTBASE_HOST: Optional[str] = Field(
+    VASTBASE_HOST: str | None = Field(
         description="Hostname or IP address of the Vastbase server with Vector extension (e.g., 'localhost')",
         default=None,
     )
@@ -19,17 +17,17 @@ class VastbaseVectorConfig(BaseSettings):
         default=5432,
     )
 
-    VASTBASE_USER: Optional[str] = Field(
+    VASTBASE_USER: str | None = Field(
         description="Username for authenticating with the Vastbase database",
         default=None,
     )
 
-    VASTBASE_PASSWORD: Optional[str] = Field(
+    VASTBASE_PASSWORD: str | None = Field(
         description="Password for authenticating with the Vastbase database",
         default=None,
     )
 
-    VASTBASE_DATABASE: Optional[str] = Field(
+    VASTBASE_DATABASE: str | None = Field(
         description="Name of the Vastbase database to connect to",
         default=None,
     )

api/configs/middleware/vdb/vikingdb_config.py

@@ -1,5 +1,3 @@
-from typing import Optional
-
 from pydantic import Field
 from pydantic_settings import BaseSettings
 
@@ -11,14 +9,14 @@ class VikingDBConfig(BaseSettings):
     https://www.volcengine.com/docs/6291/65568
     """
 
-    VIKINGDB_ACCESS_KEY: Optional[str] = Field(
+    VIKINGDB_ACCESS_KEY: str | None = Field(
         description="The Access Key provided by Volcengine VikingDB for API authentication."
         "Refer to the following documentation for details on obtaining credentials:"
         "https://www.volcengine.com/docs/6291/65568",
         default=None,
     )
 
-    VIKINGDB_SECRET_KEY: Optional[str] = Field(
+    VIKINGDB_SECRET_KEY: str | None = Field(
         description="The Secret Key provided by Volcengine VikingDB for API authentication.",
         default=None,
     )

api/configs/middleware/vdb/weaviate_config.py

@@ -1,5 +1,3 @@
-from typing import Optional
-
 from pydantic import Field, PositiveInt
 from pydantic_settings import BaseSettings
 
@@ -9,12 +7,12 @@ class WeaviateConfig(BaseSettings):
     Configuration settings for Weaviate vector database
     """
 
-    WEAVIATE_ENDPOINT: Optional[str] = Field(
+    WEAVIATE_ENDPOINT: str | None = Field(
         description="URL of the Weaviate server (e.g., 'http://localhost:8080' or 'https://weaviate.example.com')",
         default=None,
     )
 
-    WEAVIATE_API_KEY: Optional[str] = Field(
+    WEAVIATE_API_KEY: str | None = Field(
         description="API key for authenticating with the Weaviate server",
         default=None,
     )
@@ -24,7 +22,17 @@ class WeaviateConfig(BaseSettings):
         default=True,
     )
 
+    WEAVIATE_GRPC_ENDPOINT: str | None = Field(
+        description="URL of the Weaviate gRPC server (e.g., 'grpc://localhost:50051' or 'grpcs://weaviate.example.com:443')",
+        default=None,
+    )
+
     WEAVIATE_BATCH_SIZE: PositiveInt = Field(
         description="Number of objects to be processed in a single batch operation (default is 100)",
         default=100,
     )
+
+    WEAVIATE_TOKENIZATION: str | None = Field(
+        description="Tokenization for Weaviate (default is word)",
+        default="word",
+    )

api/configs/remote_settings_sources/apollo/__init__.py

@@ -1,5 +1,5 @@
 from collections.abc import Mapping
-from typing import Any, Optional
+from typing import Any
 
 from pydantic import Field
 from pydantic.fields import FieldInfo
@@ -15,22 +15,22 @@ class ApolloSettingsSourceInfo(BaseSettings):
     Packaging build information
     """
 
-    APOLLO_APP_ID: Optional[str] = Field(
+    APOLLO_APP_ID: str | None = Field(
         description="apollo app_id",
         default=None,
     )
 
-    APOLLO_CLUSTER: Optional[str] = Field(
+    APOLLO_CLUSTER: str | None = Field(
         description="apollo cluster",
         default=None,
     )
 
