add sign-content

2025-01-26 09:59:58 +08:00
310 changed files with 3066 additions and 5402 deletions
@@ -5,8 +5,6 @@ on:
    branches:
      - "main"
      - "deploy/dev"
-      - "deploy/enterprise"
-      - "e-0154"
  release:
    types: [published]

@@ -1,29 +0,0 @@
-name: Deploy Enterprise
-
-permissions:
-  contents: read
-
-on:
-  workflow_run:
-    workflows: ["Build and Push API & Web"]
-    branches:
-      - "deploy/enterprise"
-    types:
-      - completed
-
-jobs:
-  deploy:
-    runs-on: ubuntu-latest
-    if: |
-      github.event.workflow_run.conclusion == 'success' &&
-      github.event.workflow_run.head_branch == 'deploy/enterprise'
-
-    steps:
-      - name: Deploy to server
-        uses: appleboy/ssh-action@v0.1.8
-        with:
-          host: ${{ secrets.ENTERPRISE_SSH_HOST }}
-          username: ${{ secrets.ENTERPRISE_SSH_USER }}
-          password: ${{ secrets.ENTERPRISE_SSH_PASSWORD }}
-          script: |
-            ${{ vars.ENTERPRISE_SSH_SCRIPT || secrets.ENTERPRISE_SSH_SCRIPT }}
@@ -1,47 +0,0 @@
-name: Build docker image
-
-on:
-  pull_request:
-    branches:
-      - "main"
-    paths:
-      - api/Dockerfile
-      - web/Dockerfile
-
-concurrency:
-  group: docker-build-${{ 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/*

@@ -78,6 +76,7 @@ COPY . /app/api/
 COPY docker/entrypoint.sh /entrypoint.sh
 RUN chmod +x /entrypoint.sh

+
 ARG COMMIT_SHA
 ENV COMMIT_SHA=${COMMIT_SHA}

@@ -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="0.15.4",
+        default="0.15.2",
    )

    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
@@ -2,28 +2,30 @@ import uuid
 from typing import cast

 from flask_login import current_user  # type: ignore
-from flask_restful import (Resource, inputs, marshal,  # type: ignore
-                           marshal_with, reqparse)
+from flask_restful import Resource, inputs, marshal, marshal_with, reqparse  # type: ignore
 from sqlalchemy import select
 from sqlalchemy.orm import Session
 from werkzeug.exceptions import BadRequest, Forbidden, abort

 from controllers.console import api
 from controllers.console.app.wraps import get_app_model
-from controllers.console.wraps import (account_initialization_required,
-                                       cloud_edition_billing_resource_check,
-                                       enterprise_license_required,
-                                       setup_required)
+from controllers.console.wraps import (
+    account_initialization_required,
+    cloud_edition_billing_resource_check,
+    enterprise_license_required,
+    setup_required,
+)
 from core.ops.ops_trace_manager import OpsTraceManager
 from extensions.ext_database import db
-from fields.app_fields import (app_detail_fields, app_detail_fields_with_site,
-                               app_pagination_fields)
+from fields.app_fields import (
+    app_detail_fields,
+    app_detail_fields_with_site,
+    app_pagination_fields,
+)
 from libs.login import login_required
 from models import Account, App
 from services.app_dsl_service import AppDslService, ImportMode
 from services.app_service import AppService
-from services.enterprise.enterprise_service import EnterpriseService
-from services.feature_service import FeatureService

 ALLOW_CREATE_APP_MODES = ["chat", "agent-chat", "advanced-chat", "workflow", "completion"]

@@ -65,17 +67,7 @@ class AppListApi(Resource):
        if not app_pagination:
            return {"data": [], "total": 0, "page": 1, "limit": 20, "has_more": False}

-        if FeatureService.get_system_features().webapp_auth.enabled:
-            app_ids = [str(app.id) for app in app_pagination.items]
-            res = EnterpriseService.WebAppAuth.batch_get_app_access_mode_by_id(app_ids=app_ids)
-            if len(res) != len(app_ids):
-                raise BadRequest("Invalid app id in webapp auth")
-
-            for app in app_pagination.items:
-                if str(app.id) in res:
-                    app.access_mode = res[str(app.id)].access_mode
-
-        return marshal(app_pagination, app_pagination_fields), 200
+        return marshal(app_pagination, app_pagination_fields)

    @setup_required
    @login_required
@@ -119,10 +111,6 @@ class AppApi(Resource):

        app_model = app_service.get_app(app_model)

-        if FeatureService.get_system_features().webapp_auth.enabled:
-            app_setting = EnterpriseService.WebAppAuth.get_app_access_mode_by_id(app_id=str(app_model.id))
-            app_model.access_mode = app_setting.access_mode
-
        return app_model

    @setup_required
@@ -6,13 +6,9 @@ from flask_restful import Resource, reqparse  # type: ignore

 from constants.languages import languages
 from controllers.console import api
-from controllers.console.auth.error import (EmailCodeError, InvalidEmailError,
-                                            InvalidTokenError,
-                                            PasswordMismatchError)
-from controllers.console.error import (AccountInFreezeError, AccountNotFound,
-                                       EmailSendIpLimitError)
-from controllers.console.wraps import (email_password_login_enabled,
-                                       setup_required)
+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
 from extensions.ext_database import db
 from libs.helper import email, extract_remote_ip
@@ -26,7 +22,6 @@ from services.feature_service import FeatureService

 class ForgotPasswordSendEmailApi(Resource):
    @setup_required
-    @email_password_login_enabled
    def post(self):
        parser = reqparse.RequestParser()
        parser.add_argument("email", type=email, required=True, location="json")
@@ -58,7 +53,6 @@ class ForgotPasswordSendEmailApi(Resource):

 class ForgotPasswordCheckApi(Resource):
    @setup_required
-    @email_password_login_enabled
    def post(self):
        parser = reqparse.RequestParser()
        parser.add_argument("email", type=str, required=True, location="json")
@@ -78,20 +72,11 @@ class ForgotPasswordCheckApi(Resource):
        if args["code"] != token_data.get("code"):
            raise EmailCodeError()

-        # Verified, revoke the first token
-        AccountService.revoke_reset_password_token(args["token"])
-
-        # Refresh token data by generating a new token
-        _, new_token = AccountService.generate_reset_password_token(
-            user_email, code=args["code"], additional_data={"phase": "reset"}
-        )
-
-        return {"is_valid": True, "email": token_data.get("email"), "token": new_token}
+        return {"is_valid": True, "email": token_data.get("email")}


 class ForgotPasswordResetApi(Resource):
    @setup_required
-    @email_password_login_enabled
    def post(self):
        parser = reqparse.RequestParser()
        parser.add_argument("token", type=str, required=True, nullable=False, location="json")
@@ -110,9 +95,6 @@ class ForgotPasswordResetApi(Resource):

        if reset_data is None:
            raise InvalidTokenError()
-        # Must use token in reset phase
-        if reset_data.get("phase", "") != "reset":
-            raise InvalidTokenError()

        AccountService.revoke_reset_password_token(token)

@@ -22,7 +22,7 @@ from controllers.console.error import (
    EmailSendIpLimitError,
    NotAllowedCreateWorkspace,
 )
-from controllers.console.wraps import email_password_login_enabled, setup_required
+from controllers.console.wraps import setup_required
 from events.tenant_event import tenant_was_created
 from libs.helper import email, extract_remote_ip
 from libs.password import valid_password
@@ -38,7 +38,6 @@ class LoginApi(Resource):
    """Resource for user login."""

