feat: agent node custom tool input

fix: ci
Merge branch 'plugins/beta' into dev/plugin-deploy
2025-02-07 11:02:31 +08:00 · 2025-02-06 18:36:14 +08:00 · 2025-02-06 18:30:49 +08:00 · 2025-01-26 16:08:58 +08:00 · 2025-01-26 16:05:19 +08:00 · 2025-01-22 09:59:40 +08:00
291 changed files with 2768 additions and 4552 deletions
@@ -6,6 +6,7 @@ on:
      - "main"
      - "deploy/dev"
      - "plugins/beta"
+      - "dev/plugin-deploy"
  release:
    types: [published]

@@ -140,3 +141,16 @@ jobs:
      - name: Inspect image
        run: |
          docker buildx imagetools inspect ${{ env[matrix.image_name_env] }}:${{ steps.meta.outputs.version }}
+
+      - name: print context var
+        uses: actions/checkout@v4
+
+      - name: deploy pod in plugin env
+        if: github.ref == 'refs/heads/dev/plugin-deploy'
+        env:
+          IMAGEHASH: ${{ github.sha }}
+          APICMD: "${{ secrets.PLUGIN_CD_API_CURL }}"
+          WEBCMD: "${{ secrets.PLUGIN_CD_WEB_CURL }}"
+        run: |
+          bash -c "${APICMD/yourNewVersion/$IMAGEHASH}"
+          bash -c "${WEBCMD/yourNewVersion/$IMAGEHASH}"
@@ -0,0 +1,23 @@
+name: Deploy Plugin Dev
+
+on:
+  workflow_run:
+    workflows: ["Build and Push API & Web"]
+    branches:
+      - "dev/plugin-deploy"
+    types:
+      - completed
+
+jobs:
+  deploy:
+    runs-on: ubuntu-latest
+    if: |
+      github.event.workflow_run.conclusion == 'success'
+    steps:
+      - name: Deploy to server
+        uses: appleboy/ssh-action@v0.1.8
+        with:
+          host: ${{ secrets.SSH_HOST }}
+          username: ${{ secrets.SSH_USER }}
+          key: ${{ secrets.SSH_PRIVATE_KEY }}
+          script: "echo 123"
@@ -1,47 +0,0 @@
-name: Build docker image
-
-on:
-  pull_request:
-    branches:
-      - "main"
-    paths:
-      - api/Dockerfile
-      - web/Dockerfile
-
-concurrency:
-  group: docker-build-${{ github.head_ref || github.run_id }}
-  cancel-in-progress: true
-
-jobs:
-  build-docker:
-    runs-on: ubuntu-latest
-    strategy:
-      matrix:
-        include:
-          - service_name: "api-amd64"
-            platform: linux/amd64
-            context: "api"
-          - service_name: "api-arm64"
-            platform: linux/arm64
-            context: "api"
-          - service_name: "web-amd64"
-            platform: linux/amd64
-            context: "web"
-          - service_name: "web-arm64"
-            platform: linux/arm64
-            context: "web"
-    steps:
-      - name: Set up QEMU
-        uses: docker/setup-qemu-action@v3
-
-      - name: Set up Docker Buildx
-        uses: docker/setup-buildx-action@v3
-
-      - name: Build Docker Image
-        uses: docker/build-push-action@v6
-        with:
-          push: false
-          context: "{{defaultContext}}:${{ matrix.context }}"
-          platforms: ${{ matrix.platform }}
-          cache-from: type=gha
-          cache-to: type=gha,mode=max
@@ -25,9 +25,6 @@
    <a href="https://twitter.com/intent/follow?screen_name=dify_ai" target="_blank">
        <img src="https://img.shields.io/twitter/follow/dify_ai?logo=X&color=%20%23f5f5f5"
            alt="follow on X(Twitter)"></a>
-    <a href="https://www.linkedin.com/company/langgenius/" target="_blank">
-        <img src="https://custom-icon-badges.demolab.com/badge/LinkedIn-0A66C2?logo=linkedin-white&logoColor=fff"
-            alt="follow on LinkedIn"></a>
    <a href="https://hub.docker.com/u/langgenius" target="_blank">
        <img alt="Docker Pulls" src="https://img.shields.io/docker/pulls/langgenius/dify-web?labelColor=%20%23FDB062&color=%20%23f79009"></a>
    <a href="https://github.com/langgenius/dify/graphs/commit-activity" target="_blank">
@@ -21,9 +21,6 @@
    <a href="https://twitter.com/intent/follow?screen_name=dify_ai" target="_blank">
        <img src="https://img.shields.io/twitter/follow/dify_ai?logo=X&color=%20%23f5f5f5"
            alt="follow on X(Twitter)"></a>
-    <a href="https://www.linkedin.com/company/langgenius/" target="_blank">
-        <img src="https://custom-icon-badges.demolab.com/badge/LinkedIn-0A66C2?logo=linkedin-white&logoColor=fff"
-            alt="follow on LinkedIn"></a>
    <a href="https://hub.docker.com/u/langgenius" target="_blank">
        <img alt="Docker Pulls" src="https://img.shields.io/docker/pulls/langgenius/dify-web?labelColor=%20%23FDB062&color=%20%23f79009"></a>
    <a href="https://github.com/langgenius/dify/graphs/commit-activity" target="_blank">
@@ -21,9 +21,6 @@
    <a href="https://twitter.com/intent/follow?screen_name=dify_ai" target="_blank">
        <img src="https://img.shields.io/twitter/follow/dify_ai?logo=X&color=%20%23f5f5f5"
            alt="follow on X(Twitter)"></a>
-    <a href="https://www.linkedin.com/company/langgenius/" target="_blank">
-        <img src="https://custom-icon-badges.demolab.com/badge/LinkedIn-0A66C2?logo=linkedin-white&logoColor=fff"
-            alt="follow on LinkedIn"></a>
    <a href="https://hub.docker.com/u/langgenius" target="_blank">
        <img alt="Docker Pulls" src="https://img.shields.io/docker/pulls/langgenius/dify-web?labelColor=%20%23FDB062&color=%20%23f79009"></a>
    <a href="https://github.com/langgenius/dify/graphs/commit-activity" target="_blank">
@@ -21,9 +21,6 @@
    <a href="https://twitter.com/intent/follow?screen_name=dify_ai" target="_blank">
        <img src="https://img.shields.io/twitter/follow/dify_ai?logo=X&color=%20%23f5f5f5"
            alt="seguir en X(Twitter)"></a>
-    <a href="https://www.linkedin.com/company/langgenius/" target="_blank">
-        <img src="https://custom-icon-badges.demolab.com/badge/LinkedIn-0A66C2?logo=linkedin-white&logoColor=fff"
-            alt="seguir en LinkedIn"></a>
    <a href="https://hub.docker.com/u/langgenius" target="_blank">
        <img alt="Descargas de Docker" src="https://img.shields.io/docker/pulls/langgenius/dify-web?labelColor=%20%23FDB062&color=%20%23f79009"></a>
    <a href="https://github.com/langgenius/dify/graphs/commit-activity" target="_blank">
@@ -21,9 +21,6 @@
    <a href="https://twitter.com/intent/follow?screen_name=dify_ai" target="_blank">
        <img src="https://img.shields.io/twitter/follow/dify_ai?logo=X&color=%20%23f5f5f5"
            alt="suivre sur X(Twitter)"></a>
-    <a href="https://www.linkedin.com/company/langgenius/" target="_blank">
-        <img src="https://custom-icon-badges.demolab.com/badge/LinkedIn-0A66C2?logo=linkedin-white&logoColor=fff"
-            alt="suivre sur LinkedIn"></a>
    <a href="https://hub.docker.com/u/langgenius" target="_blank">
        <img alt="Tirages Docker" src="https://img.shields.io/docker/pulls/langgenius/dify-web?labelColor=%20%23FDB062&color=%20%23f79009"></a>
    <a href="https://github.com/langgenius/dify/graphs/commit-activity" target="_blank">
@@ -21,9 +21,6 @@
    <a href="https://twitter.com/intent/follow?screen_name=dify_ai" target="_blank">
        <img src="https://img.shields.io/twitter/follow/dify_ai?logo=X&color=%20%23f5f5f5"
            alt="X(Twitter)でフォロー"></a>
-    <a href="https://www.linkedin.com/company/langgenius/" target="_blank">
-        <img src="https://custom-icon-badges.demolab.com/badge/LinkedIn-0A66C2?logo=linkedin-white&logoColor=fff"
-            alt="LinkedInでフォロー"></a>
    <a href="https://hub.docker.com/u/langgenius" target="_blank">
        <img alt="Docker Pulls" src="https://img.shields.io/docker/pulls/langgenius/dify-web?labelColor=%20%23FDB062&color=%20%23f79009"></a>
    <a href="https://github.com/langgenius/dify/graphs/commit-activity" target="_blank">
@@ -21,9 +21,6 @@
    <a href="https://twitter.com/intent/follow?screen_name=dify_ai" target="_blank">
        <img src="https://img.shields.io/twitter/follow/dify_ai?logo=X&color=%20%23f5f5f5"
            alt="follow on X(Twitter)"></a>
-    <a href="https://www.linkedin.com/company/langgenius/" target="_blank">
-        <img src="https://custom-icon-badges.demolab.com/badge/LinkedIn-0A66C2?logo=linkedin-white&logoColor=fff"
-            alt="follow on LinkedIn"></a>
    <a href="https://hub.docker.com/u/langgenius" target="_blank">
        <img alt="Docker Pulls" src="https://img.shields.io/docker/pulls/langgenius/dify-web?labelColor=%20%23FDB062&color=%20%23f79009"></a>
    <a href="https://github.com/langgenius/dify/graphs/commit-activity" target="_blank">
@@ -21,9 +21,6 @@
    <a href="https://twitter.com/intent/follow?screen_name=dify_ai" target="_blank">
        <img src="https://img.shields.io/twitter/follow/dify_ai?logo=X&color=%20%23f5f5f5"
            alt="follow on X(Twitter)"></a>
-    <a href="https://www.linkedin.com/company/langgenius/" target="_blank">
-        <img src="https://custom-icon-badges.demolab.com/badge/LinkedIn-0A66C2?logo=linkedin-white&logoColor=fff"
-            alt="follow on LinkedIn"></a>
    <a href="https://hub.docker.com/u/langgenius" target="_blank">
        <img alt="Docker Pulls" src="https://img.shields.io/docker/pulls/langgenius/dify-web?labelColor=%20%23FDB062&color=%20%23f79009"></a>
    <a href="https://github.com/langgenius/dify/graphs/commit-activity" target="_blank">
@@ -25,9 +25,6 @@
    <a href="https://twitter.com/intent/follow?screen_name=dify_ai" target="_blank">
        <img src="https://img.shields.io/twitter/follow/dify_ai?logo=X&color=%20%23f5f5f5"
            alt="follow on X(Twitter)"></a>
-    <a href="https://www.linkedin.com/company/langgenius/" target="_blank">
-        <img src="https://custom-icon-badges.demolab.com/badge/LinkedIn-0A66C2?logo=linkedin-white&logoColor=fff"
-            alt="follow on LinkedIn"></a>
    <a href="https://hub.docker.com/u/langgenius" target="_blank">
        <img alt="Docker Pulls" src="https://img.shields.io/docker/pulls/langgenius/dify-web?labelColor=%20%23FDB062&color=%20%23f79009"></a>
    <a href="https://github.com/langgenius/dify/graphs/commit-activity" target="_blank">
@@ -22,9 +22,6 @@
    <a href="https://twitter.com/intent/follow?screen_name=dify_ai" target="_blank">
        <img src="https://img.shields.io/twitter/follow/dify_ai?logo=X&color=%20%23f5f5f5"
            alt="follow on X(Twitter)"></a>
-    <a href="https://www.linkedin.com/company/langgenius/" target="_blank">
-        <img src="https://custom-icon-badges.demolab.com/badge/LinkedIn-0A66C2?logo=linkedin-white&logoColor=fff"
-            alt="follow on LinkedIn"></a>
    <a href="https://hub.docker.com/u/langgenius" target="_blank">
        <img alt="Docker Pulls" src="https://img.shields.io/docker/pulls/langgenius/dify-web?labelColor=%20%23FDB062&color=%20%23f79009"></a>
    <a href="https://github.com/langgenius/dify/graphs/commit-activity" target="_blank">
@@ -21,9 +21,6 @@
    <a href="https://twitter.com/intent/follow?screen_name=dify_ai" target="_blank">
        <img src="https://img.shields.io/twitter/follow/dify_ai?logo=X&color=%20%23f5f5f5"
            alt="X(Twitter)'da takip et"></a>
-    <a href="https://www.linkedin.com/company/langgenius/" target="_blank">
-        <img src="https://custom-icon-badges.demolab.com/badge/LinkedIn-0A66C2?logo=linkedin-white&logoColor=fff"
-            alt="LinkedIn'da takip et"></a>
    <a href="https://hub.docker.com/u/langgenius" target="_blank">
        <img alt="Docker Çekmeleri" src="https://img.shields.io/docker/pulls/langgenius/dify-web?labelColor=%20%23FDB062&color=%20%23f79009"></a>
    <a href="https://github.com/langgenius/dify/graphs/commit-activity" target="_blank">
@@ -65,6 +62,8 @@ Görsel bir arayüz üzerinde güçlü AI iş akışları oluşturun ve test edi
 ![providers-v5](https://github.com/langgenius/dify/assets/13230914/5a17bdbe-097a-4100-8363-40255b70f6e3)


+Özür dilerim, haklısınız. Daha anlamlı ve akıcı bir çeviri yapmaya çalışayım. İşte güncellenmiş çeviri:
+
 **3. Prompt IDE**: 
  Komut istemlerini oluşturmak, model performansını karşılaştırmak ve sohbet tabanlı uygulamalara metin-konuşma gibi ek özellikler eklemek için kullanıcı dostu bir arayüz.

@@ -151,6 +150,8 @@ Görsel bir arayüz üzerinde güçlü AI iş akışları oluşturun ve test edi
 ## Dify'ı Kullanma

 - **Cloud </br>**
+İşte verdiğiniz metnin Türkçe çevirisi, kod bloğu içinde:
+- 
 Herkesin sıfır kurulumla denemesi için bir [Dify Cloud](https://dify.ai) hizmeti sunuyoruz. Bu hizmet, kendi kendine dağıtılan versiyonun tüm yeteneklerini sağlar ve sandbox planında 200 ücretsiz GPT-4 çağrısı içerir.

 - **Dify Topluluk Sürümünü Kendi Sunucunuzda Barındırma</br>**
@@ -176,6 +177,8 @@ GitHub'da Dify'a yıldız verin ve yeni sürümlerden anında haberdar olun.
