fix: add explicit default to httpx.timeout

Co-authored-by: autofix-ci[bot] <114827586+autofix-ci[bot]@users.noreply.github.com>

.cursorrules

@@ -0,0 +1,6 @@
+# Cursor Rules for Dify Project
+
+## Automated Test Generation
+
+- Use `web/testing/testing.md` as the canonical instruction set for generating frontend automated tests.
+- When proposing or saving tests, re-read that document and follow every requirement.

.github/copilot-instructions.md

@@ -0,0 +1,12 @@
+# Copilot Instructions
+
+GitHub Copilot must follow the unified frontend testing requirements documented in `web/testing/testing.md`.
+
+Key reminders:
+
+- Generate tests using the mandated tech stack, naming, and code style (AAA pattern, `fireEvent`, descriptive test names, cleans up mocks).
+- Cover rendering, prop combinations, and edge cases by default; extend coverage for hooks, routing, async flows, and domain-specific components when applicable.
+- Target >95% line and branch coverage and 100% function/statement coverage.
+- Apply the project's mocking conventions for i18n, toast notifications, and Next.js utilities.
+
+Any suggestions from Copilot that conflict with `web/testing/testing.md` should be revised before acceptance.

.github/workflows/translate-i18n-base-on-english.yml

@@ -20,22 +20,22 @@ jobs:
     steps:
       - uses: actions/checkout@v4
         with:
-          fetch-depth: 2
+          fetch-depth: 0
           token: ${{ secrets.GITHUB_TOKEN }}
 
       - name: Check for file changes in i18n/en-US
         id: check_files
         run: |
-          recent_commit_sha=$(git rev-parse HEAD)
-          second_recent_commit_sha=$(git rev-parse HEAD~1)
-          changed_files=$(git diff --name-only $recent_commit_sha $second_recent_commit_sha -- 'i18n/en-US/*.ts')
+          git fetch origin "${{ github.event.before }}" || true
+          git fetch origin "${{ github.sha }}" || true
+          changed_files=$(git diff --name-only "${{ github.event.before }}" "${{ github.sha }}" -- 'i18n/en-US/*.ts')
           echo "Changed files: $changed_files"
           if [ -n "$changed_files" ]; then
             echo "FILES_CHANGED=true" >> $GITHUB_ENV
             file_args=""
             for file in $changed_files; do
               filename=$(basename "$file" .ts)
-              file_args="$file_args --file=$filename"
+              file_args="$file_args --file $filename"
             done
             echo "FILE_ARGS=$file_args" >> $GITHUB_ENV
             echo "File arguments: $file_args"
@@ -77,12 +77,15 @@ jobs:
         uses: peter-evans/create-pull-request@v6
         with:
           token: ${{ secrets.GITHUB_TOKEN }}
-          commit-message: Update i18n files and type definitions based on en-US changes
-          title: 'chore: translate i18n files and update type definitions'
+          commit-message: 'chore(i18n): update translations based on en-US changes'
+          title: 'chore(i18n): translate i18n files and update type definitions'
           body: |
             This PR was automatically created to update i18n files and TypeScript type definitions based on changes in en-US locale.
-            
+
+            **Triggered by:** ${{ github.sha }}
+
             **Changes included:**
             - Updated translation files for all locales
             - Regenerated TypeScript type definitions for type safety
-          branch: chore/automated-i18n-updates
+          branch: chore/automated-i18n-updates-${{ github.sha }}
+          delete-branch: true

.windsurf/rules/testing.md

@@ -0,0 +1,5 @@
+# Windsurf Testing Rules
+
+- Use `web/testing/testing.md` as the single source of truth for frontend automated testing.
+- Honor every requirement in that document when generating or accepting tests.
+- When proposing or saving tests, re-read that document and follow every requirement.

CONTRIBUTING.md

@@ -77,6 +77,8 @@ How we prioritize:
 
 For setting up the frontend service, please refer to our comprehensive [guide](https://github.com/langgenius/dify/blob/main/web/README.md) in the `web/README.md` file. This document provides detailed instructions to help you set up the frontend environment properly.
 
+**Testing**: All React components must have comprehensive test coverage. See [web/testing/testing.md](https://github.com/langgenius/dify/blob/main/web/testing/testing.md) for the canonical frontend testing guidelines and follow every requirement described there.
+
 #### Backend
 
 For setting up the backend service, kindly refer to our detailed [instructions](https://github.com/langgenius/dify/blob/main/api/README.md) in the `api/README.md` file. This document contains step-by-step guidance to help you get the backend up and running smoothly.

README.md

@@ -36,6 +36,12 @@
         <img alt="Issues closed" src="https://img.shields.io/github/issues-search?query=repo%3Alanggenius%2Fdify%20is%3Aclosed&label=issues%20closed&labelColor=%20%237d89b0&color=%20%235d6b98"></a>
     <a href="https://github.com/langgenius/dify/discussions/" target="_blank">
         <img alt="Discussion posts" src="https://img.shields.io/github/discussions/langgenius/dify?labelColor=%20%239b8afb&color=%20%237a5af8"></a>
+    <a href="https://insights.linuxfoundation.org/project/langgenius-dify" target="_blank">
+        <img alt="LFX Health Score" src="https://insights.linuxfoundation.org/api/badge/health-score?project=langgenius-dify"></a>
+    <a href="https://insights.linuxfoundation.org/project/langgenius-dify" target="_blank">
+        <img alt="LFX Contributors" src="https://insights.linuxfoundation.org/api/badge/contributors?project=langgenius-dify"></a>
+    <a href="https://insights.linuxfoundation.org/project/langgenius-dify" target="_blank">
+        <img alt="LFX Active Contributors" src="https://insights.linuxfoundation.org/api/badge/active-contributors?project=langgenius-dify"></a>
 </p>
 
 <p align="center">

api/.env.example

@@ -176,6 +176,7 @@ WEAVIATE_ENDPOINT=http://localhost:8080
 WEAVIATE_API_KEY=WVF5YThaHlkYwhGUSmCRgsX3tD5ngdN8pkih
 WEAVIATE_GRPC_ENABLED=false
 WEAVIATE_BATCH_SIZE=100
+WEAVIATE_TOKENIZATION=word
 
 # OceanBase Vector configuration
 OCEANBASE_VECTOR_HOST=127.0.0.1
@@ -539,6 +540,7 @@ WORKFLOW_LOG_CLEANUP_BATCH_SIZE=100
 
 # App configuration
 APP_MAX_EXECUTION_TIME=1200
+APP_DEFAULT_ACTIVE_REQUESTS=0
 APP_MAX_ACTIVE_REQUESTS=0
 
 # Celery beat configuration

api/.idea/vcs.xml

@@ -1,11 +1,5 @@
 <?xml version="1.0" encoding="UTF-8"?>
 <project version="4">
-  <component name="CommitMessageInspectionProfile">
-    <profile version="1.0">
-      <inspection_tool class="CommitFormat" enabled="true" level="WARNING" enabled_by_default="true" />
-      <inspection_tool class="CommitNamingConvention" enabled="true" level="WARNING" enabled_by_default="true" />
-    </profile>
-  </component>
   <component name="IssueNavigationConfiguration">
     <option name="links">
       <list>
@@ -20,4 +14,4 @@
     <mapping directory="" vcs="Git" />
     <mapping directory="$PROJECT_DIR$/.." vcs="Git" />
   </component>
-</project>
+</project>

api/.importlinter

@@ -16,6 +16,7 @@ layers =
     graph
     nodes
     node_events
+    runtime
     entities
 containers =
     core.workflow

api/Dockerfile

@@ -48,6 +48,12 @@ ENV PYTHONIOENCODING=utf-8
 
 WORKDIR /app/api
 
+# Create non-root user
+ARG dify_uid=1001
+RUN groupadd -r -g ${dify_uid} dify && \
+    useradd -r -u ${dify_uid} -g ${dify_uid} -s /bin/bash dify && \
+    chown -R dify:dify /app
+
 RUN \
     apt-get update \
     # Install dependencies
@@ -57,7 +63,7 @@ RUN \
         # for gmpy2 \
         libgmp-dev libmpfr-dev libmpc-dev \
         # For Security
-        expat libldap-2.5-0 perl libsqlite3-0 zlib1g \
+        expat libldap-2.5-0=2.5.13+dfsg-5 perl libsqlite3-0=3.40.1-2+deb12u2 zlib1g=1:1.2.13.dfsg-1 \
         # install fonts to support the use of tools like pypdfium2
         fonts-noto-cjk \
         # install a package to improve the accuracy of guessing mime type and file extension
@@ -69,24 +75,29 @@ RUN \
 
 # Copy Python environment and packages
 ENV VIRTUAL_ENV=/app/api/.venv
-COPY --from=packages ${VIRTUAL_ENV} ${VIRTUAL_ENV}
+COPY --from=packages --chown=dify:dify ${VIRTUAL_ENV} ${VIRTUAL_ENV}
 ENV PATH="${VIRTUAL_ENV}/bin:${PATH}"
 
 # Download nltk data
-RUN python -c "import nltk; nltk.download('punkt'); nltk.download('averaged_perceptron_tagger')"
+RUN mkdir -p /usr/local/share/nltk_data && NLTK_DATA=/usr/local/share/nltk_data python -c "import nltk; nltk.download('punkt'); nltk.download('averaged_perceptron_tagger'); nltk.download('stopwords')" \
+    && chmod -R 755 /usr/local/share/nltk_data
 
 ENV TIKTOKEN_CACHE_DIR=/app/api/.tiktoken_cache
 
-RUN python -c "import tiktoken; tiktoken.encoding_for_model('gpt2')"
+RUN python -c "import tiktoken; tiktoken.encoding_for_model('gpt2')" \
+    && chown -R dify:dify ${TIKTOKEN_CACHE_DIR}
 
 # Copy source code
-COPY . /app/api/
+COPY --chown=dify:dify . /app/api/
+
+# Prepare entrypoint script
+COPY --chown=dify:dify --chmod=755 docker/entrypoint.sh /entrypoint.sh
 
-# Copy entrypoint
-COPY docker/entrypoint.sh /entrypoint.sh
-RUN chmod +x /entrypoint.sh
 
 ARG COMMIT_SHA
 ENV COMMIT_SHA=${COMMIT_SHA}
+ENV NLTK_DATA=/usr/local/share/nltk_data
+
+USER dify
 
 ENTRYPOINT ["/bin/bash", "/entrypoint.sh"]

api/configs/feature/__init__.py

@@ -73,6 +73,10 @@ class AppExecutionConfig(BaseSettings):
         description="Maximum allowed execution time for the application in seconds",
         default=1200,
     )
+    APP_DEFAULT_ACTIVE_REQUESTS: NonNegativeInt = Field(
+        description="Default number of concurrent active requests per app (0 for unlimited)",
+        default=0,
+    )
     APP_MAX_ACTIVE_REQUESTS: NonNegativeInt = Field(
         description="Maximum number of concurrent active requests per app (0 for unlimited)",
         default=0,

api/configs/middleware/vdb/weaviate_config.py

@@ -31,3 +31,8 @@ class WeaviateConfig(BaseSettings):
         description="Number of objects to be processed in a single batch operation (default is 100)",
         default=100,
     )
+
+    WEAVIATE_TOKENIZATION: str | None = Field(
+        description="Tokenization for Weaviate (default is word)",
+        default="word",
+    )

api/controllers/console/apikey.py

@@ -24,6 +24,12 @@ api_key_fields = {
 
 api_key_list = {"data": fields.List(fields.Nested(api_key_fields), attribute="items")}
 
+api_key_item_model = console_ns.model("ApiKeyItem", api_key_fields)
+
+api_key_list_model = console_ns.model(
+    "ApiKeyList", {"data": fields.List(fields.Nested(api_key_item_model), attribute="items")}
+)
+
 
 def _get_resource(resource_id, tenant_id, resource_model):
     if resource_model == App:
@@ -52,7 +58,7 @@ class BaseApiKeyListResource(Resource):
     token_prefix: str | None = None
     max_keys = 10
 
-    @marshal_with(api_key_list)
+    @marshal_with(api_key_list_model)
     def get(self, resource_id):
         assert self.resource_id_field is not None, "resource_id_field must be set"
         resource_id = str(resource_id)
@@ -66,7 +72,7 @@ class BaseApiKeyListResource(Resource):
         ).all()
         return {"items": keys}
 
-    @marshal_with(api_key_fields)
+    @marshal_with(api_key_item_model)
     @edit_permission_required
     def post(self, resource_id):
         assert self.resource_id_field is not None, "resource_id_field must be set"
@@ -136,7 +142,7 @@ class AppApiKeyListResource(BaseApiKeyListResource):
     @console_ns.doc("get_app_api_keys")
     @console_ns.doc(description="Get all API keys for an app")
     @console_ns.doc(params={"resource_id": "App ID"})
-    @console_ns.response(200, "Success", api_key_list)
+    @console_ns.response(200, "Success", api_key_list_model)
     def get(self, resource_id):  # type: ignore
         """Get all API keys for an app"""
         return super().get(resource_id)
@@ -144,7 +150,7 @@ class AppApiKeyListResource(BaseApiKeyListResource):
     @console_ns.doc("create_app_api_key")
     @console_ns.doc(description="Create a new API key for an app")
     @console_ns.doc(params={"resource_id": "App ID"})
-    @console_ns.response(201, "API key created successfully", api_key_fields)
+    @console_ns.response(201, "API key created successfully", api_key_item_model)
     @console_ns.response(400, "Maximum keys exceeded")
     def post(self, resource_id):  # type: ignore
         """Create a new API key for an app"""
@@ -176,7 +182,7 @@ class DatasetApiKeyListResource(BaseApiKeyListResource):
     @console_ns.doc("get_dataset_api_keys")
     @console_ns.doc(description="Get all API keys for a dataset")
     @console_ns.doc(params={"resource_id": "Dataset ID"})
-    @console_ns.response(200, "Success", api_key_list)
+    @console_ns.response(200, "Success", api_key_list_model)
     def get(self, resource_id):  # type: ignore
         """Get all API keys for a dataset"""
         return super().get(resource_id)
@@ -184,7 +190,7 @@ class DatasetApiKeyListResource(BaseApiKeyListResource):
     @console_ns.doc("create_dataset_api_key")
     @console_ns.doc(description="Create a new API key for a dataset")
     @console_ns.doc(params={"resource_id": "Dataset ID"})
-    @console_ns.response(201, "API key created successfully", api_key_fields)
+    @console_ns.response(201, "API key created successfully", api_key_item_model)
     @console_ns.response(400, "Maximum keys exceeded")
     def post(self, resource_id):  # type: ignore
         """Create a new API key for a dataset"""

api/controllers/console/app/annotation.py

@@ -15,6 +15,7 @@ from extensions.ext_redis import redis_client
 from fields.annotation_fields import (
     annotation_fields,
     annotation_hit_history_fields,
+    build_annotation_model,
 )
 from libs.helper import uuid_value
 from libs.login import login_required
@@ -184,7 +185,7 @@ class AnnotationApi(Resource):
             },
         )
     )
-    @console_ns.response(201, "Annotation created successfully", annotation_fields)
+    @console_ns.response(201, "Annotation created successfully", build_annotation_model(console_ns))
     @console_ns.response(403, "Insufficient permissions")
     @setup_required
     @login_required
@@ -238,7 +239,11 @@ class AnnotationExportApi(Resource):
     @console_ns.doc("export_annotations")
     @console_ns.doc(description="Export all annotations for an app")
     @console_ns.doc(params={"app_id": "Application ID"})
-    @console_ns.response(200, "Annotations exported successfully", fields.List(fields.Nested(annotation_fields)))
+    @console_ns.response(
+        200,
+        "Annotations exported successfully",
+        console_ns.model("AnnotationList", {"data": fields.List(fields.Nested(build_annotation_model(console_ns)))}),
+    )
     @console_ns.response(403, "Insufficient permissions")
     @setup_required
     @login_required
@@ -263,7 +268,7 @@ class AnnotationUpdateDeleteApi(Resource):
     @console_ns.doc("update_delete_annotation")
     @console_ns.doc(description="Update or delete an annotation")
     @console_ns.doc(params={"app_id": "Application ID", "annotation_id": "Annotation ID"})
-    @console_ns.response(200, "Annotation updated successfully", annotation_fields)
+    @console_ns.response(200, "Annotation updated successfully", build_annotation_model(console_ns))
     @console_ns.response(204, "Annotation deleted successfully")
     @console_ns.response(403, "Insufficient permissions")
     @console_ns.expect(parser)
@@ -359,7 +364,16 @@ class AnnotationHitHistoryListApi(Resource):
         .add_argument("limit", type=int, location="args", default=20, help="Page size")
     )
     @console_ns.response(
-        200, "Hit histories retrieved successfully", fields.List(fields.Nested(annotation_hit_history_fields))
+        200,
+        "Hit histories retrieved successfully",
+        console_ns.model(
+            "AnnotationHitHistoryList",
+            {
+                "data": fields.List(
+                    fields.Nested(console_ns.model("AnnotationHitHistoryItem", annotation_hit_history_fields))
+                )
+            },
+        ),
     )
     @console_ns.response(403, "Insufficient permissions")
     @setup_required

api/controllers/console/app/app.py

@@ -18,7 +18,15 @@ from controllers.console.wraps import (
 from core.ops.ops_trace_manager import OpsTraceManager
 from core.workflow.enums import NodeType
 from extensions.ext_database import db
-from fields.app_fields import app_detail_fields, app_detail_fields_with_site, app_pagination_fields
+from fields.app_fields import (
+    deleted_tool_fields,
+    model_config_fields,
+    model_config_partial_fields,
+    site_fields,
+    tag_fields,
+)
+from fields.workflow_fields import workflow_partial_fields as _workflow_partial_fields_dict
+from libs.helper import AppIconUrlField, TimestampField
 from libs.login import current_account_with_tenant, login_required
 from libs.validators import validate_description_length
 from models import App, Workflow
@@ -29,6 +37,111 @@ from services.feature_service import FeatureService
 
 ALLOW_CREATE_APP_MODES = ["chat", "agent-chat", "advanced-chat", "workflow", "completion"]
 
+# Register models for flask_restx to avoid dict type issues in Swagger
+# Register base models first
+tag_model = console_ns.model("Tag", tag_fields)
+
+workflow_partial_model = console_ns.model("WorkflowPartial", _workflow_partial_fields_dict)
+
+model_config_model = console_ns.model("ModelConfig", model_config_fields)
+
+model_config_partial_model = console_ns.model("ModelConfigPartial", model_config_partial_fields)
+
+deleted_tool_model = console_ns.model("DeletedTool", deleted_tool_fields)
+
+site_model = console_ns.model("Site", site_fields)
+
+app_partial_model = console_ns.model(
+    "AppPartial",
+    {
+        "id": fields.String,
+        "name": fields.String,
+        "max_active_requests": fields.Raw(),
+        "description": fields.String(attribute="desc_or_prompt"),
+        "mode": fields.String(attribute="mode_compatible_with_agent"),
+        "icon_type": fields.String,
+        "icon": fields.String,
+        "icon_background": fields.String,
+        "icon_url": AppIconUrlField,
+        "model_config": fields.Nested(model_config_partial_model, attribute="app_model_config", allow_null=True),
+        "workflow": fields.Nested(workflow_partial_model, allow_null=True),
+        "use_icon_as_answer_icon": fields.Boolean,
+        "created_by": fields.String,
+        "created_at": TimestampField,
+        "updated_by": fields.String,
+        "updated_at": TimestampField,
+        "tags": fields.List(fields.Nested(tag_model)),
+        "access_mode": fields.String,
+        "create_user_name": fields.String,
+        "author_name": fields.String,
+        "has_draft_trigger": fields.Boolean,
+    },
+)
+
+app_detail_model = console_ns.model(
+    "AppDetail",
+    {
+        "id": fields.String,
+        "name": fields.String,
+        "description": fields.String,
+        "mode": fields.String(attribute="mode_compatible_with_agent"),
+        "icon": fields.String,
+        "icon_background": fields.String,
+        "enable_site": fields.Boolean,
+        "enable_api": fields.Boolean,
+        "model_config": fields.Nested(model_config_model, attribute="app_model_config", allow_null=True),
+        "workflow": fields.Nested(workflow_partial_model, allow_null=True),
+        "tracing": fields.Raw,
+        "use_icon_as_answer_icon": fields.Boolean,
+        "created_by": fields.String,
+        "created_at": TimestampField,
+        "updated_by": fields.String,
+        "updated_at": TimestampField,
+        "access_mode": fields.String,
+        "tags": fields.List(fields.Nested(tag_model)),
+    },
+)
+
+app_detail_with_site_model = console_ns.model(
+    "AppDetailWithSite",
+    {
+        "id": fields.String,
+        "name": fields.String,
+        "description": fields.String,
+        "mode": fields.String(attribute="mode_compatible_with_agent"),
+        "icon_type": fields.String,
+        "icon": fields.String,
+        "icon_background": fields.String,
+        "icon_url": AppIconUrlField,
+        "enable_site": fields.Boolean,
+        "enable_api": fields.Boolean,
+        "model_config": fields.Nested(model_config_model, attribute="app_model_config", allow_null=True),
+        "workflow": fields.Nested(workflow_partial_model, allow_null=True),
+        "api_base_url": fields.String,
+        "use_icon_as_answer_icon": fields.Boolean,
+        "max_active_requests": fields.Integer,
+        "created_by": fields.String,
+        "created_at": TimestampField,
+        "updated_by": fields.String,
+        "updated_at": TimestampField,
+        "deleted_tools": fields.List(fields.Nested(deleted_tool_model)),
+        "access_mode": fields.String,
+        "tags": fields.List(fields.Nested(tag_model)),
+        "site": fields.Nested(site_model),
+    },
+)
+
+app_pagination_model = console_ns.model(
+    "AppPagination",
+    {
+        "page": fields.Integer,
+        "limit": fields.Integer(attribute="per_page"),
+        "total": fields.Integer,
+        "has_more": fields.Boolean(attribute="has_next"),
+        "data": fields.List(fields.Nested(app_partial_model), attribute="items"),
+    },
+)
+
 
 @console_ns.route("/apps")
 class AppListApi(Resource):
@@ -50,7 +163,7 @@ class AppListApi(Resource):
         .add_argument("tag_ids", type=str, location="args", help="Comma-separated tag IDs")
         .add_argument("is_created_by_me", type=bool, location="args", help="Filter by creator")
     )
-    @console_ns.response(200, "Success", app_pagination_fields)
+    @console_ns.response(200, "Success", app_pagination_model)
     @setup_required
     @login_required
     @account_initialization_required
@@ -137,7 +250,7 @@ class AppListApi(Resource):
         for app in app_pagination.items:
             app.has_draft_trigger = str(app.id) in draft_trigger_app_ids
 
-        return marshal(app_pagination, app_pagination_fields), 200
+        return marshal(app_pagination, app_pagination_model), 200
 
     @console_ns.doc("create_app")
     @console_ns.doc(description="Create a new application")
@@ -154,13 +267,13 @@ class AppListApi(Resource):
             },
         )
     )
-    @console_ns.response(201, "App created successfully", app_detail_fields)
+    @console_ns.response(201, "App created successfully", app_detail_model)
     @console_ns.response(403, "Insufficient permissions")
     @console_ns.response(400, "Invalid request parameters")
     @setup_required
     @login_required
     @account_initialization_required
-    @marshal_with(app_detail_fields)
+    @marshal_with(app_detail_model)
     @cloud_edition_billing_resource_check("apps")
     @edit_permission_required
     def post(self):
@@ -191,13 +304,13 @@ class AppApi(Resource):
     @console_ns.doc("get_app_detail")
     @console_ns.doc(description="Get application details")
     @console_ns.doc(params={"app_id": "Application ID"})
-    @console_ns.response(200, "Success", app_detail_fields_with_site)
+    @console_ns.response(200, "Success", app_detail_with_site_model)
     @setup_required
     @login_required
     @account_initialization_required
     @enterprise_license_required
     @get_app_model
-    @marshal_with(app_detail_fields_with_site)
+    @marshal_with(app_detail_with_site_model)
     def get(self, app_model):
         """Get app detail"""
         app_service = AppService()
@@ -227,7 +340,7 @@ class AppApi(Resource):
             },
         )
     )
-    @console_ns.response(200, "App updated successfully", app_detail_fields_with_site)
+    @console_ns.response(200, "App updated successfully", app_detail_with_site_model)
     @console_ns.response(403, "Insufficient permissions")
     @console_ns.response(400, "Invalid request parameters")
     @setup_required
@@ -235,7 +348,7 @@ class AppApi(Resource):
     @account_initialization_required
     @get_app_model
     @edit_permission_required
-    @marshal_with(app_detail_fields_with_site)
+    @marshal_with(app_detail_with_site_model)
     def put(self, app_model):
         """Update app"""
         parser = (
@@ -300,14 +413,14 @@ class AppCopyApi(Resource):
             },
         )
     )
-    @console_ns.response(201, "App copied successfully", app_detail_fields_with_site)
+    @console_ns.response(201, "App copied successfully", app_detail_with_site_model)
     @console_ns.response(403, "Insufficient permissions")
     @setup_required
     @login_required
     @account_initialization_required
     @get_app_model
     @edit_permission_required
-    @marshal_with(app_detail_fields_with_site)
+    @marshal_with(app_detail_with_site_model)
     def post(self, app_model):
         """Copy app"""
         # The role of the current user in the ta table must be admin, owner, or editor
@@ -396,7 +509,7 @@ class AppNameApi(Resource):
     @login_required
     @account_initialization_required
     @get_app_model
-    @marshal_with(app_detail_fields)
+    @marshal_with(app_detail_model)
     @edit_permission_required
     def post(self, app_model):
         args = parser.parse_args()
@@ -428,7 +541,7 @@ class AppIconApi(Resource):
     @login_required
     @account_initialization_required
     @get_app_model
-    @marshal_with(app_detail_fields)
+    @marshal_with(app_detail_model)
     @edit_permission_required
     def post(self, app_model):
         parser = (
@@ -454,13 +567,13 @@ class AppSiteStatus(Resource):
             "AppSiteStatusRequest", {"enable_site": fields.Boolean(required=True, description="Enable or disable site")}
         )
     )
-    @console_ns.response(200, "Site status updated successfully", app_detail_fields)
+    @console_ns.response(200, "Site status updated successfully", app_detail_model)
     @console_ns.response(403, "Insufficient permissions")
     @setup_required
     @login_required
     @account_initialization_required
     @get_app_model
-    @marshal_with(app_detail_fields)
+    @marshal_with(app_detail_model)
     @edit_permission_required
     def post(self, app_model):
         parser = reqparse.RequestParser().add_argument("enable_site", type=bool, required=True, location="json")
@@ -482,14 +595,14 @@ class AppApiStatus(Resource):
             "AppApiStatusRequest", {"enable_api": fields.Boolean(required=True, description="Enable or disable API")}
         )
     )
-    @console_ns.response(200, "API status updated successfully", app_detail_fields)
+    @console_ns.response(200, "API status updated successfully", app_detail_model)
     @console_ns.response(403, "Insufficient permissions")
     @setup_required
     @login_required
     @is_admin_or_owner_required
     @account_initialization_required
     @get_app_model
-    @marshal_with(app_detail_fields)
+    @marshal_with(app_detail_model)
     def post(self, app_model):
         parser = reqparse.RequestParser().add_argument("enable_api", type=bool, required=True, location="json")
         args = parser.parse_args()

api/controllers/console/app/app_import.py

@@ -1,4 +1,4 @@
-from flask_restx import Resource, marshal_with, reqparse
+from flask_restx import Resource, fields, marshal_with, reqparse
 from sqlalchemy.orm import Session
 
 from controllers.console.app.wraps import get_app_model
@@ -9,7 +9,11 @@ from controllers.console.wraps import (
     setup_required,
 )
 from extensions.ext_database import db
-from fields.app_fields import app_import_check_dependencies_fields, app_import_fields
+from fields.app_fields import (
+    app_import_check_dependencies_fields,
+    app_import_fields,
+    leaked_dependency_fields,
+)
 from libs.login import current_account_with_tenant, login_required
 from models.model import App
 from services.app_dsl_service import AppDslService, ImportStatus
@@ -18,6 +22,19 @@ from services.feature_service import FeatureService
 
 from .. import console_ns
 
+# Register models for flask_restx to avoid dict type issues in Swagger
+# Register base model first
+leaked_dependency_model = console_ns.model("LeakedDependency", leaked_dependency_fields)
+
+app_import_model = console_ns.model("AppImport", app_import_fields)
+
+# For nested models, need to replace nested dict with registered model
+app_import_check_dependencies_fields_copy = app_import_check_dependencies_fields.copy()
+app_import_check_dependencies_fields_copy["leaked_dependencies"] = fields.List(fields.Nested(leaked_dependency_model))
+app_import_check_dependencies_model = console_ns.model(
+    "AppImportCheckDependencies", app_import_check_dependencies_fields_copy
+)
+
 parser = (
     reqparse.RequestParser()
     .add_argument("mode", type=str, required=True, location="json")
@@ -38,7 +55,7 @@ class AppImportApi(Resource):
     @setup_required
     @login_required
     @account_initialization_required
-    @marshal_with(app_import_fields)
+    @marshal_with(app_import_model)
     @cloud_edition_billing_resource_check("apps")
     @edit_permission_required
     def post(self):
@@ -81,7 +98,7 @@ class AppImportConfirmApi(Resource):
     @setup_required
     @login_required
     @account_initialization_required
-    @marshal_with(app_import_fields)
+    @marshal_with(app_import_model)
     @edit_permission_required
     def post(self, import_id):
         # Check user role first
@@ -107,7 +124,7 @@ class AppImportCheckDependenciesApi(Resource):
     @login_required
     @get_app_model
     @account_initialization_required
-    @marshal_with(app_import_check_dependencies_fields)
+    @marshal_with(app_import_check_dependencies_model)
     @edit_permission_required
     def get(self, app_model: App):
         with Session(db.engine) as session:

api/controllers/console/app/completion.py

@@ -17,7 +17,6 @@ from controllers.console.app.error import (
 from controllers.console.app.wraps import get_app_model
 from controllers.console.wraps import account_initialization_required, edit_permission_required, setup_required
 from controllers.web.error import InvokeRateLimitError as InvokeRateLimitHttpError
-from core.app.apps.base_app_queue_manager import AppQueueManager
 from core.app.entities.app_invoke_entities import InvokeFrom
 from core.errors.error import (
     ModelCurrentlyNotSupportError,
@@ -32,6 +31,7 @@ from libs.login import current_user, login_required
 from models import Account
 from models.model import AppMode
 from services.app_generate_service import AppGenerateService
+from services.app_task_service import AppTaskService
 from services.errors.llm import InvokeRateLimitError
 
 logger = logging.getLogger(__name__)
@@ -121,7 +121,13 @@ class CompletionMessageStopApi(Resource):
     def post(self, app_model, task_id):
         if not isinstance(current_user, Account):
             raise ValueError("current_user must be an Account instance")
-        AppQueueManager.set_stop_flag(task_id, InvokeFrom.DEBUGGER, current_user.id)
+
+        AppTaskService.stop_task(
+            task_id=task_id,
+            invoke_from=InvokeFrom.DEBUGGER,
+            user_id=current_user.id,
+            app_mode=AppMode.value_of(app_model.mode),
+        )
 
         return {"result": "success"}, 200
 
@@ -220,6 +226,12 @@ class ChatMessageStopApi(Resource):
     def post(self, app_model, task_id):
         if not isinstance(current_user, Account):
             raise ValueError("current_user must be an Account instance")
-        AppQueueManager.set_stop_flag(task_id, InvokeFrom.DEBUGGER, current_user.id)
+
+        AppTaskService.stop_task(
+            task_id=task_id,
+            invoke_from=InvokeFrom.DEBUGGER,
+            user_id=current_user.id,
+            app_mode=AppMode.value_of(app_model.mode),
+        )
 
         return {"result": "success"}, 200

api/controllers/console/app/conversation.py

@@ -1,6 +1,6 @@
 import sqlalchemy as sa
 from flask import abort
-from flask_restx import Resource, marshal_with, reqparse
+from flask_restx import Resource, fields, marshal_with, reqparse
 from flask_restx.inputs import int_range
 from sqlalchemy import func, or_
 from sqlalchemy.orm import joinedload
@@ -11,20 +11,272 @@ from controllers.console.app.wraps import get_app_model
 from controllers.console.wraps import account_initialization_required, edit_permission_required, setup_required
 from core.app.entities.app_invoke_entities import InvokeFrom
 from extensions.ext_database import db
-from fields.conversation_fields import (
-    conversation_detail_fields,
-    conversation_message_detail_fields,
-    conversation_pagination_fields,
-    conversation_with_summary_pagination_fields,
-)
+from fields.conversation_fields import MessageTextField
+from fields.raws import FilesContainedField
 from libs.datetime_utils import naive_utc_now, parse_time_range
-from libs.helper import DatetimeString
+from libs.helper import DatetimeString, TimestampField
 from libs.login import current_account_with_tenant, login_required
 from models import Conversation, EndUser, Message, MessageAnnotation
 from models.model import AppMode
 from services.conversation_service import ConversationService
 from services.errors.conversation import ConversationNotExistsError
 