    @setup_required
-    @email_password_login_enabled
    def post(self):
        """Authenticate user and login."""
        parser = reqparse.RequestParser()
@@ -111,7 +110,6 @@ class LogoutApi(Resource):

 class ResetPasswordSendEmailApi(Resource):
    @setup_required
-    @email_password_login_enabled
    def post(self):
        parser = reqparse.RequestParser()
        parser.add_argument("email", type=email, required=True, location="json")
@@ -620,6 +620,7 @@ class DatasetRetrievalSettingApi(Resource):
        match vector_type:
            case (
                VectorType.RELYT
+                | VectorType.PGVECTOR
                | VectorType.TIDB_VECTOR
                | VectorType.CHROMA
                | VectorType.TENCENT
@@ -23,9 +23,3 @@ class AppSuggestedQuestionsAfterAnswerDisabledError(BaseHTTPException):
    error_code = "app_suggested_questions_after_answer_disabled"
    description = "Function Suggested questions after answer disabled."
    code = 403
-
-
-class AppAccessDeniedError(BaseHTTPException):
-    error_code = "access_denied"
-    description = "App access denied."
-    code = 403
@@ -1,26 +1,20 @@
-import logging
 from datetime import UTC, datetime
 from typing import Any

 from flask import request
 from flask_login import current_user  # type: ignore
-from flask_restful import (Resource, inputs, marshal_with,  # type: ignore
-                           reqparse)
+from flask_restful import Resource, inputs, marshal_with, reqparse  # type: ignore
 from sqlalchemy import and_
 from werkzeug.exceptions import BadRequest, Forbidden, NotFound

 from controllers.console import api
 from controllers.console.explore.wraps import InstalledAppResource
-from controllers.console.wraps import (account_initialization_required,
-                                       cloud_edition_billing_resource_check)
+from controllers.console.wraps import account_initialization_required, cloud_edition_billing_resource_check
 from extensions.ext_database import db
 from fields.installed_app_fields import installed_app_list_fields
 from libs.login import login_required
 from models import App, InstalledApp, RecommendedApp
 from services.account_service import TenantService
-from services.app_service import AppService
-from services.enterprise.enterprise_service import EnterpriseService
-from services.feature_service import FeatureService


 class InstalledAppsListApi(Resource):
@@ -54,23 +48,6 @@ class InstalledAppsListApi(Resource):
            for installed_app in installed_apps
            if installed_app.app is not None
        ]
-
-        # filter out apps that user doesn't have access to
-        if FeatureService.get_system_features().webapp_auth.enabled:
-            user_id = current_user.id
-            res = []
-            for installed_app in installed_app_list:
-                app_code = AppService.get_app_code_by_id(str(installed_app["app"].id))
-                if EnterpriseService.WebAppAuth.is_user_allowed_to_access_webapp(
-                    user_id=user_id,
-                    app_code=app_code,
-                ):
-                    res.append(installed_app)
-            installed_app_list = res
-            logging.info(
-                f"installed_app_list: {installed_app_list}, user_id: {user_id}"
-            )
-
        installed_app_list.sort(
            key=lambda app: (
                -app["is_pinned"],
@@ -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.")
@@ -4,14 +4,10 @@ from flask_login import current_user  # type: ignore
 from flask_restful import Resource  # type: ignore
 from werkzeug.exceptions import NotFound

-from controllers.console.explore.error import AppAccessDeniedError
 from controllers.console.wraps import account_initialization_required
 from extensions.ext_database import db
 from libs.login import login_required
 from models import InstalledApp
-from services.app_service import AppService
-from services.enterprise.enterprise_service import EnterpriseService
-from services.feature_service import FeatureService


 def installed_app_required(view=None):
@@ -52,30 +48,6 @@ def installed_app_required(view=None):
    return decorator


-def user_allowed_to_access_app(view=None):
-    def decorator(view):
-        @wraps(view)
-        def decorated(installed_app: InstalledApp, *args, **kwargs):
-            feature = FeatureService.get_system_features()
-            if feature.webapp_auth.enabled:
-                app_id = installed_app.app_id
-                app_code = AppService.get_app_code_by_id(app_id)
-                res = EnterpriseService.WebAppAuth.is_user_allowed_to_access_webapp(
-                    user_id=str(current_user.id),
-                    app_code=app_code,
-                )
-                if not res:
-                    raise AppAccessDeniedError()
-
-            return view(installed_app, *args, **kwargs)
-
-        return decorated
-    if view:
-        return decorator(view)
-    return decorator
-
-
 class InstalledAppResource(Resource):
    # must be reversed if there are multiple decorators
-
-    method_decorators = [user_allowed_to_access_app, installed_app_required, account_initialization_required, login_required]
+    method_decorators = [installed_app_required, account_initialization_required, login_required]
@@ -11,8 +11,7 @@ from models.model import DifySetup
 from services.feature_service import FeatureService, LicenseStatus
 from services.operation_service import OperationService

-from .error import (NotInitValidateError, NotSetupError,
-                    UnauthorizedAndForceLogout)
+from .error import NotInitValidateError, NotSetupError, UnauthorizedAndForceLogout


 def account_initialization_required(view):
@@ -40,17 +39,6 @@ def only_edition_cloud(view):
    return decorated


-def only_enterprise_edition(view):
-    @wraps(view)
-    def decorated(*args, **kwargs):
-        if not dify_config.ENTERPRISE_ENABLED:
-            abort(404)
-
-        return view(*args, **kwargs)
-
-    return decorated
-
-
 def only_edition_self_hosted(view):
    @wraps(view)
    def decorated(*args, **kwargs):
@@ -166,16 +154,3 @@ def enterprise_license_required(view):
        return view(*args, **kwargs)

    return decorated
-
-
-def email_password_login_enabled(view):
-    @wraps(view)
-    def decorated(*args, **kwargs):
-        features = FeatureService.get_system_features()
-        if features.enable_email_password_login:
-            return view(*args, **kwargs)
-
-        # otherwise, return 403
-        abort(403)
-
-    return decorated
@@ -5,5 +5,4 @@ from libs.external_api import ExternalApi
 bp = Blueprint("inner_api", __name__, url_prefix="/inner/api")
 api = ExternalApi(bp)

-from . import mail
 from .workspace import workspace
@@ -1,27 +0,0 @@
-from flask_restful import (
-    Resource,  # type: ignore
-    reqparse,
-)
-
-from controllers.console.wraps import setup_required
-from controllers.inner_api import api
-from controllers.inner_api.wraps import inner_api_only
-from services.enterprise.mail_service import DifyMail, EnterpriseMailService
-
-
-class EnterpriseMail(Resource):
-    @setup_required
-    @inner_api_only
-    def post(self):
-        parser = reqparse.RequestParser()
-        parser.add_argument("to", type=str, action="append", required=True)
-        parser.add_argument("subject", type=str, required=True)
-        parser.add_argument("body", type=str, required=True)
-        parser.add_argument("substitutions", type=dict, required=False)
-        args = parser.parse_args()
-
-        EnterpriseMailService.send_mail(DifyMail(**args))
-        return {"message": "success"}, 200
-
-
-api.add_resource(EnterpriseMail, "/enterprise/mail")
@@ -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
-    @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)
@@ -1,16 +1,12 @@
-
-from flask import request
-from flask_restful import Resource, marshal_with, reqparse  # type: ignore
+from flask_restful import marshal_with  # type: ignore

 from controllers.common import fields
 from controllers.common import helpers as controller_helpers
 from controllers.web import api
 from controllers.web.error import AppUnavailableError
 from controllers.web.wraps import WebApiResource
-from libs.passport import PassportService
 from models.model import App, AppMode
 from services.app_service import AppService
-from services.enterprise.enterprise_service import EnterpriseService


 class AppParameterApi(WebApiResource):
@@ -46,51 +42,5 @@ class AppMeta(WebApiResource):
        return AppService().get_app_meta(app_model)


-class AppAccessMode(Resource):
-    def get(self):
-        parser = reqparse.RequestParser()
-        parser.add_argument("appId", type=str, required=True, location="args")
-        args = parser.parse_args()
-
-        app_id = args["appId"]
-        res = EnterpriseService.WebAppAuth.get_app_access_mode_by_id(app_id)
-
-        return {"accessMode": res.access_mode}
-
-
-class AppWebAuthPermission(Resource):
-    def get(self):
-        user_id = "visitor"
-        try:
-            auth_header = request.headers.get("Authorization")
-            if auth_header is None:
-                raise
-            if " " not in auth_header:
-                raise
-
-            auth_scheme, tk = auth_header.split(None, 1)
-            auth_scheme = auth_scheme.lower()
-            if auth_scheme != "bearer":
-                raise
-
-            decoded = PassportService().verify(tk)
-            user_id = decoded.get("user_id", "visitor")
-        except Exception as e:
-            pass
-
-        parser = reqparse.RequestParser()
-        parser.add_argument("appId", type=str, required=True, location="args")
-        args = parser.parse_args()
-
-        app_id = args["appId"]
-        app_code = AppService.get_app_code_by_id(app_id)
-
-        res = EnterpriseService.WebAppAuth.is_user_allowed_to_access_webapp(str(user_id), app_code)
-        return {"result": res}
-
-
 api.add_resource(AppParameterApi, "/parameters")
 api.add_resource(AppMeta, "/meta")
-# webapp auth apis
-api.add_resource(AppAccessMode, "/webapp/access-mode")
-api.add_resource(AppWebAuthPermission, "/webapp/permission")
@@ -121,15 +121,9 @@ class UnsupportedFileTypeError(BaseHTTPException):
    code = 415


