Merge commit 'c236f05f4b575884b42fc45819ad71b05a22115c'

* commit 'c236f05f4b575884b42fc45819ad71b05a22115c': (135 commits)
  chore: bump version to 0.15.0 (langgenius#12297)
  refactor: enhance API token validation with session locking and last used timestamp update (langgenius#12426)
  Fix newline characters in tables during document parsing (langgenius#12112)
  fix:deepseek tool call not working correctly (langgenius#12437)
  add fish-speech-1.5 from siliconflow (langgenius#12425)
  chore(docker/.env.example): Add TOP_K_MAX_VALUE to the `.env.example`… (langgenius#12422)
  refactor: use tiktoken for token calculation (langgenius#12416)
  fix: [PromptEditorHeightResizeWrap] Bug  langgenius#12410  (langgenius#12406)
  Fixes langgenius#12414: Add cheaper model and long context model for Qwen2.5-72B-Instruct from siliconflow (langgenius#12415)
  Support TTS and Speech2Text for Model Provider GPUStack (langgenius#12381)
  mark deprecated models in siliconflow langgenius#12399 (langgenius#12405)
  fix: http method can be upper case and lower case close langgenius#11877 (langgenius#12401)
  fix: enhance chunk list management with new invalidation keys and imp… (langgenius#12396)
  [Fix] revert sagemaker llm to support model hub (langgenius#12378)
  sandbox doesn't provide auto disable log (langgenius#12388)
  feat: support config top max value by env (langgenius#12375)
  chore: chat app textarea auto focus (langgenius#12366)
  feat: support configuration of refresh token expiration by environment variable (langgenius#12335)
  fix: resolve issue with the opening statement generated by the `AutomaticRes` component failing to sync between states. (langgenius#12349)
  Fix the issue where `TextGeneration` component does not correctly clear input data. (langgenius#12351)
  ...

# Conflicts:
#	api/core/helper/code_executor/code_executor.py
#	api/poetry.lock

.github/workflows/api-tests.yml

@@ -56,6 +56,12 @@ jobs:
       - name: Run Tool
         run: poetry run -C api bash dev/pytest/pytest_tools.sh
 
+      - name: Run mypy
+        run: |
+          pushd api
+          poetry run python -m mypy --install-types --non-interactive .
+          popd
+
       - name: Set up dotenvs
         run: |
           cp docker/.env.example docker/.env

api/.env.example

@@ -23,6 +23,9 @@ FILES_ACCESS_TIMEOUT=300
 # Access token expiration time in minutes
 ACCESS_TOKEN_EXPIRE_MINUTES=60
 
+# Refresh token expiration time in days
+REFRESH_TOKEN_EXPIRE_DAYS=30
+
 # celery configuration
 CELERY_BROKER_URL=redis://:difyai123456@localhost:6379/1
 
@@ -65,7 +68,7 @@ OPENDAL_FS_ROOT=storage
 
 # S3 Storage configuration
 S3_USE_AWS_MANAGED_IAM=false
-S3_ENDPOINT=https://your-bucket-name.storage.s3.clooudflare.com
+S3_ENDPOINT=https://your-bucket-name.storage.s3.cloudflare.com
 S3_BUCKET_NAME=your-bucket-name
 S3_ACCESS_KEY=your-access-key
 S3_SECRET_KEY=your-secret-key
@@ -74,7 +77,7 @@ S3_REGION=your-region
 # Azure Blob Storage configuration
 AZURE_BLOB_ACCOUNT_NAME=your-account-name
 AZURE_BLOB_ACCOUNT_KEY=your-account-key
-AZURE_BLOB_CONTAINER_NAME=yout-container-name
+AZURE_BLOB_CONTAINER_NAME=your-container-name
 AZURE_BLOB_ACCOUNT_URL=https://<your_account_name>.blob.core.windows.net
 