+# Register models for flask_restx to avoid dict type issues in Swagger
+# Register in dependency order: base models first, then dependent models
+
+# Base models
+simple_account_model = console_ns.model(
+    "SimpleAccount",
+    {
+        "id": fields.String,
+        "name": fields.String,
+        "email": fields.String,
+    },
+)
+
+feedback_stat_model = console_ns.model(
+    "FeedbackStat",
+    {
+        "like": fields.Integer,
+        "dislike": fields.Integer,
+    },
+)
+
+status_count_model = console_ns.model(
+    "StatusCount",
+    {
+        "success": fields.Integer,
+        "failed": fields.Integer,
+        "partial_success": fields.Integer,
+    },
+)
+
+message_file_model = console_ns.model(
+    "MessageFile",
+    {
+        "id": fields.String,
+        "filename": fields.String,
+        "type": fields.String,
+        "url": fields.String,
+        "mime_type": fields.String,
+        "size": fields.Integer,
+        "transfer_method": fields.String,
+        "belongs_to": fields.String(default="user"),
+        "upload_file_id": fields.String(default=None),
+    },
+)
+
+agent_thought_model = console_ns.model(
+    "AgentThought",
+    {
+        "id": fields.String,
+        "chain_id": fields.String,
+        "message_id": fields.String,
+        "position": fields.Integer,
+        "thought": fields.String,
+        "tool": fields.String,
+        "tool_labels": fields.Raw,
+        "tool_input": fields.String,
+        "created_at": TimestampField,
+        "observation": fields.String,
+        "files": fields.List(fields.String),
+    },
+)
+
+simple_model_config_model = console_ns.model(
+    "SimpleModelConfig",
+    {
+        "model": fields.Raw(attribute="model_dict"),
+        "pre_prompt": fields.String,
+    },
+)
+
+model_config_model = console_ns.model(
+    "ModelConfig",
+    {
+        "opening_statement": fields.String,
+        "suggested_questions": fields.Raw,
+        "model": fields.Raw,
+        "user_input_form": fields.Raw,
+        "pre_prompt": fields.String,
+        "agent_mode": fields.Raw,
+    },
+)
+
+# Models that depend on simple_account_model
+feedback_model = console_ns.model(
+    "Feedback",
+    {
+        "rating": fields.String,
+        "content": fields.String,
+        "from_source": fields.String,
+        "from_end_user_id": fields.String,
+        "from_account": fields.Nested(simple_account_model, allow_null=True),
+    },
+)
+
+annotation_model = console_ns.model(
+    "Annotation",
+    {
+        "id": fields.String,
+        "question": fields.String,
+        "content": fields.String,
+        "account": fields.Nested(simple_account_model, allow_null=True),
+        "created_at": TimestampField,
+    },
+)
+
+annotation_hit_history_model = console_ns.model(
+    "AnnotationHitHistory",
+    {
+        "annotation_id": fields.String(attribute="id"),
+        "annotation_create_account": fields.Nested(simple_account_model, allow_null=True),
+        "created_at": TimestampField,
+    },
+)
+
+# Simple message detail model
+simple_message_detail_model = console_ns.model(
+    "SimpleMessageDetail",
+    {
+        "inputs": FilesContainedField,
+        "query": fields.String,
+        "message": MessageTextField,
+        "answer": fields.String,
+    },
+)
+
+# Message detail model that depends on multiple models
+message_detail_model = console_ns.model(
+    "MessageDetail",
+    {
+        "id": fields.String,
+        "conversation_id": fields.String,
+        "inputs": FilesContainedField,
+        "query": fields.String,
+        "message": fields.Raw,
+        "message_tokens": fields.Integer,
+        "answer": fields.String(attribute="re_sign_file_url_answer"),
+        "answer_tokens": fields.Integer,
+        "provider_response_latency": fields.Float,
+        "from_source": fields.String,
+        "from_end_user_id": fields.String,
+        "from_account_id": fields.String,
+        "feedbacks": fields.List(fields.Nested(feedback_model)),
+        "workflow_run_id": fields.String,
+        "annotation": fields.Nested(annotation_model, allow_null=True),
+        "annotation_hit_history": fields.Nested(annotation_hit_history_model, allow_null=True),
+        "created_at": TimestampField,
+        "agent_thoughts": fields.List(fields.Nested(agent_thought_model)),
+        "message_files": fields.List(fields.Nested(message_file_model)),
+        "metadata": fields.Raw(attribute="message_metadata_dict"),
+        "status": fields.String,
+        "error": fields.String,
+        "parent_message_id": fields.String,
+    },
+)
+
+# Conversation models
+conversation_fields_model = console_ns.model(
+    "Conversation",
+    {
+        "id": fields.String,
+        "status": fields.String,
+        "from_source": fields.String,
+        "from_end_user_id": fields.String,
+        "from_end_user_session_id": fields.String(),
+        "from_account_id": fields.String,
+        "from_account_name": fields.String,
+        "read_at": TimestampField,
+        "created_at": TimestampField,
+        "updated_at": TimestampField,
+        "annotation": fields.Nested(annotation_model, allow_null=True),
+        "model_config": fields.Nested(simple_model_config_model),
+        "user_feedback_stats": fields.Nested(feedback_stat_model),
+        "admin_feedback_stats": fields.Nested(feedback_stat_model),
+        "message": fields.Nested(simple_message_detail_model, attribute="first_message"),
+    },
+)
+
+conversation_pagination_model = console_ns.model(
+    "ConversationPagination",
+    {
+        "page": fields.Integer,
+        "limit": fields.Integer(attribute="per_page"),
+        "total": fields.Integer,
+        "has_more": fields.Boolean(attribute="has_next"),
+        "data": fields.List(fields.Nested(conversation_fields_model), attribute="items"),
+    },
+)
+
+conversation_message_detail_model = console_ns.model(
+    "ConversationMessageDetail",
+    {
+        "id": fields.String,
+        "status": fields.String,
+        "from_source": fields.String,
+        "from_end_user_id": fields.String,
+        "from_account_id": fields.String,
+        "created_at": TimestampField,
+        "model_config": fields.Nested(model_config_model),
+        "message": fields.Nested(message_detail_model, attribute="first_message"),
+    },
+)
+
+conversation_with_summary_model = console_ns.model(
+    "ConversationWithSummary",
+    {
+        "id": fields.String,
+        "status": fields.String,
+        "from_source": fields.String,
+        "from_end_user_id": fields.String,
+        "from_end_user_session_id": fields.String,
+        "from_account_id": fields.String,
+        "from_account_name": fields.String,
+        "name": fields.String,
+        "summary": fields.String(attribute="summary_or_query"),
+        "read_at": TimestampField,
+        "created_at": TimestampField,
+        "updated_at": TimestampField,
+        "annotated": fields.Boolean,
+        "model_config": fields.Nested(simple_model_config_model),
+        "message_count": fields.Integer,
+        "user_feedback_stats": fields.Nested(feedback_stat_model),
+        "admin_feedback_stats": fields.Nested(feedback_stat_model),
+        "status_count": fields.Nested(status_count_model),
+    },
+)
+
+conversation_with_summary_pagination_model = console_ns.model(
+    "ConversationWithSummaryPagination",
+    {
+        "page": fields.Integer,
+        "limit": fields.Integer(attribute="per_page"),
+        "total": fields.Integer,
+        "has_more": fields.Boolean(attribute="has_next"),
+        "data": fields.List(fields.Nested(conversation_with_summary_model), attribute="items"),
+    },
+)
+
+conversation_detail_model = console_ns.model(
+    "ConversationDetail",
+    {
+        "id": fields.String,
+        "status": fields.String,
+        "from_source": fields.String,
+        "from_end_user_id": fields.String,
+        "from_account_id": fields.String,
+        "created_at": TimestampField,
+        "updated_at": TimestampField,
+        "annotated": fields.Boolean,
+        "introduction": fields.String,
+        "model_config": fields.Nested(model_config_model),
+        "message_count": fields.Integer,
+        "user_feedback_stats": fields.Nested(feedback_stat_model),
+        "admin_feedback_stats": fields.Nested(feedback_stat_model),
+    },
+)
+
 
 @console_ns.route("/apps/<uuid:app_id>/completion-conversations")
 class CompletionConversationApi(Resource):
@@ -47,13 +299,13 @@ class CompletionConversationApi(Resource):
         .add_argument("page", type=int, location="args", default=1, help="Page number")
         .add_argument("limit", type=int, location="args", default=20, help="Page size (1-100)")
     )
-    @console_ns.response(200, "Success", conversation_pagination_fields)
+    @console_ns.response(200, "Success", conversation_pagination_model)
     @console_ns.response(403, "Insufficient permissions")
     @setup_required
     @login_required
     @account_initialization_required
     @get_app_model(mode=AppMode.COMPLETION)
-    @marshal_with(conversation_pagination_fields)
+    @marshal_with(conversation_pagination_model)
     @edit_permission_required
     def get(self, app_model):
         current_user, _ = current_account_with_tenant()
@@ -125,14 +377,14 @@ class CompletionConversationDetailApi(Resource):
     @console_ns.doc("get_completion_conversation")
     @console_ns.doc(description="Get completion conversation details with messages")
     @console_ns.doc(params={"app_id": "Application ID", "conversation_id": "Conversation ID"})
-    @console_ns.response(200, "Success", conversation_message_detail_fields)
+    @console_ns.response(200, "Success", conversation_message_detail_model)
     @console_ns.response(403, "Insufficient permissions")
     @console_ns.response(404, "Conversation not found")
     @setup_required
     @login_required
     @account_initialization_required
     @get_app_model(mode=AppMode.COMPLETION)
-    @marshal_with(conversation_message_detail_fields)
+    @marshal_with(conversation_message_detail_model)
     @edit_permission_required
     def get(self, app_model, conversation_id):
         conversation_id = str(conversation_id)
@@ -192,13 +444,13 @@ class ChatConversationApi(Resource):
             help="Sort field and direction",
         )
     )
-    @console_ns.response(200, "Success", conversation_with_summary_pagination_fields)
+    @console_ns.response(200, "Success", conversation_with_summary_pagination_model)
     @console_ns.response(403, "Insufficient permissions")
     @setup_required
     @login_required
     @account_initialization_required
     @get_app_model(mode=[AppMode.CHAT, AppMode.AGENT_CHAT, AppMode.ADVANCED_CHAT])
-    @marshal_with(conversation_with_summary_pagination_fields)
+    @marshal_with(conversation_with_summary_pagination_model)
     @edit_permission_required
     def get(self, app_model):
         current_user, _ = current_account_with_tenant()
@@ -325,14 +577,14 @@ class ChatConversationDetailApi(Resource):
     @console_ns.doc("get_chat_conversation")
     @console_ns.doc(description="Get chat conversation details")
     @console_ns.doc(params={"app_id": "Application ID", "conversation_id": "Conversation ID"})
-    @console_ns.response(200, "Success", conversation_detail_fields)
+    @console_ns.response(200, "Success", conversation_detail_model)
     @console_ns.response(403, "Insufficient permissions")
     @console_ns.response(404, "Conversation not found")
     @setup_required
     @login_required
     @account_initialization_required
     @get_app_model(mode=[AppMode.CHAT, AppMode.AGENT_CHAT, AppMode.ADVANCED_CHAT])
-    @marshal_with(conversation_detail_fields)
+    @marshal_with(conversation_detail_model)
     @edit_permission_required
     def get(self, app_model, conversation_id):
         conversation_id = str(conversation_id)

api/controllers/console/app/conversation_variables.py

@@ -1,4 +1,4 @@
-from flask_restx import Resource, marshal_with, reqparse
+from flask_restx import Resource, fields, marshal_with, reqparse
 from sqlalchemy import select
 from sqlalchemy.orm import Session
 
@@ -6,11 +6,27 @@ from controllers.console import console_ns
 from controllers.console.app.wraps import get_app_model
 from controllers.console.wraps import account_initialization_required, setup_required
 from extensions.ext_database import db
-from fields.conversation_variable_fields import paginated_conversation_variable_fields
+from fields.conversation_variable_fields import (
+    conversation_variable_fields,
+    paginated_conversation_variable_fields,
+)
 from libs.login import login_required
 from models import ConversationVariable
 from models.model import AppMode
 
+# Register models for flask_restx to avoid dict type issues in Swagger
+# Register base model first
+conversation_variable_model = console_ns.model("ConversationVariable", conversation_variable_fields)
+
+# For nested models, need to replace nested dict with registered model
+paginated_conversation_variable_fields_copy = paginated_conversation_variable_fields.copy()
+paginated_conversation_variable_fields_copy["data"] = fields.List(
+    fields.Nested(conversation_variable_model), attribute="data"
+)
+paginated_conversation_variable_model = console_ns.model(
+    "PaginatedConversationVariable", paginated_conversation_variable_fields_copy
+)
+
 
 @console_ns.route("/apps/<uuid:app_id>/conversation-variables")
 class ConversationVariablesApi(Resource):
@@ -22,12 +38,12 @@ class ConversationVariablesApi(Resource):
             "conversation_id", type=str, location="args", help="Conversation ID to filter variables"
         )
     )
-    @console_ns.response(200, "Conversation variables retrieved successfully", paginated_conversation_variable_fields)
+    @console_ns.response(200, "Conversation variables retrieved successfully", paginated_conversation_variable_model)
     @setup_required
     @login_required
     @account_initialization_required
     @get_app_model(mode=AppMode.ADVANCED_CHAT)
-    @marshal_with(paginated_conversation_variable_fields)
+    @marshal_with(paginated_conversation_variable_model)
     def get(self, app_model):
         parser = reqparse.RequestParser().add_argument("conversation_id", type=str, location="args")
         args = parser.parse_args()

api/controllers/console/app/generator.py

@@ -1,3 +1,5 @@
+from collections.abc import Sequence
+
 from flask_restx import Resource, fields, reqparse
 
 from controllers.console import console_ns
@@ -9,9 +11,14 @@ from controllers.console.app.error import (
 )
 from controllers.console.wraps import account_initialization_required, setup_required
 from core.errors.error import ModelCurrentlyNotSupportError, ProviderTokenNotInitError, QuotaExceededError
+from core.helper.code_executor.code_node_provider import CodeNodeProvider
+from core.helper.code_executor.javascript.javascript_code_provider import JavascriptCodeProvider
+from core.helper.code_executor.python3.python3_code_provider import Python3CodeProvider
 from core.llm_generator.llm_generator import LLMGenerator
 from core.model_runtime.errors.invoke import InvokeError
+from extensions.ext_database import db
 from libs.login import current_account_with_tenant, login_required
+from models import App
 from services.workflow_service import WorkflowService
 
 
@@ -171,29 +178,11 @@ class InstructionGenerateApi(Resource):
         console_ns.model(
             "InstructionGenerateRequest",
             {
-                "type": fields.String(
-                    required=True,
-                    description="Request type",
-                    enum=[
-                        "legacy_prompt_generate",
-                        "workflow_prompt_generate",
-                        "workflow_code_generate",
-                        "workflow_prompt_edit",
-                        "workflow_code_edit",
-                        "memory_template_generate",
-                        "memory_instruction_generate",
-                        "memory_template_edit",
-                        "memory_instruction_edit",
-                    ]
-                ),
-                "flow_id": fields.String(description="Workflow/Flow ID"),
-                "node_id": fields.String(description="Node ID (optional)"),
-                "current": fields.String(description="Current content"),
-                "language": fields.String(
-                    default="javascript",
-                    description="Programming language (javascript/python)"
-                ),
-                "instruction": fields.String(required=True, description="User instruction"),
+                "flow_id": fields.String(required=True, description="Workflow/Flow ID"),
+                "node_id": fields.String(description="Node ID for workflow context"),
+                "current": fields.String(description="Current instruction text"),
+                "language": fields.String(default="javascript", description="Programming language (javascript/python)"),
+                "instruction": fields.String(required=True, description="Instruction for generation"),
                 "model_config": fields.Raw(required=True, description="Model configuration"),
                 "ideal_output": fields.String(description="Expected ideal output"),
             },
@@ -208,8 +197,7 @@ class InstructionGenerateApi(Resource):
     def post(self):
         parser = (
             reqparse.RequestParser()
-            .add_argument("type", type=str, required=True, nullable=False, location="json")
-            .add_argument("flow_id", type=str, required=False, default="", location="json")
+            .add_argument("flow_id", type=str, required=True, default="", location="json")
             .add_argument("node_id", type=str, required=False, default="", location="json")
             .add_argument("current", type=str, required=False, default="", location="json")
             .add_argument("language", type=str, required=False, default="javascript", location="json")
@@ -219,16 +207,70 @@ class InstructionGenerateApi(Resource):
         )
         args = parser.parse_args()
         _, current_tenant_id = current_account_with_tenant()
-
+        providers: list[type[CodeNodeProvider]] = [Python3CodeProvider, JavascriptCodeProvider]
+        code_provider: type[CodeNodeProvider] | None = next(
+            (p for p in providers if p.is_accept_language(args["language"])), None
+        )
+        code_template = code_provider.get_default_code() if code_provider else ""
         try:
-            # Validate parameters
-            is_valid, error_message = self._validate_params(args["type"], args)
-            if not is_valid:
-                return {"error": error_message}, 400
-
-            # Route based on type
-            return self._handle_by_type(args["type"], args, current_tenant_id)
-
+            # Generate from nothing for a workflow node
+            if (args["current"] == code_template or args["current"] == "") and args["node_id"] != "":
+                app = db.session.query(App).where(App.id == args["flow_id"]).first()
+                if not app:
+                    return {"error": f"app {args['flow_id']} not found"}, 400
+                workflow = WorkflowService().get_draft_workflow(app_model=app)
+                if not workflow:
+                    return {"error": f"workflow {args['flow_id']} not found"}, 400
+                nodes: Sequence = workflow.graph_dict["nodes"]
+                node = [node for node in nodes if node["id"] == args["node_id"]]
+                if len(node) == 0:
+                    return {"error": f"node {args['node_id']} not found"}, 400
+                node_type = node[0]["data"]["type"]
+                match node_type:
+                    case "llm":
+                        return LLMGenerator.generate_rule_config(
+                            current_tenant_id,
+                            instruction=args["instruction"],
+                            model_config=args["model_config"],
+                            no_variable=True,
+                        )
+                    case "agent":
+                        return LLMGenerator.generate_rule_config(
+                            current_tenant_id,
+                            instruction=args["instruction"],
+                            model_config=args["model_config"],
+                            no_variable=True,
+                        )
+                    case "code":
+                        return LLMGenerator.generate_code(
+                            tenant_id=current_tenant_id,
+                            instruction=args["instruction"],
+                            model_config=args["model_config"],
+                            code_language=args["language"],
+                        )
+                    case _:
+                        return {"error": f"invalid node type: {node_type}"}
+            if args["node_id"] == "" and args["current"] != "":  # For legacy app without a workflow
+                return LLMGenerator.instruction_modify_legacy(
+                    tenant_id=current_tenant_id,
+                    flow_id=args["flow_id"],
+                    current=args["current"],
+                    instruction=args["instruction"],
+                    model_config=args["model_config"],
+                    ideal_output=args["ideal_output"],
+                )
+            if args["node_id"] != "" and args["current"] != "":  # For workflow node
+                return LLMGenerator.instruction_modify_workflow(
+                    tenant_id=current_tenant_id,
+                    flow_id=args["flow_id"],
+                    node_id=args["node_id"],
+                    current=args["current"],
+                    instruction=args["instruction"],
+                    model_config=args["model_config"],
+                    ideal_output=args["ideal_output"],
+                    workflow_service=WorkflowService(),
+                )
+            return {"error": "incompatible parameters"}, 400
         except ProviderTokenNotInitError as ex:
             raise ProviderNotInitializeError(ex.description)
         except QuotaExceededError:
@@ -238,131 +280,6 @@ class InstructionGenerateApi(Resource):
         except InvokeError as e:
             raise CompletionRequestError(e.description)
 
-    def _validate_params(self, request_type: str, args: dict) -> tuple[bool, str]:
-        """
-        Validate request parameters
-
-        Returns:
-            (is_valid, error_message)
-        """
-        # All types require instruction and model_config
-        if not args.get("instruction"):
-            return False, "instruction is required"
-        if not args.get("model_config"):
-            return False, "model_config is required"
-
-        # Edit types require flow_id and current
-        if request_type.endswith("_edit"):
-            if not args.get("flow_id"):
-                return False, f"{request_type} requires flow_id"
-            if not args.get("current"):
-                return False, f"{request_type} requires current content"
-
-        # Code generate requires language
-        if request_type == "workflow_code_generate":
-            if args.get("language") not in ["python", "javascript"]:
-                return False, "language must be 'python' or 'javascript'"
-
-        return True, ""
-
-    def _handle_by_type(self, request_type: str, args: dict, tenant_id: str):
-        """
-        Route handling based on type
-        """
-        match request_type:
-            case "legacy_prompt_generate":
-                # Legacy prompt generation doesn't exist, this is actually an edit
-                if not args.get("flow_id"):
-                    return {"error": "legacy_prompt_generate requires flow_id"}, 400
-                return LLMGenerator.instruction_modify_legacy(
-                    tenant_id=tenant_id,
-                    flow_id=args["flow_id"],
-                    current=args["current"],
-                    instruction=args["instruction"],
-                    model_config=args["model_config"],
-                    ideal_output=args["ideal_output"],
-                )
-
-            case "workflow_prompt_generate":
-                return LLMGenerator.generate_rule_config(
-                    tenant_id,
-                    instruction=args["instruction"],
-                    model_config=args["model_config"],
-                    no_variable=True,
-                )
-
-            case "workflow_code_generate":
-                return LLMGenerator.generate_code(
-                    tenant_id=tenant_id,
-                    instruction=args["instruction"],
-                    model_config=args["model_config"],
-                    code_language=args["language"],
-                )
-
-            case "workflow_prompt_edit":
-                return LLMGenerator.instruction_modify_workflow(
-                    tenant_id=tenant_id,
-                    flow_id=args["flow_id"],
-                    node_id=args["node_id"],
-                    current=args["current"],
-                    instruction=args["instruction"],
-                    model_config=args["model_config"],
-                    ideal_output=args["ideal_output"],
-                    workflow_service=WorkflowService(),
-                )
-
-            case "workflow_code_edit":
-                # Code edit uses the same workflow edit logic
-                return LLMGenerator.instruction_modify_workflow(
-                    tenant_id=tenant_id,
-                    flow_id=args["flow_id"],
-                    node_id=args["node_id"],
-                    current=args["current"],
-                    instruction=args["instruction"],
-                    model_config=args["model_config"],
-                    ideal_output=args["ideal_output"],
-                    workflow_service=WorkflowService(),
-                )
-
-            case "memory_template_generate":
-                return LLMGenerator.generate_memory_template(
-                    tenant_id=tenant_id,
-                    instruction=args["instruction"],
-                    model_config=args["model_config"],
-                )
-
-            case "memory_instruction_generate":
-                return LLMGenerator.generate_memory_instruction(
-                    tenant_id=tenant_id,
-                    instruction=args["instruction"],
-                    model_config=args["model_config"],
-                )
-
-            case "memory_template_edit":
-                return LLMGenerator.edit_memory_template(
-                    tenant_id=tenant_id,
-                    flow_id=args["flow_id"],
-                    node_id=args.get("node_id") or None,
-                    current=args["current"],
-                    instruction=args["instruction"],
-                    model_config=args["model_config"],
-                    ideal_output=args["ideal_output"],
-                )
-
-            case "memory_instruction_edit":
-                return LLMGenerator.edit_memory_instruction(
-                    tenant_id=tenant_id,
-                    flow_id=args["flow_id"],
-                    node_id=args.get("node_id") or None,
-                    current=args["current"],
-                    instruction=args["instruction"],
-                    model_config=args["model_config"],
-                    ideal_output=args["ideal_output"],
-                )
-
-            case _:
-                return {"error": f"Invalid request type: {request_type}"}, 400
-
 
 @console_ns.route("/instruction-generate/template")
 class InstructionGenerationTemplateApi(Resource):

api/controllers/console/app/mcp_server.py

@@ -12,6 +12,9 @@ from fields.app_fields import app_server_fields
 from libs.login import current_account_with_tenant, login_required
 from models.model import AppMCPServer
 
+# Register model for flask_restx to avoid dict type issues in Swagger
+app_server_model = console_ns.model("AppServer", app_server_fields)
+
 
 class AppMCPServerStatus(StrEnum):
     ACTIVE = "active"
@@ -23,12 +26,12 @@ class AppMCPServerController(Resource):
     @console_ns.doc("get_app_mcp_server")
     @console_ns.doc(description="Get MCP server configuration for an application")
     @console_ns.doc(params={"app_id": "Application ID"})
-    @console_ns.response(200, "MCP server configuration retrieved successfully", app_server_fields)
+    @console_ns.response(200, "MCP server configuration retrieved successfully", app_server_model)
     @login_required
     @account_initialization_required
     @setup_required
     @get_app_model
-    @marshal_with(app_server_fields)
+    @marshal_with(app_server_model)
     def get(self, app_model):
         server = db.session.query(AppMCPServer).where(AppMCPServer.app_id == app_model.id).first()
         return server
@@ -45,13 +48,13 @@ class AppMCPServerController(Resource):
             },
         )
     )
-    @console_ns.response(201, "MCP server configuration created successfully", app_server_fields)
+    @console_ns.response(201, "MCP server configuration created successfully", app_server_model)
     @console_ns.response(403, "Insufficient permissions")
     @account_initialization_required
     @get_app_model
     @login_required
     @setup_required
-    @marshal_with(app_server_fields)
+    @marshal_with(app_server_model)
     @edit_permission_required
     def post(self, app_model):
         _, current_tenant_id = current_account_with_tenant()
@@ -93,14 +96,14 @@ class AppMCPServerController(Resource):
             },
         )
     )
-    @console_ns.response(200, "MCP server configuration updated successfully", app_server_fields)
+    @console_ns.response(200, "MCP server configuration updated successfully", app_server_model)
     @console_ns.response(403, "Insufficient permissions")
     @console_ns.response(404, "Server not found")
     @get_app_model
     @login_required
     @setup_required
     @account_initialization_required
-    @marshal_with(app_server_fields)
+    @marshal_with(app_server_model)
     @edit_permission_required
     def put(self, app_model):
         parser = (
@@ -137,13 +140,13 @@ class AppMCPServerRefreshController(Resource):
     @console_ns.doc("refresh_app_mcp_server")
     @console_ns.doc(description="Refresh MCP server configuration and regenerate server code")
     @console_ns.doc(params={"server_id": "Server ID"})
-    @console_ns.response(200, "MCP server refreshed successfully", app_server_fields)
+    @console_ns.response(200, "MCP server refreshed successfully", app_server_model)
     @console_ns.response(403, "Insufficient permissions")
     @console_ns.response(404, "Server not found")
     @setup_required
     @login_required
     @account_initialization_required
-    @marshal_with(app_server_fields)
+    @marshal_with(app_server_model)
     @edit_permission_required
     def get(self, server_id):
         _, current_tenant_id = current_account_with_tenant()

api/controllers/console/app/message.py

@@ -23,8 +23,8 @@ from core.app.entities.app_invoke_entities import InvokeFrom
 from core.errors.error import ModelCurrentlyNotSupportError, ProviderTokenNotInitError, QuotaExceededError
 from core.model_runtime.errors.invoke import InvokeError
 from extensions.ext_database import db
-from fields.conversation_fields import message_detail_fields
-from libs.helper import uuid_value
+from fields.raws import FilesContainedField
+from libs.helper import TimestampField, uuid_value
 from libs.infinite_scroll_pagination import InfiniteScrollPagination
 from libs.login import current_account_with_tenant, login_required
 from models.model import AppMode, Conversation, Message, MessageAnnotation, MessageFeedback
@@ -34,15 +34,126 @@ from services.message_service import MessageService
 
 logger = logging.getLogger(__name__)
 
+# Register models for flask_restx to avoid dict type issues in Swagger
+# Register in dependency order: base models first, then dependent models
+
+# Base models
+simple_account_model = console_ns.model(
+    "SimpleAccount",
+    {
+        "id": fields.String,
+        "name": fields.String,
+        "email": fields.String,
+    },
+)
+
+message_file_model = console_ns.model(
+    "MessageFile",
+    {
+        "id": fields.String,
+        "filename": fields.String,
+        "type": fields.String,
+        "url": fields.String,
+        "mime_type": fields.String,
+        "size": fields.Integer,
+        "transfer_method": fields.String,
+        "belongs_to": fields.String(default="user"),
+        "upload_file_id": fields.String(default=None),
+    },
+)
+
+agent_thought_model = console_ns.model(
+    "AgentThought",
+    {
+        "id": fields.String,
+        "chain_id": fields.String,
+        "message_id": fields.String,
+        "position": fields.Integer,
+        "thought": fields.String,
+        "tool": fields.String,
+        "tool_labels": fields.Raw,
+        "tool_input": fields.String,
+        "created_at": TimestampField,
+        "observation": fields.String,
+        "files": fields.List(fields.String),
+    },
+)
+
+# Models that depend on simple_account_model
+feedback_model = console_ns.model(
+    "Feedback",
+    {
+        "rating": fields.String,
+        "content": fields.String,
+        "from_source": fields.String,
+        "from_end_user_id": fields.String,
+        "from_account": fields.Nested(simple_account_model, allow_null=True),
+    },
+)
+
+annotation_model = console_ns.model(
+    "Annotation",
+    {
+        "id": fields.String,
+        "question": fields.String,
+        "content": fields.String,
+        "account": fields.Nested(simple_account_model, allow_null=True),
+        "created_at": TimestampField,
+    },
+)
+
+annotation_hit_history_model = console_ns.model(
+    "AnnotationHitHistory",
+    {
+        "annotation_id": fields.String(attribute="id"),
+        "annotation_create_account": fields.Nested(simple_account_model, allow_null=True),
+        "created_at": TimestampField,
+    },
+)
+
+# Message detail model that depends on multiple models
+message_detail_model = console_ns.model(
+    "MessageDetail",
+    {
+        "id": fields.String,
+        "conversation_id": fields.String,
+        "inputs": FilesContainedField,
+        "query": fields.String,
+        "message": fields.Raw,
+        "message_tokens": fields.Integer,
+        "answer": fields.String(attribute="re_sign_file_url_answer"),
+        "answer_tokens": fields.Integer,
+        "provider_response_latency": fields.Float,
+        "from_source": fields.String,
+        "from_end_user_id": fields.String,
+        "from_account_id": fields.String,
+        "feedbacks": fields.List(fields.Nested(feedback_model)),
+        "workflow_run_id": fields.String,
+        "annotation": fields.Nested(annotation_model, allow_null=True),
+        "annotation_hit_history": fields.Nested(annotation_hit_history_model, allow_null=True),
+        "created_at": TimestampField,
+        "agent_thoughts": fields.List(fields.Nested(agent_thought_model)),
+        "message_files": fields.List(fields.Nested(message_file_model)),
+        "metadata": fields.Raw(attribute="message_metadata_dict"),
+        "status": fields.String,
+        "error": fields.String,
+        "parent_message_id": fields.String,
+    },
+)
+
+# Message infinite scroll pagination model
+message_infinite_scroll_pagination_model = console_ns.model(
+    "MessageInfiniteScrollPagination",
+    {
+        "limit": fields.Integer,
+        "has_more": fields.Boolean,
+        "data": fields.List(fields.Nested(message_detail_model)),
+    },
+)
+
 
 @console_ns.route("/apps/<uuid:app_id>/chat-messages")
 class ChatMessageListApi(Resource):
-    message_infinite_scroll_pagination_fields = {
-        "limit": fields.Integer,
-        "has_more": fields.Boolean,
-        "data": fields.List(fields.Nested(message_detail_fields)),
-    }
-
     @console_ns.doc("list_chat_messages")
     @console_ns.doc(description="Get chat messages for a conversation with pagination")
     @console_ns.doc(params={"app_id": "Application ID"})
@@ -52,13 +163,13 @@ class ChatMessageListApi(Resource):
         .add_argument("first_id", type=str, location="args", help="First message ID for pagination")
         .add_argument("limit", type=int, location="args", default=20, help="Number of messages to return (1-100)")
     )
-    @console_ns.response(200, "Success", message_infinite_scroll_pagination_fields)
+    @console_ns.response(200, "Success", message_infinite_scroll_pagination_model)
     @console_ns.response(404, "Conversation not found")
     @login_required
     @account_initialization_required
     @setup_required
     @get_app_model(mode=[AppMode.CHAT, AppMode.AGENT_CHAT, AppMode.ADVANCED_CHAT])
-    @marshal_with(message_infinite_scroll_pagination_fields)
+    @marshal_with(message_infinite_scroll_pagination_model)
     @edit_permission_required
     def get(self, app_model):
         parser = (
@@ -258,18 +369,70 @@ class MessageSuggestedQuestionApi(Resource):
         return {"data": questions}
 
 
+# Shared parser for feedback export (used for both documentation and runtime parsing)
+feedback_export_parser = (
+    console_ns.parser()
+    .add_argument("from_source", type=str, choices=["user", "admin"], location="args", help="Filter by feedback source")
+    .add_argument("rating", type=str, choices=["like", "dislike"], location="args", help="Filter by rating")
+    .add_argument("has_comment", type=bool, location="args", help="Only include feedback with comments")
+    .add_argument("start_date", type=str, location="args", help="Start date (YYYY-MM-DD)")
+    .add_argument("end_date", type=str, location="args", help="End date (YYYY-MM-DD)")
+    .add_argument("format", type=str, choices=["csv", "json"], default="csv", location="args", help="Export format")
+)
+
+
+@console_ns.route("/apps/<uuid:app_id>/feedbacks/export")
+class MessageFeedbackExportApi(Resource):
+    @console_ns.doc("export_feedbacks")
+    @console_ns.doc(description="Export user feedback data for Google Sheets")
+    @console_ns.doc(params={"app_id": "Application ID"})
+    @console_ns.expect(feedback_export_parser)
+    @console_ns.response(200, "Feedback data exported successfully")
+    @console_ns.response(400, "Invalid parameters")
+    @console_ns.response(500, "Internal server error")
+    @get_app_model
+    @setup_required
+    @login_required
+    @account_initialization_required
+    def get(self, app_model):
+        args = feedback_export_parser.parse_args()
+
+        # Import the service function
+        from services.feedback_service import FeedbackService
+
+        try:
+            export_data = FeedbackService.export_feedbacks(
+                app_id=app_model.id,
+                from_source=args.get("from_source"),
+                rating=args.get("rating"),
+                has_comment=args.get("has_comment"),
+                start_date=args.get("start_date"),
+                end_date=args.get("end_date"),
+                format_type=args.get("format", "csv"),
+            )
+
+            return export_data
+
+        except ValueError as e:
+            logger.exception("Parameter validation error in feedback export")
+            return {"error": f"Parameter validation error: {str(e)}"}, 400
+        except Exception as e:
+            logger.exception("Error exporting feedback data")
+            raise InternalServerError(str(e))
+
+
 @console_ns.route("/apps/<uuid:app_id>/messages/<uuid:message_id>")
 class MessageApi(Resource):
     @console_ns.doc("get_message")
     @console_ns.doc(description="Get message details by ID")
     @console_ns.doc(params={"app_id": "Application ID", "message_id": "Message ID"})
-    @console_ns.response(200, "Message retrieved successfully", message_detail_fields)
+    @console_ns.response(200, "Message retrieved successfully", message_detail_model)
     @console_ns.response(404, "Message not found")
     @get_app_model
     @setup_required
     @login_required
     @account_initialization_required
-    @marshal_with(message_detail_fields)
+    @marshal_with(message_detail_model)
     def get(self, app_model, message_id: str):
         message_id = str(message_id)
 

api/controllers/console/app/site.py

@@ -16,6 +16,9 @@ from libs.datetime_utils import naive_utc_now
 from libs.login import current_account_with_tenant, login_required
 from models import Site
 
+# Register model for flask_restx to avoid dict type issues in Swagger
+app_site_model = console_ns.model("AppSite", app_site_fields)
+
 
 def parse_app_site_args():
     parser = (
@@ -76,7 +79,7 @@ class AppSite(Resource):
             },
         )
     )
-    @console_ns.response(200, "Site configuration updated successfully", app_site_fields)
+    @console_ns.response(200, "Site configuration updated successfully", app_site_model)
     @console_ns.response(403, "Insufficient permissions")
     @console_ns.response(404, "App not found")
     @setup_required
@@ -84,7 +87,7 @@ class AppSite(Resource):
     @edit_permission_required
     @account_initialization_required
     @get_app_model
-    @marshal_with(app_site_fields)
+    @marshal_with(app_site_model)
     def post(self, app_model):
         args = parse_app_site_args()
         current_user, _ = current_account_with_tenant()
@@ -126,7 +129,7 @@ class AppSiteAccessTokenReset(Resource):
     @console_ns.doc("reset_app_site_access_token")
     @console_ns.doc(description="Reset access token for application site")
     @console_ns.doc(params={"app_id": "Application ID"})
-    @console_ns.response(200, "Access token reset successfully", app_site_fields)
+    @console_ns.response(200, "Access token reset successfully", app_site_model)
     @console_ns.response(403, "Insufficient permissions (admin/owner required)")
     @console_ns.response(404, "App or site not found")
     @setup_required
@@ -134,7 +137,7 @@ class AppSiteAccessTokenReset(Resource):
     @is_admin_or_owner_required
     @account_initialization_required
     @get_app_model
-    @marshal_with(app_site_fields)
+    @marshal_with(app_site_model)
     def post(self, app_model):
         current_user, _ = current_account_with_tenant()
         site = db.session.query(Site).where(Site.app_id == app_model.id).first()

api/controllers/console/app/workflow.py

@@ -5,7 +5,6 @@ from typing import cast
 
 from flask import abort, request
 from flask_restx import Resource, fields, inputs, marshal_with, reqparse
-from pydantic_core import ValidationError
 from sqlalchemy.orm import Session
 from werkzeug.exceptions import Forbidden, InternalServerError, NotFound
 
@@ -33,6 +32,7 @@ from core.workflow.enums import NodeType
 from core.workflow.graph_engine.manager import GraphEngineManager
 from extensions.ext_database import db
 from factories import file_factory, variable_factory
+from fields.member_fields import simple_account_fields
 from fields.workflow_fields import workflow_fields, workflow_pagination_fields
 from fields.workflow_run_fields import workflow_run_node_execution_fields
 from libs import helper
@@ -50,6 +50,62 @@ from services.workflow_service import DraftWorkflowDeletionError, WorkflowInUseE
 logger = logging.getLogger(__name__)
 LISTENING_RETRY_IN = 2000
 
