feat: agent node custom tool input

fix: ci
Merge branch 'plugins/beta' into dev/plugin-deploy
2025-02-07 11:02:31 +08:00 · 2025-02-06 18:36:14 +08:00 · 2025-02-06 18:30:49 +08:00 · 2025-02-06 11:29:37 +08:00 · 2025-02-05 20:28:02 +08:00 · 2025-02-05 17:45:23 +08:00
537 changed files with 8968 additions and 4845 deletions
@@ -8,7 +8,7 @@ inputs:
  poetry-version:
    description: Poetry version to set up
    required: true
-    default: '1.8.4'
+    default: '2.0.1'
  poetry-lockfile:
    description: Path to the Poetry lockfile to restore cache from
    required: true
@@ -4,6 +4,7 @@ on:
  pull_request:
    branches:
      - main
+      - plugins/beta
    paths:
      - api/**
      - docker/**
@@ -42,25 +43,17 @@ jobs:
        run: poetry install -C api --with dev

      - name: Check dependencies in pyproject.toml
-        run: poetry run -C api bash dev/pytest/pytest_artifacts.sh
+        run: poetry run -P api bash dev/pytest/pytest_artifacts.sh

      - name: Run Unit tests
-        run: poetry run -C api bash dev/pytest/pytest_unit_tests.sh
-
-      - name: Run ModelRuntime
-        run: poetry run -C api bash dev/pytest/pytest_model_runtime.sh
+        run: poetry run -P api bash dev/pytest/pytest_unit_tests.sh

      - name: Run dify config tests
-        run: poetry run -C api python dev/pytest/pytest_config_tests.py
-
-      - name: Run Tool
-        run: poetry run -C api bash dev/pytest/pytest_tools.sh
+        run: poetry run -P api python dev/pytest/pytest_config_tests.py

      - name: Run mypy
        run: |
-          pushd api
-          poetry run python -m mypy --install-types --non-interactive .
-          popd
+          poetry run -C api python -m mypy --install-types --non-interactive .

      - name: Set up dotenvs
        run: |
@@ -80,4 +73,4 @@ jobs:
            ssrf_proxy

      - name: Run Workflow
-        run: poetry run -C api bash dev/pytest/pytest_workflow.sh
+        run: poetry run -P api bash dev/pytest/pytest_workflow.sh
@@ -5,6 +5,7 @@ on:
    branches:
      - "main"
      - "deploy/dev"
+      - "plugins/beta"
      - "dev/plugin-deploy"
  release:
    types: [published]
@@ -4,6 +4,7 @@ on:
  pull_request:
    branches:
      - main
+      - plugins/beta
    paths:
      - api/migrations/**
      - .github/workflows/db-migration-test.yml
@@ -4,6 +4,7 @@ on:
  pull_request:
    branches:
      - main
+      - plugins/beta

 concurrency:
  group: style-${{ github.head_ref || github.run_id }}
@@ -38,12 +39,12 @@ jobs:
        if: steps.changed-files.outputs.any_changed == 'true'
        run: |
          poetry run -C api ruff --version
-          poetry run -C api ruff check ./api
-          poetry run -C api ruff format --check ./api
+          poetry run -C api ruff check ./
+          poetry run -C api ruff format --check ./

      - name: Dotenv check
        if: steps.changed-files.outputs.any_changed == 'true'
-        run: poetry run -C api dotenv-linter ./api/.env.example ./web/.env.example
+        run: poetry run -P api dotenv-linter ./api/.env.example ./web/.env.example

      - name: Lint hints
        if: failure()
@@ -66,6 +67,12 @@ jobs:
        with:
          files: web/**

+      - name: Install pnpm
+        uses: pnpm/action-setup@v4
+        with:
+          version: 10
+          run_install: false
+
      - name: Setup NodeJS
        uses: actions/setup-node@v4
        if: steps.changed-files.outputs.any_changed == 'true'
@@ -80,7 +87,7 @@ jobs:

      - name: Web style check
        if: steps.changed-files.outputs.any_changed == 'true'
-        run: pnpm run lint
+        run: yarn run lint

  docker-compose-template:
    name: Docker Compose Template
@@ -134,7 +141,7 @@ jobs:
        if: steps.changed-files.outputs.any_changed == 'true'
        env:
          BASH_SEVERITY: warning
-          DEFAULT_BRANCH: main
+          DEFAULT_BRANCH: plugins/beta
          GITHUB_TOKEN: ${{ secrets.GITHUB_TOKEN }}
          IGNORE_GENERATED_FILES: true
          IGNORE_GITIGNORED_FILES: true
@@ -70,4 +70,4 @@ jobs:
            tidb

      - name: Test Vector Stores
-        run: poetry run -C api bash dev/pytest/pytest_vdb.sh
+        run: poetry run -P api bash dev/pytest/pytest_vdb.sh
@@ -197,3 +197,6 @@ api/.vscode

 # pnpm
 /.pnpm-store
+
+# plugin migrate
+plugins.jsonl
@@ -422,8 +422,8 @@ POSITION_PROVIDER_INCLUDES=
 POSITION_PROVIDER_EXCLUDES=

 # Plugin configuration
-PLUGIN_API_KEY=lYkiYYT6owG+71oLerGzA7GXCgOT++6ovaezWAjpCjf+Sjc3ZtU+qUEi+vRjI/+XbV1AaFy691iy+kGDv2Jvy0/eAh8Y1
-PLUGIN_API_URL=http://127.0.0.1:5002
+PLUGIN_DAEMON_KEY=lYkiYYT6owG+71oLerGzA7GXCgOT++6ovaezWAjpCjf+Sjc3ZtU+qUEi
+PLUGIN_DAEMON_URL=http://127.0.0.1:5002
 PLUGIN_REMOTE_INSTALL_PORT=5003
 PLUGIN_REMOTE_INSTALL_HOST=localhost
 PLUGIN_MAX_PACKAGE_SIZE=15728640
@@ -435,7 +435,7 @@ MARKETPLACE_ENABLED=true
 MARKETPLACE_API_URL=https://marketplace.dify.ai

 # Endpoint configuration
-ENDPOINT_URL_TEMPLATE=http://localhost/e/{hook_id}
+ENDPOINT_URL_TEMPLATE=http://localhost:5002/e/{hook_id}

 # Reset password token expiry minutes
 RESET_PASSWORD_TOKEN_EXPIRY_MINUTES=5
@@ -53,10 +53,12 @@ ignore = [
    "FURB152", # math-constant
    "UP007", # non-pep604-annotation
    "UP032", # f-string
+    "UP045", # non-pep604-annotation-optional
    "B005", # strip-with-multi-characters
    "B006", # mutable-argument-default
    "B007", # unused-loop-control-variable
    "B026", # star-arg-unpacking-after-keyword-arg
+    "B903", # class-as-data-structure
    "B904", # raise-without-from-inside-except
    "B905", # zip-without-explicit-strict
    "N806", # non-lowercase-variable-in-function
@@ -4,7 +4,7 @@ FROM python:3.12-slim-bookworm AS base
 WORKDIR /app/api

 # Install Poetry
-ENV POETRY_VERSION=1.8.4
+ENV POETRY_VERSION=2.0.1

 # if you located in China, you can use aliyun mirror to speed up
 # RUN pip install --no-cache-dir poetry==${POETRY_VERSION} -i https://mirrors.aliyun.com/pypi/simple/
@@ -55,6 +55,7 @@ RUN apt-get update \
    && echo "deb http://deb.debian.org/debian testing main" > /etc/apt/sources.list \
    && apt-get update \
    # For Security
+    # && apt-get install -y --no-install-recommends expat=2.6.4-1 libldap-2.5-0=2.5.19+dfsg-1 perl=5.40.0-8 libsqlite3-0=3.46.1-1 zlib1g=1:1.3.dfsg+really1.3.1-1+b1 \
    # install a chinese font to support the use of tools like matplotlib
    && apt-get install -y fonts-noto-cjk \
    && apt-get autoremove -y \
@@ -79,5 +79,5 @@
 2. Run the tests locally with mocked system environment variables in `tool.pytest_env` section in `pyproject.toml`

   ```bash
-   poetry run -C api bash dev/pytest/pytest_all_tests.sh
+   poetry run -P api bash dev/pytest/pytest_all_tests.sh
   ```
@@ -141,10 +141,10 @@ class PluginConfig(BaseSettings):

    PLUGIN_DAEMON_URL: HttpUrl = Field(
        description="Plugin API URL",
-        default="http://plugin:5002",
+        default="http://localhost:5002",
    )

-    PLUGIN_API_KEY: str = Field(
+    PLUGIN_DAEMON_KEY: str = Field(
        description="Plugin API key",
        default="plugin-api-key",
    )
@@ -200,7 +200,7 @@ class EndpointConfig(BaseSettings):
    )

    CONSOLE_WEB_URL: str = Field(
-        description="Base URL for the console web interface," "used for frontend references and CORS configuration",
+        description="Base URL for the console web interface,used for frontend references and CORS configuration",
        default="",
    )

@@ -181,7 +181,7 @@ class HostedFetchAppTemplateConfig(BaseSettings):
    """

    HOSTED_FETCH_APP_TEMPLATES_MODE: str = Field(
-        description="Mode for fetching app templates: remote, db, or builtin" " default to remote,",
+        description="Mode for fetching app templates: remote, db, or builtin default to remote,",
        default="remote",
    )

@@ -9,7 +9,7 @@ class PackagingInfo(BaseSettings):

    CURRENT_VERSION: str = Field(
        description="Dify version",
-        default="0.15.0",
+        default="1.0.0-beta.1",
    )

    COMMIT_SHA: str = Field(
@@ -59,7 +59,7 @@ class InsertExploreAppListApi(Resource):
        with Session(db.engine) as session:
            app = session.execute(select(App).filter(App.id == args["app_id"])).scalar_one_or_none()
        if not app:
-            raise NotFound(f'App \'{args["app_id"]}\' is not found')
+            raise NotFound(f"App '{args['app_id']}' is not found")

        site = app.site
        if not site:
@@ -22,7 +22,7 @@ from controllers.console.wraps import account_initialization_required, setup_req
 from core.errors.error import ModelCurrentlyNotSupportError, ProviderTokenNotInitError, QuotaExceededError
 from core.model_runtime.errors.invoke import InvokeError
 from libs.login import login_required
-from models.model import AppMode
+from models import App, AppMode
 from services.audio_service import AudioService
 from services.errors.audio import (
    AudioTooLargeServiceError,
@@ -79,7 +79,7 @@ class ChatMessageTextApi(Resource):
    @login_required
    @account_initialization_required
    @get_app_model
-    def post(self, app_model):
+    def post(self, app_model: App):
        from werkzeug.exceptions import InternalServerError

        try:
@@ -98,9 +98,13 @@ class ChatMessageTextApi(Resource):
                and app_model.workflow.features_dict
            ):
                text_to_speech = app_model.workflow.features_dict.get("text_to_speech")
+                if text_to_speech is None:
+                    raise ValueError("TTS is not enabled")
                voice = args.get("voice") or text_to_speech.get("voice")
            else:
                try:
+                    if app_model.app_model_config is None:
+                        raise ValueError("AppModelConfig not found")
                    voice = args.get("voice") or app_model.app_model_config.text_to_speech_dict.get("voice")
                except Exception:
                    voice = None
@@ -135,7 +135,7 @@ class DataSourceNotionListApi(Resource):
                        data_source_info = json.loads(document.data_source_info)
                        exist_page_ids.append(data_source_info["notion_page_id"])
            # get all authorized pages
-            data_source_bindings = session.execute(
+            data_source_bindings = session.scalars(
                select(DataSourceOauthBinding).filter_by(
                    tenant_id=current_user.current_tenant_id, provider="notion", disabled=False
                )
@@ -52,12 +52,12 @@ class DatasetListApi(Resource):
        # provider = request.args.get("provider", default="vendor")
        search = request.args.get("keyword", default=None, type=str)
        tag_ids = request.args.getlist("tag_ids")
-
+        include_all = request.args.get("include_all", default="false").lower() == "true"
        if ids:
            datasets, total = DatasetService.get_datasets_by_ids(ids, current_user.current_tenant_id)
        else:
            datasets, total = DatasetService.get_datasets(
-                page, limit, current_user.current_tenant_id, current_user, search, tag_ids
+                page, limit, current_user.current_tenant_id, current_user, search, tag_ids, include_all
            )

        # check embedding setting
@@ -457,7 +457,7 @@ class DatasetIndexingEstimateApi(Resource):
            )
        except LLMBadRequestError:
            raise ProviderNotInitializeError(
-                "No Embedding Model available. Please configure a valid provider " "in the Settings -> Model Provider."
+                "No Embedding Model available. Please configure a valid provider in the Settings -> Model Provider."
            )
        except ProviderTokenNotInitError as ex:
            raise ProviderNotInitializeError(ex.description)
@@ -619,8 +619,7 @@ class DatasetRetrievalSettingApi(Resource):
        vector_type = dify_config.VECTOR_STORE
        match vector_type:
            case (
-                VectorType.MILVUS
-                | VectorType.RELYT
+                VectorType.RELYT
                | VectorType.PGVECTOR
                | VectorType.TIDB_VECTOR
                | VectorType.CHROMA
@@ -645,6 +644,7 @@ class DatasetRetrievalSettingApi(Resource):
                | VectorType.TIDB_ON_QDRANT
                | VectorType.LINDORM
                | VectorType.COUCHBASE
+                | VectorType.MILVUS
            ):
                return {
                    "retrieval_method": [
@@ -362,8 +362,7 @@ class DatasetInitApi(Resource):
                )
            except InvokeAuthorizationError:
                raise ProviderNotInitializeError(
-                    "No Embedding Model available. Please configure a valid provider "
-                    "in the Settings -> Model Provider."
+                    "No Embedding Model available. Please configure a valid provider in the Settings -> Model Provider."
                )
            except ProviderTokenNotInitError as ex:
                raise ProviderNotInitializeError(ex.description)
@@ -540,8 +539,7 @@ class DocumentBatchIndexingEstimateApi(DocumentResource):
                return response.model_dump(), 200
            except LLMBadRequestError:
                raise ProviderNotInitializeError(
-                    "No Embedding Model available. Please configure a valid provider "
-                    "in the Settings -> Model Provider."
+                    "No Embedding Model available. Please configure a valid provider in the Settings -> Model Provider."
                )
            except ProviderTokenNotInitError as ex:
                raise ProviderNotInitializeError(ex.description)
@@ -168,8 +168,7 @@ class DatasetDocumentSegmentApi(Resource):
                )
            except LLMBadRequestError:
                raise ProviderNotInitializeError(
-                    "No Embedding Model available. Please configure a valid provider "
-                    "in the Settings -> Model Provider."
+                    "No Embedding Model available. Please configure a valid provider in the Settings -> Model Provider."
                )
            except ProviderTokenNotInitError as ex:
                raise ProviderNotInitializeError(ex.description)
@@ -217,8 +216,7 @@ class DatasetDocumentSegmentAddApi(Resource):
                )
            except LLMBadRequestError:
                raise ProviderNotInitializeError(
-                    "No Embedding Model available. Please configure a valid provider "
-                    "in the Settings -> Model Provider."
+                    "No Embedding Model available. Please configure a valid provider in the Settings -> Model Provider."
                )
            except ProviderTokenNotInitError as ex:
                raise ProviderNotInitializeError(ex.description)
@@ -267,8 +265,7 @@ class DatasetDocumentSegmentUpdateApi(Resource):
                )
            except LLMBadRequestError:
                raise ProviderNotInitializeError(
-                    "No Embedding Model available. Please configure a valid provider "
-                    "in the Settings -> Model Provider."
+                    "No Embedding Model available. Please configure a valid provider in the Settings -> Model Provider."
                )
            except ProviderTokenNotInitError as ex:
                raise ProviderNotInitializeError(ex.description)
@@ -368,9 +365,9 @@ class DatasetDocumentSegmentBatchImportApi(Resource):
            result = []
            for index, row in df.iterrows():
                if document.doc_form == "qa_model":
-                    data = {"content": row[0], "answer": row[1]}
+                    data = {"content": row.iloc[0], "answer": row.iloc[1]}
                else:
-                    data = {"content": row[0]}
+                    data = {"content": row.iloc[0]}
                result.append(data)
            if len(result) == 0:
                raise ValueError("The CSV file is empty.")
@@ -437,8 +434,7 @@ class ChildChunkAddApi(Resource):
                )
            except LLMBadRequestError:
                raise ProviderNotInitializeError(
-                    "No Embedding Model available. Please configure a valid provider "
-                    "in the Settings -> Model Provider."
+                    "No Embedding Model available. Please configure a valid provider in the Settings -> Model Provider."
                )
            except ProviderTokenNotInitError as ex:
                raise ProviderNotInitializeError(ex.description)
@@ -32,7 +32,7 @@ class ConversationListApi(InstalledAppResource):

        pinned = None
        if "pinned" in args and args["pinned"] is not None:
-            pinned = True if args["pinned"] == "true" else False
+            pinned = args["pinned"] == "true"

        try:
            with Session(db.engine) as session:
@@ -65,7 +65,7 @@ def enterprise_inner_api_user_auth(view):
 def plugin_inner_api_only(view):
    @wraps(view)
    def decorated(*args, **kwargs):
-        if not dify_config.PLUGIN_API_KEY:
+        if not dify_config.PLUGIN_DAEMON_KEY:
            abort(404)

