fix: eslint run failed

chore: update libs
update eslint.config.mjs
2026-01-01 12:07:11 +00:00 · 2025-02-14 15:01:02 +08:00 · 2025-02-14 14:13:44 +08:00 · 2025-02-14 14:00:59 +08:00 · 2025-02-08 17:52:10 +08:00 · 2025-02-08 17:50:35 +08:00
260 changed files with 7004 additions and 7504 deletions
--- a/.github/workflows/docker-build.yml
+++ b/.github/workflows/docker-build.yml
@@ -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
--- a/README.md
+++ b/README.md
@@ -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">
--- a/README_AR.md
+++ b/README_AR.md
@@ -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">
--- a/README_CN.md
+++ b/README_CN.md
@@ -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">
--- a/README_ES.md
+++ b/README_ES.md
@@ -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">
--- a/README_FR.md
+++ b/README_FR.md
@@ -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">
--- a/README_JA.md
+++ b/README_JA.md
@@ -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">
--- a/README_KL.md
+++ b/README_KL.md
@@ -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">
--- a/README_KR.md
+++ b/README_KR.md
@@ -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">
--- a/README_PT.md
+++ b/README_PT.md
@@ -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">
--- a/README_SI.md
+++ b/README_SI.md
@@ -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">
--- a/README_TR.md
+++ b/README_TR.md
@@ -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
--- a/README_VI.md
+++ b/README_VI.md
@@ -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">
--- a/api/Dockerfile
+++ b/api/Dockerfile
@@ -48,18 +48,18 @@ 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 bookworm main" > /etc/apt/sources.list \
+    && apt-get update \
+    # For Security
+    && apt-get install -y --no-install-recommends expat libldap-2.5-0 perl libsqlite3-0 zlib1g \
+    # install a chinese font to support the use of tools like matplotlib
+    && apt-get install -y fonts-noto-cjk \
+    # install libmagic to support the use of python-magic guess MIMETYPE
+    && apt-get install -y libmagic1 \
    && apt-get autoremove -y \
    && rm -rf /var/lib/apt/lists/*

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

+
 ARG COMMIT_SHA
 ENV COMMIT_SHA=${COMMIT_SHA}

--- a/api/configs/feature/init.py
+++ b/api/configs/feature/init.py
@@ -498,11 +498,6 @@ class AuthConfig(BaseSettings):
        default=86400,
    )

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

 class ModerationConfig(BaseSettings):
    """
--- a/api/configs/feature/hosted_service/init.py
+++ b/api/configs/feature/hosted_service/init.py
@@ -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
--- a/api/configs/packaging/init.py
+++ b/api/configs/packaging/init.py
@@ -9,7 +9,7 @@ class PackagingInfo(BaseSettings):

    CURRENT_VERSION: str = Field(
        description="Dify version",
-        default="0.15.3",
+        default="0.15.2",
    )

    COMMIT_SHA: str = Field(
--- a/api/controllers/console/auth/error.py
+++ b/api/controllers/console/auth/error.py
@@ -59,9 +59,3 @@ class EmailCodeAccountDeletionRateLimitExceededError(BaseHTTPException):
    error_code = "email_code_account_deletion_rate_limit_exceeded"
    description = "Too many account deletion emails have been sent. Please try again in 5 minutes."
    code = 429
-
-
-class EmailPasswordResetLimitError(BaseHTTPException):
-    error_code = "email_password_reset_limit"
-    description = "Too many failed password reset attempts. Please try again in 24 hours."
-    code = 429
--- a/api/controllers/console/auth/forgot_password.py
+++ b/api/controllers/console/auth/forgot_password.py
@@ -6,13 +6,7 @@ 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,
-    EmailPasswordResetLimitError,
-    InvalidEmailError,
-    InvalidTokenError,
-    PasswordMismatchError,
-)
+from controllers.console.auth.error import EmailCodeError, InvalidEmailError, InvalidTokenError, PasswordMismatchError
 from controllers.console.error import AccountInFreezeError, AccountNotFound, EmailSendIpLimitError
 from controllers.console.wraps import setup_required
 from events.tenant_event import tenant_was_created
@@ -68,10 +62,6 @@ class ForgotPasswordCheckApi(Resource):

        user_email = args["email"]

-        is_forgot_password_error_rate_limit = AccountService.is_forgot_password_error_rate_limit(args["email"])
-        if is_forgot_password_error_rate_limit:
-            raise EmailPasswordResetLimitError()
-
        token_data = AccountService.get_reset_password_data(args["token"])
        if token_data is None:
            raise InvalidTokenError()
@@ -80,10 +70,8 @@ class ForgotPasswordCheckApi(Resource):
            raise InvalidEmailError()

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

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


--- a/api/core/helper/ssrf_proxy.py
+++ b/api/core/helper/ssrf_proxy.py
@@ -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:
--- a/api/core/model_runtime/entities/init.py
+++ b/api/core/model_runtime/entities/init.py
@@ -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",
--- a/api/core/model_runtime/entities/llm_entities.py
+++ b/api/core/model_runtime/entities/llm_entities.py
@@ -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.
    """
--- a/api/core/model_runtime/model_providers/__base/large_language_model.py
+++ b/api/core/model_runtime/model_providers/__base/large_language_model.py
@@ -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,
--- a/api/core/model_runtime/model_providers/_position.yaml
+++ b/api/core/model_runtime/model_providers/_position.yaml
@@ -1,5 +1,4 @@
 - openai
- deepseek
 - anthropic
 - azure_openai
 - google
@@ -33,6 +32,7 @@
 - localai
 - volcengine_maas
 - openai_api_compatible
+- deepseek
 - hunyuan
 - siliconflow
 - perfxcloud
--- a/api/core/model_runtime/model_providers/azure_ai_studio/azure_ai_studio.yaml
+++ b/api/core/model_runtime/model_providers/azure_ai_studio/azure_ai_studio.yaml
@@ -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:
--- a/api/core/model_runtime/model_providers/azure_ai_studio/llm/llm.py
+++ b/api/core/model_runtime/model_providers/azure_ai_studio/llm/llm.py
@@ -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,
        )

--- a/api/core/model_runtime/model_providers/azure_openai/azure_openai.yaml
+++ b/api/core/model_runtime/model_providers/azure_openai/azure_openai.yaml
@@ -138,18 +138,6 @@ 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
--- a/api/core/model_runtime/model_providers/bedrock/bedrock.yaml
+++ b/api/core/model_runtime/model_providers/bedrock/bedrock.yaml
@@ -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:
--- a/api/core/model_runtime/model_providers/bedrock/get_bedrock_client.py
+++ b/api/core/model_runtime/model_providers/bedrock/get_bedrock_client.py
@@ -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
--- a/api/core/model_runtime/model_providers/deepseek/llm/llm.py
+++ b/api/core/model_runtime/model_providers/deepseek/llm/llm.py
@@ -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,
+        )
--- a/api/core/model_runtime/model_providers/google/llm/_position.yaml
+++ b/api/core/model_runtime/model_providers/google/llm/_position.yaml
@@ -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
--- a/api/core/model_runtime/model_providers/google/llm/gemini-2.0-flash-001.yaml
+++ b/api/core/model_runtime/model_providers/google/llm/gemini-2.0-flash-001.yaml
@@ -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
--- a/api/core/model_runtime/model_providers/google/llm/gemini-2.0-pro-exp-02-05.yaml
+++ b/api/core/model_runtime/model_providers/google/llm/gemini-2.0-pro-exp-02-05.yaml
@@ -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
--- a/api/core/model_runtime/model_providers/groq/llm/_position.yaml
+++ b/api/core/model_runtime/model_providers/groq/llm/_position.yaml
@@ -1,4 +1,3 @@
- deepseek-r1-distill-llama-70b
 - llama-3.1-405b-reasoning
 - llama-3.3-70b-versatile
 - llama-3.1-70b-versatile
--- a/api/core/model_runtime/model_providers/groq/llm/deepseek-r1-distill-llama-70b.yaml
+++ b/api/core/model_runtime/model_providers/groq/llm/deepseek-r1-distill-llama-70b.yaml
@@ -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
--- a/api/core/model_runtime/model_providers/nvidia/llm/_position.yaml
+++ b/api/core/model_runtime/model_providers/nvidia/llm/_position.yaml
@@ -1,4 +1,3 @@
- deepseek-ai/deepseek-r1
 - google/gemma-7b
 - google/codegemma-7b
 - google/recurrentgemma-2b
--- a/api/core/model_runtime/model_providers/nvidia/llm/deepseek-r1.yaml
+++ b/api/core/model_runtime/model_providers/nvidia/llm/deepseek-r1.yaml
@@ -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
--- a/api/core/model_runtime/model_providers/nvidia/llm/llm.py
+++ b/api/core/model_runtime/model_providers/nvidia/llm/llm.py
@@ -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:
--- a/api/core/model_runtime/model_providers/oci/llm/cohere.command-r-08-2024.yaml
+++ b/api/core/model_runtime/model_providers/oci/llm/cohere.command-r-08-2024.yaml
@@ -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
--- a/api/core/model_runtime/model_providers/oci/llm/cohere.command-r-16k.yaml
+++ b/api/core/model_runtime/model_providers/oci/llm/cohere.command-r-16k.yaml
@@ -50,4 +50,3 @@ pricing:
  output: '0.004'
  unit: '0.0001'
  currency: USD
-deprecated: true
--- a/api/core/model_runtime/model_providers/oci/llm/cohere.command-r-plus-08-2024.yaml
+++ b/api/core/model_runtime/model_providers/oci/llm/cohere.command-r-plus-08-2024.yaml
@@ -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
--- a/api/core/model_runtime/model_providers/oci/llm/cohere.command-r-plus.yaml
+++ b/api/core/model_runtime/model_providers/oci/llm/cohere.command-r-plus.yaml
@@ -50,4 +50,3 @@ pricing:
  output: '0.0219'
  unit: '0.0001'
  currency: USD
-deprecated: true
--- a/api/core/model_runtime/model_providers/oci/llm/llm.py
+++ b/api/core/model_runtime/model_providers/oci/llm/llm.py
@@ -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,
--- a/api/core/model_runtime/model_providers/oci/llm/meta.llama-3-70b-instruct.yaml
+++ b/api/core/model_runtime/model_providers/oci/llm/meta.llama-3-70b-instruct.yaml
@@ -49,4 +49,3 @@ pricing:
  output: '0.015'
  unit: '0.0001'
  currency: USD
-deprecated: true
--- a/api/core/model_runtime/model_providers/oci/llm/meta.llama-3.1-70b-instruct.yaml
+++ b/api/core/model_runtime/model_providers/oci/llm/meta.llama-3.1-70b-instruct.yaml
@@ -1,51 +0,0 @@
-model: meta.llama-3.1-70b-instruct
-label:
-  zh_Hans: meta.llama-3.1-70b-instruct
-  en_US: meta.llama-3.1-70b-instruct
-model_type: llm
-features:
-  - agent-thought
-model_properties:
-  mode: chat
-  context_size: 131072
-parameter_rules:
-  - name: temperature
-    use_template: temperature
-    default: 1
-    max: 2.0
-  - 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: -2
-    max: 2
-    default: 0
-  - name: frequencyPenalty
-    use_template: frequency_penalty
-    min: -2
-    max: 2
-    default: 0
-  - name: maxTokens
-    use_template: max_tokens
-    default: 600
-    max: 4000
-pricing:
-  input: '0.0075'
-  output: '0.0075'
-  unit: '0.0001'
-  currency: USD
--- a/api/core/model_runtime/model_providers/oci/oci.py
+++ b/api/core/model_runtime/model_providers/oci/oci.py
@@ -19,8 +19,8 @@ class OCIGENAIProvider(ModelProvider):
        try:
            model_instance = self.get_model_instance(ModelType.LLM)