+# Register models for flask_restx to avoid dict type issues in Swagger
+# Register in dependency order: base models first, then dependent models
+
+# Base models
+simple_account_model = console_ns.model("SimpleAccount", simple_account_fields)
+
+from fields.workflow_fields import pipeline_variable_fields, serialize_value_type
+
+conversation_variable_model = console_ns.model(
+    "ConversationVariable",
+    {
+        "id": fields.String,
+        "name": fields.String,
+        "value_type": fields.String(attribute=serialize_value_type),
+        "value": fields.Raw,
+        "description": fields.String,
+    },
+)
+
+pipeline_variable_model = console_ns.model("PipelineVariable", pipeline_variable_fields)
+
+# Workflow model with nested dependencies
+workflow_fields_copy = workflow_fields.copy()
+workflow_fields_copy["created_by"] = fields.Nested(simple_account_model, attribute="created_by_account")
+workflow_fields_copy["updated_by"] = fields.Nested(
+    simple_account_model, attribute="updated_by_account", allow_null=True
+)
+workflow_fields_copy["conversation_variables"] = fields.List(fields.Nested(conversation_variable_model))
+workflow_fields_copy["rag_pipeline_variables"] = fields.List(fields.Nested(pipeline_variable_model))
+workflow_model = console_ns.model("Workflow", workflow_fields_copy)
+
+# Workflow pagination model
+workflow_pagination_fields_copy = workflow_pagination_fields.copy()
+workflow_pagination_fields_copy["items"] = fields.List(fields.Nested(workflow_model), attribute="items")
+workflow_pagination_model = console_ns.model("WorkflowPagination", workflow_pagination_fields_copy)
+
+# Reuse workflow_run_node_execution_model from workflow_run.py if already registered
+# Otherwise register it here
+from fields.end_user_fields import simple_end_user_fields
+
+simple_end_user_model = None
+try:
+    simple_end_user_model = console_ns.models.get("SimpleEndUser")
+except AttributeError:
+    pass
+if simple_end_user_model is None:
+    simple_end_user_model = console_ns.model("SimpleEndUser", simple_end_user_fields)
+
+workflow_run_node_execution_model = None
+try:
+    workflow_run_node_execution_model = console_ns.models.get("WorkflowRunNodeExecution")
+except AttributeError:
+    pass
+if workflow_run_node_execution_model is None:
+    workflow_run_node_execution_model = console_ns.model("WorkflowRunNodeExecution", workflow_run_node_execution_fields)
+
 
 # TODO(QuantumGhost): Refactor existing node run API to handle file parameter parsing
 # at the controller level rather than in the workflow logic. This would improve separation
@@ -74,13 +130,13 @@ class DraftWorkflowApi(Resource):
     @console_ns.doc("get_draft_workflow")
     @console_ns.doc(description="Get draft workflow for an application")
     @console_ns.doc(params={"app_id": "Application ID"})
-    @console_ns.response(200, "Draft workflow retrieved successfully", workflow_fields)
+    @console_ns.response(200, "Draft workflow retrieved successfully", workflow_model)
     @console_ns.response(404, "Draft workflow not found")
     @setup_required
     @login_required
     @account_initialization_required
     @get_app_model(mode=[AppMode.ADVANCED_CHAT, AppMode.WORKFLOW])
-    @marshal_with(workflow_fields)
+    @marshal_with(workflow_model)
     @edit_permission_required
     def get(self, app_model: App):
         """
@@ -111,7 +167,6 @@ class DraftWorkflowApi(Resource):
                 "hash": fields.String(description="Workflow hash for validation"),
                 "environment_variables": fields.List(fields.Raw, required=True, description="Environment variables"),
                 "conversation_variables": fields.List(fields.Raw, description="Conversation variables"),
-                "memory_blocks": fields.List(fields.Raw, description="Memory blocks"),
             },
         )
     )
@@ -146,7 +201,6 @@ class DraftWorkflowApi(Resource):
                 .add_argument("hash", type=str, required=False, location="json")
                 .add_argument("environment_variables", type=list, required=True, location="json")
                 .add_argument("conversation_variables", type=list, required=False, location="json")
-                .add_argument("memory_blocks", type=list, required=False, location="json")
             )
             args = parser.parse_args()
         elif "text/plain" in content_type:
@@ -164,7 +218,6 @@ class DraftWorkflowApi(Resource):
                     "hash": data.get("hash"),
                     "environment_variables": data.get("environment_variables"),
                     "conversation_variables": data.get("conversation_variables"),
-                    "memory_blocks": data.get("memory_blocks"),
                 }
             except json.JSONDecodeError:
                 return {"message": "Invalid JSON data"}, 400
@@ -181,11 +234,6 @@ class DraftWorkflowApi(Resource):
             conversation_variables = [
                 variable_factory.build_conversation_variable_from_mapping(obj) for obj in conversation_variables_list
             ]
-            memory_blocks_list = args.get("memory_blocks") or []
-            from core.memory.entities import MemoryBlockSpec
-            memory_blocks = [
-                MemoryBlockSpec.model_validate(obj) for obj in memory_blocks_list
-            ]
             workflow = workflow_service.sync_draft_workflow(
                 app_model=app_model,
                 graph=args["graph"],
@@ -194,12 +242,9 @@ class DraftWorkflowApi(Resource):
                 account=current_user,
                 environment_variables=environment_variables,
                 conversation_variables=conversation_variables,
-                memory_blocks=memory_blocks,
             )
         except WorkflowHashNotEqualError:
             raise DraftWorkflowNotSync()
-        except ValidationError as e:
-            return {"message": str(e)}, 400
 
         return {
             "result": "success",
@@ -551,14 +596,14 @@ class DraftWorkflowNodeRunApi(Resource):
             },
         )
     )
-    @console_ns.response(200, "Node run started successfully", workflow_run_node_execution_fields)
+    @console_ns.response(200, "Node run started successfully", workflow_run_node_execution_model)
     @console_ns.response(403, "Permission denied")
     @console_ns.response(404, "Node not found")
     @setup_required
     @login_required
     @account_initialization_required
     @get_app_model(mode=[AppMode.ADVANCED_CHAT, AppMode.WORKFLOW])
-    @marshal_with(workflow_run_node_execution_fields)
+    @marshal_with(workflow_run_node_execution_model)
     @edit_permission_required
     def post(self, app_model: App, node_id: str):
         """
@@ -610,13 +655,13 @@ class PublishedWorkflowApi(Resource):
     @console_ns.doc("get_published_workflow")
     @console_ns.doc(description="Get published workflow for an application")
     @console_ns.doc(params={"app_id": "Application ID"})
-    @console_ns.response(200, "Published workflow retrieved successfully", workflow_fields)
+    @console_ns.response(200, "Published workflow retrieved successfully", workflow_model)
     @console_ns.response(404, "Published workflow not found")
     @setup_required
     @login_required
     @account_initialization_required
     @get_app_model(mode=[AppMode.ADVANCED_CHAT, AppMode.WORKFLOW])
-    @marshal_with(workflow_fields)
+    @marshal_with(workflow_model)
     @edit_permission_required
     def get(self, app_model: App):
         """
@@ -793,12 +838,12 @@ class PublishedAllWorkflowApi(Resource):
     @console_ns.doc("get_all_published_workflows")
     @console_ns.doc(description="Get all published workflows for an application")
     @console_ns.doc(params={"app_id": "Application ID"})
-    @console_ns.response(200, "Published workflows retrieved successfully", workflow_pagination_fields)
+    @console_ns.response(200, "Published workflows retrieved successfully", workflow_pagination_model)
     @setup_required
     @login_required
     @account_initialization_required
     @get_app_model(mode=[AppMode.ADVANCED_CHAT, AppMode.WORKFLOW])
-    @marshal_with(workflow_pagination_fields)
+    @marshal_with(workflow_pagination_model)
     @edit_permission_required
     def get(self, app_model: App):
         """
@@ -850,14 +895,14 @@ class WorkflowByIdApi(Resource):
             },
         )
     )
-    @console_ns.response(200, "Workflow updated successfully", workflow_fields)
+    @console_ns.response(200, "Workflow updated successfully", workflow_model)
     @console_ns.response(404, "Workflow not found")
     @console_ns.response(403, "Permission denied")
     @setup_required
     @login_required
     @account_initialization_required
     @get_app_model(mode=[AppMode.ADVANCED_CHAT, AppMode.WORKFLOW])
-    @marshal_with(workflow_fields)
+    @marshal_with(workflow_model)
     @edit_permission_required
     def patch(self, app_model: App, workflow_id: str):
         """
@@ -941,14 +986,14 @@ class DraftWorkflowNodeLastRunApi(Resource):
     @console_ns.doc("get_draft_workflow_node_last_run")
     @console_ns.doc(description="Get last run result for draft workflow node")
     @console_ns.doc(params={"app_id": "Application ID", "node_id": "Node ID"})
-    @console_ns.response(200, "Node last run retrieved successfully", workflow_run_node_execution_fields)
+    @console_ns.response(200, "Node last run retrieved successfully", workflow_run_node_execution_model)
     @console_ns.response(404, "Node last run not found")
     @console_ns.response(403, "Permission denied")
     @setup_required
     @login_required
     @account_initialization_required
     @get_app_model(mode=[AppMode.ADVANCED_CHAT, AppMode.WORKFLOW])
-    @marshal_with(workflow_run_node_execution_fields)
+    @marshal_with(workflow_run_node_execution_model)
     def get(self, app_model: App, node_id: str):
         srv = WorkflowService()
         workflow = srv.get_draft_workflow(app_model)

api/controllers/console/app/workflow_app_log.py

@@ -8,12 +8,15 @@ from controllers.console.app.wraps import get_app_model
 from controllers.console.wraps import account_initialization_required, setup_required
 from core.workflow.enums import WorkflowExecutionStatus
 from extensions.ext_database import db
-from fields.workflow_app_log_fields import workflow_app_log_pagination_fields
+from fields.workflow_app_log_fields import build_workflow_app_log_pagination_model
 from libs.login import login_required
 from models import App
 from models.model import AppMode
 from services.workflow_app_service import WorkflowAppService
 
+# Register model for flask_restx to avoid dict type issues in Swagger
+workflow_app_log_pagination_model = build_workflow_app_log_pagination_model(console_ns)
+
 
 @console_ns.route("/apps/<uuid:app_id>/workflow-app-logs")
 class WorkflowAppLogApi(Resource):
@@ -33,12 +36,12 @@ class WorkflowAppLogApi(Resource):
             "limit": "Number of items per page (1-100)",
         }
     )
-    @console_ns.response(200, "Workflow app logs retrieved successfully", workflow_app_log_pagination_fields)
+    @console_ns.response(200, "Workflow app logs retrieved successfully", workflow_app_log_pagination_model)
     @setup_required
     @login_required
     @account_initialization_required
     @get_app_model(mode=[AppMode.WORKFLOW])
-    @marshal_with(workflow_app_log_pagination_fields)
+    @marshal_with(workflow_app_log_pagination_model)
     def get(self, app_model: App):
         """
         Get workflow app logs

api/controllers/console/app/workflow_draft_variable.py

@@ -141,6 +141,37 @@ _WORKFLOW_DRAFT_VARIABLE_LIST_FIELDS = {
     "items": fields.List(fields.Nested(_WORKFLOW_DRAFT_VARIABLE_FIELDS), attribute=_get_items),
 }
 
+# Register models for flask_restx to avoid dict type issues in Swagger
+workflow_draft_variable_without_value_model = console_ns.model(
+    "WorkflowDraftVariableWithoutValue", _WORKFLOW_DRAFT_VARIABLE_WITHOUT_VALUE_FIELDS
+)
+
+workflow_draft_variable_model = console_ns.model("WorkflowDraftVariable", _WORKFLOW_DRAFT_VARIABLE_FIELDS)
+
+workflow_draft_env_variable_model = console_ns.model("WorkflowDraftEnvVariable", _WORKFLOW_DRAFT_ENV_VARIABLE_FIELDS)
+
+workflow_draft_env_variable_list_fields_copy = _WORKFLOW_DRAFT_ENV_VARIABLE_LIST_FIELDS.copy()
+workflow_draft_env_variable_list_fields_copy["items"] = fields.List(fields.Nested(workflow_draft_env_variable_model))
+workflow_draft_env_variable_list_model = console_ns.model(
+    "WorkflowDraftEnvVariableList", workflow_draft_env_variable_list_fields_copy
+)
+
+workflow_draft_variable_list_without_value_fields_copy = _WORKFLOW_DRAFT_VARIABLE_LIST_WITHOUT_VALUE_FIELDS.copy()
+workflow_draft_variable_list_without_value_fields_copy["items"] = fields.List(
+    fields.Nested(workflow_draft_variable_without_value_model), attribute=_get_items
+)
+workflow_draft_variable_list_without_value_model = console_ns.model(
+    "WorkflowDraftVariableListWithoutValue", workflow_draft_variable_list_without_value_fields_copy
+)
+
+workflow_draft_variable_list_fields_copy = _WORKFLOW_DRAFT_VARIABLE_LIST_FIELDS.copy()
+workflow_draft_variable_list_fields_copy["items"] = fields.List(
+    fields.Nested(workflow_draft_variable_model), attribute=_get_items
+)
+workflow_draft_variable_list_model = console_ns.model(
+    "WorkflowDraftVariableList", workflow_draft_variable_list_fields_copy
+)
+
 P = ParamSpec("P")
 R = TypeVar("R")
 
@@ -176,10 +207,10 @@ class WorkflowVariableCollectionApi(Resource):
     @console_ns.doc(params={"app_id": "Application ID"})
     @console_ns.doc(params={"page": "Page number (1-100000)", "limit": "Number of items per page (1-100)"})
     @console_ns.response(
-        200, "Workflow variables retrieved successfully", _WORKFLOW_DRAFT_VARIABLE_LIST_WITHOUT_VALUE_FIELDS
+        200, "Workflow variables retrieved successfully", workflow_draft_variable_list_without_value_model
     )
     @_api_prerequisite
-    @marshal_with(_WORKFLOW_DRAFT_VARIABLE_LIST_WITHOUT_VALUE_FIELDS)
+    @marshal_with(workflow_draft_variable_list_without_value_model)
     def get(self, app_model: App):
         """
         Get draft workflow
@@ -242,9 +273,9 @@ class NodeVariableCollectionApi(Resource):
     @console_ns.doc("get_node_variables")
     @console_ns.doc(description="Get variables for a specific node")
     @console_ns.doc(params={"app_id": "Application ID", "node_id": "Node ID"})
-    @console_ns.response(200, "Node variables retrieved successfully", _WORKFLOW_DRAFT_VARIABLE_LIST_FIELDS)
+    @console_ns.response(200, "Node variables retrieved successfully", workflow_draft_variable_list_model)
     @_api_prerequisite
-    @marshal_with(_WORKFLOW_DRAFT_VARIABLE_LIST_FIELDS)
+    @marshal_with(workflow_draft_variable_list_model)
     def get(self, app_model: App, node_id: str):
         validate_node_id(node_id)
         with Session(bind=db.engine, expire_on_commit=False) as session:
@@ -275,10 +306,10 @@ class VariableApi(Resource):
     @console_ns.doc("get_variable")
     @console_ns.doc(description="Get a specific workflow variable")
     @console_ns.doc(params={"app_id": "Application ID", "variable_id": "Variable ID"})
-    @console_ns.response(200, "Variable retrieved successfully", _WORKFLOW_DRAFT_VARIABLE_FIELDS)
+    @console_ns.response(200, "Variable retrieved successfully", workflow_draft_variable_model)
     @console_ns.response(404, "Variable not found")
     @_api_prerequisite
-    @marshal_with(_WORKFLOW_DRAFT_VARIABLE_FIELDS)
+    @marshal_with(workflow_draft_variable_model)
     def get(self, app_model: App, variable_id: str):
         draft_var_srv = WorkflowDraftVariableService(
             session=db.session(),
@@ -301,10 +332,10 @@ class VariableApi(Resource):
             },
         )
     )
-    @console_ns.response(200, "Variable updated successfully", _WORKFLOW_DRAFT_VARIABLE_FIELDS)
+    @console_ns.response(200, "Variable updated successfully", workflow_draft_variable_model)
     @console_ns.response(404, "Variable not found")
     @_api_prerequisite
-    @marshal_with(_WORKFLOW_DRAFT_VARIABLE_FIELDS)
+    @marshal_with(workflow_draft_variable_model)
     def patch(self, app_model: App, variable_id: str):
         # Request payload for file types:
         #
@@ -390,7 +421,7 @@ class VariableResetApi(Resource):
     @console_ns.doc("reset_variable")
     @console_ns.doc(description="Reset a workflow variable to its default value")
     @console_ns.doc(params={"app_id": "Application ID", "variable_id": "Variable ID"})
-    @console_ns.response(200, "Variable reset successfully", _WORKFLOW_DRAFT_VARIABLE_FIELDS)
+    @console_ns.response(200, "Variable reset successfully", workflow_draft_variable_model)
     @console_ns.response(204, "Variable reset (no content)")
     @console_ns.response(404, "Variable not found")
     @_api_prerequisite
@@ -416,7 +447,7 @@ class VariableResetApi(Resource):
         if resetted is None:
             return Response("", 204)
         else:
-            return marshal(resetted, _WORKFLOW_DRAFT_VARIABLE_FIELDS)
+            return marshal(resetted, workflow_draft_variable_model)
 
 
 def _get_variable_list(app_model: App, node_id) -> WorkflowDraftVariableList:
@@ -438,10 +469,10 @@ class ConversationVariableCollectionApi(Resource):
     @console_ns.doc("get_conversation_variables")
     @console_ns.doc(description="Get conversation variables for workflow")
     @console_ns.doc(params={"app_id": "Application ID"})
-    @console_ns.response(200, "Conversation variables retrieved successfully", _WORKFLOW_DRAFT_VARIABLE_LIST_FIELDS)
+    @console_ns.response(200, "Conversation variables retrieved successfully", workflow_draft_variable_list_model)
     @console_ns.response(404, "Draft workflow not found")
     @_api_prerequisite
-    @marshal_with(_WORKFLOW_DRAFT_VARIABLE_LIST_FIELDS)
+    @marshal_with(workflow_draft_variable_list_model)
     def get(self, app_model: App):
         # NOTE(QuantumGhost): Prefill conversation variables into the draft variables table
         # so their IDs can be returned to the caller.
@@ -460,9 +491,9 @@ class SystemVariableCollectionApi(Resource):
     @console_ns.doc("get_system_variables")
     @console_ns.doc(description="Get system variables for workflow")
     @console_ns.doc(params={"app_id": "Application ID"})
-    @console_ns.response(200, "System variables retrieved successfully", _WORKFLOW_DRAFT_VARIABLE_LIST_FIELDS)
+    @console_ns.response(200, "System variables retrieved successfully", workflow_draft_variable_list_model)
     @_api_prerequisite
-    @marshal_with(_WORKFLOW_DRAFT_VARIABLE_LIST_FIELDS)
+    @marshal_with(workflow_draft_variable_list_model)
     def get(self, app_model: App):
         return _get_variable_list(app_model, SYSTEM_VARIABLE_NODE_ID)
 

api/controllers/console/app/workflow_run.py

@@ -1,15 +1,20 @@
 from typing import cast
 
-from flask_restx import Resource, marshal_with, reqparse
+from flask_restx import Resource, fields, marshal_with, reqparse
 from flask_restx.inputs import int_range
 
 from controllers.console import console_ns
 from controllers.console.app.wraps import get_app_model
 from controllers.console.wraps import account_initialization_required, setup_required
+from fields.end_user_fields import simple_end_user_fields
+from fields.member_fields import simple_account_fields
 from fields.workflow_run_fields import (
+    advanced_chat_workflow_run_for_list_fields,
     advanced_chat_workflow_run_pagination_fields,
     workflow_run_count_fields,
     workflow_run_detail_fields,
+    workflow_run_for_list_fields,
+    workflow_run_node_execution_fields,
     workflow_run_node_execution_list_fields,
     workflow_run_pagination_fields,
 )
@@ -22,6 +27,71 @@ from services.workflow_run_service import WorkflowRunService
 # Workflow run status choices for filtering
 WORKFLOW_RUN_STATUS_CHOICES = ["running", "succeeded", "failed", "stopped", "partial-succeeded"]
 
+# Register models for flask_restx to avoid dict type issues in Swagger
+# Register in dependency order: base models first, then dependent models
+
+# Base models
+simple_account_model = console_ns.model("SimpleAccount", simple_account_fields)
+
+simple_end_user_model = console_ns.model("SimpleEndUser", simple_end_user_fields)
+
+# Models that depend on simple_account_fields
+workflow_run_for_list_fields_copy = workflow_run_for_list_fields.copy()
+workflow_run_for_list_fields_copy["created_by_account"] = fields.Nested(
+    simple_account_model, attribute="created_by_account", allow_null=True
+)
+workflow_run_for_list_model = console_ns.model("WorkflowRunForList", workflow_run_for_list_fields_copy)
+
+advanced_chat_workflow_run_for_list_fields_copy = advanced_chat_workflow_run_for_list_fields.copy()
+advanced_chat_workflow_run_for_list_fields_copy["created_by_account"] = fields.Nested(
+    simple_account_model, attribute="created_by_account", allow_null=True
+)
+advanced_chat_workflow_run_for_list_model = console_ns.model(
+    "AdvancedChatWorkflowRunForList", advanced_chat_workflow_run_for_list_fields_copy
+)
+
+workflow_run_detail_fields_copy = workflow_run_detail_fields.copy()
+workflow_run_detail_fields_copy["created_by_account"] = fields.Nested(
+    simple_account_model, attribute="created_by_account", allow_null=True
+)
+workflow_run_detail_fields_copy["created_by_end_user"] = fields.Nested(
+    simple_end_user_model, attribute="created_by_end_user", allow_null=True
+)
+workflow_run_detail_model = console_ns.model("WorkflowRunDetail", workflow_run_detail_fields_copy)
+
+workflow_run_node_execution_fields_copy = workflow_run_node_execution_fields.copy()
+workflow_run_node_execution_fields_copy["created_by_account"] = fields.Nested(
+    simple_account_model, attribute="created_by_account", allow_null=True
+)
+workflow_run_node_execution_fields_copy["created_by_end_user"] = fields.Nested(
+    simple_end_user_model, attribute="created_by_end_user", allow_null=True
+)
+workflow_run_node_execution_model = console_ns.model(
+    "WorkflowRunNodeExecution", workflow_run_node_execution_fields_copy
+)
+
+# Simple models without nested dependencies
+workflow_run_count_model = console_ns.model("WorkflowRunCount", workflow_run_count_fields)
+
+# Pagination models that depend on list models
+advanced_chat_workflow_run_pagination_fields_copy = advanced_chat_workflow_run_pagination_fields.copy()
+advanced_chat_workflow_run_pagination_fields_copy["data"] = fields.List(
+    fields.Nested(advanced_chat_workflow_run_for_list_model), attribute="data"
+)
+advanced_chat_workflow_run_pagination_model = console_ns.model(
+    "AdvancedChatWorkflowRunPagination", advanced_chat_workflow_run_pagination_fields_copy
+)
+
+workflow_run_pagination_fields_copy = workflow_run_pagination_fields.copy()
+workflow_run_pagination_fields_copy["data"] = fields.List(fields.Nested(workflow_run_for_list_model), attribute="data")
+workflow_run_pagination_model = console_ns.model("WorkflowRunPagination", workflow_run_pagination_fields_copy)
+
+workflow_run_node_execution_list_fields_copy = workflow_run_node_execution_list_fields.copy()
+workflow_run_node_execution_list_fields_copy["data"] = fields.List(fields.Nested(workflow_run_node_execution_model))
+workflow_run_node_execution_list_model = console_ns.model(
+    "WorkflowRunNodeExecutionList", workflow_run_node_execution_list_fields_copy
+)
+
 
 def _parse_workflow_run_list_args():
     """
@@ -100,12 +170,12 @@ class AdvancedChatAppWorkflowRunListApi(Resource):
     @console_ns.doc(
         params={"triggered_from": "Filter by trigger source (optional): debugging or app-run. Default: debugging"}
     )
-    @console_ns.response(200, "Workflow runs retrieved successfully", advanced_chat_workflow_run_pagination_fields)
+    @console_ns.response(200, "Workflow runs retrieved successfully", advanced_chat_workflow_run_pagination_model)
     @setup_required
     @login_required
     @account_initialization_required
     @get_app_model(mode=[AppMode.ADVANCED_CHAT])
-    @marshal_with(advanced_chat_workflow_run_pagination_fields)
+    @marshal_with(advanced_chat_workflow_run_pagination_model)
     def get(self, app_model: App):
         """
         Get advanced chat app workflow run list
@@ -146,12 +216,12 @@ class AdvancedChatAppWorkflowRunCountApi(Resource):
     @console_ns.doc(
         params={"triggered_from": "Filter by trigger source (optional): debugging or app-run. Default: debugging"}
     )
-    @console_ns.response(200, "Workflow runs count retrieved successfully", workflow_run_count_fields)
+    @console_ns.response(200, "Workflow runs count retrieved successfully", workflow_run_count_model)
     @setup_required
     @login_required
     @account_initialization_required
     @get_app_model(mode=[AppMode.ADVANCED_CHAT])
-    @marshal_with(workflow_run_count_fields)
+    @marshal_with(workflow_run_count_model)
     def get(self, app_model: App):
         """
         Get advanced chat workflow runs count statistics
@@ -188,12 +258,12 @@ class WorkflowRunListApi(Resource):
     @console_ns.doc(
         params={"triggered_from": "Filter by trigger source (optional): debugging or app-run. Default: debugging"}
     )
-    @console_ns.response(200, "Workflow runs retrieved successfully", workflow_run_pagination_fields)
+    @console_ns.response(200, "Workflow runs retrieved successfully", workflow_run_pagination_model)
     @setup_required
     @login_required
     @account_initialization_required
     @get_app_model(mode=[AppMode.ADVANCED_CHAT, AppMode.WORKFLOW])
-    @marshal_with(workflow_run_pagination_fields)
+    @marshal_with(workflow_run_pagination_model)
     def get(self, app_model: App):
         """
         Get workflow run list
@@ -234,12 +304,12 @@ class WorkflowRunCountApi(Resource):
     @console_ns.doc(
         params={"triggered_from": "Filter by trigger source (optional): debugging or app-run. Default: debugging"}
     )
-    @console_ns.response(200, "Workflow runs count retrieved successfully", workflow_run_count_fields)
+    @console_ns.response(200, "Workflow runs count retrieved successfully", workflow_run_count_model)
     @setup_required
     @login_required
     @account_initialization_required
     @get_app_model(mode=[AppMode.ADVANCED_CHAT, AppMode.WORKFLOW])
-    @marshal_with(workflow_run_count_fields)
+    @marshal_with(workflow_run_count_model)
     def get(self, app_model: App):
         """
         Get workflow runs count statistics
@@ -269,13 +339,13 @@ class WorkflowRunDetailApi(Resource):
     @console_ns.doc("get_workflow_run_detail")
     @console_ns.doc(description="Get workflow run detail")
     @console_ns.doc(params={"app_id": "Application ID", "run_id": "Workflow run ID"})
-    @console_ns.response(200, "Workflow run detail retrieved successfully", workflow_run_detail_fields)
+    @console_ns.response(200, "Workflow run detail retrieved successfully", workflow_run_detail_model)
     @console_ns.response(404, "Workflow run not found")
     @setup_required
     @login_required
     @account_initialization_required
     @get_app_model(mode=[AppMode.ADVANCED_CHAT, AppMode.WORKFLOW])
-    @marshal_with(workflow_run_detail_fields)
+    @marshal_with(workflow_run_detail_model)
     def get(self, app_model: App, run_id):
         """
         Get workflow run detail
@@ -293,13 +363,13 @@ class WorkflowRunNodeExecutionListApi(Resource):
     @console_ns.doc("get_workflow_run_node_executions")
     @console_ns.doc(description="Get workflow run node execution list")
     @console_ns.doc(params={"app_id": "Application ID", "run_id": "Workflow run ID"})
-    @console_ns.response(200, "Node executions retrieved successfully", workflow_run_node_execution_list_fields)
+    @console_ns.response(200, "Node executions retrieved successfully", workflow_run_node_execution_list_model)
     @console_ns.response(404, "Workflow run not found")
     @setup_required
     @login_required
     @account_initialization_required
     @get_app_model(mode=[AppMode.ADVANCED_CHAT, AppMode.WORKFLOW])
-    @marshal_with(workflow_run_node_execution_list_fields)
+    @marshal_with(workflow_run_node_execution_list_model)
     def get(self, app_model: App, run_id):
         """
         Get workflow run node execution list

api/controllers/console/app/workflow_trigger.py

@@ -1,14 +1,13 @@
 import logging
 
-from flask_restx import Resource, marshal_with, reqparse
+from flask import request
+from flask_restx import Resource, marshal_with
+from pydantic import BaseModel
 from sqlalchemy import select
 from sqlalchemy.orm import Session
 from werkzeug.exceptions import NotFound
 
 from configs import dify_config
-from controllers.console import console_ns
-from controllers.console.app.wraps import get_app_model
-from controllers.console.wraps import account_initialization_required, edit_permission_required, setup_required
 from extensions.ext_database import db
 from fields.workflow_trigger_fields import trigger_fields, triggers_list_fields, webhook_trigger_fields
 from libs.login import current_user, login_required
@@ -16,12 +15,35 @@ from models.enums import AppTriggerStatus
 from models.model import Account, App, AppMode
 from models.trigger import AppTrigger, WorkflowWebhookTrigger
 
+from .. import console_ns
+from ..app.wraps import get_app_model
+from ..wraps import account_initialization_required, edit_permission_required, setup_required
+
 logger = logging.getLogger(__name__)
+DEFAULT_REF_TEMPLATE_SWAGGER_2_0 = "#/definitions/{model}"
 
 
+class Parser(BaseModel):
+    node_id: str
+
+
+class ParserEnable(BaseModel):
+    trigger_id: str
+    enable_trigger: bool
+
+
+console_ns.schema_model(Parser.__name__, Parser.model_json_schema(ref_template=DEFAULT_REF_TEMPLATE_SWAGGER_2_0))
+
+console_ns.schema_model(
+    ParserEnable.__name__, ParserEnable.model_json_schema(ref_template=DEFAULT_REF_TEMPLATE_SWAGGER_2_0)
+)
+
+
+@console_ns.route("/apps/<uuid:app_id>/workflows/triggers/webhook")
 class WebhookTriggerApi(Resource):
     """Webhook Trigger API"""
 
+    @console_ns.expect(console_ns.models[Parser.__name__])
     @setup_required
     @login_required
     @account_initialization_required
@@ -29,10 +51,9 @@ class WebhookTriggerApi(Resource):
     @marshal_with(webhook_trigger_fields)
     def get(self, app_model: App):
         """Get webhook trigger for a node"""
-        parser = reqparse.RequestParser().add_argument("node_id", type=str, required=True, help="Node ID is required")
-        args = parser.parse_args()
+        args = Parser.model_validate(request.args.to_dict(flat=True))  # type: ignore
 
-        node_id = str(args["node_id"])
+        node_id = args.node_id
 
         with Session(db.engine) as session:
             # Get webhook trigger for this app and node
@@ -51,6 +72,7 @@ class WebhookTriggerApi(Resource):
             return webhook_trigger
 
 
+@console_ns.route("/apps/<uuid:app_id>/triggers")
 class AppTriggersApi(Resource):
     """App Triggers list API"""
 
@@ -90,7 +112,9 @@ class AppTriggersApi(Resource):
         return {"data": triggers}
 
 
+@console_ns.route("/apps/<uuid:app_id>/trigger-enable")
 class AppTriggerEnableApi(Resource):
+    @console_ns.expect(console_ns.models[ParserEnable.__name__], validate=True)
     @setup_required
     @login_required
     @account_initialization_required
@@ -99,17 +123,11 @@ class AppTriggerEnableApi(Resource):
     @marshal_with(trigger_fields)
     def post(self, app_model: App):
         """Update app trigger (enable/disable)"""
-        parser = (
-            reqparse.RequestParser()
-            .add_argument("trigger_id", type=str, required=True, nullable=False, location="json")
-            .add_argument("enable_trigger", type=bool, required=True, nullable=False, location="json")
-        )
-        args = parser.parse_args()
+        args = ParserEnable.model_validate(console_ns.payload)
 
         assert current_user.current_tenant_id is not None
 
-        trigger_id = args["trigger_id"]
-
+        trigger_id = args.trigger_id
         with Session(db.engine) as session:
             # Find the trigger using select
             trigger = session.execute(
@@ -124,7 +142,7 @@ class AppTriggerEnableApi(Resource):
                 raise NotFound("Trigger not found")
 
             # Update status based on enable_trigger boolean
-            trigger.status = AppTriggerStatus.ENABLED if args["enable_trigger"] else AppTriggerStatus.DISABLED
+            trigger.status = AppTriggerStatus.ENABLED if args.enable_trigger else AppTriggerStatus.DISABLED
 
             session.commit()
             session.refresh(trigger)
@@ -137,8 +155,3 @@ class AppTriggerEnableApi(Resource):
             trigger.icon = ""  # type: ignore
 
         return trigger
-
-
-console_ns.add_resource(WebhookTriggerApi, "/apps/<uuid:app_id>/workflows/triggers/webhook")
-console_ns.add_resource(AppTriggersApi, "/apps/<uuid:app_id>/triggers")
-console_ns.add_resource(AppTriggerEnableApi, "/apps/<uuid:app_id>/trigger-enable")

api/controllers/console/datasets/datasets.py

@@ -8,7 +8,10 @@ from werkzeug.exceptions import Forbidden, NotFound
 import services
 from configs import dify_config
 from controllers.console import console_ns
-from controllers.console.apikey import api_key_fields, api_key_list
+from controllers.console.apikey import (
+    api_key_item_model,
+    api_key_list_model,
+)
 from controllers.console.app.error import ProviderNotInitializeError
 from controllers.console.datasets.error import DatasetInUseError, DatasetNameDuplicateError, IndexingEstimateError
 from controllers.console.wraps import (
@@ -27,8 +30,22 @@ from core.rag.extractor.entity.datasource_type import DatasourceType
 from core.rag.extractor.entity.extract_setting import ExtractSetting, NotionInfo, WebsiteInfo
 from core.rag.retrieval.retrieval_methods import RetrievalMethod
 from extensions.ext_database import db
-from fields.app_fields import related_app_list
-from fields.dataset_fields import dataset_detail_fields, dataset_query_detail_fields
+from fields.app_fields import app_detail_kernel_fields, related_app_list
+from fields.dataset_fields import (
+    dataset_detail_fields,
+    dataset_fields,
+    dataset_query_detail_fields,
+    dataset_retrieval_model_fields,
+    doc_metadata_fields,
+    external_knowledge_info_fields,
+    external_retrieval_model_fields,
+    icon_info_fields,
+    keyword_setting_fields,
+    reranking_model_fields,
+    tag_fields,
+    vector_setting_fields,
+    weighted_score_fields,
+)
 from fields.document_fields import document_status_fields
 from libs.login import current_account_with_tenant, login_required
 from libs.validators import validate_description_length
@@ -38,6 +55,58 @@ from models.provider_ids import ModelProviderID
 from services.dataset_service import DatasetPermissionService, DatasetService, DocumentService
 