-    APOLLO_CONFIG_URL: Optional[str] = Field(
+    APOLLO_CONFIG_URL: str | None = Field(
         description="apollo config url",
         default=None,
     )
 
-    APOLLO_NAMESPACE: Optional[str] = Field(
+    APOLLO_NAMESPACE: str | None = Field(
         description="apollo namespace",
         default=None,
     )

api/configs/remote_settings_sources/apollo/utils.py

@@ -29,7 +29,7 @@ def no_key_cache_key(namespace: str, key: str) -> str:
 
 
 # Returns whether the obtained value is obtained, and None if it does not
-def get_value_from_dict(namespace_cache: dict[str, Any] | None, key: str) -> Any | None:
+def get_value_from_dict(namespace_cache: dict[str, Any] | None, key: str) -> Any:
     if namespace_cache:
         kv_data = namespace_cache.get(CONFIGURATIONS)
         if kv_data is None:

api/configs/remote_settings_sources/nacos/http_request.py

@@ -5,7 +5,7 @@ import logging
 import os
 import time
 
-import requests
+import httpx
 
 logger = logging.getLogger(__name__)
 
@@ -30,10 +30,10 @@ class NacosHttpClient:
             params = {}
         try:
             self._inject_auth_info(headers, params)
-            response = requests.request(method, url="http://" + self.server + url, headers=headers, params=params)
+            response = httpx.request(method, url="http://" + self.server + url, headers=headers, params=params)
             response.raise_for_status()
             return response.text
-        except requests.RequestException as e:
+        except httpx.RequestError as e:
             return f"Request to Nacos failed: {e}"
 
     def _inject_auth_info(self, headers: dict[str, str], params: dict[str, str], module: str = "config") -> None:
@@ -78,7 +78,7 @@ class NacosHttpClient:
         params = {"username": self.username, "password": self.password}
         url = "http://" + self.server + "/nacos/v1/auth/login"
         try:
-            resp = requests.request("POST", url, headers=None, params=params)
+            resp = httpx.request("POST", url, headers=None, params=params)
             resp.raise_for_status()
             response_data = resp.json()
             self.token = response_data.get("accessToken")

api/constants/__init__.py

@@ -1,4 +1,5 @@
 from configs import dify_config
+from libs.collection_utils import convert_to_lower_and_upper_set
 
 HIDDEN_VALUE = "[__HIDDEN__]"
 UNKNOWN_VALUE = "[__UNKNOWN__]"
@@ -6,24 +7,39 @@ UUID_NIL = "00000000-0000-0000-0000-000000000000"
 
 DEFAULT_FILE_NUMBER_LIMITS = 3
 
-IMAGE_EXTENSIONS = ["jpg", "jpeg", "png", "webp", "gif", "svg"]
-IMAGE_EXTENSIONS.extend([ext.upper() for ext in IMAGE_EXTENSIONS])
+IMAGE_EXTENSIONS = convert_to_lower_and_upper_set({"jpg", "jpeg", "png", "webp", "gif", "svg"})
 
-VIDEO_EXTENSIONS = ["mp4", "mov", "mpeg", "webm"]
-VIDEO_EXTENSIONS.extend([ext.upper() for ext in VIDEO_EXTENSIONS])
+VIDEO_EXTENSIONS = convert_to_lower_and_upper_set({"mp4", "mov", "mpeg", "webm"})
 
-AUDIO_EXTENSIONS = ["mp3", "m4a", "wav", "amr", "mpga"]
-AUDIO_EXTENSIONS.extend([ext.upper() for ext in AUDIO_EXTENSIONS])
+AUDIO_EXTENSIONS = convert_to_lower_and_upper_set({"mp3", "m4a", "wav", "amr", "mpga"})
 