        # get header 'X-Inner-Api-Key'
@@ -7,4 +7,4 @@ api = ExternalApi(bp)

 from . import index
 from .app import app, audio, completion, conversation, file, message, workflow
-from .dataset import dataset, document, hit_testing, segment
+from .dataset import dataset, document, hit_testing, segment, upload_file
@@ -31,8 +31,11 @@ class DatasetListApi(DatasetApiResource):
        # provider = request.args.get("provider", default="vendor")
        search = request.args.get("keyword", default=None, type=str)
        tag_ids = request.args.getlist("tag_ids")
+        include_all = request.args.get("include_all", default="false").lower() == "true"

-        datasets, total = DatasetService.get_datasets(page, limit, tenant_id, current_user, search, tag_ids)
+        datasets, total = DatasetService.get_datasets(
+            page, limit, tenant_id, current_user, search, tag_ids, include_all
+        )
        # check embedding setting
        provider_manager = ProviderManager()
        configurations = provider_manager.get_configurations(tenant_id=current_user.current_tenant_id)
@@ -53,8 +53,7 @@ class SegmentApi(DatasetApiResource):
                )
            except LLMBadRequestError:
                raise ProviderNotInitializeError(
-                    "No Embedding Model available. Please configure a valid provider "
-                    "in the Settings -> Model Provider."
+                    "No Embedding Model available. Please configure a valid provider in the Settings -> Model Provider."
                )
            except ProviderTokenNotInitError as ex:
                raise ProviderNotInitializeError(ex.description)
@@ -95,8 +94,7 @@ class SegmentApi(DatasetApiResource):
                )
            except LLMBadRequestError:
                raise ProviderNotInitializeError(
-                    "No Embedding Model available. Please configure a valid provider "
-                    "in the Settings -> Model Provider."
+                    "No Embedding Model available. Please configure a valid provider in the Settings -> Model Provider."
                )
            except ProviderTokenNotInitError as ex:
                raise ProviderNotInitializeError(ex.description)
@@ -175,8 +173,7 @@ class DatasetSegmentApi(DatasetApiResource):
                )
            except LLMBadRequestError:
                raise ProviderNotInitializeError(
-                    "No Embedding Model available. Please configure a valid provider "
-                    "in the Settings -> Model Provider."
+                    "No Embedding Model available. Please configure a valid provider in the Settings -> Model Provider."
                )
            except ProviderTokenNotInitError as ex:
                raise ProviderNotInitializeError(ex.description)
@@ -0,0 +1,54 @@
+from werkzeug.exceptions import NotFound
+
+from controllers.service_api import api
+from controllers.service_api.wraps import (
+    DatasetApiResource,
+)
+from core.file import helpers as file_helpers
+from extensions.ext_database import db
+from models.dataset import Dataset
+from models.model import UploadFile
+from services.dataset_service import DocumentService
+
+
+class UploadFileApi(DatasetApiResource):
+    def get(self, tenant_id, dataset_id, document_id):
+        """Get upload file."""
+        # check dataset
+        dataset_id = str(dataset_id)
+        tenant_id = str(tenant_id)
+        dataset = db.session.query(Dataset).filter(Dataset.tenant_id == tenant_id, Dataset.id == dataset_id).first()
+        if not dataset:
+            raise NotFound("Dataset not found.")
+        # check document
+        document_id = str(document_id)
+        document = DocumentService.get_document(dataset.id, document_id)
+        if not document:
+            raise NotFound("Document not found.")
+        # check upload file
+        if document.data_source_type != "upload_file":
+            raise ValueError(f"Document data source type ({document.data_source_type}) is not upload_file.")
+        data_source_info = document.data_source_info_dict
+        if data_source_info and "upload_file_id" in data_source_info:
+            file_id = data_source_info["upload_file_id"]
+            upload_file = db.session.query(UploadFile).filter(UploadFile.id == file_id).first()
+            if not upload_file:
+                raise NotFound("UploadFile not found.")
+        else:
+            raise ValueError("Upload file id not found in document data source info.")
+
+        url = file_helpers.get_signed_file_url(upload_file_id=upload_file.id)
+        return {
+            "id": upload_file.id,
+            "name": upload_file.name,
+            "size": upload_file.size,
+            "extension": upload_file.extension,
+            "url": url,
+            "download_url": f"{url}&as_attachment=true",
+            "mime_type": upload_file.mime_type,
+            "created_by": upload_file.created_by,
+            "created_at": upload_file.created_at.timestamp(),
+        }, 200
+
+
+api.add_resource(UploadFileApi, "/datasets/<uuid:dataset_id>/documents/<uuid:document_id>/upload-file")
@@ -195,7 +195,11 @@ def validate_and_get_api_token(scope: str | None = None):
    with Session(db.engine, expire_on_commit=False) as session:
        update_stmt = (
            update(ApiToken)
-            .where(ApiToken.token == auth_token, ApiToken.last_used_at < cutoff_time, ApiToken.type == scope)
+            .where(
+                ApiToken.token == auth_token,
+                (ApiToken.last_used_at.is_(None) | (ApiToken.last_used_at < cutoff_time)),
+                ApiToken.type == scope,
+            )
            .values(last_used_at=current_time)
            .returning(ApiToken)
        )
@@ -236,7 +240,7 @@ def create_or_update_end_user_for_user_id(app_model: App, user_id: Optional[str]
            tenant_id=app_model.tenant_id,
            app_id=app_model.id,
            type="service_api",
-            is_anonymous=True if user_id == "DEFAULT-USER" else False,
+            is_anonymous=user_id == "DEFAULT-USER",
            session_id=user_id,
        )
        db.session.add(end_user)
@@ -39,7 +39,7 @@ class ConversationListApi(WebApiResource):

        pinned = None
        if "pinned" in args and args["pinned"] is not None:
-            pinned = True if args["pinned"] == "true" else False
+            pinned = args["pinned"] == "true"

        try:
            with Session(db.engine) as session:
@@ -168,7 +168,7 @@ class CotAgentRunner(BaseAgentRunner, ABC):

            self.save_agent_thought(
                agent_thought=agent_thought,
-                tool_name=scratchpad.action.action_name if scratchpad.action else "",
+                tool_name=(scratchpad.action.action_name if scratchpad.action and not scratchpad.is_final() else ""),
                tool_input={scratchpad.action.action_name: scratchpad.action.action_input} if scratchpad.action else {},
                tool_invoke_meta={},
                thought=scratchpad.thought or "",
@@ -167,8 +167,7 @@ class AppQueueManager:
        else:
            if isinstance(data, DeclarativeMeta) or hasattr(data, "_sa_instance_state"):
                raise TypeError(
-                    "Critical Error: Passing SQLAlchemy Model instances "
-                    "that cause thread safety issues is not allowed."
+                    "Critical Error: Passing SQLAlchemy Model instances that cause thread safety issues is not allowed."
                )


@@ -89,6 +89,7 @@ class MessageBasedAppGenerator(BaseAppGenerator):
            Conversation.id == conversation_id,
            Conversation.app_id == app_model.id,
            Conversation.status == "normal",
+            Conversation.is_deleted.is_(False),
        ]

        if isinstance(user, Account):
@@ -241,6 +241,7 @@ class WorkflowBasedAppRunner(AppRunner):
                    predecessor_node_id=event.predecessor_node_id,
                    in_iteration_id=event.in_iteration_id,
                    parallel_mode_run_id=event.parallel_mode_run_id,
+                    agent_strategy=event.agent_strategy,
                )
            )
        elif isinstance(event, NodeRunSucceededEvent):
@@ -6,7 +6,7 @@ from typing import Any, Optional
 from pydantic import BaseModel

 from core.model_runtime.entities.llm_entities import LLMResult, LLMResultChunk
-from core.workflow.entities.node_entities import NodeRunMetadataKey
+from core.workflow.entities.node_entities import AgentNodeStrategyInit, NodeRunMetadataKey
 from core.workflow.graph_engine.entities.graph_runtime_state import GraphRuntimeState
 from core.workflow.nodes import NodeType
 from core.workflow.nodes.base import BaseNodeData
@@ -281,6 +281,7 @@ class QueueNodeStartedEvent(AppQueueEvent):
    start_at: datetime
    parallel_mode_run_id: Optional[str] = None
    """iteratoin run in parallel mode run id"""
+    agent_strategy: Optional[AgentNodeStrategyInit] = None


 class QueueNodeSucceededEvent(AppQueueEvent):
@@ -6,6 +6,7 @@ from pydantic import BaseModel, ConfigDict

 from core.model_runtime.entities.llm_entities import LLMResult
 from core.model_runtime.utils.encoders import jsonable_encoder
+from core.workflow.entities.node_entities import AgentNodeStrategyInit
 from models.workflow import WorkflowNodeExecutionStatus


@@ -248,6 +249,7 @@ class NodeStartStreamResponse(StreamResponse):
        parent_parallel_start_node_id: Optional[str] = None
        iteration_id: Optional[str] = None
        parallel_run_id: Optional[str] = None
+        agent_strategy: Optional[AgentNodeStrategyInit] = None

    event: StreamEvent = StreamEvent.NODE_STARTED
    workflow_run_id: str
@@ -145,7 +145,7 @@ class MessageCycleManage:

            # get extension
            if "." in message_file.url:
-                extension = f'.{message_file.url.split(".")[-1]}'
+                extension = f".{message_file.url.split('.')[-1]}"
                if len(extension) > 10:
                    extension = ".bin"
            else:
@@ -541,6 +541,7 @@ class WorkflowCycleManage:
                parent_parallel_start_node_id=event.parent_parallel_start_node_id,
                iteration_id=event.in_iteration_id,
                parallel_run_id=event.parallel_mode_run_id,
+                agent_strategy=event.agent_strategy,
            ),
        )

@@ -62,8 +62,9 @@ class ApiExternalDataTool(ExternalDataTool):

        if not api_based_extension:
            raise ValueError(
-                "[External data tool] API query failed, variable: {}, "
-                "error: api_based_extension_id is invalid".format(self.variable)
+                "[External data tool] API query failed, variable: {}, error: api_based_extension_id is invalid".format(
+                    self.variable
+                )
            )

        # decrypt api_key
@@ -33,7 +33,7 @@ def get_signed_file_url_for_plugin(filename: str, mimetype: str, tenant_id: str,
    sign = hmac.new(key, msg.encode(), hashlib.sha256).digest()
    encoded_sign = base64.urlsafe_b64encode(sign).decode()

-    return f"{url}?timestamp={timestamp}&nonce={nonce}&sign={encoded_sign}&user_id={user_id}"
+    return f"{url}?timestamp={timestamp}&nonce={nonce}&sign={encoded_sign}&user_id={user_id}&tenant_id={tenant_id}"


 def verify_plugin_file_signature(
@@ -90,7 +90,7 @@ class File(BaseModel):
    def markdown(self) -> str:
        url = self.generate_url()
        if self.type == FileType.IMAGE:
-            text = f'![{self.filename or ""}]({url})'
+            text = f"![{self.filename or ''}]({url})"
        else:
            text = f"[{self.filename or url}]({url})"

@@ -530,7 +530,6 @@ class IndexingRunner:
        # chunk nodes by chunk size
        indexing_start_at = time.perf_counter()
        tokens = 0
-        chunk_size = 10
        if dataset_document.doc_form != IndexType.PARENT_CHILD_INDEX:
            # create keyword index
            create_keyword_thread = threading.Thread(
@@ -539,11 +538,22 @@ class IndexingRunner:
            )
            create_keyword_thread.start()

+        max_workers = 10
        if dataset.indexing_technique == "high_quality":
-            with concurrent.futures.ThreadPoolExecutor(max_workers=10) as executor:
+            with concurrent.futures.ThreadPoolExecutor(max_workers=max_workers) as executor:
                futures = []
-                for i in range(0, len(documents), chunk_size):
-                    chunk_documents = documents[i : i + chunk_size]
+
+                # Distribute documents into multiple groups based on the hash values of page_content
+                # This is done to prevent multiple threads from processing the same document,
+                # Thereby avoiding potential database insertion deadlocks
+                document_groups: list[list[Document]] = [[] for _ in range(max_workers)]
+                for document in documents:
+                    hash = helper.generate_text_hash(document.page_content)
+                    group_index = int(hash, 16) % max_workers
+                    document_groups[group_index].append(document)
+                for chunk_documents in document_groups:
+                    if len(chunk_documents) == 0:
+                        continue
                    futures.append(
                        executor.submit(
                            self._process_chunk,
@@ -131,7 +131,7 @@ JAVASCRIPT_CODE_GENERATOR_PROMPT_TEMPLATE = (
 SUGGESTED_QUESTIONS_AFTER_ANSWER_INSTRUCTION_PROMPT = (
    "Please help me predict the three most likely questions that human would ask, "
    "and keeping each question under 20 characters.\n"
-    "MAKE SURE your output is the SAME language as the Assistant's latest response"
+    "MAKE SURE your output is the SAME language as the Assistant's latest response. "
    "The output must be an array in JSON format following the specified schema:\n"
    '["question1","question2","question3"]\n'
 )
@@ -107,11 +107,46 @@ class LargeLanguageModel(AIModel):
                content_list = []
                usage = LLMUsage.empty_usage()
                system_fingerprint = None
+                tools_calls: list[AssistantPromptMessage.ToolCall] = []
+
+                def increase_tool_call(new_tool_calls: list[AssistantPromptMessage.ToolCall]):
+                    def get_tool_call(tool_name: str):
+                        if not tool_name:
+                            return tools_calls[-1]
+
+                        tool_call = next(
+                            (tool_call for tool_call in tools_calls if tool_call.function.name == tool_name), None
+                        )
+                        if tool_call is None:
+                            tool_call = AssistantPromptMessage.ToolCall(
+                                id="",
+                                type="",
+                                function=AssistantPromptMessage.ToolCall.ToolCallFunction(name=tool_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
+
                for chunk in result:
                    if isinstance(chunk.delta.message.content, str):
                        content += chunk.delta.message.content
                    elif isinstance(chunk.delta.message.content, list):
                        content_list.extend(chunk.delta.message.content)
+                    if chunk.delta.message.tool_calls:
+                        increase_tool_call(chunk.delta.message.tool_calls)

                    usage = chunk.delta.usage or LLMUsage.empty_usage()
                    system_fingerprint = chunk.system_fingerprint
@@ -120,7 +155,10 @@ class LargeLanguageModel(AIModel):
                result = LLMResult(
                    model=model,
                    prompt_messages=prompt_messages,
-                    message=AssistantPromptMessage(content=content or content_list),
+                    message=AssistantPromptMessage(
+                        content=content or content_list,
+                        tool_calls=tools_calls,
+                    ),
                    usage=usage,
                    system_fingerprint=system_fingerprint,
                )
@@ -1,6 +1,9 @@
+import logging
 from threading import Lock
 from typing import Any

+logger = logging.getLogger(__name__)
+
 _tokenizer: Any = None
 _lock = Lock()