 
+def _get_or_create_model(model_name: str, field_def):
+    existing = console_ns.models.get(model_name)
+    if existing is None:
+        existing = console_ns.model(model_name, field_def)
+    return existing
+
+
+# Register models for flask_restx to avoid dict type issues in Swagger
+dataset_base_model = _get_or_create_model("DatasetBase", dataset_fields)
+
+tag_model = _get_or_create_model("Tag", tag_fields)
+
+keyword_setting_model = _get_or_create_model("DatasetKeywordSetting", keyword_setting_fields)
+vector_setting_model = _get_or_create_model("DatasetVectorSetting", vector_setting_fields)
+
+weighted_score_fields_copy = weighted_score_fields.copy()
+weighted_score_fields_copy["keyword_setting"] = fields.Nested(keyword_setting_model)
+weighted_score_fields_copy["vector_setting"] = fields.Nested(vector_setting_model)
+weighted_score_model = _get_or_create_model("DatasetWeightedScore", weighted_score_fields_copy)
+
+reranking_model = _get_or_create_model("DatasetRerankingModel", reranking_model_fields)
+
+dataset_retrieval_model_fields_copy = dataset_retrieval_model_fields.copy()
+dataset_retrieval_model_fields_copy["reranking_model"] = fields.Nested(reranking_model)
+dataset_retrieval_model_fields_copy["weights"] = fields.Nested(weighted_score_model, allow_null=True)
+dataset_retrieval_model = _get_or_create_model("DatasetRetrievalModel", dataset_retrieval_model_fields_copy)
+
+external_knowledge_info_model = _get_or_create_model("ExternalKnowledgeInfo", external_knowledge_info_fields)
+
+external_retrieval_model = _get_or_create_model("ExternalRetrievalModel", external_retrieval_model_fields)
+
+doc_metadata_model = _get_or_create_model("DatasetDocMetadata", doc_metadata_fields)
+
+icon_info_model = _get_or_create_model("DatasetIconInfo", icon_info_fields)
+
+dataset_detail_fields_copy = dataset_detail_fields.copy()
+dataset_detail_fields_copy["retrieval_model_dict"] = fields.Nested(dataset_retrieval_model)
+dataset_detail_fields_copy["tags"] = fields.List(fields.Nested(tag_model))
+dataset_detail_fields_copy["external_knowledge_info"] = fields.Nested(external_knowledge_info_model)
+dataset_detail_fields_copy["external_retrieval_model"] = fields.Nested(external_retrieval_model, allow_null=True)
+dataset_detail_fields_copy["doc_metadata"] = fields.List(fields.Nested(doc_metadata_model))
+dataset_detail_fields_copy["icon_info"] = fields.Nested(icon_info_model)
+dataset_detail_model = _get_or_create_model("DatasetDetail", dataset_detail_fields_copy)
+
+dataset_query_detail_model = _get_or_create_model("DatasetQueryDetail", dataset_query_detail_fields)
+
+app_detail_kernel_model = _get_or_create_model("AppDetailKernel", app_detail_kernel_fields)
+related_app_list_copy = related_app_list.copy()
+related_app_list_copy["data"] = fields.List(fields.Nested(app_detail_kernel_model))
+related_app_list_model = _get_or_create_model("RelatedAppList", related_app_list_copy)
+
+
 def _validate_name(name: str) -> str:
     if not name or len(name) < 1 or len(name) > 40:
         raise ValueError("Name must be between 1 to 40 characters.")
@@ -282,7 +351,7 @@ class DatasetApi(Resource):
     @console_ns.doc("get_dataset")
     @console_ns.doc(description="Get dataset details")
     @console_ns.doc(params={"dataset_id": "Dataset ID"})
-    @console_ns.response(200, "Dataset retrieved successfully", dataset_detail_fields)
+    @console_ns.response(200, "Dataset retrieved successfully", dataset_detail_model)
     @console_ns.response(404, "Dataset not found")
     @console_ns.response(403, "Permission denied")
     @setup_required
@@ -342,7 +411,7 @@ class DatasetApi(Resource):
             },
         )
     )
-    @console_ns.response(200, "Dataset updated successfully", dataset_detail_fields)
+    @console_ns.response(200, "Dataset updated successfully", dataset_detail_model)
     @console_ns.response(404, "Dataset not found")
     @console_ns.response(403, "Permission denied")
     @setup_required
@@ -507,7 +576,7 @@ class DatasetQueryApi(Resource):
     @console_ns.doc("get_dataset_queries")
     @console_ns.doc(description="Get dataset query history")
     @console_ns.doc(params={"dataset_id": "Dataset ID"})
-    @console_ns.response(200, "Query history retrieved successfully", dataset_query_detail_fields)
+    @console_ns.response(200, "Query history retrieved successfully", dataset_query_detail_model)
     @setup_required
     @login_required
     @account_initialization_required
@@ -529,7 +598,7 @@ class DatasetQueryApi(Resource):
         dataset_queries, total = DatasetService.get_dataset_queries(dataset_id=dataset.id, page=page, per_page=limit)
 
         response = {
-            "data": marshal(dataset_queries, dataset_query_detail_fields),
+            "data": marshal(dataset_queries, dataset_query_detail_model),
             "has_more": len(dataset_queries) == limit,
             "limit": limit,
             "total": total,
@@ -653,11 +722,11 @@ class DatasetRelatedAppListApi(Resource):
     @console_ns.doc("get_dataset_related_apps")
     @console_ns.doc(description="Get applications related to dataset")
     @console_ns.doc(params={"dataset_id": "Dataset ID"})
-    @console_ns.response(200, "Related apps retrieved successfully", related_app_list)
+    @console_ns.response(200, "Related apps retrieved successfully", related_app_list_model)
     @setup_required
     @login_required
     @account_initialization_required
-    @marshal_with(related_app_list)
+    @marshal_with(related_app_list_model)
     def get(self, dataset_id):
         current_user, _ = current_account_with_tenant()
         dataset_id_str = str(dataset_id)
@@ -740,11 +809,11 @@ class DatasetApiKeyApi(Resource):
 
     @console_ns.doc("get_dataset_api_keys")
     @console_ns.doc(description="Get dataset API keys")
-    @console_ns.response(200, "API keys retrieved successfully", api_key_list)
+    @console_ns.response(200, "API keys retrieved successfully", api_key_list_model)
     @setup_required
     @login_required
     @account_initialization_required
-    @marshal_with(api_key_list)
+    @marshal_with(api_key_list_model)
     def get(self):
         _, current_tenant_id = current_account_with_tenant()
         keys = db.session.scalars(
@@ -756,7 +825,7 @@ class DatasetApiKeyApi(Resource):
     @login_required
     @is_admin_or_owner_required
     @account_initialization_required
-    @marshal_with(api_key_fields)
+    @marshal_with(api_key_item_model)
     def post(self):
         _, current_tenant_id = current_account_with_tenant()
 

api/controllers/console/datasets/datasets_document.py

@@ -45,9 +45,11 @@ from core.plugin.impl.exc import PluginDaemonClientSideError
 from core.rag.extractor.entity.datasource_type import DatasourceType
 from core.rag.extractor.entity.extract_setting import ExtractSetting, NotionInfo, WebsiteInfo
 from extensions.ext_database import db
+from fields.dataset_fields import dataset_fields
 from fields.document_fields import (
     dataset_and_document_fields,
     document_fields,
+    document_metadata_fields,
     document_status_fields,
     document_with_segments_fields,
 )
@@ -61,6 +63,36 @@ from services.entities.knowledge_entities.knowledge_entities import KnowledgeCon
 logger = logging.getLogger(__name__)
 
 
+def _get_or_create_model(model_name: str, field_def):
+    existing = console_ns.models.get(model_name)
+    if existing is None:
+        existing = console_ns.model(model_name, field_def)
+    return existing
+
+
+# Register models for flask_restx to avoid dict type issues in Swagger
+dataset_model = _get_or_create_model("Dataset", dataset_fields)
+
+document_metadata_model = _get_or_create_model("DocumentMetadata", document_metadata_fields)
+
+document_fields_copy = document_fields.copy()
+document_fields_copy["doc_metadata"] = fields.List(
+    fields.Nested(document_metadata_model), attribute="doc_metadata_details"
+)
+document_model = _get_or_create_model("Document", document_fields_copy)
+
+document_with_segments_fields_copy = document_with_segments_fields.copy()
+document_with_segments_fields_copy["doc_metadata"] = fields.List(
+    fields.Nested(document_metadata_model), attribute="doc_metadata_details"
+)
+document_with_segments_model = _get_or_create_model("DocumentWithSegments", document_with_segments_fields_copy)
+
+dataset_and_document_fields_copy = dataset_and_document_fields.copy()
+dataset_and_document_fields_copy["dataset"] = fields.Nested(dataset_model)
+dataset_and_document_fields_copy["documents"] = fields.List(fields.Nested(document_model))
+dataset_and_document_model = _get_or_create_model("DatasetAndDocument", dataset_and_document_fields_copy)
+
+
 class DocumentResource(Resource):
     def get_document(self, dataset_id: str, document_id: str) -> Document:
         current_user, current_tenant_id = current_account_with_tenant()
@@ -169,9 +201,8 @@ class DatasetDocumentListApi(Resource):
     @setup_required
     @login_required
     @account_initialization_required
-    def get(self, dataset_id):
+    def get(self, dataset_id: str):
         current_user, current_tenant_id = current_account_with_tenant()
-        dataset_id = str(dataset_id)
         page = request.args.get("page", default=1, type=int)
         limit = request.args.get("limit", default=20, type=int)
         search = request.args.get("keyword", default=None, type=str)
@@ -276,7 +307,7 @@ class DatasetDocumentListApi(Resource):
     @setup_required
     @login_required
     @account_initialization_required
-    @marshal_with(dataset_and_document_fields)
+    @marshal_with(dataset_and_document_model)
     @cloud_edition_billing_resource_check("vector_space")
     @cloud_edition_billing_rate_limit_check("knowledge")
     def post(self, dataset_id):
@@ -370,12 +401,12 @@ class DatasetInitApi(Resource):
             },
         )
     )
-    @console_ns.response(201, "Dataset initialized successfully", dataset_and_document_fields)
+    @console_ns.response(201, "Dataset initialized successfully", dataset_and_document_model)
     @console_ns.response(400, "Invalid request parameters")
     @setup_required
     @login_required
     @account_initialization_required
-    @marshal_with(dataset_and_document_fields)
+    @marshal_with(dataset_and_document_model)
     @cloud_edition_billing_resource_check("vector_space")
     @cloud_edition_billing_rate_limit_check("knowledge")
     def post(self):

api/controllers/console/datasets/external.py

@@ -6,7 +6,19 @@ import services
 from controllers.console import console_ns
 from controllers.console.datasets.error import DatasetNameDuplicateError
 from controllers.console.wraps import account_initialization_required, edit_permission_required, setup_required
-from fields.dataset_fields import dataset_detail_fields
+from fields.dataset_fields import (
+    dataset_detail_fields,
+    dataset_retrieval_model_fields,
+    doc_metadata_fields,
+    external_knowledge_info_fields,
+    external_retrieval_model_fields,
+    icon_info_fields,
+    keyword_setting_fields,
+    reranking_model_fields,
+    tag_fields,
+    vector_setting_fields,
+    weighted_score_fields,
+)
 from libs.login import current_account_with_tenant, login_required
 from services.dataset_service import DatasetService
 from services.external_knowledge_service import ExternalDatasetService
@@ -14,6 +26,51 @@ from services.hit_testing_service import HitTestingService
 from services.knowledge_service import ExternalDatasetTestService
 
 
+def _get_or_create_model(model_name: str, field_def):
+    existing = console_ns.models.get(model_name)
+    if existing is None:
+        existing = console_ns.model(model_name, field_def)
+    return existing
+
+
+def _build_dataset_detail_model():
+    keyword_setting_model = _get_or_create_model("DatasetKeywordSetting", keyword_setting_fields)
+    vector_setting_model = _get_or_create_model("DatasetVectorSetting", vector_setting_fields)
+
+    weighted_score_fields_copy = weighted_score_fields.copy()
+    weighted_score_fields_copy["keyword_setting"] = fields.Nested(keyword_setting_model)
+    weighted_score_fields_copy["vector_setting"] = fields.Nested(vector_setting_model)
+    weighted_score_model = _get_or_create_model("DatasetWeightedScore", weighted_score_fields_copy)
+
+    reranking_model = _get_or_create_model("DatasetRerankingModel", reranking_model_fields)
+
+    dataset_retrieval_model_fields_copy = dataset_retrieval_model_fields.copy()
+    dataset_retrieval_model_fields_copy["reranking_model"] = fields.Nested(reranking_model)
+    dataset_retrieval_model_fields_copy["weights"] = fields.Nested(weighted_score_model, allow_null=True)
+    dataset_retrieval_model = _get_or_create_model("DatasetRetrievalModel", dataset_retrieval_model_fields_copy)
+
+    tag_model = _get_or_create_model("Tag", tag_fields)
+    doc_metadata_model = _get_or_create_model("DatasetDocMetadata", doc_metadata_fields)
+    external_knowledge_info_model = _get_or_create_model("ExternalKnowledgeInfo", external_knowledge_info_fields)
+    external_retrieval_model = _get_or_create_model("ExternalRetrievalModel", external_retrieval_model_fields)
+    icon_info_model = _get_or_create_model("DatasetIconInfo", icon_info_fields)
+
+    dataset_detail_fields_copy = dataset_detail_fields.copy()
+    dataset_detail_fields_copy["retrieval_model_dict"] = fields.Nested(dataset_retrieval_model)
+    dataset_detail_fields_copy["tags"] = fields.List(fields.Nested(tag_model))
+    dataset_detail_fields_copy["external_knowledge_info"] = fields.Nested(external_knowledge_info_model)
+    dataset_detail_fields_copy["external_retrieval_model"] = fields.Nested(external_retrieval_model, allow_null=True)
+    dataset_detail_fields_copy["doc_metadata"] = fields.List(fields.Nested(doc_metadata_model))
+    dataset_detail_fields_copy["icon_info"] = fields.Nested(icon_info_model)
+    return _get_or_create_model("DatasetDetail", dataset_detail_fields_copy)
+
+
+try:
+    dataset_detail_model = console_ns.models["DatasetDetail"]
+except KeyError:
+    dataset_detail_model = _build_dataset_detail_model()
+
+
 def _validate_name(name: str) -> str:
     if not name or len(name) < 1 or len(name) > 100:
         raise ValueError("Name must be between 1 to 100 characters.")
@@ -194,7 +251,7 @@ class ExternalDatasetCreateApi(Resource):
             },
         )
     )
-    @console_ns.response(201, "External dataset created successfully", dataset_detail_fields)
+    @console_ns.response(201, "External dataset created successfully", dataset_detail_model)
     @console_ns.response(400, "Invalid parameters")
     @console_ns.response(403, "Permission denied")
     @setup_required

api/controllers/console/explore/completion.py

@@ -15,7 +15,6 @@ from controllers.console.app.error import (
 from controllers.console.explore.error import NotChatAppError, NotCompletionAppError
 from controllers.console.explore.wraps import InstalledAppResource
 from controllers.web.error import InvokeRateLimitError as InvokeRateLimitHttpError
-from core.app.apps.base_app_queue_manager import AppQueueManager
 from core.app.entities.app_invoke_entities import InvokeFrom
 from core.errors.error import (
     ModelCurrentlyNotSupportError,
@@ -31,6 +30,7 @@ from libs.login import current_user
 from models import Account
 from models.model import AppMode
 from services.app_generate_service import AppGenerateService
+from services.app_task_service import AppTaskService
 from services.errors.llm import InvokeRateLimitError
 
 from .. import console_ns
@@ -46,7 +46,7 @@ logger = logging.getLogger(__name__)
 class CompletionApi(InstalledAppResource):
     def post(self, installed_app):
         app_model = installed_app.app
-        if app_model.mode != "completion":
+        if app_model.mode != AppMode.COMPLETION:
             raise NotCompletionAppError()
 
         parser = (
@@ -102,12 +102,18 @@ class CompletionApi(InstalledAppResource):
 class CompletionStopApi(InstalledAppResource):
     def post(self, installed_app, task_id):
         app_model = installed_app.app
-        if app_model.mode != "completion":
+        if app_model.mode != AppMode.COMPLETION:
             raise NotCompletionAppError()
 
         if not isinstance(current_user, Account):
             raise ValueError("current_user must be an Account instance")
-        AppQueueManager.set_stop_flag(task_id, InvokeFrom.EXPLORE, current_user.id)
+
+        AppTaskService.stop_task(
+            task_id=task_id,
+            invoke_from=InvokeFrom.EXPLORE,
+            user_id=current_user.id,
+            app_mode=AppMode.value_of(app_model.mode),
+        )
 
         return {"result": "success"}, 200
 
@@ -184,6 +190,12 @@ class ChatStopApi(InstalledAppResource):
 
         if not isinstance(current_user, Account):
             raise ValueError("current_user must be an Account instance")
-        AppQueueManager.set_stop_flag(task_id, InvokeFrom.EXPLORE, current_user.id)
+
+        AppTaskService.stop_task(
+            task_id=task_id,
+            invoke_from=InvokeFrom.EXPLORE,
+            user_id=current_user.id,
+            app_mode=app_mode,
+        )
 
         return {"result": "success"}, 200

api/controllers/console/extension.py

@@ -9,6 +9,10 @@ from models.api_based_extension import APIBasedExtension
 from services.api_based_extension_service import APIBasedExtensionService
 from services.code_based_extension_service import CodeBasedExtensionService
 
+api_based_extension_model = console_ns.model("ApiBasedExtensionModel", api_based_extension_fields)
+
+api_based_extension_list_model = fields.List(fields.Nested(api_based_extension_model))
+
 
 @console_ns.route("/code-based-extension")
 class CodeBasedExtensionAPI(Resource):
@@ -41,11 +45,11 @@ class CodeBasedExtensionAPI(Resource):
 class APIBasedExtensionAPI(Resource):
     @console_ns.doc("get_api_based_extensions")
     @console_ns.doc(description="Get all API-based extensions for current tenant")
-    @console_ns.response(200, "Success", fields.List(fields.Nested(api_based_extension_fields)))
+    @console_ns.response(200, "Success", api_based_extension_list_model)
     @setup_required
     @login_required
     @account_initialization_required
-    @marshal_with(api_based_extension_fields)
+    @marshal_with(api_based_extension_model)
     def get(self):
         _, tenant_id = current_account_with_tenant()
         return APIBasedExtensionService.get_all_by_tenant_id(tenant_id)
@@ -62,11 +66,11 @@ class APIBasedExtensionAPI(Resource):
             },
         )
     )
-    @console_ns.response(201, "Extension created successfully", api_based_extension_fields)
+    @console_ns.response(201, "Extension created successfully", api_based_extension_model)
     @setup_required
     @login_required
     @account_initialization_required
-    @marshal_with(api_based_extension_fields)
+    @marshal_with(api_based_extension_model)
     def post(self):
         args = console_ns.payload
         _, current_tenant_id = current_account_with_tenant()
@@ -86,11 +90,11 @@ class APIBasedExtensionDetailAPI(Resource):
     @console_ns.doc("get_api_based_extension")
     @console_ns.doc(description="Get API-based extension by ID")
     @console_ns.doc(params={"id": "Extension ID"})
-    @console_ns.response(200, "Success", api_based_extension_fields)
+    @console_ns.response(200, "Success", api_based_extension_model)
     @setup_required
     @login_required
     @account_initialization_required
-    @marshal_with(api_based_extension_fields)
+    @marshal_with(api_based_extension_model)
     def get(self, id):
         api_based_extension_id = str(id)
         _, tenant_id = current_account_with_tenant()
@@ -110,11 +114,11 @@ class APIBasedExtensionDetailAPI(Resource):
             },
         )
     )
-    @console_ns.response(200, "Extension updated successfully", api_based_extension_fields)
+    @console_ns.response(200, "Extension updated successfully", api_based_extension_model)
     @setup_required
     @login_required
     @account_initialization_required
-    @marshal_with(api_based_extension_fields)
+    @marshal_with(api_based_extension_model)
     def post(self, id):
         api_based_extension_id = str(id)
         _, current_tenant_id = current_account_with_tenant()

api/controllers/console/version.py

@@ -58,7 +58,7 @@ class VersionApi(Resource):
             response = httpx.get(
                 check_update_url,
                 params={"current_version": args["current_version"]},
-                timeout=httpx.Timeout(connect=3, read=10),
+                timeout=httpx.Timeout(10.0, connect=3.0),
             )
         except Exception as error:
             logger.warning("Check update version error: %s.", str(error))

api/controllers/console/workspace/account.py

@@ -1,8 +1,10 @@
 from datetime import datetime
+from typing import Literal
 
 import pytz
 from flask import request
-from flask_restx import Resource, fields, marshal_with, reqparse
+from flask_restx import Resource, fields, marshal_with
+from pydantic import BaseModel, Field, field_validator, model_validator
 from sqlalchemy import select
 from sqlalchemy.orm import Session
 
@@ -42,20 +44,198 @@ from services.account_service import AccountService
 from services.billing_service import BillingService
 from services.errors.account import CurrentPasswordIncorrectError as ServiceCurrentPasswordIncorrectError
 
+DEFAULT_REF_TEMPLATE_SWAGGER_2_0 = "#/definitions/{model}"
 
-def _init_parser():
-    parser = reqparse.RequestParser()
-    if dify_config.EDITION == "CLOUD":
-        parser.add_argument("invitation_code", type=str, location="json")
-    parser.add_argument("interface_language", type=supported_language, required=True, location="json").add_argument(
-        "timezone", type=timezone, required=True, location="json"
-    )
-    return parser
+
+class AccountInitPayload(BaseModel):
+    interface_language: str
+    timezone: str
+    invitation_code: str | None = None
+
+    @field_validator("interface_language")
+    @classmethod
+    def validate_language(cls, value: str) -> str:
+        return supported_language(value)
+
+    @field_validator("timezone")
+    @classmethod
+    def validate_timezone(cls, value: str) -> str:
+        return timezone(value)
+
+
+class AccountNamePayload(BaseModel):
+    name: str = Field(min_length=3, max_length=30)
+
+
+class AccountAvatarPayload(BaseModel):
+    avatar: str
+
+
+class AccountInterfaceLanguagePayload(BaseModel):
+    interface_language: str
+
+    @field_validator("interface_language")
+    @classmethod
+    def validate_language(cls, value: str) -> str:
+        return supported_language(value)
+
+
+class AccountInterfaceThemePayload(BaseModel):
+    interface_theme: Literal["light", "dark"]
+
+
+class AccountTimezonePayload(BaseModel):
+    timezone: str
+
+    @field_validator("timezone")
+    @classmethod
+    def validate_timezone(cls, value: str) -> str:
+        return timezone(value)
+
+
+class AccountPasswordPayload(BaseModel):
+    password: str | None = None
+    new_password: str
+    repeat_new_password: str
+
+    @model_validator(mode="after")
+    def check_passwords_match(self) -> "AccountPasswordPayload":
+        if self.new_password != self.repeat_new_password:
+            raise RepeatPasswordNotMatchError()
+        return self
+
+
+class AccountDeletePayload(BaseModel):
+    token: str
+    code: str
+
+
+class AccountDeletionFeedbackPayload(BaseModel):
+    email: str
+    feedback: str
+
+    @field_validator("email")
+    @classmethod
+    def validate_email(cls, value: str) -> str:
+        return email(value)
+
+
+class EducationActivatePayload(BaseModel):
+    token: str
+    institution: str
+    role: str
+
+
+class EducationAutocompleteQuery(BaseModel):
+    keywords: str
+    page: int = 0
+    limit: int = 20
+
+
+class ChangeEmailSendPayload(BaseModel):
+    email: str
+    language: str | None = None
+    phase: str | None = None
+    token: str | None = None
+
+    @field_validator("email")
+    @classmethod
+    def validate_email(cls, value: str) -> str:
+        return email(value)
+
+
+class ChangeEmailValidityPayload(BaseModel):
+    email: str
+    code: str
+    token: str
+
+    @field_validator("email")
+    @classmethod
+    def validate_email(cls, value: str) -> str:
+        return email(value)
+
+
+class ChangeEmailResetPayload(BaseModel):
+    new_email: str
+    token: str
+
+    @field_validator("new_email")
+    @classmethod
+    def validate_email(cls, value: str) -> str:
+        return email(value)
+
+
+class CheckEmailUniquePayload(BaseModel):
+    email: str
+
+    @field_validator("email")
+    @classmethod
+    def validate_email(cls, value: str) -> str:
+        return email(value)
+
+
+console_ns.schema_model(
+    AccountInitPayload.__name__, AccountInitPayload.model_json_schema(ref_template=DEFAULT_REF_TEMPLATE_SWAGGER_2_0)
+)
+console_ns.schema_model(
+    AccountNamePayload.__name__, AccountNamePayload.model_json_schema(ref_template=DEFAULT_REF_TEMPLATE_SWAGGER_2_0)
+)
+console_ns.schema_model(
+    AccountAvatarPayload.__name__, AccountAvatarPayload.model_json_schema(ref_template=DEFAULT_REF_TEMPLATE_SWAGGER_2_0)
+)
+console_ns.schema_model(
+    AccountInterfaceLanguagePayload.__name__,
+    AccountInterfaceLanguagePayload.model_json_schema(ref_template=DEFAULT_REF_TEMPLATE_SWAGGER_2_0),
+)
+console_ns.schema_model(
+    AccountInterfaceThemePayload.__name__,
+    AccountInterfaceThemePayload.model_json_schema(ref_template=DEFAULT_REF_TEMPLATE_SWAGGER_2_0),
+)
+console_ns.schema_model(
+    AccountTimezonePayload.__name__,
+    AccountTimezonePayload.model_json_schema(ref_template=DEFAULT_REF_TEMPLATE_SWAGGER_2_0),
+)
+console_ns.schema_model(
+    AccountPasswordPayload.__name__,
+    AccountPasswordPayload.model_json_schema(ref_template=DEFAULT_REF_TEMPLATE_SWAGGER_2_0),
+)
+console_ns.schema_model(
+    AccountDeletePayload.__name__,
+    AccountDeletePayload.model_json_schema(ref_template=DEFAULT_REF_TEMPLATE_SWAGGER_2_0),
+)
+console_ns.schema_model(
+    AccountDeletionFeedbackPayload.__name__,
+    AccountDeletionFeedbackPayload.model_json_schema(ref_template=DEFAULT_REF_TEMPLATE_SWAGGER_2_0),
+)
+console_ns.schema_model(
+    EducationActivatePayload.__name__,
+    EducationActivatePayload.model_json_schema(ref_template=DEFAULT_REF_TEMPLATE_SWAGGER_2_0),
+)
+console_ns.schema_model(
+    EducationAutocompleteQuery.__name__,
+    EducationAutocompleteQuery.model_json_schema(ref_template=DEFAULT_REF_TEMPLATE_SWAGGER_2_0),
+)
+console_ns.schema_model(
+    ChangeEmailSendPayload.__name__,
+    ChangeEmailSendPayload.model_json_schema(ref_template=DEFAULT_REF_TEMPLATE_SWAGGER_2_0),
+)
+console_ns.schema_model(
+    ChangeEmailValidityPayload.__name__,
+    ChangeEmailValidityPayload.model_json_schema(ref_template=DEFAULT_REF_TEMPLATE_SWAGGER_2_0),
+)
+console_ns.schema_model(
+    ChangeEmailResetPayload.__name__,
+    ChangeEmailResetPayload.model_json_schema(ref_template=DEFAULT_REF_TEMPLATE_SWAGGER_2_0),
+)
+console_ns.schema_model(
+    CheckEmailUniquePayload.__name__,
+    CheckEmailUniquePayload.model_json_schema(ref_template=DEFAULT_REF_TEMPLATE_SWAGGER_2_0),
+)
 
 
 @console_ns.route("/account/init")
 class AccountInitApi(Resource):
-    @console_ns.expect(_init_parser())
+    @console_ns.expect(console_ns.models[AccountInitPayload.__name__])
     @setup_required
     @login_required
     def post(self):
@@ -64,17 +244,18 @@ class AccountInitApi(Resource):
         if account.status == "active":
             raise AccountAlreadyInitedError()
 
-        args = _init_parser().parse_args()
+        payload = console_ns.payload or {}
+        args = AccountInitPayload.model_validate(payload)
 
         if dify_config.EDITION == "CLOUD":
-            if not args["invitation_code"]:
+            if not args.invitation_code:
                 raise ValueError("invitation_code is required")
 
             # check invitation code
             invitation_code = (
                 db.session.query(InvitationCode)
                 .where(
-                    InvitationCode.code == args["invitation_code"],
+                    InvitationCode.code == args.invitation_code,
                     InvitationCode.status == "unused",
                 )
                 .first()
@@ -88,8 +269,8 @@ class AccountInitApi(Resource):
             invitation_code.used_by_tenant_id = account.current_tenant_id
             invitation_code.used_by_account_id = account.id
 
-        account.interface_language = args["interface_language"]
-        account.timezone = args["timezone"]
+        account.interface_language = args.interface_language
+        account.timezone = args.timezone
         account.interface_theme = "light"
         account.status = "active"
         account.initialized_at = naive_utc_now()
@@ -110,137 +291,104 @@ class AccountProfileApi(Resource):
         return current_user
 
 
-parser_name = reqparse.RequestParser().add_argument("name", type=str, required=True, location="json")
-
-
 @console_ns.route("/account/name")
 class AccountNameApi(Resource):
-    @console_ns.expect(parser_name)
+    @console_ns.expect(console_ns.models[AccountNamePayload.__name__])
     @setup_required
     @login_required
     @account_initialization_required
     @marshal_with(account_fields)
     def post(self):
         current_user, _ = current_account_with_tenant()
-        args = parser_name.parse_args()
-
-        # Validate account name length
-        if len(args["name"]) < 3 or len(args["name"]) > 30:
-            raise ValueError("Account name must be between 3 and 30 characters.")
-
-        updated_account = AccountService.update_account(current_user, name=args["name"])
+        payload = console_ns.payload or {}
+        args = AccountNamePayload.model_validate(payload)
+        updated_account = AccountService.update_account(current_user, name=args.name)
 
         return updated_account
 
 
-parser_avatar = reqparse.RequestParser().add_argument("avatar", type=str, required=True, location="json")
-
-
 @console_ns.route("/account/avatar")
 class AccountAvatarApi(Resource):
-    @console_ns.expect(parser_avatar)
+    @console_ns.expect(console_ns.models[AccountAvatarPayload.__name__])
     @setup_required
     @login_required
     @account_initialization_required
     @marshal_with(account_fields)
     def post(self):
         current_user, _ = current_account_with_tenant()
-        args = parser_avatar.parse_args()
+        payload = console_ns.payload or {}
+        args = AccountAvatarPayload.model_validate(payload)
 
-        updated_account = AccountService.update_account(current_user, avatar=args["avatar"])
+        updated_account = AccountService.update_account(current_user, avatar=args.avatar)
 
         return updated_account
 
 
-parser_interface = reqparse.RequestParser().add_argument(
-    "interface_language", type=supported_language, required=True, location="json"
-)
-
-
 @console_ns.route("/account/interface-language")
 class AccountInterfaceLanguageApi(Resource):
-    @console_ns.expect(parser_interface)
+    @console_ns.expect(console_ns.models[AccountInterfaceLanguagePayload.__name__])
     @setup_required
     @login_required
     @account_initialization_required
     @marshal_with(account_fields)
     def post(self):
         current_user, _ = current_account_with_tenant()
-        args = parser_interface.parse_args()
+        payload = console_ns.payload or {}
+        args = AccountInterfaceLanguagePayload.model_validate(payload)
 
-        updated_account = AccountService.update_account(current_user, interface_language=args["interface_language"])
+        updated_account = AccountService.update_account(current_user, interface_language=args.interface_language)
 
         return updated_account
 
 
-parser_theme = reqparse.RequestParser().add_argument(
-    "interface_theme", type=str, choices=["light", "dark"], required=True, location="json"
-)
-
-
 @console_ns.route("/account/interface-theme")
 class AccountInterfaceThemeApi(Resource):
-    @console_ns.expect(parser_theme)
+    @console_ns.expect(console_ns.models[AccountInterfaceThemePayload.__name__])
     @setup_required
     @login_required
     @account_initialization_required
     @marshal_with(account_fields)
     def post(self):
         current_user, _ = current_account_with_tenant()
-        args = parser_theme.parse_args()
+        payload = console_ns.payload or {}
+        args = AccountInterfaceThemePayload.model_validate(payload)
 
-        updated_account = AccountService.update_account(current_user, interface_theme=args["interface_theme"])
+        updated_account = AccountService.update_account(current_user, interface_theme=args.interface_theme)
 
         return updated_account
 
 
-parser_timezone = reqparse.RequestParser().add_argument("timezone", type=str, required=True, location="json")
-
-
 @console_ns.route("/account/timezone")
 class AccountTimezoneApi(Resource):
-    @console_ns.expect(parser_timezone)
+    @console_ns.expect(console_ns.models[AccountTimezonePayload.__name__])
     @setup_required
     @login_required
     @account_initialization_required
     @marshal_with(account_fields)
     def post(self):
         current_user, _ = current_account_with_tenant()
-        args = parser_timezone.parse_args()
+        payload = console_ns.payload or {}
+        args = AccountTimezonePayload.model_validate(payload)
 
-        # Validate timezone string, e.g. America/New_York, Asia/Shanghai
-        if args["timezone"] not in pytz.all_timezones:
-            raise ValueError("Invalid timezone string.")
-
-        updated_account = AccountService.update_account(current_user, timezone=args["timezone"])
+        updated_account = AccountService.update_account(current_user, timezone=args.timezone)
 
         return updated_account
 
 
-parser_pw = (
-    reqparse.RequestParser()
-    .add_argument("password", type=str, required=False, location="json")
-    .add_argument("new_password", type=str, required=True, location="json")
-    .add_argument("repeat_new_password", type=str, required=True, location="json")
-)
-
-
 @console_ns.route("/account/password")
 class AccountPasswordApi(Resource):
-    @console_ns.expect(parser_pw)
+    @console_ns.expect(console_ns.models[AccountPasswordPayload.__name__])
     @setup_required
     @login_required
     @account_initialization_required
     @marshal_with(account_fields)
     def post(self):
         current_user, _ = current_account_with_tenant()
-        args = parser_pw.parse_args()
-
-        if args["new_password"] != args["repeat_new_password"]:
-            raise RepeatPasswordNotMatchError()
+        payload = console_ns.payload or {}
+        args = AccountPasswordPayload.model_validate(payload)
 
         try:
-            AccountService.update_account_password(current_user, args["password"], args["new_password"])
+            AccountService.update_account_password(current_user, args.password, args.new_password)
         except ServiceCurrentPasswordIncorrectError:
             raise CurrentPasswordIncorrectError()
 
@@ -316,25 +464,19 @@ class AccountDeleteVerifyApi(Resource):
         return {"result": "success", "data": token}
 
 
-parser_delete = (
-    reqparse.RequestParser()
-    .add_argument("token", type=str, required=True, location="json")
-    .add_argument("code", type=str, required=True, location="json")
-)
-
-
 @console_ns.route("/account/delete")
 class AccountDeleteApi(Resource):
-    @console_ns.expect(parser_delete)
+    @console_ns.expect(console_ns.models[AccountDeletePayload.__name__])
     @setup_required
     @login_required
     @account_initialization_required
     def post(self):
         account, _ = current_account_with_tenant()
 
-        args = parser_delete.parse_args()
+        payload = console_ns.payload or {}
+        args = AccountDeletePayload.model_validate(payload)
 
-        if not AccountService.verify_account_deletion_code(args["token"], args["code"]):
+        if not AccountService.verify_account_deletion_code(args.token, args.code):
             raise InvalidAccountDeletionCodeError()
 
         AccountService.delete_account(account)
@@ -342,21 +484,15 @@ class AccountDeleteApi(Resource):
         return {"result": "success"}
 
 
-parser_feedback = (
-    reqparse.RequestParser()
-    .add_argument("email", type=str, required=True, location="json")
-    .add_argument("feedback", type=str, required=True, location="json")
-)
-
-
 @console_ns.route("/account/delete/feedback")
 class AccountDeleteUpdateFeedbackApi(Resource):
-    @console_ns.expect(parser_feedback)
+    @console_ns.expect(console_ns.models[AccountDeletionFeedbackPayload.__name__])
     @setup_required
     def post(self):
-        args = parser_feedback.parse_args()
+        payload = console_ns.payload or {}
+        args = AccountDeletionFeedbackPayload.model_validate(payload)
 
-        BillingService.update_account_deletion_feedback(args["email"], args["feedback"])
+        BillingService.update_account_deletion_feedback(args.email, args.feedback)
 
         return {"result": "success"}
 
@@ -379,14 +515,6 @@ class EducationVerifyApi(Resource):
         return BillingService.EducationIdentity.verify(account.id, account.email)
 
 
-parser_edu = (
-    reqparse.RequestParser()
-    .add_argument("token", type=str, required=True, location="json")
-    .add_argument("institution", type=str, required=True, location="json")
-    .add_argument("role", type=str, required=True, location="json")
-)
-
-
 @console_ns.route("/account/education")
 class EducationApi(Resource):
     status_fields = {
@@ -396,7 +524,7 @@ class EducationApi(Resource):
         "allow_refresh": fields.Boolean,
     }
 
-    @console_ns.expect(parser_edu)
+    @console_ns.expect(console_ns.models[EducationActivatePayload.__name__])
     @setup_required
     @login_required
     @account_initialization_required
@@ -405,9 +533,10 @@ class EducationApi(Resource):
     def post(self):
         account, _ = current_account_with_tenant()
 