 # Aliyun oss Storage configuration
@@ -88,7 +91,7 @@ ALIYUN_OSS_REGION=your-region
 ALIYUN_OSS_PATH=your-path
 
 # Google Storage configuration
-GOOGLE_STORAGE_BUCKET_NAME=yout-bucket-name
+GOOGLE_STORAGE_BUCKET_NAME=your-bucket-name
 GOOGLE_STORAGE_SERVICE_ACCOUNT_JSON_BASE64=your-google-service-account-json-base64-string
 
 # Tencent COS Storage configuration

api/.ruff.toml

@@ -67,7 +67,7 @@ ignore = [
     "SIM105", # suppressible-exception
     "SIM107", # return-in-try-except-finally
     "SIM108", # if-else-block-instead-of-if-exp
-    "SIM113", # eumerate-for-loop
+    "SIM113", # enumerate-for-loop
     "SIM117", # multiple-with-statements
     "SIM210", # if-expr-with-true-false
 ]
@@ -85,11 +85,11 @@ ignore = [
 ]
 "tests/*" = [
     "F811", # redefined-while-unused
-    "F401", # unused-import
 ]
 
 [lint.pyflakes]
-extend-generics = [
+allowed-unused-imports = [
     "_pytest.monkeypatch",
     "tests.integration_tests",
+    "tests.unit_tests",
 ]

api/Dockerfile

@@ -55,7 +55,7 @@ RUN apt-get update \
     && echo "deb http://deb.debian.org/debian testing main" > /etc/apt/sources.list \
     && apt-get update \
     # For Security
-    && apt-get install -y --no-install-recommends expat=2.6.4-1 libldap-2.5-0=2.5.18+dfsg-3+b1 perl=5.40.0-8 libsqlite3-0=3.46.1-1 zlib1g=1:1.3.dfsg+really1.3.1-1+b1 \
+    && apt-get install -y --no-install-recommends expat=2.6.4-1 libldap-2.5-0=2.5.19+dfsg-1 perl=5.40.0-8 libsqlite3-0=3.46.1-1 zlib1g=1:1.3.dfsg+really1.3.1-1+b1 \
     # install a chinese font to support the use of tools like matplotlib
     && apt-get install -y fonts-noto-cjk \
     && apt-get autoremove -y \

api/app.py

@@ -1,12 +1,8 @@
-from libs import version_utils
-
-# preparation before creating app
-version_utils.check_supported_python_version()
+import os
+import sys
 
 
 def is_db_command():
-    import sys
-
     if len(sys.argv) > 1 and sys.argv[0].endswith("flask") and sys.argv[1] == "db":
         return True
     return False
@@ -18,10 +14,25 @@ def is_db_command():
 
     app = create_migrations_app()
 else:
-    from app_factory import create_app
-    from libs import threadings_utils
+    # 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  # type: ignore
+
+        # gevent
+        monkey.patch_all()
+
+        from grpc.experimental import gevent as grpc_gevent  # type: ignore
 
-    threadings_utils.apply_gevent_threading_patch()
+        # grpc gevent
+        grpc_gevent.init_gevent()
+
+        import psycogreen.gevent  # type: ignore
+
+        psycogreen.gevent.patch_psycopg()
+
+    from app_factory import create_app
 
     app = create_app()
     celery = app.extensions["celery"]

api/commands.py

@@ -159,8 +159,7 @@ def migrate_annotation_vector_database():
         try:
             # get apps info
             apps = (
-                db.session.query(App)
-                .filter(App.status == "normal")
+                App.query.filter(App.status == "normal")
                 .order_by(App.created_at.desc())
                 .paginate(page=page, per_page=50)
             )
@@ -285,8 +284,7 @@ def migrate_knowledge_vector_database():
     while True:
         try:
             datasets = (
-                db.session.query(Dataset)
-                .filter(Dataset.indexing_technique == "high_quality")
+                Dataset.query.filter(Dataset.indexing_technique == "high_quality")
                 .order_by(Dataset.created_at.desc())
                 .paginate(page=page, per_page=50)
             )
@@ -450,7 +448,8 @@ def convert_to_agent_apps():
                 if app_id not in proceeded_app_ids:
                     proceeded_app_ids.append(app_id)
                     app = db.session.query(App).filter(App.id == app_id).first()
-                    apps.append(app)
+                    if app is not None:
+                        apps.append(app)
 
             if len(apps) == 0:
                 break
@@ -562,8 +561,13 @@ def create_tenant(email: str, language: Optional[str] = None, name: Optional[str
     new_password = secrets.token_urlsafe(16)
 