-
-_doc_extensions: list[str]
+_doc_extensions: set[str]
 if dify_config.ETL_TYPE == "Unstructured":
-    _doc_extensions = ["txt", "markdown", "md", "mdx", "pdf", "html", "htm", "xlsx", "xls", "vtt", "properties"]
-    _doc_extensions.extend(("doc", "docx", "csv", "eml", "msg", "pptx", "xml", "epub"))
+    _doc_extensions = {
+        "txt",
+        "markdown",
+        "md",
+        "mdx",
+        "pdf",
+        "html",
+        "htm",
+        "xlsx",
+        "xls",
+        "vtt",
+        "properties",
+        "doc",
+        "docx",
+        "csv",
+        "eml",
+        "msg",
+        "pptx",
+        "xml",
+        "epub",
+    }
     if dify_config.UNSTRUCTURED_API_URL:
-        _doc_extensions.append("ppt")
+        _doc_extensions.add("ppt")
 else:
-    _doc_extensions = [
+    _doc_extensions = {
         "txt",
         "markdown",
         "md",
@@ -37,5 +53,18 @@ else:
         "csv",
         "vtt",
         "properties",
-    ]
-DOCUMENT_EXTENSIONS = _doc_extensions + [ext.upper() for ext in _doc_extensions]
+    }
+DOCUMENT_EXTENSIONS: set[str] = convert_to_lower_and_upper_set(_doc_extensions)
+
+# console
+COOKIE_NAME_ACCESS_TOKEN = "access_token"
+COOKIE_NAME_REFRESH_TOKEN = "refresh_token"
+COOKIE_NAME_CSRF_TOKEN = "csrf_token"
+
+# webapp
+COOKIE_NAME_WEBAPP_ACCESS_TOKEN = "webapp_access_token"
+COOKIE_NAME_PASSPORT = "passport"
+
+HEADER_NAME_CSRF_TOKEN = "X-CSRF-Token"
+HEADER_NAME_APP_CODE = "X-App-Code"
+HEADER_NAME_PASSPORT = "X-App-Passport"

api/constants/languages.py

@@ -31,3 +31,9 @@ def supported_language(lang):
 
     error = f"{lang} is not a valid language."
     raise ValueError(error)
+
+
+def get_valid_language(lang: str | None) -> str:
+    if lang and lang in languages:
+        return lang
+    return languages[0]

api/contexts/__init__.py

@@ -5,9 +5,11 @@ from typing import TYPE_CHECKING
 from contexts.wrapper import RecyclableContextVar
 
 if TYPE_CHECKING:
+    from core.datasource.__base.datasource_provider import DatasourcePluginProviderController
     from core.model_runtime.entities.model_entities import AIModelEntity
     from core.plugin.entities.plugin_daemon import PluginModelProviderEntity
     from core.tools.plugin_tool.provider import PluginToolProviderController
+    from core.trigger.provider import PluginTriggerProviderController
 
 
 """
@@ -32,3 +34,19 @@ plugin_model_schema_lock: RecyclableContextVar[Lock] = RecyclableContextVar(Cont
 plugin_model_schemas: RecyclableContextVar[dict[str, "AIModelEntity"]] = RecyclableContextVar(
     ContextVar("plugin_model_schemas")
 )
+
+datasource_plugin_providers: RecyclableContextVar[dict[str, "DatasourcePluginProviderController"]] = (
+    RecyclableContextVar(ContextVar("datasource_plugin_providers"))
+)
+
+datasource_plugin_providers_lock: RecyclableContextVar[Lock] = RecyclableContextVar(
+    ContextVar("datasource_plugin_providers_lock")
+)
+
+plugin_trigger_providers: RecyclableContextVar[dict[str, "PluginTriggerProviderController"]] = RecyclableContextVar(
+    ContextVar("plugin_trigger_providers")
+)
+
+plugin_trigger_providers_lock: RecyclableContextVar[Lock] = RecyclableContextVar(
+    ContextVar("plugin_trigger_providers_lock")
+)

api/controllers/common/errors.py

@@ -25,6 +25,12 @@ class UnsupportedFileTypeError(BaseHTTPException):
     code = 415
 
 
+class BlockedFileExtensionError(BaseHTTPException):
+    error_code = "file_extension_blocked"
+    description = "The file extension is blocked for security reasons."
+    code = 400
+
+
 class TooManyFilesError(BaseHTTPException):
     error_code = "too_many_files"
     description = "Only one file is allowed."