-        args = parser_edu.parse_args()
+        payload = console_ns.payload or {}
+        args = EducationActivatePayload.model_validate(payload)
 
-        return BillingService.EducationIdentity.activate(account, args["token"], args["institution"], args["role"])
+        return BillingService.EducationIdentity.activate(account, args.token, args.institution, args.role)
 
     @setup_required
     @login_required
@@ -425,14 +554,6 @@ class EducationApi(Resource):
         return res
 
 
-parser_autocomplete = (
-    reqparse.RequestParser()
-    .add_argument("keywords", type=str, required=True, location="args")
-    .add_argument("page", type=int, required=False, location="args", default=0)
-    .add_argument("limit", type=int, required=False, location="args", default=20)
-)
-
-
 @console_ns.route("/account/education/autocomplete")
 class EducationAutoCompleteApi(Resource):
     data_fields = {
@@ -441,7 +562,7 @@ class EducationAutoCompleteApi(Resource):
         "has_next": fields.Boolean,
     }
 
-    @console_ns.expect(parser_autocomplete)
+    @console_ns.expect(console_ns.models[EducationAutocompleteQuery.__name__])
     @setup_required
     @login_required
     @account_initialization_required
@@ -449,46 +570,39 @@ class EducationAutoCompleteApi(Resource):
     @cloud_edition_billing_enabled
     @marshal_with(data_fields)
     def get(self):
-        args = parser_autocomplete.parse_args()
+        payload = request.args.to_dict(flat=True)  # type: ignore
+        args = EducationAutocompleteQuery.model_validate(payload)
 
-        return BillingService.EducationIdentity.autocomplete(args["keywords"], args["page"], args["limit"])
-
-
-parser_change_email = (
-    reqparse.RequestParser()
-    .add_argument("email", type=email, required=True, location="json")
-    .add_argument("language", type=str, required=False, location="json")
-    .add_argument("phase", type=str, required=False, location="json")
-    .add_argument("token", type=str, required=False, location="json")
-)
+        return BillingService.EducationIdentity.autocomplete(args.keywords, args.page, args.limit)
 
 
 @console_ns.route("/account/change-email")
 class ChangeEmailSendEmailApi(Resource):
-    @console_ns.expect(parser_change_email)
+    @console_ns.expect(console_ns.models[ChangeEmailSendPayload.__name__])
     @enable_change_email
     @setup_required
     @login_required
     @account_initialization_required
     def post(self):
         current_user, _ = current_account_with_tenant()
-        args = parser_change_email.parse_args()
+        payload = console_ns.payload or {}
+        args = ChangeEmailSendPayload.model_validate(payload)
 
         ip_address = extract_remote_ip(request)
         if AccountService.is_email_send_ip_limit(ip_address):
             raise EmailSendIpLimitError()
 
-        if args["language"] is not None and args["language"] == "zh-Hans":
+        if args.language is not None and args.language == "zh-Hans":
             language = "zh-Hans"
         else:
             language = "en-US"
         account = None
-        user_email = args["email"]
-        if args["phase"] is not None and args["phase"] == "new_email":
-            if args["token"] is None:
+        user_email = args.email
+        if args.phase is not None and args.phase == "new_email":
+            if args.token is None:
                 raise InvalidTokenError()
 
-            reset_data = AccountService.get_change_email_data(args["token"])
+            reset_data = AccountService.get_change_email_data(args.token)
             if reset_data is None:
                 raise InvalidTokenError()
             user_email = reset_data.get("email", "")
@@ -497,118 +611,103 @@ class ChangeEmailSendEmailApi(Resource):
                 raise InvalidEmailError()
         else:
             with Session(db.engine) as session:
-                account = session.execute(select(Account).filter_by(email=args["email"])).scalar_one_or_none()
+                account = session.execute(select(Account).filter_by(email=args.email)).scalar_one_or_none()
             if account is None:
                 raise AccountNotFound()
 
         token = AccountService.send_change_email_email(
-            account=account, email=args["email"], old_email=user_email, language=language, phase=args["phase"]
+            account=account, email=args.email, old_email=user_email, language=language, phase=args.phase
         )
         return {"result": "success", "data": token}
 
 
-parser_validity = (
-    reqparse.RequestParser()
-    .add_argument("email", type=email, required=True, location="json")
-    .add_argument("code", type=str, required=True, location="json")
-    .add_argument("token", type=str, required=True, nullable=False, location="json")
-)
-
-
 @console_ns.route("/account/change-email/validity")
 class ChangeEmailCheckApi(Resource):
-    @console_ns.expect(parser_validity)
+    @console_ns.expect(console_ns.models[ChangeEmailValidityPayload.__name__])
     @enable_change_email
     @setup_required
     @login_required
     @account_initialization_required
     def post(self):
-        args = parser_validity.parse_args()
+        payload = console_ns.payload or {}
+        args = ChangeEmailValidityPayload.model_validate(payload)
 
-        user_email = args["email"]
+        user_email = args.email
 
-        is_change_email_error_rate_limit = AccountService.is_change_email_error_rate_limit(args["email"])
+        is_change_email_error_rate_limit = AccountService.is_change_email_error_rate_limit(args.email)
         if is_change_email_error_rate_limit:
             raise EmailChangeLimitError()
 
-        token_data = AccountService.get_change_email_data(args["token"])
+        token_data = AccountService.get_change_email_data(args.token)
         if token_data is None:
             raise InvalidTokenError()
 
         if user_email != token_data.get("email"):
             raise InvalidEmailError()
 
-        if args["code"] != token_data.get("code"):
-            AccountService.add_change_email_error_rate_limit(args["email"])
+        if args.code != token_data.get("code"):
+            AccountService.add_change_email_error_rate_limit(args.email)
             raise EmailCodeError()
 
         # Verified, revoke the first token
-        AccountService.revoke_change_email_token(args["token"])
+        AccountService.revoke_change_email_token(args.token)
 
         # Refresh token data by generating a new token
         _, new_token = AccountService.generate_change_email_token(
-            user_email, code=args["code"], old_email=token_data.get("old_email"), additional_data={}
+            user_email, code=args.code, old_email=token_data.get("old_email"), additional_data={}
         )
 
-        AccountService.reset_change_email_error_rate_limit(args["email"])
+        AccountService.reset_change_email_error_rate_limit(args.email)
         return {"is_valid": True, "email": token_data.get("email"), "token": new_token}
 
 
-parser_reset = (
-    reqparse.RequestParser()
-    .add_argument("new_email", type=email, required=True, location="json")
-    .add_argument("token", type=str, required=True, nullable=False, location="json")
-)
-
-
 @console_ns.route("/account/change-email/reset")
 class ChangeEmailResetApi(Resource):
-    @console_ns.expect(parser_reset)
+    @console_ns.expect(console_ns.models[ChangeEmailResetPayload.__name__])
     @enable_change_email
     @setup_required
     @login_required
     @account_initialization_required
     @marshal_with(account_fields)
     def post(self):
-        args = parser_reset.parse_args()
+        payload = console_ns.payload or {}
+        args = ChangeEmailResetPayload.model_validate(payload)
 
-        if AccountService.is_account_in_freeze(args["new_email"]):
+        if AccountService.is_account_in_freeze(args.new_email):
             raise AccountInFreezeError()
 
-        if not AccountService.check_email_unique(args["new_email"]):
+        if not AccountService.check_email_unique(args.new_email):
             raise EmailAlreadyInUseError()
 
-        reset_data = AccountService.get_change_email_data(args["token"])
+        reset_data = AccountService.get_change_email_data(args.token)
         if not reset_data:
             raise InvalidTokenError()
 
-        AccountService.revoke_change_email_token(args["token"])
+        AccountService.revoke_change_email_token(args.token)
 
         old_email = reset_data.get("old_email", "")
         current_user, _ = current_account_with_tenant()
         if current_user.email != old_email:
             raise AccountNotFound()
 
-        updated_account = AccountService.update_account_email(current_user, email=args["new_email"])
+        updated_account = AccountService.update_account_email(current_user, email=args.new_email)
 
         AccountService.send_change_email_completed_notify_email(
-            email=args["new_email"],
+            email=args.new_email,
         )
 
         return updated_account
 
 
-parser_check = reqparse.RequestParser().add_argument("email", type=email, required=True, location="json")
-
-
 @console_ns.route("/account/change-email/check-email-unique")
 class CheckEmailUnique(Resource):
-    @console_ns.expect(parser_check)
+    @console_ns.expect(console_ns.models[CheckEmailUniquePayload.__name__])
     @setup_required
     def post(self):
-        args = parser_check.parse_args()
-        if AccountService.is_account_in_freeze(args["email"]):
+        payload = console_ns.payload or {}
+        args = CheckEmailUniquePayload.model_validate(payload)
+        if AccountService.is_account_in_freeze(args.email):
             raise AccountInFreezeError()
-        if not AccountService.check_email_unique(args["email"]):
+        if not AccountService.check_email_unique(args.email):
             raise EmailAlreadyInUseError()
         return {"result": "success"}

api/controllers/console/workspace/members.py

@@ -1,7 +1,8 @@
 from urllib import parse
 
 from flask import abort, request
-from flask_restx import Resource, marshal_with, reqparse
+from flask_restx import Resource, marshal_with
+from pydantic import BaseModel, Field
 
 import services
 from configs import dify_config
@@ -31,6 +32,53 @@ from services.account_service import AccountService, RegisterService, TenantServ
 from services.errors.account import AccountAlreadyInTenantError
 from services.feature_service import FeatureService
 
+DEFAULT_REF_TEMPLATE_SWAGGER_2_0 = "#/definitions/{model}"
+
+
+class MemberInvitePayload(BaseModel):
+    emails: list[str] = Field(default_factory=list)
+    role: TenantAccountRole
+    language: str | None = None
+
+
+class MemberRoleUpdatePayload(BaseModel):
+    role: str
+
+
+class OwnerTransferEmailPayload(BaseModel):
+    language: str | None = None
+
+
+class OwnerTransferCheckPayload(BaseModel):
+    code: str
+    token: str
+
+
+class OwnerTransferPayload(BaseModel):
+    token: str
+
+
+console_ns.schema_model(
+    MemberInvitePayload.__name__,
+    MemberInvitePayload.model_json_schema(ref_template=DEFAULT_REF_TEMPLATE_SWAGGER_2_0),
+)
+console_ns.schema_model(
+    MemberRoleUpdatePayload.__name__,
+    MemberRoleUpdatePayload.model_json_schema(ref_template=DEFAULT_REF_TEMPLATE_SWAGGER_2_0),
+)
+console_ns.schema_model(
+    OwnerTransferEmailPayload.__name__,
+    OwnerTransferEmailPayload.model_json_schema(ref_template=DEFAULT_REF_TEMPLATE_SWAGGER_2_0),
+)
+console_ns.schema_model(
+    OwnerTransferCheckPayload.__name__,
+    OwnerTransferCheckPayload.model_json_schema(ref_template=DEFAULT_REF_TEMPLATE_SWAGGER_2_0),
+)
+console_ns.schema_model(
+    OwnerTransferPayload.__name__,
+    OwnerTransferPayload.model_json_schema(ref_template=DEFAULT_REF_TEMPLATE_SWAGGER_2_0),
+)
+
 
 @console_ns.route("/workspaces/current/members")
 class MemberListApi(Resource):
@@ -48,29 +96,22 @@ class MemberListApi(Resource):
         return {"result": "success", "accounts": members}, 200
 
 
-parser_invite = (
-    reqparse.RequestParser()
-    .add_argument("emails", type=list, required=True, location="json")
-    .add_argument("role", type=str, required=True, default="admin", location="json")
-    .add_argument("language", type=str, required=False, location="json")
-)
-
-
 @console_ns.route("/workspaces/current/members/invite-email")
 class MemberInviteEmailApi(Resource):
     """Invite a new member by email."""
 
-    @console_ns.expect(parser_invite)
+    @console_ns.expect(console_ns.models[MemberInvitePayload.__name__])
     @setup_required
     @login_required
     @account_initialization_required
     @cloud_edition_billing_resource_check("members")
     def post(self):
-        args = parser_invite.parse_args()
+        payload = console_ns.payload or {}
+        args = MemberInvitePayload.model_validate(payload)
 
-        invitee_emails = args["emails"]
-        invitee_role = args["role"]
-        interface_language = args["language"]
+        invitee_emails = args.emails
+        invitee_role = args.role
+        interface_language = args.language
         if not TenantAccountRole.is_non_owner_role(invitee_role):
             return {"code": "invalid-role", "message": "Invalid role"}, 400
         current_user, _ = current_account_with_tenant()
@@ -146,20 +187,18 @@ class MemberCancelInviteApi(Resource):
         }, 200
 
 
-parser_update = reqparse.RequestParser().add_argument("role", type=str, required=True, location="json")
-
-
 @console_ns.route("/workspaces/current/members/<uuid:member_id>/update-role")
 class MemberUpdateRoleApi(Resource):
     """Update member role."""
 
-    @console_ns.expect(parser_update)
+    @console_ns.expect(console_ns.models[MemberRoleUpdatePayload.__name__])
     @setup_required
     @login_required
     @account_initialization_required
     def put(self, member_id):
-        args = parser_update.parse_args()
-        new_role = args["role"]
+        payload = console_ns.payload or {}
+        args = MemberRoleUpdatePayload.model_validate(payload)
+        new_role = args.role
 
         if not TenantAccountRole.is_valid_role(new_role):
             return {"code": "invalid-role", "message": "Invalid role"}, 400
@@ -197,20 +236,18 @@ class DatasetOperatorMemberListApi(Resource):
         return {"result": "success", "accounts": members}, 200
 
 
-parser_send = reqparse.RequestParser().add_argument("language", type=str, required=False, location="json")
-
-
 @console_ns.route("/workspaces/current/members/send-owner-transfer-confirm-email")
 class SendOwnerTransferEmailApi(Resource):
     """Send owner transfer email."""
 
-    @console_ns.expect(parser_send)
+    @console_ns.expect(console_ns.models[OwnerTransferEmailPayload.__name__])
     @setup_required
     @login_required
     @account_initialization_required
     @is_allow_transfer_owner
     def post(self):
-        args = parser_send.parse_args()
+        payload = console_ns.payload or {}
+        args = OwnerTransferEmailPayload.model_validate(payload)
         ip_address = extract_remote_ip(request)
         if AccountService.is_email_send_ip_limit(ip_address):
             raise EmailSendIpLimitError()
@@ -221,7 +258,7 @@ class SendOwnerTransferEmailApi(Resource):
         if not TenantService.is_owner(current_user, current_user.current_tenant):
             raise NotOwnerError()
 
-        if args["language"] is not None and args["language"] == "zh-Hans":
+        if args.language is not None and args.language == "zh-Hans":
             language = "zh-Hans"
         else:
             language = "en-US"
@@ -238,22 +275,16 @@ class SendOwnerTransferEmailApi(Resource):
         return {"result": "success", "data": token}
 
 
-parser_owner = (
-    reqparse.RequestParser()
-    .add_argument("code", type=str, required=True, location="json")
-    .add_argument("token", type=str, required=True, nullable=False, location="json")
-)
-
-
 @console_ns.route("/workspaces/current/members/owner-transfer-check")
 class OwnerTransferCheckApi(Resource):
-    @console_ns.expect(parser_owner)
+    @console_ns.expect(console_ns.models[OwnerTransferCheckPayload.__name__])
     @setup_required
     @login_required
     @account_initialization_required
     @is_allow_transfer_owner
     def post(self):
-        args = parser_owner.parse_args()
+        payload = console_ns.payload or {}
+        args = OwnerTransferCheckPayload.model_validate(payload)
         # check if the current user is the owner of the workspace
         current_user, _ = current_account_with_tenant()
         if not current_user.current_tenant:
@@ -267,41 +298,37 @@ class OwnerTransferCheckApi(Resource):
         if is_owner_transfer_error_rate_limit:
             raise OwnerTransferLimitError()
 
-        token_data = AccountService.get_owner_transfer_data(args["token"])
+        token_data = AccountService.get_owner_transfer_data(args.token)
         if token_data is None:
             raise InvalidTokenError()
 
         if user_email != token_data.get("email"):
             raise InvalidEmailError()
 
-        if args["code"] != token_data.get("code"):
+        if args.code != token_data.get("code"):
             AccountService.add_owner_transfer_error_rate_limit(user_email)
             raise EmailCodeError()
 
         # Verified, revoke the first token
-        AccountService.revoke_owner_transfer_token(args["token"])
+        AccountService.revoke_owner_transfer_token(args.token)
 
         # Refresh token data by generating a new token
-        _, new_token = AccountService.generate_owner_transfer_token(user_email, code=args["code"], additional_data={})
+        _, new_token = AccountService.generate_owner_transfer_token(user_email, code=args.code, additional_data={})
 
         AccountService.reset_owner_transfer_error_rate_limit(user_email)
         return {"is_valid": True, "email": token_data.get("email"), "token": new_token}
 
 
-parser_owner_transfer = reqparse.RequestParser().add_argument(
-    "token", type=str, required=True, nullable=False, location="json"
-)
-
-
 @console_ns.route("/workspaces/current/members/<uuid:member_id>/owner-transfer")
 class OwnerTransfer(Resource):
-    @console_ns.expect(parser_owner_transfer)
+    @console_ns.expect(console_ns.models[OwnerTransferPayload.__name__])
     @setup_required
     @login_required
     @account_initialization_required
     @is_allow_transfer_owner
     def post(self, member_id):
-        args = parser_owner_transfer.parse_args()
+        payload = console_ns.payload or {}
+        args = OwnerTransferPayload.model_validate(payload)
 
         # check if the current user is the owner of the workspace
         current_user, _ = current_account_with_tenant()
@@ -313,14 +340,14 @@ class OwnerTransfer(Resource):
         if current_user.id == str(member_id):
             raise CannotTransferOwnerToSelfError()
 
-        transfer_token_data = AccountService.get_owner_transfer_data(args["token"])
+        transfer_token_data = AccountService.get_owner_transfer_data(args.token)
         if not transfer_token_data:
             raise InvalidTokenError()
 
         if transfer_token_data.get("email") != current_user.email:
             raise InvalidEmailError()
 
-        AccountService.revoke_owner_transfer_token(args["token"])
+        AccountService.revoke_owner_transfer_token(args.token)
 
         member = db.session.get(Account, str(member_id))
         if not member:

api/controllers/console/workspace/model_providers.py

@@ -1,31 +1,123 @@
 import io
+from typing import Any, Literal
 
-from flask import send_file
-from flask_restx import Resource, reqparse
+from flask import request, send_file
+from flask_restx import Resource
+from pydantic import BaseModel, Field, field_validator
 
 from controllers.console import console_ns
 from controllers.console.wraps import account_initialization_required, is_admin_or_owner_required, setup_required
 from core.model_runtime.entities.model_entities import ModelType
 from core.model_runtime.errors.validate import CredentialsValidateFailedError
 from core.model_runtime.utils.encoders import jsonable_encoder
-from libs.helper import StrLen, uuid_value
+from libs.helper import uuid_value
 from libs.login import current_account_with_tenant, login_required
 from services.billing_service import BillingService
 from services.model_provider_service import ModelProviderService
 
-parser_model = reqparse.RequestParser().add_argument(
-    "model_type",
-    type=str,
-    required=False,
-    nullable=True,
-    choices=[mt.value for mt in ModelType],
-    location="args",
+DEFAULT_REF_TEMPLATE_SWAGGER_2_0 = "#/definitions/{model}"
+
+
+class ParserModelList(BaseModel):
+    model_type: ModelType | None = None
+
+
+class ParserCredentialId(BaseModel):
+    credential_id: str | None = None
+
+    @field_validator("credential_id")
+    @classmethod
+    def validate_optional_credential_id(cls, value: str | None) -> str | None:
+        if value is None:
+            return value
+        return uuid_value(value)
+
+
+class ParserCredentialCreate(BaseModel):
+    credentials: dict[str, Any]
+    name: str | None = Field(default=None, max_length=30)
+
+
+class ParserCredentialUpdate(BaseModel):
+    credential_id: str
+    credentials: dict[str, Any]
+    name: str | None = Field(default=None, max_length=30)
+
+    @field_validator("credential_id")
+    @classmethod
+    def validate_update_credential_id(cls, value: str) -> str:
+        return uuid_value(value)
+
+
+class ParserCredentialDelete(BaseModel):
+    credential_id: str
+
+    @field_validator("credential_id")
+    @classmethod
+    def validate_delete_credential_id(cls, value: str) -> str:
+        return uuid_value(value)
+
+
+class ParserCredentialSwitch(BaseModel):
+    credential_id: str
+
+    @field_validator("credential_id")
+    @classmethod
+    def validate_switch_credential_id(cls, value: str) -> str:
+        return uuid_value(value)
+
+
+class ParserCredentialValidate(BaseModel):
+    credentials: dict[str, Any]
+
+
+class ParserPreferredProviderType(BaseModel):
+    preferred_provider_type: Literal["system", "custom"]
+
+
+console_ns.schema_model(
+    ParserModelList.__name__, ParserModelList.model_json_schema(ref_template=DEFAULT_REF_TEMPLATE_SWAGGER_2_0)
+)
+
+console_ns.schema_model(
+    ParserCredentialId.__name__,
+    ParserCredentialId.model_json_schema(ref_template=DEFAULT_REF_TEMPLATE_SWAGGER_2_0),
+)
+
+console_ns.schema_model(
+    ParserCredentialCreate.__name__,
+    ParserCredentialCreate.model_json_schema(ref_template=DEFAULT_REF_TEMPLATE_SWAGGER_2_0),
+)
+
+console_ns.schema_model(
+    ParserCredentialUpdate.__name__,
+    ParserCredentialUpdate.model_json_schema(ref_template=DEFAULT_REF_TEMPLATE_SWAGGER_2_0),
+)
+
+console_ns.schema_model(
+    ParserCredentialDelete.__name__,
+    ParserCredentialDelete.model_json_schema(ref_template=DEFAULT_REF_TEMPLATE_SWAGGER_2_0),
+)
+
+console_ns.schema_model(
+    ParserCredentialSwitch.__name__,
+    ParserCredentialSwitch.model_json_schema(ref_template=DEFAULT_REF_TEMPLATE_SWAGGER_2_0),
+)
+
+console_ns.schema_model(
+    ParserCredentialValidate.__name__,
+    ParserCredentialValidate.model_json_schema(ref_template=DEFAULT_REF_TEMPLATE_SWAGGER_2_0),
+)
+
+console_ns.schema_model(
+    ParserPreferredProviderType.__name__,
+    ParserPreferredProviderType.model_json_schema(ref_template=DEFAULT_REF_TEMPLATE_SWAGGER_2_0),
 )
 
 
 @console_ns.route("/workspaces/current/model-providers")
 class ModelProviderListApi(Resource):
-    @console_ns.expect(parser_model)
+    @console_ns.expect(console_ns.models[ParserModelList.__name__])
     @setup_required
     @login_required
     @account_initialization_required
@@ -33,38 +125,18 @@ class ModelProviderListApi(Resource):
         _, current_tenant_id = current_account_with_tenant()
         tenant_id = current_tenant_id
 
-        args = parser_model.parse_args()
+        payload = request.args.to_dict(flat=True)  # type: ignore
+        args = ParserModelList.model_validate(payload)
 
         model_provider_service = ModelProviderService()
-        provider_list = model_provider_service.get_provider_list(tenant_id=tenant_id, model_type=args.get("model_type"))
+        provider_list = model_provider_service.get_provider_list(tenant_id=tenant_id, model_type=args.model_type)
 
         return jsonable_encoder({"data": provider_list})
 
 
-parser_cred = reqparse.RequestParser().add_argument(
-    "credential_id", type=uuid_value, required=False, nullable=True, location="args"
-)
-parser_post_cred = (
-    reqparse.RequestParser()
-    .add_argument("credentials", type=dict, required=True, nullable=False, location="json")
-    .add_argument("name", type=StrLen(30), required=False, nullable=True, location="json")
-)
-
-parser_put_cred = (
-    reqparse.RequestParser()
-    .add_argument("credential_id", type=uuid_value, required=True, nullable=False, location="json")
-    .add_argument("credentials", type=dict, required=True, nullable=False, location="json")
-    .add_argument("name", type=StrLen(30), required=False, nullable=True, location="json")
-)
-
-parser_delete_cred = reqparse.RequestParser().add_argument(
-    "credential_id", type=uuid_value, required=True, nullable=False, location="json"
-)
-
-
 @console_ns.route("/workspaces/current/model-providers/<path:provider>/credentials")
 class ModelProviderCredentialApi(Resource):
-    @console_ns.expect(parser_cred)
+    @console_ns.expect(console_ns.models[ParserCredentialId.__name__])
     @setup_required
     @login_required
     @account_initialization_required
@@ -72,23 +144,25 @@ class ModelProviderCredentialApi(Resource):
         _, current_tenant_id = current_account_with_tenant()
         tenant_id = current_tenant_id
         # if credential_id is not provided, return current used credential
-        args = parser_cred.parse_args()
+        payload = request.args.to_dict(flat=True)  # type: ignore
+        args = ParserCredentialId.model_validate(payload)
 
         model_provider_service = ModelProviderService()
         credentials = model_provider_service.get_provider_credential(
-            tenant_id=tenant_id, provider=provider, credential_id=args.get("credential_id")
+            tenant_id=tenant_id, provider=provider, credential_id=args.credential_id
         )
 
         return {"credentials": credentials}
 
-    @console_ns.expect(parser_post_cred)
+    @console_ns.expect(console_ns.models[ParserCredentialCreate.__name__])
     @setup_required
     @login_required
     @is_admin_or_owner_required
     @account_initialization_required
     def post(self, provider: str):
         _, current_tenant_id = current_account_with_tenant()
-        args = parser_post_cred.parse_args()
+        payload = console_ns.payload or {}
+        args = ParserCredentialCreate.model_validate(payload)
 
         model_provider_service = ModelProviderService()
 
@@ -96,15 +170,15 @@ class ModelProviderCredentialApi(Resource):
             model_provider_service.create_provider_credential(
                 tenant_id=current_tenant_id,
                 provider=provider,
-                credentials=args["credentials"],
-                credential_name=args["name"],
+                credentials=args.credentials,
+                credential_name=args.name,
             )
         except CredentialsValidateFailedError as ex:
             raise ValueError(str(ex))
 
         return {"result": "success"}, 201
 
-    @console_ns.expect(parser_put_cred)
+    @console_ns.expect(console_ns.models[ParserCredentialUpdate.__name__])
     @setup_required
     @login_required
     @is_admin_or_owner_required
@@ -112,7 +186,8 @@ class ModelProviderCredentialApi(Resource):
     def put(self, provider: str):
         _, current_tenant_id = current_account_with_tenant()
 
-        args = parser_put_cred.parse_args()
+        payload = console_ns.payload or {}
+        args = ParserCredentialUpdate.model_validate(payload)
 
         model_provider_service = ModelProviderService()
 
@@ -120,71 +195,64 @@ class ModelProviderCredentialApi(Resource):
             model_provider_service.update_provider_credential(
                 tenant_id=current_tenant_id,
                 provider=provider,
-                credentials=args["credentials"],
-                credential_id=args["credential_id"],
-                credential_name=args["name"],
+                credentials=args.credentials,
+                credential_id=args.credential_id,
+                credential_name=args.name,
             )
         except CredentialsValidateFailedError as ex:
             raise ValueError(str(ex))
 
         return {"result": "success"}
 
-    @console_ns.expect(parser_delete_cred)
+    @console_ns.expect(console_ns.models[ParserCredentialDelete.__name__])
     @setup_required
     @login_required
     @is_admin_or_owner_required
     @account_initialization_required
     def delete(self, provider: str):
         _, current_tenant_id = current_account_with_tenant()
-        args = parser_delete_cred.parse_args()
+        payload = console_ns.payload or {}
+        args = ParserCredentialDelete.model_validate(payload)
 
         model_provider_service = ModelProviderService()
         model_provider_service.remove_provider_credential(
-            tenant_id=current_tenant_id, provider=provider, credential_id=args["credential_id"]
+            tenant_id=current_tenant_id, provider=provider, credential_id=args.credential_id
         )
 
         return {"result": "success"}, 204
 
 
-parser_switch = reqparse.RequestParser().add_argument(
-    "credential_id", type=str, required=True, nullable=False, location="json"
-)
-
-
 @console_ns.route("/workspaces/current/model-providers/<path:provider>/credentials/switch")
 class ModelProviderCredentialSwitchApi(Resource):
-    @console_ns.expect(parser_switch)
+    @console_ns.expect(console_ns.models[ParserCredentialSwitch.__name__])
     @setup_required
     @login_required
     @is_admin_or_owner_required
     @account_initialization_required
     def post(self, provider: str):
         _, current_tenant_id = current_account_with_tenant()
-        args = parser_switch.parse_args()
+        payload = console_ns.payload or {}
+        args = ParserCredentialSwitch.model_validate(payload)
 
         service = ModelProviderService()
         service.switch_active_provider_credential(
             tenant_id=current_tenant_id,
             provider=provider,
-            credential_id=args["credential_id"],
+            credential_id=args.credential_id,
         )
         return {"result": "success"}
 
 
-parser_validate = reqparse.RequestParser().add_argument(
-    "credentials", type=dict, required=True, nullable=False, location="json"
-)
-
-
 @console_ns.route("/workspaces/current/model-providers/<path:provider>/credentials/validate")
 class ModelProviderValidateApi(Resource):
-    @console_ns.expect(parser_validate)
+    @console_ns.expect(console_ns.models[ParserCredentialValidate.__name__])
     @setup_required
     @login_required
     @account_initialization_required
     def post(self, provider: str):
         _, current_tenant_id = current_account_with_tenant()
-        args = parser_validate.parse_args()
+        payload = console_ns.payload or {}
+        args = ParserCredentialValidate.model_validate(payload)
 
         tenant_id = current_tenant_id
 
@@ -195,7 +263,7 @@ class ModelProviderValidateApi(Resource):
 
         try:
             model_provider_service.validate_provider_credentials(
-                tenant_id=tenant_id, provider=provider, credentials=args["credentials"]
+                tenant_id=tenant_id, provider=provider, credentials=args.credentials
             )
         except CredentialsValidateFailedError as ex:
             result = False
@@ -228,19 +296,9 @@ class ModelProviderIconApi(Resource):
         return send_file(io.BytesIO(icon), mimetype=mimetype)
 
 
-parser_preferred = reqparse.RequestParser().add_argument(
-    "preferred_provider_type",
-    type=str,
-    required=True,
-    nullable=False,
-    choices=["system", "custom"],
-    location="json",
-)
-
-
 @console_ns.route("/workspaces/current/model-providers/<path:provider>/preferred-provider-type")
 class PreferredProviderTypeUpdateApi(Resource):
-    @console_ns.expect(parser_preferred)
+    @console_ns.expect(console_ns.models[ParserPreferredProviderType.__name__])
     @setup_required
     @login_required
     @is_admin_or_owner_required
@@ -250,11 +308,12 @@ class PreferredProviderTypeUpdateApi(Resource):
 
         tenant_id = current_tenant_id
 
-        args = parser_preferred.parse_args()
+        payload = console_ns.payload or {}
+        args = ParserPreferredProviderType.model_validate(payload)
 
         model_provider_service = ModelProviderService()
         model_provider_service.switch_preferred_provider(
-            tenant_id=tenant_id, provider=provider, preferred_provider_type=args["preferred_provider_type"]
+            tenant_id=tenant_id, provider=provider, preferred_provider_type=args.preferred_provider_type
         )
 
         return {"result": "success"}

api/controllers/console/workspace/models.py

@@ -1,52 +1,172 @@
 import logging
+from typing import Any, cast
 
-from flask_restx import Resource, reqparse
+from flask import request
+from flask_restx import Resource
+from pydantic import BaseModel, Field, field_validator
 
 from controllers.console import console_ns
 from controllers.console.wraps import account_initialization_required, is_admin_or_owner_required, setup_required
 from core.model_runtime.entities.model_entities import ModelType
 from core.model_runtime.errors.validate import CredentialsValidateFailedError
 from core.model_runtime.utils.encoders import jsonable_encoder
-from libs.helper import StrLen, uuid_value
+from libs.helper import uuid_value
 from libs.login import current_account_with_tenant, login_required
 from services.model_load_balancing_service import ModelLoadBalancingService
 from services.model_provider_service import ModelProviderService
 
 logger = logging.getLogger(__name__)
+DEFAULT_REF_TEMPLATE_SWAGGER_2_0 = "#/definitions/{model}"
 
 
-parser_get_default = reqparse.RequestParser().add_argument(
-    "model_type",
-    type=str,
-    required=True,
-    nullable=False,
-    choices=[mt.value for mt in ModelType],
-    location="args",
+class ParserGetDefault(BaseModel):
+    model_type: ModelType
+
+
+class ParserPostDefault(BaseModel):
+    class Inner(BaseModel):
+        model_type: ModelType
+        model: str | None = None
+        provider: str | None = None
+
+    model_settings: list[Inner]
+
+
+console_ns.schema_model(
+    ParserGetDefault.__name__, ParserGetDefault.model_json_schema(ref_template=DEFAULT_REF_TEMPLATE_SWAGGER_2_0)
 )
-parser_post_default = reqparse.RequestParser().add_argument(
-    "model_settings", type=list, required=True, nullable=False, location="json"
+
+console_ns.schema_model(
+    ParserPostDefault.__name__, ParserPostDefault.model_json_schema(ref_template=DEFAULT_REF_TEMPLATE_SWAGGER_2_0)
+)
+
+
+class ParserDeleteModels(BaseModel):
+    model: str
+    model_type: ModelType
+
+
+console_ns.schema_model(
+    ParserDeleteModels.__name__, ParserDeleteModels.model_json_schema(ref_template=DEFAULT_REF_TEMPLATE_SWAGGER_2_0)
+)
+
+
+class LoadBalancingPayload(BaseModel):
+    configs: list[dict[str, Any]] | None = None
+    enabled: bool | None = None
+
+
+class ParserPostModels(BaseModel):
+    model: str
+    model_type: ModelType
+    load_balancing: LoadBalancingPayload | None = None
+    config_from: str | None = None
+    credential_id: str | None = None
+
+    @field_validator("credential_id")
+    @classmethod
+    def validate_credential_id(cls, value: str | None) -> str | None:
+        if value is None:
+            return value
+        return uuid_value(value)
+
+
+class ParserGetCredentials(BaseModel):
+    model: str
+    model_type: ModelType
+    config_from: str | None = None
+    credential_id: str | None = None
+
+    @field_validator("credential_id")
+    @classmethod
+    def validate_get_credential_id(cls, value: str | None) -> str | None:
+        if value is None:
+            return value
+        return uuid_value(value)
+
+
+class ParserCredentialBase(BaseModel):
+    model: str
+    model_type: ModelType
+
+
+class ParserCreateCredential(ParserCredentialBase):
+    name: str | None = Field(default=None, max_length=30)
+    credentials: dict[str, Any]
+
+
+class ParserUpdateCredential(ParserCredentialBase):
+    credential_id: str
+    credentials: dict[str, Any]
+    name: str | None = Field(default=None, max_length=30)
+
+    @field_validator("credential_id")
+    @classmethod
+    def validate_update_credential_id(cls, value: str) -> str:
+        return uuid_value(value)
+
+
+class ParserDeleteCredential(ParserCredentialBase):
+    credential_id: str
+
+    @field_validator("credential_id")
+    @classmethod
+    def validate_delete_credential_id(cls, value: str) -> str:
+        return uuid_value(value)
+
+
+class ParserParameter(BaseModel):
+    model: str
+
+
+console_ns.schema_model(
+    ParserPostModels.__name__, ParserPostModels.model_json_schema(ref_template=DEFAULT_REF_TEMPLATE_SWAGGER_2_0)
+)
+
+console_ns.schema_model(
+    ParserGetCredentials.__name__,
+    ParserGetCredentials.model_json_schema(ref_template=DEFAULT_REF_TEMPLATE_SWAGGER_2_0),
+)
+
+console_ns.schema_model(
+    ParserCreateCredential.__name__,
+    ParserCreateCredential.model_json_schema(ref_template=DEFAULT_REF_TEMPLATE_SWAGGER_2_0),
+)
+
+console_ns.schema_model(
+    ParserUpdateCredential.__name__,
+    ParserUpdateCredential.model_json_schema(ref_template=DEFAULT_REF_TEMPLATE_SWAGGER_2_0),
+)
+
+console_ns.schema_model(
+    ParserDeleteCredential.__name__,
+    ParserDeleteCredential.model_json_schema(ref_template=DEFAULT_REF_TEMPLATE_SWAGGER_2_0),
+)
+
+console_ns.schema_model(
+    ParserParameter.__name__, ParserParameter.model_json_schema(ref_template=DEFAULT_REF_TEMPLATE_SWAGGER_2_0)
 )
 