@@ -43,5 +46,6 @@ class GPT2Tokenizer:
                    base_path = abspath(__file__)
                    gpt2_tokenizer_path = join(dirname(base_path), "gpt2")
                    _tokenizer = TransformerGPT2Tokenizer.from_pretrained(gpt2_tokenizer_path)
+                    logger.info("Fallback to Transformers' GPT-2 tokenizer from tiktoken")

            return _tokenizer
@@ -1,42 +0,0 @@
-model: ernie-lite-pro-128k
-label:
-  en_US: Ernie-Lite-Pro-128K
-model_type: llm
-features:
-  - agent-thought
-model_properties:
-  mode: chat
-  context_size: 128000
-parameter_rules:
-  - name: temperature
-    use_template: temperature
-    min: 0.1
-    max: 1.0
-    default: 0.8
-  - name: top_p
-    use_template: top_p
-  - name: min_output_tokens
-    label:
-      en_US: "Min Output Tokens"
-      zh_Hans: "最小输出Token数"
-    use_template: max_tokens
-    min: 2
-    max: 2048
-    help:
-      zh_Hans: 指定模型最小输出token数
-      en_US: Specifies the lower limit on the length of generated results.
-  - name: max_output_tokens
-    label:
-      en_US: "Max Output Tokens"
-      zh_Hans: "最大输出Token数"
-    use_template: max_tokens
-    min: 2
-    max: 2048
-    default: 2048
-    help:
-      zh_Hans: 指定模型最大输出token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: presence_penalty
-    use_template: presence_penalty
-  - name: frequency_penalty
-    use_template: frequency_penalty
@@ -87,6 +87,6 @@ class CommonValidator:
            if value.lower() not in {"true", "false"}:
                raise ValueError(f"Variable {credential_form_schema.variable} should be true or false")

-            value = True if value.lower() == "true" else False
+            value = value.lower() == "true"

        return value
@@ -6,6 +6,7 @@ from pydantic import BaseModel, ValidationInfo, field_validator
 class TracingProviderEnum(Enum):
    LANGFUSE = "langfuse"
    LANGSMITH = "langsmith"
+    OPIK = "opik"


 class BaseTracingConfig(BaseModel):
@@ -56,5 +57,36 @@ class LangSmithConfig(BaseTracingConfig):
        return v


+class OpikConfig(BaseTracingConfig):
+    """
+    Model class for Opik tracing config.
+    """
+
+    api_key: str | None = None
+    project: str | None = None
+    workspace: str | None = None
+    url: str = "https://www.comet.com/opik/api/"
+
+    @field_validator("project")
+    @classmethod
+    def project_validator(cls, v, info: ValidationInfo):
+        if v is None or v == "":
+            v = "Default Project"
+
+        return v
+
+    @field_validator("url")
+    @classmethod
+    def url_validator(cls, v, info: ValidationInfo):
+        if v is None or v == "":
+            v = "https://www.comet.com/opik/api/"
+        if not v.startswith(("https://", "http://")):
+            raise ValueError("url must start with https:// or http://")
+        if not v.endswith("/api/"):
+            raise ValueError("url should ends with /api/")
+
+        return v
+
+
 OPS_FILE_PATH = "ops_trace/"
 OPS_TRACE_FAILED_KEY = "FAILED_OPS_TRACE"
@@ -0,0 +1,469 @@
+import json
+import logging
+import os
+import uuid
+from datetime import datetime, timedelta
+from typing import Optional, cast
+
+from opik import Opik, Trace
+from opik.id_helpers import uuid4_to_uuid7
+
+from core.ops.base_trace_instance import BaseTraceInstance
+from core.ops.entities.config_entity import OpikConfig
+from core.ops.entities.trace_entity import (
+    BaseTraceInfo,
+    DatasetRetrievalTraceInfo,
+    GenerateNameTraceInfo,
+    MessageTraceInfo,
+    ModerationTraceInfo,
+    SuggestedQuestionTraceInfo,
+    ToolTraceInfo,
+    TraceTaskName,
+    WorkflowTraceInfo,
+)
+from extensions.ext_database import db
+from models.model import EndUser, MessageFile
+from models.workflow import WorkflowNodeExecution
+
+logger = logging.getLogger(__name__)
+
+
+def wrap_dict(key_name, data):
+    """Make sure that the input data is a dict"""
+    if not isinstance(data, dict):
+        return {key_name: data}
+
+    return data
+
+
+def wrap_metadata(metadata, **kwargs):
+    """Add common metatada to all Traces and Spans"""
+    metadata["created_from"] = "dify"
+
+    metadata.update(kwargs)
+
+    return metadata
+
+
+def prepare_opik_uuid(user_datetime: Optional[datetime], user_uuid: Optional[str]):
+    """Opik needs UUIDv7 while Dify uses UUIDv4 for identifier of most
+    messages and objects. The type-hints of BaseTraceInfo indicates that
+    objects start_time and message_id could be null which means we cannot map
+    it to a UUIDv7. Given that we have no way to identify that object
+    uniquely, generate a new random one UUIDv7 in that case.
+    """
+
+    if user_datetime is None:
+        user_datetime = datetime.now()
+
+    if user_uuid is None:
+        user_uuid = str(uuid.uuid4())
+
+    return uuid4_to_uuid7(user_datetime, user_uuid)
+
+
+class OpikDataTrace(BaseTraceInstance):
+    def __init__(
+        self,
+        opik_config: OpikConfig,
+    ):
+        super().__init__(opik_config)
+        self.opik_client = Opik(
+            project_name=opik_config.project,
+            workspace=opik_config.workspace,
+            host=opik_config.url,
+            api_key=opik_config.api_key,
+        )
+        self.project = opik_config.project
+        self.file_base_url = os.getenv("FILES_URL", "http://127.0.0.1:5001")
+
+    def trace(self, trace_info: BaseTraceInfo):
+        if isinstance(trace_info, WorkflowTraceInfo):
+            self.workflow_trace(trace_info)
+        if isinstance(trace_info, MessageTraceInfo):
+            self.message_trace(trace_info)
+        if isinstance(trace_info, ModerationTraceInfo):
+            self.moderation_trace(trace_info)
+        if isinstance(trace_info, SuggestedQuestionTraceInfo):
+            self.suggested_question_trace(trace_info)
+        if isinstance(trace_info, DatasetRetrievalTraceInfo):
+            self.dataset_retrieval_trace(trace_info)
+        if isinstance(trace_info, ToolTraceInfo):
+            self.tool_trace(trace_info)
+        if isinstance(trace_info, GenerateNameTraceInfo):
+            self.generate_name_trace(trace_info)
+
+    def workflow_trace(self, trace_info: WorkflowTraceInfo):
+        dify_trace_id = trace_info.workflow_run_id
+        opik_trace_id = prepare_opik_uuid(trace_info.start_time, dify_trace_id)
+        workflow_metadata = wrap_metadata(
+            trace_info.metadata, message_id=trace_info.message_id, workflow_app_log_id=trace_info.workflow_app_log_id
+        )
+        root_span_id = None
+
+        if trace_info.message_id:
+            dify_trace_id = trace_info.message_id
+            opik_trace_id = prepare_opik_uuid(trace_info.start_time, dify_trace_id)
+
+            trace_data = {
+                "id": opik_trace_id,
+                "name": TraceTaskName.MESSAGE_TRACE.value,
+                "start_time": trace_info.start_time,
+                "end_time": trace_info.end_time,
+                "metadata": workflow_metadata,
+                "input": wrap_dict("input", trace_info.workflow_run_inputs),
+                "output": wrap_dict("output", trace_info.workflow_run_outputs),
+                "tags": ["message", "workflow"],
+                "project_name": self.project,
+            }
+            self.add_trace(trace_data)
+
+            root_span_id = prepare_opik_uuid(trace_info.start_time, trace_info.workflow_run_id)
+            span_data = {
+                "id": root_span_id,
+                "parent_span_id": None,
+                "trace_id": opik_trace_id,
+                "name": TraceTaskName.WORKFLOW_TRACE.value,
+                "input": wrap_dict("input", trace_info.workflow_run_inputs),
+                "output": wrap_dict("output", trace_info.workflow_run_outputs),
+                "start_time": trace_info.start_time,
+                "end_time": trace_info.end_time,
+                "metadata": workflow_metadata,
+                "tags": ["workflow"],
+                "project_name": self.project,
+            }
+            self.add_span(span_data)
+        else:
+            trace_data = {
+                "id": opik_trace_id,
+                "name": TraceTaskName.MESSAGE_TRACE.value,
+                "start_time": trace_info.start_time,
+                "end_time": trace_info.end_time,
+                "metadata": workflow_metadata,
+                "input": wrap_dict("input", trace_info.workflow_run_inputs),
+                "output": wrap_dict("output", trace_info.workflow_run_outputs),
+                "tags": ["workflow"],
+                "project_name": self.project,
+            }
+            self.add_trace(trace_data)
+
+        # through workflow_run_id get all_nodes_execution
+        workflow_nodes_execution_id_records = (
+            db.session.query(WorkflowNodeExecution.id)
+            .filter(WorkflowNodeExecution.workflow_run_id == trace_info.workflow_run_id)
+            .all()
+        )
+
+        for node_execution_id_record in workflow_nodes_execution_id_records:
+            node_execution = (
+                db.session.query(
+                    WorkflowNodeExecution.id,
+                    WorkflowNodeExecution.tenant_id,
+                    WorkflowNodeExecution.app_id,
+                    WorkflowNodeExecution.title,
+                    WorkflowNodeExecution.node_type,
+                    WorkflowNodeExecution.status,
+                    WorkflowNodeExecution.inputs,
+                    WorkflowNodeExecution.outputs,
+                    WorkflowNodeExecution.created_at,
+                    WorkflowNodeExecution.elapsed_time,
+                    WorkflowNodeExecution.process_data,
+                    WorkflowNodeExecution.execution_metadata,
+                )
+                .filter(WorkflowNodeExecution.id == node_execution_id_record.id)
+                .first()
+            )
+
+            if not node_execution:
+                continue
+
+            node_execution_id = node_execution.id
+            tenant_id = node_execution.tenant_id
+            app_id = node_execution.app_id
+            node_name = node_execution.title
+            node_type = node_execution.node_type
+            status = node_execution.status
+            if node_type == "llm":
+                inputs = (
+                    json.loads(node_execution.process_data).get("prompts", {}) if node_execution.process_data else {}
+                )
+            else:
+                inputs = json.loads(node_execution.inputs) if node_execution.inputs else {}
+            outputs = json.loads(node_execution.outputs) if node_execution.outputs else {}
+            created_at = node_execution.created_at or datetime.now()
+            elapsed_time = node_execution.elapsed_time
+            finished_at = created_at + timedelta(seconds=elapsed_time)
+
+            execution_metadata = (
+                json.loads(node_execution.execution_metadata) if node_execution.execution_metadata else {}
+            )
+            metadata = execution_metadata.copy()
+            metadata.update(
+                {
+                    "workflow_run_id": trace_info.workflow_run_id,
+                    "node_execution_id": node_execution_id,
+                    "tenant_id": tenant_id,
+                    "app_id": app_id,
+                    "app_name": node_name,
+                    "node_type": node_type,
+                    "status": status,
+                }
+            )
+
+            process_data = json.loads(node_execution.process_data) if node_execution.process_data else {}
+
+            provider = None
+            model = None
+            total_tokens = 0
+            completion_tokens = 0
+            prompt_tokens = 0
+
+            if process_data and process_data.get("model_mode") == "chat":
+                run_type = "llm"
+                provider = process_data.get("model_provider", None)
+                model = process_data.get("model_name", "")
+                metadata.update(
+                    {
+                        "ls_provider": provider,
+                        "ls_model_name": model,
+                    }
+                )
+
+                try:
+                    if outputs.get("usage"):
+                        total_tokens = outputs["usage"].get("total_tokens", 0)
+                        prompt_tokens = outputs["usage"].get("prompt_tokens", 0)
+                        completion_tokens = outputs["usage"].get("completion_tokens", 0)
+                except Exception:
+                    logger.error("Failed to extract usage", exc_info=True)
+
+            else:
+                run_type = "tool"
+
+            parent_span_id = trace_info.workflow_app_log_id or trace_info.workflow_run_id
+
+            if not total_tokens:
+                total_tokens = execution_metadata.get("total_tokens", 0)
+
+            span_data = {
+                "trace_id": opik_trace_id,
+                "id": prepare_opik_uuid(created_at, node_execution_id),
+                "parent_span_id": prepare_opik_uuid(trace_info.start_time, parent_span_id),
+                "name": node_type,
+                "type": run_type,
+                "start_time": created_at,
+                "end_time": finished_at,
+                "metadata": wrap_metadata(metadata),
+                "input": wrap_dict("input", inputs),
+                "output": wrap_dict("output", outputs),
+                "tags": ["node_execution"],
+                "project_name": self.project,
+                "usage": {
+                    "total_tokens": total_tokens,
+                    "completion_tokens": completion_tokens,
+                    "prompt_tokens": prompt_tokens,
+                },
+                "model": model,
+                "provider": provider,
+            }
+
+            self.add_span(span_data)
+
+    def message_trace(self, trace_info: MessageTraceInfo):
+        # get message file data
+        file_list = cast(list[str], trace_info.file_list) or []
+        message_file_data: Optional[MessageFile] = trace_info.message_file_data
+
+        if message_file_data is not None:
+            file_url = f"{self.file_base_url}/{message_file_data.url}" if message_file_data else ""
+            file_list.append(file_url)
+
+        message_data = trace_info.message_data
+        if message_data is None:
+            return
+
+        metadata = trace_info.metadata
+        message_id = trace_info.message_id
+
+        user_id = message_data.from_account_id
+        metadata["user_id"] = user_id
+        metadata["file_list"] = file_list
+
+        if message_data.from_end_user_id:
+            end_user_data: Optional[EndUser] = (
+                db.session.query(EndUser).filter(EndUser.id == message_data.from_end_user_id).first()
+            )
+            if end_user_data is not None:
+                end_user_id = end_user_data.session_id
+                metadata["end_user_id"] = end_user_id
+
+        trace_data = {
+            "id": prepare_opik_uuid(trace_info.start_time, message_id),
+            "name": TraceTaskName.MESSAGE_TRACE.value,
+            "start_time": trace_info.start_time,
+            "end_time": trace_info.end_time,
+            "metadata": wrap_metadata(metadata),
+            "input": trace_info.inputs,
+            "output": message_data.answer,
+            "tags": ["message", str(trace_info.conversation_mode)],
+            "project_name": self.project,
+        }
+        trace = self.add_trace(trace_data)
+
+        span_data = {
+            "trace_id": trace.id,
+            "name": "llm",
+            "type": "llm",
+            "start_time": trace_info.start_time,
+            "end_time": trace_info.end_time,
+            "metadata": wrap_metadata(metadata),
+            "input": {"input": trace_info.inputs},
+            "output": {"output": message_data.answer},
+            "tags": ["llm", str(trace_info.conversation_mode)],
+            "usage": {
+                "completion_tokens": trace_info.answer_tokens,
+                "prompt_tokens": trace_info.message_tokens,
+                "total_tokens": trace_info.total_tokens,
+            },
+            "project_name": self.project,
+        }
+        self.add_span(span_data)
+
+    def moderation_trace(self, trace_info: ModerationTraceInfo):
+        if trace_info.message_data is None:
+            return
+
+        start_time = trace_info.start_time or trace_info.message_data.created_at
+
+        span_data = {
+            "trace_id": prepare_opik_uuid(start_time, trace_info.message_id),
+            "name": TraceTaskName.MODERATION_TRACE.value,
+            "type": "tool",
+            "start_time": start_time,
+            "end_time": trace_info.end_time or trace_info.message_data.updated_at,
+            "metadata": wrap_metadata(trace_info.metadata),
+            "input": wrap_dict("input", trace_info.inputs),
+            "output": {
+                "action": trace_info.action,
+                "flagged": trace_info.flagged,
+                "preset_response": trace_info.preset_response,
+                "inputs": trace_info.inputs,
+            },
+            "tags": ["moderation"],
+        }
+
+        self.add_span(span_data)
+
+    def suggested_question_trace(self, trace_info: SuggestedQuestionTraceInfo):
+        message_data = trace_info.message_data
+        if message_data is None:
+            return
+
+        start_time = trace_info.start_time or message_data.created_at
+
+        span_data = {
+            "trace_id": prepare_opik_uuid(start_time, trace_info.message_id),
+            "name": TraceTaskName.SUGGESTED_QUESTION_TRACE.value,
+            "type": "tool",
+            "start_time": start_time,
+            "end_time": trace_info.end_time or message_data.updated_at,
+            "metadata": wrap_metadata(trace_info.metadata),
+            "input": wrap_dict("input", trace_info.inputs),
+            "output": wrap_dict("output", trace_info.suggested_question),
+            "tags": ["suggested_question"],
+        }
+
+        self.add_span(span_data)
+
+    def dataset_retrieval_trace(self, trace_info: DatasetRetrievalTraceInfo):
+        if trace_info.message_data is None:
+            return
+
+        start_time = trace_info.start_time or trace_info.message_data.created_at
+
+        span_data = {
+            "trace_id": prepare_opik_uuid(start_time, trace_info.message_id),
+            "name": TraceTaskName.DATASET_RETRIEVAL_TRACE.value,
+            "type": "tool",
+            "start_time": start_time,
+            "end_time": trace_info.end_time or trace_info.message_data.updated_at,
+            "metadata": wrap_metadata(trace_info.metadata),
+            "input": wrap_dict("input", trace_info.inputs),
+            "output": {"documents": trace_info.documents},
+            "tags": ["dataset_retrieval"],
+        }
+
+        self.add_span(span_data)
+
+    def tool_trace(self, trace_info: ToolTraceInfo):
+        span_data = {
+            "trace_id": prepare_opik_uuid(trace_info.start_time, trace_info.message_id),
+            "name": trace_info.tool_name,
+            "type": "tool",
+            "start_time": trace_info.start_time,
+            "end_time": trace_info.end_time,
+            "metadata": wrap_metadata(trace_info.metadata),
+            "input": wrap_dict("input", trace_info.tool_inputs),
+            "output": wrap_dict("output", trace_info.tool_outputs),
+            "tags": ["tool", trace_info.tool_name],
+        }
+
+        self.add_span(span_data)
+
+    def generate_name_trace(self, trace_info: GenerateNameTraceInfo):
+        trace_data = {
+            "id": prepare_opik_uuid(trace_info.start_time, trace_info.message_id),
+            "name": TraceTaskName.GENERATE_NAME_TRACE.value,
+            "start_time": trace_info.start_time,
+            "end_time": trace_info.end_time,
+            "metadata": wrap_metadata(trace_info.metadata),
+            "input": trace_info.inputs,
+            "output": trace_info.outputs,
+            "tags": ["generate_name"],
+            "project_name": self.project,
+        }
+
+        trace = self.add_trace(trace_data)
+
+        span_data = {
+            "trace_id": trace.id,
+            "name": TraceTaskName.GENERATE_NAME_TRACE.value,
+            "start_time": trace_info.start_time,
+            "end_time": trace_info.end_time,
+            "metadata": wrap_metadata(trace_info.metadata),
+            "input": wrap_dict("input", trace_info.inputs),
+            "output": wrap_dict("output", trace_info.outputs),
+            "tags": ["generate_name"],
+        }
+
+        self.add_span(span_data)
+
+    def add_trace(self, opik_trace_data: dict) -> Trace:
+        try:
+            trace = self.opik_client.trace(**opik_trace_data)
+            logger.debug("Opik Trace created successfully")
+            return trace
+        except Exception as e:
+            raise ValueError(f"Opik Failed to create trace: {str(e)}")
+
+    def add_span(self, opik_span_data: dict):
+        try:
+            self.opik_client.span(**opik_span_data)
+            logger.debug("Opik Span created successfully")
+        except Exception as e:
+            raise ValueError(f"Opik Failed to create span: {str(e)}")
+
+    def api_check(self):
+        try:
+            self.opik_client.auth_check()
+            return True
+        except Exception as e:
+            logger.info(f"Opik API check failed: {str(e)}", exc_info=True)
+            raise ValueError(f"Opik API check failed: {str(e)}")
+
+    def get_project_url(self):
+        try:
+            return self.opik_client.get_project_url(project_name=self.project)
+        except Exception as e:
+            logger.info(f"Opik get run url failed: {str(e)}", exc_info=True)
+            raise ValueError(f"Opik get run url failed: {str(e)}")
@@ -17,6 +17,7 @@ from core.ops.entities.config_entity import (
    OPS_FILE_PATH,
    LangfuseConfig,
    LangSmithConfig,
+    OpikConfig,
    TracingProviderEnum,
 )
 from core.ops.entities.trace_entity import (
@@ -32,6 +33,7 @@ from core.ops.entities.trace_entity import (
 )
 from core.ops.langfuse_trace.langfuse_trace import LangFuseDataTrace
 from core.ops.langsmith_trace.langsmith_trace import LangSmithDataTrace
+from core.ops.opik_trace.opik_trace import OpikDataTrace
 from core.ops.utils import get_message_data
 from extensions.ext_database import db
 from extensions.ext_storage import storage
@@ -52,6 +54,12 @@ provider_config_map: dict[str, dict[str, Any]] = {
        "other_keys": ["project", "endpoint"],
        "trace_instance": LangSmithDataTrace,
    },
+    TracingProviderEnum.OPIK.value: {
+        "config_class": OpikConfig,
+        "secret_keys": ["api_key"],
+        "other_keys": ["project", "url", "workspace"],
+        "trace_instance": OpikDataTrace,
+    },
 }