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


@@ -1,121 +0,0 @@
-from flask import request
-from flask_restful import Resource, reqparse
-from jwt import InvalidTokenError  # type: ignore
-from web import api
-from werkzeug.exceptions import BadRequest
-
-import services
-from controllers.console.auth.error import EmailCodeError, EmailOrPasswordMismatchError, InvalidEmailError
-from controllers.console.error import AccountBannedError, AccountNotFound
-from controllers.console.wraps import setup_required
-from libs.helper import email
-from libs.password import valid_password
-from services.account_service import AccountService
-from services.webapp_auth_service import WebAppAuthService
-
-
-class LoginApi(Resource):
-    """Resource for web app email/password login."""
-
-    def post(self):
-        """Authenticate user and login."""
-        parser = reqparse.RequestParser()
-        parser.add_argument("email", type=email, required=True, location="json")
-        parser.add_argument("password", type=valid_password, required=True, location="json")
-        args = parser.parse_args()
-
-        app_code = request.headers.get("X-App-Code")
-        if app_code is None:
-            raise BadRequest("X-App-Code header is missing.")
-
-        try:
-            account = WebAppAuthService.authenticate(args["email"], args["password"])
-        except services.errors.account.AccountLoginError:
-            raise AccountBannedError()
-        except services.errors.account.AccountPasswordError:
-            raise EmailOrPasswordMismatchError()
-        except services.errors.account.AccountNotFoundError:
-            raise AccountNotFound()
-
-        WebAppAuthService._validate_user_accessibility(account=account, app_code=app_code)
-
-        end_user = WebAppAuthService.create_end_user(email=args["email"], app_code=app_code)
-
-        token = WebAppAuthService.login(account=account, app_code=app_code, end_user_id=end_user.id)
-        return {"result": "success", "token": token}
-
-
-# class LogoutApi(Resource):
-#     @setup_required
-#     def get(self):
-#         account = cast(Account, flask_login.current_user)
-#         if isinstance(account, flask_login.AnonymousUserMixin):
-#             return {"result": "success"}
-#         flask_login.logout_user()
-#         return {"result": "success"}
-
-
-class EmailCodeLoginSendEmailApi(Resource):
-    @setup_required
-    def post(self):
-        parser = reqparse.RequestParser()
-        parser.add_argument("email", type=email, required=True, location="json")
-        parser.add_argument("language", type=str, required=False, location="json")
-        args = parser.parse_args()
-
-        if args["language"] is not None and args["language"] == "zh-Hans":
-            language = "zh-Hans"
-        else:
-            language = "en-US"
-
-        account = WebAppAuthService.get_user_through_email(args["email"])
-        if account is None:
-            raise AccountNotFound()
-        else:
-            token = WebAppAuthService.send_email_code_login_email(account=account, language=language)
-
-        return {"result": "success", "data": token}
-
-
-class EmailCodeLoginApi(Resource):
-    @setup_required
-    def post(self):
-        parser = reqparse.RequestParser()
-        parser.add_argument("email", type=str, required=True, location="json")
-        parser.add_argument("code", type=str, required=True, location="json")
-        parser.add_argument("token", type=str, required=True, location="json")
-        args = parser.parse_args()
-
-        user_email = args["email"]
-        app_code = request.headers.get("X-App-Code")
-        if app_code is None:
-            raise BadRequest("X-App-Code header is missing.")
-
-        token_data = WebAppAuthService.get_email_code_login_data(args["token"])
-        if token_data is None:
-            raise InvalidTokenError()
-
-        if token_data["email"] != args["email"]:
-            raise InvalidEmailError()
-
-        if token_data["code"] != args["code"]:
-            raise EmailCodeError()
-
-        WebAppAuthService.revoke_email_code_login_token(args["token"])
-        account = WebAppAuthService.get_user_through_email(user_email)
-        if not account:
-            raise AccountNotFound()
-
-        WebAppAuthService._validate_user_accessibility(account=account, app_code=app_code)
-
-        end_user = WebAppAuthService.create_end_user(email=user_email, app_code=app_code)
-
-        token = WebAppAuthService.login(account=account, app_code=app_code, end_user_id=end_user.id)
-        AccountService.reset_login_error_rate_limit(args["email"])
-        return {"result": "success", "token": token}
-
-
-api.add_resource(LoginApi, "/login")
-# api.add_resource(LogoutApi, "/logout")
-api.add_resource(EmailCodeLoginSendEmailApi, "/email-code-login")
-api.add_resource(EmailCodeLoginApi, "/email-code-login/validity")
@@ -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.")
@@ -5,7 +5,7 @@ from flask_restful import Resource  # type: ignore
 from werkzeug.exceptions import NotFound, Unauthorized

 from controllers.web import api
-from controllers.web.error import WebAppAuthRequiredError
+from controllers.web.error import WebSSOAuthRequiredError
 from extensions.ext_database import db
 from libs.passport import PassportService
 from models.model import App, EndUser, Site
@@ -22,10 +22,10 @@ class PassportResource(Resource):
        if app_code is None:
            raise Unauthorized("X-App-Code header is missing.")

-        if system_features.webapp_auth.enabled:
-            app_settings = EnterpriseService.WebAppAuth.get_app_access_mode_by_code(app_code=app_code)
-            if not app_settings or not app_settings.access_mode == "public":
-                raise WebAppAuthRequiredError()
+        if system_features.sso_enforced_for_web:
+            app_web_sso_enabled = EnterpriseService.get_app_web_sso_enabled(app_code).get("enabled", False)
+            if app_web_sso_enabled:
+                raise WebSSOAuthRequiredError()

        # get site from db and check if it is normal
        site = db.session.query(Site).filter(Site.code == app_code, Site.status == "normal").first()
@@ -4,7 +4,7 @@ from flask import request
 from flask_restful import Resource  # type: ignore
 from werkzeug.exceptions import BadRequest, NotFound, Unauthorized

-from controllers.web.error import WebAppAuthAccessDeniedError, WebAppAuthRequiredError
+from controllers.web.error import WebSSOAuthRequiredError
 from extensions.ext_database import db
 from libs.passport import PassportService
 from models.model import App, EndUser, Site
@@ -57,53 +57,35 @@ def decode_jwt_token():
        if not end_user:
            raise NotFound()

-        # for enterprise webapp auth
-        app_web_auth_enabled = False
-        if system_features.webapp_auth.enabled:
-            app_web_auth_enabled = (
-                EnterpriseService.WebAppAuth.get_app_access_mode_by_code(app_code=app_code).access_mode != "public"
-            )
-
-        _validate_webapp_token(decoded, app_web_auth_enabled, system_features.webapp_auth.enabled)
-        _validate_user_accessibility(decoded, app_code, app_web_auth_enabled, system_features.webapp_auth.enabled)
+        _validate_web_sso_token(decoded, system_features, app_code)

        return app_model, end_user
    except Unauthorized as e:
-        if system_features.webapp_auth.enabled:
-            app_web_auth_enabled = (
-                EnterpriseService.WebAppAuth.get_app_access_mode_by_code(app_code=app_code).access_mode != "public"
-            )
-            if app_web_auth_enabled:
-                raise WebAppAuthRequiredError()
+        if system_features.sso_enforced_for_web:
+            app_web_sso_enabled = EnterpriseService.get_app_web_sso_enabled(app_code).get("enabled", False)
+            if app_web_sso_enabled:
+                raise WebSSOAuthRequiredError()

        raise Unauthorized(e.description)