 
 @console_ns.route("/workspaces/current/default-model")
 class DefaultModelApi(Resource):
-    @console_ns.expect(parser_get_default)
+    @console_ns.expect(console_ns.models[ParserGetDefault.__name__])
     @setup_required
     @login_required
     @account_initialization_required
     def get(self):
         _, tenant_id = current_account_with_tenant()
 
-        args = parser_get_default.parse_args()
+        args = ParserGetDefault.model_validate(request.args.to_dict(flat=True))  # type: ignore
 
         model_provider_service = ModelProviderService()
         default_model_entity = model_provider_service.get_default_model_of_model_type(
-            tenant_id=tenant_id, model_type=args["model_type"]
+            tenant_id=tenant_id, model_type=args.model_type
         )
 
         return jsonable_encoder({"data": default_model_entity})
 
-    @console_ns.expect(parser_post_default)
+    @console_ns.expect(console_ns.models[ParserPostDefault.__name__])
     @setup_required
     @login_required
     @is_admin_or_owner_required
@@ -54,66 +174,31 @@ class DefaultModelApi(Resource):
     def post(self):
         _, tenant_id = current_account_with_tenant()
 
-        args = parser_post_default.parse_args()
+        args = ParserPostDefault.model_validate(console_ns.payload)
         model_provider_service = ModelProviderService()
-        model_settings = args["model_settings"]
+        model_settings = args.model_settings
         for model_setting in model_settings:
-            if "model_type" not in model_setting or model_setting["model_type"] not in [mt.value for mt in ModelType]:
-                raise ValueError("invalid model type")
-
-            if "provider" not in model_setting:
+            if model_setting.provider is None:
                 continue
 
-            if "model" not in model_setting:
-                raise ValueError("invalid model")
-
             try:
                 model_provider_service.update_default_model_of_model_type(
                     tenant_id=tenant_id,
-                    model_type=model_setting["model_type"],
-                    provider=model_setting["provider"],
-                    model=model_setting["model"],
+                    model_type=model_setting.model_type,
+                    provider=model_setting.provider,
+                    model=cast(str, model_setting.model),
                 )
             except Exception as ex:
                 logger.exception(
                     "Failed to update default model, model type: %s, model: %s",
-                    model_setting["model_type"],
-                    model_setting.get("model"),
+                    model_setting.model_type,
+                    model_setting.model,
                 )
                 raise ex
 
         return {"result": "success"}
 
 
-parser_post_models = (
-    reqparse.RequestParser()
-    .add_argument("model", type=str, required=True, nullable=False, location="json")
-    .add_argument(
-        "model_type",
-        type=str,
-        required=True,
-        nullable=False,
-        choices=[mt.value for mt in ModelType],
-        location="json",
-    )
-    .add_argument("load_balancing", type=dict, required=False, nullable=True, location="json")
-    .add_argument("config_from", type=str, required=False, nullable=True, location="json")
-    .add_argument("credential_id", type=uuid_value, required=False, nullable=True, location="json")
-)
-parser_delete_models = (
-    reqparse.RequestParser()
-    .add_argument("model", type=str, required=True, nullable=False, location="json")
-    .add_argument(
-        "model_type",
-        type=str,
-        required=True,
-        nullable=False,
-        choices=[mt.value for mt in ModelType],
-        location="json",
-    )
-)
-
-
 @console_ns.route("/workspaces/current/model-providers/<path:provider>/models")
 class ModelProviderModelApi(Resource):
     @setup_required
@@ -127,7 +212,7 @@ class ModelProviderModelApi(Resource):
 
         return jsonable_encoder({"data": models})
 
-    @console_ns.expect(parser_post_models)
+    @console_ns.expect(console_ns.models[ParserPostModels.__name__])
     @setup_required
     @login_required
     @is_admin_or_owner_required
@@ -135,45 +220,45 @@ class ModelProviderModelApi(Resource):
     def post(self, provider: str):
         # To save the model's load balance configs
         _, tenant_id = current_account_with_tenant()
-        args = parser_post_models.parse_args()
+        args = ParserPostModels.model_validate(console_ns.payload)
 
-        if args.get("config_from", "") == "custom-model":
-            if not args.get("credential_id"):
+        if args.config_from == "custom-model":
+            if not args.credential_id:
                 raise ValueError("credential_id is required when configuring a custom-model")
             service = ModelProviderService()
             service.switch_active_custom_model_credential(
                 tenant_id=tenant_id,
                 provider=provider,
-                model_type=args["model_type"],
-                model=args["model"],
-                credential_id=args["credential_id"],
+                model_type=args.model_type,
+                model=args.model,
+                credential_id=args.credential_id,
             )
 
         model_load_balancing_service = ModelLoadBalancingService()
 
-        if "load_balancing" in args and args["load_balancing"] and "configs" in args["load_balancing"]:
+        if args.load_balancing and args.load_balancing.configs:
             # save load balancing configs
             model_load_balancing_service.update_load_balancing_configs(
                 tenant_id=tenant_id,
                 provider=provider,
-                model=args["model"],
-                model_type=args["model_type"],
-                configs=args["load_balancing"]["configs"],
-                config_from=args.get("config_from", ""),
+                model=args.model,
+                model_type=args.model_type,
+                configs=args.load_balancing.configs,
+                config_from=args.config_from or "",
             )
 
-            if args.get("load_balancing", {}).get("enabled"):
+            if args.load_balancing.enabled:
                 model_load_balancing_service.enable_model_load_balancing(
-                    tenant_id=tenant_id, provider=provider, model=args["model"], model_type=args["model_type"]
+                    tenant_id=tenant_id, provider=provider, model=args.model, model_type=args.model_type
                 )
             else:
                 model_load_balancing_service.disable_model_load_balancing(
-                    tenant_id=tenant_id, provider=provider, model=args["model"], model_type=args["model_type"]
+                    tenant_id=tenant_id, provider=provider, model=args.model, model_type=args.model_type
                 )
 
         return {"result": "success"}, 200
 
-    @console_ns.expect(parser_delete_models)
+    @console_ns.expect(console_ns.models[ParserDeleteModels.__name__], validate=True)
     @setup_required
     @login_required
     @is_admin_or_owner_required
@@ -181,113 +266,53 @@ class ModelProviderModelApi(Resource):
     def delete(self, provider: str):
         _, tenant_id = current_account_with_tenant()
 
-        args = parser_delete_models.parse_args()
+        args = ParserDeleteModels.model_validate(console_ns.payload)
 
         model_provider_service = ModelProviderService()
         model_provider_service.remove_model(
-            tenant_id=tenant_id, provider=provider, model=args["model"], model_type=args["model_type"]
+            tenant_id=tenant_id, provider=provider, model=args.model, model_type=args.model_type
         )
 
         return {"result": "success"}, 204
 
 
-parser_get_credentials = (
-    reqparse.RequestParser()
-    .add_argument("model", type=str, required=True, nullable=False, location="args")
-    .add_argument(
-        "model_type",
-        type=str,
-        required=True,
-        nullable=False,
-        choices=[mt.value for mt in ModelType],
-        location="args",
-    )
-    .add_argument("config_from", type=str, required=False, nullable=True, location="args")
-    .add_argument("credential_id", type=uuid_value, required=False, nullable=True, location="args")
-)
-
-
-parser_post_cred = (
-    reqparse.RequestParser()
-    .add_argument("model", type=str, required=True, nullable=False, location="json")
-    .add_argument(
-        "model_type",
-        type=str,
-        required=True,
-        nullable=False,
-        choices=[mt.value for mt in ModelType],
-        location="json",
-    )
-    .add_argument("name", type=StrLen(30), required=False, nullable=True, location="json")
-    .add_argument("credentials", type=dict, required=True, nullable=False, location="json")
-)
-parser_put_cred = (
-    reqparse.RequestParser()
-    .add_argument("model", type=str, required=True, nullable=False, location="json")
-    .add_argument(
-        "model_type",
-        type=str,
-        required=True,
-        nullable=False,
-        choices=[mt.value for mt in ModelType],
-        location="json",
-    )
-    .add_argument("credential_id", type=uuid_value, required=True, nullable=False, location="json")
-    .add_argument("credentials", type=dict, required=True, nullable=False, location="json")
-    .add_argument("name", type=StrLen(30), required=False, nullable=True, location="json")
-)
-parser_delete_cred = (
-    reqparse.RequestParser()
-    .add_argument("model", type=str, required=True, nullable=False, location="json")
-    .add_argument(
-        "model_type",
-        type=str,
-        required=True,
-        nullable=False,
-        choices=[mt.value for mt in ModelType],
-        location="json",
-    )
-    .add_argument("credential_id", type=uuid_value, required=True, nullable=False, location="json")
-)
-
-
 @console_ns.route("/workspaces/current/model-providers/<path:provider>/models/credentials")
 class ModelProviderModelCredentialApi(Resource):
-    @console_ns.expect(parser_get_credentials)
+    @console_ns.expect(console_ns.models[ParserGetCredentials.__name__])
     @setup_required
     @login_required
     @account_initialization_required
     def get(self, provider: str):
         _, tenant_id = current_account_with_tenant()
 
-        args = parser_get_credentials.parse_args()
+        args = ParserGetCredentials.model_validate(request.args.to_dict(flat=True))  # type: ignore
 
         model_provider_service = ModelProviderService()
         current_credential = model_provider_service.get_model_credential(
             tenant_id=tenant_id,
             provider=provider,
-            model_type=args["model_type"],
-            model=args["model"],
-            credential_id=args.get("credential_id"),
+            model_type=args.model_type,
+            model=args.model,
+            credential_id=args.credential_id,
         )
 
         model_load_balancing_service = ModelLoadBalancingService()
         is_load_balancing_enabled, load_balancing_configs = model_load_balancing_service.get_load_balancing_configs(
             tenant_id=tenant_id,
             provider=provider,
-            model=args["model"],
-            model_type=args["model_type"],
-            config_from=args.get("config_from", ""),
+            model=args.model,
+            model_type=args.model_type,
+            config_from=args.config_from or "",
         )
 
-        if args.get("config_from", "") == "predefined-model":
+        if args.config_from == "predefined-model":
             available_credentials = model_provider_service.provider_manager.get_provider_available_credentials(
                 tenant_id=tenant_id, provider_name=provider
             )
         else:
-            model_type = ModelType.value_of(args["model_type"]).to_origin_model_type()
+            model_type = args.model_type
             available_credentials = model_provider_service.provider_manager.get_provider_model_available_credentials(
-                tenant_id=tenant_id, provider_name=provider, model_type=model_type, model_name=args["model"]
+                tenant_id=tenant_id, provider_name=provider, model_type=model_type, model_name=args.model
             )
 
         return jsonable_encoder(
@@ -304,7 +329,7 @@ class ModelProviderModelCredentialApi(Resource):
             }
         )
 
-    @console_ns.expect(parser_post_cred)
+    @console_ns.expect(console_ns.models[ParserCreateCredential.__name__])
     @setup_required
     @login_required
     @is_admin_or_owner_required
@@ -312,7 +337,7 @@ class ModelProviderModelCredentialApi(Resource):
     def post(self, provider: str):
         _, tenant_id = current_account_with_tenant()
 
-        args = parser_post_cred.parse_args()
+        args = ParserCreateCredential.model_validate(console_ns.payload)
 
         model_provider_service = ModelProviderService()
 
@@ -320,30 +345,30 @@ class ModelProviderModelCredentialApi(Resource):
             model_provider_service.create_model_credential(
                 tenant_id=tenant_id,
                 provider=provider,
-                model=args["model"],
-                model_type=args["model_type"],
-                credentials=args["credentials"],
-                credential_name=args["name"],
+                model=args.model,
+                model_type=args.model_type,
+                credentials=args.credentials,
+                credential_name=args.name,
             )
         except CredentialsValidateFailedError as ex:
             logger.exception(
                 "Failed to save model credentials, tenant_id: %s, model: %s, model_type: %s",
                 tenant_id,
-                args.get("model"),
-                args.get("model_type"),
+                args.model,
+                args.model_type,
             )
             raise ValueError(str(ex))
 
         return {"result": "success"}, 201
 
-    @console_ns.expect(parser_put_cred)
+    @console_ns.expect(console_ns.models[ParserUpdateCredential.__name__])
     @setup_required
     @login_required
     @is_admin_or_owner_required
     @account_initialization_required
     def put(self, provider: str):
         _, current_tenant_id = current_account_with_tenant()
-        args = parser_put_cred.parse_args()
+        args = ParserUpdateCredential.model_validate(console_ns.payload)
 
         model_provider_service = ModelProviderService()
 
@@ -351,106 +376,87 @@ class ModelProviderModelCredentialApi(Resource):
             model_provider_service.update_model_credential(
                 tenant_id=current_tenant_id,
                 provider=provider,
-                model_type=args["model_type"],
-                model=args["model"],
-                credentials=args["credentials"],
-                credential_id=args["credential_id"],
-                credential_name=args["name"],
+                model_type=args.model_type,
+                model=args.model,
+                credentials=args.credentials,
+                credential_id=args.credential_id,
+                credential_name=args.name,
             )
         except CredentialsValidateFailedError as ex:
             raise ValueError(str(ex))
 
         return {"result": "success"}
 
-    @console_ns.expect(parser_delete_cred)
+    @console_ns.expect(console_ns.models[ParserDeleteCredential.__name__])
     @setup_required
     @login_required
     @is_admin_or_owner_required
     @account_initialization_required
     def delete(self, provider: str):
         _, current_tenant_id = current_account_with_tenant()
-        args = parser_delete_cred.parse_args()
+        args = ParserDeleteCredential.model_validate(console_ns.payload)
 
         model_provider_service = ModelProviderService()
         model_provider_service.remove_model_credential(
             tenant_id=current_tenant_id,
             provider=provider,
-            model_type=args["model_type"],
-            model=args["model"],
-            credential_id=args["credential_id"],
+            model_type=args.model_type,
+            model=args.model,
+            credential_id=args.credential_id,
         )
 
         return {"result": "success"}, 204
 
 
-parser_switch = (
-    reqparse.RequestParser()
-    .add_argument("model", type=str, required=True, nullable=False, location="json")
-    .add_argument(
-        "model_type",
-        type=str,
-        required=True,
-        nullable=False,
-        choices=[mt.value for mt in ModelType],
-        location="json",
-    )
-    .add_argument("credential_id", type=str, required=True, nullable=False, location="json")
+class ParserSwitch(BaseModel):
+    model: str
+    model_type: ModelType
+    credential_id: str
+
+
+console_ns.schema_model(
+    ParserSwitch.__name__, ParserSwitch.model_json_schema(ref_template=DEFAULT_REF_TEMPLATE_SWAGGER_2_0)
 )
 
 
 @console_ns.route("/workspaces/current/model-providers/<path:provider>/models/credentials/switch")
 class ModelProviderModelCredentialSwitchApi(Resource):
-    @console_ns.expect(parser_switch)
+    @console_ns.expect(console_ns.models[ParserSwitch.__name__])
     @setup_required
     @login_required
     @is_admin_or_owner_required
     @account_initialization_required
     def post(self, provider: str):
         _, current_tenant_id = current_account_with_tenant()
-
-        args = parser_switch.parse_args()
+        args = ParserSwitch.model_validate(console_ns.payload)
 
         service = ModelProviderService()
         service.add_model_credential_to_model_list(
             tenant_id=current_tenant_id,
             provider=provider,
-            model_type=args["model_type"],
-            model=args["model"],
-            credential_id=args["credential_id"],
+            model_type=args.model_type,
+            model=args.model,
+            credential_id=args.credential_id,
         )
         return {"result": "success"}
 
 
-parser_model_enable_disable = (
-    reqparse.RequestParser()
-    .add_argument("model", type=str, required=True, nullable=False, location="json")
-    .add_argument(
-        "model_type",
-        type=str,
-        required=True,
-        nullable=False,
-        choices=[mt.value for mt in ModelType],
-        location="json",
-    )
-)
-
-
 @console_ns.route(
     "/workspaces/current/model-providers/<path:provider>/models/enable", endpoint="model-provider-model-enable"
 )
 class ModelProviderModelEnableApi(Resource):
-    @console_ns.expect(parser_model_enable_disable)
+    @console_ns.expect(console_ns.models[ParserDeleteModels.__name__])
     @setup_required
     @login_required
     @account_initialization_required
     def patch(self, provider: str):
         _, tenant_id = current_account_with_tenant()
 
-        args = parser_model_enable_disable.parse_args()
+        args = ParserDeleteModels.model_validate(console_ns.payload)
 
         model_provider_service = ModelProviderService()
         model_provider_service.enable_model(
-            tenant_id=tenant_id, provider=provider, model=args["model"], model_type=args["model_type"]
+            tenant_id=tenant_id, provider=provider, model=args.model, model_type=args.model_type
         )
 
         return {"result": "success"}
@@ -460,48 +466,43 @@ class ModelProviderModelEnableApi(Resource):
     "/workspaces/current/model-providers/<path:provider>/models/disable", endpoint="model-provider-model-disable"
 )
 class ModelProviderModelDisableApi(Resource):
-    @console_ns.expect(parser_model_enable_disable)
+    @console_ns.expect(console_ns.models[ParserDeleteModels.__name__])
     @setup_required
     @login_required
     @account_initialization_required
     def patch(self, provider: str):
         _, tenant_id = current_account_with_tenant()
 
-        args = parser_model_enable_disable.parse_args()
+        args = ParserDeleteModels.model_validate(console_ns.payload)
 
         model_provider_service = ModelProviderService()
         model_provider_service.disable_model(
-            tenant_id=tenant_id, provider=provider, model=args["model"], model_type=args["model_type"]
+            tenant_id=tenant_id, provider=provider, model=args.model, model_type=args.model_type
         )
 
         return {"result": "success"}
 
 
-parser_validate = (
-    reqparse.RequestParser()
-    .add_argument("model", type=str, required=True, nullable=False, location="json")
-    .add_argument(
-        "model_type",
-        type=str,
-        required=True,
-        nullable=False,
-        choices=[mt.value for mt in ModelType],
-        location="json",
-    )
-    .add_argument("credentials", type=dict, required=True, nullable=False, location="json")
+class ParserValidate(BaseModel):
+    model: str
+    model_type: ModelType
+    credentials: dict
+
+
+console_ns.schema_model(
+    ParserValidate.__name__, ParserValidate.model_json_schema(ref_template=DEFAULT_REF_TEMPLATE_SWAGGER_2_0)
 )
 
 
 @console_ns.route("/workspaces/current/model-providers/<path:provider>/models/credentials/validate")
 class ModelProviderModelValidateApi(Resource):
-    @console_ns.expect(parser_validate)
+    @console_ns.expect(console_ns.models[ParserValidate.__name__])
     @setup_required
     @login_required
     @account_initialization_required
     def post(self, provider: str):
         _, tenant_id = current_account_with_tenant()
-
-        args = parser_validate.parse_args()
+        args = ParserValidate.model_validate(console_ns.payload)
 
         model_provider_service = ModelProviderService()
 
@@ -512,9 +513,9 @@ class ModelProviderModelValidateApi(Resource):
             model_provider_service.validate_model_credentials(
                 tenant_id=tenant_id,
                 provider=provider,
-                model=args["model"],
-                model_type=args["model_type"],
-                credentials=args["credentials"],
+                model=args.model,
+                model_type=args.model_type,
+                credentials=args.credentials,
             )
         except CredentialsValidateFailedError as ex:
             result = False
@@ -528,24 +529,19 @@ class ModelProviderModelValidateApi(Resource):
         return response
 
 
-parser_parameter = reqparse.RequestParser().add_argument(
-    "model", type=str, required=True, nullable=False, location="args"
-)
-
-
 @console_ns.route("/workspaces/current/model-providers/<path:provider>/models/parameter-rules")
 class ModelProviderModelParameterRuleApi(Resource):
-    @console_ns.expect(parser_parameter)
+    @console_ns.expect(console_ns.models[ParserParameter.__name__])
     @setup_required
     @login_required
     @account_initialization_required
     def get(self, provider: str):
-        args = parser_parameter.parse_args()
+        args = ParserParameter.model_validate(request.args.to_dict(flat=True))  # type: ignore
         _, tenant_id = current_account_with_tenant()
 
         model_provider_service = ModelProviderService()
         parameter_rules = model_provider_service.get_model_parameter_rules(
-            tenant_id=tenant_id, provider=provider, model=args["model"]
+            tenant_id=tenant_id, provider=provider, model=args.model
         )
 
         return jsonable_encoder({"data": parameter_rules})

api/controllers/console/workspace/plugin.py

@@ -1,7 +1,9 @@
 import io
+from typing import Literal
 
 from flask import request, send_file
-from flask_restx import Resource, reqparse
+from flask_restx import Resource
+from pydantic import BaseModel, Field
 from werkzeug.exceptions import Forbidden
 
 from configs import dify_config
@@ -17,6 +19,8 @@ from services.plugin.plugin_parameter_service import PluginParameterService
 from services.plugin.plugin_permission_service import PluginPermissionService
 from services.plugin.plugin_service import PluginService
 
+DEFAULT_REF_TEMPLATE_SWAGGER_2_0 = "#/definitions/{model}"
+
 
 @console_ns.route("/workspaces/current/plugin/debugging-key")
 class PluginDebuggingKeyApi(Resource):
@@ -37,88 +41,251 @@ class PluginDebuggingKeyApi(Resource):
             raise ValueError(e)
 
 
-parser_list = (
-    reqparse.RequestParser()
-    .add_argument("page", type=int, required=False, location="args", default=1)
-    .add_argument("page_size", type=int, required=False, location="args", default=256)
+class ParserList(BaseModel):
+    page: int = Field(default=1)
+    page_size: int = Field(default=256)
+
+
+console_ns.schema_model(
+    ParserList.__name__, ParserList.model_json_schema(ref_template=DEFAULT_REF_TEMPLATE_SWAGGER_2_0)
 )
 
 
 @console_ns.route("/workspaces/current/plugin/list")
 class PluginListApi(Resource):
-    @console_ns.expect(parser_list)
+    @console_ns.expect(console_ns.models[ParserList.__name__])
     @setup_required
     @login_required
     @account_initialization_required
     def get(self):
         _, tenant_id = current_account_with_tenant()
-        args = parser_list.parse_args()
+        args = ParserList.model_validate(request.args.to_dict(flat=True))  # type: ignore
         try:
-            plugins_with_total = PluginService.list_with_total(tenant_id, args["page"], args["page_size"])
+            plugins_with_total = PluginService.list_with_total(tenant_id, args.page, args.page_size)
         except PluginDaemonClientSideError as e:
             raise ValueError(e)
 
         return jsonable_encoder({"plugins": plugins_with_total.list, "total": plugins_with_total.total})
 
 
-parser_latest = reqparse.RequestParser().add_argument("plugin_ids", type=list, required=True, location="json")
+class ParserLatest(BaseModel):
+    plugin_ids: list[str]
+
+
+console_ns.schema_model(
+    ParserLatest.__name__, ParserLatest.model_json_schema(ref_template=DEFAULT_REF_TEMPLATE_SWAGGER_2_0)
+)
+
+
+class ParserIcon(BaseModel):
+    tenant_id: str
+    filename: str
+
+
+class ParserAsset(BaseModel):
+    plugin_unique_identifier: str
+    file_name: str
+
+
+class ParserGithubUpload(BaseModel):
+    repo: str
+    version: str
+    package: str
+
+
+class ParserPluginIdentifiers(BaseModel):
+    plugin_unique_identifiers: list[str]
+
+
+class ParserGithubInstall(BaseModel):
+    plugin_unique_identifier: str
+    repo: str
+    version: str
+    package: str
+
+
+class ParserPluginIdentifierQuery(BaseModel):
+    plugin_unique_identifier: str
+
+
+class ParserTasks(BaseModel):
+    page: int
+    page_size: int
+
+
+class ParserMarketplaceUpgrade(BaseModel):
+    original_plugin_unique_identifier: str
+    new_plugin_unique_identifier: str
+
+
+class ParserGithubUpgrade(BaseModel):
+    original_plugin_unique_identifier: str
+    new_plugin_unique_identifier: str
+    repo: str
+    version: str
+    package: str
+
+
+class ParserUninstall(BaseModel):
+    plugin_installation_id: str
+
+
+class ParserPermissionChange(BaseModel):
+    install_permission: TenantPluginPermission.InstallPermission
+    debug_permission: TenantPluginPermission.DebugPermission
+
+
+class ParserDynamicOptions(BaseModel):
+    plugin_id: str
+    provider: str
+    action: str
+    parameter: str
+    credential_id: str | None = None
+    provider_type: Literal["tool", "trigger"]
+
+
+class PluginPermissionSettingsPayload(BaseModel):
+    install_permission: TenantPluginPermission.InstallPermission = TenantPluginPermission.InstallPermission.EVERYONE
+    debug_permission: TenantPluginPermission.DebugPermission = TenantPluginPermission.DebugPermission.EVERYONE
+
+
+class PluginAutoUpgradeSettingsPayload(BaseModel):
+    strategy_setting: TenantPluginAutoUpgradeStrategy.StrategySetting = (
+        TenantPluginAutoUpgradeStrategy.StrategySetting.FIX_ONLY
+    )
+    upgrade_time_of_day: int = 0
+    upgrade_mode: TenantPluginAutoUpgradeStrategy.UpgradeMode = TenantPluginAutoUpgradeStrategy.UpgradeMode.EXCLUDE
+    exclude_plugins: list[str] = Field(default_factory=list)
+    include_plugins: list[str] = Field(default_factory=list)
+
+
+class ParserPreferencesChange(BaseModel):
+    permission: PluginPermissionSettingsPayload
+    auto_upgrade: PluginAutoUpgradeSettingsPayload
+
+
+class ParserExcludePlugin(BaseModel):
+    plugin_id: str
+
+
+class ParserReadme(BaseModel):
+    plugin_unique_identifier: str
+    language: str = Field(default="en-US")
+
+
+console_ns.schema_model(
+    ParserIcon.__name__, ParserIcon.model_json_schema(ref_template=DEFAULT_REF_TEMPLATE_SWAGGER_2_0)
+)
+
+console_ns.schema_model(
+    ParserAsset.__name__, ParserAsset.model_json_schema(ref_template=DEFAULT_REF_TEMPLATE_SWAGGER_2_0)
+)
+
+console_ns.schema_model(
+    ParserGithubUpload.__name__, ParserGithubUpload.model_json_schema(ref_template=DEFAULT_REF_TEMPLATE_SWAGGER_2_0)
+)
+
+console_ns.schema_model(
+    ParserPluginIdentifiers.__name__,
+    ParserPluginIdentifiers.model_json_schema(ref_template=DEFAULT_REF_TEMPLATE_SWAGGER_2_0),
+)
+
+console_ns.schema_model(
+    ParserGithubInstall.__name__, ParserGithubInstall.model_json_schema(ref_template=DEFAULT_REF_TEMPLATE_SWAGGER_2_0)
+)
+
+console_ns.schema_model(
+    ParserPluginIdentifierQuery.__name__,
+    ParserPluginIdentifierQuery.model_json_schema(ref_template=DEFAULT_REF_TEMPLATE_SWAGGER_2_0),
+)
+
+console_ns.schema_model(
+    ParserTasks.__name__, ParserTasks.model_json_schema(ref_template=DEFAULT_REF_TEMPLATE_SWAGGER_2_0)
+)
+
+console_ns.schema_model(
+    ParserMarketplaceUpgrade.__name__,
+    ParserMarketplaceUpgrade.model_json_schema(ref_template=DEFAULT_REF_TEMPLATE_SWAGGER_2_0),
+)
+
+console_ns.schema_model(
+    ParserGithubUpgrade.__name__, ParserGithubUpgrade.model_json_schema(ref_template=DEFAULT_REF_TEMPLATE_SWAGGER_2_0)
+)
+
+console_ns.schema_model(
+    ParserUninstall.__name__, ParserUninstall.model_json_schema(ref_template=DEFAULT_REF_TEMPLATE_SWAGGER_2_0)
+)
+
+console_ns.schema_model(
+    ParserPermissionChange.__name__,
+    ParserPermissionChange.model_json_schema(ref_template=DEFAULT_REF_TEMPLATE_SWAGGER_2_0),
+)
+
+console_ns.schema_model(
+    ParserDynamicOptions.__name__,
+    ParserDynamicOptions.model_json_schema(ref_template=DEFAULT_REF_TEMPLATE_SWAGGER_2_0),
+)
+
+console_ns.schema_model(
+    ParserPreferencesChange.__name__,
+    ParserPreferencesChange.model_json_schema(ref_template=DEFAULT_REF_TEMPLATE_SWAGGER_2_0),
+)
+
+console_ns.schema_model(
+    ParserExcludePlugin.__name__,
+    ParserExcludePlugin.model_json_schema(ref_template=DEFAULT_REF_TEMPLATE_SWAGGER_2_0),
+)
+
+console_ns.schema_model(
+    ParserReadme.__name__, ParserReadme.model_json_schema(ref_template=DEFAULT_REF_TEMPLATE_SWAGGER_2_0)
+)
 
 
 @console_ns.route("/workspaces/current/plugin/list/latest-versions")
 class PluginListLatestVersionsApi(Resource):
-    @console_ns.expect(parser_latest)
+    @console_ns.expect(console_ns.models[ParserLatest.__name__])
     @setup_required
     @login_required
     @account_initialization_required
     def post(self):
-        args = parser_latest.parse_args()
+        args = ParserLatest.model_validate(console_ns.payload)
 
         try:
-            versions = PluginService.list_latest_versions(args["plugin_ids"])
+            versions = PluginService.list_latest_versions(args.plugin_ids)
         except PluginDaemonClientSideError as e:
             raise ValueError(e)
 
         return jsonable_encoder({"versions": versions})
 
 
-parser_ids = reqparse.RequestParser().add_argument("plugin_ids", type=list, required=True, location="json")
-
-
 @console_ns.route("/workspaces/current/plugin/list/installations/ids")
 class PluginListInstallationsFromIdsApi(Resource):
-    @console_ns.expect(parser_ids)
+    @console_ns.expect(console_ns.models[ParserLatest.__name__])
     @setup_required
     @login_required
     @account_initialization_required
     def post(self):
         _, tenant_id = current_account_with_tenant()
 
-        args = parser_ids.parse_args()
+        args = ParserLatest.model_validate(console_ns.payload)
 
         try:
-            plugins = PluginService.list_installations_from_ids(tenant_id, args["plugin_ids"])
+            plugins = PluginService.list_installations_from_ids(tenant_id, args.plugin_ids)
         except PluginDaemonClientSideError as e:
             raise ValueError(e)
 
         return jsonable_encoder({"plugins": plugins})
 
 
-parser_icon = (
-    reqparse.RequestParser()
-    .add_argument("tenant_id", type=str, required=True, location="args")
-    .add_argument("filename", type=str, required=True, location="args")
-)
-
-
 @console_ns.route("/workspaces/current/plugin/icon")
 class PluginIconApi(Resource):
-    @console_ns.expect(parser_icon)
+    @console_ns.expect(console_ns.models[ParserIcon.__name__])
     @setup_required
     def get(self):
-        args = parser_icon.parse_args()
+        args = ParserIcon.model_validate(request.args.to_dict(flat=True))  # type: ignore
 
         try:
-            icon_bytes, mimetype = PluginService.get_asset(args["tenant_id"], args["filename"])
+            icon_bytes, mimetype = PluginService.get_asset(args.tenant_id, args.filename)
         except PluginDaemonClientSideError as e:
             raise ValueError(e)
 
@@ -128,20 +295,16 @@ class PluginIconApi(Resource):
 
 @console_ns.route("/workspaces/current/plugin/asset")
 class PluginAssetApi(Resource):
+    @console_ns.expect(console_ns.models[ParserAsset.__name__])
     @setup_required
     @login_required
     @account_initialization_required
     def get(self):
-        req = (
-            reqparse.RequestParser()
-            .add_argument("plugin_unique_identifier", type=str, required=True, location="args")
-            .add_argument("file_name", type=str, required=True, location="args")
-        )
-        args = req.parse_args()
+        args = ParserAsset.model_validate(request.args.to_dict(flat=True))  # type: ignore
 
         _, tenant_id = current_account_with_tenant()
         try:
-            binary = PluginService.extract_asset(tenant_id, args["plugin_unique_identifier"], args["file_name"])
+            binary = PluginService.extract_asset(tenant_id, args.plugin_unique_identifier, args.file_name)
             return send_file(io.BytesIO(binary), mimetype="application/octet-stream")
         except PluginDaemonClientSideError as e:
             raise ValueError(e)
@@ -171,17 +334,9 @@ class PluginUploadFromPkgApi(Resource):
         return jsonable_encoder(response)
 
 
-parser_github = (
-    reqparse.RequestParser()
-    .add_argument("repo", type=str, required=True, location="json")
-    .add_argument("version", type=str, required=True, location="json")
-    .add_argument("package", type=str, required=True, location="json")
-)
-
-
 @console_ns.route("/workspaces/current/plugin/upload/github")
 class PluginUploadFromGithubApi(Resource):
-    @console_ns.expect(parser_github)
+    @console_ns.expect(console_ns.models[ParserGithubUpload.__name__])
     @setup_required
     @login_required
     @account_initialization_required
@@ -189,10 +344,10 @@ class PluginUploadFromGithubApi(Resource):
     def post(self):
         _, tenant_id = current_account_with_tenant()
 
-        args = parser_github.parse_args()
+        args = ParserGithubUpload.model_validate(console_ns.payload)
 
         try:
-            response = PluginService.upload_pkg_from_github(tenant_id, args["repo"], args["version"], args["package"])
+            response = PluginService.upload_pkg_from_github(tenant_id, args.repo, args.version, args.package)
         except PluginDaemonClientSideError as e:
             raise ValueError(e)
 
@@ -223,47 +378,28 @@ class PluginUploadFromBundleApi(Resource):
         return jsonable_encoder(response)
 
 
-parser_pkg = reqparse.RequestParser().add_argument(
-    "plugin_unique_identifiers", type=list, required=True, location="json"
-)
-
-
 @console_ns.route("/workspaces/current/plugin/install/pkg")
 class PluginInstallFromPkgApi(Resource):
-    @console_ns.expect(parser_pkg)
+    @console_ns.expect(console_ns.models[ParserPluginIdentifiers.__name__])
     @setup_required
     @login_required
     @account_initialization_required
     @plugin_permission_required(install_required=True)
     def post(self):
         _, tenant_id = current_account_with_tenant()
-        args = parser_pkg.parse_args()
-
-        # check if all plugin_unique_identifiers are valid string
-        for plugin_unique_identifier in args["plugin_unique_identifiers"]:
-            if not isinstance(plugin_unique_identifier, str):
-                raise ValueError("Invalid plugin unique identifier")
+        args = ParserPluginIdentifiers.model_validate(console_ns.payload)
 
         try:
-            response = PluginService.install_from_local_pkg(tenant_id, args["plugin_unique_identifiers"])
+            response = PluginService.install_from_local_pkg(tenant_id, args.plugin_unique_identifiers)
         except PluginDaemonClientSideError as e:
             raise ValueError(e)
 
         return jsonable_encoder(response)
 
 
-parser_githubapi = (
-    reqparse.RequestParser()
-    .add_argument("repo", type=str, required=True, location="json")
-    .add_argument("version", type=str, required=True, location="json")
-    .add_argument("package", type=str, required=True, location="json")
-    .add_argument("plugin_unique_identifier", type=str, required=True, location="json")
-)
-
-
 @console_ns.route("/workspaces/current/plugin/install/github")
 class PluginInstallFromGithubApi(Resource):
-    @console_ns.expect(parser_githubapi)
+    @console_ns.expect(console_ns.models[ParserGithubInstall.__name__])
     @setup_required
     @login_required
     @account_initialization_required
@@ -271,15 +407,15 @@ class PluginInstallFromGithubApi(Resource):
     def post(self):
         _, tenant_id = current_account_with_tenant()
 