@@ -30,7 +30,7 @@ from core.plugin.manager.exc import (
 )

 plugin_daemon_inner_api_baseurl = dify_config.PLUGIN_DAEMON_URL
-plugin_daemon_inner_api_key = dify_config.PLUGIN_API_KEY
+plugin_daemon_inner_api_key = dify_config.PLUGIN_DAEMON_KEY

 T = TypeVar("T", bound=(BaseModel | dict | list | bool | str))

@@ -48,8 +48,10 @@ class PluginToolManager(BasePluginManager):
        tool_provider_id = GenericProviderID(provider)

        def transformer(json_response: dict[str, Any]) -> dict:
-            for tool in json_response.get("data", {}).get("declaration", {}).get("tools", []):
-                tool["identity"]["provider"] = tool_provider_id.provider_name
+            data = json_response.get("data")
+            if data:
+                for tool in data.get("declaration", {}).get("tools", []):
+                    tool["identity"]["provider"] = tool_provider_id.provider_name

            return json_response

@@ -23,7 +23,12 @@ from core.helper import encrypter
 from core.helper.model_provider_cache import ProviderCredentialsCache, ProviderCredentialsCacheType
 from core.helper.position_helper import is_filtered
 from core.model_runtime.entities.model_entities import ModelType
-from core.model_runtime.entities.provider_entities import CredentialFormSchema, FormType, ProviderEntity
+from core.model_runtime.entities.provider_entities import (
+    ConfigurateMethod,
+    CredentialFormSchema,
+    FormType,
+    ProviderEntity,
+)
 from core.model_runtime.model_providers.model_provider_factory import ModelProviderFactory
 from extensions import ext_hosting_provider
 from extensions.ext_database import db
@@ -839,11 +844,18 @@ class ProviderManager:
        :return:
        """
        # Get provider model credential secret variables
-        model_credential_secret_variables = self._extract_secret_variables(
-            provider_entity.model_credential_schema.credential_form_schemas
-            if provider_entity.model_credential_schema
-            else []
-        )
+        if ConfigurateMethod.PREDEFINED_MODEL in provider_entity.configurate_methods:
+            model_credential_secret_variables = self._extract_secret_variables(
+                provider_entity.provider_credential_schema.credential_form_schemas
+                if provider_entity.provider_credential_schema
+                else []
+            )
+        else:
+            model_credential_secret_variables = self._extract_secret_variables(
+                provider_entity.model_credential_schema.credential_form_schemas
+                if provider_entity.model_credential_schema
+                else []
+            )

        model_settings: list[ModelSettings] = []
        if not provider_model_settings:
@@ -258,7 +258,7 @@ class LindormVectorStore(BaseVector):
            hnsw_ef_construction = kwargs.pop("hnsw_ef_construction", 500)
            ivfpq_m = kwargs.pop("ivfpq_m", dimension)
            nlist = kwargs.pop("nlist", 1000)
-            centroids_use_hnsw = kwargs.pop("centroids_use_hnsw", True if nlist >= 5000 else False)
+            centroids_use_hnsw = kwargs.pop("centroids_use_hnsw", nlist >= 5000)
            centroids_hnsw_m = kwargs.pop("centroids_hnsw_m", 24)
            centroids_hnsw_ef_construct = kwargs.pop("centroids_hnsw_ef_construct", 500)
            centroids_hnsw_ef_search = kwargs.pop("centroids_hnsw_ef_search", 100)
@@ -305,7 +305,7 @@ def default_text_mapping(dimension: int, method_name: str, **kwargs: Any) -> dic
    if method_name == "ivfpq":
        ivfpq_m = kwargs["ivfpq_m"]
        nlist = kwargs["nlist"]
-        centroids_use_hnsw = True if nlist > 10000 else False
+        centroids_use_hnsw = nlist > 10000
        centroids_hnsw_m = 24
        centroids_hnsw_ef_construct = 500
        centroids_hnsw_ef_search = 100
@@ -57,6 +57,11 @@ CREATE TABLE IF NOT EXISTS {table_name} (
 ) using heap;
 """

+SQL_CREATE_INDEX = """
+CREATE INDEX IF NOT EXISTS embedding_cosine_v1_idx ON {table_name} 
+USING hnsw (embedding vector_cosine_ops) WITH (m = 16, ef_construction = 64);
+"""
+

 class PGVector(BaseVector):
    def __init__(self, collection_name: str, config: PGVectorConfig):
@@ -205,7 +210,10 @@ class PGVector(BaseVector):
            with self._get_cursor() as cur:
                cur.execute("CREATE EXTENSION IF NOT EXISTS vector")
                cur.execute(SQL_CREATE_TABLE.format(table_name=self.table_name, dimension=dimension))
-                # TODO: create index https://github.com/pgvector/pgvector?tab=readme-ov-file#indexing
+                # PG hnsw index only support 2000 dimension or less
+                # ref: https://github.com/pgvector/pgvector?tab=readme-ov-file#indexing
+                if dimension <= 2000:
+                    cur.execute(SQL_CREATE_INDEX.format(table_name=self.table_name))
            redis_client.set(collection_exist_cache_key, 1, ex=3600)


@@ -74,7 +74,7 @@ class CacheEmbedding(Embeddings):
                            embedding_queue_embeddings.append(normalized_embedding)
                        except IntegrityError:
                            db.session.rollback()
-                        except Exception as e:
+                        except Exception:
                            logging.exception("Failed transform embedding")
                cache_embeddings = []
                try:
@@ -31,7 +31,7 @@ class FirecrawlApp:
                    "markdown": data.get("markdown"),
                }
            else:
-                raise Exception(f'Failed to scrape URL. Error: {response_data["error"]}')
+                raise Exception(f"Failed to scrape URL. Error: {response_data['error']}")

        elif response.status_code in {402, 409, 500}:
            error_message = response.json().get("error", "Unknown error occurred")
@@ -358,8 +358,7 @@ class NotionExtractor(BaseExtractor):

        if not data_source_binding:
            raise Exception(
-                f"No notion data source binding found for tenant {tenant_id} "
-                f"and notion workspace {notion_workspace_id}"
+                f"No notion data source binding found for tenant {tenant_id} and notion workspace {notion_workspace_id}"
            )

        return cast(str, data_source_binding.access_token)
@@ -50,7 +50,7 @@ class WordExtractor(BaseExtractor):

            self.web_path = self.file_path
            # TODO: use a better way to handle the file
-            self.temp_file = tempfile.NamedTemporaryFile()  # noqa: SIM115
+            self.temp_file = tempfile.NamedTemporaryFile()  # noqa SIM115
            self.temp_file.write(r.content)
            self.file_path = self.temp_file.name
        elif not os.path.isfile(self.file_path):
@@ -112,7 +112,7 @@ class QAIndexProcessor(BaseIndexProcessor):
            df = pd.read_csv(file)
            text_docs = []
            for index, row in df.iterrows():
-                data = Document(page_content=row[0], metadata={"answer": row[1]})
+                data = Document(page_content=row.iloc[0], metadata={"answer": row.iloc[1]})
                text_docs.append(data)
            if len(text_docs) == 0:
                raise ValueError("The CSV file is empty.")
@@ -48,6 +48,6 @@ class TimezoneConversionTool(BuiltinTool):
            datetime_with_tz = input_timezone.localize(local_time)
            # timezone convert
            converted_datetime = datetime_with_tz.astimezone(output_timezone)
-            return converted_datetime.strftime(format=time_format)
+            return converted_datetime.strftime(format=time_format)  # type: ignore
        except Exception as e:
            raise ToolInvokeError(str(e))
@@ -5,4 +5,7 @@ from core.tools.builtin_tool.provider import BuiltinToolProviderController

 class WebscraperProvider(BuiltinToolProviderController):
    def _validate_credentials(self, user_id: str, credentials: dict[str, Any]) -> None:
+        """
+        Validate credentials
+        """
        pass
@@ -94,9 +94,9 @@ class ApiTool(Tool):
            if "api_key_header_prefix" in credentials:
                api_key_header_prefix = credentials["api_key_header_prefix"]
                if api_key_header_prefix == "basic" and credentials["api_key_value"]:
-                    credentials["api_key_value"] = f'Basic {credentials["api_key_value"]}'
+                    credentials["api_key_value"] = f"Basic {credentials['api_key_value']}"
                elif api_key_header_prefix == "bearer" and credentials["api_key_value"]:
-                    credentials["api_key_value"] = f'Bearer {credentials["api_key_value"]}'
+                    credentials["api_key_value"] = f"Bearer {credentials['api_key_value']}"
                elif api_key_header_prefix == "custom":
                    pass

@@ -48,7 +48,9 @@ class PluginToolProviderController(BuiltinToolProviderController):
        """
        return tool with given name
        """
-        tool_entity = next(tool_entity for tool_entity in self.entity.tools if tool_entity.identity.name == tool_name)
+        tool_entity = next(
+            (tool_entity for tool_entity in self.entity.tools if tool_entity.identity.name == tool_name), None
+        )

        if not tool_entity:
            raise ValueError(f"Tool with name {tool_name} not found")
@@ -39,7 +39,7 @@ class ToolFileMessageTransformer:
                        conversation_id=conversation_id,
                    )

-                    url = f'/files/tools/{file.id}{guess_extension(file.mimetype) or ".png"}'
+                    url = f"/files/tools/{file.id}{guess_extension(file.mimetype) or '.png'}"

                    yield ToolInvokeMessage(
                        type=ToolInvokeMessage.MessageType.IMAGE_LINK,
@@ -115,4 +115,4 @@ class ToolFileMessageTransformer:

    @classmethod
    def get_tool_file_url(cls, tool_file_id: str, extension: Optional[str]) -> str:
-        return f'/files/tools/{tool_file_id}{extension or ".bin"}'
+        return f"/files/tools/{tool_file_id}{extension or '.bin'}"
@@ -5,6 +5,7 @@ from json import loads as json_loads
 from json.decoder import JSONDecodeError
 from typing import Optional

+from flask import request
 from requests import get
 from yaml import YAMLError, safe_load  # type: ignore

@@ -29,6 +30,10 @@ class ApiBasedToolSchemaParser:
            raise ToolProviderNotFoundError("No server found in the openapi yaml.")

        server_url = openapi["servers"][0]["url"]
+        request_env = request.headers.get("X-Request-Env")
+        if request_env:
+            matched_servers = [server["url"] for server in openapi["servers"] if server["env"] == request_env]
+            server_url = matched_servers[0] if matched_servers else server_url

        # list all interfaces
        interfaces = []
@@ -112,7 +117,7 @@ class ApiBasedToolSchemaParser:
                                llm_description=property.get("description", ""),
                                default=property.get("default", None),
                                placeholder=I18nObject(
-                                    en_US=parameter.get("description", ""), zh_Hans=parameter.get("description", "")
+                                    en_US=property.get("description", ""), zh_Hans=property.get("description", "")
                                ),
                            )

@@ -144,7 +149,7 @@ class ApiBasedToolSchemaParser:
                if not path:
                    path = str(uuid.uuid4())

-                interface["operation"]["operationId"] = f'{path}_{interface["method"]}'
+                interface["operation"]["operationId"] = f"{path}_{interface['method']}"

            bundles.append(
                ApiToolBundle(
@@ -134,6 +134,10 @@ class ArrayStringSegment(ArraySegment):
    value_type: SegmentType = SegmentType.ARRAY_STRING
    value: Sequence[str]

+    @property
+    def text(self) -> str:
+        return json.dumps(self.value)
+

 class ArrayNumberSegment(ArraySegment):
    value_type: SegmentType = SegmentType.ARRAY_NUMBER
@@ -49,3 +49,8 @@ class NodeRunResult(BaseModel):