-def _validate_webapp_token(decoded, app_web_auth_enabled: bool, system_webapp_auth_enabled: bool):
-    # Check if authentication is enforced for web app, and if the token source is not webapp,
-    # raise an error and redirect to login
-    if system_webapp_auth_enabled and app_web_auth_enabled:
-        source = decoded.get("token_source")
-        if not source or source != "webapp":
-            raise WebAppAuthRequiredError()
+def _validate_web_sso_token(decoded, system_features, app_code):
+    app_web_sso_enabled = False

-    # Check if authentication is not enforced for web, and if the token source is webapp,
+    # Check if SSO is enforced for web, and if the token source is not SSO, raise an error and redirect to SSO login
+    if system_features.sso_enforced_for_web:
+        app_web_sso_enabled = EnterpriseService.get_app_web_sso_enabled(app_code).get("enabled", False)
+        if app_web_sso_enabled:
+            source = decoded.get("token_source")
+            if not source or source != "sso":
+                raise WebSSOAuthRequiredError()
+
+    # Check if SSO is not enforced for web, and if the token source is SSO,
    # raise an error and redirect to normal passport login
-    if not system_webapp_auth_enabled or not app_web_auth_enabled:
+    if not system_features.sso_enforced_for_web or not app_web_sso_enabled:
        source = decoded.get("token_source")
-        if source and source == "webapp":
-            raise Unauthorized("webapp token expired.")
-
-
-def _validate_user_accessibility(decoded, app_code, app_web_auth_enabled: bool, system_webapp_auth_enabled: bool):
-    if system_webapp_auth_enabled and app_web_auth_enabled:
-        # Check if the user is allowed to access the web app
-        user_id = decoded.get("user_id")
-        if not user_id:
-            raise WebAppAuthRequiredError()
-
-        if not EnterpriseService.WebAppAuth.is_user_allowed_to_access_webapp(user_id, app_code=app_code):
-            raise WebAppAuthAccessDeniedError()
+        if source and source == "sso":
+            raise Unauthorized("sso token expired.")


 class WebApiResource(Resource):
@@ -202,7 +202,7 @@ 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:
+        if not model_schema or not model_schema.features:
            raise ValueError("Model schema not found")

        if {ModelFeature.MULTI_TOOL_CALL, ModelFeature.TOOL_CALL}.intersection(model_schema.features or []):
@@ -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]

@@ -42,11 +51,7 @@ 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:
@@ -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.
    """
@@ -221,12 +221,13 @@ class AIModel(ABC):
        :param credentials: model credentials
        :return: model schema
        """
-        # Try to get model schema from predefined models
-        for predefined_model in self.predefined_models():
-            if model == predefined_model.model:
-                return predefined_model
+        # get predefined models (predefined_models)
+        models = self.predefined_models()
+
+        model_map = {model.model: model for model in models}
+        if model in model_map:
+            return model_map[model]

-        # Try to get model schema from credentials
        if credentials:
            model_schema = self.get_customizable_model_schema_from_credentials(model, credentials)
            if model_schema:
@@ -30,11 +30,6 @@ from core.model_runtime.model_providers.__base.ai_model import AIModel

 logger = logging.getLogger(__name__)

-HTML_THINKING_TAG = (
-    '<details style="color:gray;background-color: #f8f8f8;padding: 8px;border-radius: 4px;" open> '
-    "<summary> Thinking... </summary>"
-)
-

 class LargeLanguageModel(AIModel):
    """
@@ -405,40 +400,6 @@ if you are not sure about the structure.
                    ),
                )

-    def _wrap_thinking_by_reasoning_content(self, delta: dict, is_reasoning: bool) -> tuple[str, bool]:
-        """
-        If the reasoning response is from delta.get("reasoning_content"), we wrap
-        it with HTML details tag.
-
-        :param delta: delta dictionary from LLM streaming response
-        :param is_reasoning: is reasoning
-        :return: tuple of (processed_content, is_reasoning)
-        """
-
-        content = delta.get("content") or ""
-        reasoning_content = delta.get("reasoning_content")
-
-        if reasoning_content:
-            if not is_reasoning:
-                content = HTML_THINKING_TAG + reasoning_content
-                is_reasoning = True
-            else:
-                content = reasoning_content
-        elif is_reasoning:
-            content = "</details>" + content
-            is_reasoning = False
-        return content, is_reasoning
-
-    def _wrap_thinking_by_tag(self, content: str) -> str:
-        """
-        if the reasoning response is a <think>...</think> block from delta.get("content"),
-        we replace <think> to <detail>.
-
-        :param content: delta.get("content")
-        :return: processed_content
-        """
-        return content.replace("<think>", HTML_THINKING_TAG).replace("</think>", "</details>")
-
    def _invoke_result_generator(
        self,
        model: str,
@@ -1,5 +1,4 @@
 - openai
- deepseek
 - anthropic
 - azure_openai
 - google
@@ -33,6 +32,7 @@
 - localai
 - volcengine_maas
 - openai_api_compatible
+- deepseek
 - hunyuan
 - siliconflow
 - perfxcloud
@@ -51,40 +51,6 @@ model_credential_schema:
      show_on:
        - variable: __model_type
          value: llm
-    - variable: mode
-      show_on:
-        - variable: __model_type
-          value: llm
-      label:
-        en_US: Completion mode
-      type: select
-      required: false
-      default: chat
-      placeholder:
-        zh_Hans: 选择对话类型
-        en_US: Select completion mode
-      options:
-        - value: completion
-          label:
-            en_US: Completion
-            zh_Hans: 补全
-        - value: chat
-          label:
-            en_US: Chat
-            zh_Hans: 对话
-    - variable: context_size
-      label:
-        zh_Hans: 模型上下文长度
-        en_US: Model context size
-      required: true
-      show_on:
-        - variable: __model_type
-          value: llm
-      type: text-input
-      default: "4096"
-      placeholder:
-        zh_Hans: 在此输入您的模型上下文长度
-        en_US: Enter your Model context size
    - variable: jwt_token
      required: true
      label:
@@ -1,9 +1,9 @@
 import logging
-from collections.abc import Generator, Sequence
+from collections.abc import Generator
 from typing import Any, Optional, Union

 from azure.ai.inference import ChatCompletionsClient
-from azure.ai.inference.models import StreamingChatCompletionsUpdate, SystemMessage, UserMessage
+from azure.ai.inference.models import StreamingChatCompletionsUpdate
 from azure.core.credentials import AzureKeyCredential
 from azure.core.exceptions import (
    ClientAuthenticationError,
@@ -20,7 +20,7 @@ from azure.core.exceptions import (
 )

 from core.model_runtime.callbacks.base_callback import Callback
-from core.model_runtime.entities.llm_entities import LLMMode, LLMResult, LLMResultChunk, LLMResultChunkDelta, LLMUsage
+from core.model_runtime.entities.llm_entities import LLMResult, LLMResultChunk, LLMResultChunkDelta, LLMUsage
 from core.model_runtime.entities.message_entities import (
    AssistantPromptMessage,
    PromptMessage,
@@ -30,7 +30,6 @@ from core.model_runtime.entities.model_entities import (
    AIModelEntity,
    FetchFrom,
    I18nObject,
-    ModelPropertyKey,
    ModelType,
    ParameterRule,
    ParameterType,
@@ -61,10 +60,10 @@ class AzureAIStudioLargeLanguageModel(LargeLanguageModel):
        self,
        model: str,
        credentials: dict,
-        prompt_messages: Sequence[PromptMessage],
+        prompt_messages: list[PromptMessage],
        model_parameters: dict,
-        tools: Optional[Sequence[PromptMessageTool]] = None,
-        stop: Optional[Sequence[str]] = None,
+        tools: Optional[list[PromptMessageTool]] = None,
+        stop: Optional[list[str]] = None,
        stream: bool = True,
        user: Optional[str] = None,
    ) -> Union[LLMResult, Generator]:
@@ -83,8 +82,8 @@ class AzureAIStudioLargeLanguageModel(LargeLanguageModel):
        """

        if not self.client:
-            endpoint = str(credentials.get("endpoint"))
-            api_key = str(credentials.get("api_key"))
+            endpoint = credentials.get("endpoint")
+            api_key = credentials.get("api_key")
            self.client = ChatCompletionsClient(endpoint=endpoint, credential=AzureKeyCredential(api_key))

        messages = [{"role": msg.role.value, "content": msg.content} for msg in prompt_messages]
@@ -95,7 +94,6 @@ class AzureAIStudioLargeLanguageModel(LargeLanguageModel):
            "temperature": model_parameters.get("temperature", 0),
            "top_p": model_parameters.get("top_p", 1),
            "stream": stream,
-            "model": model,
        }

        if stop:
@@ -257,16 +255,10 @@ class AzureAIStudioLargeLanguageModel(LargeLanguageModel):
        :return:
        """
        try:
-            endpoint = str(credentials.get("endpoint"))
-            api_key = str(credentials.get("api_key"))
+            endpoint = credentials.get("endpoint")
+            api_key = credentials.get("api_key")
            client = ChatCompletionsClient(endpoint=endpoint, credential=AzureKeyCredential(api_key))
-            client.complete(
-                messages=[
-                    SystemMessage(content="I say 'ping', you say 'pong'"),
-                    UserMessage(content="ping"),
-                ],
-                model=model,
-            )
+            client.get_model_info()
        except Exception as ex:
            raise CredentialsValidateFailedError(str(ex))