-        args = parser_githubapi.parse_args()
+        args = ParserGithubInstall.model_validate(console_ns.payload)
 
         try:
             response = PluginService.install_from_github(
                 tenant_id,
-                args["plugin_unique_identifier"],
-                args["repo"],
-                args["version"],
-                args["package"],
+                args.plugin_unique_identifier,
+                args.repo,
+                args.version,
+                args.package,
             )
         except PluginDaemonClientSideError as e:
             raise ValueError(e)
@@ -287,14 +423,9 @@ class PluginInstallFromGithubApi(Resource):
         return jsonable_encoder(response)
 
 
-parser_marketplace = reqparse.RequestParser().add_argument(
-    "plugin_unique_identifiers", type=list, required=True, location="json"
-)
-
-
 @console_ns.route("/workspaces/current/plugin/install/marketplace")
 class PluginInstallFromMarketplaceApi(Resource):
-    @console_ns.expect(parser_marketplace)
+    @console_ns.expect(console_ns.models[ParserPluginIdentifiers.__name__])
     @setup_required
     @login_required
     @account_initialization_required
@@ -302,43 +433,33 @@ class PluginInstallFromMarketplaceApi(Resource):
     def post(self):
         _, tenant_id = current_account_with_tenant()
 
-        args = parser_marketplace.parse_args()
-
-        # check if all plugin_unique_identifiers are valid string
-        for plugin_unique_identifier in args["plugin_unique_identifiers"]:
-            if not isinstance(plugin_unique_identifier, str):
-                raise ValueError("Invalid plugin unique identifier")
+        args = ParserPluginIdentifiers.model_validate(console_ns.payload)
 
         try:
-            response = PluginService.install_from_marketplace_pkg(tenant_id, args["plugin_unique_identifiers"])
+            response = PluginService.install_from_marketplace_pkg(tenant_id, args.plugin_unique_identifiers)
         except PluginDaemonClientSideError as e:
             raise ValueError(e)
 
         return jsonable_encoder(response)
 
 
-parser_pkgapi = reqparse.RequestParser().add_argument(
-    "plugin_unique_identifier", type=str, required=True, location="args"
-)
-
-
 @console_ns.route("/workspaces/current/plugin/marketplace/pkg")
 class PluginFetchMarketplacePkgApi(Resource):
-    @console_ns.expect(parser_pkgapi)
+    @console_ns.expect(console_ns.models[ParserPluginIdentifierQuery.__name__])
     @setup_required
     @login_required
     @account_initialization_required
     @plugin_permission_required(install_required=True)
     def get(self):
         _, tenant_id = current_account_with_tenant()
-        args = parser_pkgapi.parse_args()
+        args = ParserPluginIdentifierQuery.model_validate(request.args.to_dict(flat=True))  # type: ignore
 
         try:
             return jsonable_encoder(
                 {
                     "manifest": PluginService.fetch_marketplace_pkg(
                         tenant_id,
-                        args["plugin_unique_identifier"],
+                        args.plugin_unique_identifier,
                     )
                 }
             )
@@ -346,14 +467,9 @@ class PluginFetchMarketplacePkgApi(Resource):
             raise ValueError(e)
 
 
-parser_fetch = reqparse.RequestParser().add_argument(
-    "plugin_unique_identifier", type=str, required=True, location="args"
-)
-
-
 @console_ns.route("/workspaces/current/plugin/fetch-manifest")
 class PluginFetchManifestApi(Resource):
-    @console_ns.expect(parser_fetch)
+    @console_ns.expect(console_ns.models[ParserPluginIdentifierQuery.__name__])
     @setup_required
     @login_required
     @account_initialization_required
@@ -361,30 +477,19 @@ class PluginFetchManifestApi(Resource):
     def get(self):
         _, tenant_id = current_account_with_tenant()
 
-        args = parser_fetch.parse_args()
+        args = ParserPluginIdentifierQuery.model_validate(request.args.to_dict(flat=True))  # type: ignore
 
         try:
             return jsonable_encoder(
-                {
-                    "manifest": PluginService.fetch_plugin_manifest(
-                        tenant_id, args["plugin_unique_identifier"]
-                    ).model_dump()
-                }
+                {"manifest": PluginService.fetch_plugin_manifest(tenant_id, args.plugin_unique_identifier).model_dump()}
             )
         except PluginDaemonClientSideError as e:
             raise ValueError(e)
 
 
-parser_tasks = (
-    reqparse.RequestParser()
-    .add_argument("page", type=int, required=True, location="args")
-    .add_argument("page_size", type=int, required=True, location="args")
-)
-
-
 @console_ns.route("/workspaces/current/plugin/tasks")
 class PluginFetchInstallTasksApi(Resource):
-    @console_ns.expect(parser_tasks)
+    @console_ns.expect(console_ns.models[ParserTasks.__name__])
     @setup_required
     @login_required
     @account_initialization_required
@@ -392,12 +497,10 @@ class PluginFetchInstallTasksApi(Resource):
     def get(self):
         _, tenant_id = current_account_with_tenant()
 
-        args = parser_tasks.parse_args()
+        args = ParserTasks.model_validate(request.args.to_dict(flat=True))  # type: ignore
 
         try:
-            return jsonable_encoder(
-                {"tasks": PluginService.fetch_install_tasks(tenant_id, args["page"], args["page_size"])}
-            )
+            return jsonable_encoder({"tasks": PluginService.fetch_install_tasks(tenant_id, args.page, args.page_size)})
         except PluginDaemonClientSideError as e:
             raise ValueError(e)
 
@@ -462,16 +565,9 @@ class PluginDeleteInstallTaskItemApi(Resource):
             raise ValueError(e)
 
 
-parser_marketplace_api = (
-    reqparse.RequestParser()
-    .add_argument("original_plugin_unique_identifier", type=str, required=True, location="json")
-    .add_argument("new_plugin_unique_identifier", type=str, required=True, location="json")
-)
-
-
 @console_ns.route("/workspaces/current/plugin/upgrade/marketplace")
 class PluginUpgradeFromMarketplaceApi(Resource):
-    @console_ns.expect(parser_marketplace_api)
+    @console_ns.expect(console_ns.models[ParserMarketplaceUpgrade.__name__])
     @setup_required
     @login_required
     @account_initialization_required
@@ -479,31 +575,21 @@ class PluginUpgradeFromMarketplaceApi(Resource):
     def post(self):
         _, tenant_id = current_account_with_tenant()
 
-        args = parser_marketplace_api.parse_args()
+        args = ParserMarketplaceUpgrade.model_validate(console_ns.payload)
 
         try:
             return jsonable_encoder(
                 PluginService.upgrade_plugin_with_marketplace(
-                    tenant_id, args["original_plugin_unique_identifier"], args["new_plugin_unique_identifier"]
+                    tenant_id, args.original_plugin_unique_identifier, args.new_plugin_unique_identifier
                 )
             )
         except PluginDaemonClientSideError as e:
             raise ValueError(e)
 
 
-parser_github_post = (
-    reqparse.RequestParser()
-    .add_argument("original_plugin_unique_identifier", type=str, required=True, location="json")
-    .add_argument("new_plugin_unique_identifier", type=str, required=True, location="json")
-    .add_argument("repo", type=str, required=True, location="json")
-    .add_argument("version", type=str, required=True, location="json")
-    .add_argument("package", type=str, required=True, location="json")
-)
-
-
 @console_ns.route("/workspaces/current/plugin/upgrade/github")
 class PluginUpgradeFromGithubApi(Resource):
-    @console_ns.expect(parser_github_post)
+    @console_ns.expect(console_ns.models[ParserGithubUpgrade.__name__])
     @setup_required
     @login_required
     @account_initialization_required
@@ -511,56 +597,44 @@ class PluginUpgradeFromGithubApi(Resource):
     def post(self):
         _, tenant_id = current_account_with_tenant()
 
-        args = parser_github_post.parse_args()
+        args = ParserGithubUpgrade.model_validate(console_ns.payload)
 
         try:
             return jsonable_encoder(
                 PluginService.upgrade_plugin_with_github(
                     tenant_id,
-                    args["original_plugin_unique_identifier"],
-                    args["new_plugin_unique_identifier"],
-                    args["repo"],
-                    args["version"],
-                    args["package"],
+                    args.original_plugin_unique_identifier,
+                    args.new_plugin_unique_identifier,
+                    args.repo,
+                    args.version,
+                    args.package,
                 )
             )
         except PluginDaemonClientSideError as e:
             raise ValueError(e)
 
 
-parser_uninstall = reqparse.RequestParser().add_argument(
-    "plugin_installation_id", type=str, required=True, location="json"
-)
-
-
 @console_ns.route("/workspaces/current/plugin/uninstall")
 class PluginUninstallApi(Resource):
-    @console_ns.expect(parser_uninstall)
+    @console_ns.expect(console_ns.models[ParserUninstall.__name__])
     @setup_required
     @login_required
     @account_initialization_required
     @plugin_permission_required(install_required=True)
     def post(self):
-        args = parser_uninstall.parse_args()
+        args = ParserUninstall.model_validate(console_ns.payload)
 
         _, tenant_id = current_account_with_tenant()
 
         try:
-            return {"success": PluginService.uninstall(tenant_id, args["plugin_installation_id"])}
+            return {"success": PluginService.uninstall(tenant_id, args.plugin_installation_id)}
         except PluginDaemonClientSideError as e:
             raise ValueError(e)
 
 
-parser_change_post = (
-    reqparse.RequestParser()
-    .add_argument("install_permission", type=str, required=True, location="json")
-    .add_argument("debug_permission", type=str, required=True, location="json")
-)
-
-
 @console_ns.route("/workspaces/current/plugin/permission/change")
 class PluginChangePermissionApi(Resource):
-    @console_ns.expect(parser_change_post)
+    @console_ns.expect(console_ns.models[ParserPermissionChange.__name__])
     @setup_required
     @login_required
     @account_initialization_required
@@ -570,14 +644,15 @@ class PluginChangePermissionApi(Resource):
         if not user.is_admin_or_owner:
             raise Forbidden()
 
-        args = parser_change_post.parse_args()
-
-        install_permission = TenantPluginPermission.InstallPermission(args["install_permission"])
-        debug_permission = TenantPluginPermission.DebugPermission(args["debug_permission"])
+        args = ParserPermissionChange.model_validate(console_ns.payload)
 
         tenant_id = current_tenant_id
 
-        return {"success": PluginPermissionService.change_permission(tenant_id, install_permission, debug_permission)}
+        return {
+            "success": PluginPermissionService.change_permission(
+                tenant_id, args.install_permission, args.debug_permission
+            )
+        }
 
 
 @console_ns.route("/workspaces/current/plugin/permission/fetch")
@@ -605,20 +680,9 @@ class PluginFetchPermissionApi(Resource):
         )
 
 
-parser_dynamic = (
-    reqparse.RequestParser()
-    .add_argument("plugin_id", type=str, required=True, location="args")
-    .add_argument("provider", type=str, required=True, location="args")
-    .add_argument("action", type=str, required=True, location="args")
-    .add_argument("parameter", type=str, required=True, location="args")
-    .add_argument("credential_id", type=str, required=False, location="args")
-    .add_argument("provider_type", type=str, required=True, location="args")
-)
-
-
 @console_ns.route("/workspaces/current/plugin/parameters/dynamic-options")
 class PluginFetchDynamicSelectOptionsApi(Resource):
-    @console_ns.expect(parser_dynamic)
+    @console_ns.expect(console_ns.models[ParserDynamicOptions.__name__])
     @setup_required
     @login_required
     @is_admin_or_owner_required
@@ -627,18 +691,18 @@ class PluginFetchDynamicSelectOptionsApi(Resource):
         current_user, tenant_id = current_account_with_tenant()
         user_id = current_user.id
 
-        args = parser_dynamic.parse_args()
+        args = ParserDynamicOptions.model_validate(request.args.to_dict(flat=True))  # type: ignore
 
         try:
             options = PluginParameterService.get_dynamic_select_options(
                 tenant_id=tenant_id,
                 user_id=user_id,
-                plugin_id=args["plugin_id"],
-                provider=args["provider"],
-                action=args["action"],
-                parameter=args["parameter"],
-                credential_id=args["credential_id"],
-                provider_type=args["provider_type"],
+                plugin_id=args.plugin_id,
+                provider=args.provider,
+                action=args.action,
+                parameter=args.parameter,
+                credential_id=args.credential_id,
+                provider_type=args.provider_type,
             )
         except PluginDaemonClientSideError as e:
             raise ValueError(e)
@@ -646,16 +710,9 @@ class PluginFetchDynamicSelectOptionsApi(Resource):
         return jsonable_encoder({"options": options})
 
 
-parser_change = (
-    reqparse.RequestParser()
-    .add_argument("permission", type=dict, required=True, location="json")
-    .add_argument("auto_upgrade", type=dict, required=True, location="json")
-)
-
-
 @console_ns.route("/workspaces/current/plugin/preferences/change")
 class PluginChangePreferencesApi(Resource):
-    @console_ns.expect(parser_change)
+    @console_ns.expect(console_ns.models[ParserPreferencesChange.__name__])
     @setup_required
     @login_required
     @account_initialization_required
@@ -664,22 +721,20 @@ class PluginChangePreferencesApi(Resource):
         if not user.is_admin_or_owner:
             raise Forbidden()
 
-        args = parser_change.parse_args()
+        args = ParserPreferencesChange.model_validate(console_ns.payload)
 
-        permission = args["permission"]
+        permission = args.permission
 
-        install_permission = TenantPluginPermission.InstallPermission(permission.get("install_permission", "everyone"))
-        debug_permission = TenantPluginPermission.DebugPermission(permission.get("debug_permission", "everyone"))
+        install_permission = permission.install_permission
+        debug_permission = permission.debug_permission
 
-        auto_upgrade = args["auto_upgrade"]
+        auto_upgrade = args.auto_upgrade
 
-        strategy_setting = TenantPluginAutoUpgradeStrategy.StrategySetting(
-            auto_upgrade.get("strategy_setting", "fix_only")
-        )
-        upgrade_time_of_day = auto_upgrade.get("upgrade_time_of_day", 0)
-        upgrade_mode = TenantPluginAutoUpgradeStrategy.UpgradeMode(auto_upgrade.get("upgrade_mode", "exclude"))
-        exclude_plugins = auto_upgrade.get("exclude_plugins", [])
-        include_plugins = auto_upgrade.get("include_plugins", [])
+        strategy_setting = auto_upgrade.strategy_setting
+        upgrade_time_of_day = auto_upgrade.upgrade_time_of_day
+        upgrade_mode = auto_upgrade.upgrade_mode
+        exclude_plugins = auto_upgrade.exclude_plugins
+        include_plugins = auto_upgrade.include_plugins
 
         # set permission
         set_permission_result = PluginPermissionService.change_permission(
@@ -744,12 +799,9 @@ class PluginFetchPreferencesApi(Resource):
         return jsonable_encoder({"permission": permission_dict, "auto_upgrade": auto_upgrade_dict})
 
 
-parser_exclude = reqparse.RequestParser().add_argument("plugin_id", type=str, required=True, location="json")
-
-
 @console_ns.route("/workspaces/current/plugin/preferences/autoupgrade/exclude")
 class PluginAutoUpgradeExcludePluginApi(Resource):
-    @console_ns.expect(parser_exclude)
+    @console_ns.expect(console_ns.models[ParserExcludePlugin.__name__])
     @setup_required
     @login_required
     @account_initialization_required
@@ -757,28 +809,20 @@ class PluginAutoUpgradeExcludePluginApi(Resource):
         # exclude one single plugin
         _, tenant_id = current_account_with_tenant()
 
-        args = parser_exclude.parse_args()
+        args = ParserExcludePlugin.model_validate(console_ns.payload)
 
-        return jsonable_encoder({"success": PluginAutoUpgradeService.exclude_plugin(tenant_id, args["plugin_id"])})
+        return jsonable_encoder({"success": PluginAutoUpgradeService.exclude_plugin(tenant_id, args.plugin_id)})
 
 
 @console_ns.route("/workspaces/current/plugin/readme")
 class PluginReadmeApi(Resource):
+    @console_ns.expect(console_ns.models[ParserReadme.__name__])
     @setup_required
     @login_required
     @account_initialization_required
     def get(self):
         _, tenant_id = current_account_with_tenant()
-        parser = (
-            reqparse.RequestParser()
-            .add_argument("plugin_unique_identifier", type=str, required=True, location="args")
-            .add_argument("language", type=str, required=False, location="args")
-        )
-        args = parser.parse_args()
+        args = ParserReadme.model_validate(request.args.to_dict(flat=True))  # type: ignore
         return jsonable_encoder(
-            {
-                "readme": PluginService.fetch_plugin_readme(
-                    tenant_id, args["plugin_unique_identifier"], args.get("language", "en-US")
-                )
-            }
+            {"readme": PluginService.fetch_plugin_readme(tenant_id, args.plugin_unique_identifier, args.language)}
         )

api/controllers/console/workspace/trigger_providers.py

@@ -6,8 +6,6 @@ from sqlalchemy.orm import Session
 from werkzeug.exceptions import BadRequest, Forbidden
 
 from configs import dify_config
-from controllers.console import console_ns
-from controllers.console.wraps import account_initialization_required, is_admin_or_owner_required, setup_required
 from controllers.web.error import NotFoundError
 from core.model_runtime.utils.encoders import jsonable_encoder
 from core.plugin.entities.plugin_daemon import CredentialType
@@ -23,9 +21,13 @@ from services.trigger.trigger_provider_service import TriggerProviderService
 from services.trigger.trigger_subscription_builder_service import TriggerSubscriptionBuilderService
 from services.trigger.trigger_subscription_operator_service import TriggerSubscriptionOperatorService
 
+from .. import console_ns
+from ..wraps import account_initialization_required, is_admin_or_owner_required, setup_required
+
 logger = logging.getLogger(__name__)
 
 
+@console_ns.route("/workspaces/current/trigger-provider/<path:provider>/icon")
 class TriggerProviderIconApi(Resource):
     @setup_required
     @login_required
@@ -38,6 +40,7 @@ class TriggerProviderIconApi(Resource):
         return TriggerManager.get_trigger_plugin_icon(tenant_id=user.current_tenant_id, provider_id=provider)
 
 
+@console_ns.route("/workspaces/current/triggers")
 class TriggerProviderListApi(Resource):
     @setup_required
     @login_required
@@ -50,6 +53,7 @@ class TriggerProviderListApi(Resource):
         return jsonable_encoder(TriggerProviderService.list_trigger_providers(user.current_tenant_id))
 
 
+@console_ns.route("/workspaces/current/trigger-provider/<path:provider>/info")
 class TriggerProviderInfoApi(Resource):
     @setup_required
     @login_required
@@ -64,6 +68,7 @@ class TriggerProviderInfoApi(Resource):
         )
 
 
+@console_ns.route("/workspaces/current/trigger-provider/<path:provider>/subscriptions/list")
 class TriggerSubscriptionListApi(Resource):
     @setup_required
     @login_required
@@ -87,7 +92,16 @@ class TriggerSubscriptionListApi(Resource):
             raise
 
 
+parser = reqparse.RequestParser().add_argument(
+    "credential_type", type=str, required=False, nullable=True, location="json"
+)
+
+
+@console_ns.route(
+    "/workspaces/current/trigger-provider/<path:provider>/subscriptions/builder/create",
+)
 class TriggerSubscriptionBuilderCreateApi(Resource):
+    @console_ns.expect(parser)
     @setup_required
     @login_required
     @is_admin_or_owner_required
@@ -97,9 +111,6 @@ class TriggerSubscriptionBuilderCreateApi(Resource):
         user = current_user
         assert user.current_tenant_id is not None
 
-        parser = reqparse.RequestParser().add_argument(
-            "credential_type", type=str, required=False, nullable=True, location="json"
-        )
         args = parser.parse_args()
 
         try:
@@ -116,6 +127,9 @@ class TriggerSubscriptionBuilderCreateApi(Resource):
             raise
 
 
+@console_ns.route(
+    "/workspaces/current/trigger-provider/<path:provider>/subscriptions/builder/<path:subscription_builder_id>",
+)
 class TriggerSubscriptionBuilderGetApi(Resource):
     @setup_required
     @login_required
@@ -127,7 +141,18 @@ class TriggerSubscriptionBuilderGetApi(Resource):
         )
 
 
+parser_api = (
+    reqparse.RequestParser()
+    # The credentials of the subscription builder
+    .add_argument("credentials", type=dict, required=False, nullable=True, location="json")
+)
+
+
+@console_ns.route(
+    "/workspaces/current/trigger-provider/<path:provider>/subscriptions/builder/verify/<path:subscription_builder_id>",
+)
 class TriggerSubscriptionBuilderVerifyApi(Resource):
+    @console_ns.expect(parser_api)
     @setup_required
     @login_required
     @is_admin_or_owner_required
@@ -136,12 +161,8 @@ class TriggerSubscriptionBuilderVerifyApi(Resource):
         """Verify a subscription instance for a trigger provider"""
         user = current_user
         assert user.current_tenant_id is not None
-        parser = (
-            reqparse.RequestParser()
-            # The credentials of the subscription builder
-            .add_argument("credentials", type=dict, required=False, nullable=True, location="json")
-        )
-        args = parser.parse_args()
+
+        args = parser_api.parse_args()
 
         try:
             # Use atomic update_and_verify to prevent race conditions
@@ -159,7 +180,24 @@ class TriggerSubscriptionBuilderVerifyApi(Resource):
             raise ValueError(str(e)) from e
 
 
+parser_update_api = (
+    reqparse.RequestParser()
+    # The name of the subscription builder
+    .add_argument("name", type=str, required=False, nullable=True, location="json")
+    # The parameters of the subscription builder
+    .add_argument("parameters", type=dict, required=False, nullable=True, location="json")
+    # The properties of the subscription builder
+    .add_argument("properties", type=dict, required=False, nullable=True, location="json")
+    # The credentials of the subscription builder
+    .add_argument("credentials", type=dict, required=False, nullable=True, location="json")
+)
+
+
+@console_ns.route(
+    "/workspaces/current/trigger-provider/<path:provider>/subscriptions/builder/update/<path:subscription_builder_id>",
+)
 class TriggerSubscriptionBuilderUpdateApi(Resource):
+    @console_ns.expect(parser_update_api)
     @setup_required
     @login_required
     @account_initialization_required
@@ -169,18 +207,7 @@ class TriggerSubscriptionBuilderUpdateApi(Resource):
         assert isinstance(user, Account)
         assert user.current_tenant_id is not None
 
-        parser = (
-            reqparse.RequestParser()
-            # The name of the subscription builder
-            .add_argument("name", type=str, required=False, nullable=True, location="json")
-            # The parameters of the subscription builder
-            .add_argument("parameters", type=dict, required=False, nullable=True, location="json")
-            # The properties of the subscription builder
-            .add_argument("properties", type=dict, required=False, nullable=True, location="json")
-            # The credentials of the subscription builder
-            .add_argument("credentials", type=dict, required=False, nullable=True, location="json")
-        )
-        args = parser.parse_args()
+        args = parser_update_api.parse_args()
         try:
             return jsonable_encoder(
                 TriggerSubscriptionBuilderService.update_trigger_subscription_builder(
@@ -200,6 +227,9 @@ class TriggerSubscriptionBuilderUpdateApi(Resource):
             raise
 
 
+@console_ns.route(
+    "/workspaces/current/trigger-provider/<path:provider>/subscriptions/builder/logs/<path:subscription_builder_id>",
+)
 class TriggerSubscriptionBuilderLogsApi(Resource):
     @setup_required
     @login_required
@@ -218,7 +248,11 @@ class TriggerSubscriptionBuilderLogsApi(Resource):
             raise
 
 
+@console_ns.route(
+    "/workspaces/current/trigger-provider/<path:provider>/subscriptions/builder/build/<path:subscription_builder_id>",
+)
 class TriggerSubscriptionBuilderBuildApi(Resource):
+    @console_ns.expect(parser_update_api)
     @setup_required
     @login_required
     @is_admin_or_owner_required
@@ -227,18 +261,7 @@ class TriggerSubscriptionBuilderBuildApi(Resource):
         """Build a subscription instance for a trigger provider"""
         user = current_user
         assert user.current_tenant_id is not None
-        parser = (
-            reqparse.RequestParser()
-            # The name of the subscription builder
-            .add_argument("name", type=str, required=False, nullable=True, location="json")
-            # The parameters of the subscription builder
-            .add_argument("parameters", type=dict, required=False, nullable=True, location="json")
-            # The properties of the subscription builder
-            .add_argument("properties", type=dict, required=False, nullable=True, location="json")
-            # The credentials of the subscription builder
-            .add_argument("credentials", type=dict, required=False, nullable=True, location="json")
-        )
-        args = parser.parse_args()
+        args = parser_update_api.parse_args()
         try:
             # Use atomic update_and_build to prevent race conditions
             TriggerSubscriptionBuilderService.update_and_build_builder(
@@ -258,6 +281,9 @@ class TriggerSubscriptionBuilderBuildApi(Resource):
             raise ValueError(str(e)) from e
 
 
+@console_ns.route(
+    "/workspaces/current/trigger-provider/<path:subscription_id>/subscriptions/delete",
+)
 class TriggerSubscriptionDeleteApi(Resource):
     @setup_required
     @login_required
@@ -291,6 +317,7 @@ class TriggerSubscriptionDeleteApi(Resource):
             raise
 
 
+@console_ns.route("/workspaces/current/trigger-provider/<path:provider>/subscriptions/oauth/authorize")
 class TriggerOAuthAuthorizeApi(Resource):
     @setup_required
     @login_required
@@ -374,6 +401,7 @@ class TriggerOAuthAuthorizeApi(Resource):
             raise
 
 
+@console_ns.route("/oauth/plugin/<path:provider>/trigger/callback")
 class TriggerOAuthCallbackApi(Resource):
     @setup_required
     def get(self, provider):
@@ -438,6 +466,14 @@ class TriggerOAuthCallbackApi(Resource):
         return redirect(f"{dify_config.CONSOLE_WEB_URL}/oauth-callback")
 
 
+parser_oauth_client = (
+    reqparse.RequestParser()
+    .add_argument("client_params", type=dict, required=False, nullable=True, location="json")
+    .add_argument("enabled", type=bool, required=False, nullable=True, location="json")
+)
+
+
+@console_ns.route("/workspaces/current/trigger-provider/<path:provider>/oauth/client")
 class TriggerOAuthClientManageApi(Resource):
     @setup_required
     @login_required
@@ -484,6 +520,7 @@ class TriggerOAuthClientManageApi(Resource):
             logger.exception("Error getting OAuth client", exc_info=e)
             raise
 
+    @console_ns.expect(parser_oauth_client)
     @setup_required
     @login_required
     @is_admin_or_owner_required
@@ -493,12 +530,7 @@ class TriggerOAuthClientManageApi(Resource):
         user = current_user
         assert user.current_tenant_id is not None
 
-        parser = (
-            reqparse.RequestParser()
-            .add_argument("client_params", type=dict, required=False, nullable=True, location="json")
-            .add_argument("enabled", type=bool, required=False, nullable=True, location="json")
-        )
-        args = parser.parse_args()
+        args = parser_oauth_client.parse_args()
 
         try:
             provider_id = TriggerProviderID(provider)
@@ -536,52 +568,3 @@ class TriggerOAuthClientManageApi(Resource):
         except Exception as e:
             logger.exception("Error removing OAuth client", exc_info=e)
             raise
-
-
-# Trigger Subscription
-console_ns.add_resource(TriggerProviderIconApi, "/workspaces/current/trigger-provider/<path:provider>/icon")
-console_ns.add_resource(TriggerProviderListApi, "/workspaces/current/triggers")
-console_ns.add_resource(TriggerProviderInfoApi, "/workspaces/current/trigger-provider/<path:provider>/info")
-console_ns.add_resource(
-    TriggerSubscriptionListApi, "/workspaces/current/trigger-provider/<path:provider>/subscriptions/list"
-)
-console_ns.add_resource(
-    TriggerSubscriptionDeleteApi,
-    "/workspaces/current/trigger-provider/<path:subscription_id>/subscriptions/delete",
-)
-
-# Trigger Subscription Builder
-console_ns.add_resource(
-    TriggerSubscriptionBuilderCreateApi,
-    "/workspaces/current/trigger-provider/<path:provider>/subscriptions/builder/create",
-)
-console_ns.add_resource(
-    TriggerSubscriptionBuilderGetApi,
-    "/workspaces/current/trigger-provider/<path:provider>/subscriptions/builder/<path:subscription_builder_id>",
-)
-console_ns.add_resource(
-    TriggerSubscriptionBuilderUpdateApi,
-    "/workspaces/current/trigger-provider/<path:provider>/subscriptions/builder/update/<path:subscription_builder_id>",
-)
-console_ns.add_resource(
-    TriggerSubscriptionBuilderVerifyApi,
-    "/workspaces/current/trigger-provider/<path:provider>/subscriptions/builder/verify/<path:subscription_builder_id>",
-)
-console_ns.add_resource(
-    TriggerSubscriptionBuilderBuildApi,
-    "/workspaces/current/trigger-provider/<path:provider>/subscriptions/builder/build/<path:subscription_builder_id>",
-)
-console_ns.add_resource(
-    TriggerSubscriptionBuilderLogsApi,
-    "/workspaces/current/trigger-provider/<path:provider>/subscriptions/builder/logs/<path:subscription_builder_id>",
-)
-
-
-# OAuth
-console_ns.add_resource(
-    TriggerOAuthAuthorizeApi, "/workspaces/current/trigger-provider/<path:provider>/subscriptions/oauth/authorize"
-)
-console_ns.add_resource(TriggerOAuthCallbackApi, "/oauth/plugin/<path:provider>/trigger/callback")
-console_ns.add_resource(
-    TriggerOAuthClientManageApi, "/workspaces/current/trigger-provider/<path:provider>/oauth/client"
-)

api/controllers/console/workspace/workspace.py

@@ -1,7 +1,8 @@
 import logging
 
 from flask import request
-from flask_restx import Resource, fields, inputs, marshal, marshal_with, reqparse
+from flask_restx import Resource, fields, marshal, marshal_with
+from pydantic import BaseModel, Field
 from sqlalchemy import select
 from werkzeug.exceptions import Unauthorized
 
@@ -32,6 +33,45 @@ from services.file_service import FileService
 from services.workspace_service import WorkspaceService
 
 logger = logging.getLogger(__name__)
+DEFAULT_REF_TEMPLATE_SWAGGER_2_0 = "#/definitions/{model}"
+
+
+class WorkspaceListQuery(BaseModel):
+    page: int = Field(default=1, ge=1, le=99999)
+    limit: int = Field(default=20, ge=1, le=100)
+
+
+class SwitchWorkspacePayload(BaseModel):
+    tenant_id: str
+
+
+class WorkspaceCustomConfigPayload(BaseModel):
+    remove_webapp_brand: bool | None = None
+    replace_webapp_logo: str | None = None
+
+
+class WorkspaceInfoPayload(BaseModel):
+    name: str
+
+
+console_ns.schema_model(
+    WorkspaceListQuery.__name__, WorkspaceListQuery.model_json_schema(ref_template=DEFAULT_REF_TEMPLATE_SWAGGER_2_0)
+)
+
+console_ns.schema_model(
+    SwitchWorkspacePayload.__name__,
+    SwitchWorkspacePayload.model_json_schema(ref_template=DEFAULT_REF_TEMPLATE_SWAGGER_2_0),
+)
+
+console_ns.schema_model(
+    WorkspaceCustomConfigPayload.__name__,
+    WorkspaceCustomConfigPayload.model_json_schema(ref_template=DEFAULT_REF_TEMPLATE_SWAGGER_2_0),
+)
+
+console_ns.schema_model(
+    WorkspaceInfoPayload.__name__,
+    WorkspaceInfoPayload.model_json_schema(ref_template=DEFAULT_REF_TEMPLATE_SWAGGER_2_0),
+)
 
 
 provider_fields = {
@@ -95,18 +135,15 @@ class TenantListApi(Resource):
 
 @console_ns.route("/all-workspaces")
 class WorkspaceListApi(Resource):
+    @console_ns.expect(console_ns.models[WorkspaceListQuery.__name__])
     @setup_required
     @admin_required
     def get(self):
-        parser = (
-            reqparse.RequestParser()
-            .add_argument("page", type=inputs.int_range(1, 99999), required=False, default=1, location="args")
-            .add_argument("limit", type=inputs.int_range(1, 100), required=False, default=20, location="args")
-        )
-        args = parser.parse_args()
+        payload = request.args.to_dict(flat=True)  # type: ignore
+        args = WorkspaceListQuery.model_validate(payload)
 
         stmt = select(Tenant).order_by(Tenant.created_at.desc())
-        tenants = db.paginate(select=stmt, page=args["page"], per_page=args["limit"], error_out=False)
+        tenants = db.paginate(select=stmt, page=args.page, per_page=args.limit, error_out=False)
         has_more = False
 
         if tenants.has_next:
@@ -115,8 +152,8 @@ class WorkspaceListApi(Resource):
         return {
             "data": marshal(tenants.items, workspace_fields),
             "has_more": has_more,
-            "limit": args["limit"],
-            "page": args["page"],
+            "limit": args.limit,
+            "page": args.page,
             "total": tenants.total,
         }, 200
 
@@ -150,26 +187,24 @@ class TenantApi(Resource):
         return WorkspaceService.get_tenant_info(tenant), 200
 
 
-parser_switch = reqparse.RequestParser().add_argument("tenant_id", type=str, required=True, location="json")
-
-
 @console_ns.route("/workspaces/switch")
 class SwitchWorkspaceApi(Resource):
-    @console_ns.expect(parser_switch)
+    @console_ns.expect(console_ns.models[SwitchWorkspacePayload.__name__])
     @setup_required
     @login_required
     @account_initialization_required
     def post(self):
         current_user, _ = current_account_with_tenant()
-        args = parser_switch.parse_args()
+        payload = console_ns.payload or {}
+        args = SwitchWorkspacePayload.model_validate(payload)
 
         # check if tenant_id is valid, 403 if not
         try:
-            TenantService.switch_tenant(current_user, args["tenant_id"])
+            TenantService.switch_tenant(current_user, args.tenant_id)
         except Exception:
             raise AccountNotLinkTenantError("Account not link tenant")
 
-        new_tenant = db.session.query(Tenant).get(args["tenant_id"])  # Get new tenant
+        new_tenant = db.session.query(Tenant).get(args.tenant_id)  # Get new tenant
         if new_tenant is None:
             raise ValueError("Tenant not found")
 
@@ -178,24 +213,21 @@ class SwitchWorkspaceApi(Resource):
 
 @console_ns.route("/workspaces/custom-config")
 class CustomConfigWorkspaceApi(Resource):
+    @console_ns.expect(console_ns.models[WorkspaceCustomConfigPayload.__name__])
     @setup_required
     @login_required
     @account_initialization_required
     @cloud_edition_billing_resource_check("workspace_custom")
     def post(self):
         _, current_tenant_id = current_account_with_tenant()
-        parser = (
-            reqparse.RequestParser()
-            .add_argument("remove_webapp_brand", type=bool, location="json")
-            .add_argument("replace_webapp_logo", type=str, location="json")
-        )
-        args = parser.parse_args()
+        payload = console_ns.payload or {}
+        args = WorkspaceCustomConfigPayload.model_validate(payload)
         tenant = db.get_or_404(Tenant, current_tenant_id)
 
         custom_config_dict = {
-            "remove_webapp_brand": args["remove_webapp_brand"],
-            "replace_webapp_logo": args["replace_webapp_logo"]
-            if args["replace_webapp_logo"] is not None
+            "remove_webapp_brand": args.remove_webapp_brand,
+            "replace_webapp_logo": args.replace_webapp_logo
+            if args.replace_webapp_logo is not None
             else tenant.custom_config_dict.get("replace_webapp_logo"),
         }
 