-            # Use `cohere.command-r-plus-08-2024` model for validate,
-            model_instance.validate_credentials(model="cohere.command-r-plus-08-2024", credentials=credentials)
+            # Use `cohere.command-r-plus` model for validate,
+            model_instance.validate_credentials(model="cohere.command-r-plus", credentials=credentials)
        except CredentialsValidateFailedError as ex:
            raise ex
        except Exception as ex:
--- a/api/core/model_runtime/model_providers/ollama/llm/llm.py
+++ b/api/core/model_runtime/model_providers/ollama/llm/llm.py
@@ -367,7 +367,6 @@ class OllamaLargeLanguageModel(LargeLanguageModel):

                # transform assistant message to prompt message
                text = chunk_json["response"]
-            text = self._wrap_thinking_by_tag(text)

            assistant_prompt_message = AssistantPromptMessage(content=text)

--- a/api/core/model_runtime/model_providers/openai/llm/_position.yaml
+++ b/api/core/model_runtime/model_providers/openai/llm/_position.yaml
@@ -2,8 +2,6 @@
 - o1-2024-12-17
 - o1-mini
 - o1-mini-2024-09-12
- o3-mini
- o3-mini-2025-01-31
 - gpt-4
 - gpt-4o
 - gpt-4o-2024-05-13
--- a/api/core/model_runtime/model_providers/openai/llm/llm.py
+++ b/api/core/model_runtime/model_providers/openai/llm/llm.py
@@ -619,9 +619,9 @@ class OpenAILargeLanguageModel(_CommonOpenAI, LargeLanguageModel):
        # clear illegal prompt messages
        prompt_messages = self._clear_illegal_prompt_messages(model, prompt_messages)

-        # o1, o3 compatibility
+        # o1 compatibility
        block_as_stream = False
-        if model.startswith(("o1", "o3")):
+        if model.startswith("o1"):
            if "max_tokens" in model_parameters:
                model_parameters["max_completion_tokens"] = model_parameters["max_tokens"]
                del model_parameters["max_tokens"]
@@ -941,7 +941,7 @@ class OpenAILargeLanguageModel(_CommonOpenAI, LargeLanguageModel):
                                ]
                            )

-        if model.startswith(("o1", "o3")):
+        if model.startswith("o1"):
            system_message_count = len([m for m in prompt_messages if isinstance(m, SystemPromptMessage)])
            if system_message_count > 0:
                new_prompt_messages = []
@@ -1053,7 +1053,7 @@ class OpenAILargeLanguageModel(_CommonOpenAI, LargeLanguageModel):
            model = model.split(":")[1]

        # Currently, we can use gpt4o to calculate chatgpt-4o-latest's token.
-        if model == "chatgpt-4o-latest" or model.startswith(("o1", "o3")):
+        if model == "chatgpt-4o-latest" or model.startswith("o1"):
            model = "gpt-4o"

        try:
@@ -1068,7 +1068,7 @@ class OpenAILargeLanguageModel(_CommonOpenAI, LargeLanguageModel):
            tokens_per_message = 4
            # if there's a name, the role is omitted
            tokens_per_name = -1
-        elif model.startswith("gpt-3.5-turbo") or model.startswith("gpt-4") or model.startswith(("o1", "o3")):
+        elif model.startswith("gpt-3.5-turbo") or model.startswith("gpt-4") or model.startswith("o1"):
            tokens_per_message = 3
            tokens_per_name = 1
        else:
--- a/api/core/model_runtime/model_providers/openai/llm/o1-2024-12-17.yaml
+++ b/api/core/model_runtime/model_providers/openai/llm/o1-2024-12-17.yaml
@@ -16,19 +16,6 @@ parameter_rules:
    default: 50000
    min: 1
    max: 50000
-  - name: reasoning_effort
-    label:
-      zh_Hans: 推理工作
-      en_US: reasoning_effort
-    type: string
-    help:
-      zh_Hans: 限制推理模型的推理工作
-      en_US: constrains effort on reasoning for reasoning models
-    required: false
-    options:
-      - low
-      - medium
-      - high
  - name: response_format
    label:
      zh_Hans: 回复格式
--- a/api/core/model_runtime/model_providers/openai/llm/o1.yaml
+++ b/api/core/model_runtime/model_providers/openai/llm/o1.yaml
@@ -17,19 +17,6 @@ parameter_rules:
    default: 50000
    min: 1
    max: 50000
-  - name: reasoning_effort
-    label:
-      zh_Hans: 推理工作
-      en_US: reasoning_effort
-    type: string
-    help:
-      zh_Hans: 限制推理模型的推理工作
-      en_US: constrains effort on reasoning for reasoning models
-    required: false
-    options:
-      - low
-      - medium
-      - high
  - name: response_format
    label:
      zh_Hans: 回复格式
--- a/api/core/model_runtime/model_providers/openai/llm/o3-mini-2025-01-31.yaml
+++ b/api/core/model_runtime/model_providers/openai/llm/o3-mini-2025-01-31.yaml
@@ -1,46 +0,0 @@
-model: o3-mini-2025-01-31
-label:
-  zh_Hans: o3-mini-2025-01-31
-  en_US: o3-mini-2025-01-31
-model_type: llm
-features:
-  - agent-thought
-model_properties:
-  mode: chat
-  context_size: 200000
-parameter_rules:
-  - name: max_tokens
-    use_template: max_tokens
-    default: 100000
-    min: 1
-    max: 100000
-  - name: reasoning_effort
-    label:
-      zh_Hans: 推理工作
-      en_US: reasoning_effort
-    type: string
-    help:
-      zh_Hans: 限制推理模型的推理工作
-      en_US: constrains effort on reasoning for reasoning models
-    required: false
-    options:
-      - low
-      - medium
-      - high
-  - 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: '1.10'
-  output: '4.40'
-  unit: '0.000001'
-  currency: USD
--- a/api/core/model_runtime/model_providers/openai/llm/o3-mini.yaml
+++ b/api/core/model_runtime/model_providers/openai/llm/o3-mini.yaml
@@ -1,46 +0,0 @@
-model: o3-mini
-label:
-  zh_Hans: o3-mini
-  en_US: o3-mini
-model_type: llm
-features:
-  - agent-thought
-model_properties:
-  mode: chat
-  context_size: 200000
-parameter_rules:
-  - name: max_tokens
-    use_template: max_tokens
-    default: 100000
-    min: 1
-    max: 100000
-  - name: reasoning_effort
-    label:
-      zh_Hans: 推理工作
-      en_US: reasoning_effort
-    type: string
-    help:
-      zh_Hans: 限制推理模型的推理工作
-      en_US: constrains effort on reasoning for reasoning models
-    required: false
-    options:
-      - low
-      - medium
-      - high
-  - 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: '1.10'
-  output: '4.40'
-  unit: '0.000001'
-  currency: USD
--- a/api/core/model_runtime/model_providers/openai_api_compatible/llm/llm.py
+++ b/api/core/model_runtime/model_providers/openai_api_compatible/llm/llm.py
@@ -1,5 +1,5 @@
-import codecs
 import json
+import logging
 from collections.abc import Generator
 from decimal import Decimal
 from typing import Optional, Union, cast
@@ -38,6 +38,8 @@ from core.model_runtime.model_providers.__base.large_language_model import Large
 from core.model_runtime.model_providers.openai_api_compatible._common import _CommonOaiApiCompat
 from core.model_runtime.utils import helper

+logger = logging.getLogger(__name__)
+

 class OAIAPICompatLargeLanguageModel(_CommonOaiApiCompat, LargeLanguageModel):
    """
@@ -97,7 +99,7 @@ class OAIAPICompatLargeLanguageModel(_CommonOaiApiCompat, LargeLanguageModel):
        :param tools: tools for tool calling
        :return:
        """
-        return self._num_tokens_from_messages(prompt_messages, tools, credentials)
+        return self._num_tokens_from_messages(model, prompt_messages, tools, credentials)

    def validate_credentials(self, model: str, credentials: dict) -> None:
        """
@@ -396,73 +398,6 @@ class OAIAPICompatLargeLanguageModel(_CommonOaiApiCompat, LargeLanguageModel):

        return self._handle_generate_response(model, credentials, response, prompt_messages)