 >- RAM >= 4GB

 </br>
+İşte verdiğiniz metnin Türkçe çevirisi, kod bloğu içinde:
+
 Dify sunucusunu başlatmanın en kolay yolu, [docker-compose.yml](docker/docker-compose.yaml) dosyamızı çalıştırmaktır. Kurulum komutunu çalıştırmadan önce, makinenizde [Docker](https://docs.docker.com/get-docker/) ve [Docker Compose](https://docs.docker.com/compose/install/)'un kurulu olduğundan emin olun:

 ```bash
@@ -21,9 +21,6 @@
    <a href="https://twitter.com/intent/follow?screen_name=dify_ai" target="_blank">
        <img src="https://img.shields.io/twitter/follow/dify_ai?logo=X&color=%20%23f5f5f5"
            alt="theo dõi trên X(Twitter)"></a>
-    <a href="https://www.linkedin.com/company/langgenius/" target="_blank">
-        <img src="https://custom-icon-badges.demolab.com/badge/LinkedIn-0A66C2?logo=linkedin-white&logoColor=fff"
-            alt="theo dõi trên LinkedIn"></a>
    <a href="https://hub.docker.com/u/langgenius" target="_blank">
        <img alt="Docker Pulls" src="https://img.shields.io/docker/pulls/langgenius/dify-web?labelColor=%20%23FDB062&color=%20%23f79009"></a>
    <a href="https://github.com/langgenius/dify/graphs/commit-activity" target="_blank">
@@ -48,18 +48,16 @@ ENV TZ=UTC

 WORKDIR /app/api

-RUN \
-    apt-get update \
-    # Install dependencies
-    && apt-get install -y --no-install-recommends \
-        # basic environment
-        curl nodejs libgmp-dev libmpfr-dev libmpc-dev \
-        # For Security
-        # expat libldap-2.5-0 perl libsqlite3-0 zlib1g \
-        # install a chinese font to support the use of tools like matplotlib
-        fonts-noto-cjk \
-        # install libmagic to support the use of python-magic guess MIMETYPE
-        libmagic1 \
+RUN apt-get update \
+    && apt-get install -y --no-install-recommends curl nodejs libgmp-dev libmpfr-dev libmpc-dev \
+    # if you located in China, you can use aliyun mirror to speed up
+    # && echo "deb http://mirrors.aliyun.com/debian testing main" > /etc/apt/sources.list \
+    && 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=2.5.19+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 \
    && rm -rf /var/lib/apt/lists/*

@@ -82,6 +80,7 @@ COPY . /app/api/
 COPY docker/entrypoint.sh /entrypoint.sh
 RUN chmod +x /entrypoint.sh

+
 ARG COMMIT_SHA
 ENV COMMIT_SHA=${COMMIT_SHA}

@@ -556,11 +556,6 @@ class AuthConfig(BaseSettings):
        default=86400,
    )

-    FORGOT_PASSWORD_LOCKOUT_DURATION: PositiveInt = Field(
-        description="Time (in seconds) a user must wait before retrying password reset after exceeding the rate limit.",
-        default=86400,
-    )
-

 class ModerationConfig(BaseSettings):
    """
@@ -1,40 +1,9 @@
 from typing import Optional

-from pydantic import Field, NonNegativeInt, computed_field
+from pydantic import Field, NonNegativeInt
 from pydantic_settings import BaseSettings


-class HostedCreditConfig(BaseSettings):
-    HOSTED_MODEL_CREDIT_CONFIG: str = Field(
-        description="Model credit configuration in format 'model:credits,model:credits', e.g., 'gpt-4:20,gpt-4o:10'",
-        default="",
-    )
-
-    def get_model_credits(self, model_name: str) -> int:
-        """
-        Get credit value for a specific model name.
-        Returns 1 if model is not found in configuration (default credit).
-
-        :param model_name: The name of the model to search for
-        :return: The credit value for the model
-        """
-        if not self.HOSTED_MODEL_CREDIT_CONFIG:
-            return 1
-
-        try:
-            credit_map = dict(
-                item.strip().split(":", 1) for item in self.HOSTED_MODEL_CREDIT_CONFIG.split(",") if ":" in item
-            )
-
-            # Search for matching model pattern
-            for pattern, credit in credit_map.items():
-                if pattern.strip() == model_name:
-                    return int(credit)
-            return 1  # Default quota if no match found
-        except (ValueError, AttributeError):
-            return 1  # Return default quota if parsing fails
-
-
 class HostedOpenAiConfig(BaseSettings):
    """
    Configuration for hosted OpenAI service
@@ -233,7 +202,5 @@ class HostedServiceConfig(
    HostedZhipuAIConfig,
    # moderation
    HostedModerationConfig,
-    # credit config
-    HostedCreditConfig,
 ):
    pass
@@ -9,7 +9,7 @@ class PackagingInfo(BaseSettings):

    CURRENT_VERSION: str = Field(
        description="Dify version",
-        default="1.0.0",
+        default="1.0.0-beta.1",
    )

    COMMIT_SHA: str = Field(
@@ -1,32 +1,12 @@
 import mimetypes
 import os
-import platform
 import re
 import urllib.parse
-import warnings
 from collections.abc import Mapping
 from typing import Any
 from uuid import uuid4

 import httpx
-
-try:
-    import magic
-except ImportError:
-    if platform.system() == "Windows":
-        warnings.warn(
-            "To use python-magic guess MIMETYPE, you need to run `pip install python-magic-bin`", stacklevel=2
-        )
-    elif platform.system() == "Darwin":
-        warnings.warn("To use python-magic guess MIMETYPE, you need to run `brew install libmagic`", stacklevel=2)
-    elif platform.system() == "Linux":
-        warnings.warn(
-            "To use python-magic guess MIMETYPE, you need to run `sudo apt-get install libmagic1`", stacklevel=2
-        )
-    else:
-        warnings.warn("To use python-magic guess MIMETYPE, you need to install `libmagic`", stacklevel=2)
-    magic = None  # type: ignore
-
 from pydantic import BaseModel

 from configs import dify_config
@@ -67,13 +47,6 @@ def guess_file_info_from_response(response: httpx.Response):
        # If guessing fails, use Content-Type from response headers
        mimetype = response.headers.get("Content-Type", "application/octet-stream")

-    # Use python-magic to guess MIME type if still unknown or generic
-    if mimetype == "application/octet-stream" and magic is not None:
-        try:
-            mimetype = magic.from_buffer(response.content[:1024], mime=True)
-        except magic.MagicException:
-            pass
-
    extension = os.path.splitext(filename)[1]

    # Ensure filename has an extension
@@ -59,9 +59,3 @@ class EmailCodeAccountDeletionRateLimitExceededError(BaseHTTPException):
    error_code = "email_code_account_deletion_rate_limit_exceeded"
    description = "Too many account deletion emails have been sent. Please try again in 5 minutes."
    code = 429
-
-
-class EmailPasswordResetLimitError(BaseHTTPException):
-    error_code = "email_password_reset_limit"
-    description = "Too many failed password reset attempts. Please try again in 24 hours."
-    code = 429
@@ -8,13 +8,7 @@ from sqlalchemy.orm import Session

 from constants.languages import languages
 from controllers.console import api
-from controllers.console.auth.error import (
-    EmailCodeError,
-    EmailPasswordResetLimitError,
-    InvalidEmailError,
-    InvalidTokenError,
-    PasswordMismatchError,
-)
+from controllers.console.auth.error import EmailCodeError, InvalidEmailError, InvalidTokenError, PasswordMismatchError
 from controllers.console.error import AccountInFreezeError, AccountNotFound, EmailSendIpLimitError
 from controllers.console.wraps import setup_required
 from events.tenant_event import tenant_was_created
@@ -71,10 +65,6 @@ class ForgotPasswordCheckApi(Resource):

        user_email = args["email"]

-        is_forgot_password_error_rate_limit = AccountService.is_forgot_password_error_rate_limit(args["email"])
-        if is_forgot_password_error_rate_limit:
-            raise EmailPasswordResetLimitError()
-
        token_data = AccountService.get_reset_password_data(args["token"])
        if token_data is None:
            raise InvalidTokenError()
@@ -83,10 +73,8 @@ class ForgotPasswordCheckApi(Resource):
            raise InvalidEmailError()

        if args["code"] != token_data.get("code"):
-            AccountService.add_forgot_password_error_rate_limit(args["email"])
            raise EmailCodeError()

-        AccountService.reset_forgot_password_error_rate_limit(args["email"])
        return {"is_valid": True, "email": token_data.get("email")}


@@ -14,7 +14,6 @@ from controllers.console.wraps import account_initialization_required, enterpris
 from core.errors.error import LLMBadRequestError, ProviderTokenNotInitError
 from core.indexing_runner import IndexingRunner
 from core.model_runtime.entities.model_entities import ModelType
-from core.plugin.entities.plugin import ModelProviderID
 from core.provider_manager import ProviderManager
 from core.rag.datasource.vdb.vector_type import VectorType
 from core.rag.extractor.entity.extract_setting import ExtractSetting
@@ -73,9 +72,7 @@ class DatasetListApi(Resource):

        data = marshal(datasets, dataset_detail_fields)
        for item in data:
-            # convert embedding_model_provider to plugin standard format
            if item["indexing_technique"] == "high_quality":
-                item["embedding_model_provider"] = str(ModelProviderID(item["embedding_model_provider"]))
                item_model = f"{item['embedding_model']}:{item['embedding_model_provider']}"
                if item_model in model_names:
                    item["embedding_available"] = True
@@ -50,7 +50,7 @@ class MessageListApi(InstalledAppResource):

        try:
            return MessageService.pagination_by_first_id(
-                app_model, current_user, args["conversation_id"], args["first_id"], args["limit"]
+                app_model, current_user, args["conversation_id"], args["first_id"], args["limit"], "desc"
            )
        except services.errors.conversation.ConversationNotExistsError:
            raise NotFound("Conversation Not Exists.")
@@ -1,5 +1,3 @@
-import json
-
 from flask_restful import Resource, reqparse  # type: ignore

 from controllers.console.wraps import setup_required
@@ -31,34 +29,4 @@ class EnterpriseWorkspace(Resource):
        return {"message": "enterprise workspace created."}


-class EnterpriseWorkspaceNoOwnerEmail(Resource):
-    @setup_required
-    @enterprise_inner_api_only
-    def post(self):
-        parser = reqparse.RequestParser()
-        parser.add_argument("name", type=str, required=True, location="json")
-        args = parser.parse_args()
-
-        tenant = TenantService.create_tenant(args["name"], is_from_dashboard=True)
-
-        tenant_was_created.send(tenant)
-
-        resp = {
-            "id": tenant.id,
-            "name": tenant.name,
-            "encrypt_public_key": tenant.encrypt_public_key,
-            "plan": tenant.plan,
-            "status": tenant.status,
-            "custom_config": json.loads(tenant.custom_config) if tenant.custom_config else {},
-            "created_at": tenant.created_at.isoformat() if tenant.created_at else None,
-            "updated_at": tenant.updated_at.isoformat() if tenant.updated_at else None,
-        }
-
-        return {
-            "message": "enterprise workspace created.",
-            "tenant": resp,
-        }
-
-
 api.add_resource(EnterpriseWorkspace, "/enterprise/workspace")
-api.add_resource(EnterpriseWorkspaceNoOwnerEmail, "/enterprise/workspace/ownerless")
@@ -18,7 +18,6 @@ from controllers.service_api.app.error import (
 from controllers.service_api.dataset.error import (
    ArchivedDocumentImmutableError,
    DocumentIndexingError,
-    InvalidMetadataError,
 )
 from controllers.service_api.wraps import DatasetApiResource, cloud_edition_billing_resource_check
 from core.errors.error import ProviderTokenNotInitError
@@ -51,9 +50,6 @@ class DocumentAddByTextApi(DatasetApiResource):
            "indexing_technique", type=str, choices=Dataset.INDEXING_TECHNIQUE_LIST, nullable=False, location="json"
        )
        parser.add_argument("retrieval_model", type=dict, required=False, nullable=False, location="json")
-        parser.add_argument("doc_type", type=str, required=False, nullable=True, location="json")
-        parser.add_argument("doc_metadata", type=dict, required=False, nullable=True, location="json")
-
        args = parser.parse_args()
        dataset_id = str(dataset_id)
        tenant_id = str(tenant_id)
@@ -65,28 +61,6 @@ class DocumentAddByTextApi(DatasetApiResource):
        if not dataset.indexing_technique and not args["indexing_technique"]:
            raise ValueError("indexing_technique is required.")

-        # Validate metadata if provided
-        if args.get("doc_type") or args.get("doc_metadata"):
-            if not args.get("doc_type") or not args.get("doc_metadata"):
-                raise InvalidMetadataError("Both doc_type and doc_metadata must be provided when adding metadata")
-
-            if args["doc_type"] not in DocumentService.DOCUMENT_METADATA_SCHEMA:
-                raise InvalidMetadataError(
-                    "Invalid doc_type. Must be one of: " + ", ".join(DocumentService.DOCUMENT_METADATA_SCHEMA.keys())
-                )
-
-            if not isinstance(args["doc_metadata"], dict):
-                raise InvalidMetadataError("doc_metadata must be a dictionary")
-
-            # Validate metadata schema based on doc_type
-            if args["doc_type"] != "others":
-                metadata_schema = DocumentService.DOCUMENT_METADATA_SCHEMA[args["doc_type"]]
-                for key, value in args["doc_metadata"].items():
-                    if key in metadata_schema and not isinstance(value, metadata_schema[key]):
-                        raise InvalidMetadataError(f"Invalid type for metadata field {key}")
-            # set to MetaDataConfig
-            args["metadata"] = {"doc_type": args["doc_type"], "doc_metadata": args["doc_metadata"]}
-
        text = args.get("text")
        name = args.get("name")
        if text is None or name is None:
@@ -133,8 +107,6 @@ class DocumentUpdateByTextApi(DatasetApiResource):
            "doc_language", type=str, default="English", required=False, nullable=False, location="json"
        )
        parser.add_argument("retrieval_model", type=dict, required=False, nullable=False, location="json")
-        parser.add_argument("doc_type", type=str, required=False, nullable=True, location="json")
-        parser.add_argument("doc_metadata", type=dict, required=False, nullable=True, location="json")
        args = parser.parse_args()
        dataset_id = str(dataset_id)
        tenant_id = str(tenant_id)
@@ -143,32 +115,6 @@ class DocumentUpdateByTextApi(DatasetApiResource):
        if not dataset:
            raise ValueError("Dataset is not exist.")