api/controllers/common/helpers.py

@@ -24,7 +24,7 @@ except ImportError:
         )
     else:
         warnings.warn("To use python-magic guess MIMETYPE, you need to install `libmagic`", stacklevel=2)
-    magic = None  # type: ignore
+    magic = None  # type: ignore[assignment]
 
 from pydantic import BaseModel
 

api/controllers/console/__init__.py

@@ -1,31 +1,10 @@
+from importlib import import_module
+
 from flask import Blueprint
 from flask_restx import Namespace
 
 from libs.external_api import ExternalApi
 
-from .app.app_import import AppImportApi, AppImportCheckDependenciesApi, AppImportConfirmApi
-from .explore.audio import ChatAudioApi, ChatTextApi
-from .explore.completion import ChatApi, ChatStopApi, CompletionApi, CompletionStopApi
-from .explore.conversation import (
-    ConversationApi,
-    ConversationListApi,
-    ConversationPinApi,
-    ConversationRenameApi,
-    ConversationUnPinApi,
-)
-from .explore.message import (
-    MessageFeedbackApi,
-    MessageListApi,
-    MessageMoreLikeThisApi,
-    MessageSuggestedQuestionApi,
-)
-from .explore.workflow import (
-    InstalledAppWorkflowRunApi,
-    InstalledAppWorkflowTaskStopApi,
-)
-from .files import FileApi, FilePreviewApi, FileSupportTypeApi
-from .remote_files import RemoteFileInfoApi, RemoteFileUploadApi
-
 bp = Blueprint("console", __name__, url_prefix="/console/api")
 
 api = ExternalApi(
@@ -35,23 +14,23 @@ api = ExternalApi(
     description="Console management APIs for app configuration, monitoring, and administration",
 )
 
-# Create namespace
 console_ns = Namespace("console", description="Console management API operations", path="/")
 
-# File
-api.add_resource(FileApi, "/files/upload")
-api.add_resource(FilePreviewApi, "/files/<uuid:file_id>/preview")
-api.add_resource(FileSupportTypeApi, "/files/support-type")
+RESOURCE_MODULES = (
+    "controllers.console.app.app_import",
+    "controllers.console.explore.audio",
+    "controllers.console.explore.completion",
+    "controllers.console.explore.conversation",
+    "controllers.console.explore.message",
+    "controllers.console.explore.workflow",
+    "controllers.console.files",
+    "controllers.console.remote_files",
+)
 
-# Remote files
-api.add_resource(RemoteFileInfoApi, "/remote-files/<path:url>")
-api.add_resource(RemoteFileUploadApi, "/remote-files/upload")
-
-# Import App
-api.add_resource(AppImportApi, "/apps/imports")
-api.add_resource(AppImportConfirmApi, "/apps/imports/<string:import_id>/confirm")
-api.add_resource(AppImportCheckDependenciesApi, "/apps/imports/<string:app_id>/check-dependencies")
+for module_name in RESOURCE_MODULES:
+    import_module(module_name)
 
+# Ensure resource modules are imported so route decorators are evaluated.
 # Import other controllers
 from . import (
     admin,
@@ -61,6 +40,7 @@ from . import (
     init_validate,
     ping,
     setup,
+    spec,
     version,
 )
 
@@ -86,6 +66,7 @@ from .app import (
     workflow_draft_variable,
     workflow_run,
     workflow_statistic,
+    workflow_trigger,
 )
 
 # Import auth controllers
@@ -114,6 +95,15 @@ from .datasets import (
     metadata,
     website,
 )
+from .datasets.rag_pipeline import (
+    datasource_auth,
+    datasource_content_preview,
+    rag_pipeline,
+    rag_pipeline_datasets,
+    rag_pipeline_draft_variable,
+    rag_pipeline_import,
+    rag_pipeline_workflow,
+)
 
 # Import explore controllers
 from .explore import (
@@ -137,80 +127,10 @@ from .workspace import (
     models,
     plugin,
     tool_providers,
+    trigger_providers,
     workspace,
 )
 