-    def _create_final_llm_result_chunk(
-        self,
-        index: int,
-        message: AssistantPromptMessage,
-        finish_reason: str,
-        usage: dict,
-        model: str,
-        prompt_messages: list[PromptMessage],
-        credentials: dict,
-        full_content: str,
-    ) -> LLMResultChunk:
-        # calculate num tokens
-        prompt_tokens = usage and usage.get("prompt_tokens")
-        if prompt_tokens is None:
-            prompt_tokens = self._num_tokens_from_string(text=prompt_messages[0].content)
-        completion_tokens = usage and usage.get("completion_tokens")
-        if completion_tokens is None:
-            completion_tokens = self._num_tokens_from_string(text=full_content)
-
-        # transform usage
-        usage = self._calc_response_usage(model, credentials, prompt_tokens, completion_tokens)
-
-        return LLMResultChunk(
-            model=model,
-            prompt_messages=prompt_messages,
-            delta=LLMResultChunkDelta(index=index, message=message, finish_reason=finish_reason, usage=usage),
-        )
-
-    def _get_tool_call(self, tool_call_id: str, tools_calls: list[AssistantPromptMessage.ToolCall]):
-        """
-        Get or create a tool call by ID
-
-        :param tool_call_id: tool call ID
-        :param tools_calls: list of existing tool calls
-        :return: existing or new tool call, updated tools_calls
-        """
-        if not tool_call_id:
-            return tools_calls[-1], tools_calls
-
-        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, tools_calls
-
-    def _increase_tool_call(
-        self, new_tool_calls: list[AssistantPromptMessage.ToolCall], tools_calls: list[AssistantPromptMessage.ToolCall]
-    ) -> list[AssistantPromptMessage.ToolCall]:
-        for new_tool_call in new_tool_calls:
-            # get tool call
-            tool_call, tools_calls = self._get_tool_call(new_tool_call.function.name, tools_calls)
-            # 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
-        return tools_calls
-
    def _handle_generate_stream_response(
        self, model: str, credentials: dict, response: requests.Response, prompt_messages: list[PromptMessage]
    ) -> Generator:
@@ -475,15 +410,69 @@ class OAIAPICompatLargeLanguageModel(_CommonOaiApiCompat, LargeLanguageModel):
        :param prompt_messages: prompt messages
        :return: llm response chunk generator
        """
-        chunk_index = 0
        full_assistant_content = ""
-        tools_calls: list[AssistantPromptMessage.ToolCall] = []
-        finish_reason = None
-        usage = None
-        is_reasoning_started = False
+        chunk_index = 0
+
+        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:
@@ -498,15 +487,12 @@ class OAIAPICompatLargeLanguageModel(_CommonOaiApiCompat, LargeLanguageModel):
                    chunk_json: dict = json.loads(decoded_chunk)
                # stream ended
                except json.JSONDecodeError as e:
-                    yield self._create_final_llm_result_chunk(
+                    yield create_final_llm_result_chunk(
+                        id=message_id,
                        index=chunk_index + 1,
                        message=AssistantPromptMessage(content=""),
                        finish_reason="Non-JSON encountered.",
                        usage=usage,
-                        model=model,
-                        credentials=credentials,
-                        prompt_messages=prompt_messages,
-                        full_content=full_assistant_content,
                    )
                    break
                # handle the error here. for issue #11629
@@ -521,14 +507,12 @@ class OAIAPICompatLargeLanguageModel(_CommonOaiApiCompat, LargeLanguageModel):

                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"]
-                    delta_content, is_reasoning_started = self._wrap_thinking_by_reasoning_content(
-                        delta, is_reasoning_started
-                    )
-                    delta_content = self._wrap_thinking_by_tag(delta_content)
+                    delta_content = delta.get("content")

                    assistant_message_tool_calls = None

@@ -542,10 +526,12 @@ class OAIAPICompatLargeLanguageModel(_CommonOaiApiCompat, LargeLanguageModel):
                            {"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)
-                        tools_calls = self._increase_tool_call(tool_calls, tools_calls)
+                        increase_tool_call(tool_calls)

                    if delta_content is None or delta_content == "":
                        continue
@@ -570,6 +556,7 @@ class OAIAPICompatLargeLanguageModel(_CommonOaiApiCompat, LargeLanguageModel):
                    continue

                yield LLMResultChunk(
+                    id=message_id,
                    model=model,
                    prompt_messages=prompt_messages,
                    delta=LLMResultChunkDelta(
@@ -582,6 +569,7 @@ class OAIAPICompatLargeLanguageModel(_CommonOaiApiCompat, LargeLanguageModel):

        if tools_calls:
            yield LLMResultChunk(
+                id=message_id,
                model=model,
                prompt_messages=prompt_messages,
                delta=LLMResultChunkDelta(
@@ -590,15 +578,12 @@ class OAIAPICompatLargeLanguageModel(_CommonOaiApiCompat, LargeLanguageModel):
                ),
            )

-        yield self._create_final_llm_result_chunk(
+        yield create_final_llm_result_chunk(
+            id=message_id,
            index=chunk_index,
            message=AssistantPromptMessage(content=""),
            finish_reason=finish_reason,
            usage=usage,
-            model=model,
-            credentials=credentials,
-            prompt_messages=prompt_messages,
-            full_content=full_assistant_content,
        )

    def _handle_generate_response(
@@ -712,11 +697,12 @@ class OAIAPICompatLargeLanguageModel(_CommonOaiApiCompat, LargeLanguageModel):
        return message_dict

    def _num_tokens_from_string(
-        self, text: Union[str, list[PromptMessageContent]], tools: Optional[list[PromptMessageTool]] = None
+        self, model: str, text: Union[str, list[PromptMessageContent]], tools: Optional[list[PromptMessageTool]] = None
    ) -> int:
        """
        Approximate num tokens for model with gpt2 tokenizer.

+        :param model: model name
        :param text: prompt text
        :param tools: tools for tool calling
        :return: number of tokens
@@ -739,6 +725,7 @@ class OAIAPICompatLargeLanguageModel(_CommonOaiApiCompat, LargeLanguageModel):