-        # indexing_technique is already set in dataset since this is an update
-        args["indexing_technique"] = dataset.indexing_technique
-
-        # Validate metadata if provided
-        if args.get("doc_type") or args.get("doc_metadata"):
-            if not args.get("doc_type") or not args.get("doc_metadata"):
-                raise InvalidMetadataError("Both doc_type and doc_metadata must be provided when adding metadata")
-
-            if args["doc_type"] not in DocumentService.DOCUMENT_METADATA_SCHEMA:
-                raise InvalidMetadataError(
-                    "Invalid doc_type. Must be one of: " + ", ".join(DocumentService.DOCUMENT_METADATA_SCHEMA.keys())
-                )
-
-            if not isinstance(args["doc_metadata"], dict):
-                raise InvalidMetadataError("doc_metadata must be a dictionary")
-
-            # Validate metadata schema based on doc_type
-            if args["doc_type"] != "others":
-                metadata_schema = DocumentService.DOCUMENT_METADATA_SCHEMA[args["doc_type"]]
-                for key, value in args["doc_metadata"].items():
-                    if key in metadata_schema and not isinstance(value, metadata_schema[key]):
-                        raise InvalidMetadataError(f"Invalid type for metadata field {key}")
-
-            # set to MetaDataConfig
-            args["metadata"] = {"doc_type": args["doc_type"], "doc_metadata": args["doc_metadata"]}
-
        if args["text"]:
            text = args.get("text")
            name = args.get("name")
@@ -215,30 +161,6 @@ class DocumentAddByFileApi(DatasetApiResource):
            args["doc_form"] = "text_model"
        if "doc_language" not in args:
            args["doc_language"] = "English"
-
-        # Validate metadata if provided
-        if args.get("doc_type") or args.get("doc_metadata"):
-            if not args.get("doc_type") or not args.get("doc_metadata"):
-                raise InvalidMetadataError("Both doc_type and doc_metadata must be provided when adding metadata")
-
-            if args["doc_type"] not in DocumentService.DOCUMENT_METADATA_SCHEMA:
-                raise InvalidMetadataError(
-                    "Invalid doc_type. Must be one of: " + ", ".join(DocumentService.DOCUMENT_METADATA_SCHEMA.keys())
-                )
-
-            if not isinstance(args["doc_metadata"], dict):
-                raise InvalidMetadataError("doc_metadata must be a dictionary")
-
-            # Validate metadata schema based on doc_type
-            if args["doc_type"] != "others":
-                metadata_schema = DocumentService.DOCUMENT_METADATA_SCHEMA[args["doc_type"]]
-                for key, value in args["doc_metadata"].items():
-                    if key in metadata_schema and not isinstance(value, metadata_schema[key]):
-                        raise InvalidMetadataError(f"Invalid type for metadata field {key}")
-
-            # set to MetaDataConfig
-            args["metadata"] = {"doc_type": args["doc_type"], "doc_metadata": args["doc_metadata"]}
-
        # get dataset info
        dataset_id = str(dataset_id)
        tenant_id = str(tenant_id)
@@ -306,29 +228,6 @@ class DocumentUpdateByFileApi(DatasetApiResource):
        if "doc_language" not in args:
            args["doc_language"] = "English"

-        # Validate metadata if provided
-        if args.get("doc_type") or args.get("doc_metadata"):
-            if not args.get("doc_type") or not args.get("doc_metadata"):
-                raise InvalidMetadataError("Both doc_type and doc_metadata must be provided when adding metadata")
-
-            if args["doc_type"] not in DocumentService.DOCUMENT_METADATA_SCHEMA:
-                raise InvalidMetadataError(
-                    "Invalid doc_type. Must be one of: " + ", ".join(DocumentService.DOCUMENT_METADATA_SCHEMA.keys())
-                )
-
-            if not isinstance(args["doc_metadata"], dict):
-                raise InvalidMetadataError("doc_metadata must be a dictionary")
-
-            # Validate metadata schema based on doc_type
-            if args["doc_type"] != "others":
-                metadata_schema = DocumentService.DOCUMENT_METADATA_SCHEMA[args["doc_type"]]
-                for key, value in args["doc_metadata"].items():
-                    if key in metadata_schema and not isinstance(value, metadata_schema[key]):
-                        raise InvalidMetadataError(f"Invalid type for metadata field {key}")
-
-            # set to MetaDataConfig
-            args["metadata"] = {"doc_type": args["doc_type"], "doc_metadata": args["doc_metadata"]}
-
        # get dataset info
        dataset_id = str(dataset_id)
        tenant_id = str(tenant_id)
@@ -91,7 +91,7 @@ class MessageListApi(WebApiResource):

        try:
            return MessageService.pagination_by_first_id(
-                app_model, end_user, args["conversation_id"], args["first_id"], args["limit"]
+                app_model, end_user, args["conversation_id"], args["first_id"], args["limit"], "desc"
            )
        except services.errors.conversation.ConversationNotExistsError:
            raise NotFound("Conversation Not Exists.")
@@ -329,7 +329,6 @@ class BaseAgentRunner(AppRunner):
        )
        if not updated_agent_thought:
            raise ValueError("agent thought not found")
-        agent_thought = updated_agent_thought

        if thought:
            agent_thought.thought = thought
@@ -384,7 +384,6 @@ class AdvancedChatAppGenerateTaskPipeline:
                        task_id=self._application_generate_entity.task_id,
                        workflow_node_execution=workflow_node_execution,
                    )
-                    session.commit()

                if node_finish_resp:
                    yield node_finish_resp
@@ -8,16 +8,16 @@ from core.agent.fc_agent_runner import FunctionCallAgentRunner
 from core.app.apps.agent_chat.app_config_manager import AgentChatAppConfig
 from core.app.apps.base_app_queue_manager import AppQueueManager, PublishFrom
 from core.app.apps.base_app_runner import AppRunner
-from core.app.entities.app_invoke_entities import AgentChatAppGenerateEntity
+from core.app.entities.app_invoke_entities import AgentChatAppGenerateEntity, ModelConfigWithCredentialsEntity
 from core.app.entities.queue_entities import QueueAnnotationReplyEvent
 from core.memory.token_buffer_memory import TokenBufferMemory
 from core.model_manager import ModelInstance
-from core.model_runtime.entities.llm_entities import LLMMode
+from core.model_runtime.entities.llm_entities import LLMMode, LLMUsage
 from core.model_runtime.entities.model_entities import ModelFeature, ModelPropertyKey
 from core.model_runtime.model_providers.__base.large_language_model import LargeLanguageModel
 from core.moderation.base import ModerationError
 from extensions.ext_database import db
-from models.model import App, Conversation, Message
+from models.model import App, Conversation, Message, MessageAgentThought

 logger = logging.getLogger(__name__)

@@ -191,8 +191,7 @@ class AgentChatAppRunner(AppRunner):
        # change function call strategy based on LLM model
        llm_model = cast(LargeLanguageModel, model_instance.model_type_instance)
        model_schema = llm_model.get_model_schema(model_instance.model, model_instance.credentials)
-        if not model_schema:
-            raise ValueError("Model schema not found")
+        assert model_schema is not None

        if {ModelFeature.MULTI_TOOL_CALL, ModelFeature.TOOL_CALL}.intersection(model_schema.features or []):
            agent_entity.strategy = AgentEntity.Strategy.FUNCTION_CALLING
@@ -248,3 +247,29 @@ class AgentChatAppRunner(AppRunner):
            stream=application_generate_entity.stream,
            agent=True,
        )
+
+    def _get_usage_of_all_agent_thoughts(
+        self, model_config: ModelConfigWithCredentialsEntity, message: Message
+    ) -> LLMUsage:
+        """
+        Get usage of all agent thoughts
+        :param model_config: model config
+        :param message: message
+        :return:
+        """
+        agent_thoughts = (
+            db.session.query(MessageAgentThought).filter(MessageAgentThought.message_id == message.id).all()
+        )
+
+        all_message_tokens = 0
+        all_answer_tokens = 0
+        for agent_thought in agent_thoughts:
+            all_message_tokens += agent_thought.message_tokens
+            all_answer_tokens += agent_thought.answer_tokens
+
+        model_type_instance = model_config.provider_model_bundle.model_type_instance
+        model_type_instance = cast(LargeLanguageModel, model_type_instance)
+
+        return model_type_instance._calc_response_usage(
+            model_config.model, model_config.credentials, all_message_tokens, all_answer_tokens
+        )
@@ -387,6 +387,7 @@ class WorkflowBasedAppRunner(AppRunner):
                    status=event.status,
                    data=event.data,
                    metadata=event.metadata,
+                    node_id=event.node_id,
                )
            )
        elif isinstance(event, ParallelBranchRunStartedEvent):
@@ -331,6 +331,7 @@ class QueueAgentLogEvent(AppQueueEvent):
    status: str
    data: Mapping[str, Any]
    metadata: Optional[Mapping[str, Any]] = None
+    node_id: str


 class QueueNodeRetryEvent(QueueNodeStartedEvent):
@@ -719,6 +719,7 @@ class AgentLogStreamResponse(StreamResponse):
        status: str
        data: Mapping[str, Any]
        metadata: Optional[Mapping[str, Any]] = None
+        node_id: str

    event: StreamEvent = StreamEvent.AGENT_LOG
    data: Data
@@ -864,5 +864,6 @@ class WorkflowCycleManage:
                status=event.status,
                data=event.data,
                metadata=event.metadata,
+                node_id=event.node_id,
            ),
        )
@@ -11,6 +11,15 @@ from configs import dify_config

 SSRF_DEFAULT_MAX_RETRIES = dify_config.SSRF_DEFAULT_MAX_RETRIES

+proxy_mounts = (
+    {
+        "http://": httpx.HTTPTransport(proxy=dify_config.SSRF_PROXY_HTTP_URL),
+        "https://": httpx.HTTPTransport(proxy=dify_config.SSRF_PROXY_HTTPS_URL),
+    }
+    if dify_config.SSRF_PROXY_HTTP_URL and dify_config.SSRF_PROXY_HTTPS_URL
+    else None
+)
+
 BACKOFF_FACTOR = 0.5
 STATUS_FORCELIST = [429, 500, 502, 503, 504]

@@ -41,11 +50,7 @@ def make_request(method, url, max_retries=SSRF_DEFAULT_MAX_RETRIES, **kwargs):
            if dify_config.SSRF_PROXY_ALL_URL:
                with httpx.Client(proxy=dify_config.SSRF_PROXY_ALL_URL) as client:
                    response = client.request(method=method, url=url, **kwargs)
-            elif dify_config.SSRF_PROXY_HTTP_URL and dify_config.SSRF_PROXY_HTTPS_URL:
-                proxy_mounts = {
-                    "http://": httpx.HTTPTransport(proxy=dify_config.SSRF_PROXY_HTTP_URL),
-                    "https://": httpx.HTTPTransport(proxy=dify_config.SSRF_PROXY_HTTPS_URL),
-                }
+            elif proxy_mounts:
                with httpx.Client(mounts=proxy_mounts) as client:
                    response = client.request(method=method, url=url, **kwargs)
            else:
@@ -65,7 +70,8 @@ def make_request(method, url, max_retries=SSRF_DEFAULT_MAX_RETRIES, **kwargs):
        retries += 1
        if retries <= max_retries:
            time.sleep(BACKOFF_FACTOR * (2 ** (retries - 1)))
-    raise MaxRetriesExceededError(f"Reached maximum retries ({max_retries}) for URL {url}")
+    raise MaxRetriesExceededError(
+        f"Reached maximum retries ({max_retries}) for URL {url}")


 def get(url, max_retries=SSRF_DEFAULT_MAX_RETRIES, **kwargs):
@@ -1,4 +1,4 @@
-from .llm_entities import LLMMode, LLMResult, LLMResultChunk, LLMResultChunkDelta, LLMUsage
+from .llm_entities import LLMResult, LLMResultChunk, LLMResultChunkDelta, LLMUsage
 from .message_entities import (
    AssistantPromptMessage,
    AudioPromptMessageContent,
@@ -23,7 +23,6 @@ __all__ = [
    "AudioPromptMessageContent",
    "DocumentPromptMessageContent",
    "ImagePromptMessageContent",
-    "LLMMode",
    "LLMResult",
    "LLMResultChunk",
    "LLMResultChunkDelta",
@@ -1,5 +1,5 @@
 from decimal import Decimal
-from enum import StrEnum
+from enum import Enum
 from typing import Optional

 from pydantic import BaseModel
@@ -8,7 +8,7 @@ from core.model_runtime.entities.message_entities import AssistantPromptMessage,
 from core.model_runtime.entities.model_entities import ModelUsage, PriceInfo


-class LLMMode(StrEnum):
+class LLMMode(Enum):
    """
    Enum class for large language model mode.
    """
@@ -3,11 +3,8 @@ from typing import Optional

 from pydantic import BaseModel, ConfigDict, Field

-from core.model_runtime.entities.common_entities import I18nObject
-from core.model_runtime.entities.defaults import PARAMETER_RULE_TEMPLATE
 from core.model_runtime.entities.model_entities import (
    AIModelEntity,
-    DefaultParameterName,
    ModelType,
    PriceConfig,
    PriceInfo,
@@ -21,7 +18,6 @@ from core.model_runtime.errors.invoke import (
    InvokeRateLimitError,
    InvokeServerUnavailableError,
 )
-from core.model_runtime.model_providers.__base.tokenizers.gpt2_tokenzier import GPT2Tokenizer
 from core.plugin.entities.plugin_daemon import PluginDaemonInnerError, PluginModelProviderEntity
 from core.plugin.manager.model import PluginModelManager

@@ -148,102 +144,3 @@ class AIModel(BaseModel):
            model=model,
            credentials=credentials or {},
        )
-
-    def get_customizable_model_schema_from_credentials(self, model: str, credentials: dict) -> Optional[AIModelEntity]:
-        """
-        Get customizable model schema from credentials
-
-        :param model: model name
-        :param credentials: model credentials
-        :return: model schema
-        """
-        return self._get_customizable_model_schema(model, credentials)
-
-    def _get_customizable_model_schema(self, model: str, credentials: dict) -> Optional[AIModelEntity]:
-        """
-        Get customizable model schema and fill in the template
-        """
-        schema = self.get_customizable_model_schema(model, credentials)
-
-        if not schema:
-            return None
-
-        # fill in the template
-        new_parameter_rules = []
-        for parameter_rule in schema.parameter_rules:
-            if parameter_rule.use_template:
-                try:
-                    default_parameter_name = DefaultParameterName.value_of(parameter_rule.use_template)
-                    default_parameter_rule = self._get_default_parameter_rule_variable_map(default_parameter_name)
-                    if not parameter_rule.max and "max" in default_parameter_rule:
-                        parameter_rule.max = default_parameter_rule["max"]
-                    if not parameter_rule.min and "min" in default_parameter_rule:
-                        parameter_rule.min = default_parameter_rule["min"]
-                    if not parameter_rule.default and "default" in default_parameter_rule:
-                        parameter_rule.default = default_parameter_rule["default"]
-                    if not parameter_rule.precision and "precision" in default_parameter_rule:
-                        parameter_rule.precision = default_parameter_rule["precision"]
-                    if not parameter_rule.required and "required" in default_parameter_rule:
-                        parameter_rule.required = default_parameter_rule["required"]
-                    if not parameter_rule.help and "help" in default_parameter_rule:
-                        parameter_rule.help = I18nObject(
-                            en_US=default_parameter_rule["help"]["en_US"],
-                        )
-                    if (
-                        parameter_rule.help
-                        and not parameter_rule.help.en_US
-                        and ("help" in default_parameter_rule and "en_US" in default_parameter_rule["help"])
-                    ):
-                        parameter_rule.help.en_US = default_parameter_rule["help"]["en_US"]
-                    if (
-                        parameter_rule.help
-                        and not parameter_rule.help.zh_Hans
-                        and ("help" in default_parameter_rule and "zh_Hans" in default_parameter_rule["help"])
-                    ):
-                        parameter_rule.help.zh_Hans = default_parameter_rule["help"].get(
-                            "zh_Hans", default_parameter_rule["help"]["en_US"]
-                        )
-                except ValueError:
-                    pass
-
-            new_parameter_rules.append(parameter_rule)
-
-        schema.parameter_rules = new_parameter_rules
-
-        return schema
-
-    def get_customizable_model_schema(self, model: str, credentials: dict) -> Optional[AIModelEntity]:
-        """
-        Get customizable model schema
-
-        :param model: model name
-        :param credentials: model credentials
-        :return: model schema
-        """
-        return None
-
-    def _get_default_parameter_rule_variable_map(self, name: DefaultParameterName) -> dict:
-        """
-        Get default parameter rule for given name
-
-        :param name: parameter name
-        :return: parameter rule
-        """
-        default_parameter_rule = PARAMETER_RULE_TEMPLATE.get(name)
-
-        if not default_parameter_rule:
-            raise Exception(f"Invalid model parameter rule name {name}")
-
-        return default_parameter_rule
-
-    def _get_num_tokens_by_gpt2(self, text: str) -> int:
-        """
-        Get number of tokens for given prompt messages by gpt2
-        Some provider models do not provide an interface for obtaining the number of tokens.
-        Here, the gpt2 tokenizer is used to calculate the number of tokens.
-        This method can be executed offline, and the gpt2 tokenizer has been cached in the project.