    # single step node run retry
    retry_index: int = 0
+
+
+class AgentNodeStrategyInit(BaseModel):
+    name: str
+    icon: str | None = None
@@ -4,6 +4,7 @@ from typing import Any, Optional

 from pydantic import BaseModel, Field

+from core.workflow.entities.node_entities import AgentNodeStrategyInit
 from core.workflow.graph_engine.entities.runtime_route_state import RouteNodeState
 from core.workflow.nodes import NodeType
 from core.workflow.nodes.base import BaseNodeData
@@ -66,8 +67,10 @@ class BaseNodeEvent(GraphEngineEvent):

 class NodeRunStartedEvent(BaseNodeEvent):
    predecessor_node_id: Optional[str] = None
-    parallel_mode_run_id: Optional[str] = None
    """predecessor node id"""
+    parallel_mode_run_id: Optional[str] = None
+    """iteration node parallel mode run id"""
+    agent_strategy: Optional[AgentNodeStrategyInit] = None


 class NodeRunStreamChunkEvent(BaseNodeEvent):
@@ -14,7 +14,7 @@ from flask import Flask, current_app
 from configs import dify_config
 from core.app.apps.base_app_queue_manager import GenerateTaskStoppedError
 from core.app.entities.app_invoke_entities import InvokeFrom
-from core.workflow.entities.node_entities import NodeRunMetadataKey, NodeRunResult
+from core.workflow.entities.node_entities import AgentNodeStrategyInit, NodeRunMetadataKey, NodeRunResult
 from core.workflow.entities.variable_pool import VariablePool, VariableValue
 from core.workflow.graph_engine.condition_handlers.condition_manager import ConditionManager
 from core.workflow.graph_engine.entities.event import (
@@ -40,6 +40,8 @@ from core.workflow.graph_engine.entities.graph_init_params import GraphInitParam
 from core.workflow.graph_engine.entities.graph_runtime_state import GraphRuntimeState
 from core.workflow.graph_engine.entities.runtime_route_state import RouteNodeState
 from core.workflow.nodes import NodeType
+from core.workflow.nodes.agent.agent_node import AgentNode
+from core.workflow.nodes.agent.entities import AgentNodeData
 from core.workflow.nodes.answer.answer_stream_processor import AnswerStreamProcessor
 from core.workflow.nodes.answer.base_stream_processor import StreamProcessor
 from core.workflow.nodes.base import BaseNode
@@ -606,6 +608,14 @@ class GraphEngine:
        Run node
        """
        # trigger node run start event
+        agent_strategy = (
+            AgentNodeStrategyInit(
+                name=cast(AgentNodeData, node_instance.node_data).agent_strategy_name,
+                icon=cast(AgentNode, node_instance).agent_strategy_icon,
+            )
+            if node_instance.node_type == NodeType.AGENT
+            else None
+        )
        yield NodeRunStartedEvent(
            id=node_instance.id,
            node_id=node_instance.node_id,
@@ -617,6 +627,7 @@ class GraphEngine:
            parallel_start_node_id=parallel_start_node_id,
            parent_parallel_id=parent_parallel_id,
            parent_parallel_start_node_id=parent_parallel_start_node_id,
+            agent_strategy=agent_strategy,
        )

        db.session.close()
@@ -8,12 +8,12 @@ from core.model_manager import ModelManager
 from core.model_runtime.entities.model_entities import ModelType
 from core.plugin.manager.exc import PluginDaemonClientSideError
 from core.plugin.manager.plugin import PluginInstallationManager
-from core.tools.entities.tool_entities import ToolProviderType
+from core.tools.entities.tool_entities import ToolParameter, ToolProviderType
 from core.tools.tool_manager import ToolManager
 from core.workflow.entities.node_entities import NodeRunResult
 from core.workflow.entities.variable_pool import VariablePool
 from core.workflow.enums import SystemVariableKey
-from core.workflow.nodes.agent.entities import AgentNodeData
+from core.workflow.nodes.agent.entities import AgentNodeData, ParamsAutoGenerated
 from core.workflow.nodes.base.entities import BaseNodeData
 from core.workflow.nodes.enums import NodeType
 from core.workflow.nodes.event.event import RunCompletedEvent
@@ -90,18 +90,11 @@ class AgentNode(ToolNode):

        try:
            # convert tool messages
-            manager = PluginInstallationManager()
-            plugins = manager.list_plugins(self.tenant_id)
-            current_plugin = next(
-                plugin
-                for plugin in plugins
-                if f"{plugin.plugin_id}/{plugin.name}"
-                == cast(AgentNodeData, self.node_data).agent_strategy_provider_name
-            )
+
            yield from self._transform_message(
                message_stream,
                {
-                    "icon": current_plugin.declaration.icon,
+                    "icon": self.agent_strategy_icon,
                    "agent_strategy": cast(AgentNodeData, self.node_data).agent_strategy_name,
                },
                parameters_for_log,
@@ -168,11 +161,29 @@ class AgentNode(ToolNode):
                    value = cast(list[dict[str, Any]], value)
                    tool_value = []
                    for tool in value:
+                        provider_type = ToolProviderType(tool.get("type", ToolProviderType.BUILT_IN.value))
+                        # handle the original settings
+                        original_parameters = tool.get("parameters", {})
+                        setting_params = tool.get("settings", {})
+                        manual_input_params = []
+                        # handle legacy data compatibility
+                        if not all(isinstance(v, dict) for _, v in original_parameters.items()):
+                            parameters = original_parameters
+                        else:
+                            params = {}
+                            for key, param in original_parameters.items():
+                                if param.get("auto", ParamsAutoGenerated.OPEN.value) == ParamsAutoGenerated.CLOSE.value:
+                                    params[key] = param.get("value", "")
+                                    manual_input_params.append(key)
+                                else:
+                                    params[key] = None
+                            settings = {k: v.get("value", None) for k, v in setting_params.items()}
+                            parameters = {**params, **settings}
                        entity = AgentToolEntity(
                            provider_id=tool.get("provider_name", ""),
-                            provider_type=ToolProviderType.BUILT_IN,
+                            provider_type=provider_type,
                            tool_name=tool.get("tool_name", ""),
-                            tool_parameters=tool.get("parameters", {}),
+                            tool_parameters=parameters,
                            plugin_unique_identifier=tool.get("plugin_unique_identifier", None),
                        )

@@ -185,13 +196,27 @@ class AgentNode(ToolNode):
                            tool_runtime.entity.description.llm = (
                                extra.get("descrption", "") or tool_runtime.entity.description.llm
                            )
-
-                        tool_value.append(
-                            {
-                                **tool_runtime.entity.model_dump(mode="json"),
-                                "runtime_parameters": tool_runtime.runtime.runtime_parameters,
+                        for params in tool_runtime.entity.parameters:
+                            params.form = (
+                                ToolParameter.ToolParameterForm.FORM
+                                if params.name in manual_input_params
+                                else params.form
+                            )
+                        if tool_runtime.entity.parameters:
+                            manual_input_value = {
+                                key: value for key, value in parameters.items() if key in manual_input_params
                            }
-                        )
+                            runtime_parameters = {
+                                **tool_runtime.runtime.runtime_parameters,
+                                **manual_input_value,
+                            }
+                            tool_value.append(
+                                {
+                                    **tool_runtime.entity.model_dump(mode="json"),
+                                    "runtime_parameters": runtime_parameters,
+                                    "provider_type": provider_type.value,
+                                }
+                            )
                    value = tool_value
                if parameter.type == "model-selector":
                    value = cast(dict[str, Any], value)
@@ -229,16 +254,33 @@ class AgentNode(ToolNode):
        result: dict[str, Any] = {}
        for parameter_name in node_data.agent_parameters:
            input = node_data.agent_parameters[parameter_name]
-            if input.type == "mixed":
-                assert isinstance(input.value, str)
-                selectors = VariableTemplateParser(input.value).extract_variable_selectors()
+            if input.type in ["mixed", "constant"]:
+                selectors = VariableTemplateParser(str(input.value)).extract_variable_selectors()
                for selector in selectors:
                    result[selector.variable] = selector.value_selector
            elif input.type == "variable":
                result[parameter_name] = input.value
-            elif input.type == "constant":
-                pass

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

        return result
+
+    @property
+    def agent_strategy_icon(self) -> str | None:
+        """
+        Get agent strategy icon
+        :return:
+        """
+        manager = PluginInstallationManager()
+        plugins = manager.list_plugins(self.tenant_id)
+        try:
+            current_plugin = next(
+                plugin
+                for plugin in plugins
+                if f"{plugin.plugin_id}/{plugin.name}"
+                == cast(AgentNodeData, self.node_data).agent_strategy_provider_name
+            )
+            icon = current_plugin.declaration.icon
+        except StopIteration:
+            icon = None
+        return icon
@@ -1,3 +1,4 @@
+from enum import Enum
 from typing import Any, Literal, Union

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

    agent_parameters: dict[str, AgentInput]
+
+
+class ParamsAutoGenerated(Enum):
+    CLOSE = 0
+    OPEN = 1
@@ -1,6 +1,7 @@
 import logging
 from abc import ABC, abstractmethod
 from collections.abc import Generator
+from typing import Optional

 from core.workflow.entities.variable_pool import VariablePool
 from core.workflow.graph_engine.entities.event import GraphEngineEvent, NodeRunExceptionEvent, NodeRunSucceededEvent
@@ -48,25 +49,35 @@ class StreamProcessor(ABC):
                    # we remove the node maybe shortcut the answer node, so comment this code for now
                    # there is not effect on the answer node and the workflow, when we have a better solution
                    # we can open this code. Issues: #11542 #9560 #10638 #10564
-                    ids = self._fetch_node_ids_in_reachable_branch(edge.target_node_id)
-                    if "answer" in ids:
-                        continue
-                    else:
-                        reachable_node_ids.extend(ids)
+                    # ids = self._fetch_node_ids_in_reachable_branch(edge.target_node_id)
+                    # if "answer" in ids:
+                    #     continue
+                    # else:
+                    #     reachable_node_ids.extend(ids)
+
+                    # The branch_identify parameter is added to ensure that
+                    # only nodes in the correct logical branch are included.
+                    ids = self._fetch_node_ids_in_reachable_branch(edge.target_node_id, run_result.edge_source_handle)
+                    reachable_node_ids.extend(ids)
                else:
                    unreachable_first_node_ids.append(edge.target_node_id)

            for node_id in unreachable_first_node_ids:
                self._remove_node_ids_in_unreachable_branch(node_id, reachable_node_ids)

-    def _fetch_node_ids_in_reachable_branch(self, node_id: str) -> list[str]:
+    def _fetch_node_ids_in_reachable_branch(self, node_id: str, branch_identify: Optional[str] = None) -> list[str]:
        node_ids = []
        for edge in self.graph.edge_mapping.get(node_id, []):
            if edge.target_node_id == self.graph.root_node_id:
                continue

+            # Only follow edges that match the branch_identify or have no run_condition
+            if edge.run_condition and edge.run_condition.branch_identify:
+                if not branch_identify or edge.run_condition.branch_identify != branch_identify:
+                    continue
+
            node_ids.append(edge.target_node_id)
-            node_ids.extend(self._fetch_node_ids_in_reachable_branch(edge.target_node_id))
+            node_ids.extend(self._fetch_node_ids_in_reachable_branch(edge.target_node_id, branch_identify))
        return node_ids

    def _remove_node_ids_in_unreachable_branch(self, node_id: str, reachable_node_ids: list[str]) -> None:
@@ -64,7 +64,7 @@ class EndStreamGeneratorRouter:
                node_type = node.get("data", {}).get("type")
                if (
                    variable_selector.value_selector not in value_selectors
-                    and node_type == NodeType.LLM.value
+                    and (node_type in (NodeType.LLM.value, NodeType.AGENT.value))
                    and variable_selector.value_selector[1] == "text"
                ):
                    value_selectors.append(list(variable_selector.value_selector))
@@ -253,9 +253,9 @@ class Executor:
        )
        if executor_response.size > threshold_size:
            raise ResponseSizeError(
-                f'{"File" if executor_response.is_file else "Text"} size is too large,'
-                f' max size is {threshold_size / 1024 / 1024:.2f} MB,'
-                f' but current size is {executor_response.readable_size}.'
+                f"{'File' if executor_response.is_file else 'Text'} size is too large,"
+                f" max size is {threshold_size / 1024 / 1024:.2f} MB,"
+                f" but current size is {executor_response.readable_size}."
            )

        return executor_response
@@ -338,7 +338,7 @@ class Executor:
                if self.auth.config and self.auth.config.header:
                    authorization_header = self.auth.config.header
                if k.lower() == authorization_header.lower():
-                    raw += f'{k}: {"*" * len(v)}\r\n'
+                    raw += f"{k}: {'*' * len(v)}\r\n"
                    continue
            raw += f"{k}: {v}\r\n"

@@ -1,4 +1,5 @@
 import json
+from collections.abc import Sequence
 from typing import Any, cast

 from core.variables import SegmentType, Variable
@@ -31,7 +32,7 @@ class VariableAssignerNode(BaseNode[VariableAssignerNodeData]):
        inputs = self.node_data.model_dump()
        process_data: dict[str, Any] = {}
        # NOTE: This node has no outputs
-        updated_variables: list[Variable] = []
+        updated_variable_selectors: list[Sequence[str]] = []

        try:
            for item in self.node_data.items:
@@ -98,7 +99,8 @@ class VariableAssignerNode(BaseNode[VariableAssignerNodeData]):
                    value=item.value,
                )
                variable = variable.model_copy(update={"value": updated_value})
-                updated_variables.append(variable)
+                self.graph_runtime_state.variable_pool.add(variable.selector, variable)
+                updated_variable_selectors.append(variable.selector)
        except VariableOperatorNodeError as e:
            return NodeRunResult(
                status=WorkflowNodeExecutionStatus.FAILED,
@@ -107,9 +109,15 @@ class VariableAssignerNode(BaseNode[VariableAssignerNodeData]):
                error=str(e),
            )

+        # The `updated_variable_selectors` is a list contains list[str] which not hashable,
+        # remove the duplicated items first.
+        updated_variable_selectors = list(set(map(tuple, updated_variable_selectors)))
+
        # Update variables
-        for variable in updated_variables:
-            self.graph_runtime_state.variable_pool.add(variable.selector, variable)
+        for selector in updated_variable_selectors:
+            variable = self.graph_runtime_state.variable_pool.get(selector)
+            if not isinstance(variable, Variable):
+                raise VariableNotFoundError(variable_selector=selector)
            process_data[variable.name] = variable.value

            if variable.selector[0] == CONVERSATION_VARIABLE_NODE_ID:
@@ -26,7 +26,7 @@ def handle(sender, **kwargs):
                    tool_runtime=tool_runtime,
                    provider_name=tool_entity.provider_name,
                    provider_type=tool_entity.provider_type,
-                    identity_id=f'WORKFLOW.{app.id}.{node_data.get("id")}',
+                    identity_id=f"WORKFLOW.{app.id}.{node_data.get('id')}",
                )
                manager.delete_tool_parameters_cache()
            except:
@@ -34,7 +34,7 @@ class OpenDALStorage(BaseStorage):
            root = kwargs.get("root", "storage")
            Path(root).mkdir(parents=True, exist_ok=True)

-        self.op = opendal.Operator(scheme=scheme, **kwargs)
+        self.op = opendal.Operator(scheme=scheme, **kwargs)  # type: ignore
        logger.debug(f"opendal operator created with scheme {scheme}")
        retry_layer = opendal.layers.RetryLayer(max_times=3, factor=2.0, jitter=True)
        self.op = self.op.layer(retry_layer)
@@ -14,6 +14,7 @@ segment_fields = {
    "position": fields.Integer,
    "document_id": fields.String,
    "content": fields.String,
+    "sign_content": fields.String,
    "answer": fields.String,
    "word_count": fields.Integer,
    "tokens": fields.Integer,
@@ -1,6 +1,6 @@
 from flask_restful import fields  # type: ignore

-from libs.helper import TimestampField
+from libs.helper import AvatarUrlField, TimestampField

 simple_account_fields = {"id": fields.String, "name": fields.String, "email": fields.String}

@@ -8,6 +8,7 @@ account_fields = {
    "id": fields.String,
    "name": fields.String,
    "avatar": fields.String,
+    "avatar_url": AvatarUrlField,
    "email": fields.String,
    "is_password_set": fields.Boolean,
    "interface_language": fields.String,
@@ -22,6 +23,7 @@ account_with_role_fields = {
    "id": fields.String,
    "name": fields.String,
    "avatar": fields.String,
+    "avatar_url": AvatarUrlField,
    "email": fields.String,
    "last_login_at": TimestampField,
    "last_active_at": TimestampField,
@@ -18,6 +18,7 @@ segment_fields = {
    "position": fields.Integer,
    "document_id": fields.String,
    "content": fields.String,
+    "sign_content": fields.String,
    "answer": fields.String,
    "word_count": fields.Integer,
    "tokens": fields.Integer,
@@ -43,6 +43,18 @@ class AppIconUrlField(fields.Raw):
        return None