@@ -335,10 +327,7 @@ class AzureAIStudioLargeLanguageModel(LargeLanguageModel):
            fetch_from=FetchFrom.CUSTOMIZABLE_MODEL,
            model_type=ModelType.LLM,
            features=[],
-            model_properties={
-                ModelPropertyKey.CONTEXT_SIZE: int(credentials.get("context_size", "4096")),
-                ModelPropertyKey.MODE: credentials.get("mode", LLMMode.CHAT),
-            },
+            model_properties={},
            parameter_rules=rules,
        )

@@ -53,9 +53,6 @@ model_credential_schema:
      type: select
      required: true
      options:
-        - label:
-            en_US: 2024-12-01-preview
-          value: 2024-12-01-preview
        - label:
            en_US: 2024-10-01-preview
          value: 2024-10-01-preview
@@ -138,18 +135,6 @@ model_credential_schema:
          show_on:
            - variable: __model_type
              value: llm
-        - label:
-            en_US: o3-mini
-          value: o3-mini
-          show_on:
-            - variable: __model_type
-              value: llm
-        - label:
-            en_US: o3-mini-2025-01-31
-          value: o3-mini-2025-01-31
-          show_on:
-            - variable: __model_type
-              value: llm
        - label:
            en_US: o1-preview
          value: o1-preview
@@ -123,15 +123,6 @@ provider_credential_schema:
            en_US: AWS GovCloud (US-West)
            zh_Hans: AWS GovCloud (US-West)
            ja_JP: AWS GovCloud (米国西部)
-    - variable: bedrock_endpoint_url
-      label:
-        zh_Hans: Bedrock Endpoint URL
-        en_US: Bedrock Endpoint URL
-      type: text-input
-      required: false
-      placeholder:
-        zh_Hans: 在此输入您的 Bedrock Endpoint URL, 如：https://123456.cloudfront.net
-        en_US: Enter your Bedrock Endpoint URL, e.g. https://123456.cloudfront.net
    - variable: model_for_validation
      required: false
      label:
@@ -13,7 +13,6 @@ def get_bedrock_client(service_name: str, credentials: Mapping[str, str]):
    client_config = Config(region_name=region_name)
    aws_access_key_id = credentials.get("aws_access_key_id")
    aws_secret_access_key = credentials.get("aws_secret_access_key")
-    bedrock_endpoint_url = credentials.get("bedrock_endpoint_url")

    if aws_access_key_id and aws_secret_access_key:
        # use aksk to call bedrock
@@ -22,7 +21,6 @@ def get_bedrock_client(service_name: str, credentials: Mapping[str, str]):
            config=client_config,
            aws_access_key_id=aws_access_key_id,
            aws_secret_access_key=aws_secret_access_key,
-            **({"endpoint_url": bedrock_endpoint_url} if bedrock_endpoint_url else {}),
        )
    else:
        # use iam without aksk to call
@@ -677,17 +677,16 @@ class CohereLargeLanguageModel(LargeLanguageModel):

        :return: model schema
        """
-        mode = credentials.get("mode")
-        base_model_schema = None
-        for predefined_model in self.predefined_models():
-            if (
-                mode == "chat" and predefined_model.model == "command-light-chat"
-            ) or predefined_model.model == "command-light":
-                base_model_schema = predefined_model
-                break
+        # get model schema
+        models = self.predefined_models()
+        model_map = {model.model: model for model in models}

-        if not base_model_schema:
-            raise ValueError("Model not found")
+        mode = credentials.get("mode")
+
+        if mode == "chat":
+            base_model_schema = model_map["command-light-chat"]
+        else:
+            base_model_schema = model_map["command-light"]

        base_model_schema = cast(AIModelEntity, base_model_schema)

@@ -1,10 +1,13 @@
+import json
 from collections.abc import Generator
 from typing import Optional, Union