-# Explore Audio
-api.add_resource(ChatAudioApi, "/installed-apps/<uuid:installed_app_id>/audio-to-text", endpoint="installed_app_audio")
-api.add_resource(ChatTextApi, "/installed-apps/<uuid:installed_app_id>/text-to-audio", endpoint="installed_app_text")
-
-# Explore Completion
-api.add_resource(
-    CompletionApi, "/installed-apps/<uuid:installed_app_id>/completion-messages", endpoint="installed_app_completion"
-)
-api.add_resource(
-    CompletionStopApi,
-    "/installed-apps/<uuid:installed_app_id>/completion-messages/<string:task_id>/stop",
-    endpoint="installed_app_stop_completion",
-)
-api.add_resource(
-    ChatApi, "/installed-apps/<uuid:installed_app_id>/chat-messages", endpoint="installed_app_chat_completion"
-)
-api.add_resource(
-    ChatStopApi,
-    "/installed-apps/<uuid:installed_app_id>/chat-messages/<string:task_id>/stop",
-    endpoint="installed_app_stop_chat_completion",
-)
-
-# Explore Conversation
-api.add_resource(
-    ConversationRenameApi,
-    "/installed-apps/<uuid:installed_app_id>/conversations/<uuid:c_id>/name",
-    endpoint="installed_app_conversation_rename",
-)
-api.add_resource(
-    ConversationListApi, "/installed-apps/<uuid:installed_app_id>/conversations", endpoint="installed_app_conversations"
-)
-api.add_resource(
-    ConversationApi,
-    "/installed-apps/<uuid:installed_app_id>/conversations/<uuid:c_id>",
-    endpoint="installed_app_conversation",
-)
-api.add_resource(
-    ConversationPinApi,
-    "/installed-apps/<uuid:installed_app_id>/conversations/<uuid:c_id>/pin",
-    endpoint="installed_app_conversation_pin",
-)
-api.add_resource(
-    ConversationUnPinApi,
-    "/installed-apps/<uuid:installed_app_id>/conversations/<uuid:c_id>/unpin",
-    endpoint="installed_app_conversation_unpin",
-)
-
-
-# Explore Message
-api.add_resource(MessageListApi, "/installed-apps/<uuid:installed_app_id>/messages", endpoint="installed_app_messages")
-api.add_resource(
-    MessageFeedbackApi,
-    "/installed-apps/<uuid:installed_app_id>/messages/<uuid:message_id>/feedbacks",
-    endpoint="installed_app_message_feedback",
-)
-api.add_resource(
-    MessageMoreLikeThisApi,
-    "/installed-apps/<uuid:installed_app_id>/messages/<uuid:message_id>/more-like-this",
-    endpoint="installed_app_more_like_this",
-)
-api.add_resource(
-    MessageSuggestedQuestionApi,
-    "/installed-apps/<uuid:installed_app_id>/messages/<uuid:message_id>/suggested-questions",
-    endpoint="installed_app_suggested_question",
-)
-# Explore Workflow
-api.add_resource(InstalledAppWorkflowRunApi, "/installed-apps/<uuid:installed_app_id>/workflows/run")
-api.add_resource(
-    InstalledAppWorkflowTaskStopApi, "/installed-apps/<uuid:installed_app_id>/workflows/tasks/<string:task_id>/stop"
-)
-
 api.add_namespace(console_ns)
 
 __all__ = [
@@ -238,6 +158,8 @@ __all__ = [
     "datasets",
     "datasets_document",
     "datasets_segments",
+    "datasource_auth",
+    "datasource_content_preview",
     "email_register",
     "endpoint",
     "extension",
@@ -263,13 +185,20 @@ __all__ = [
     "parameter",
     "ping",
     "plugin",
+    "rag_pipeline",
+    "rag_pipeline_datasets",
+    "rag_pipeline_draft_variable",
+    "rag_pipeline_import",
+    "rag_pipeline_workflow",
     "recommended_app",
     "saved_message",
     "setup",
     "site",
+    "spec",
     "statistic",
     "tags",
     "tool_providers",
+    "trigger_providers",
     "version",
     "website",
     "workflow",
@@ -277,5 +206,6 @@ __all__ = [
     "workflow_draft_variable",
     "workflow_run",
     "workflow_statistic",
+    "workflow_trigger",
     "workspace",
 ]

api/controllers/console/admin.py

@@ -12,9 +12,10 @@ P = ParamSpec("P")
 R = TypeVar("R")
 from configs import dify_config
 from constants.languages import supported_language
-from controllers.console import api, console_ns
+from controllers.console import console_ns
 from controllers.console.wraps import only_edition_cloud
 from extensions.ext_database import db
+from libs.token import extract_access_token
 from models.model import App, InstalledApp, RecommendedApp
 
 
@@ -24,19 +25,9 @@ def admin_required(view: Callable[P, R]):
         if not dify_config.ADMIN_API_KEY:
             raise Unauthorized("API key is invalid.")
 