-
-        :param text: plain text of prompt. You need to convert the original message to plain text
-        :return: number of tokens
-        """
-        return GPT2Tokenizer.get_num_tokens(text)
@@ -1,5 +1,4 @@
 - openai
- deepseek
 - anthropic
 - azure_openai
 - google
@@ -33,6 +32,7 @@
 - localai
 - volcengine_maas
 - openai_api_compatible
+- deepseek
 - hunyuan
 - siliconflow
 - perfxcloud
@@ -20,7 +20,6 @@ from core.model_runtime.model_providers.__base.text_embedding_model import TextE
 from core.model_runtime.model_providers.__base.tts_model import TTSModel
 from core.model_runtime.schema_validators.model_credential_schema_validator import ModelCredentialSchemaValidator
 from core.model_runtime.schema_validators.provider_credential_schema_validator import ProviderCredentialSchemaValidator
-from core.plugin.entities.plugin import ModelProviderID
 from core.plugin.entities.plugin_daemon import PluginModelProviderEntity
 from core.plugin.manager.asset import PluginAssetManager
 from core.plugin.manager.model import PluginModelManager
@@ -113,9 +112,6 @@ class ModelProviderFactory:
        :param provider: provider name
        :return: provider schema
        """
-        if "/" not in provider:
-            provider = str(ModelProviderID(provider))
-
        # fetch plugin model providers
        plugin_model_provider_entities = self.get_plugin_model_providers()

@@ -367,4 +363,4 @@ class ModelProviderFactory:
            plugin_id = "/".join(provider.split("/")[:-1])
            provider_name = provider.split("/")[-1]

-        return str(plugin_id), provider_name
+        return plugin_id, provider_name
@@ -1,41 +0,0 @@
-model: gemini-2.0-flash-001
-label:
-  en_US: Gemini 2.0 Flash 001
-model_type: llm
-features:
-  - agent-thought
-  - vision
-  - tool-call
-  - stream-tool-call
-  - document
-  - video
-  - audio
-model_properties:
-  mode: chat
-  context_size: 1048576
-parameter_rules:
-  - name: temperature
-    use_template: temperature
-  - name: top_p
-    use_template: top_p
-  - name: top_k
-    label:
-      zh_Hans: 取样数量
-      en_US: Top k
-    type: int
-    help:
-      zh_Hans: 仅从每个后续标记的前 K 个选项中采样。
-      en_US: Only sample from the top K options for each subsequent token.
-    required: false
-  - name: max_output_tokens
-    use_template: max_tokens
-    default: 8192
-    min: 1
-    max: 8192
-  - name: json_schema
-    use_template: json_schema
-pricing:
-  input: '0.00'
-  output: '0.00'
-  unit: '0.000001'
-  currency: USD
@@ -1,41 +0,0 @@
-model: gemini-2.0-flash-lite-preview-02-05
-label:
-  en_US: Gemini 2.0 Flash Lite Preview 0205
-model_type: llm
-features:
-  - agent-thought
-  - vision
-  - tool-call
-  - stream-tool-call
-  - document
-  - video
-  - audio
-model_properties:
-  mode: chat
-  context_size: 1048576
-parameter_rules:
-  - name: temperature
-    use_template: temperature
-  - name: top_p
-    use_template: top_p
-  - name: top_k
-    label:
-      zh_Hans: 取样数量
-      en_US: Top k
-    type: int
-    help:
-      zh_Hans: 仅从每个后续标记的前 K 个选项中采样。
-      en_US: Only sample from the top K options for each subsequent token.
-    required: false
-  - name: max_output_tokens
-    use_template: max_tokens
-    default: 8192
-    min: 1
-    max: 8192
-  - name: json_schema
-    use_template: json_schema
-pricing:
-  input: '0.00'
-  output: '0.00'
-  unit: '0.000001'
-  currency: USD
@@ -1,39 +0,0 @@
-model: gemini-2.0-flash-thinking-exp-01-21
-label:
-  en_US: Gemini 2.0 Flash Thinking Exp 0121
-model_type: llm
-features:
-  - agent-thought
-  - vision
-  - document
-  - video
-  - audio
-model_properties:
-  mode: chat
-  context_size: 32767
-parameter_rules:
-  - name: temperature
-    use_template: temperature
-  - name: top_p
-    use_template: top_p
-  - name: top_k
-    label:
-      zh_Hans: 取样数量
-      en_US: Top k
-    type: int
-    help:
-      zh_Hans: 仅从每个后续标记的前 K 个选项中采样。
-      en_US: Only sample from the top K options for each subsequent token.
-    required: false
-  - name: max_output_tokens
-    use_template: max_tokens
-    default: 8192
-    min: 1
-    max: 8192
-  - name: json_schema
-    use_template: json_schema
-pricing:
-  input: '0.00'
-  output: '0.00'
-  unit: '0.000001'
-  currency: USD
@@ -1,39 +0,0 @@
-model: gemini-2.0-flash-thinking-exp-1219
-label:
-  en_US: Gemini 2.0 Flash Thinking Exp 1219
-model_type: llm
-features:
-  - agent-thought
-  - vision
-  - document
-  - video
-  - audio
-model_properties:
-  mode: chat
-  context_size: 32767
-parameter_rules:
-  - name: temperature
-    use_template: temperature
-  - name: top_p
-    use_template: top_p
-  - name: top_k
-    label:
-      zh_Hans: 取样数量
-      en_US: Top k
-    type: int
-    help:
-      zh_Hans: 仅从每个后续标记的前 K 个选项中采样。
-      en_US: Only sample from the top K options for each subsequent token.
-    required: false
-  - name: max_output_tokens
-    use_template: max_tokens
-    default: 8192
-    min: 1
-    max: 8192
-  - name: json_schema
-    use_template: json_schema
-pricing:
-  input: '0.00'
-  output: '0.00'
-  unit: '0.000001'
-  currency: USD
@@ -1,37 +0,0 @@
-model: gemini-2.0-pro-exp-02-05
-label:
-  en_US: Gemini 2.0 Pro Exp 0205
-model_type: llm
-features:
-  - agent-thought
-  - document
-model_properties:
-  mode: chat
-  context_size: 2000000
-parameter_rules:
-  - name: temperature
-    use_template: temperature
-  - name: top_p
-    use_template: top_p
-  - name: top_k
-    label:
-      en_US: Top k
-    type: int
-    help:
-      en_US: Only sample from the top K options for each subsequent token.
-    required: false
-  - name: presence_penalty
-    use_template: presence_penalty
-  - name: frequency_penalty
-    use_template: frequency_penalty
-  - name: max_output_tokens
-    use_template: max_tokens
-    required: true
-    default: 8192
-    min: 1
-    max: 8192
-pricing:
-  input: '0.00'
-  output: '0.00'
-  unit: '0.000001'
-  currency: USD
@@ -1,41 +0,0 @@
-model: gemini-exp-1114
-label:
-  en_US: Gemini exp 1114
-model_type: llm
-features:
-  - agent-thought
-  - vision
-  - tool-call
-  - stream-tool-call
-  - document
-  - video
-  - audio
-model_properties:
-  mode: chat
-  context_size: 32767
-parameter_rules:
-  - name: temperature
-    use_template: temperature
-  - name: top_p
-    use_template: top_p
-  - name: top_k
-    label:
-      zh_Hans: 取样数量
-      en_US: Top k
-    type: int
-    help:
-      zh_Hans: 仅从每个后续标记的前 K 个选项中采样。
-      en_US: Only sample from the top K options for each subsequent token.
-    required: false
-  - name: max_output_tokens
-    use_template: max_tokens
-    default: 8192
-    min: 1
-    max: 8192
-  - name: json_schema
-    use_template: json_schema
-pricing:
-  input: '0.00'
-  output: '0.00'
-  unit: '0.000001'
-  currency: USD
@@ -1,41 +0,0 @@
-model: gemini-exp-1121
-label:
-  en_US: Gemini exp 1121
-model_type: llm
-features:
-  - agent-thought
-  - vision
-  - tool-call
-  - stream-tool-call
-  - document
-  - video
-  - audio
-model_properties:
-  mode: chat
-  context_size: 32767
-parameter_rules:
-  - name: temperature
-    use_template: temperature
-  - name: top_p
-    use_template: top_p
-  - name: top_k
-    label:
-      zh_Hans: 取样数量
-      en_US: Top k
-    type: int
-    help:
-      zh_Hans: 仅从每个后续标记的前 K 个选项中采样。
-      en_US: Only sample from the top K options for each subsequent token.
-    required: false
-  - name: max_output_tokens
-    use_template: max_tokens
-    default: 8192
-    min: 1
-    max: 8192
-  - name: json_schema
-    use_template: json_schema
-pricing:
-  input: '0.00'
-  output: '0.00'
-  unit: '0.000001'
-  currency: USD
@@ -1,41 +0,0 @@
-model: gemini-exp-1206
-label:
-  en_US: Gemini exp 1206
-model_type: llm
-features:
-  - agent-thought
-  - vision
-  - tool-call
-  - stream-tool-call
-  - document
-  - video
-  - audio
-model_properties:
-  mode: chat
-  context_size: 2097152
-parameter_rules:
-  - name: temperature
-    use_template: temperature
-  - name: top_p
-    use_template: top_p
-  - name: top_k
-    label:
-      zh_Hans: 取样数量
-      en_US: Top k
-    type: int
-    help:
-      zh_Hans: 仅从每个后续标记的前 K 个选项中采样。
-      en_US: Only sample from the top K options for each subsequent token.
-    required: false
-  - name: max_output_tokens
-    use_template: max_tokens
-    default: 8192
-    min: 1
-    max: 8192
-  - name: json_schema
-    use_template: json_schema
-pricing:
-  input: '0.00'
-  output: '0.00'
-  unit: '0.000001'
-  currency: USD
@@ -1,66 +0,0 @@
-model: glm-4-air-0111
-label:
-  en_US: glm-4-air-0111
-model_type: llm
-features:
-  - multi-tool-call
-  - agent-thought
-  - stream-tool-call
-model_properties:
-  mode: chat
-  context_size: 131072
-parameter_rules:
-  - name: temperature
-    use_template: temperature
-    default: 0.95
-    min: 0.0
-    max: 1.0
-    help:
-      zh_Hans: 采样温度，控制输出的随机性，必须为正数取值范围是：(0.0,1.0]，不能等于 0,默认值为 0.95 值越大，会使输出更随机，更具创造性；值越小，输出会更加稳定或确定建议您根据应用场景调整 top_p 或 temperature 参数，但不要同时调整两个参数。
-      en_US: Sampling temperature, controls the randomness of the output, must be a positive number. The value range is (0.0,1.0], which cannot be equal to 0. The default value is 0.95. The larger the value, the more random and creative the output will be; the smaller the value, The output will be more stable or certain. It is recommended that you adjust the top_p or temperature parameters according to the application scenario, but do not adjust both parameters at the same time.
-  - name: top_p
-    use_template: top_p
-    default: 0.7
-    help:
-      zh_Hans: 用温度取样的另一种方法，称为核取样取值范围是：(0.0, 1.0) 开区间，不能等于 0 或 1，默认值为 0.7 模型考虑具有 top_p 概率质量tokens的结果例如：0.1 意味着模型解码器只考虑从前 10% 的概率的候选集中取 tokens 建议您根据应用场景调整 top_p 或 temperature 参数，但不要同时调整两个参数。
-      en_US: Another method of temperature sampling is called kernel sampling. The value range is (0.0, 1.0) open interval, which cannot be equal to 0 or 1. The default value is 0.7. The model considers the results with top_p probability mass tokens. For example 0.1 means The model decoder only considers tokens from the candidate set with the top 10% probability. It is recommended that you adjust the top_p or temperature parameters according to the application scenario, but do not adjust both parameters at the same time.
-  - name: do_sample
-    label:
-      zh_Hans: 采样策略
-      en_US: Sampling strategy
-    type: boolean
-    help:
-      zh_Hans: do_sample 为 true 时启用采样策略，do_sample 为 false 时采样策略 temperature、top_p 将不生效。默认值为 true。
-      en_US: When `do_sample` is set to true, the sampling strategy is enabled. When `do_sample` is set to false, the sampling strategies such as `temperature` and `top_p` will not take effect. The default value is true.
-    default: true
-  - name: max_tokens
-    use_template: max_tokens
-    default: 1024
-    min: 1
-    max: 4095
-  - name: web_search
-    type: boolean
-    label:
-      zh_Hans: 联网搜索
-      en_US: Web Search
-    default: false
-    help:
-      zh_Hans: 模型内置了互联网搜索服务，该参数控制模型在生成文本时是否参考使用互联网搜索结果。启用互联网搜索，模型会将搜索结果作为文本生成过程中的参考信息，但模型会基于其内部逻辑“自行判断”是否使用互联网搜索结果。
-      en_US: The model has a built-in Internet search service. This parameter controls whether the model refers to Internet search results when generating text. When Internet search is enabled, the model will use the search results as reference information in the text generation process, but the model will "judge" whether to use Internet search results based on its internal logic.