+import requests
 from yarl import URL

-from core.model_runtime.entities.llm_entities import LLMMode, LLMResult
+from core.model_runtime.entities.llm_entities import LLMMode, LLMResult, LLMResultChunk, LLMResultChunkDelta
 from core.model_runtime.entities.message_entities import (
+    AssistantPromptMessage,
    PromptMessage,
    PromptMessageTool,
 )
@@ -36,3 +39,208 @@ class DeepseekLargeLanguageModel(OAIAPICompatLargeLanguageModel):
        credentials["mode"] = LLMMode.CHAT.value
        credentials["function_calling_type"] = "tool_call"
        credentials["stream_function_calling"] = "support"
+
+    def _handle_generate_stream_response(
+        self, model: str, credentials: dict, response: requests.Response, prompt_messages: list[PromptMessage]
+    ) -> Generator:
+        """
+        Handle llm stream response
+
+        :param model: model name
+        :param credentials: model credentials
+        :param response: streamed response
+        :param prompt_messages: prompt messages
+        :return: llm response chunk generator
+        """
+        full_assistant_content = ""
+        chunk_index = 0
+        is_reasoning_started = False  # Add flag to track reasoning state
+
+        def create_final_llm_result_chunk(
+            id: Optional[str], index: int, message: AssistantPromptMessage, finish_reason: str, usage: dict
+        ) -> LLMResultChunk:
+            # calculate num tokens
+            prompt_tokens = usage and usage.get("prompt_tokens")
+            if prompt_tokens is None:
+                prompt_tokens = self._num_tokens_from_string(model, prompt_messages[0].content)
+            completion_tokens = usage and usage.get("completion_tokens")
+            if completion_tokens is None:
+                completion_tokens = self._num_tokens_from_string(model, full_assistant_content)
+
+            # transform usage
+            usage = self._calc_response_usage(model, credentials, prompt_tokens, completion_tokens)
+
+            return LLMResultChunk(
+                id=id,
+                model=model,
+                prompt_messages=prompt_messages,
+                delta=LLMResultChunkDelta(index=index, message=message, finish_reason=finish_reason, usage=usage),
+            )
+
+        # delimiter for stream response, need unicode_escape
+        import codecs
+
+        delimiter = credentials.get("stream_mode_delimiter", "\n\n")
+        delimiter = codecs.decode(delimiter, "unicode_escape")
+
+        tools_calls: list[AssistantPromptMessage.ToolCall] = []
+
+        def increase_tool_call(new_tool_calls: list[AssistantPromptMessage.ToolCall]):
+            def get_tool_call(tool_call_id: str):
+                if not tool_call_id:
+                    return tools_calls[-1]
+
+                tool_call = next((tool_call for tool_call in tools_calls if tool_call.id == tool_call_id), None)
+                if tool_call is None:
+                    tool_call = AssistantPromptMessage.ToolCall(
+                        id=tool_call_id,
+                        type="function",
+                        function=AssistantPromptMessage.ToolCall.ToolCallFunction(name="", arguments=""),
+                    )
+                    tools_calls.append(tool_call)
+
+                return tool_call
+
+            for new_tool_call in new_tool_calls:
+                # get tool call
+                tool_call = get_tool_call(new_tool_call.function.name)
+                # update tool call
+                if new_tool_call.id:
+                    tool_call.id = new_tool_call.id
+                if new_tool_call.type:
+                    tool_call.type = new_tool_call.type
+                if new_tool_call.function.name:
+                    tool_call.function.name = new_tool_call.function.name
+                if new_tool_call.function.arguments:
+                    tool_call.function.arguments += new_tool_call.function.arguments
+
+        finish_reason = None  # The default value of finish_reason is None
+        message_id, usage = None, None
+        for chunk in response.iter_lines(decode_unicode=True, delimiter=delimiter):
+            chunk = chunk.strip()
+            if chunk:
+                # ignore sse comments
+                if chunk.startswith(":"):
+                    continue
+                decoded_chunk = chunk.strip().removeprefix("data:").lstrip()
+                if decoded_chunk == "[DONE]":  # Some provider returns "data: [DONE]"
+                    continue
+
+                try:
+                    chunk_json: dict = json.loads(decoded_chunk)
+                # stream ended
+                except json.JSONDecodeError as e:
+                    yield create_final_llm_result_chunk(
+                        id=message_id,
+                        index=chunk_index + 1,
+                        message=AssistantPromptMessage(content=""),
+                        finish_reason="Non-JSON encountered.",
+                        usage=usage,
+                    )
+                    break
+                # handle the error here. for issue #11629
+                if chunk_json.get("error") and chunk_json.get("choices") is None:
+                    raise ValueError(chunk_json.get("error"))
+
+                if chunk_json:
+                    if u := chunk_json.get("usage"):
+                        usage = u
+                if not chunk_json or len(chunk_json["choices"]) == 0:
+                    continue
+
+                choice = chunk_json["choices"][0]
+                finish_reason = chunk_json["choices"][0].get("finish_reason")
+                message_id = chunk_json.get("id")
+                chunk_index += 1
+
+                if "delta" in choice:
+                    delta = choice["delta"]
+                    is_reasoning = delta.get("reasoning_content")
+                    delta_content = delta.get("content") or delta.get("reasoning_content")
+
+                    assistant_message_tool_calls = None
+
+                    if "tool_calls" in delta and credentials.get("function_calling_type", "no_call") == "tool_call":
+                        assistant_message_tool_calls = delta.get("tool_calls", None)
+                    elif (
+                        "function_call" in delta
+                        and credentials.get("function_calling_type", "no_call") == "function_call"
+                    ):
+                        assistant_message_tool_calls = [
+                            {"id": "tool_call_id", "type": "function", "function": delta.get("function_call", {})}
+                        ]
+
+                    # assistant_message_function_call = delta.delta.function_call
+
+                    # extract tool calls from response
+                    if assistant_message_tool_calls:
+                        tool_calls = self._extract_response_tool_calls(assistant_message_tool_calls)
+                        increase_tool_call(tool_calls)
+
+                    if delta_content is None or delta_content == "":
+                        continue
+
+                    # Add markdown quote markers for reasoning content
+                    if is_reasoning:
+                        if not is_reasoning_started:
+                            delta_content = "> 💭 " + delta_content
+                            is_reasoning_started = True
+                        elif "\n\n" in delta_content:
+                            delta_content = delta_content.replace("\n\n", "\n> ")
+                        elif "\n" in delta_content:
+                            delta_content = delta_content.replace("\n", "\n> ")
+                    elif is_reasoning_started:
+                        # If we were in reasoning mode but now getting regular content,
+                        # add \n\n to close the reasoning block
+                        delta_content = "\n\n" + delta_content
+                        is_reasoning_started = False
+
+                    # transform assistant message to prompt message
+                    assistant_prompt_message = AssistantPromptMessage(
+                        content=delta_content,
+                    )
+
+                    # reset tool calls
+                    tool_calls = []
+                    full_assistant_content += delta_content
+                elif "text" in choice:
+                    choice_text = choice.get("text", "")
+                    if choice_text == "":
+                        continue
+
+                    # transform assistant message to prompt message
+                    assistant_prompt_message = AssistantPromptMessage(content=choice_text)
+                    full_assistant_content += choice_text
+                else:
+                    continue
+
+                yield LLMResultChunk(
+                    id=message_id,
+                    model=model,
+                    prompt_messages=prompt_messages,
+                    delta=LLMResultChunkDelta(
+                        index=chunk_index,
+                        message=assistant_prompt_message,
+                    ),
+                )
+
+            chunk_index += 1
+
+        if tools_calls:
+            yield LLMResultChunk(
+                id=message_id,
+                model=model,
+                prompt_messages=prompt_messages,
+                delta=LLMResultChunkDelta(
+                    index=chunk_index,
+                    message=AssistantPromptMessage(tool_calls=tools_calls, content=""),
+                ),
+            )
+
+        yield create_final_llm_result_chunk(
+            id=message_id,
+            index=chunk_index,
+            message=AssistantPromptMessage(content=""),
+            finish_reason=finish_reason,
+            usage=usage,
+        )
@@ -1,6 +1,4 @@
- gemini-2.0-flash-001
 - gemini-2.0-flash-exp
- gemini-2.0-pro-exp-02-05
 - gemini-2.0-flash-thinking-exp-1219
 - gemini-2.0-flash-thinking-exp-01-21
 - gemini-1.5-pro
@@ -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-pro-exp-02-05
-label:
-  en_US: Gemini 2.0 pro exp 02-05
-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
@@ -1,4 +1,3 @@
- deepseek-r1-distill-llama-70b
 - llama-3.1-405b-reasoning
 - llama-3.3-70b-versatile
 - llama-3.1-70b-versatile
@@ -1,36 +0,0 @@
-model: deepseek-r1-distill-llama-70b
-label:
-  en_US: DeepSeek R1 Distill Llama 70b
-model_type: llm
-features:
-  - agent-thought
-model_properties:
-  mode: chat
-  context_size: 128000
-parameter_rules:
-  - name: temperature
-    use_template: temperature
-  - name: top_p
-    use_template: top_p
-  - name: max_tokens
-    use_template: max_tokens
-    default: 512
-    min: 1
-    max: 8192
-  - 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: '3.00'
-  output: '3.00'
-  unit: '0.000001'
-  currency: USD
@@ -1,7 +1,7 @@
 model: Sao10K/L3-8B-Stheno-v3.2
 label:
-  zh_Hans: L3 8B Stheno V3.2
-  en_US: L3 8B Stheno V3.2
+  zh_Hans: Sao10K/L3-8B-Stheno-v3.2
+  en_US: Sao10K/L3-8B-Stheno-v3.2
 model_type: llm
 features:
  - agent-thought
@@ -1,5 +1,4 @@
 # Deepseek Models
- deepseek/deepseek-r1
 - deepseek/deepseek_v3