+class AvatarUrlField(fields.Raw):
+    def output(self, key, obj):
+        if obj is None:
+            return None
+
+        from models.account import Account
+
+        if isinstance(obj, Account) and obj.avatar is not None:
+            return file_helpers.get_signed_file_url(obj.avatar)
+        return None
+
+
 class TimestampField(fields.Raw):
    def format(self, value) -> int:
        return int(value.timestamp())
@@ -13,6 +13,7 @@ from typing import Any, cast

 from sqlalchemy import func
 from sqlalchemy.dialects.postgresql import JSONB
+from sqlalchemy.orm import Mapped

 from configs import dify_config
 from core.rag.retrieval.retrieval_methods import RetrievalMethod
@@ -515,7 +516,7 @@ class DocumentSegment(db.Model):  # type: ignore[name-defined]
    tenant_id = db.Column(StringUUID, nullable=False)
    dataset_id = db.Column(StringUUID, nullable=False)
    document_id = db.Column(StringUUID, nullable=False)
-    position = db.Column(db.Integer, nullable=False)
+    position: Mapped[int]
    content = db.Column(db.Text, nullable=False)
    answer = db.Column(db.Text, nullable=True)
    word_count = db.Column(db.Integer, nullable=False)
@@ -583,6 +584,10 @@ class DocumentSegment(db.Model):  # type: ignore[name-defined]
        else:
            return []

+    @property
+    def sign_content(self):
+        return self.get_sign_content()
+
    def get_sign_content(self):
        signed_urls = []
        text = self.content
@@ -743,7 +748,7 @@ class DatasetKeywordTable(db.Model):  # type: ignore[name-defined]
                if keyword_table_text:
                    return json.loads(keyword_table_text.decode("utf-8"), cls=SetDecoder)
                return None
-            except Exception as e:
+            except Exception:
                logging.exception(f"Failed to load keyword table from file: {file_key}")
                return None

@@ -1486,9 +1486,8 @@ class ApiToken(Base):
    def generate_api_key(prefix, n):
        while True:
            result = prefix + generate_string(n)
-            while db.session.query(ApiToken).filter(ApiToken.token == result).count() > 0:
-                result = prefix + generate_string(n)
-
+            if db.session.query(ApiToken).filter(ApiToken.token == result).count() > 0:
+                continue
            return result


@@ -1,9 +1,10 @@
 [project]
 name = "dify-api"
 requires-python = ">=3.11,<3.13"
+dynamic = [ "dependencies" ]

 [build-system]
-requires = ["poetry-core"]
+requires = ["poetry-core>=2.0.0"]
 build-backend = "poetry.core.masonry.api"

 [tool.poetry]
@@ -48,6 +49,7 @@ numpy = "~1.26.4"
 oci = "~2.135.1"
 openai = "~1.52.0"
 openpyxl = "~3.1.5"
+opik = "~1.3.4"
 pandas = { version = "~2.2.2", extras = ["performance", "excel"] }
 pandas-stubs = "~2.2.3.241009"
 psycogreen = "~1.0.2"
@@ -157,4 +159,4 @@ pytest-mock = "~3.14.0"
 optional = true
 [tool.poetry.group.lint.dependencies]
 dotenv-linter = "~0.5.0"
-ruff = "~0.8.1"
+ruff = "~0.9.2"
@@ -7,6 +7,12 @@ env =
    CODE_EXECUTION_API_KEY = dify-sandbox
    CODE_EXECUTION_ENDPOINT = http://127.0.0.1:8194
    CODE_MAX_STRING_LENGTH = 80000
+    PLUGIN_DAEMON_KEY=lYkiYYT6owG+71oLerGzA7GXCgOT++6ovaezWAjpCjf+Sjc3ZtU+qUEi
+    PLUGIN_DAEMON_URL=http://127.0.0.1:5002
+    PLUGIN_MAX_PACKAGE_SIZE=15728640
+    INNER_API_KEY_FOR_PLUGIN=QaHbTe77CtuXmsfyhR7+vRjI/+XbV1AaFy691iy+kGDv2Jvy0/eAh8Y1
+    MARKETPLACE_ENABLED=true
+    MARKETPLACE_API_URL=https://marketplace.dify.ai
    FIRECRAWL_API_KEY = fc-
    FIREWORKS_API_KEY = fw_aaaaaaaaaaaaaaaaaaaa
    GOOGLE_API_KEY = abcdefghijklmnopqrstuvwxyz
@@ -286,7 +286,7 @@ class AppAnnotationService:
            df = pd.read_csv(file)
            result = []
            for index, row in df.iterrows():
-                content = {"question": row[0], "answer": row[1]}
+                content = {"question": row.iloc[0], "answer": row.iloc[1]}
                result.append(content)
            if len(result) == 0:
                raise ValueError("The CSV file is empty.")
@@ -1,7 +1,7 @@
 import logging
 import uuid
 from enum import StrEnum
-from typing import Optional, cast
+from typing import Optional
 from urllib.parse import urlparse
 from uuid import uuid4

@@ -159,15 +159,6 @@ class AppDslService:
                        status=ImportStatus.FAILED,
                        error="Empty content from url",
                    )
-
-                try:
-                    content = cast(bytes, content).decode("utf-8")
-                except UnicodeDecodeError as e:
-                    return Import(
-                        id=import_id,
-                        status=ImportStatus.FAILED,
-                        error=f"Error decoding content: {e}",
-                    )
            except Exception as e:
                return Import(
                    id=import_id,
@@ -82,7 +82,7 @@ class AudioService:
        from app import app
        from extensions.ext_database import db

-        def invoke_tts(text_content: str, app_model, voice: Optional[str] = None):
+        def invoke_tts(text_content: str, app_model: App, voice: Optional[str] = None):
            with app.app_context():
                if app_model.mode in {AppMode.ADVANCED_CHAT.value, AppMode.WORKFLOW.value}:
                    workflow = app_model.workflow
@@ -95,6 +95,8 @@ class AudioService:

                    voice = features_dict["text_to_speech"].get("voice") if voice is None else voice
                else:
+                    if app_model.app_model_config is None:
+                        raise ValueError("AppModelConfig not found")
                    text_to_speech_dict = app_model.app_model_config.text_to_speech_dict

                    if not text_to_speech_dict.get("enabled"):
@@ -4,13 +4,16 @@ import logging
 import random
 import time
 import uuid
+from collections import Counter
 from typing import Any, Optional

 from flask_login import current_user  # type: ignore
 from sqlalchemy import func
+from sqlalchemy.orm import Session
 from werkzeug.exceptions import NotFound

 from configs import dify_config
+from core.entities import DEFAULT_PLUGIN_ID
 from core.errors.error import LLMBadRequestError, ProviderTokenNotInitError
 from core.model_manager import ModelManager
 from core.model_runtime.entities.model_entities import ModelType
@@ -71,7 +74,7 @@ from tasks.sync_website_document_indexing_task import sync_website_document_inde

 class DatasetService:
    @staticmethod
-    def get_datasets(page, per_page, tenant_id=None, user=None, search=None, tag_ids=None):
+    def get_datasets(page, per_page, tenant_id=None, user=None, search=None, tag_ids=None, include_all=False):
        query = Dataset.query.filter(Dataset.tenant_id == tenant_id).order_by(Dataset.created_at.desc())

        if user:
@@ -86,7 +89,7 @@ class DatasetService:
                else:
                    return [], 0
            else:
-                if user.current_role != TenantAccountRole.OWNER:
+                if user.current_role != TenantAccountRole.OWNER or not include_all:
                    # show all datasets that the user has permission to access
                    if permitted_dataset_ids:
                        query = query.filter(
@@ -221,8 +224,7 @@ class DatasetService:
                )
            except LLMBadRequestError:
                raise ValueError(
-                    "No Embedding Model available. Please configure a valid provider "
-                    "in the Settings -> Model Provider."
+                    "No Embedding Model available. Please configure a valid provider in the Settings -> Model Provider."
                )
            except ProviderTokenNotInitError as ex:
                raise ValueError(f"The dataset in unavailable, due to: {ex.description}")
@@ -267,7 +269,15 @@ class DatasetService:
            external_knowledge_api_id = data.get("external_knowledge_api_id", None)
            if not external_knowledge_api_id:
                raise ValueError("External knowledge api id is required.")
-            external_knowledge_binding = ExternalKnowledgeBindings.query.filter_by(dataset_id=dataset_id).first()
+
+            with Session(db.engine) as session:
+                external_knowledge_binding = (
+                    session.query(ExternalKnowledgeBindings).filter_by(dataset_id=dataset_id).first()
+                )
+
+                if not external_knowledge_binding:
+                    raise ValueError("External knowledge binding not found.")
+
            if (
                external_knowledge_binding.external_knowledge_id != external_knowledge_id
                or external_knowledge_binding.external_knowledge_api_id != external_knowledge_api_id
@@ -315,8 +325,19 @@ class DatasetService:
                    except ProviderTokenNotInitError as ex:
                        raise ValueError(ex.description)
            else:
+                # add default plugin id to both setting sets, to make sure the plugin model provider is consistent
+                plugin_model_provider = dataset.embedding_model_provider
+                if "/" not in plugin_model_provider:
+                    plugin_model_provider = f"{DEFAULT_PLUGIN_ID}/{plugin_model_provider}/{plugin_model_provider}"
+
+                new_plugin_model_provider = data["embedding_model_provider"]
+                if "/" not in new_plugin_model_provider:
+                    new_plugin_model_provider = (
+                        f"{DEFAULT_PLUGIN_ID}/{new_plugin_model_provider}/{new_plugin_model_provider}"
+                    )
+
                if (
-                    data["embedding_model_provider"] != dataset.embedding_model_provider
+                    new_plugin_model_provider != plugin_model_provider
                    or data["embedding_model"] != dataset.embedding_model
                ):
                    action = "update"
@@ -859,7 +880,7 @@ class DocumentService:
                position = DocumentService.get_documents_position(dataset.id)
                document_ids = []
                duplicate_document_ids = []
-                if knowledge_config.data_source.info_list.data_source_type == "upload_file":
+                if knowledge_config.data_source.info_list.data_source_type == "upload_file":  # type: ignore
                    upload_file_list = knowledge_config.data_source.info_list.file_info_list.file_ids  # type: ignore
                    for file_id in upload_file_list:
                        file = (
@@ -901,7 +922,7 @@ class DocumentService:
                        document = DocumentService.build_document(
                            dataset,
                            dataset_process_rule.id,  # type: ignore
-                            knowledge_config.data_source.info_list.data_source_type,
+                            knowledge_config.data_source.info_list.data_source_type,  # type: ignore
                            knowledge_config.doc_form,
                            knowledge_config.doc_language,
                            data_source_info,
@@ -916,8 +937,8 @@ class DocumentService:
                        document_ids.append(document.id)
                        documents.append(document)
                        position += 1
-                elif knowledge_config.data_source.info_list.data_source_type == "notion_import":
-                    notion_info_list = knowledge_config.data_source.info_list.notion_info_list
+                elif knowledge_config.data_source.info_list.data_source_type == "notion_import":  # type: ignore
+                    notion_info_list = knowledge_config.data_source.info_list.notion_info_list  # type: ignore
                    if not notion_info_list:
                        raise ValueError("No notion info list found.")
                    exist_page_ids = []
@@ -956,7 +977,7 @@ class DocumentService:
                                document = DocumentService.build_document(
                                    dataset,
                                    dataset_process_rule.id,  # type: ignore
-                                    knowledge_config.data_source.info_list.data_source_type,
+                                    knowledge_config.data_source.info_list.data_source_type,  # type: ignore
                                    knowledge_config.doc_form,
                                    knowledge_config.doc_language,
                                    data_source_info,
@@ -976,8 +997,8 @@ class DocumentService:
                    # delete not selected documents
                    if len(exist_document) > 0:
                        clean_notion_document_task.delay(list(exist_document.values()), dataset.id)
-                elif knowledge_config.data_source.info_list.data_source_type == "website_crawl":
-                    website_info = knowledge_config.data_source.info_list.website_info_list
+                elif knowledge_config.data_source.info_list.data_source_type == "website_crawl":  # type: ignore
+                    website_info = knowledge_config.data_source.info_list.website_info_list  # type: ignore
                    if not website_info:
                        raise ValueError("No website info list found.")
                    urls = website_info.urls
@@ -996,7 +1017,7 @@ class DocumentService:
                        document = DocumentService.build_document(
                            dataset,
                            dataset_process_rule.id,  # type: ignore
-                            knowledge_config.data_source.info_list.data_source_type,
+                            knowledge_config.data_source.info_list.data_source_type,  # type: ignore
                            knowledge_config.doc_form,
                            knowledge_config.doc_language,
                            data_source_info,
@@ -1195,20 +1216,20 @@ class DocumentService:

        if features.billing.enabled:
            count = 0
-            if knowledge_config.data_source.info_list.data_source_type == "upload_file":
+            if knowledge_config.data_source.info_list.data_source_type == "upload_file":  # type: ignore
                upload_file_list = (
-                    knowledge_config.data_source.info_list.file_info_list.file_ids
-                    if knowledge_config.data_source.info_list.file_info_list
+                    knowledge_config.data_source.info_list.file_info_list.file_ids  # type: ignore
+                    if knowledge_config.data_source.info_list.file_info_list  # type: ignore
                    else []
                )
                count = len(upload_file_list)
-            elif knowledge_config.data_source.info_list.data_source_type == "notion_import":
-                notion_info_list = knowledge_config.data_source.info_list.notion_info_list
+            elif knowledge_config.data_source.info_list.data_source_type == "notion_import":  # type: ignore
+                notion_info_list = knowledge_config.data_source.info_list.notion_info_list  # type: ignore
                if notion_info_list:
                    for notion_info in notion_info_list:
                        count = count + len(notion_info.pages)
-            elif knowledge_config.data_source.info_list.data_source_type == "website_crawl":
-                website_info = knowledge_config.data_source.info_list.website_info_list
+            elif knowledge_config.data_source.info_list.data_source_type == "website_crawl":  # type: ignore
+                website_info = knowledge_config.data_source.info_list.website_info_list  # type: ignore
                if website_info:
                    count = len(website_info.urls)
            batch_upload_limit = int(dify_config.BATCH_UPLOAD_LIMIT)
@@ -1239,7 +1260,7 @@ class DocumentService:
        dataset = Dataset(
            tenant_id=tenant_id,
            name="",
-            data_source_type=knowledge_config.data_source.info_list.data_source_type,
+            data_source_type=knowledge_config.data_source.info_list.data_source_type,  # type: ignore
            indexing_technique=knowledge_config.indexing_technique,
            created_by=account.id,
            embedding_model=knowledge_config.embedding_model,
@@ -1614,8 +1635,11 @@ class SegmentService:
                    segment.answer = args.answer
                    segment.word_count += len(args.answer) if args.answer else 0
                word_count_change = segment.word_count - word_count_change
+                keyword_changed = False
                if args.keywords:
-                    segment.keywords = args.keywords
+                    if Counter(segment.keywords) != Counter(args.keywords):
+                        segment.keywords = args.keywords
+                        keyword_changed = True
                segment.enabled = True
                segment.disabled_at = None
                segment.disabled_by = None
@@ -1626,13 +1650,6 @@ class SegmentService:
                    document.word_count = max(0, document.word_count + word_count_change)
                    db.session.add(document)
                # update segment index task
-                if args.enabled:
-                    VectorService.create_segments_vector(
-                        [args.keywords] if args.keywords else None,
-                        [segment],
-                        dataset,
-                        document.doc_form,
-                    )
                if document.doc_form == IndexType.PARENT_CHILD_INDEX and args.regenerate_child_chunks:
                    # regenerate child chunks
                    # get embedding model instance
@@ -1665,6 +1682,14 @@ class SegmentService:
                    VectorService.generate_child_chunks(
                        segment, document, dataset, embedding_model_instance, processing_rule, True
                    )
+                elif document.doc_form in (IndexType.PARAGRAPH_INDEX, IndexType.QA_INDEX):
+                    if args.enabled or keyword_changed:
+                        VectorService.create_segments_vector(
+                            [args.keywords] if args.keywords else None,
+                            [segment],
+                            dataset,
+                            document.doc_form,
+                        )
            else:
                segment_hash = helper.generate_text_hash(content)
                tokens = 0
@@ -97,7 +97,7 @@ class KnowledgeConfig(BaseModel):
    original_document_id: Optional[str] = None
    duplicate: bool = True
    indexing_technique: Literal["high_quality", "economy"]
-    data_source: DataSource
+    data_source: Optional[DataSource] = None
    process_rule: Optional[ProcessRule] = None
    retrieval_model: Optional[RetrievalModel] = None
    doc_form: str = "text_model"
@@ -155,7 +155,7 @@ class ExternalDatasetService:
            if custom_parameters:
                for parameter in custom_parameters:
                    if parameter.get("required", False) and not process_parameter.get(parameter.get("name")):
-                        raise ValueError(f'{parameter.get("name")} is required')
+                        raise ValueError(f"{parameter.get('name')} is required")