-  - name: response_format
-    label:
-      zh_Hans: 回复格式
-      en_US: Response Format
-    type: string
-    help:
-      zh_Hans: 指定模型必须输出的格式
-      en_US: specifying the format that the model must output
-    required: false
-    options:
-      - text
-      - json_object
-pricing:
-  input: '0.0005'
-  output: '0.0005'
-  unit: '0.001'
-  currency: RMB
@@ -169,21 +169,6 @@ class GenericProviderID:
        return f"{self.organization}/{self.plugin_name}"


-class ModelProviderID(GenericProviderID):
-    def __init__(self, value: str, is_hardcoded: bool = False) -> None:
-        super().__init__(value, is_hardcoded)
-        if self.organization == "langgenius" and self.provider_name == "google":
-            self.plugin_name = "gemini"
-
-
-class ToolProviderID(GenericProviderID):
-    def __init__(self, value: str, is_hardcoded: bool = False) -> None:
-        super().__init__(value, is_hardcoded)
-        if self.organization == "langgenius":
-            if self.provider_name in ["jina", "siliconflow"]:
-                self.plugin_name = f"{self.provider_name}_tool"
-
-
 class PluginDependency(BaseModel):
    class Type(enum.StrEnum):
        Github = PluginInstallationSource.Github.value
@@ -30,7 +30,6 @@ from core.model_runtime.entities.provider_entities import (
    ProviderEntity,
 )
 from core.model_runtime.model_providers.model_provider_factory import ModelProviderFactory
-from core.plugin.entities.plugin import ModelProviderID
 from extensions import ext_hosting_provider
 from extensions.ext_database import db
 from extensions.ext_redis import redis_client
@@ -192,7 +191,7 @@ class ProviderManager:
                model_settings=model_settings,
            )

-            provider_configurations[str(ModelProviderID(provider_name))] = provider_configuration
+            provider_configurations[provider_name] = provider_configuration

        # Return the encapsulated object
        return provider_configurations
@@ -1,6 +1,6 @@
 import json
 import time
-from typing import Any, cast
+from typing import cast

 import requests

@@ -14,47 +14,48 @@ class FirecrawlApp:
        if self.api_key is None and self.base_url == "https://api.firecrawl.dev":
            raise ValueError("No API key provided")

-    def scrape_url(self, url, params=None) -> dict[str, Any]:
-        # Documentation: https://docs.firecrawl.dev/api-reference/endpoint/scrape
-        headers = self._prepare_headers()
-        json_data = {
-            "url": url,
-            "formats": ["markdown"],
-            "onlyMainContent": True,
-            "timeout": 30000,
-        }
+    def scrape_url(self, url, params=None) -> dict:
+        headers = {"Content-Type": "application/json", "Authorization": f"Bearer {self.api_key}"}
+        json_data = {"url": url}
        if params:
            json_data.update(params)
-        response = self._post_request(f"{self.base_url}/v1/scrape", json_data, headers)
+        response = requests.post(f"{self.base_url}/v0/scrape", headers=headers, json=json_data)
        if response.status_code == 200:
            response_data = response.json()
-            data = response_data["data"]
-            return self._extract_common_fields(data)
-        elif response.status_code in {402, 409, 500, 429, 408}:
-            self._handle_error(response, "scrape URL")
-            return {}  # Avoid additional exception after handling error
+            if response_data["success"] == True:
+                data = response_data["data"]
+                return {
+                    "title": data.get("metadata").get("title"),
+                    "description": data.get("metadata").get("description"),
+                    "source_url": data.get("metadata").get("sourceURL"),
+                    "markdown": data.get("markdown"),
+                }
+            else:
+                raise Exception(f"Failed to scrape URL. Error: {response_data['error']}")
+
+        elif response.status_code in {402, 409, 500}:
+            error_message = response.json().get("error", "Unknown error occurred")
+            raise Exception(f"Failed to scrape URL. Status code: {response.status_code}. Error: {error_message}")
        else:
            raise Exception(f"Failed to scrape URL. Status code: {response.status_code}")

    def crawl_url(self, url, params=None) -> str:
-        # Documentation: https://docs.firecrawl.dev/api-reference/endpoint/crawl-post
        headers = self._prepare_headers()
        json_data = {"url": url}
        if params:
            json_data.update(params)
-        response = self._post_request(f"{self.base_url}/v1/crawl", json_data, headers)
+        response = self._post_request(f"{self.base_url}/v0/crawl", json_data, headers)
        if response.status_code == 200:
-            # There's also another two fields in the response: "success" (bool) and "url" (str)
-            job_id = response.json().get("id")
+            job_id = response.json().get("jobId")
            return cast(str, job_id)
        else:
            self._handle_error(response, "start crawl job")
            # FIXME: unreachable code for mypy
            return ""  # unreachable

-    def check_crawl_status(self, job_id) -> dict[str, Any]:
+    def check_crawl_status(self, job_id) -> dict:
        headers = self._prepare_headers()
-        response = self._get_request(f"{self.base_url}/v1/crawl/{job_id}", headers)
+        response = self._get_request(f"{self.base_url}/v0/crawl/status/{job_id}", headers)
        if response.status_code == 200:
            crawl_status_response = response.json()
            if crawl_status_response.get("status") == "completed":
@@ -65,48 +66,42 @@ class FirecrawlApp:
                url_data_list = []
                for item in data:
                    if isinstance(item, dict) and "metadata" in item and "markdown" in item:
-                        url_data = self._extract_common_fields(item)
+                        url_data = {
+                            "title": item.get("metadata", {}).get("title"),
+                            "description": item.get("metadata", {}).get("description"),
+                            "source_url": item.get("metadata", {}).get("sourceURL"),
+                            "markdown": item.get("markdown"),
+                        }
                        url_data_list.append(url_data)
                if url_data_list:
                    file_key = "website_files/" + job_id + ".txt"
-                    try:
-                        if storage.exists(file_key):
-                            storage.delete(file_key)
-                        storage.save(file_key, json.dumps(url_data_list).encode("utf-8"))
-                    except Exception as e:
-                        raise Exception(f"Error saving crawl data: {e}")
-                return self._format_crawl_status_response("completed", crawl_status_response, url_data_list)
+                    if storage.exists(file_key):
+                        storage.delete(file_key)
+                    storage.save(file_key, json.dumps(url_data_list).encode("utf-8"))
+                return {
+                    "status": "completed",
+                    "total": crawl_status_response.get("total"),
+                    "current": crawl_status_response.get("current"),
+                    "data": url_data_list,
+                }
+
            else:
-                return self._format_crawl_status_response(
-                    crawl_status_response.get("status"), crawl_status_response, []
-                )
+                return {
+                    "status": crawl_status_response.get("status"),
+                    "total": crawl_status_response.get("total"),
+                    "current": crawl_status_response.get("current"),
+                    "data": [],
+                }
+
        else:
            self._handle_error(response, "check crawl status")
            # FIXME: unreachable code for mypy
            return {}  # unreachable

-    def _format_crawl_status_response(
-        self, status: str, crawl_status_response: dict[str, Any], url_data_list: list[dict[str, Any]]
-    ) -> dict[str, Any]:
-        return {
-            "status": status,
-            "total": crawl_status_response.get("total"),
-            "current": crawl_status_response.get("completed"),
-            "data": url_data_list,
-        }
-
-    def _extract_common_fields(self, item: dict[str, Any]) -> dict[str, Any]:
-        return {
-            "title": item.get("metadata", {}).get("title"),
-            "description": item.get("metadata", {}).get("description"),
-            "source_url": item.get("metadata", {}).get("sourceURL"),
-            "markdown": item.get("markdown"),
-        }
-
-    def _prepare_headers(self) -> dict[str, Any]:
+    def _prepare_headers(self):
        return {"Content-Type": "application/json", "Authorization": f"Bearer {self.api_key}"}

-    def _post_request(self, url, data, headers, retries=3, backoff_factor=0.5) -> requests.Response:
+    def _post_request(self, url, data, headers, retries=3, backoff_factor=0.5):
        for attempt in range(retries):
            response = requests.post(url, headers=headers, json=data)
            if response.status_code == 502:
@@ -115,7 +110,7 @@ class FirecrawlApp:
                return response
        return response

-    def _get_request(self, url, headers, retries=3, backoff_factor=0.5) -> requests.Response:
+    def _get_request(self, url, headers, retries=3, backoff_factor=0.5):
        for attempt in range(retries):
            response = requests.get(url, headers=headers)
            if response.status_code == 502:
@@ -124,6 +119,6 @@ class FirecrawlApp:
                return response
        return response

-    def _handle_error(self, response, action) -> None:
+    def _handle_error(self, response, action):
        error_message = response.json().get("error", "Unknown error occurred")
        raise Exception(f"Failed to {action}. Status code: {response.status_code}. Error: {error_message}")
@@ -13,10 +13,9 @@ class FirecrawlWebExtractor(BaseExtractor):
        api_key: The API key for Firecrawl.
        base_url: The base URL for the Firecrawl API. Defaults to 'https://api.firecrawl.dev'.
        mode: The mode of operation. Defaults to 'scrape'. Options are 'crawl', 'scrape' and 'crawl_return_urls'.
-        only_main_content: Only return the main content of the page excluding headers, navs, footers, etc.
    """

-    def __init__(self, url: str, job_id: str, tenant_id: str, mode: str = "crawl", only_main_content: bool = True):
+    def __init__(self, url: str, job_id: str, tenant_id: str, mode: str = "crawl", only_main_content: bool = False):
        """Initialize with url, api_key, base_url and mode."""
        self._url = url
        self.job_id = job_id
@@ -47,8 +47,6 @@ class ParentChildIndexProcessor(BaseIndexProcessor):
                embedding_model_instance=kwargs.get("embedding_model_instance"),
            )
            for document in documents:
-                if kwargs.get("preview") and len(all_documents) >= 10:
-                    return all_documents
                # document clean
                document_text = CleanProcessor.clean(document.page_content, process_rule)
                document.page_content = document_text
@@ -125,7 +125,7 @@ class ToolInvokeMessage(BaseModel):

    class VariableMessage(BaseModel):
        variable_name: str = Field(..., description="The name of the variable")
-        variable_value: Any = Field(..., description="The value of the variable")
+        variable_value: str = Field(..., description="The value of the variable")
        stream: bool = Field(default=False, description="Whether the variable is streamed")

        @model_validator(mode="before")
@@ -160,8 +160,8 @@ class ToolManager:
        """
        get the tool runtime

-        :param provider_type: the type of the provider
-        :param provider_name: the name of the provider
+        :param provider_type: the type of  the provider
+        :param provider_name: the name of  the provider
        :param tool_name: the name of the tool

        :return: the tool
@@ -223,14 +223,14 @@ class WorkflowTool(Tool):
            if isinstance(value, list):
                for item in value:
                    if isinstance(item, dict) and item.get("dify_model_identity") == FILE_MODEL_IDENTITY:
-                        item = self._update_file_mapping(item)
+                        item["tool_file_id"] = item.get("related_id")
                        file = build_from_mapping(
                            mapping=item,
                            tenant_id=str(cast(ToolRuntime, self.runtime).tenant_id),
                        )
                        files.append(file)
            elif isinstance(value, dict) and value.get("dify_model_identity") == FILE_MODEL_IDENTITY:
-                value = self._update_file_mapping(value)
+                value["tool_file_id"] = value.get("related_id")
                file = build_from_mapping(
                    mapping=value,
                    tenant_id=str(cast(ToolRuntime, self.runtime).tenant_id),
@@ -240,11 +240,3 @@ class WorkflowTool(Tool):
            result[key] = value

        return result, files
-
-    def _update_file_mapping(self, file_dict: dict) -> dict:
-        transfer_method = FileTransferMethod.value_of(file_dict.get("transfer_method"))
-        if transfer_method == FileTransferMethod.TOOL_FILE:
-            file_dict["tool_file_id"] = file_dict.get("related_id")
-        elif transfer_method == FileTransferMethod.LOCAL_FILE:
-            file_dict["upload_file_id"] = file_dict.get("related_id")
-        return file_dict
@@ -207,6 +207,7 @@ class AgentLogEvent(BaseAgentEvent):
    status: str = Field(..., description="status")
    data: Mapping[str, Any] = Field(..., description="data")
    metadata: Optional[Mapping[str, Any]] = Field(default=None, description="metadata")
+    node_id: str = Field(..., description="agent node id")


 InNodeEvent = BaseNodeEvent | BaseParallelBranchEvent | BaseIterationEvent | BaseAgentEvent
@@ -590,8 +590,6 @@ class Graph(BaseModel):
                            start_node_id=node_id,
                            routes_node_ids=routes_node_ids,
                        )
-                        # Exclude conditional branch nodes
-                        and all(edge.run_condition is None for edge in reverse_edge_mapping.get(node_id, []))
                    ):
                        if node_id not in merge_branch_node_ids:
                            merge_branch_node_ids[node_id] = []
@@ -8,12 +8,12 @@ from core.model_manager import ModelManager
 from core.model_runtime.entities.model_entities import ModelType
 from core.plugin.manager.exc import PluginDaemonClientSideError
 from core.plugin.manager.plugin import PluginInstallationManager
-from core.tools.entities.tool_entities import ToolProviderType
+from core.tools.entities.tool_entities import ToolParameter, ToolProviderType
 from core.tools.tool_manager import ToolManager
 from core.workflow.entities.node_entities import NodeRunResult
 from core.workflow.entities.variable_pool import VariablePool
 from core.workflow.enums import SystemVariableKey
-from core.workflow.nodes.agent.entities import AgentNodeData
+from core.workflow.nodes.agent.entities import AgentNodeData, ParamsAutoGenerated
 from core.workflow.nodes.base.entities import BaseNodeData
 from core.workflow.nodes.enums import NodeType
 from core.workflow.nodes.event.event import RunCompletedEvent
@@ -161,11 +161,29 @@ class AgentNode(ToolNode):
                    value = cast(list[dict[str, Any]], value)
                    tool_value = []
                    for tool in value:
+                        provider_type = ToolProviderType(tool.get("type", ToolProviderType.BUILT_IN.value))
+                        # handle the original settings
+                        original_parameters = tool.get("parameters", {})
+                        setting_params = tool.get("settings", {})
+                        manual_input_params = []
+                        # handle legacy data compatibility
+                        if not all(isinstance(v, dict) for _, v in original_parameters.items()):
+                            parameters = original_parameters
+                        else:
+                            params = {}
+                            for key, param in original_parameters.items():
+                                if param.get("auto", ParamsAutoGenerated.OPEN.value) == ParamsAutoGenerated.CLOSE.value:
+                                    params[key] = param.get("value", "")
+                                    manual_input_params.append(key)
+                                else:
+                                    params[key] = None
+                            settings = {k: v.get("value", None) for k, v in setting_params.items()}
+                            parameters = {**params, **settings}
                        entity = AgentToolEntity(
                            provider_id=tool.get("provider_name", ""),
-                            provider_type=ToolProviderType.BUILT_IN,
+                            provider_type=provider_type,
                            tool_name=tool.get("tool_name", ""),
-                            tool_parameters=tool.get("parameters", {}),
+                            tool_parameters=parameters,
                            plugin_unique_identifier=tool.get("plugin_unique_identifier", None),
                        )

@@ -178,13 +196,27 @@ class AgentNode(ToolNode):
                            tool_runtime.entity.description.llm = (
                                extra.get("descrption", "") or tool_runtime.entity.description.llm
                            )
-
-                        tool_value.append(
-                            {
-                                **tool_runtime.entity.model_dump(mode="json"),
-                                "runtime_parameters": tool_runtime.runtime.runtime_parameters,
+                        for params in tool_runtime.entity.parameters:
+                            params.form = (
+                                ToolParameter.ToolParameterForm.FORM
+                                if params.name in manual_input_params
+                                else params.form
+                            )
+                        if tool_runtime.entity.parameters:
+                            manual_input_value = {
+                                key: value for key, value in parameters.items() if key in manual_input_params
                            }
-                        )
+                            runtime_parameters = {
+                                **tool_runtime.runtime.runtime_parameters,
+                                **manual_input_value,
+                            }
+                            tool_value.append(
+                                {
+                                    **tool_runtime.entity.model_dump(mode="json"),
+                                    "runtime_parameters": runtime_parameters,
+                                    "provider_type": provider_type.value,
+                                }
+                            )
                    value = tool_value
                if parameter.type == "model-selector":
                    value = cast(dict[str, Any], value)
@@ -1,3 +1,4 @@
+from enum import Enum
 from typing import Any, Literal, Union

 from pydantic import BaseModel
@@ -16,3 +17,8 @@ class AgentNodeData(BaseNodeData):
        type: Literal["mixed", "variable", "constant"]

    agent_parameters: dict[str, AgentInput]
+
+
+class ParamsAutoGenerated(Enum):
+    CLOSE = 0
+    OPEN = 1
@@ -195,7 +195,7 @@ class CodeNode(BaseNode[CodeNodeData]):
            if output_config.type == "object":