 # LLaMA Models
@@ -1,7 +1,7 @@
 model: jondurbin/airoboros-l2-70b
 label:
-  zh_Hans: Airoboros L2 70B
-  en_US: Airoboros L2 70B
+  zh_Hans: jondurbin/airoboros-l2-70b
+  en_US: jondurbin/airoboros-l2-70b
 model_type: llm
 features:
  - agent-thought
@@ -1,41 +0,0 @@
-model: deepseek/deepseek-r1
-label:
-  zh_Hans: DeepSeek R1
-  en_US: DeepSeek R1
-model_type: llm
-features:
-  - agent-thought
-model_properties:
-  mode: chat
-  context_size: 64000
-parameter_rules:
-  - name: temperature
-    use_template: temperature
-    min: 0
-    max: 2
-    default: 1
-  - name: top_p
-    use_template: top_p
-    min: 0
-    max: 1
-    default: 1
-  - name: max_tokens
-    use_template: max_tokens
-    min: 1
-    max: 2048
-    default: 512
-  - name: frequency_penalty
-    use_template: frequency_penalty
-    min: -2
-    max: 2
-    default: 0
-  - name: presence_penalty
-    use_template: presence_penalty
-    min: -2
-    max: 2
-    default: 0
-pricing:
-  input: '0.04'
-  output: '0.04'
-  unit: '0.0001'
-  currency: USD
@@ -1,7 +1,7 @@
 model: deepseek/deepseek_v3
 label:
-  zh_Hans: DeepSeek V3
-  en_US: DeepSeek V3
+  zh_Hans: deepseek/deepseek_v3
+  en_US: deepseek/deepseek_v3
 model_type: llm
 features:
  - agent-thought
@@ -1,7 +1,7 @@
 model: cognitivecomputations/dolphin-mixtral-8x22b
 label:
-  zh_Hans: Dolphin Mixtral 8x22B
-  en_US: Dolphin Mixtral 8x22B
+  zh_Hans: cognitivecomputations/dolphin-mixtral-8x22b
+  en_US: cognitivecomputations/dolphin-mixtral-8x22b
 model_type: llm
 features:
  - agent-thought
@@ -1,7 +1,7 @@
 model: google/gemma-2-9b-it
 label:
-  zh_Hans: Gemma 2 9B
-  en_US: Gemma 2 9B
+  zh_Hans: google/gemma-2-9b-it
+  en_US: google/gemma-2-9b-it
 model_type: llm
 features:
  - agent-thought
@@ -1,7 +1,7 @@
 model: nousresearch/hermes-2-pro-llama-3-8b
 label:
-  zh_Hans: Hermes 2 Pro Llama 3 8B
-  en_US: Hermes 2 Pro Llama 3 8B
+  zh_Hans: nousresearch/hermes-2-pro-llama-3-8b
+  en_US: nousresearch/hermes-2-pro-llama-3-8b
 model_type: llm
 features:
  - agent-thought
@@ -1,7 +1,7 @@
 model: sao10k/l3-70b-euryale-v2.1
 label:
-  zh_Hans: "L3 70B Euryale V2.1\t"
-  en_US: "L3 70B Euryale V2.1\t"
+  zh_Hans: sao10k/l3-70b-euryale-v2.1
+  en_US: sao10k/l3-70b-euryale-v2.1
 model_type: llm
 features:
  - agent-thought
@@ -1,7 +1,7 @@
 model: sao10k/l3-8b-lunaris
 label:
-  zh_Hans: "Sao10k L3 8B Lunaris"
-  en_US: "Sao10k L3 8B Lunaris"
+  zh_Hans: sao10k/l3-8b-lunaris
+  en_US: sao10k/l3-8b-lunaris
 model_type: llm
 features:
  - agent-thought
@@ -1,7 +1,7 @@
 model: sao10k/l31-70b-euryale-v2.2
 label:
-  zh_Hans: L31 70B Euryale V2.2
-  en_US: L31 70B Euryale V2.2
+  zh_Hans: sao10k/l31-70b-euryale-v2.2
+  en_US: sao10k/l31-70b-euryale-v2.2
 model_type: llm
 features:
  - agent-thought
@@ -1,7 +1,7 @@
 model: meta-llama/llama-3-70b-instruct
 label:
-  zh_Hans: Llama3 70b Instruct
-  en_US: Llama3 70b Instruct
+  zh_Hans: meta-llama/llama-3-70b-instruct
+  en_US: meta-llama/llama-3-70b-instruct
 model_type: llm
 features:
  - agent-thought
@@ -1,7 +1,7 @@
 model: meta-llama/llama-3-8b-instruct
 label:
-  zh_Hans: Llama 3 8B Instruct
-  en_US: Llama 3 8B Instruct
+  zh_Hans: meta-llama/llama-3-8b-instruct
+  en_US: meta-llama/llama-3-8b-instruct
 model_type: llm
 features:
  - agent-thought
@@ -1,7 +1,7 @@
 model: meta-llama/llama-3.1-70b-instruct
 label:
-  zh_Hans: Llama 3.1 70B Instruct
-  en_US: Llama 3.1 70B Instruct
+  zh_Hans: meta-llama/llama-3.1-70b-instruct
+  en_US: meta-llama/llama-3.1-70b-instruct
 model_type: llm
 features:
  - agent-thought
@@ -1,7 +1,7 @@
 model: meta-llama/llama-3.1-8b-instruct-bf16
 label:
-  zh_Hans: Llama 3.1 8B Instruct BF16
-  en_US: Llama 3.1 8B Instruct BF16
+  zh_Hans: meta-llama/llama-3.1-8b-instruct-bf16
+  en_US: meta-llama/llama-3.1-8b-instruct-bf16
 model_type: llm
 features:
  - agent-thought
@@ -1,7 +1,7 @@
 model: meta-llama/llama-3.1-8b-instruct-max
 label:
-  zh_Hans: "Llama3.1 8B Instruct Max\t"
-  en_US: "Llama3.1 8B Instruct Max\t"
+  zh_Hans: meta-llama/llama-3.1-8b-instruct-max
+  en_US: meta-llama/llama-3.1-8b-instruct-max
 model_type: llm
 features:
  - agent-thought
@@ -1,7 +1,7 @@
 model: meta-llama/llama-3.1-8b-instruct
 label:
-  zh_Hans: Llama 3.1 8B Instruct
-  en_US: Llama 3.1 8B Instruct
+  zh_Hans: meta-llama/llama-3.1-8b-instruct
+  en_US: meta-llama/llama-3.1-8b-instruct
 model_type: llm
 features:
  - agent-thought
@@ -1,7 +1,7 @@
 model: meta-llama/llama-3.2-11b-vision-instruct
 label:
-  zh_Hans: "Llama 3.2 11B Vision Instruct\t"
-  en_US: "Llama 3.2 11B Vision Instruct\t"
+  zh_Hans: meta-llama/llama-3.2-11b-vision-instruct
+  en_US: meta-llama/llama-3.2-11b-vision-instruct
 model_type: llm
 features:
  - agent-thought
@@ -1,7 +1,7 @@
 model: meta-llama/llama-3.2-1b-instruct
 label:
-  zh_Hans: "Llama 3.2 1B Instruct\t"
-  en_US: "Llama 3.2 1B Instruct\t"
+  zh_Hans: meta-llama/llama-3.2-1b-instruct
+  en_US: meta-llama/llama-3.2-1b-instruct
 model_type: llm
 features:
  - agent-thought
@@ -1,7 +1,7 @@
 model: meta-llama/llama-3.2-3b-instruct
 label:
-  zh_Hans: Llama 3.2 3B Instruct
-  en_US: Llama 3.2 3B Instruct
+  zh_Hans: meta-llama/llama-3.2-3b-instruct
+  en_US: meta-llama/llama-3.2-3b-instruct
 model_type: llm
 features:
  - agent-thought
@@ -1,7 +1,7 @@
 model: meta-llama/llama-3.3-70b-instruct
 label:
-  zh_Hans: Llama 3.3 70B Instruct
-  en_US: Llama 3.3 70B Instruct
+  zh_Hans: meta-llama/llama-3.3-70b-instruct
+  en_US: meta-llama/llama-3.3-70b-instruct
 model_type: llm
 features:
  - agent-thought
@@ -1,7 +1,7 @@
 model: sophosympatheia/midnight-rose-70b
 label:
-  zh_Hans: Midnight Rose 70B
-  en_US: Midnight Rose 70B
+  zh_Hans: sophosympatheia/midnight-rose-70b
+  en_US: sophosympatheia/midnight-rose-70b
 model_type: llm
 features:
  - agent-thought
@@ -1,7 +1,7 @@
 model: mistralai/mistral-7b-instruct
 label:
-  zh_Hans: Mistral 7B Instruct
-  en_US: Mistral 7B Instruct
+  zh_Hans: mistralai/mistral-7b-instruct
+  en_US: mistralai/mistral-7b-instruct
 model_type: llm
 features:
  - agent-thought
@@ -1,7 +1,7 @@
 model: mistralai/mistral-nemo
 label:
-  zh_Hans: Mistral Nemo
-  en_US: Mistral Nemo
+  zh_Hans: mistralai/mistral-nemo
+  en_US: mistralai/mistral-nemo
 model_type: llm
 features:
  - agent-thought
@@ -1,7 +1,7 @@
 model: gryphe/mythomax-l2-13b
 label:
-  zh_Hans: Mythomax L2 13B
-  en_US: Mythomax L2 13B
+  zh_Hans: gryphe/mythomax-l2-13b
+  en_US: gryphe/mythomax-l2-13b
 model_type: llm
 features:
  - agent-thought
@@ -1,7 +1,7 @@
 model: nousresearch/nous-hermes-llama2-13b
 label:
-  zh_Hans: Nous Hermes Llama2 13B
-  en_US: Nous Hermes Llama2 13B
+  zh_Hans: nousresearch/nous-hermes-llama2-13b
+  en_US: nousresearch/nous-hermes-llama2-13b
 model_type: llm
 features:
  - agent-thought
@@ -1,7 +1,7 @@
 model: openchat/openchat-7b
 label:
-  zh_Hans: OpenChat 7B
-  en_US: OpenChat 7B
+  zh_Hans: openchat/openchat-7b
+  en_US: openchat/openchat-7b
 model_type: llm
 features:
  - agent-thought
@@ -1,7 +1,7 @@
 model: teknium/openhermes-2.5-mistral-7b
 label:
-  zh_Hans: Openhermes2.5 Mistral 7B
-  en_US: Openhermes2.5 Mistral 7B
+  zh_Hans: teknium/openhermes-2.5-mistral-7b
+  en_US: teknium/openhermes-2.5-mistral-7b
 model_type: llm
 features:
  - agent-thought
@@ -1,7 +1,7 @@
 model: qwen/qwen-2-72b-instruct
 label:
-  zh_Hans: Qwen2 72B Instruct
-  en_US: Qwen2 72B Instruct
+  zh_Hans: qwen/qwen-2-72b-instruct
+  en_US: qwen/qwen-2-72b-instruct
 model_type: llm
 features:
  - agent-thought
@@ -1,7 +1,7 @@
 model: qwen/qwen-2-7b-instruct
 label:
-  zh_Hans: Qwen 2 7B Instruct
-  en_US: Qwen 2 7B Instruct
+  zh_Hans: qwen/qwen-2-7b-instruct
+  en_US: qwen/qwen-2-7b-instruct
 model_type: llm
 features:
  - agent-thought
@@ -1,7 +1,7 @@
 model: qwen/qwen-2-vl-72b-instruct
 label:
-  zh_Hans: Qwen 2 VL 72B Instruct
-  en_US: Qwen 2 VL 72B Instruct
+  zh_Hans: qwen/qwen-2-vl-72b-instruct
+  en_US: qwen/qwen-2-vl-72b-instruct
 model_type: llm
 features:
  - agent-thought
@@ -1,7 +1,7 @@
 model: qwen/qwen-2.5-72b-instruct
 label:
-  zh_Hans: Qwen 2.5 72B Instruct
-  en_US: Qwen 2.5 72B Instruct
+  zh_Hans: qwen/qwen-2.5-72b-instruct
+  en_US: qwen/qwen-2.5-72b-instruct
 model_type: llm
 features:
  - agent-thought
@@ -1,7 +1,7 @@
 model: microsoft/wizardlm-2-8x22b
 label:
-  zh_Hans: Wizardlm 2 8x22B
-  en_US: Wizardlm 2 8x22B
+  zh_Hans: microsoft/wizardlm-2-8x22b
+  en_US: microsoft/wizardlm-2-8x22b
 model_type: llm
 features:
  - agent-thought
@@ -8,7 +8,7 @@ icon_small:
  en_US: icon_s_en.svg
 icon_large:
  en_US: icon_l_en.svg
-background: "#c7fce2"
+background: "#eadeff"
 help:
  title:
    en_US: Get your API key from Novita AI
@@ -1,4 +1,3 @@
- deepseek-ai/deepseek-r1
 - google/gemma-7b
 - google/codegemma-7b
 - google/recurrentgemma-2b
@@ -1,35 +0,0 @@
-model: deepseek-ai/deepseek-r1
-label:
-  en_US: deepseek-ai/deepseek-r1
-model_type: llm
-features:
-  - agent-thought
-model_properties:
-  mode: chat
-  context_size: 128000
-parameter_rules:
-  - name: temperature
-    use_template: temperature
-    min: 0
-    max: 1
-    default: 0.5
-  - name: top_p
-    use_template: top_p
-    min: 0
-    max: 1
-    default: 1
-  - name: max_tokens
-    use_template: max_tokens
-    min: 1
-    max: 1024
-    default: 1024
-  - name: frequency_penalty
-    use_template: frequency_penalty
-    min: -2
-    max: 2
-    default: 0
-  - name: presence_penalty
-    use_template: presence_penalty
-    min: -2
-    max: 2
-    default: 0
@@ -83,7 +83,7 @@ class NVIDIALargeLanguageModel(OAIAPICompatLargeLanguageModel):
    def _add_custom_parameters(self, credentials: dict, model: str) -> None:
        credentials["mode"] = "chat"