    @staticmethod
    def process_external_api(
@@ -59,6 +59,15 @@ class OpsService:
            except Exception:
                new_decrypt_tracing_config.update({"project_url": "https://smith.langchain.com/"})

+        if tracing_provider == "opik" and (
+            "project_url" not in decrypt_tracing_config or not decrypt_tracing_config.get("project_url")
+        ):
+            try:
+                project_url = OpsTraceManager.get_trace_config_project_url(decrypt_tracing_config, tracing_provider)
+                new_decrypt_tracing_config.update({"project_url": project_url})
+            except Exception:
+                new_decrypt_tracing_config.update({"project_url": "https://www.comet.com/opik/"})
+
        trace_config_data.tracing_config = new_decrypt_tracing_config
        return trace_config_data.to_dict()

@@ -92,7 +101,7 @@ class OpsService:
        if tracing_provider == "langfuse":
            project_key = OpsTraceManager.get_trace_config_project_key(tracing_config, tracing_provider)
            project_url = "{host}/project/{key}".format(host=tracing_config.get("host"), key=project_key)
-        elif tracing_provider == "langsmith":
+        elif tracing_provider in ("langsmith", "opik"):
            project_url = OpsTraceManager.get_trace_config_project_url(tracing_config, tracing_provider)
        else:
            project_url = None
@@ -5,7 +5,8 @@ import uuid

 import click
 from celery import shared_task  # type: ignore
-from sqlalchemy import func
+from sqlalchemy import func, select
+from sqlalchemy.orm import Session

 from core.model_manager import ModelManager
 from core.model_runtime.entities.model_entities import ModelType
@@ -18,7 +19,12 @@ from services.vector_service import VectorService

@shared_task(queue="dataset")
 def batch_create_segment_to_index_task(
-    job_id: str, content: list, dataset_id: str, document_id: str, tenant_id: str, user_id: str
+    job_id: str,
+    content: list,
+    dataset_id: str,
+    document_id: str,
+    tenant_id: str,
+    user_id: str,
 ):
    """
    Async batch create segment to index
@@ -37,25 +43,35 @@ def batch_create_segment_to_index_task(
    indexing_cache_key = "segment_batch_import_{}".format(job_id)

    try:
-        dataset = db.session.query(Dataset).filter(Dataset.id == dataset_id).first()
-        if not dataset:
-            raise ValueError("Dataset not exist.")
+        with Session(db.engine) as session:
+            dataset = session.get(Dataset, dataset_id)
+            if not dataset:
+                raise ValueError("Dataset not exist.")

-        dataset_document = db.session.query(Document).filter(Document.id == document_id).first()
-        if not dataset_document:
-            raise ValueError("Document not exist.")
+            dataset_document = session.get(Document, document_id)
+            if not dataset_document:
+                raise ValueError("Document not exist.")

-        if not dataset_document.enabled or dataset_document.archived or dataset_document.indexing_status != "completed":
-            raise ValueError("Document is not available.")
-        document_segments = []
-        embedding_model = None
-        if dataset.indexing_technique == "high_quality":
-            model_manager = ModelManager()
-            embedding_model = model_manager.get_model_instance(
-                tenant_id=dataset.tenant_id,
-                provider=dataset.embedding_model_provider,
-                model_type=ModelType.TEXT_EMBEDDING,
-                model=dataset.embedding_model,
+            if (
+                not dataset_document.enabled
+                or dataset_document.archived
+                or dataset_document.indexing_status != "completed"
+            ):
+                raise ValueError("Document is not available.")
+            document_segments = []
+            embedding_model = None
+            if dataset.indexing_technique == "high_quality":
+                model_manager = ModelManager()
+                embedding_model = model_manager.get_model_instance(
+                    tenant_id=dataset.tenant_id,
+                    provider=dataset.embedding_model_provider,
+                    model_type=ModelType.TEXT_EMBEDDING,
+                    model=dataset.embedding_model,
+                )
+            word_count_change = 0
+            segments_to_insert: list[str] = []
+            max_position_stmt = select(func.max(DocumentSegment.position)).where(
+                DocumentSegment.document_id == dataset_document.id
            )
        word_count_change = 0
        if embedding_model:
@@ -103,7 +119,10 @@ def batch_create_segment_to_index_task(
        redis_client.setex(indexing_cache_key, 600, "completed")
        end_at = time.perf_counter()
        logging.info(
-            click.style("Segment batch created job: {} latency: {}".format(job_id, end_at - start_at), fg="green")
+            click.style(
+                "Segment batch created job: {} latency: {}".format(job_id, end_at - start_at),
+                fg="green",
+            )
        )
    except Exception:
        logging.exception("Segments batch created index failed")
@@ -44,6 +44,6 @@ def test_duplicated_dependency_crossing_groups() -> None:
        dependency_names = list(dependencies.keys())
        all_dependency_names.extend(dependency_names)
    expected_all_dependency_names = set(all_dependency_names)
-    assert sorted(expected_all_dependency_names) == sorted(
-        all_dependency_names
-    ), "Duplicated dependencies crossing groups are found"
+    assert sorted(expected_all_dependency_names) == sorted(all_dependency_names), (
+        "Duplicated dependencies crossing groups are found"
+    )
@@ -85,7 +85,7 @@ VOLC_EMBEDDING_ENDPOINT_ID=
 ZHINAO_API_KEY=