                # check if output is object
                if not isinstance(result.get(output_name), dict):
-                    if result[output_name] is None:
+                    if isinstance(result.get(output_name), type(None)):
                        transformed_result[output_name] = None
                    else:
                        raise OutputValidationError(
@@ -223,7 +223,7 @@ class CodeNode(BaseNode[CodeNodeData]):
            elif output_config.type == "array[number]":
                # check if array of number available
                if not isinstance(result[output_name], list):
-                    if result[output_name] is None:
+                    if isinstance(result[output_name], type(None)):
                        transformed_result[output_name] = None
                    else:
                        raise OutputValidationError(
@@ -244,7 +244,7 @@ class CodeNode(BaseNode[CodeNodeData]):
            elif output_config.type == "array[string]":
                # check if array of string available
                if not isinstance(result[output_name], list):
-                    if result[output_name] is None:
+                    if isinstance(result[output_name], type(None)):
                        transformed_result[output_name] = None
                    else:
                        raise OutputValidationError(
@@ -265,7 +265,7 @@ class CodeNode(BaseNode[CodeNodeData]):
            elif output_config.type == "array[object]":
                # check if array of object available
                if not isinstance(result[output_name], list):
-                    if result[output_name] is None:
+                    if isinstance(result[output_name], type(None)):
                        transformed_result[output_name] = None
                    else:
                        raise OutputValidationError(
@@ -64,7 +64,7 @@ class EndStreamGeneratorRouter:
                node_type = node.get("data", {}).get("type")
                if (
                    variable_selector.value_selector not in value_selectors
-                    and node_type == NodeType.LLM.value
+                    and (node_type in (NodeType.LLM.value, NodeType.AGENT.value))
                    and variable_selector.value_selector[1] == "text"
                ):
                    value_selectors.append(list(variable_selector.value_selector))
@@ -3,7 +3,7 @@ from typing import Any, Optional

 from pydantic import BaseModel, Field, field_validator

-from core.model_runtime.entities import ImagePromptMessageContent, LLMMode
+from core.model_runtime.entities import ImagePromptMessageContent
 from core.prompt.entities.advanced_prompt_entities import ChatModelMessage, CompletionModelPromptTemplate, MemoryConfig
 from core.workflow.entities.variable_entities import VariableSelector
 from core.workflow.nodes.base import BaseNodeData
@@ -12,7 +12,7 @@ from core.workflow.nodes.base import BaseNodeData
 class ModelConfig(BaseModel):
    provider: str
    name: str
-    mode: LLMMode
+    mode: str
    completion_params: dict[str, Any] = {}


@@ -3,7 +3,6 @@ import logging
 from collections.abc import Generator, Mapping, Sequence
 from typing import TYPE_CHECKING, Any, Optional, cast

-from configs import dify_config
 from core.app.entities.app_invoke_entities import ModelConfigWithCredentialsEntity
 from core.entities.model_entities import ModelStatus
 from core.entities.provider_entities import QuotaUnit
@@ -186,8 +185,6 @@ class LLMNode(BaseNode[LLMNodeData]):
                    result_text = event.text
                    usage = event.usage
                    finish_reason = event.finish_reason
-                    # deduct quota
-                    self.deduct_llm_quota(tenant_id=self.tenant_id, model_instance=model_instance, usage=usage)
                    break
        except LLMNodeError as e:
            yield RunCompletedEvent(
@@ -243,7 +240,17 @@ class LLMNode(BaseNode[LLMNodeData]):
            user=self.user_id,
        )

-        return self._handle_invoke_result(invoke_result=invoke_result)
+        # handle invoke result
+        generator = self._handle_invoke_result(invoke_result=invoke_result)
+
+        usage = LLMUsage.empty_usage()
+        for event in generator:
+            yield event
+            if isinstance(event, ModelInvokeCompletedEvent):
+                usage = event.usage
+
+        # deduct quota
+        self.deduct_llm_quota(tenant_id=self.tenant_id, model_instance=model_instance, usage=usage)

    def _handle_invoke_result(self, invoke_result: LLMResult | Generator) -> Generator[NodeEvent, None, None]:
        if isinstance(invoke_result, LLMResult):
@@ -733,7 +740,10 @@ class LLMNode(BaseNode[LLMNodeData]):
            if quota_unit == QuotaUnit.TOKENS:
                used_quota = usage.total_tokens
            elif quota_unit == QuotaUnit.CREDITS:
-                used_quota = dify_config.get_model_credits(model_instance.model)
+                used_quota = 1
+
+                if "gpt-4" in model_instance.model:
+                    used_quota = 20
            else:
                used_quota = 1

@@ -44,11 +44,13 @@ class QuestionClassifierNode(LLMNode):
        variable_pool = self.graph_runtime_state.variable_pool

        # extract variables
-        variable = variable_pool.get(node_data.query_variable_selector) if node_data.query_variable_selector else None
+        variable = variable_pool.get(
+            node_data.query_variable_selector) if node_data.query_variable_selector else None
        query = variable.value if variable else None
        variables = {"query": query}
        # fetch model config
-        model_instance, model_config = self._fetch_model_config(node_data.model)
+        model_instance, model_config = self._fetch_model_config(
+            node_data.model)
        # fetch memory
        memory = self._fetch_memory(
            node_data_memory=node_data.memory,
@@ -56,7 +58,8 @@ class QuestionClassifierNode(LLMNode):
        )
        # fetch instruction
        node_data.instruction = node_data.instruction or ""
-        node_data.instruction = variable_pool.convert_template(node_data.instruction).text
+        node_data.instruction = variable_pool.convert_template(
+            node_data.instruction).text

        files = (
            self._fetch_files(
@@ -178,12 +181,15 @@ class QuestionClassifierNode(LLMNode):
        variable_mapping = {"query": node_data.query_variable_selector}
        variable_selectors = []
        if node_data.instruction:
-            variable_template_parser = VariableTemplateParser(template=node_data.instruction)
-            variable_selectors.extend(variable_template_parser.extract_variable_selectors())
+            variable_template_parser = VariableTemplateParser(
+                template=node_data.instruction)
+            variable_selectors.extend(
+                variable_template_parser.extract_variable_selectors())
        for variable_selector in variable_selectors:
            variable_mapping[variable_selector.variable] = variable_selector.value_selector

-        variable_mapping = {node_id + "." + key: value for key, value in variable_mapping.items()}
+        variable_mapping = {node_id + "." + key: value for key,
+                            value in variable_mapping.items()}

        return variable_mapping

@@ -204,7 +210,8 @@ class QuestionClassifierNode(LLMNode):
        context: Optional[str],
    ) -> int:
        prompt_transform = AdvancedPromptTransform(with_variable_tmpl=True)
-        prompt_template = self._get_prompt_template(node_data, query, None, 2000)
+        prompt_template = self._get_prompt_template(
+            node_data, query, None, 2000)
        prompt_messages = prompt_transform.get_prompt(
            prompt_template=prompt_template,
            inputs={},
@@ -217,13 +224,15 @@ class QuestionClassifierNode(LLMNode):
        )
        rest_tokens = 2000

-        model_context_tokens = model_config.model_schema.model_properties.get(ModelPropertyKey.CONTEXT_SIZE)
+        model_context_tokens = model_config.model_schema.model_properties.get(
+            ModelPropertyKey.CONTEXT_SIZE)
        if model_context_tokens:
            model_instance = ModelInstance(
                provider_model_bundle=model_config.provider_model_bundle, model=model_config.model
            )

-            curr_message_tokens = model_instance.get_llm_num_tokens(prompt_messages)
+            curr_message_tokens = model_instance.get_llm_num_tokens(
+                prompt_messages)

            max_tokens = 0
            for parameter_rule in model_config.model_schema.parameter_rules:
@@ -264,7 +273,8 @@ class QuestionClassifierNode(LLMNode):
        prompt_messages: list[LLMNodeChatModelMessage] = []
        if model_mode == ModelMode.CHAT:
            system_prompt_messages = LLMNodeChatModelMessage(
-                role=PromptMessageRole.SYSTEM, text=QUESTION_CLASSIFIER_SYSTEM_PROMPT.format(histories=memory_str)
+                role=PromptMessageRole.SYSTEM, text=QUESTION_CLASSIFIER_SYSTEM_PROMPT.format(
+                    histories=memory_str)
            )
            prompt_messages.append(system_prompt_messages)
            user_prompt_message_1 = LLMNodeChatModelMessage(
@@ -305,4 +315,5 @@ class QuestionClassifierNode(LLMNode):
            )

        else:
-            raise InvalidModelTypeError(f"Model mode {model_mode} not support.")
+            raise InvalidModelTypeError(
+                f"Model mode {model_mode} not support.")
@@ -338,6 +338,7 @@ class ToolNode(BaseNode[ToolNodeData]):
                    data=message.message.data,
                    label=message.message.label,
                    metadata=message.message.metadata,
+                    node_id=self.node_id,
                )

                # check if the agent log is already in the list
@@ -20,11 +20,11 @@ if [[ "${MODE}" == "worker" ]]; then
    CONCURRENCY_OPTION="-c ${CELERY_WORKER_AMOUNT:-1}"
  fi

-  exec celery -A app.celery worker -P ${CELERY_WORKER_CLASS:-gevent} $CONCURRENCY_OPTION --loglevel ${LOG_LEVEL:-INFO} \
+  exec celery -A app.celery worker -P ${CELERY_WORKER_CLASS:-gevent} $CONCURRENCY_OPTION --loglevel ${LOG_LEVEL} \
    -Q ${CELERY_QUEUES:-dataset,mail,ops_trace,app_deletion}

 elif [[ "${MODE}" == "beat" ]]; then
-  exec celery -A app.celery beat --loglevel ${LOG_LEVEL:-INFO}
+  exec celery -A app.celery beat --loglevel ${LOG_LEVEL}
 else
  if [[ "${DEBUG}" == "true" ]]; then
    exec flask run --host=${DIFY_BIND_ADDRESS:-0.0.0.0} --port=${DIFY_PORT:-5001} --debug
@@ -1,4 +1,3 @@
-from configs import dify_config
 from core.app.entities.app_invoke_entities import AgentChatAppGenerateEntity, ChatAppGenerateEntity
 from core.entities.provider_entities import QuotaUnit
 from events.message_event import message_was_created
@@ -41,7 +40,10 @@ def handle(sender, **kwargs):
        if quota_unit == QuotaUnit.TOKENS:
            used_quota = message.message_tokens + message.answer_tokens
        elif quota_unit == QuotaUnit.CREDITS:
-            used_quota = dify_config.get_model_credits(model_config.model)
+            used_quota = 1
+
+            if "gpt-4" in model_config.model:
+                used_quota = 20
        else:
            used_quota = 1

@@ -27,11 +27,12 @@ def init_app(app: DifyApp):
    # Always add StreamHandler to log to console
    sh = logging.StreamHandler(sys.stdout)
    sh.addFilter(RequestIdFilter())
+    log_formatter = logging.Formatter(fmt=dify_config.LOG_FORMAT)
+    sh.setFormatter(log_formatter)
    log_handlers.append(sh)

    logging.basicConfig(
        level=dify_config.LOG_LEVEL,
-        format=dify_config.LOG_FORMAT,
        datefmt=dify_config.LOG_DATEFORMAT,
        handlers=log_handlers,
        force=True,
@@ -32,11 +32,7 @@ class AwsS3Storage(BaseStorage):
                aws_access_key_id=dify_config.S3_ACCESS_KEY,
                endpoint_url=dify_config.S3_ENDPOINT,
                region_name=dify_config.S3_REGION,
-                config=Config(
-                    s3={"addressing_style": dify_config.S3_ADDRESS_STYLE},
-                    request_checksum_calculation="when_required",
-                    response_checksum_validation="when_required",
-                ),
+                config=Config(s3={"addressing_style": dify_config.S3_ADDRESS_STYLE}),
            )
        # create bucket
        try:
@@ -1,8 +1,6 @@
 from collections.abc import Generator
 from datetime import UTC, datetime, timedelta
-from typing import Optional

-from azure.identity import ChainedTokenCredential, DefaultAzureCredential
 from azure.storage.blob import AccountSasPermissions, BlobServiceClient, ResourceTypes, generate_account_sas

 from configs import dify_config
@@ -20,12 +18,6 @@ class AzureBlobStorage(BaseStorage):
        self.account_name = dify_config.AZURE_BLOB_ACCOUNT_NAME
        self.account_key = dify_config.AZURE_BLOB_ACCOUNT_KEY

-        self.credential: Optional[ChainedTokenCredential] = None
-        if self.account_key == "managedidentity":
-            self.credential = DefaultAzureCredential()
-        else:
-            self.credential = None
-
    def save(self, filename, data):
        client = self._sync_client()
        blob_container = client.get_container_client(container=self.bucket_name)
@@ -65,9 +57,6 @@ class AzureBlobStorage(BaseStorage):
        blob_container.delete_blob(filename)

    def _sync_client(self):
-        if self.account_key == "managedidentity":
-            return BlobServiceClient(account_url=self.account_url, credential=self.credential)  # type: ignore
-
        cache_key = "azure_blob_sas_token_{}_{}".format(self.account_name, self.account_key)
        cache_result = redis_client.get(cache_key)
        if cache_result is not None:
@@ -748,7 +748,7 @@ class DatasetKeywordTable(db.Model):  # type: ignore[name-defined]
                if keyword_table_text:
                    return json.loads(keyword_table_text.decode("utf-8"), cls=SetDecoder)
                return None
-            except Exception as e:
+            except Exception:
                logging.exception(f"Failed to load keyword table from file: {file_key}")
                return None

@@ -1147,10 +1147,8 @@ class Message(Base):
            "id": self.id,
            "app_id": self.app_id,
            "conversation_id": self.conversation_id,
-            "model_id": self.model_id,
            "inputs": self.inputs,
            "query": self.query,
-            "total_price": self.total_price,
            "message": self.message,
            "answer": self.answer,
            "status": self.status,
@@ -1171,9 +1169,7 @@ class Message(Base):
            id=data["id"],
            app_id=data["app_id"],
            conversation_id=data["conversation_id"],
-            model_id=data["model_id"],
            inputs=data["inputs"],
-            total_price=data["total_price"],
            query=data["query"],
            message=data["message"],
            answer=data["answer"],
@@ -0,0 +1,27 @@
+from datetime import datetime
+
+from sqlalchemy.orm import Mapped
+
+from extensions.ext_database import db
+from models.base import Base
+
+from .types import StringUUID
+
+
+class StagingAccountWhitelist(Base):
+    __tablename__ = "staging_account_whitelists"
+
+    __table_args__ = (
+        db.PrimaryKeyConstraint("id", name="staging_account_whitelist_pkey"),
+        db.Index("account_email_idx", "email"),
+    )
+
+    id: Mapped[str] = db.Column(StringUUID, server_default=db.text("uuid_generate_v4()"))
+    email: Mapped[str] = db.Column(db.String(255), nullable=False)
+    disabled: Mapped[bool] = db.Column(db.Boolean, nullable=False, server_default=db.text("false"))
+    created_at: Mapped[datetime] = db.Column(
+        db.DateTime, nullable=False, server_default=db.text("CURRENT_TIMESTAMP(0)")
+    )
+    updated_at: Mapped[datetime] = db.Column(
+        db.DateTime, nullable=False, server_default=db.text("CURRENT_TIMESTAMP(0)")
+    )
@@ -18,7 +18,7 @@ package-mode = false
 authlib = "1.3.1"
 azure-identity = "1.16.1"
 beautifulsoup4 = "4.12.2"
-boto3 = "1.36.12"
+boto3 = "1.35.74"
 bs4 = "~0.0.1"
 cachetools = "~5.3.0"
 celery = "~5.4.0"
@@ -47,7 +47,7 @@ mailchimp-transactional = "~1.0.50"
 markdown = "~3.5.1"
 numpy = "~1.26.4"
 oci = "~2.135.1"
-openai = "~1.61.0"
+openai = "~1.52.0"
 openpyxl = "~3.1.5"
 opik = "~1.3.4"
 pandas = { version = "~2.2.2", extras = ["performance", "excel"] }
@@ -73,6 +73,7 @@ starlette = "0.41.0"
 tiktoken = "~0.8.0"
 tokenizers = "~0.15.0"
 transformers = "~4.35.0"
+types-pytz = "~2024.2.0.20241003"
 unstructured = { version = "~0.16.1", extras = ["docx", "epub", "md", "msg", "ppt", "pptx"] }
 validators = "0.21.0"
 yarl = "~1.18.3"
@@ -149,21 +150,6 @@ pytest = "~8.3.2"
 pytest-benchmark = "~4.0.0"
 pytest-env = "~1.1.3"
 pytest-mock = "~3.14.0"
-types-beautifulsoup4 = "~4.12.0.20241020"
-types-flask-cors = "~5.0.0.20240902"
-types-flask-migrate = "~4.1.0.20250112"
-types-html5lib = "~1.1.11.20241018"
-types-openpyxl = "~3.1.5.20241225"
-types-protobuf = "~5.29.1.20241207"
-types-psutil = "~6.1.0.20241221"
-types-psycopg2 = "~2.9.21.20250121"
-types-python-dateutil = "~2.9.0.20241206"
-types-pytz = "~2024.2.0.20241221"
-types-pyyaml = "~6.0.12.20241230"
-types-regex = "~2024.11.6.20241221"
-types-requests = "~2.32.0.20241016"
-types-six = "~1.17.0.20241205"
-types-tqdm = "~4.67.0.20241221"

 ############################################################
 # [ Lint ] dependency group
@@ -33,6 +33,7 @@ from models.account import (
    TenantStatus,
 )
 from models.model import DifySetup
+from models.staging import StagingAccountWhitelist
 from services.billing_service import BillingService
 from services.errors.account import (
    AccountAlreadyInTenantError,
@@ -78,7 +79,6 @@ class AccountService:
        prefix="email_code_account_deletion_rate_limit", max_attempts=1, time_window=60 * 1
    )
    LOGIN_MAX_ERROR_LIMITS = 5
-    FORGOT_PASSWORD_MAX_ERROR_LIMITS = 5

    @staticmethod
    def _get_refresh_token_key(refresh_token: str) -> str:
@@ -348,6 +348,9 @@ class AccountService:

    @staticmethod
    def login(account: Account, *, ip_address: Optional[str] = None) -> TokenPair:
+        if not AccountService.verify_account_whitelist(account.email):
+            raise ValueError("Account is not whitelisted")
+
        if ip_address:
            AccountService.update_login_info(account=account, ip_address=ip_address)

@@ -379,6 +382,9 @@ class AccountService:
        if not account:
            raise ValueError("Invalid account")

+        if not AccountService.verify_account_whitelist(account.email):
+            raise ValueError("Account is not whitelisted")
+
        # Generate new access token and refresh token
        new_access_token = AccountService.get_account_jwt_token(account)
        new_refresh_token = _generate_refresh_token()
@@ -388,6 +394,16 @@ class AccountService:

        return TokenPair(access_token=new_access_token, refresh_token=new_refresh_token)

+    @staticmethod
+    def verify_account_whitelist(email: str) -> bool:
+        with Session(db.engine) as session:
+            return (
+                session.query(StagingAccountWhitelist)
+                .filter(StagingAccountWhitelist.email == email, StagingAccountWhitelist.disabled == False)
+                .first()
+                is not None
+            )
+
    @staticmethod
    def load_logged_in_account(*, account_id: str):
        return AccountService.load_user(account_id)
@@ -432,9 +448,13 @@ class AccountService:
    def send_email_code_login_email(
        cls, account: Optional[Account] = None, email: Optional[str] = None, language: Optional[str] = "en-US"
    ):
-        email = account.email if account else email
-        if email is None:
-            raise ValueError("Email must be provided.")
