Merge branch 'langgenius:main' into main

Author: henrybit

.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

@@ -6,11 +6,10 @@ cd web && pnpm install
 pipx install uv
 
 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 gevent -c 1 --loglevel INFO -Q dataset,generation,mail,ops_trace,app_deletion,plugin,workflow_storage\"" >> ~/.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
-

.github/workflows/autofix.yml

@@ -2,6 +2,8 @@ name: autofix.ci
 on:
   pull_request:
     branches: ["main"]
+  push:
+    branches: ["main"]
 permissions:
   contents: read
 

.github/workflows/style.yml

@@ -103,6 +103,11 @@ jobs:
         run: |
           pnpm run lint
 
+      - 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
     runs-on: ubuntu-latest

.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
@@ -234,4 +238,7 @@ scripts/stress-test/reports/
 
 # mcp
 .playwright-mcp/
-.serena/
+.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,mail,ops_trace,app_deletion,plugin,workflow_storage,conversation,priority_pipeline,pipeline",
                 "--loglevel",
                 "INFO"
             ],

README.md

@@ -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.
 

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
 
@@ -156,6 +159,9 @@ SUPABASE_URL=your-server-url
 # CORS configuration
 WEB_API_CORS_ALLOW_ORIGINS=http://localhost:3000,*
 CONSOLE_CORS_ALLOW_ORIGINS=http://localhost:3000,*
+# Set COOKIE_DOMAIN when the console frontend and API are on different subdomains.
+# Provide the registrable 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`.
@@ -368,6 +374,12 @@ 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
@@ -457,6 +469,9 @@ 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
 
@@ -512,7 +527,7 @@ 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)
@@ -534,6 +549,12 @@ 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=
@@ -605,3 +626,9 @@ 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/.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.