-        if self.MODEL_SUFFIX_MAP.get(model):
+        if self.MODEL_SUFFIX_MAP[model]:
            credentials["server_url"] = f"https://ai.api.nvidia.com/v1/{self.MODEL_SUFFIX_MAP[model]}"
            credentials.pop("endpoint_url")
        else:
@@ -1,52 +0,0 @@
-model: cohere.command-r-08-2024
-label:
-  en_US: cohere.command-r-08-2024 v1.7
-model_type: llm
-features:
-  - multi-tool-call
-  - agent-thought
-  - stream-tool-call
-model_properties:
-  mode: chat
-  context_size: 128000
-parameter_rules:
-  - name: temperature
-    use_template: temperature
-    default: 1
-    max: 1.0
-  - name: topP
-    use_template: top_p
-    default: 0.75
-    min: 0
-    max: 1
-  - name: topK
-    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
-    default: 0
-    min: 0
-    max: 500
-  - name: presencePenalty
-    use_template: presence_penalty
-    min: 0
-    max: 1
-    default: 0
-  - name: frequencyPenalty
-    use_template: frequency_penalty
-    min: 0
-    max: 1
-    default: 0
-  - name: maxTokens
-    use_template: max_tokens
-    default: 600
-    max: 4000
-pricing:
-  input: '0.0009'
-  output: '0.0009'
-  unit: '0.0001'
-  currency: USD
@@ -50,4 +50,3 @@ pricing:
  output: '0.004'
  unit: '0.0001'
  currency: USD
-deprecated: true
@@ -1,52 +0,0 @@
-model: cohere.command-r-plus-08-2024
-label:
-  en_US: cohere.command-r-plus-08-2024 v1.6
-model_type: llm
-features:
-  - multi-tool-call
-  - agent-thought
-  - stream-tool-call
-model_properties:
-  mode: chat
-  context_size: 128000
-parameter_rules:
-  - name: temperature
-    use_template: temperature
-    default: 1
-    max: 1.0
-  - name: topP
-    use_template: top_p
-    default: 0.75
-    min: 0
-    max: 1
-  - name: topK
-    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
-    default: 0
-    min: 0
-    max: 500
-  - name: presencePenalty
-    use_template: presence_penalty
-    min: 0
-    max: 1
-    default: 0
-  - name: frequencyPenalty
-    use_template: frequency_penalty
-    min: 0
-    max: 1
-    default: 0
-  - name: maxTokens
-    use_template: max_tokens
-    default: 600
-    max: 4000
-pricing:
-  input: '0.0156'
-  output: '0.0156'
-  unit: '0.0001'
-  currency: USD
@@ -50,4 +50,3 @@ pricing:
  output: '0.0219'
  unit: '0.0001'
  currency: USD
-deprecated: true
@@ -33,7 +33,7 @@ logger = logging.getLogger(__name__)

 request_template = {
    "compartmentId": "",
-    "servingMode": {"modelId": "cohere.command-r-plus-08-2024", "servingType": "ON_DEMAND"},
+    "servingMode": {"modelId": "cohere.command-r-plus", "servingType": "ON_DEMAND"},
    "chatRequest": {
        "apiFormat": "COHERE",
        # "preambleOverride": "You are a helpful assistant.",
@@ -60,19 +60,19 @@ oci_config_template = {
 class OCILargeLanguageModel(LargeLanguageModel):
    # https://docs.oracle.com/en-us/iaas/Content/generative-ai/pretrained-models.htm
    _supported_models = {
-        "meta.llama-3.1-70b-instruct": {
+        "meta.llama-3-70b-instruct": {
            "system": True,
            "multimodal": False,
            "tool_call": False,
            "stream_tool_call": False,
        },
-        "cohere.command-r-08-2024": {
+        "cohere.command-r-16k": {
            "system": True,
            "multimodal": False,
            "tool_call": True,
            "stream_tool_call": False,
        },
-        "cohere.command-r-plus-08-2024": {
+        "cohere.command-r-plus": {
            "system": True,
            "multimodal": False,
            "tool_call": True,
@@ -49,4 +49,3 @@ pricing:
  output: '0.015'
  unit: '0.0001'
  currency: USD
-deprecated: true
--- a/Show More
+++ b/Show More