+        if email:
+            if not AccountService.verify_account_whitelist(email):
+                raise ValueError("Account is not whitelisted")
+        elif account:
+            if not AccountService.verify_account_whitelist(account.email):
+                raise ValueError("Account is not whitelisted")
+
        if cls.email_code_login_rate_limiter.is_rate_limited(email):
            from controllers.console.auth.error import EmailCodeLoginRateLimitExceededError

@@ -505,32 +525,6 @@ class AccountService:
        key = f"login_error_rate_limit:{email}"
        redis_client.delete(key)

-    @staticmethod
-    def add_forgot_password_error_rate_limit(email: str) -> None:
-        key = f"forgot_password_error_rate_limit:{email}"
-        count = redis_client.get(key)
-        if count is None:
-            count = 0
-        count = int(count) + 1
-        redis_client.setex(key, dify_config.FORGOT_PASSWORD_LOCKOUT_DURATION, count)
-
-    @staticmethod
-    def is_forgot_password_error_rate_limit(email: str) -> bool:
-        key = f"forgot_password_error_rate_limit:{email}"
-        count = redis_client.get(key)
-        if count is None:
-            return False
-
-        count = int(count)
-        if count > AccountService.FORGOT_PASSWORD_MAX_ERROR_LIMITS:
-            return True
-        return False
-
-    @staticmethod
-    def reset_forgot_password_error_rate_limit(email: str):
-        key = f"forgot_password_error_rate_limit:{email}"
-        redis_client.delete(key)
-
    @staticmethod
    def is_email_send_ip_limit(ip_address: str):
        minute_key = f"email_send_ip_limit_minute:{ip_address}"
@@ -21,12 +21,10 @@ class FirecrawlAuth(ApiKeyAuthBase):
        headers = self._prepare_headers()
        options = {
            "url": "https://example.com",
-            "includePaths": [],
-            "excludePaths": [],
-            "limit": 1,
-            "scrapeOptions": {"onlyMainContent": True},
+            "crawlerOptions": {"excludes": [], "includes": [], "limit": 1},
+            "pageOptions": {"onlyMainContent": True},
        }
-        response = self._post_request(f"{self.base_url}/v1/crawl", options, headers)
+        response = self._post_request(f"{self.base_url}/v0/crawl", options, headers)
        if response.status_code == 200:
            return True
        else:
@@ -44,7 +44,6 @@ from models.source import DataSourceOauthBinding
 from services.entities.knowledge_entities.knowledge_entities import (
    ChildChunkUpdateArgs,
    KnowledgeConfig,
-    MetaDataConfig,
    RerankingModel,
    RetrievalModel,
    SegmentUpdateArgs,
@@ -916,9 +915,6 @@ class DocumentService:
                                document.data_source_info = json.dumps(data_source_info)
                                document.batch = batch
                                document.indexing_status = "waiting"
-                                if knowledge_config.metadata:
-                                    document.doc_type = knowledge_config.metadata.doc_type
-                                    document.metadata = knowledge_config.metadata.doc_metadata
                                db.session.add(document)
                                documents.append(document)
                                duplicate_document_ids.append(document.id)
@@ -935,7 +931,6 @@ class DocumentService:
                            account,
                            file_name,
                            batch,
-                            knowledge_config.metadata,
                        )
                        db.session.add(document)
                        db.session.flush()
@@ -991,7 +986,6 @@ class DocumentService:
                                    account,
                                    page.page_name,
                                    batch,
-                                    knowledge_config.metadata,
                                )
                                db.session.add(document)
                                db.session.flush()
@@ -1032,7 +1026,6 @@ class DocumentService:
                            account,
                            document_name,
                            batch,
-                            knowledge_config.metadata,
                        )
                        db.session.add(document)
                        db.session.flush()
@@ -1070,7 +1063,6 @@ class DocumentService:
        account: Account,
        name: str,
        batch: str,
-        metadata: Optional[MetaDataConfig] = None,
    ):
        document = Document(
            tenant_id=dataset.tenant_id,
@@ -1086,9 +1078,6 @@ class DocumentService:
            doc_form=document_form,
            doc_language=document_language,
        )
-        if metadata is not None:
-            document.doc_metadata = metadata.doc_metadata
-            document.doc_type = metadata.doc_type
        return document

    @staticmethod
@@ -1201,10 +1190,6 @@ class DocumentService:
        # update document name
        if document_data.name:
            document.name = document_data.name
-        # update doc_type and doc_metadata if provided
-        if document_data.metadata is not None:
-            document.doc_metadata = document_data.metadata.doc_type
-            document.doc_type = document_data.metadata.doc_type
        # update document to be waiting
        document.indexing_status = "waiting"
        document.completed_at = None
@@ -93,11 +93,6 @@ class RetrievalModel(BaseModel):
    score_threshold: Optional[float] = None


-class MetaDataConfig(BaseModel):
-    doc_type: str
-    doc_metadata: dict
-
-
 class KnowledgeConfig(BaseModel):
    original_document_id: Optional[str] = None
    duplicate: bool = True
@@ -110,7 +105,6 @@ class KnowledgeConfig(BaseModel):
    embedding_model: Optional[str] = None
    embedding_model_provider: Optional[str] = None
    name: Optional[str] = None
-    metadata: Optional[MetaDataConfig] = None


 class SegmentUpdateArgs(BaseModel):
@@ -1,6 +1,7 @@
 import datetime
 import json
 import logging
+import sys
 import time
 from collections.abc import Mapping, Sequence
 from concurrent.futures import ThreadPoolExecutor
@@ -417,6 +418,8 @@ class PluginMigration:

        logger.info("Uninstall plugins")

+        sys.exit(-1)
+
        # get installation
        try:
            installation = manager.list_plugins(fake_tenant_id)
@@ -7,7 +7,7 @@ from sqlalchemy.orm import Session
 from configs import dify_config
 from core.helper.position_helper import is_filtered
 from core.model_runtime.utils.encoders import jsonable_encoder
-from core.plugin.entities.plugin import GenericProviderID, ToolProviderID
+from core.plugin.entities.plugin import GenericProviderID
 from core.plugin.manager.exc import PluginDaemonClientSideError
 from core.tools.builtin_tool.providers._positions import BuiltinToolProviderSort
 from core.tools.entities.api_entities import ToolApiEntity, ToolProviderApiEntity
@@ -240,7 +240,10 @@ class BuiltinToolManageService:

        # rewrite db_providers
        for db_provider in db_providers:
-            db_provider.provider = str(ToolProviderID(db_provider.provider))
+            try:
+                GenericProviderID(db_provider.provider)
+            except Exception:
+                db_provider.provider = f"langgenius/{db_provider.provider}/{db_provider.provider}"

        # find provider
        def find_provider(provider):
@@ -255,7 +258,7 @@ class BuiltinToolManageService:
                    include_set=dify_config.POSITION_TOOL_INCLUDES_SET,  # type: ignore
                    exclude_set=dify_config.POSITION_TOOL_EXCLUDES_SET,  # type: ignore
                    data=provider_controller,
-                    name_func=lambda x: x.identity.name,
+                    name_func=lambda x: x.entity.identity.name,
                ):
                    continue

@@ -54,7 +54,7 @@ class ToolTransformService:
    @staticmethod
    def repack_provider(tenant_id: str, provider: Union[dict, ToolProviderApiEntity]):
        """
-        repack provider
+        repack  provider

        :param provider: the provider dict
        """
@@ -38,22 +38,30 @@ class WebsiteService:
            only_main_content = options.get("only_main_content", False)
            if not crawl_sub_pages:
                params = {
-                    "includePaths": [],
-                    "excludePaths": [],
-                    "limit": 1,
-                    "scrapeOptions": {"onlyMainContent": only_main_content},
+                    "crawlerOptions": {
+                        "includes": [],
+                        "excludes": [],
+                        "generateImgAltText": True,
+                        "limit": 1,
+                        "returnOnlyUrls": False,
+                        "pageOptions": {"onlyMainContent": only_main_content, "includeHtml": False},
+                    }
                }
            else:
                includes = options.get("includes").split(",") if options.get("includes") else []
                excludes = options.get("excludes").split(",") if options.get("excludes") else []
                params = {
-                    "includePaths": includes,
-                    "excludePaths": excludes,
-                    "limit": options.get("limit", 1),
-                    "scrapeOptions": {"onlyMainContent": only_main_content},
+                    "crawlerOptions": {
+                        "includes": includes,
+                        "excludes": excludes,
+                        "generateImgAltText": True,
+                        "limit": options.get("limit", 1),
+                        "returnOnlyUrls": False,
+                        "pageOptions": {"onlyMainContent": only_main_content, "includeHtml": False},
+                    }
                }
                if options.get("max_depth"):
-                    params["maxDepth"] = options.get("max_depth")
+                    params["crawlerOptions"]["maxDepth"] = options.get("max_depth")
            job_id = firecrawl_app.crawl_url(url, params)
            website_crawl_time_cache_key = f"website_crawl_{job_id}"
            time = str(datetime.datetime.now().timestamp())
@@ -220,7 +228,7 @@ class WebsiteService:
            # decrypt api_key
            api_key = encrypter.decrypt_token(tenant_id=tenant_id, token=credentials.get("config").get("api_key"))
            firecrawl_app = FirecrawlApp(api_key=api_key, base_url=credentials.get("config").get("base_url", None))
-            params = {"onlyMainContent": only_main_content}
+            params = {"pageOptions": {"onlyMainContent": only_main_content, "includeHtml": False}}
            result = firecrawl_app.scrape_url(url, params)
            return result
        else:
@@ -10,17 +10,19 @@ def test_firecrawl_web_extractor_crawl_mode(mocker):
    base_url = "https://api.firecrawl.dev"
    firecrawl_app = FirecrawlApp(api_key=api_key, base_url=base_url)
    params = {
-        "includePaths": [],
-        "excludePaths": [],
-        "maxDepth": 1,
-        "limit": 1,
+        "crawlerOptions": {
+            "includes": [],
+            "excludes": [],
+            "generateImgAltText": True,
+            "maxDepth": 1,
+            "limit": 1,
+            "returnOnlyUrls": False,
+        }
    }
    mocked_firecrawl = {
-        "id": "test",
+        "jobId": "test",
    }
    mocker.patch("requests.post", return_value=_mock_response(mocked_firecrawl))
    job_id = firecrawl_app.crawl_url(url, params)
-    print(f"job_id: {job_id}")
-
-    assert job_id is not None
+    print(job_id)
    assert isinstance(job_id, str)
@@ -68,7 +68,8 @@ def test_executor_with_json_body_and_object_variable():
        system_variables={},
        user_inputs={},
    )
-    variable_pool.add(["pre_node_id", "object"], {"name": "John Doe", "age": 30, "email": "john@example.com"})
+    variable_pool.add(["pre_node_id", "object"], {
+                      "name": "John Doe", "age": 30, "email": "john@example.com"})

    # Prepare the node data
    node_data = HttpRequestNodeData(
@@ -123,7 +124,8 @@ def test_executor_with_json_body_and_nested_object_variable():
        system_variables={},
        user_inputs={},
    )
-    variable_pool.add(["pre_node_id", "object"], {"name": "John Doe", "age": 30, "email": "john@example.com"})
+    variable_pool.add(["pre_node_id", "object"], {
+                      "name": "John Doe", "age": 30, "email": "john@example.com"})

    # Prepare the node data
    node_data = HttpRequestNodeData(
@@ -18,6 +18,14 @@ from models.enums import UserFrom
 from models.workflow import WorkflowNodeExecutionStatus, WorkflowType


+def test_plain_text_to_dict():
+    assert _plain_text_to_dict("aa\n cc:") == {"aa": "", "cc": ""}
+    assert _plain_text_to_dict("aa:bb\n cc:dd") == {"aa": "bb", "cc": "dd"}
+    assert _plain_text_to_dict("aa:bb\n cc:dd\n") == {"aa": "bb", "cc": "dd"}
+    assert _plain_text_to_dict("aa:bb\n\n cc : dd\n\n") == {
+        "aa": "bb", "cc": "dd"}
+
+
 def test_http_request_node_binary_file(monkeypatch):
    data = HttpRequestNodeData(
        title="test",
@@ -183,7 +191,8 @@ def test_http_request_node_form_with_file(monkeypatch):

    def attr_checker(*args, **kwargs):
        assert kwargs["data"] == {"name": "test"}
-        assert kwargs["files"] == {"file": (None, b"test", "application/octet-stream")}
+        assert kwargs["files"] == {
+            "file": (None, b"test", "application/octet-stream")}
        return httpx.Response(200, content=b"")

    monkeypatch.setattr(
@@ -2,7 +2,7 @@ x-shared-env: &shared-api-worker-env
 services:
  # API service
  api:
-    image: langgenius/dify-api:1.0.0
+    image: langgenius/dify-api:1.0.0-beta.1
    restart: always
    environment:
      # Use the shared environment variables.
@@ -27,7 +27,7 @@ services:
  # worker service
  # The Celery worker for processing the queue.
  worker:
-    image: langgenius/dify-api:1.0.0
+    image: langgenius/dify-api:1.0.0-beta.1
    restart: always
    environment:
      # Use the shared environment variables.
@@ -51,7 +51,7 @@ services:

  # Frontend web application.
  web:
-    image: langgenius/dify-web:1.0.0
+    image: langgenius/dify-web:1.0.0-beta.1
    restart: always
    environment:
      CONSOLE_API_URL: ${CONSOLE_API_URL:-}
@@ -410,7 +410,7 @@ x-shared-env: &shared-api-worker-env
 services:
  # API service
  api:
-    image: langgenius/dify-api:1.0.0
+    image: langgenius/dify-api:1.0.0-beta.1
    restart: always
    environment:
      # Use the shared environment variables.
@@ -435,7 +435,7 @@ services:
  # worker service
  # The Celery worker for processing the queue.
  worker:
-    image: langgenius/dify-api:1.0.0
+    image: langgenius/dify-api:1.0.0-beta.1
    restart: always
    environment:
      # Use the shared environment variables.
@@ -459,11 +459,13 @@ services:

  # Frontend web application.
  web:
-    image: langgenius/dify-web:1.0.0
+    image: langgenius/dify-web:1.0.0-beta.1
    restart: always
    environment:
      CONSOLE_API_URL: ${CONSOLE_API_URL:-}
      APP_API_URL: ${APP_API_URL:-}
+      MARKETPLACE_API_URL: ${MARKETPLACE_API_URL:-}
+      MARKETPLACE_URL: ${MARKETPLACE_URL:-}
      SENTRY_DSN: ${WEB_SENTRY_DSN:-}
      NEXT_TELEMETRY_DISABLED: ${NEXT_TELEMETRY_DISABLED:-0}
      TEXT_GENERATION_TIMEOUT_MS: ${TEXT_GENERATION_TIMEOUT_MS:-60000}
@@ -31,7 +31,6 @@ server {

    location /e {
      proxy_pass http://plugin_daemon:5002;
-      proxy_set_header Dify-Hook-Url $scheme://$host$request_uri;
      include proxy.conf;
    }

@@ -7,7 +7,6 @@ acl localnet src 192.168.0.0/16		# RFC 1918 local private network (LAN)
 acl localnet src fc00::/7       	# RFC 4193 local private network range
 acl localnet src fe80::/10      	# RFC 4291 link-local (directly plugged) machines
 acl SSL_ports port 443
-# acl SSL_ports port 1025-65535   # Enable the configuration to resolve this issue: https://github.com/langgenius/dify/issues/12792
 acl Safe_ports port 80		# http
 acl Safe_ports port 21		# ftp
 acl Safe_ports port 443		# https
@@ -87,7 +87,7 @@ class TestKnowledgeBaseClient(unittest.TestCase):
    def _test_005_batch_indexing_status(self):
        client = self._get_dataset_kb_client()
        response = client.batch_indexing_status(self.batch_id)
-        response.json()
+        data = response.json()
        self.assertEqual(response.status_code, 200)

    def _test_006_update_document_by_file(self):
@@ -68,6 +68,7 @@ RUN pnpm add -g pm2 \
    && chown -R 1001:0 /.pm2 /app/web \
    && chmod -R g=u /.pm2 /app/web

+
 ARG COMMIT_SHA
 ENV COMMIT_SHA=${COMMIT_SHA}

@@ -162,9 +162,9 @@ const AppDetailLayout: FC<IAppDetailLayoutProps> = (props) => {
  }

  return (
-    <div className={cn(s.app, 'flex relative', 'overflow-hidden')}>
+    <div className={cn(s.app, 'flex', 'overflow-hidden')}>
      {appDetail && (
-        <AppSideBar title={appDetail.name} icon={appDetail.icon} icon_background={appDetail.icon_background as string} desc={appDetail.mode} navigation={navigation} />
+        <AppSideBar title={appDetail.name} icon={appDetail.icon} icon_background={appDetail.icon_background} desc={appDetail.mode} navigation={navigation} />
      )}
      <div className="bg-components-panel-bg grow overflow-hidden">
        {children}
@@ -24,11 +24,9 @@ import AppContext from '@/context/app-context'

 export type ICardViewProps = {
  appId: string
-  isInPanel?: boolean
-  className?: string
 }

-const CardView: FC<ICardViewProps> = ({ appId, isInPanel, className }) => {
+const CardView: FC<ICardViewProps> = ({ appId }) => {
  const { t } = useTranslation()
  const { notify } = useContext(ToastContext)
  const appDetail = useAppStore(state => state.appDetail)
@@ -122,11 +120,10 @@ const CardView: FC<ICardViewProps> = ({ appId, isInPanel, className }) => {
    return <Loading />

  return (
-    <div className={className || 'grid gap-6 grid-cols-1 xl:grid-cols-2 w-full mb-6'}>
+    <div className="grid gap-6 grid-cols-1 xl:grid-cols-2 w-full mb-6">
      <AppCard
        appInfo={appDetail}
        cardType="webapp"
-        isInPanel={isInPanel}
        onChangeStatus={onChangeSiteStatus}
        onGenerateCode={onGenerateCode}
        onSaveSiteConfig={onSaveSiteConfig}
@@ -134,7 +131,6 @@ const CardView: FC<ICardViewProps> = ({ appId, isInPanel, className }) => {
      <AppCard
        cardType="api"
        appInfo={appDetail}
-        isInPanel={isInPanel}
        onChangeStatus={onChangeApiStatus}
      />
    </div>
@@ -11,7 +11,6 @@ import type { LangFuseConfig, LangSmithConfig, OpikConfig } from './type'
 import { TracingProvider } from './type'
 import TracingIcon from './tracing-icon'
 import ConfigButton from './config-button'
-import cn from '@/utils/classnames'
 import { LangfuseIcon, LangsmithIcon, OpikIcon } from '@/app/components/base/icons/src/public/tracing'
 import Indicator from '@/app/components/header/indicator'
 import { fetchTracingConfig as doFetchTracingConfig, fetchTracingStatus, updateTracingStatus } from '@/service/apps'
@@ -20,6 +19,7 @@ import Toast from '@/app/components/base/toast'
 import { useAppContext } from '@/context/app-context'
 import Loading from '@/app/components/base/loading'
 import Divider from '@/app/components/base/divider'
+import cn from '@/utils/classnames'

 const I18N_PREFIX = 'app.tracing'

@@ -80,9 +80,7 @@ const Panel: FC = () => {
      ? LangsmithIcon
      : inUseTracingProvider === TracingProvider.langfuse
        ? LangfuseIcon
-        : inUseTracingProvider === TracingProvider.opik
-          ? OpikIcon
-          : null
+        : OpikIcon

  const [langSmithConfig, setLangSmithConfig] = useState<LangSmithConfig | null>(null)
  const [langFuseConfig, setLangFuseConfig] = useState<LangFuseConfig | null>(null)
@@ -283,7 +283,7 @@ const ProviderConfigModal: FC<Props> = ({
                            >
                              <span className='text-[#D92D20]'>{t('common.operation.remove')}</span>
                            </Button>
-                            <Divider className='mx-3 h-[18px]' />
+                            <Divider className='mx-3 h-[18px]'/>
                          </>
                        )}
                        <Button
@@ -30,7 +30,9 @@ const ApiServer: FC<ApiServerProps> = ({
        {t('appApi.ok')}
      </div>
      <SecretKeyButton
-        className='shrink-0 !h-8 bg-white'
+        className='flex-shrink-0 !h-8 bg-white'
+        textCls='!text-gray-700 font-medium'
+        iconCls='stroke-[1.2px]'
      />
    </div>
  )
@@ -47,44 +47,6 @@ import { Row, Col, Properties, Property, Heading, SubProperty, PropertyInstructi
      <Property name='text' type='string' key='text'>
        Document content
      </Property>
-      <Property name='doc_type' type='string' key='doc_type'>
-        Type of document (optional):
-          - <code>book</code> Book
-          - <code>web_page</code> Web page
-          - <code>paper</code> Academic paper/article 
-          - <code>social_media_post</code> Social media post
-          - <code>wikipedia_entry</code> Wikipedia entry
-          - <code>personal_document</code> Personal document
-          - <code>business_document</code> Business document
-          - <code>im_chat_log</code> Chat log
-          - <code>synced_from_notion</code> Notion document
-          - <code>synced_from_github</code> GitHub document
-          - <code>others</code> Other document types
-      </Property>
-      <Property name='doc_metadata' type='object' key='doc_metadata'>
-        Document metadata (required if doc_type is provided). Fields vary by doc_type:
-          For <code>book</code>:
-          - <code>title</code> Book title 
-          - <code>language</code> Book language
-          - <code>author</code> Book author
-          - <code>publisher</code> Publisher name
-          - <code>publication_date</code> Publication date
-          - <code>isbn</code> ISBN number
-          - <code>category</code> Book category
-
-          For <code>web_page</code>:
-          - <code>title</code> Page title
-          - <code>url</code> Page URL
-          - <code>language</code> Page language
-          - <code>publish_date</code> Publish date
-          - <code>author/publisher</code> Author or publisher
-          - <code>topic/keywords</code> Topic or keywords
-          - <code>description</code> Page description
-
-          Please check [api/services/dataset_service.py](https://github.com/langgenius/dify/blob/main/api/services/dataset_service.py#L475) for more details on the fields required for each doc_type.
-
-          For doc_type "others", any valid JSON object is accepted
-      </Property>
      <Property name='indexing_technique' type='string' key='indexing_technique'>
        Index mode
          - <code>high_quality</code> High quality: embedding using embedding model, built as vector database index
@@ -233,68 +195,6 @@ import { Row, Col, Properties, Property, Heading, SubProperty, PropertyInstructi
          - <code>hierarchical_model</code> Parent-child mode
          - <code>qa_model</code> Q&A Mode: Generates Q&A pairs for segmented documents and then embeds the questions

-        - <code>doc_type</code> Type of document (optional)
-          - <code>book</code> Book
-            Document records a book or publication
-          - <code>web_page</code> Web page 
-            Document records web page content
-          - <code>paper</code> Academic paper/article
-            Document records academic paper or research article
-          - <code>social_media_post</code> Social media post
-            Content from social media posts
-          - <code>wikipedia_entry</code> Wikipedia entry
-            Content from Wikipedia entries
-          - <code>personal_document</code> Personal document
-            Documents related to personal content
-          - <code>business_document</code> Business document
-            Documents related to business content
-          - <code>im_chat_log</code> Chat log
-            Records of instant messaging chats
-          - <code>synced_from_notion</code> Notion document
-            Documents synchronized from Notion
-          - <code>synced_from_github</code> GitHub document
-            Documents synchronized from GitHub
-          - <code>others</code> Other document types
-            Other document types not listed above
-
-        - <code>doc_metadata</code> Document metadata (required if doc_type is provided)
-          Fields vary by doc_type:
-
-          For <code>book</code>:
-          - <code>title</code> Book title
-            Title of the book
-          - <code>language</code> Book language
-            Language of the book
-          - <code>author</code> Book author
-            Author of the book
-          - <code>publisher</code> Publisher name
-            Name of the publishing house
-          - <code>publication_date</code> Publication date
-            Date when the book was published
-          - <code>isbn</code> ISBN number
-            International Standard Book Number
-          - <code>category</code> Book category
-            Category or genre of the book
-
-          For <code>web_page</code>:
-          - <code>title</code> Page title
-            Title of the web page
-          - <code>url</code> Page URL
-            URL address of the web page
-          - <code>language</code> Page language
-            Language of the web page
-          - <code>publish_date</code> Publish date
-            Date when the web page was published
-          - <code>author/publisher</code> Author or publisher
-            Author or publisher of the web page
-          - <code>topic/keywords</code> Topic or keywords
-            Topics or keywords of the web page
-          - <code>description</code> Page description
-            Description of the web page content
-
-          Please check [api/services/dataset_service.py](https://github.com/langgenius/dify/blob/main/api/services/dataset_service.py#L475) for more details on the fields required for each doc_type.
-          For doc_type "others", any valid JSON object is accepted
-
        - <code>doc_language</code> In Q&A mode, specify the language of the document, for example: <code>English</code>, <code>Chinese</code>

        - <code>process_rule</code> Processing rules
@@ -407,44 +307,6 @@ import { Row, Col, Properties, Property, Heading, SubProperty, PropertyInstructi
      <Property name='description' type='string' key='description'>
        Knowledge description (optional)
      </Property>
-      <Property name='doc_type' type='string' key='doc_type'>
-        Type of document (optional):
-          - <code>book</code> Book
-          - <code>web_page</code> Web page
-          - <code>paper</code> Academic paper/article 
-          - <code>social_media_post</code> Social media post
-          - <code>wikipedia_entry</code> Wikipedia entry
-          - <code>personal_document</code> Personal document
-          - <code>business_document</code> Business document
-          - <code>im_chat_log</code> Chat log
-          - <code>synced_from_notion</code> Notion document
-          - <code>synced_from_github</code> GitHub document
-          - <code>others</code> Other document types
-      </Property>
-      <Property name='doc_metadata' type='object' key='doc_metadata'>
-        Document metadata (required if doc_type is provided). Fields vary by doc_type:
-          For <code>book</code>:
-          - <code>title</code> Book title 
-          - <code>language</code> Book language
-          - <code>author</code> Book author
-          - <code>publisher</code> Publisher name
-          - <code>publication_date</code> Publication date
-          - <code>isbn</code> ISBN number
-          - <code>category</code> Book category
-
-          For <code>web_page</code>:
-          - <code>title</code> Page title
-          - <code>url</code> Page URL
-          - <code>language</code> Page language
-          - <code>publish_date</code> Publish date
-          - <code>author/publisher</code> Author or publisher
-          - <code>topic/keywords</code> Topic or keywords
-          - <code>description</code> Page description
-
-          Please check [api/services/dataset_service.py](https://github.com/langgenius/dify/blob/main/api/services/dataset_service.py#L475) for more details on the fields required for each doc_type.
-
-          For doc_type "others", any valid JSON object is accepted
-      </Property>
      <Property name='indexing_technique' type='string' key='indexing_technique'>
        Index technique (optional)
          - <code>high_quality</code> High quality
@@ -762,67 +624,6 @@ import { Row, Col, Properties, Property, Heading, SubProperty, PropertyInstructi
              - <code>separator</code> Segmentation identifier. Currently, only one delimiter is allowed. The default is <code>***</code>
              - <code>max_tokens</code> The maximum length (tokens) must be validated to be shorter than the length of the parent chunk
              - <code>chunk_overlap</code> Define the overlap between adjacent chunks (optional)
-            - <code>doc_type</code> Type of document (optional)
-              - <code>book</code> Book
-                Document records a book or publication
-              - <code>web_page</code> Web page 
-                Document records web page content
-              - <code>paper</code> Academic paper/article
-                Document records academic paper or research article
-              - <code>social_media_post</code> Social media post
-                Content from social media posts
-              - <code>wikipedia_entry</code> Wikipedia entry
-                Content from Wikipedia entries
-              - <code>personal_document</code> Personal document
-                Documents related to personal content
-              - <code>business_document</code> Business document
-                Documents related to business content
-              - <code>im_chat_log</code> Chat log
-                Records of instant messaging chats
-              - <code>synced_from_notion</code> Notion document
-                Documents synchronized from Notion
-              - <code>synced_from_github</code> GitHub document
-                Documents synchronized from GitHub
-              - <code>others</code> Other document types
-                Other document types not listed above
-
-            - <code>doc_metadata</code> Document metadata (required if doc_type is provided)
-              Fields vary by doc_type:
-
-              For <code>book</code>:
-              - <code>title</code> Book title
-                Title of the book
-              - <code>language</code> Book language
-                Language of the book
-              - <code>author</code> Book author
-                Author of the book
-              - <code>publisher</code> Publisher name
-                Name of the publishing house
-              - <code>publication_date</code> Publication date
-                Date when the book was published
-              - <code>isbn</code> ISBN number
-                International Standard Book Number
-              - <code>category</code> Book category
-                Category or genre of the book
-
-              For <code>web_page</code>:
-              - <code>title</code> Page title
-                Title of the web page
-              - <code>url</code> Page URL
-                URL address of the web page
-              - <code>language</code> Page language
-                Language of the web page
-              - <code>publish_date</code> Publish date
-                Date when the web page was published
-              - <code>author/publisher</code> Author or publisher
-                Author or publisher of the web page
-              - <code>topic/keywords</code> Topic or keywords
-                Topics or keywords of the web page
-              - <code>description</code> Page description
-                Description of the web page content
-
-              Please check [api/services/dataset_service.py](https://github.com/langgenius/dify/blob/main/api/services/dataset_service.py#L475) for more details on the fields required for each doc_type.
-              For doc_type "others", any valid JSON object is accepted
      </Property>
    </Properties>
  </Col>
--- a/Show More
+++ b/Show More