    def _num_tokens_from_messages(
        self,
+        model: str,
        messages: list[PromptMessage],
        tools: Optional[list[PromptMessageTool]] = None,
        credentials: Optional[dict] = None,
--- a/api/core/model_runtime/model_providers/openrouter/llm/_position.yaml
+++ b/api/core/model_runtime/model_providers/openrouter/llm/_position.yaml
@@ -1,7 +1,5 @@
 - openai/o1-preview
 - openai/o1-mini
- openai/o3-mini
- openai/o3-mini-2025-01-31
 - openai/gpt-4o
 - openai/gpt-4o-mini
 - openai/gpt-4
@@ -30,6 +28,5 @@
 - mistralai/mistral-7b-instruct
 - qwen/qwen-2.5-72b-instruct
 - qwen/qwen-2-72b-instruct
- deepseek/deepseek-r1
 - deepseek/deepseek-chat
 - deepseek/deepseek-coder
--- a/api/core/model_runtime/model_providers/openrouter/llm/deepseek-chat.yaml
+++ b/api/core/model_runtime/model_providers/openrouter/llm/deepseek-chat.yaml
@@ -53,7 +53,7 @@ parameter_rules:
      zh_Hans: 介于 -2.0 和 2.0 之间的数字。如果该值为正，那么新 token 会根据其在已有文本中的出现频率受到相应的惩罚，降低模型重复相同内容的可能性。
      en_US: A number between -2.0 and 2.0. If the value is positive, new tokens are penalized based on their frequency of occurrence in existing text, reducing the likelihood that the model will repeat the same content.
 pricing:
-  input: "0.49"
-  output: "0.89"
+  input: "0.14"
+  output: "0.28"
  unit: "0.000001"
  currency: USD
--- a/api/core/model_runtime/model_providers/openrouter/llm/deepseek-r1.yaml
+++ b/api/core/model_runtime/model_providers/openrouter/llm/deepseek-r1.yaml
@@ -1,59 +0,0 @@
-model: deepseek/deepseek-r1
-label:
-  en_US: deepseek-r1
-model_type: llm
-features:
-  - agent-thought
-model_properties:
-  mode: chat
-  context_size: 163840
-parameter_rules:
-  - name: temperature
-    use_template: temperature
-    type: float
-    default: 1
-    min: 0.0
-    max: 2.0
-    help:
-      zh_Hans: 控制生成结果的多样性和随机性。数值越小，越严谨；数值越大，越发散。
-      en_US: Control the diversity and randomness of generated results. The smaller the value, the more rigorous it is; the larger the value, the more divergent it is.
-  - name: max_tokens
-    use_template: max_tokens
-    type: int
-    default: 4096
-    min: 1
-    max: 4096
-    help:
-      zh_Hans: 指定生成结果长度的上限。如果生成结果截断，可以调大该参数。
-      en_US: Specifies the upper limit on the length of generated results. If the generated results are truncated, you can increase this parameter.
-  - name: top_p
-    use_template: top_p
-    type: float
-    default: 1
-    min: 0.01
-    max: 1.00
-    help:
-      zh_Hans: 控制生成结果的随机性。数值越小，随机性越弱；数值越大，随机性越强。一般而言，top_p 和 temperature 两个参数选择一个进行调整即可。
-      en_US: Control the randomness of generated results. The smaller the value, the weaker the randomness; the larger the value, the stronger the randomness. Generally speaking, you can adjust one of the two parameters top_p and temperature.
-  - 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: frequency_penalty
-    use_template: frequency_penalty
-    default: 0
-    min: -2.0
-    max: 2.0
-    help:
-      zh_Hans: 介于 -2.0 和 2.0 之间的数字。如果该值为正，那么新 token 会根据其在已有文本中的出现频率受到相应的惩罚，降低模型重复相同内容的可能性。
-      en_US: A number between -2.0 and 2.0. If the value is positive, new tokens are penalized based on their frequency of occurrence in existing text, reducing the likelihood that the model will repeat the same content.
-pricing:
-  input: "3"
-  output: "8"
-  unit: "0.000001"
-  currency: USD
--- a/api/core/model_runtime/model_providers/openrouter/llm/o3-mini-2025-01-31.yaml
+++ b/api/core/model_runtime/model_providers/openrouter/llm/o3-mini-2025-01-31.yaml
@@ -1,49 +0,0 @@
-model: openai/o3-mini-2025-01-31
-label:
-  en_US: o3-mini-2025-01-31
-model_type: llm
-features:
-  - agent-thought
-model_properties:
-  mode: chat
-  context_size: 200000
-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: presence_penalty
-    use_template: presence_penalty
-  - name: frequency_penalty
-    use_template: frequency_penalty
-  - name: max_tokens
-    use_template: max_tokens
-    default: 512
-    min: 1
-    max: 100000
-  - 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: "1.10"
-  output: "4.40"
-  unit: "0.000001"
-  currency: USD
--- a/api/core/model_runtime/model_providers/openrouter/llm/o3-mini.yaml
+++ b/api/core/model_runtime/model_providers/openrouter/llm/o3-mini.yaml
@@ -1,49 +0,0 @@
-model: openai/o3-mini
-label:
-  en_US: o3-mini
-model_type: llm
-features:
-  - agent-thought
-model_properties:
-  mode: chat
-  context_size: 200000
-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: presence_penalty
-    use_template: presence_penalty
-  - name: frequency_penalty
-    use_template: frequency_penalty
-  - name: max_tokens
-    use_template: max_tokens
-    default: 512
-    min: 1
-    max: 100000
-  - 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: "1.10"
-  output: "4.40"
-  unit: "0.000001"
-  currency: USD
--- a/api/core/model_runtime/model_providers/siliconflow/llm/_position.yaml
+++ b/api/core/model_runtime/model_providers/siliconflow/llm/_position.yaml
@@ -12,18 +12,7 @@
 - Pro/Qwen/Qwen2-VL-7B-Instruct
 - OpenGVLab/InternVL2-26B
 - Pro/OpenGVLab/InternVL2-8B
- deepseek-ai/DeepSeek-R1
- deepseek-ai/DeepSeek-V2-Chat
 - deepseek-ai/DeepSeek-V2.5
- deepseek-ai/DeepSeek-V3
- deepseek-ai/DeepSeek-Coder-V2-Instruct
- deepseek-ai/DeepSeek-R1-Distill-Llama-8B
- deepseek-ai/DeepSeek-R1-Distill-Llama-70B
- deepseek-ai/DeepSeek-R1-Distill-Qwen-1.5B
- deepseek-ai/DeepSeek-R1-Distill-Qwen-7B
- deepseek-ai/DeepSeek-R1-Distill-Qwen-14B
- deepseek-ai/DeepSeek-R1-Distill-Qwen-32B
- deepseek-ai/Janus-Pro-7B
 - THUDM/glm-4-9b-chat
 - 01-ai/Yi-1.5-34B-Chat-16K
 - 01-ai/Yi-1.5-9B-Chat-16K
@@ -36,4 +25,3 @@
 - meta-llama/Meta-Llama-3.1-8B-Instruct
 - google/gemma-2-27b-it
 - google/gemma-2-9b-it
- Tencent/Hunyuan-A52B-Instruct
--- a/api/core/model_runtime/model_providers/siliconflow/llm/deepseek-r1-distill-llama-70B.yaml
+++ b/api/core/model_runtime/model_providers/siliconflow/llm/deepseek-r1-distill-llama-70B.yaml
@@ -1,21 +0,0 @@
-model: deepseek-ai/DeepSeek-R1-Distill-Llama-70B
-label:
-  zh_Hans: deepseek-ai/DeepSeek-R1-Distill-Llama-70B
-  en_US: deepseek-ai/DeepSeek-R1-Distill-Llama-70B
-model_type: llm
-features:
-  - agent-thought
-model_properties:
-  mode: chat
-  context_size: 32000
-parameter_rules:
-  - name: max_tokens
-    use_template: max_tokens
-    min: 1
-    max: 8192
-    default: 4096
-pricing:
-  input: "0.00"
-  output: "4.3"
-  unit: "0.000001"
-  currency: RMB
--- a/api/core/model_runtime/model_providers/siliconflow/llm/deepseek-r1-distill-llama-8B.yaml
+++ b/api/core/model_runtime/model_providers/siliconflow/llm/deepseek-r1-distill-llama-8B.yaml
@@ -1,21 +0,0 @@
-model: deepseek-ai/DeepSeek-R1-Distill-Llama-8B
-label:
-  zh_Hans: deepseek-ai/DeepSeek-R1-Distill-Llama-8B
-  en_US: deepseek-ai/DeepSeek-R1-Distill-Llama-8B
-model_type: llm
-features:
-  - agent-thought
-model_properties:
-  mode: chat
-  context_size: 32000
-parameter_rules:
-  - name: max_tokens
-    use_template: max_tokens
-    min: 1
-    max: 8192
-    default: 4096
-pricing:
-  input: "0.00"
-  output: "0.00"
-  unit: "0.000001"
-  currency: RMB
--- a/api/core/model_runtime/model_providers/siliconflow/llm/deepseek-r1-distill-qwen-1.5B.yaml
+++ b/api/core/model_runtime/model_providers/siliconflow/llm/deepseek-r1-distill-qwen-1.5B.yaml
@@ -1,21 +0,0 @@
-model: deepseek-ai/DeepSeek-R1-Distill-Qwen-1.5B
-label:
-  zh_Hans: deepseek-ai/DeepSeek-R1-Distill-Qwen-1.5B
-  en_US: deepseek-ai/DeepSeek-R1-Distill-Qwen-1.5B
-model_type: llm
-features:
-  - agent-thought
-model_properties:
-  mode: chat
-  context_size: 32000
-parameter_rules:
-  - name: max_tokens
-    use_template: max_tokens
-    min: 1
-    max: 8192
-    default: 4096
-pricing:
-  input: "0.00"
-  output: "1.26"
-  unit: "0.000001"
-  currency: RMB
--- a/api/core/model_runtime/model_providers/siliconflow/llm/deepseek-r1-distill-qwen-14B.yaml
+++ b/api/core/model_runtime/model_providers/siliconflow/llm/deepseek-r1-distill-qwen-14B.yaml
@@ -1,21 +0,0 @@
-model: deepseek-ai/DeepSeek-R1-Distill-Qwen-14B
-label:
-  zh_Hans: deepseek-ai/DeepSeek-R1-Distill-Qwen-14B
-  en_US: deepseek-ai/DeepSeek-R1-Distill-Qwen-14B
-model_type: llm
-features:
-  - agent-thought
-model_properties:
-  mode: chat
-  context_size: 32000
-parameter_rules:
-  - name: max_tokens
-    use_template: max_tokens
-    min: 1
-    max: 8192
-    default: 4096
-pricing:
-  input: "0.00"
-  output: "0.70"
-  unit: "0.000001"
-  currency: RMB
--- a/api/core/model_runtime/model_providers/siliconflow/llm/deepseek-r1-distill-qwen-32B.yaml
+++ b/api/core/model_runtime/model_providers/siliconflow/llm/deepseek-r1-distill-qwen-32B.yaml
@@ -1,21 +0,0 @@
-model: deepseek-ai/DeepSeek-R1-Distill-Qwen-32B
-label:
-  zh_Hans: deepseek-ai/DeepSeek-R1-Distill-Qwen-32B
-  en_US: deepseek-ai/DeepSeek-R1-Distill-Qwen-32B
-model_type: llm
-features:
-  - agent-thought
-model_properties:
-  mode: chat
-  context_size: 32000
-parameter_rules:
-  - name: max_tokens
-    use_template: max_tokens
-    min: 1
-    max: 8192
-    default: 4096
-pricing:
-  input: "0.00"
-  output: "1.26"
-  unit: "0.000001"
-  currency: RMB
--- a/api/core/model_runtime/model_providers/siliconflow/llm/deepseek-r1-distill-qwen-7B.yaml
+++ b/api/core/model_runtime/model_providers/siliconflow/llm/deepseek-r1-distill-qwen-7B.yaml
@@ -1,21 +0,0 @@
-model: deepseek-ai/DeepSeek-R1-Distill-Qwen-7B
-label:
-  zh_Hans: deepseek-ai/DeepSeek-R1-Distill-Qwen-7B
-  en_US: deepseek-ai/DeepSeek-R1-Distill-Qwen-7B
-model_type: llm
-features:
-  - agent-thought
-model_properties:
-  mode: chat
-  context_size: 32000
-parameter_rules:
-  - name: max_tokens
-    use_template: max_tokens
-    min: 1
-    max: 8192
-    default: 4096
-pricing:
-  input: "0.00"
-  output: "0.00"
-  unit: "0.000001"
-  currency: RMB
--- a/api/core/model_runtime/model_providers/siliconflow/llm/deepseek-r1.yaml
+++ b/api/core/model_runtime/model_providers/siliconflow/llm/deepseek-r1.yaml
@@ -1,21 +0,0 @@
-model: deepseek-ai/DeepSeek-R1
-label:
-  zh_Hans: deepseek-ai/DeepSeek-R1
-  en_US: deepseek-ai/DeepSeek-R1
-model_type: llm
-features:
-  - agent-thought
-model_properties:
-  mode: chat
-  context_size: 64000
-parameter_rules:
-  - name: max_tokens
-    use_template: max_tokens
-    min: 1
-    max: 8192
-    default: 4096
-pricing:
-  input: "4"
-  output: "16"
-  unit: "0.000001"
-  currency: RMB
--- a/api/core/model_runtime/model_providers/siliconflow/llm/deepseek-v3.yaml
+++ b/api/core/model_runtime/model_providers/siliconflow/llm/deepseek-v3.yaml
@@ -1,53 +0,0 @@
-model: deepseek-ai/DeepSeek-V3
-label:
-  en_US: deepseek-ai/DeepSeek-V3
-model_type: llm
-features:
-  - agent-thought
-  - tool-call
-  - stream-tool-call
-model_properties:
-  mode: chat
-  context_size: 64000
-parameter_rules:
-  - name: temperature
-    use_template: temperature
-  - name: max_tokens
-    use_template: max_tokens
-    type: int
-    default: 512
-    min: 1
-    max: 4096
-    help:
-      zh_Hans: 指定生成结果长度的上限。如果生成结果截断，可以调大该参数。
-      en_US: Specifies the upper limit on the length of generated results. If the generated results are truncated, you can increase this parameter.
-  - 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: frequency_penalty
-    use_template: frequency_penalty
-  - 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: "1"
-  output: "2"
-  unit: "0.000001"
-  currency: RMB
--- a/api/core/model_runtime/model_providers/siliconflow/llm/janus-pro-7B.yaml
+++ b/api/core/model_runtime/model_providers/siliconflow/llm/janus-pro-7B.yaml
@@ -1,22 +0,0 @@
-model: deepseek-ai/Janus-Pro-7B
-label:
-  zh_Hans: deepseek-ai/Janus-Pro-7B
-  en_US: deepseek-ai/Janus-Pro-7B
-model_type: llm
-features:
-  - agent-thought
-  - vision
-model_properties:
-  mode: chat
-  context_size: 32000
-parameter_rules:
-  - name: max_tokens
-    use_template: max_tokens
-    min: 1
-    max: 8192
-    default: 4096
-pricing:
-  input: "0.00"
-  output: "0.00"
-  unit: "0.000001"
-  currency: RMB
--- a/api/core/model_runtime/model_providers/siliconflow/llm/llm.py
+++ b/api/core/model_runtime/model_providers/siliconflow/llm/llm.py
@@ -1,9 +1,13 @@
+import json
 from collections.abc import Generator
 from typing import Optional, Union