     # register account
-    account = RegisterService.register(email=email, name=account_name, password=new_password, language=language)
-
+    account = RegisterService.register(
+        email=email,
+        name=account_name,
+        password=new_password,
+        language=language,
+        create_workspace_required=False,
+    )
     TenantService.create_owner_tenant_if_not_exist(account, name)
 
     click.echo(
@@ -583,7 +587,7 @@ def upgrade_db():
             click.echo(click.style("Starting database migration.", fg="green"))
 
             # run db migration
-            import flask_migrate
+            import flask_migrate  # type: ignore
 
             flask_migrate.upgrade()
 
@@ -621,6 +625,10 @@ def fix_app_site_missing():
 
                 try:
                     app = db.session.query(App).filter(App.id == app_id).first()
+                    if not app:
+                        print(f"App {app_id} not found")
+                        continue
+
                     tenant = app.tenant
                     if tenant:
                         accounts = tenant.get_accounts()

api/configs/feature/__init__.py

@@ -240,7 +240,6 @@ class HttpConfig(BaseSettings):
     )
 
     @computed_field
-    @property
     def CONSOLE_CORS_ALLOW_ORIGINS(self) -> list[str]:
         return self.inner_CONSOLE_CORS_ALLOW_ORIGINS.split(",")
 
@@ -251,7 +250,6 @@ def CONSOLE_CORS_ALLOW_ORIGINS(self) -> list[str]:
     )
 
     @computed_field
-    @property
     def WEB_API_CORS_ALLOW_ORIGINS(self) -> list[str]:
         return self.inner_WEB_API_CORS_ALLOW_ORIGINS.split(",")
 
@@ -491,6 +489,11 @@ class AuthConfig(BaseSettings):
         default=60,
     )
 
+    REFRESH_TOKEN_EXPIRE_DAYS: PositiveFloat = Field(
+        description="Expiration time for refresh tokens in days",
+        default=30,
+    )
+
     LOGIN_LOCKOUT_DURATION: PositiveInt = Field(
         description="Time (in seconds) a user must wait before retrying login after exceeding the rate limit.",
         default=86400,
@@ -604,7 +607,7 @@ class RagEtlConfig(BaseSettings):
 
     UNSTRUCTURED_API_KEY: Optional[str] = Field(
         description="API key for Unstructured.io service",
-        default=None,
+        default="",
     )
 
     SCARF_NO_ANALYTICS: Optional[str] = Field(
@@ -670,6 +673,11 @@ class IndexingConfig(BaseSettings):
         default=4000,
     )
 
+    CHILD_CHUNKS_PREVIEW_NUMBER: PositiveInt = Field(
+        description="Maximum number of child chunks to preview",
+        default=50,
+    )
+
 
 class MultiModalTransferConfig(BaseSettings):
     MULTIMODAL_SEND_FORMAT: Literal["base64", "url"] = Field(
@@ -716,27 +724,27 @@ class PositionConfig(BaseSettings):
         default="",
     )
 
-    @computed_field
+    @property
     def POSITION_PROVIDER_PINS_LIST(self) -> list[str]:
         return [item.strip() for item in self.POSITION_PROVIDER_PINS.split(",") if item.strip() != ""]
 
-    @computed_field
+    @property
     def POSITION_PROVIDER_INCLUDES_SET(self) -> set[str]:
         return {item.strip() for item in self.POSITION_PROVIDER_INCLUDES.split(",") if item.strip() != ""}
 
-    @computed_field
+    @property
     def POSITION_PROVIDER_EXCLUDES_SET(self) -> set[str]:
         return {item.strip() for item in self.POSITION_PROVIDER_EXCLUDES.split(",") if item.strip() != ""}
 
-    @computed_field
+    @property
     def POSITION_TOOL_PINS_LIST(self) -> list[str]:
         return [item.strip() for item in self.POSITION_TOOL_PINS.split(",") if item.strip() != ""]
 