-        auth_header = request.headers.get("Authorization")
-        if auth_header is None:
+        auth_token = extract_access_token(request)
+        if not auth_token:
             raise Unauthorized("Authorization header is missing.")
-
-        if " " not in auth_header:
-            raise Unauthorized("Invalid Authorization header format. Expected 'Bearer <api-key>' format.")
-
-        auth_scheme, auth_token = auth_header.split(None, 1)
-        auth_scheme = auth_scheme.lower()
-
-        if auth_scheme != "bearer":
-            raise Unauthorized("Invalid Authorization header format. Expected 'Bearer <api-key>' format.")
-
         if auth_token != dify_config.ADMIN_API_KEY:
             raise Unauthorized("API key is invalid.")
 
@@ -47,10 +38,10 @@ def admin_required(view: Callable[P, R]):
 
 @console_ns.route("/admin/insert-explore-apps")
 class InsertExploreAppListApi(Resource):
-    @api.doc("insert_explore_app")
-    @api.doc(description="Insert or update an app in the explore list")
-    @api.expect(
-        api.model(
+    @console_ns.doc("insert_explore_app")
+    @console_ns.doc(description="Insert or update an app in the explore list")
+    @console_ns.expect(
+        console_ns.model(
             "InsertExploreAppRequest",
             {
                 "app_id": fields.String(required=True, description="Application ID"),
@@ -64,21 +55,23 @@ class InsertExploreAppListApi(Resource):
             },
         )
     )
-    @api.response(200, "App updated successfully")
-    @api.response(201, "App inserted successfully")
-    @api.response(404, "App not found")
+    @console_ns.response(200, "App updated successfully")
+    @console_ns.response(201, "App inserted successfully")
+    @console_ns.response(404, "App not found")
     @only_edition_cloud
     @admin_required
     def post(self):
-        parser = reqparse.RequestParser()
-        parser.add_argument("app_id", type=str, required=True, nullable=False, location="json")
-        parser.add_argument("desc", type=str, location="json")
-        parser.add_argument("copyright", type=str, location="json")
-        parser.add_argument("privacy_policy", type=str, location="json")
-        parser.add_argument("custom_disclaimer", type=str, location="json")
-        parser.add_argument("language", type=supported_language, required=True, nullable=False, location="json")
-        parser.add_argument("category", type=str, required=True, nullable=False, location="json")
-        parser.add_argument("position", type=int, required=True, nullable=False, location="json")
+        parser = (
+            reqparse.RequestParser()
+            .add_argument("app_id", type=str, required=True, nullable=False, location="json")
+            .add_argument("desc", type=str, location="json")
+            .add_argument("copyright", type=str, location="json")
+            .add_argument("privacy_policy", type=str, location="json")
+            .add_argument("custom_disclaimer", type=str, location="json")
+            .add_argument("language", type=supported_language, required=True, nullable=False, location="json")
+            .add_argument("category", type=str, required=True, nullable=False, location="json")
+            .add_argument("position", type=int, required=True, nullable=False, location="json")
+        )
         args = parser.parse_args()
 
         app = db.session.execute(select(App).where(App.id == args["app_id"])).scalar_one_or_none()
@@ -138,10 +131,10 @@ class InsertExploreAppListApi(Resource):
 
 @console_ns.route("/admin/insert-explore-apps/<uuid:app_id>")
 class InsertExploreAppApi(Resource):
-    @api.doc("delete_explore_app")
-    @api.doc(description="Remove an app from the explore list")
-    @api.doc(params={"app_id": "Application ID to remove"})
-    @api.response(204, "App removed successfully")
+    @console_ns.doc("delete_explore_app")
+    @console_ns.doc(description="Remove an app from the explore list")
+    @console_ns.doc(params={"app_id": "Application ID to remove"})
+    @console_ns.response(204, "App removed successfully")
     @only_edition_cloud
     @admin_required
     def delete(self, app_id):