+import requests
+
 from core.model_runtime.entities.common_entities import I18nObject
-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,
 )
@@ -92,3 +96,208 @@ class SiliconflowLargeLanguageModel(OAIAPICompatLargeLanguageModel):
                ),
            ],
        )
+
+    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"]
+                    delta_content = delta.get("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
+
+                    # Check for think tags
+                    if "<think>" in delta_content:
+                        is_reasoning_started = True
+                        # Remove <think> tag and add markdown quote
+                        delta_content = "> 💭 " + delta_content.replace("<think>", "")
+                    elif "</think>" in delta_content:
+                        # Remove </think> tag and add newlines to end quote block
+                        delta_content = delta_content.replace("</think>", "") + "\n\n"
+                        is_reasoning_started = False
+                    elif is_reasoning_started:
+                        # Add quote markers for content within thinking block
+                        if "\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> ")
+
+                    # 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,
+        )
--- a/api/core/model_runtime/model_providers/tongyi/llm/qwen-max-0107.yaml
+++ b/api/core/model_runtime/model_providers/tongyi/llm/qwen-max-0107.yaml
@@ -69,15 +69,6 @@ parameter_rules:
    help:
      zh_Hans: 用于控制模型生成时的重复度。提高repetition_penalty时可以降低模型生成的重复度。1.0表示不做惩罚。
      en_US: Used to control the repeatability when generating models. Increasing repetition_penalty can reduce the duplication of model generation. 1.0 means no punishment.
-  - name: enable_search
-    type: boolean
-    default: false
-    label:
-      zh_Hans: 联网搜索
-      en_US: Web Search
-    help:
-      zh_Hans: 模型内置了互联网搜索服务，该参数控制模型在生成文本时是否参考使用互联网搜索结果。启用互联网搜索，模型会将搜索结果作为文本生成过程中的参考信息，但模型会基于其内部逻辑“自行判断”是否使用互联网搜索结果。
-      en_US: The model has a built-in Internet search service. This parameter controls whether the model refers to Internet search results when generating text. When Internet search is enabled, the model will use the search results as reference information in the text generation process, but the model will "judge" whether to use Internet search results based on its internal logic.
  - name: response_format
    use_template: response_format
 pricing:
--- a/api/core/model_runtime/model_providers/tongyi/llm/qwen-max-0403.yaml
+++ b/api/core/model_runtime/model_providers/tongyi/llm/qwen-max-0403.yaml
@@ -69,15 +69,6 @@ parameter_rules:
    help:
      zh_Hans: 用于控制模型生成时的重复度。提高repetition_penalty时可以降低模型生成的重复度。1.0表示不做惩罚。
      en_US: Used to control the repeatability when generating models. Increasing repetition_penalty can reduce the duplication of model generation. 1.0 means no punishment.
-  - name: enable_search
-    type: boolean
-    default: false
-    label:
-      zh_Hans: 联网搜索
-      en_US: Web Search
-    help:
-      zh_Hans: 模型内置了互联网搜索服务，该参数控制模型在生成文本时是否参考使用互联网搜索结果。启用互联网搜索，模型会将搜索结果作为文本生成过程中的参考信息，但模型会基于其内部逻辑“自行判断”是否使用互联网搜索结果。
-      en_US: The model has a built-in Internet search service. This parameter controls whether the model refers to Internet search results when generating text. When Internet search is enabled, the model will use the search results as reference information in the text generation process, but the model will "judge" whether to use Internet search results based on its internal logic.
  - name: response_format
    use_template: response_format
 pricing:
--- a/api/core/model_runtime/model_providers/tongyi/llm/qwen-max-0428.yaml
+++ b/api/core/model_runtime/model_providers/tongyi/llm/qwen-max-0428.yaml
@@ -69,15 +69,6 @@ parameter_rules:
    help:
      zh_Hans: 用于控制模型生成时的重复度。提高repetition_penalty时可以降低模型生成的重复度。1.0表示不做惩罚。
      en_US: Used to control the repeatability when generating models. Increasing repetition_penalty can reduce the duplication of model generation. 1.0 means no punishment.
-  - name: enable_search
-    type: boolean
-    default: false
-    label:
-      zh_Hans: 联网搜索
-      en_US: Web Search
-    help:
-      zh_Hans: 模型内置了互联网搜索服务，该参数控制模型在生成文本时是否参考使用互联网搜索结果。启用互联网搜索，模型会将搜索结果作为文本生成过程中的参考信息，但模型会基于其内部逻辑“自行判断”是否使用互联网搜索结果。
-      en_US: The model has a built-in Internet search service. This parameter controls whether the model refers to Internet search results when generating text. When Internet search is enabled, the model will use the search results as reference information in the text generation process, but the model will "judge" whether to use Internet search results based on its internal logic.
  - name: response_format
    use_template: response_format
 pricing:
--- a/api/core/model_runtime/model_providers/tongyi/llm/qwen-max-0919.yaml
+++ b/api/core/model_runtime/model_providers/tongyi/llm/qwen-max-0919.yaml
@@ -69,15 +69,6 @@ parameter_rules:
    help:
      zh_Hans: 用于控制模型生成时的重复度。提高repetition_penalty时可以降低模型生成的重复度。1.0表示不做惩罚。
      en_US: Used to control the repeatability when generating models. Increasing repetition_penalty can reduce the duplication of model generation. 1.0 means no punishment.
-  - name: enable_search
-    type: boolean
-    default: false
-    label:
-      zh_Hans: 联网搜索
-      en_US: Web Search
-    help:
-      zh_Hans: 模型内置了互联网搜索服务，该参数控制模型在生成文本时是否参考使用互联网搜索结果。启用互联网搜索，模型会将搜索结果作为文本生成过程中的参考信息，但模型会基于其内部逻辑“自行判断”是否使用互联网搜索结果。
-      en_US: The model has a built-in Internet search service. This parameter controls whether the model refers to Internet search results when generating text. When Internet search is enabled, the model will use the search results as reference information in the text generation process, but the model will "judge" whether to use Internet search results based on its internal logic.
  - name: response_format
    use_template: response_format
 pricing:
--- a/api/core/model_runtime/model_providers/tongyi/llm/qwen-max-1201.yaml
+++ b/api/core/model_runtime/model_providers/tongyi/llm/qwen-max-1201.yaml
@@ -68,15 +68,6 @@ parameter_rules:
    help:
      zh_Hans: 用于控制模型生成时的重复度。提高repetition_penalty时可以降低模型生成的重复度。1.0表示不做惩罚。
      en_US: Used to control the repeatability when generating models. Increasing repetition_penalty can reduce the duplication of model generation. 1.0 means no punishment.
-  - name: enable_search
-    type: boolean
-    default: false
-    label:
-      zh_Hans: 联网搜索
-      en_US: Web Search
-    help:
-      zh_Hans: 模型内置了互联网搜索服务，该参数控制模型在生成文本时是否参考使用互联网搜索结果。启用互联网搜索，模型会将搜索结果作为文本生成过程中的参考信息，但模型会基于其内部逻辑“自行判断”是否使用互联网搜索结果。
-      en_US: The model has a built-in Internet search service. This parameter controls whether the model refers to Internet search results when generating text. When Internet search is enabled, the model will use the search results as reference information in the text generation process, but the model will "judge" whether to use Internet search results based on its internal logic.
  - name: response_format
    use_template: response_format
 pricing:
--- a/api/core/model_runtime/model_providers/tongyi/llm/qwen-max-latest.yaml
+++ b/api/core/model_runtime/model_providers/tongyi/llm/qwen-max-latest.yaml
@@ -69,15 +69,6 @@ parameter_rules:
    help:
      zh_Hans: 用于控制模型生成时的重复度。提高repetition_penalty时可以降低模型生成的重复度。1.0表示不做惩罚。
      en_US: Used to control the repeatability when generating models. Increasing repetition_penalty can reduce the duplication of model generation. 1.0 means no punishment.
-  - name: enable_search
-    type: boolean
-    default: false
-    label:
-      zh_Hans: 联网搜索
-      en_US: Web Search
-    help:
-      zh_Hans: 模型内置了互联网搜索服务，该参数控制模型在生成文本时是否参考使用互联网搜索结果。启用互联网搜索，模型会将搜索结果作为文本生成过程中的参考信息，但模型会基于其内部逻辑“自行判断”是否使用互联网搜索结果。
-      en_US: The model has a built-in Internet search service. This parameter controls whether the model refers to Internet search results when generating text. When Internet search is enabled, the model will use the search results as reference information in the text generation process, but the model will "judge" whether to use Internet search results based on its internal logic.
  - name: response_format
    use_template: response_format
 pricing:
--- a/api/core/model_runtime/model_providers/tongyi/llm/qwen-max-longcontext.yaml
+++ b/api/core/model_runtime/model_providers/tongyi/llm/qwen-max-longcontext.yaml
@@ -69,15 +69,6 @@ parameter_rules:
    help:
      zh_Hans: 用于控制模型生成时的重复度。提高repetition_penalty时可以降低模型生成的重复度。1.0表示不做惩罚。
      en_US: Used to control the repeatability when generating models. Increasing repetition_penalty can reduce the duplication of model generation. 1.0 means no punishment.
-  - name: enable_search
-    type: boolean
-    default: false
-    label:
-      zh_Hans: 联网搜索
-      en_US: Web Search
-    help:
-      zh_Hans: 模型内置了互联网搜索服务，该参数控制模型在生成文本时是否参考使用互联网搜索结果。启用互联网搜索，模型会将搜索结果作为文本生成过程中的参考信息，但模型会基于其内部逻辑“自行判断”是否使用互联网搜索结果。
-      en_US: The model has a built-in Internet search service. This parameter controls whether the model refers to Internet search results when generating text. When Internet search is enabled, the model will use the search results as reference information in the text generation process, but the model will "judge" whether to use Internet search results based on its internal logic.
  - name: response_format
    use_template: response_format
 pricing:
--- a/api/core/model_runtime/model_providers/tongyi/llm/qwen-plus-0206.yaml
+++ b/api/core/model_runtime/model_providers/tongyi/llm/qwen-plus-0206.yaml
@@ -67,15 +67,6 @@ parameter_rules:
    help:
      zh_Hans: 用于控制模型生成时的重复度。提高repetition_penalty时可以降低模型生成的重复度。1.0表示不做惩罚。
      en_US: Used to control the repeatability when generating models. Increasing repetition_penalty can reduce the duplication of model generation. 1.0 means no punishment.
-  - name: enable_search
-    type: boolean
-    default: false
-    label:
-      zh_Hans: 联网搜索
-      en_US: Web Search
-    help:
-      zh_Hans: 模型内置了互联网搜索服务，该参数控制模型在生成文本时是否参考使用互联网搜索结果。启用互联网搜索，模型会将搜索结果作为文本生成过程中的参考信息，但模型会基于其内部逻辑“自行判断”是否使用互联网搜索结果。
-      en_US: The model has a built-in Internet search service. This parameter controls whether the model refers to Internet search results when generating text. When Internet search is enabled, the model will use the search results as reference information in the text generation process, but the model will "judge" whether to use Internet search results based on its internal logic.
  - name: response_format
    use_template: response_format
 pricing:
--- a/api/core/model_runtime/model_providers/tongyi/llm/qwen-plus-0624.yaml
+++ b/api/core/model_runtime/model_providers/tongyi/llm/qwen-plus-0624.yaml
@@ -67,15 +67,6 @@ parameter_rules:
    help:
      zh_Hans: 用于控制模型生成时的重复度。提高repetition_penalty时可以降低模型生成的重复度。1.0表示不做惩罚。
      en_US: Used to control the repeatability when generating models. Increasing repetition_penalty can reduce the duplication of model generation. 1.0 means no punishment.
-  - name: enable_search
-    type: boolean
-    default: false
-    label:
-      zh_Hans: 联网搜索
-      en_US: Web Search
-    help:
-      zh_Hans: 模型内置了互联网搜索服务，该参数控制模型在生成文本时是否参考使用互联网搜索结果。启用互联网搜索，模型会将搜索结果作为文本生成过程中的参考信息，但模型会基于其内部逻辑“自行判断”是否使用互联网搜索结果。
-      en_US: The model has a built-in Internet search service. This parameter controls whether the model refers to Internet search results when generating text. When Internet search is enabled, the model will use the search results as reference information in the text generation process, but the model will "judge" whether to use Internet search results based on its internal logic.
  - name: response_format
    use_template: response_format
 pricing:
--- a/api/core/model_runtime/model_providers/tongyi/llm/qwen-plus-0723.yaml
+++ b/api/core/model_runtime/model_providers/tongyi/llm/qwen-plus-0723.yaml
@@ -67,15 +67,6 @@ parameter_rules:
    help:
      zh_Hans: 用于控制模型生成时的重复度。提高repetition_penalty时可以降低模型生成的重复度。1.0表示不做惩罚。
      en_US: Used to control the repeatability when generating models. Increasing repetition_penalty can reduce the duplication of model generation. 1.0 means no punishment.
-  - name: enable_search
-    type: boolean
-    default: false
-    label:
-      zh_Hans: 联网搜索
-      en_US: Web Search
-    help:
-      zh_Hans: 模型内置了互联网搜索服务，该参数控制模型在生成文本时是否参考使用互联网搜索结果。启用互联网搜索，模型会将搜索结果作为文本生成过程中的参考信息，但模型会基于其内部逻辑“自行判断”是否使用互联网搜索结果。
-      en_US: The model has a built-in Internet search service. This parameter controls whether the model refers to Internet search results when generating text. When Internet search is enabled, the model will use the search results as reference information in the text generation process, but the model will "judge" whether to use Internet search results based on its internal logic.
  - name: response_format
    use_template: response_format
 pricing:
--- a/api/core/model_runtime/model_providers/tongyi/llm/qwen-plus-0806.yaml
+++ b/api/core/model_runtime/model_providers/tongyi/llm/qwen-plus-0806.yaml
@@ -67,15 +67,6 @@ parameter_rules:
    help:
      zh_Hans: 用于控制模型生成时的重复度。提高repetition_penalty时可以降低模型生成的重复度。1.0表示不做惩罚。
      en_US: Used to control the repeatability when generating models. Increasing repetition_penalty can reduce the duplication of model generation. 1.0 means no punishment.
-  - name: enable_search
-    type: boolean
-    default: false
-    label:
-      zh_Hans: 联网搜索
-      en_US: Web Search
-    help:
-      zh_Hans: 模型内置了互联网搜索服务，该参数控制模型在生成文本时是否参考使用互联网搜索结果。启用互联网搜索，模型会将搜索结果作为文本生成过程中的参考信息，但模型会基于其内部逻辑“自行判断”是否使用互联网搜索结果。
-      en_US: The model has a built-in Internet search service. This parameter controls whether the model refers to Internet search results when generating text. When Internet search is enabled, the model will use the search results as reference information in the text generation process, but the model will "judge" whether to use Internet search results based on its internal logic.
  - name: response_format
    use_template: response_format
 pricing:
--- a/api/core/model_runtime/model_providers/tongyi/llm/qwen-plus-0919.yaml
+++ b/api/core/model_runtime/model_providers/tongyi/llm/qwen-plus-0919.yaml
@@ -67,15 +67,6 @@ parameter_rules:
    help:
      zh_Hans: 用于控制模型生成时的重复度。提高repetition_penalty时可以降低模型生成的重复度。1.0表示不做惩罚。
      en_US: Used to control the repeatability when generating models. Increasing repetition_penalty can reduce the duplication of model generation. 1.0 means no punishment.
-  - name: enable_search
-    type: boolean
-    default: false
-    label:
-      zh_Hans: 联网搜索
-      en_US: Web Search
-    help:
-      zh_Hans: 模型内置了互联网搜索服务，该参数控制模型在生成文本时是否参考使用互联网搜索结果。启用互联网搜索，模型会将搜索结果作为文本生成过程中的参考信息，但模型会基于其内部逻辑“自行判断”是否使用互联网搜索结果。
-      en_US: The model has a built-in Internet search service. This parameter controls whether the model refers to Internet search results when generating text. When Internet search is enabled, the model will use the search results as reference information in the text generation process, but the model will "judge" whether to use Internet search results based on its internal logic.
  - name: response_format
    use_template: response_format
 pricing:
--- a/api/core/model_runtime/model_providers/tongyi/llm/qwen-plus-chat.yaml
+++ b/api/core/model_runtime/model_providers/tongyi/llm/qwen-plus-chat.yaml
@@ -69,15 +69,6 @@ parameter_rules:
    help:
      zh_Hans: 用于控制模型生成时的重复度。提高repetition_penalty时可以降低模型生成的重复度。1.0表示不做惩罚。