-    @computed_field
+    @property
     def POSITION_TOOL_INCLUDES_SET(self) -> set[str]:
         return {item.strip() for item in self.POSITION_TOOL_INCLUDES.split(",") if item.strip() != ""}
 
-    @computed_field
+    @property
     def POSITION_TOOL_EXCLUDES_SET(self) -> set[str]:
         return {item.strip() for item in self.POSITION_TOOL_EXCLUDES.split(",") if item.strip() != ""}
 
@@ -768,6 +776,13 @@ class LoginConfig(BaseSettings):
     )
 
 
+class AccountConfig(BaseSettings):
+    ACCOUNT_DELETION_TOKEN_EXPIRY_MINUTES: PositiveInt = Field(
+        description="Duration in minutes for which a account deletion token remains valid",
+        default=5,
+    )
+
+
 class FeatureConfig(
     # place the configs in alphabet order
     AppExecutionConfig,
@@ -795,6 +810,7 @@ class FeatureConfig(
     WorkflowNodeExecutionConfig,
     WorkspaceConfig,
     LoginConfig,
+    AccountConfig,
     # hosted services config
     HostedServiceConfig,
     CeleryBeatConfig,

api/configs/middleware/__init__.py

@@ -130,7 +130,6 @@ class DatabaseConfig(BaseSettings):
     )
 
     @computed_field
-    @property
     def SQLALCHEMY_DATABASE_URI(self) -> str:
         db_extras = (
             f"{self.DB_EXTRAS}&client_encoding={self.DB_CHARSET}" if self.DB_CHARSET else self.DB_EXTRAS
@@ -168,7 +167,6 @@ def SQLALCHEMY_DATABASE_URI(self) -> str:
     )
 
     @computed_field
-    @property
     def SQLALCHEMY_ENGINE_OPTIONS(self) -> dict[str, Any]:
         return {
             "pool_size": self.SQLALCHEMY_POOL_SIZE,
@@ -206,15 +204,13 @@ class CeleryConfig(DatabaseConfig):
     )
 
     @computed_field
-    @property
     def CELERY_RESULT_BACKEND(self) -> str | None:
         return (
             "db+{}".format(self.SQLALCHEMY_DATABASE_URI)
             if self.CELERY_BACKEND == "database"
             else self.CELERY_BROKER_URL
         )
 
-    @computed_field
     @property
     def BROKER_USE_SSL(self) -> bool:
         return self.CELERY_BROKER_URL.startswith("rediss://") if self.CELERY_BROKER_URL else False

api/configs/packaging/__init__.py

@@ -9,7 +9,7 @@ class PackagingInfo(BaseSettings):
 
     CURRENT_VERSION: str = Field(
         description="Dify version",
-        default="0.14.2",
+        default="0.15.0",
     )
 
     COMMIT_SHA: str = Field(

api/configs/remote_settings_sources/apollo/client.py

@@ -4,6 +4,7 @@
 import os
 import threading
 import time
+from collections.abc import Mapping
 from pathlib import Path
 
 from .python_3x import http_request, makedirs_wrapper
@@ -255,8 +256,8 @@ def _listener(self):
         logger.info("stopped, long_poll")
 
     # add the need for endorsement to the header
-    def _sign_headers(self, url):
-        headers = {}
+    def _sign_headers(self, url: str) -> Mapping[str, str]:
+        headers: dict[str, str] = {}
         if self.secret == "":
             return headers
         uri = url[len(self.config_url) : len(url)]

api/constants/model_template.py

@@ -1,8 +1,9 @@
 import json
+from collections.abc import Mapping
 
 from models.model import AppMode
 
-default_app_templates = {
+default_app_templates: Mapping[AppMode, Mapping] = {
     # workflow default mode
     AppMode.WORKFLOW: {
         "app": {

api/controllers/common/fields.py

@@ -1,4 +1,4 @@
-from flask_restful import fields
+from flask_restful import fields  # type: ignore
 
 parameters__system_parameters = {
     "image_file_size_limit": fields.Integer,