 # Plugin configuration
-PLUGIN_API_KEY=
+PLUGIN_DAEMON_KEY=
 PLUGIN_DAEMON_URL=
 INNER_API_KEY=

@@ -4,7 +4,6 @@ from app_fixture import mock_user  # type: ignore


 def test_post_requires_login(app):
-    with app.test_client() as client:
-        with patch("flask_login.utils._get_user", mock_user):
-            response = client.get("/console/api/data-source/integrates")
-            assert response.status_code == 200
+    with app.test_client() as client, patch("flask_login.utils._get_user", mock_user):
+        response = client.get("/console/api/data-source/integrates")
+        assert response.status_code == 200
@@ -0,0 +1,44 @@
+import os
+from collections.abc import Callable
+
+import pytest
+
+# import monkeypatch
+from _pytest.monkeypatch import MonkeyPatch
+
+from core.plugin.manager.model import PluginModelManager
+from tests.integration_tests.model_runtime.__mock.plugin_model import MockModelClass
+
+
+def mock_plugin_daemon(
+    monkeypatch: MonkeyPatch,
+) -> Callable[[], None]:
+    """
+    mock openai module
+
+    :param monkeypatch: pytest monkeypatch fixture
+    :return: unpatch function
+    """
+
+    def unpatch() -> None:
+        monkeypatch.undo()
+
+    monkeypatch.setattr(PluginModelManager, "invoke_llm", MockModelClass.invoke_llm)
+    monkeypatch.setattr(PluginModelManager, "fetch_model_providers", MockModelClass.fetch_model_providers)
+    monkeypatch.setattr(PluginModelManager, "get_model_schema", MockModelClass.get_model_schema)
+
+    return unpatch
+
+
+MOCK = os.getenv("MOCK_SWITCH", "false").lower() == "true"
+
+
+@pytest.fixture
+def setup_model_mock(monkeypatch):
+    if MOCK:
+        unpatch = mock_plugin_daemon(monkeypatch)
+
+    yield
+
+    if MOCK:
+        unpatch()
@@ -0,0 +1,249 @@
+import datetime
+import uuid
+from collections.abc import Generator, Sequence
+from decimal import Decimal
+from json import dumps
+
+# import monkeypatch
+from typing import Optional
+
+from core.model_runtime.entities.common_entities import I18nObject
+from core.model_runtime.entities.llm_entities import LLMMode, LLMResult, LLMResultChunk, LLMResultChunkDelta, LLMUsage
+from core.model_runtime.entities.message_entities import AssistantPromptMessage, PromptMessage, PromptMessageTool
+from core.model_runtime.entities.model_entities import (
+    AIModelEntity,
+    FetchFrom,
+    ModelFeature,
+    ModelPropertyKey,
+    ModelType,
+)
+from core.model_runtime.entities.provider_entities import ConfigurateMethod, ProviderEntity
+from core.plugin.entities.plugin_daemon import PluginModelProviderEntity
+from core.plugin.manager.model import PluginModelManager
+
+
+class MockModelClass(PluginModelManager):
+    def fetch_model_providers(self, tenant_id: str) -> Sequence[PluginModelProviderEntity]:
+        """
+        Fetch model providers for the given tenant.
+        """
+        return [
+            PluginModelProviderEntity(
+                id=uuid.uuid4().hex,
+                created_at=datetime.datetime.now(),
+                updated_at=datetime.datetime.now(),
+                provider="openai",
+                tenant_id=tenant_id,
+                plugin_unique_identifier="langgenius/openai/openai",
+                plugin_id="langgenius/openai",
+                declaration=ProviderEntity(
+                    provider="openai",
+                    label=I18nObject(
+                        en_US="OpenAI",
+                        zh_Hans="OpenAI",
+                    ),
+                    description=I18nObject(
+                        en_US="OpenAI",
+                        zh_Hans="OpenAI",
+                    ),
+                    icon_small=I18nObject(
+                        en_US="https://example.com/icon_small.png",
+                        zh_Hans="https://example.com/icon_small.png",
+                    ),
+                    icon_large=I18nObject(
+                        en_US="https://example.com/icon_large.png",
+                        zh_Hans="https://example.com/icon_large.png",
+                    ),
+                    supported_model_types=[ModelType.LLM],
+                    configurate_methods=[ConfigurateMethod.PREDEFINED_MODEL],
+                    models=[
+                        AIModelEntity(
+                            model="gpt-3.5-turbo",
+                            label=I18nObject(
+                                en_US="gpt-3.5-turbo",
+                                zh_Hans="gpt-3.5-turbo",
+                            ),
+                            model_type=ModelType.LLM,
+                            fetch_from=FetchFrom.PREDEFINED_MODEL,
+                            model_properties={},
+                            features=[ModelFeature.TOOL_CALL, ModelFeature.MULTI_TOOL_CALL],
+                        ),
+                        AIModelEntity(
+                            model="gpt-3.5-turbo-instruct",
+                            label=I18nObject(
+                                en_US="gpt-3.5-turbo-instruct",
+                                zh_Hans="gpt-3.5-turbo-instruct",
+                            ),
+                            model_type=ModelType.LLM,
+                            fetch_from=FetchFrom.PREDEFINED_MODEL,
+                            model_properties={
+                                ModelPropertyKey.MODE: LLMMode.COMPLETION,
+                            },
+                            features=[],
+                        ),
+                    ],
+                ),
+            )
+        ]
+
+    def get_model_schema(
+        self,
+        tenant_id: str,
+        user_id: str,
+        plugin_id: str,
+        provider: str,
+        model_type: str,
+        model: str,
+        credentials: dict,
+    ) -> AIModelEntity | None:
+        """
+        Get model schema
+        """
+        return AIModelEntity(
+            model=model,
+            label=I18nObject(
+                en_US="OpenAI",
+                zh_Hans="OpenAI",
+            ),
+            model_type=ModelType(model_type),
+            fetch_from=FetchFrom.PREDEFINED_MODEL,
+            model_properties={},
+            features=[ModelFeature.TOOL_CALL, ModelFeature.MULTI_TOOL_CALL] if model == "gpt-3.5-turbo" else [],
+        )
+
+    @staticmethod
+    def generate_function_call(
+        tools: Optional[list[PromptMessageTool]],
+    ) -> Optional[AssistantPromptMessage.ToolCall]:
+        if not tools or len(tools) == 0:
+            return None
+        function: PromptMessageTool = tools[0]
+        function_name = function.name
+        function_parameters = function.parameters
+        function_parameters_type = function_parameters["type"]
+        if function_parameters_type != "object":
+            return None
+        function_parameters_properties = function_parameters["properties"]
+        function_parameters_required = function_parameters["required"]
+        parameters = {}
+        for parameter_name, parameter in function_parameters_properties.items():
+            if parameter_name not in function_parameters_required:
+                continue
+            parameter_type = parameter["type"]
+            if parameter_type == "string":
+                if "enum" in parameter:
+                    if len(parameter["enum"]) == 0:
+                        continue
+                    parameters[parameter_name] = parameter["enum"][0]
+                else:
+                    parameters[parameter_name] = "kawaii"
+            elif parameter_type == "integer":
+                parameters[parameter_name] = 114514
+            elif parameter_type == "number":
+                parameters[parameter_name] = 1919810.0
+            elif parameter_type == "boolean":
+                parameters[parameter_name] = True
+
+        return AssistantPromptMessage.ToolCall(
+            id=str(uuid.uuid4()),
+            type="function",
+            function=AssistantPromptMessage.ToolCall.ToolCallFunction(
+                name=function_name,
+                arguments=dumps(parameters),
+            ),
+        )
+
+    @staticmethod
+    def mocked_chat_create_sync(
+        model: str,
+        prompt_messages: list[PromptMessage],
+        tools: Optional[list[PromptMessageTool]] = None,
+    ) -> LLMResult:
+        tool_call = MockModelClass.generate_function_call(tools=tools)
+
+        return LLMResult(
+            id=str(uuid.uuid4()),
+            model=model,
+            prompt_messages=prompt_messages,
+            message=AssistantPromptMessage(content="elaina", tool_calls=[tool_call] if tool_call else []),
+            usage=LLMUsage(
+                prompt_tokens=2,
+                completion_tokens=1,
+                total_tokens=3,
+                prompt_unit_price=Decimal(0.0001),
+                completion_unit_price=Decimal(0.0002),
+                prompt_price_unit=Decimal(1),
+                prompt_price=Decimal(0.0001),
+                completion_price_unit=Decimal(1),
+                completion_price=Decimal(0.0002),
+                total_price=Decimal(0.0003),
+                currency="USD",
+                latency=0.001,
+            ),
+        )
+
+    @staticmethod
+    def mocked_chat_create_stream(
+        model: str,
+        prompt_messages: list[PromptMessage],
+        tools: Optional[list[PromptMessageTool]] = None,
+    ) -> Generator[LLMResultChunk, None, None]:
+        tool_call = MockModelClass.generate_function_call(tools=tools)
+
+        full_text = "Hello, world!\n\n```python\nprint('Hello, world!')\n```"
+        for i in range(0, len(full_text) + 1):
+            if i == len(full_text):
+                yield LLMResultChunk(
+                    model=model,
+                    prompt_messages=prompt_messages,
+                    delta=LLMResultChunkDelta(
+                        index=0,
+                        message=AssistantPromptMessage(
+                            content="",
+                            tool_calls=[tool_call] if tool_call else [],
+                        ),
+                    ),
+                )
+            else:
+                yield LLMResultChunk(
+                    model=model,
+                    prompt_messages=prompt_messages,
+                    delta=LLMResultChunkDelta(
+                        index=0,
+                        message=AssistantPromptMessage(
+                            content=full_text[i],
+                            tool_calls=[tool_call] if tool_call else [],
+                        ),
+                        usage=LLMUsage(
+                            prompt_tokens=2,
+                            completion_tokens=17,
+                            total_tokens=19,
+                            prompt_unit_price=Decimal(0.0001),
+                            completion_unit_price=Decimal(0.0002),
+                            prompt_price_unit=Decimal(1),
+                            prompt_price=Decimal(0.0001),
+                            completion_price_unit=Decimal(1),
+                            completion_price=Decimal(0.0002),
+                            total_price=Decimal(0.0003),
+                            currency="USD",
+                            latency=0.001,
+                        ),
+                    ),
+                )
+
+    def invoke_llm(
+        self: PluginModelManager,
+        *,
+        tenant_id: str,
+        user_id: str,
+        plugin_id: str,
+        provider: str,
+        model: str,
+        credentials: dict,
+        prompt_messages: list[PromptMessage],
+        model_parameters: Optional[dict] = None,
+        tools: Optional[list[PromptMessageTool]] = None,
+        stop: Optional[list[str]] = None,
+        stream: bool = True,
+    ):
+        return MockModelClass.mocked_chat_create_stream(model=model, prompt_messages=prompt_messages, tools=tools)
@@ -1,55 +0,0 @@
-import os
-from pathlib import Path
-
-import pytest
-
-from core.model_runtime.errors.validate import CredentialsValidateFailedError
-from core.model_runtime.model_providers.gpustack.speech2text.speech2text import GPUStackSpeech2TextModel
-
-
-def test_validate_credentials():
-    model = GPUStackSpeech2TextModel()
-
-    with pytest.raises(CredentialsValidateFailedError):
-        model.validate_credentials(
-            model="faster-whisper-medium",
-            credentials={
-                "endpoint_url": "invalid_url",
-                "api_key": "invalid_api_key",
-            },
-        )
-
-    model.validate_credentials(
-        model="faster-whisper-medium",
-        credentials={
-            "endpoint_url": os.environ.get("GPUSTACK_SERVER_URL"),
-            "api_key": os.environ.get("GPUSTACK_API_KEY"),
-        },
-    )
-
-
-def test_invoke_model():
-    model = GPUStackSpeech2TextModel()
-
-    # Get the directory of the current file
-    current_dir = os.path.dirname(os.path.abspath(__file__))
-
-    # Get assets directory
-    assets_dir = os.path.join(os.path.dirname(current_dir), "assets")
-
-    # Construct the path to the audio file
-    audio_file_path = os.path.join(assets_dir, "audio.mp3")
-
-    file = Path(audio_file_path).read_bytes()
-
-    result = model.invoke(
-        model="faster-whisper-medium",
-        credentials={
-            "endpoint_url": os.environ.get("GPUSTACK_SERVER_URL"),
-            "api_key": os.environ.get("GPUSTACK_API_KEY"),
-        },
-        file=file,
-    )
-
-    assert isinstance(result, str)
-    assert result == "1, 2, 3, 4, 5, 6, 7, 8, 9, 10"
--- a/Show More
+++ b/Show More
Author	SHA1	Message	Date
Novice Lee	95eeb7b0d1	feat: agent node custom tool input	2025-02-07 11:02:31 +08:00
Yeuoly	933b6abc13	fix: ci	2025-02-06 18:36:14 +08:00
Yeuoly	1097bf314a	Merge branch 'plugins/beta' into dev/plugin-deploy	2025-02-06 18:30:49 +08:00
Boris PolonskyandGitHub	beebba0340	Unify plugin endpoint configuration for api and worker: An alternative solution to PR #13214 (#13239 )	2025-02-06 11:29:37 +08:00
YeuolyandGitHub	4e27d82d68	improve: remove docker-legacy (#13236 )	2025-02-05 20:28:02 +08:00
Boris PolonskyandGitHub	cdeaf3f70b	Fix ruff linting error caused by `api/models/dataset.py` (#13221 )	2025-02-05 17:45:23 +08:00
YeuolyandGitHub	24839bb3e1	fix: mismatches dependencies in dockerfile (#13220 )	2025-02-05 17:00:26 +08:00
KVOJJJinandGitHub	1650dbfbb1	Fix: merge error of tracing and web app setting modal (#13219 )	2025-02-05 16:16:28 +08:00
JoelandGitHub	fd11817044	fix: select input not show save value (#13218 )	2025-02-05 16:13:40 +08:00
Wu TianweiandGitHub	6642fc6012	fix: fix fallback route logic (#13199 )	2025-02-05 14:38:36 +08:00
KVOJJJinandGitHub	2710242982	Feat: feature and log dark mode (#13208 )	2025-02-05 13:58:19 +08:00
kurokoboandGitHub	1de84fdda0	fix: correct env vars for docker deployment (#13055 )	2025-01-27 11:19:29 +08:00
Wu TianweiandWTW0313	4920821270	feat: docx image preview (#13057 )	2025-01-26 16:08:58 +08:00
JyongandWTW0313	a16c729d5a	add sign-content (#13050 )	2025-01-26 16:05:19 +08:00
Wu TianweiandGitHub	3befbc1d68	feat: docx image preview (#13057 )	2025-01-26 15:12:05 +08:00
JyongandGitHub	62c413aca5	add sign-content (#13050 )	2025-01-26 10:58:47 +08:00
JoelandGitHub	6887b501b8	fix: can choose selected tools and show tool name instead of label (#13025 )	2025-01-24 22:34:09 +08:00
非法操作andGitHub	f93bf131ab	fix(1.0): explore market page empty (#13017 )	2025-01-24 18:43:56 +08:00
非法操作andGitHub	ef1f429437	fix(1.0): update github plugin 404 (#13014 )	2025-01-24 18:42:14 +08:00
KVOJJJinandGitHub	c966bf1474	Feat: dark mode of app configure (#13010 )	2025-01-24 14:16:35 +08:00
+42 Yeuoly GitHub kurokobo Hiroshi Fujita NFish Gen Sato eux huangzhuo1949 huangzhuo lotsik crazywoola Wu Tianwei nite-knite Jyonggithub-actions[bot] <41898282+github-actions[bot]@users.noreply.github.com>gakkiyomi CN-P5 CN-P5 Chuehnone yihong Kevin9703 -LAN-Boris Feld mbo mabo Warren Chen KVOJJJin JzoNgKVO jiandanfeng zhu-an zhaoqingyu.1075 海狸大師 Xu Song rayshaw001 Ding Jiatong Bowen Liang JasonVV le0zh zhuxinliang k-zaku Joel luckylhb90 hobo.l jiangbo721 刘江波 Shun Miyazawa EricPan crazywoola zxhlyh sino Jhvcc lowell	899df30bf6	Plugin/merge main to plugin/beta 20250122 (#12962 ) Signed-off-by: yihong0618 <zouzou0208@gmail.com> Signed-off-by: -LAN- <laipz8200@outlook.com> Co-authored-by: kurokobo <kuro664@gmail.com> Co-authored-by: Hiroshi Fujita <fujita-h@users.noreply.github.com> Co-authored-by: NFish <douxc512@gmail.com> Co-authored-by: Gen Sato <52241300+halogen22@users.noreply.github.com> Co-authored-by: eux <euxuuu@gmail.com> Co-authored-by: huangzhuo1949 <167434202+huangzhuo1949@users.noreply.github.com> Co-authored-by: huangzhuo <huangzhuo1@xiaomi.com> Co-authored-by: lotsik <lotsik@mail.ru> Co-authored-by: crazywoola <100913391+crazywoola@users.noreply.github.com> Co-authored-by: Wu Tianwei <30284043+WTW0313@users.noreply.github.com> Co-authored-by: nite-knite <nkCoding@gmail.com> Co-authored-by: Jyong <76649700+JohnJyong@users.noreply.github.com> Co-authored-by: github-actions[bot] <41898282+github-actions[bot]@users.noreply.github.com> Co-authored-by: gakkiyomi <gakkiyomi@aliyun.com> Co-authored-by: CN-P5 <heibai2006@gmail.com> Co-authored-by: CN-P5 <heibai2006@qq.com> Co-authored-by: Chuehnone <1897025+chuehnone@users.noreply.github.com> Co-authored-by: yihong <zouzou0208@gmail.com> Co-authored-by: Kevin9703 <51311316+Kevin9703@users.noreply.github.com> Co-authored-by: -LAN- <laipz8200@outlook.com> Co-authored-by: Boris Feld <lothiraldan@gmail.com> Co-authored-by: mbo <himabo@gmail.com> Co-authored-by: mabo <mabo@aeyes.ai> Co-authored-by: Warren Chen <warren.chen830@gmail.com> Co-authored-by: KVOJJJin <jzongcode@gmail.com> Co-authored-by: JzoNgKVO <27049666+JzoNgKVO@users.noreply.github.com> Co-authored-by: jiandanfeng <chenjh3@wangsu.com> Co-authored-by: zhu-an <70234959+xhdd123321@users.noreply.github.com> Co-authored-by: zhaoqingyu.1075 <zhaoqingyu.1075@bytedance.com> Co-authored-by: 海狸大師 <86974027+yenslife@users.noreply.github.com> Co-authored-by: Xu Song <xusong.vip@gmail.com> Co-authored-by: rayshaw001 <396301947@163.com> Co-authored-by: Ding Jiatong <dingjiatong@gmail.com> Co-authored-by: Bowen Liang <liangbowen@gf.com.cn> Co-authored-by: JasonVV <jasonwangiii@outlook.com> Co-authored-by: le0zh <newlight@qq.com> Co-authored-by: zhuxinliang <zhuxinliang@didiglobal.com> Co-authored-by: k-zaku <zaku99@outlook.jp> Co-authored-by: Joel <iamjoel007@gmail.com> Co-authored-by: luckylhb90 <luckylhb90@gmail.com> Co-authored-by: hobo.l <hobo.l@binance.com> Co-authored-by: jiangbo721 <365065261@qq.com> Co-authored-by: 刘江波 <jiangbo721@163.com> Co-authored-by: Shun Miyazawa <34241526+miya@users.noreply.github.com> Co-authored-by: EricPan <30651140+Egfly@users.noreply.github.com> Co-authored-by: crazywoola <427733928@qq.com> Co-authored-by: zxhlyh <jasonapring2015@outlook.com> Co-authored-by: sino <sino2322@gmail.com> Co-authored-by: Jhvcc <37662342+Jhvcc@users.noreply.github.com> Co-authored-by: lowell <lowell.hu@zkteco.in>	2025-01-23 14:48:16 +08:00
zxhlyhandGitHub	8d8d3e3f2f	fix: plugin search api url (#12977 )	2025-01-23 14:25:24 +08:00
非法操作andGitHub	5f0fa38ec6	fix(1.0): invoke llm raise error (#12753 )	2025-01-22 16:46:35 +08:00
YeuolyandGitHub	cc1fe70d34	fix: add adapter for datasets update checking (#12939 )	2025-01-22 15:40:06 +08:00
Hiroki NagaiandGitHub	15ee1e11be	fix: 500 error in Notion integration API (#12934 )	2025-01-22 14:38:01 +08:00
JoelandGitHub	c8b4a76530	fix: agent node output vars error (#12931 )	2025-01-22 13:33:27 +08:00
Novice Lee	4765728cef	feat: add agent node stream output	2025-01-22 09:59:40 +08:00
YeuolyandGitHub	6ee4eba86b	fix: change default PLUGIN_DAEMON_URL to http://localhost:5002 (#12915 )	2025-01-21 22:30:24 +08:00
非法操作andGitHub	357d2e8be8	fix(1.0): add cross-env to pnpm run dev (#12600 )	2025-01-21 19:51:32 +08:00
kurokoboandGitHub	b5accda3fe	fix: correct validation for agent node which is invoked before publishing the app (#12805 )	2025-01-21 10:07:25 +08:00
非法操作andGitHub	de4752a16b	fix(1.0): unexpected error raise (#12812 )	2025-01-21 10:04:56 +08:00
非法操作andGitHub	60427f1adf	chore(1.0): improve some environment variables (#12814 )	2025-01-21 10:04:46 +08:00
非法操作andGitHub	1a313c868d	fix(1.0): sometimes add tool raise error (#12821 )	2025-01-21 10:04:05 +08:00
YeuolyandGitHub	0b32b1988f	fix: missing tenant_id in get_signed_file_url_for_plugin (#12734 )	2025-01-14 19:39:21 +08:00
KVOJJJinandGitHub	e56c051d97	Fix: tool card info (#12726 )	2025-01-14 16:10:00 +08:00
Novice Lee	5063f27916	Merge branch 'fix/correct-provider-type' into dev/plugin-deploy	2025-01-14 14:21:15 +08:00
Novice Lee	11428172eb	fix: correct the provider type	2025-01-14 14:20:03 +08:00
Joel	0ae072dd75	chore: add plugin/deploy deploy	2025-01-14 14:13:43 +08:00
Joel	d6b9648332	merge	2025-01-14 11:35:29 +08:00
JoelandGitHub	0a6b4d01d7	fix: save tool not add type (#12712 )	2025-01-14 10:28:41 +08:00
Novice Lee	8865bdca05	feat: add agent strategy on node start	2025-01-13 13:30:35 +08:00
Novice GitHub Novice Lee	98b139c680	feat: add agent strategy on node start (#12667 ) Co-authored-by: Novice Lee <novicelee@NoviPro.local>	2025-01-13 13:04:05 +08:00
zxhlyhandGitHub	f0a3c14adb	fix: plugins task (#12662 )	2025-01-13 10:59:34 +08:00
YeuolyandGitHub	51947575c2	feat: add skip signature verification (#12627 )	2025-01-10 20:37:33 +08:00
YeuolyandGitHub	cb8debee3e	Plugins/fix backend ci errors (#12615 )	2025-01-10 19:46:59 +08:00
zxhlyhandGitHub	d56079a549	fix: marketplace card i18n (#12623 )	2025-01-10 18:15:58 +08:00
zxhlyhandGitHub	c08b451874	fix: marketplace page list style (#12613 )	2025-01-10 17:31:09 +08:00
非法操作andGitHub	ac336ff359	fix(1.0): add missing environment variable (#12599 )	2025-01-10 17:17:13 +08:00
JoelandGitHub	4cbd511cd7	fix: ci use pnpm error (#12597 )	2025-01-10 16:55:16 +08:00
YeuolyandGitHub	c03adcb154	Fix: style checks and unittests (#12603 )	2025-01-10 16:40:39 +08:00
Hiroshi FujitaandGitHub	04dade2f9b	fix: update fetchReleases to use owner and repo from meta (#12590 )	2025-01-10 15:46:10 +08:00
kurokoboandGitHub	f69220ca96	fix: add location directive for /explore (#12572 )	2025-01-10 15:42:32 +08:00
Wu TianweiandGitHub	a5e24ff6d3	fix: update language change handling in I18n component (#12596 ) ok	2025-01-10 14:47:24 +08:00
zxhlyhandGitHub	71976f9192	fix: marketplace serach bundle (#12581 )	2025-01-10 14:03:00 +08:00
Joel GitHub JzoNg	39ec6c8025	Fix/setting model page crash (#12594 ) Co-authored-by: JzoNg <jzongcode@gmail.com>	2025-01-10 13:10:58 +08:00
NFishandGitHub	e370045ac4	Fix:screenshots image missed (#12589 )	2025-01-10 11:47:20 +08:00
YeuolyandGitHub	28edbbac0b	Plugins/bump to 1.0.0 beta.1 (#12568 )	2025-01-09 22:46:24 +08:00
YeuolyandGitHub	782abcecd8	bump version to 1.0.0-beta.1 (#12567 )	2025-01-09 22:38:20 +08:00
YeuolyandGitHub	4deb02fc2c	fix: rename plugin db name to dify_plugin (#12565 )	2025-01-09 21:56:24 +08:00
JoelandGitHub	f967180dc2	fix: not show stragry type (#12561 )	2025-01-09 20:55:17 +08:00
YeuolyandGitHub	cead13cbc3	plugins: remove middleware.1.yaml (#12559 )	2025-01-09 20:34:49 +08:00
YeuolyandGitHub	078c151065	fix: add-default-console-url (#12558 )	2025-01-09 20:34:13 +08:00
YeuolyandGitHub	17babca362	Introducing: Plugin Mechanism (#12553 )	2025-01-09 19:54:17 +08:00
AkaraChenandGitHub	8efed8858c	feat: reset parameters when switch agent strategy (#12549 )	2025-01-09 19:31:02 +08:00
YeuolyandGitHub	0d411a0b5a	feat: refactor docker-compose (#12550 )	2025-01-09 19:08:11 +08:00
Yeuoly GitHub Novice Lee	13f0c01f93	feat: add ci checks to plugins/beta branch (#12542 ) Co-authored-by: Novice Lee <novicelee@NoviPro.local>	2025-01-09 18:57:09 +08:00
zxhlyh GitHub AkaraChen Yi Joel JzoNg twwu kurokobo Hiroshi Fujita	3c014f3ae5	Feat/plugins (#12547 ) Co-authored-by: AkaraChen <akarachen@outlook.com> Co-authored-by: Yi <yxiaoisme@gmail.com> Co-authored-by: Joel <iamjoel007@gmail.com> Co-authored-by: JzoNg <jzongcode@gmail.com> Co-authored-by: twwu <twwu@dify.ai> Co-authored-by: kurokobo <kuro664@gmail.com> Co-authored-by: Hiroshi Fujita <fujita-h@users.noreply.github.com>	2025-01-09 18:47:41 +08:00
Yeuoly	e4c4490175	refactor	2025-01-09 17:27:05 +08:00