      en_US: Used to control the repeatability when generating models. Increasing repetition_penalty can reduce the duplication of model generation. 1.0 means no punishment.
-  - name: enable_search
-    type: boolean
-    default: false
-    label:
-      zh_Hans: 联网搜索
-      en_US: Web Search
-    help:
-      zh_Hans: 模型内置了互联网搜索服务，该参数控制模型在生成文本时是否参考使用互联网搜索结果。启用互联网搜索，模型会将搜索结果作为文本生成过程中的参考信息，但模型会基于其内部逻辑“自行判断”是否使用互联网搜索结果。
-      en_US: The model has a built-in Internet search service. This parameter controls whether the model refers to Internet search results when generating text. When Internet search is enabled, the model will use the search results as reference information in the text generation process, but the model will "judge" whether to use Internet search results based on its internal logic.
  - name: response_format
    use_template: response_format
 pricing:
--- a/api/core/model_runtime/model_providers/tongyi/llm/qwen-plus-latest.yaml
+++ b/api/core/model_runtime/model_providers/tongyi/llm/qwen-plus-latest.yaml
@@ -67,15 +67,6 @@ parameter_rules:
    help:
      zh_Hans: 用于控制模型生成时的重复度。提高repetition_penalty时可以降低模型生成的重复度。1.0表示不做惩罚。
      en_US: Used to control the repeatability when generating models. Increasing repetition_penalty can reduce the duplication of model generation. 1.0 means no punishment.
-  - name: enable_search
-    type: boolean
-    default: false
-    label:
-      zh_Hans: 联网搜索
-      en_US: Web Search
-    help:
-      zh_Hans: 模型内置了互联网搜索服务，该参数控制模型在生成文本时是否参考使用互联网搜索结果。启用互联网搜索，模型会将搜索结果作为文本生成过程中的参考信息，但模型会基于其内部逻辑“自行判断”是否使用互联网搜索结果。
-      en_US: The model has a built-in Internet search service. This parameter controls whether the model refers to Internet search results when generating text. When Internet search is enabled, the model will use the search results as reference information in the text generation process, but the model will "judge" whether to use Internet search results based on its internal logic.
  - name: response_format
    use_template: response_format
 pricing:
--- a/api/core/model_runtime/model_providers/tongyi/llm/qwen-turbo-0206.yaml
+++ b/api/core/model_runtime/model_providers/tongyi/llm/qwen-turbo-0206.yaml
@@ -68,15 +68,6 @@ parameter_rules:
    help:
      zh_Hans: 用于控制模型生成时的重复度。提高repetition_penalty时可以降低模型生成的重复度。1.0表示不做惩罚。
      en_US: Used to control the repeatability when generating models. Increasing repetition_penalty can reduce the duplication of model generation. 1.0 means no punishment.
-  - name: enable_search
-    type: boolean
-    default: false
-    label:
-      zh_Hans: 联网搜索
-      en_US: Web Search
-    help:
-      zh_Hans: 模型内置了互联网搜索服务，该参数控制模型在生成文本时是否参考使用互联网搜索结果。启用互联网搜索，模型会将搜索结果作为文本生成过程中的参考信息，但模型会基于其内部逻辑“自行判断”是否使用互联网搜索结果。
-      en_US: The model has a built-in Internet search service. This parameter controls whether the model refers to Internet search results when generating text. When Internet search is enabled, the model will use the search results as reference information in the text generation process, but the model will "judge" whether to use Internet search results based on its internal logic.
  - name: response_format
    use_template: response_format
 pricing:
--- a/api/core/model_runtime/model_providers/tongyi/llm/qwen-turbo-0624.yaml
+++ b/api/core/model_runtime/model_providers/tongyi/llm/qwen-turbo-0624.yaml
@@ -67,15 +67,6 @@ parameter_rules:
    help:
      zh_Hans: 用于控制模型生成时的重复度。提高repetition_penalty时可以降低模型生成的重复度。1.0表示不做惩罚。
      en_US: Used to control the repeatability when generating models. Increasing repetition_penalty can reduce the duplication of model generation. 1.0 means no punishment.
-  - name: enable_search
-    type: boolean
-    default: false
-    label:
-      zh_Hans: 联网搜索
-      en_US: Web Search
-    help:
-      zh_Hans: 模型内置了互联网搜索服务，该参数控制模型在生成文本时是否参考使用互联网搜索结果。启用互联网搜索，模型会将搜索结果作为文本生成过程中的参考信息，但模型会基于其内部逻辑“自行判断”是否使用互联网搜索结果。
-      en_US: The model has a built-in Internet search service. This parameter controls whether the model refers to Internet search results when generating text. When Internet search is enabled, the model will use the search results as reference information in the text generation process, but the model will "judge" whether to use Internet search results based on its internal logic.
  - name: response_format
    use_template: response_format
 pricing:
--- a/api/core/model_runtime/model_providers/tongyi/llm/qwen-turbo-0919.yaml
+++ b/api/core/model_runtime/model_providers/tongyi/llm/qwen-turbo-0919.yaml
@@ -67,15 +67,6 @@ parameter_rules:
    help:
      zh_Hans: 用于控制模型生成时的重复度。提高repetition_penalty时可以降低模型生成的重复度。1.0表示不做惩罚。
      en_US: Used to control the repeatability when generating models. Increasing repetition_penalty can reduce the duplication of model generation. 1.0 means no punishment.
-  - name: enable_search
-    type: boolean
-    default: false
-    label:
-      zh_Hans: 联网搜索
-      en_US: Web Search
-    help:
-      zh_Hans: 模型内置了互联网搜索服务，该参数控制模型在生成文本时是否参考使用互联网搜索结果。启用互联网搜索，模型会将搜索结果作为文本生成过程中的参考信息，但模型会基于其内部逻辑“自行判断”是否使用互联网搜索结果。
-      en_US: The model has a built-in Internet search service. This parameter controls whether the model refers to Internet search results when generating text. When Internet search is enabled, the model will use the search results as reference information in the text generation process, but the model will "judge" whether to use Internet search results based on its internal logic.
  - name: response_format
    use_template: response_format
 pricing:
--- a/api/core/model_runtime/model_providers/tongyi/llm/qwen-turbo-chat.yaml
+++ b/api/core/model_runtime/model_providers/tongyi/llm/qwen-turbo-chat.yaml
@@ -69,15 +69,6 @@ parameter_rules:
    help:
      zh_Hans: 用于控制模型生成时的重复度。提高repetition_penalty时可以降低模型生成的重复度。1.0表示不做惩罚。
      en_US: Used to control the repeatability when generating models. Increasing repetition_penalty can reduce the duplication of model generation. 1.0 means no punishment.
-  - name: enable_search
-    type: boolean
-    default: false
-    label:
-      zh_Hans: 联网搜索
-      en_US: Web Search
-    help:
-      zh_Hans: 模型内置了互联网搜索服务，该参数控制模型在生成文本时是否参考使用互联网搜索结果。启用互联网搜索，模型会将搜索结果作为文本生成过程中的参考信息，但模型会基于其内部逻辑“自行判断”是否使用互联网搜索结果。
-      en_US: The model has a built-in Internet search service. This parameter controls whether the model refers to Internet search results when generating text. When Internet search is enabled, the model will use the search results as reference information in the text generation process, but the model will "judge" whether to use Internet search results based on its internal logic.
  - name: response_format
    use_template: response_format
 pricing:
--- a/api/core/model_runtime/model_providers/tongyi/llm/qwen-turbo-latest.yaml
+++ b/api/core/model_runtime/model_providers/tongyi/llm/qwen-turbo-latest.yaml
@@ -67,15 +67,6 @@ parameter_rules:
    help:
      zh_Hans: 用于控制模型生成时的重复度。提高repetition_penalty时可以降低模型生成的重复度。1.0表示不做惩罚。
      en_US: Used to control the repeatability when generating models. Increasing repetition_penalty can reduce the duplication of model generation. 1.0 means no punishment.
-  - name: enable_search
-    type: boolean
-    default: false
-    label:
-      zh_Hans: 联网搜索
-      en_US: Web Search
-    help:
-      zh_Hans: 模型内置了互联网搜索服务，该参数控制模型在生成文本时是否参考使用互联网搜索结果。启用互联网搜索，模型会将搜索结果作为文本生成过程中的参考信息，但模型会基于其内部逻辑“自行判断”是否使用互联网搜索结果。
-      en_US: The model has a built-in Internet search service. This parameter controls whether the model refers to Internet search results when generating text. When Internet search is enabled, the model will use the search results as reference information in the text generation process, but the model will "judge" whether to use Internet search results based on its internal logic.
  - name: response_format
    use_template: response_format
 pricing:
--- a/api/core/model_runtime/model_providers/vertex_ai/llm/gemini-2.0-flash-001.yaml
+++ b/api/core/model_runtime/model_providers/vertex_ai/llm/gemini-2.0-flash-001.yaml
@@ -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
--- a/api/core/model_runtime/model_providers/vertex_ai/llm/gemini-2.0-flash-lite-preview-02-05.yaml
+++ b/api/core/model_runtime/model_providers/vertex_ai/llm/gemini-2.0-flash-lite-preview-02-05.yaml
@@ -1,41 +0,0 @@
-model: gemini-2.0-flash-lite-preview-02-05
-label:
-  en_US: Gemini 2.0 Flash Lite Preview 0205
-model_type: llm
-features:
-  - agent-thought
-  - vision
-  - tool-call
-  - stream-tool-call
-  - document
-  - video
-  - audio
-model_properties:
-  mode: chat
-  context_size: 1048576
-parameter_rules:
-  - name: temperature
-    use_template: temperature
-  - name: top_p
-    use_template: top_p
-  - name: top_k
-    label:
-      zh_Hans: 取样数量
-      en_US: Top k
-    type: int
-    help:
-      zh_Hans: 仅从每个后续标记的前 K 个选项中采样。
-      en_US: Only sample from the top K options for each subsequent token.
-    required: false
-  - name: max_output_tokens
-    use_template: max_tokens
-    default: 8192
-    min: 1
-    max: 8192
-  - name: json_schema
-    use_template: json_schema
-pricing:
-  input: '0.00'
-  output: '0.00'
-  unit: '0.000001'
-  currency: USD
--- a/api/core/model_runtime/model_providers/vertex_ai/llm/gemini-2.0-flash-thinking-exp-01-21.yaml
+++ b/api/core/model_runtime/model_providers/vertex_ai/llm/gemini-2.0-flash-thinking-exp-01-21.yaml
@@ -1,39 +0,0 @@
-model: gemini-2.0-flash-thinking-exp-01-21
-label:
-  en_US: Gemini 2.0 Flash Thinking Exp 0121
-model_type: llm
-features:
-  - agent-thought
-  - vision
-  - document
-  - video
-  - audio
-model_properties:
-  mode: chat
-  context_size: 32767
-parameter_rules:
-  - name: temperature
-    use_template: temperature
-  - name: top_p
-    use_template: top_p
-  - name: top_k
-    label:
-      zh_Hans: 取样数量
-      en_US: Top k
-    type: int
-    help:
-      zh_Hans: 仅从每个后续标记的前 K 个选项中采样。
-      en_US: Only sample from the top K options for each subsequent token.
-    required: false
-  - name: max_output_tokens
-    use_template: max_tokens
-    default: 8192
-    min: 1
-    max: 8192
-  - name: json_schema
-    use_template: json_schema
-pricing:
-  input: '0.00'
-  output: '0.00'
-  unit: '0.000001'
-  currency: USD
--- a/api/core/model_runtime/model_providers/vertex_ai/llm/gemini-2.0-flash-thinking-exp-1219.yaml
+++ b/api/core/model_runtime/model_providers/vertex_ai/llm/gemini-2.0-flash-thinking-exp-1219.yaml
@@ -1,39 +0,0 @@
-model: gemini-2.0-flash-thinking-exp-1219
-label:
-  en_US: Gemini 2.0 Flash Thinking Exp 1219
-model_type: llm
-features:
-  - agent-thought
-  - vision
-  - document
-  - video
-  - audio
-model_properties:
-  mode: chat
-  context_size: 32767
-parameter_rules:
-  - name: temperature
-    use_template: temperature
-  - name: top_p
-    use_template: top_p
-  - name: top_k
-    label:
-      zh_Hans: 取样数量
-      en_US: Top k
-    type: int
-    help:
-      zh_Hans: 仅从每个后续标记的前 K 个选项中采样。
-      en_US: Only sample from the top K options for each subsequent token.
-    required: false
-  - name: max_output_tokens
-    use_template: max_tokens
-    default: 8192
-    min: 1
-    max: 8192
-  - name: json_schema
-    use_template: json_schema
-pricing:
-  input: '0.00'
-  output: '0.00'
-  unit: '0.000001'
-  currency: USD
--- a/api/core/model_runtime/model_providers/vertex_ai/llm/gemini-2.0-pro-exp-02-05.yaml
+++ b/api/core/model_runtime/model_providers/vertex_ai/llm/gemini-2.0-pro-exp-02-05.yaml
@@ -1,37 +0,0 @@
-model: gemini-2.0-pro-exp-02-05
-label:
-  en_US: Gemini 2.0 Pro Exp 0205
-model_type: llm
-features:
-  - agent-thought
-  - document
-model_properties:
-  mode: chat
-  context_size: 2000000
-parameter_rules:
-  - name: temperature
-    use_template: temperature
-  - name: top_p
-    use_template: top_p
-  - name: top_k
-    label:
-      en_US: Top k
-    type: int
-    help:
-      en_US: Only sample from the top K options for each subsequent token.
-    required: false
-  - name: presence_penalty
-    use_template: presence_penalty
-  - name: frequency_penalty
-    use_template: frequency_penalty
-  - name: max_output_tokens
-    use_template: max_tokens
-    required: true
-    default: 8192
-    min: 1
-    max: 8192
-pricing:
-  input: '0.00'
-  output: '0.00'
-  unit: '0.000001'
-  currency: USD
--- a/api/core/model_runtime/model_providers/vertex_ai/llm/gemini-exp-1114.yaml
+++ b/api/core/model_runtime/model_providers/vertex_ai/llm/gemini-exp-1114.yaml
@@ -1,41 +0,0 @@
-model: gemini-exp-1114
-label:
-  en_US: Gemini exp 1114
-model_type: llm
-features:
-  - agent-thought
-  - vision
-  - tool-call
-  - stream-tool-call
-  - document
-  - video
-  - audio
-model_properties:
-  mode: chat
-  context_size: 32767
-parameter_rules:
-  - name: temperature
-    use_template: temperature
-  - name: top_p
-    use_template: top_p
-  - name: top_k
-    label:
-      zh_Hans: 取样数量
-      en_US: Top k
-    type: int
-    help:
-      zh_Hans: 仅从每个后续标记的前 K 个选项中采样。
-      en_US: Only sample from the top K options for each subsequent token.
-    required: false
-  - name: max_output_tokens
-    use_template: max_tokens
-    default: 8192
-    min: 1
-    max: 8192
-  - name: json_schema
-    use_template: json_schema
-pricing:
-  input: '0.00'
-  output: '0.00'
-  unit: '0.000001'
-  currency: USD
--- a/api/core/model_runtime/model_providers/vertex_ai/llm/gemini-exp-1121.yaml
+++ b/api/core/model_runtime/model_providers/vertex_ai/llm/gemini-exp-1121.yaml
@@ -1,41 +0,0 @@
-model: gemini-exp-1121
-label:
-  en_US: Gemini exp 1121
-model_type: llm
-features:
-  - agent-thought
-  - vision
-  - tool-call
-  - stream-tool-call
-  - document
-  - video
-  - audio
-model_properties:
-  mode: chat
-  context_size: 32767
-parameter_rules:
-  - name: temperature
-    use_template: temperature
-  - name: top_p
-    use_template: top_p
-  - name: top_k
-    label:
-      zh_Hans: 取样数量
-      en_US: Top k
-    type: int
-    help:
-      zh_Hans: 仅从每个后续标记的前 K 个选项中采样。
-      en_US: Only sample from the top K options for each subsequent token.
-    required: false
-  - name: max_output_tokens
-    use_template: max_tokens
-    default: 8192
-    min: 1
-    max: 8192
-  - name: json_schema
-    use_template: json_schema
-pricing:
-  input: '0.00'
-  output: '0.00'
-  unit: '0.000001'
-  currency: USD
--- a/api/core/model_runtime/model_providers/vertex_ai/llm/gemini-exp-1206.yaml
+++ b/api/core/model_runtime/model_providers/vertex_ai/llm/gemini-exp-1206.yaml
@@ -1,41 +0,0 @@
-model: gemini-exp-1206
-label:
-  en_US: Gemini exp 1206
-model_type: llm
-features:
-  - agent-thought
-  - vision
-  - tool-call
-  - stream-tool-call
-  - document
-  - video
-  - audio
-model_properties:
-  mode: chat
-  context_size: 2097152
-parameter_rules:
-  - name: temperature
-    use_template: temperature
-  - name: top_p
-    use_template: top_p
-  - name: top_k
-    label:
-      zh_Hans: 取样数量
-      en_US: Top k
-    type: int
-    help:
-      zh_Hans: 仅从每个后续标记的前 K 个选项中采样。
-      en_US: Only sample from the top K options for each subsequent token.
-    required: false
-  - name: max_output_tokens
-    use_template: max_tokens
-    default: 8192
-    min: 1
-    max: 8192
-  - name: json_schema
-    use_template: json_schema
-pricing:
-  input: '0.00'
-  output: '0.00'
-  unit: '0.000001'
-  currency: USD
--- a/api/core/model_runtime/model_providers/volcengine_maas/llm/llm.py
+++ b/api/core/model_runtime/model_providers/volcengine_maas/llm/llm.py
@@ -1,5 +1,4 @@
 import logging
-import re
 from collections.abc import Generator
 from typing import Optional

@@ -248,34 +247,15 @@ class VolcengineMaaSLargeLanguageModel(LargeLanguageModel):
            req_params["tools"] = tools

        def _handle_stream_chat_response(chunks: Generator[ChatCompletionChunk]) -> Generator:
-            is_reasoning_started = False
            for chunk in chunks:
-                content = ""
-                if chunk.choices:
-                    delta = chunk.choices[0].delta
-                    if is_reasoning_started and not hasattr(delta, "reasoning_content") and not delta.content:
-                        content = ""
-                    elif hasattr(delta, "reasoning_content"):
-                        if not is_reasoning_started:
-                            is_reasoning_started = True
-                            content = "> 💭 " + delta.reasoning_content
-                        else:
-                            content = delta.reasoning_content
-
-                        if "\n" in content:
-                            content = re.sub(r"\n(?!(>|\n))", "\n> ", content)
-                    elif is_reasoning_started:
-                        content = "\n\n" + delta.content
-                        is_reasoning_started = False
-                    else:
-                        content = delta.content
-
                yield LLMResultChunk(
                    model=model,
                    prompt_messages=prompt_messages,
                    delta=LLMResultChunkDelta(
                        index=0,
-                        message=AssistantPromptMessage(content=content, tool_calls=[]),
+                        message=AssistantPromptMessage(
+                            content=chunk.choices[0].delta.content if chunk.choices else "", tool_calls=[]
+                        ),
                        usage=self._calc_response_usage(
                            model=model,
                            credentials=credentials,
--- a/api/core/model_runtime/model_providers/volcengine_maas/llm/models.py
+++ b/api/core/model_runtime/model_providers/volcengine_maas/llm/models.py
@@ -18,22 +18,6 @@ class ModelConfig(BaseModel):


 configs: dict[str, ModelConfig] = {
-    "DeepSeek-R1-Distill-Qwen-32B": ModelConfig(
-        properties=ModelProperties(context_size=64000, max_tokens=8192, mode=LLMMode.CHAT),
-        features=[ModelFeature.AGENT_THOUGHT],
-    ),
-    "DeepSeek-R1-Distill-Qwen-7B": ModelConfig(
-        properties=ModelProperties(context_size=64000, max_tokens=8192, mode=LLMMode.CHAT),
-        features=[ModelFeature.AGENT_THOUGHT],
-    ),
-    "DeepSeek-R1": ModelConfig(
-        properties=ModelProperties(context_size=64000, max_tokens=8192, mode=LLMMode.CHAT),
-        features=[ModelFeature.AGENT_THOUGHT],
-    ),
-    "DeepSeek-V3": ModelConfig(
-        properties=ModelProperties(context_size=64000, max_tokens=8192, mode=LLMMode.CHAT),
-        features=[ModelFeature.AGENT_THOUGHT, ModelFeature.TOOL_CALL, ModelFeature.STREAM_TOOL_CALL],
-    ),
    "Doubao-1.5-vision-pro-32k": ModelConfig(
        properties=ModelProperties(context_size=32768, max_tokens=12288, mode=LLMMode.CHAT),
        features=[ModelFeature.AGENT_THOUGHT, ModelFeature.VISION],
--- a/api/core/model_runtime/model_providers/volcengine_maas/volcengine_maas.yaml
+++ b/api/core/model_runtime/model_providers/volcengine_maas/volcengine_maas.yaml
@@ -118,30 +118,6 @@ model_credential_schema:
      type: select
      required: true
      options:
-        - label:
-            en_US: DeepSeek-R1-Distill-Qwen-32B
-          value: DeepSeek-R1-Distill-Qwen-32B
-          show_on:
-            - variable: __model_type
-              value: llm
-        - label:
-            en_US: DeepSeek-R1-Distill-Qwen-7B
-          value: DeepSeek-R1-Distill-Qwen-7B
-          show_on:
-            - variable: __model_type
-              value: llm
-        - label:
-            en_US: DeepSeek-R1
-          value: DeepSeek-R1
-          show_on:
-            - variable: __model_type
-              value: llm
-        - label:
-            en_US: DeepSeek-V3
-          value: DeepSeek-V3
-          show_on:
-            - variable: __model_type
-              value: llm
        - label:
            en_US: Doubao-1.5-vision-pro-32k
          value: Doubao-1.5-vision-pro-32k
--- a/Show More
+++ b/Show More
Author	SHA1	Message	Date
NFish	8c1bca3119	fix: eslint run failed	2025-02-14 15:01:02 +08:00
NFish	a8982a98f4	chore: update libs	2025-02-14 14:13:44 +08:00
NFish	130964d9a7	update eslint.config.mjs	2025-02-14 14:00:59 +08:00
NFish	1a8a1a9574	fix: ignore .storybook folder	2025-02-08 17:52:10 +08:00
NFish	20bcb49932	fix: ignore rule no-explicit-any	2025-02-08 17:50:35 +08:00
NFish	91e411bbaa	wip: update eslint config and stash	2025-02-08 15:45:16 +08:00