@@ -245,24 +277,22 @@ class WebappLogoWorkspaceApi(Resource):
         return {"id": upload_file.id}, 201
 
 
-parser_info = reqparse.RequestParser().add_argument("name", type=str, required=True, location="json")
-
-
 @console_ns.route("/workspaces/info")
 class WorkspaceInfoApi(Resource):
-    @console_ns.expect(parser_info)
+    @console_ns.expect(console_ns.models[WorkspaceInfoPayload.__name__])
     @setup_required
     @login_required
     @account_initialization_required
     # Change workspace name
     def post(self):
         _, current_tenant_id = current_account_with_tenant()
-        args = parser_info.parse_args()
+        payload = console_ns.payload or {}
+        args = WorkspaceInfoPayload.model_validate(payload)
 
         if not current_tenant_id:
             raise ValueError("No current tenant")
         tenant = db.get_or_404(Tenant, current_tenant_id)
-        tenant.name = args["name"]
+        tenant.name = args.name
         db.session.commit()
 
         return {"result": "success", "tenant": marshal(WorkspaceService.get_tenant_info(tenant), tenant_fields)}

api/controllers/service_api/__init__.py

@@ -19,7 +19,6 @@ from .app import (
     annotation,
     app,
     audio,
-    chatflow_memory,
     completion,
     conversation,
     file,
@@ -41,7 +40,6 @@ __all__ = [
     "annotation",
     "app",
     "audio",
-    "chatflow_memory",
     "completion",
     "conversation",
     "dataset",

api/controllers/service_api/app/chatflow_memory.py

@@ -1,124 +0,0 @@
-from flask_restx import Resource, reqparse
-
-from controllers.service_api import api
-from controllers.service_api.wraps import FetchUserArg, WhereisUserArg, validate_app_token
-from core.memory.entities import MemoryBlock, MemoryCreatedBy
-from core.workflow.runtime import VariablePool
-from models import App, EndUser
-from services.chatflow_memory_service import ChatflowMemoryService
-from services.workflow_service import WorkflowService
-
-
-class MemoryListApi(Resource):
-    @validate_app_token(fetch_user_arg=FetchUserArg(fetch_from=WhereisUserArg.JSON, required=True))
-    def get(self, app_model: App, end_user: EndUser):
-        parser = reqparse.RequestParser()
-        parser.add_argument("conversation_id", required=False, type=str | None, default=None)
-        parser.add_argument("memory_id", required=False, type=str | None, default=None)
-        parser.add_argument("version", required=False, type=int | None, default=None)
-        args = parser.parse_args()
-        conversation_id: str | None = args.get("conversation_id")
-        memory_id = args.get("memory_id")
-        version = args.get("version")
-
-        if conversation_id:
-            result = ChatflowMemoryService.get_persistent_memories_with_conversation(
-                app_model,
-                MemoryCreatedBy(end_user_id=end_user.id),
-                conversation_id,
-                version
-            )
-            session_memories = ChatflowMemoryService.get_session_memories_with_conversation(
-                app_model,
-                MemoryCreatedBy(end_user_id=end_user.id),
-                conversation_id,
-                version
-            )
-            result = [*result, *session_memories]
-        else:
-            result = ChatflowMemoryService.get_persistent_memories(
-                app_model,
-                MemoryCreatedBy(end_user_id=end_user.id),
-                version
-            )
-
-        if memory_id:
-            result = [it for it in result if it.spec.id == memory_id]
-        return [it for it in result if it.spec.end_user_visible]
-
-
-class MemoryEditApi(Resource):
-    @validate_app_token(fetch_user_arg=FetchUserArg(fetch_from=WhereisUserArg.JSON, required=True))
-    def put(self, app_model: App, end_user: EndUser):
-        parser = reqparse.RequestParser()
-        parser.add_argument('id', type=str, required=True)
-        parser.add_argument("conversation_id", type=str | None, required=False, default=None)
-        parser.add_argument('node_id', type=str | None, required=False, default=None)
-        parser.add_argument('update', type=str, required=True)
-        args = parser.parse_args()
-        workflow = WorkflowService().get_published_workflow(app_model)
-        update = args.get("update")
-        conversation_id = args.get("conversation_id")
-        node_id = args.get("node_id")
-        if not isinstance(update, str):
-            return {'error': 'Invalid update'}, 400
-        if not workflow:
-            return {'error': 'Workflow not found'}, 404
-        memory_spec = next((it for it in workflow.memory_blocks if it.id == args['id']), None)
-        if not memory_spec:
-            return {'error': 'Memory not found'}, 404
-
-        # First get existing memory
-        existing_memory = ChatflowMemoryService.get_memory_by_spec(
-            spec=memory_spec,
-            tenant_id=app_model.tenant_id,
-            app_id=app_model.id,
-            created_by=MemoryCreatedBy(end_user_id=end_user.id),
-            conversation_id=conversation_id,
-            node_id=node_id,
-            is_draft=False
-        )
-
-        # Create updated memory instance with incremented version
-        updated_memory = MemoryBlock(
-            spec=existing_memory.spec,
-            tenant_id=existing_memory.tenant_id,
-            app_id=existing_memory.app_id,
-            conversation_id=existing_memory.conversation_id,
-            node_id=existing_memory.node_id,
-            value=update,  # New value
-            version=existing_memory.version + 1,  # Increment version for update
-            edited_by_user=True,
-            created_by=existing_memory.created_by,
-        )
-
-        ChatflowMemoryService.save_memory(updated_memory, VariablePool(), False)
-        return '', 204
-
-
-class MemoryDeleteApi(Resource):
-    @validate_app_token(fetch_user_arg=FetchUserArg(fetch_from=WhereisUserArg.JSON, required=True))
-    def delete(self, app_model: App, end_user: EndUser):
-        parser = reqparse.RequestParser()
-        parser.add_argument('id', type=str, required=False, default=None)
-        args = parser.parse_args()
-        memory_id = args.get('id')
-
-        if memory_id:
-            ChatflowMemoryService.delete_memory(
-                app_model,
-                memory_id,
-                MemoryCreatedBy(end_user_id=end_user.id)
-            )
-            return '', 204
-        else:
-            ChatflowMemoryService.delete_all_user_memories(
-                app_model,
-                MemoryCreatedBy(end_user_id=end_user.id)
-            )
-            return '', 200
-
-
-api.add_resource(MemoryListApi, '/memories')
-api.add_resource(MemoryEditApi, '/memory-edit')
-api.add_resource(MemoryDeleteApi, '/memories')

api/controllers/service_api/app/completion.py

@@ -17,7 +17,6 @@ from controllers.service_api.app.error import (
 )
 from controllers.service_api.wraps import FetchUserArg, WhereisUserArg, validate_app_token
 from controllers.web.error import InvokeRateLimitError as InvokeRateLimitHttpError
-from core.app.apps.base_app_queue_manager import AppQueueManager
 from core.app.entities.app_invoke_entities import InvokeFrom
 from core.errors.error import (
     ModelCurrentlyNotSupportError,
@@ -30,6 +29,7 @@ from libs import helper
 from libs.helper import uuid_value
 from models.model import App, AppMode, EndUser
 from services.app_generate_service import AppGenerateService
+from services.app_task_service import AppTaskService
 from services.errors.app import IsDraftWorkflowError, WorkflowIdFormatError, WorkflowNotFoundError
 from services.errors.llm import InvokeRateLimitError
 
@@ -88,7 +88,7 @@ class CompletionApi(Resource):
         This endpoint generates a completion based on the provided inputs and query.
         Supports both blocking and streaming response modes.
         """
-        if app_model.mode != "completion":
+        if app_model.mode != AppMode.COMPLETION:
             raise AppUnavailableError()
 
         args = completion_parser.parse_args()
@@ -147,10 +147,15 @@ class CompletionStopApi(Resource):
     @validate_app_token(fetch_user_arg=FetchUserArg(fetch_from=WhereisUserArg.JSON, required=True))
     def post(self, app_model: App, end_user: EndUser, task_id: str):
         """Stop a running completion task."""
-        if app_model.mode != "completion":
+        if app_model.mode != AppMode.COMPLETION:
             raise AppUnavailableError()
 
-        AppQueueManager.set_stop_flag(task_id, InvokeFrom.SERVICE_API, end_user.id)
+        AppTaskService.stop_task(
+            task_id=task_id,
+            invoke_from=InvokeFrom.SERVICE_API,
+            user_id=end_user.id,
+            app_mode=AppMode.value_of(app_model.mode),
+        )
 
         return {"result": "success"}, 200
 
@@ -244,6 +249,11 @@ class ChatStopApi(Resource):
         if app_mode not in {AppMode.CHAT, AppMode.AGENT_CHAT, AppMode.ADVANCED_CHAT}:
             raise NotChatAppError()
 
-        AppQueueManager.set_stop_flag(task_id, InvokeFrom.SERVICE_API, end_user.id)
+        AppTaskService.stop_task(
+            task_id=task_id,
+            invoke_from=InvokeFrom.SERVICE_API,
+            user_id=end_user.id,
+            app_mode=app_mode,
+        )
 
         return {"result": "success"}, 200

api/controllers/trigger/webhook.py

@@ -1,7 +1,7 @@
 import logging
 import time
 
-from flask import jsonify
+from flask import jsonify, request
 from werkzeug.exceptions import NotFound, RequestEntityTooLarge
 
 from controllers.trigger import bp
@@ -28,8 +28,14 @@ def _prepare_webhook_execution(webhook_id: str, is_debug: bool = False):
         webhook_data = WebhookService.extract_and_validate_webhook_data(webhook_trigger, node_config)
         return webhook_trigger, workflow, node_config, webhook_data, None
     except ValueError as e:
-        # Fall back to raw extraction for error reporting
-        webhook_data = WebhookService.extract_webhook_data(webhook_trigger)
+        # Provide minimal context for error reporting without risking another parse failure
+        webhook_data = {
+            "method": request.method,
+            "headers": dict(request.headers),
+            "query_params": dict(request.args),
+            "body": {},
+            "files": {},
+        }
         return webhook_trigger, workflow, node_config, webhook_data, str(e)
 
 

api/controllers/web/__init__.py

@@ -18,7 +18,6 @@ web_ns = Namespace("web", description="Web application API operations", path="/"
 from . import (
     app,
     audio,
-    chatflow_memory,
     completion,
     conversation,
     feature,
@@ -40,7 +39,6 @@ __all__ = [
     "app",
     "audio",
     "bp",
-    "chatflow_memory",
     "completion",
     "conversation",
     "feature",

api/controllers/web/chatflow_memory.py

@@ -1,123 +0,0 @@
-from flask_restx import reqparse
-
-from controllers.web import api
-from controllers.web.wraps import WebApiResource
-from core.memory.entities import MemoryBlock, MemoryCreatedBy
-from core.workflow.runtime import VariablePool
-from models import App, EndUser
-from services.chatflow_memory_service import ChatflowMemoryService
-from services.workflow_service import WorkflowService
-
-
-class MemoryListApi(WebApiResource):
-    def get(self, app_model: App, end_user: EndUser):
-        parser = reqparse.RequestParser()
-        parser.add_argument("conversation_id", required=False, type=str | None, default=None)
-        parser.add_argument("memory_id", required=False, type=str | None, default=None)
-        parser.add_argument("version", required=False, type=int | None, default=None)
-        args = parser.parse_args()
-        conversation_id: str | None = args.get("conversation_id")
-        memory_id = args.get("memory_id")
-        version = args.get("version")
-
-        if conversation_id:
-            result = ChatflowMemoryService.get_persistent_memories_with_conversation(
-                app_model,
-                MemoryCreatedBy(end_user_id=end_user.id),
-                conversation_id,
-                version
-            )
-            session_memories = ChatflowMemoryService.get_session_memories_with_conversation(
-                app_model,
-                MemoryCreatedBy(end_user_id=end_user.id),
-                conversation_id,
-                version
-            )
-            result = [*result, *session_memories]
-        else:
-            result = ChatflowMemoryService.get_persistent_memories(
-                app_model,
-                MemoryCreatedBy(end_user_id=end_user.id),
-                version
-            )
-
-        if memory_id:
-            result = [it for it in result if it.spec.id == memory_id]
-        return [it for it in result if it.spec.end_user_visible]
-
-
-class MemoryEditApi(WebApiResource):
-    def put(self, app_model: App, end_user: EndUser):
-        parser = reqparse.RequestParser()
-        parser.add_argument('id', type=str, required=True)
-        parser.add_argument("conversation_id", type=str | None, required=False, default=None)
-        parser.add_argument('node_id', type=str | None, required=False, default=None)
-        parser.add_argument('update', type=str, required=True)
-        args = parser.parse_args()
-        workflow = WorkflowService().get_published_workflow(app_model)
-        update = args.get("update")
-        conversation_id = args.get("conversation_id")
-        node_id = args.get("node_id")
-        if not isinstance(update, str):
-            return {'error': 'Update must be a string'}, 400
-        if not workflow:
-            return {'error': 'Workflow not found'}, 404
-        memory_spec = next((it for it in workflow.memory_blocks if it.id == args['id']), None)
-        if not memory_spec:
-            return {'error': 'Memory not found'}, 404
-        if not memory_spec.end_user_editable:
-            return {'error': 'Memory not editable'}, 403
-
-        # First get existing memory
-        existing_memory = ChatflowMemoryService.get_memory_by_spec(
-            spec=memory_spec,
-            tenant_id=app_model.tenant_id,
-            app_id=app_model.id,
-            created_by=MemoryCreatedBy(end_user_id=end_user.id),
-            conversation_id=conversation_id,
-            node_id=node_id,
-            is_draft=False
-        )
-
-        # Create updated memory instance with incremented version
-        updated_memory = MemoryBlock(
-            spec=existing_memory.spec,
-            tenant_id=existing_memory.tenant_id,
-            app_id=existing_memory.app_id,
-            conversation_id=existing_memory.conversation_id,
-            node_id=existing_memory.node_id,
-            value=update,  # New value
-            version=existing_memory.version + 1,  # Increment version for update
-            edited_by_user=True,
-            created_by=existing_memory.created_by,
-        )
-
-        ChatflowMemoryService.save_memory(updated_memory, VariablePool(), False)
-        return '', 204
-
-
-class MemoryDeleteApi(WebApiResource):
-    def delete(self, app_model: App, end_user: EndUser):
-        parser = reqparse.RequestParser()
-        parser.add_argument('id', type=str, required=False, default=None)
-        args = parser.parse_args()
-        memory_id = args.get('id')
-
-        if memory_id:
-            ChatflowMemoryService.delete_memory(
-                app_model,
-                memory_id,
-                MemoryCreatedBy(end_user_id=end_user.id)
-            )
-            return '', 204
-        else:
-            ChatflowMemoryService.delete_all_user_memories(
-                app_model,
-                MemoryCreatedBy(end_user_id=end_user.id)
-            )
-            return '', 200
-
-
-api.add_resource(MemoryListApi, '/memories')
-api.add_resource(MemoryEditApi, '/memory-edit')
-api.add_resource(MemoryDeleteApi, '/memories')

api/controllers/web/completion.py

@@ -17,7 +17,6 @@ from controllers.web.error import (
 )
 from controllers.web.error import InvokeRateLimitError as InvokeRateLimitHttpError
 from controllers.web.wraps import WebApiResource
-from core.app.apps.base_app_queue_manager import AppQueueManager
 from core.app.entities.app_invoke_entities import InvokeFrom
 from core.errors.error import (
     ModelCurrentlyNotSupportError,
@@ -29,6 +28,7 @@ from libs import helper
 from libs.helper import uuid_value
 from models.model import AppMode
 from services.app_generate_service import AppGenerateService
+from services.app_task_service import AppTaskService
 from services.errors.llm import InvokeRateLimitError
 
 logger = logging.getLogger(__name__)
@@ -64,7 +64,7 @@ class CompletionApi(WebApiResource):
         }
     )
     def post(self, app_model, end_user):
-        if app_model.mode != "completion":
+        if app_model.mode != AppMode.COMPLETION:
             raise NotCompletionAppError()
 
         parser = (
@@ -125,10 +125,15 @@ class CompletionStopApi(WebApiResource):
         }
     )
     def post(self, app_model, end_user, task_id):
-        if app_model.mode != "completion":
+        if app_model.mode != AppMode.COMPLETION:
             raise NotCompletionAppError()
 
-        AppQueueManager.set_stop_flag(task_id, InvokeFrom.WEB_APP, end_user.id)
+        AppTaskService.stop_task(
+            task_id=task_id,
+            invoke_from=InvokeFrom.WEB_APP,
+            user_id=end_user.id,
+            app_mode=AppMode.value_of(app_model.mode),
+        )
 
         return {"result": "success"}, 200
 
@@ -234,6 +239,11 @@ class ChatStopApi(WebApiResource):
         if app_mode not in {AppMode.CHAT, AppMode.AGENT_CHAT, AppMode.ADVANCED_CHAT}:
             raise NotChatAppError()
 
-        AppQueueManager.set_stop_flag(task_id, InvokeFrom.WEB_APP, end_user.id)
+        AppTaskService.stop_task(
+            task_id=task_id,
+            invoke_from=InvokeFrom.WEB_APP,
+            user_id=end_user.id,
+            app_mode=app_mode,
+        )
 
         return {"result": "success"}, 200

api/core/app/apps/advanced_chat/app_runner.py

@@ -1,11 +1,10 @@
 import logging
 import time
-from collections.abc import Mapping, MutableMapping, Sequence
+from collections.abc import Mapping, Sequence
 from typing import Any, cast
 
 from sqlalchemy import select
 from sqlalchemy.orm import Session
-from typing_extensions import override
 
 from core.app.apps.advanced_chat.app_config_manager import AdvancedChatAppConfig
 from core.app.apps.base_app_queue_manager import AppQueueManager
@@ -21,8 +20,6 @@ from core.app.entities.queue_entities import (
     QueueTextChunkEvent,
 )
 from core.app.features.annotation_reply.annotation_reply import AnnotationReplyFeature
-from core.memory.entities import MemoryCreatedBy, MemoryScope
-from core.model_runtime.entities import AssistantPromptMessage, UserPromptMessage
 from core.moderation.base import ModerationError
 from core.moderation.input_moderation import InputModeration
 from core.variables.variables import VariableUnion
@@ -30,7 +27,6 @@ from core.workflow.enums import WorkflowType
 from core.workflow.graph_engine.command_channels.redis_channel import RedisChannel
 from core.workflow.graph_engine.layers.base import GraphEngineLayer
 from core.workflow.graph_engine.layers.persistence import PersistenceWorkflowInfo, WorkflowPersistenceLayer
-from core.workflow.graph_events import GraphRunSucceededEvent
 from core.workflow.repositories.workflow_execution_repository import WorkflowExecutionRepository
 from core.workflow.repositories.workflow_node_execution_repository import WorkflowNodeExecutionRepository
 from core.workflow.runtime import GraphRuntimeState, VariablePool
@@ -43,8 +39,6 @@ from models import Workflow
 from models.enums import UserFrom
 from models.model import App, Conversation, Message, MessageAnnotation
 from models.workflow import ConversationVariable
-from services.chatflow_history_service import ChatflowHistoryService
-from services.chatflow_memory_service import ChatflowMemoryService
 
 logger = logging.getLogger(__name__)
 
@@ -87,11 +81,6 @@ class AdvancedChatAppRunner(WorkflowBasedAppRunner):
         self._workflow_node_execution_repository = workflow_node_execution_repository
 
     def run(self):
-        ChatflowMemoryService.wait_for_sync_memory_completion(
-            workflow=self._workflow,
-            conversation_id=self.conversation.id
-        )
-
         app_config = self.application_generate_entity.app_config
         app_config = cast(AdvancedChatAppConfig, app_config)
 
@@ -154,7 +143,6 @@ class AdvancedChatAppRunner(WorkflowBasedAppRunner):
                 # Based on the definition of `VariableUnion`,
                 # `list[Variable]` can be safely used as `list[VariableUnion]` since they are compatible.
                 conversation_variables=conversation_variables,
-                memory_blocks=self._fetch_memory_blocks(),
             )
 
             # init graph
@@ -218,31 +206,6 @@ class AdvancedChatAppRunner(WorkflowBasedAppRunner):
         for event in generator:
             self._handle_event(workflow_entry, event)
 
-        try:
-            self._check_app_memory_updates(variable_pool)
-        except Exception as e:
-            logger.exception("Failed to check app memory updates", exc_info=e)
-
-    @override
-    def _handle_event(self, workflow_entry: WorkflowEntry, event: Any) -> None:
-        super()._handle_event(workflow_entry, event)
-        if isinstance(event, GraphRunSucceededEvent):
-            workflow_outputs = event.outputs
-            if not workflow_outputs:
-                logger.warning("Chatflow output is empty.")
-                return
-            assistant_message = workflow_outputs.get('answer')
-            if not assistant_message:
-                logger.warning("Chatflow output does not contain 'answer'.")
-                return
-            if not isinstance(assistant_message, str):
-                logger.warning("Chatflow output 'answer' is not a string.")
-                return
-            try:
-                self._sync_conversation_to_chatflow_tables(assistant_message)
-            except Exception as e:
-                logger.exception("Failed to sync conversation to memory tables", exc_info=e)
-
     def handle_input_moderation(
         self,
         app_record: App,
@@ -440,67 +403,3 @@ class AdvancedChatAppRunner(WorkflowBasedAppRunner):
 
         # Return combined list
         return existing_variables + new_variables
-
-    def _fetch_memory_blocks(self) -> Mapping[str, str]:
-        """fetch all memory blocks for current app"""
-
-        memory_blocks_dict: MutableMapping[str, str] = {}
-        is_draft = (self.application_generate_entity.invoke_from == InvokeFrom.DEBUGGER)
-        conversation_id = self.conversation.id
-        memory_block_specs = self._workflow.memory_blocks
-        # Get runtime memory values
-        memories = ChatflowMemoryService.get_memories_by_specs(
-            memory_block_specs=memory_block_specs,
-            tenant_id=self._workflow.tenant_id,
-            app_id=self._workflow.app_id,
-            node_id=None,
-            conversation_id=conversation_id,
-            is_draft=is_draft,
-            created_by=self._get_created_by(),
-        )
-
-        # Build memory_id -> value mapping
-        for memory in memories:
-            if memory.spec.scope == MemoryScope.APP:
-                # App level: use memory_id directly
-                memory_blocks_dict[memory.spec.id] = memory.value
-            else:  # NODE scope
-                node_id = memory.node_id
-                if not node_id:
-                    logger.warning("Memory block %s has no node_id, skip.", memory.spec.id)
-                    continue
-                key = f"{node_id}_{memory.spec.id}"
-                memory_blocks_dict[key] = memory.value
-
-        return memory_blocks_dict
-
-    def _sync_conversation_to_chatflow_tables(self, assistant_message: str):
-        ChatflowHistoryService.save_app_message(
-            prompt_message=UserPromptMessage(content=(self.application_generate_entity.query)),
-            conversation_id=self.conversation.id,
-            app_id=self._workflow.app_id,
-            tenant_id=self._workflow.tenant_id
-        )
-        ChatflowHistoryService.save_app_message(
-            prompt_message=AssistantPromptMessage(content=assistant_message),
-            conversation_id=self.conversation.id,
-            app_id=self._workflow.app_id,
-            tenant_id=self._workflow.tenant_id
-        )
-
-    def _check_app_memory_updates(self, variable_pool: VariablePool):
-        is_draft = (self.application_generate_entity.invoke_from == InvokeFrom.DEBUGGER)
-
-        ChatflowMemoryService.update_app_memory_if_needed(
-            workflow=self._workflow,
-            conversation_id=self.conversation.id,
-            variable_pool=variable_pool,
-            is_draft=is_draft,
-            created_by=self._get_created_by()
-        )
-
-    def _get_created_by(self) -> MemoryCreatedBy:
-        if self.application_generate_entity.invoke_from in {InvokeFrom.DEBUGGER, InvokeFrom.EXPLORE}:
-            return MemoryCreatedBy(account_id=self.application_generate_entity.user_id)
-        else:
-            return MemoryCreatedBy(end_user_id=self.application_generate_entity.user_id)

api/core/app/apps/advanced_chat/generate_task_pipeline.py

@@ -62,7 +62,8 @@ from core.app.task_pipeline.message_cycle_manager import MessageCycleManager
 from core.base.tts import AppGeneratorTTSPublisher, AudioTrunk
 from core.model_runtime.entities.llm_entities import LLMUsage
 from core.model_runtime.utils.encoders import jsonable_encoder
-from core.ops.ops_trace_manager import TraceQueueManager
+from core.ops.entities.trace_entity import TraceTaskName
+from core.ops.ops_trace_manager import TraceQueueManager, TraceTask
 from core.workflow.enums import WorkflowExecutionStatus
 from core.workflow.nodes import NodeType
 from core.workflow.repositories.draft_variable_repository import DraftVariableSaverFactory
@@ -72,7 +73,7 @@ from extensions.ext_database import db
 from libs.datetime_utils import naive_utc_now
 from models import Account, Conversation, EndUser, Message, MessageFile
 from models.enums import CreatorUserRole
-from models.workflow import Workflow
+from models.workflow import Workflow, WorkflowNodeExecutionModel
 
 logger = logging.getLogger(__name__)
 
@@ -580,7 +581,7 @@ class AdvancedChatAppGenerateTaskPipeline(GraphRuntimeStateSupport):
 
             with self._database_session() as session:
                 # Save message
-                self._save_message(session=session, graph_runtime_state=resolved_state)
+                self._save_message(session=session, graph_runtime_state=resolved_state, trace_manager=trace_manager)
 
             yield workflow_finish_resp
         elif event.stopped_by in (
@@ -590,7 +591,7 @@ class AdvancedChatAppGenerateTaskPipeline(GraphRuntimeStateSupport):
             # When hitting input-moderation or annotation-reply, the workflow will not start
             with self._database_session() as session:
                 # Save message
-                self._save_message(session=session)
+                self._save_message(session=session, trace_manager=trace_manager)
 
         yield self._message_end_to_stream_response()
 
@@ -599,6 +600,7 @@ class AdvancedChatAppGenerateTaskPipeline(GraphRuntimeStateSupport):
         event: QueueAdvancedChatMessageEndEvent,
         *,
         graph_runtime_state: GraphRuntimeState | None = None,
+        trace_manager: TraceQueueManager | None = None,
         **kwargs,
     ) -> Generator[StreamResponse, None, None]:
         """Handle advanced chat message end events."""
@@ -616,7 +618,7 @@ class AdvancedChatAppGenerateTaskPipeline(GraphRuntimeStateSupport):
 
         # Save message
         with self._database_session() as session:
-            self._save_message(session=session, graph_runtime_state=resolved_state)
+            self._save_message(session=session, graph_runtime_state=resolved_state, trace_manager=trace_manager)
 
         yield self._message_end_to_stream_response()
 
@@ -770,7 +772,13 @@ class AdvancedChatAppGenerateTaskPipeline(GraphRuntimeStateSupport):
         if self._conversation_name_generate_thread:
             self._conversation_name_generate_thread.join()
 
-    def _save_message(self, *, session: Session, graph_runtime_state: GraphRuntimeState | None = None):
+    def _save_message(
+        self,
+        *,
+        session: Session,
+        graph_runtime_state: GraphRuntimeState | None = None,
+        trace_manager: TraceQueueManager | None = None,
+    ):
         message = self._get_message(session=session)
 
         # If there are assistant files, remove markdown image links from answer
@@ -809,6 +817,14 @@ class AdvancedChatAppGenerateTaskPipeline(GraphRuntimeStateSupport):
 
         metadata = self._task_state.metadata.model_dump()
         message.message_metadata = json.dumps(jsonable_encoder(metadata))
+
+        # Extract model provider and model_id from workflow node executions for tracing
+        if message.workflow_run_id:
+            model_info = self._extract_model_info_from_workflow(session, message.workflow_run_id)
+            if model_info:
+                message.model_provider = model_info.get("provider")
+                message.model_id = model_info.get("model")
+
         message_files = [
             MessageFile(
                 message_id=message.id,
@@ -826,6 +842,68 @@ class AdvancedChatAppGenerateTaskPipeline(GraphRuntimeStateSupport):
         ]
         session.add_all(message_files)
 
+        # Trigger MESSAGE_TRACE for tracing integrations
+        if trace_manager:
+            trace_manager.add_trace_task(
+                TraceTask(
+                    TraceTaskName.MESSAGE_TRACE, conversation_id=self._conversation_id, message_id=self._message_id
+                )
+            )
+
+    def _extract_model_info_from_workflow(self, session: Session, workflow_run_id: str) -> dict[str, str] | None:
+        """
+        Extract model provider and model_id from workflow node executions.
+        Returns dict with 'provider' and 'model' keys, or None if not found.
+        """
+        try:
+            # Query workflow node executions for LLM or Agent nodes
+            stmt = (
+                select(WorkflowNodeExecutionModel)
+                .where(WorkflowNodeExecutionModel.workflow_run_id == workflow_run_id)
+                .where(WorkflowNodeExecutionModel.node_type.in_(["llm", "agent"]))
+                .order_by(WorkflowNodeExecutionModel.created_at.desc())
+                .limit(1)
+            )
+            node_execution = session.scalar(stmt)
+
+            if not node_execution:
+                return None
+
+            # Try to extract from execution_metadata for agent nodes
+            if node_execution.execution_metadata:
+                try:
+                    metadata = json.loads(node_execution.execution_metadata)
+                    agent_log = metadata.get("agent_log", [])
+                    # Look for the first agent thought with provider info
+                    for log_entry in agent_log:
+                        entry_metadata = log_entry.get("metadata", {})
+                        provider_str = entry_metadata.get("provider")
+                        if provider_str:
+                            # Parse format like "langgenius/deepseek/deepseek"
+                            parts = provider_str.split("/")
+                            if len(parts) >= 3:
+                                return {"provider": parts[1], "model": parts[2]}
+                            elif len(parts) == 2:
+                                return {"provider": parts[0], "model": parts[1]}
+                except (json.JSONDecodeError, KeyError, AttributeError) as e:
+                    logger.debug("Failed to parse execution_metadata: %s", e)
+
+            # Try to extract from process_data for llm nodes
+            if node_execution.process_data:
+                try:
+                    process_data = json.loads(node_execution.process_data)
+                    provider = process_data.get("model_provider")
+                    model = process_data.get("model_name")
+                    if provider and model:
+                        return {"provider": provider, "model": model}
+                except (json.JSONDecodeError, KeyError) as e:
+                    logger.debug("Failed to parse process_data: %s", e)
+
+            return None
+        except Exception as e:
+            logger.warning("Failed to extract model info from workflow: %s", e)
+            return None
+
     def _seed_graph_runtime_state_from_queue_manager(self) -> None:
         """Bootstrap the cached runtime state from the queue manager when present."""
         candidate = self._base_task_pipeline.queue_manager.graph_runtime_state

api/core/app/apps/base_app_generator.py

@@ -155,8 +155,17 @@ class BaseAppGenerator:
                         f"{variable_entity.variable} in input form must be less than {variable_entity.max_length} files"
                     )
             case VariableEntityType.CHECKBOX:
-                if not isinstance(value, bool):
-                    raise ValueError(f"{variable_entity.variable} in input form must be a valid boolean value")
+                if isinstance(value, str):
+                    normalized_value = value.strip().lower()
+                    if normalized_value in {"true", "1", "yes", "on"}:
+                        value = True
+                    elif normalized_value in {"false", "0", "no", "off"}:
+                        value = False
+                elif isinstance(value, (int, float)):
+                    if value == 1:
+                        value = True
+                    elif value == 0:
+                        value = False
             case _:
                 raise AssertionError("this statement should be unreachable.")
 

api/core/app/apps/workflow/generate_task_pipeline.py

@@ -258,6 +258,10 @@ class WorkflowAppGenerateTaskPipeline(GraphRuntimeStateSupport):
 
         run_id = self._extract_workflow_run_id(runtime_state)
         self._workflow_execution_id = run_id
+
+        with self._database_session() as session:
+            self._save_workflow_app_log(session=session, workflow_run_id=self._workflow_execution_id)
+
         start_resp = self._workflow_response_converter.workflow_start_to_stream_response(
             task_id=self._application_generate_entity.task_id,
             workflow_run_id=run_id,
@@ -414,9 +418,6 @@ class WorkflowAppGenerateTaskPipeline(GraphRuntimeStateSupport):
             graph_runtime_state=validated_state,
         )
 
-        with self._database_session() as session:
-            self._save_workflow_app_log(session=session, workflow_run_id=self._workflow_execution_id)
-
         yield workflow_finish_resp
 
     def _handle_workflow_partial_success_event(
@@ -437,10 +438,6 @@ class WorkflowAppGenerateTaskPipeline(GraphRuntimeStateSupport):
             graph_runtime_state=validated_state,
             exceptions_count=event.exceptions_count,
         )
-
-        with self._database_session() as session:
-            self._save_workflow_app_log(session=session, workflow_run_id=self._workflow_execution_id)
-
         yield workflow_finish_resp
 
     def _handle_workflow_failed_and_stop_events(
@@ -471,10 +468,6 @@ class WorkflowAppGenerateTaskPipeline(GraphRuntimeStateSupport):
             error=error,
             exceptions_count=exceptions_count,
         )
-
-        with self._database_session() as session:
-            self._save_workflow_app_log(session=session, workflow_run_id=self._workflow_execution_id)
-
         yield workflow_finish_resp
 
     def _handle_text_chunk_event(
@@ -655,7 +648,6 @@ class WorkflowAppGenerateTaskPipeline(GraphRuntimeStateSupport):
         )
 
         session.add(workflow_app_log)
-        session.commit()
 
     def _text_chunk_to_stream_response(
         self, text: str, from_variable_selector: list[str] | None = None

api/core/app/entities/task_entities.py

@@ -40,6 +40,9 @@ class EasyUITaskState(TaskState):
     """
 
     llm_result: LLMResult
+    first_token_time: float | None = None
+    last_token_time: float | None = None
+    is_streaming_response: bool = False
 
 
 class WorkflowTaskState(TaskState):

api/core/app/layers/pause_state_persist_layer.py

@@ -118,6 +118,7 @@ class PauseStatePersistenceLayer(GraphEngineLayer):
             workflow_run_id=workflow_run_id,
             state_owner_user_id=self._state_owner_user_id,
             state=state.dumps(),
+            pause_reasons=event.reasons,
         )
 
     def on_graph_end(self, error: Exception | None) -> None:

api/core/app/task_pipeline/easy_ui_based_generate_task_pipeline.py

@@ -332,6 +332,12 @@ class EasyUIBasedGenerateTaskPipeline(BasedGenerateTaskPipeline):
                 if not self._task_state.llm_result.prompt_messages:
                     self._task_state.llm_result.prompt_messages = chunk.prompt_messages
 
+                # Track streaming response times
+                if self._task_state.first_token_time is None:
+                    self._task_state.first_token_time = time.perf_counter()
+                    self._task_state.is_streaming_response = True
+                self._task_state.last_token_time = time.perf_counter()
+
                 # handle output moderation chunk
                 should_direct_answer = self._handle_output_moderation_chunk(cast(str, delta_text))
                 if should_direct_answer:
@@ -398,6 +404,18 @@ class EasyUIBasedGenerateTaskPipeline(BasedGenerateTaskPipeline):
         message.total_price = usage.total_price
         message.currency = usage.currency
         self._task_state.llm_result.usage.latency = message.provider_response_latency
+
+        # Add streaming metrics to usage if available
+        if self._task_state.is_streaming_response and self._task_state.first_token_time:
+            start_time = self.start_at
+            first_token_time = self._task_state.first_token_time
+            last_token_time = self._task_state.last_token_time or first_token_time
+            usage.time_to_first_token = round(first_token_time - start_time, 3)
+            usage.time_to_generate = round(last_token_time - first_token_time, 3)
+
+        # Update metadata with the complete usage info
+        self._task_state.metadata.usage = usage
+
         message.message_metadata = self._task_state.metadata.model_dump_json()
 
         if trace_manager:

api/core/helper/code_executor/code_executor.py

@@ -152,10 +152,5 @@ class CodeExecutor:
             raise CodeExecutionError(f"Unsupported language {language}")
 
         runner, preload = template_transformer.transform_caller(code, inputs)
-
-        try:
-            response = cls.execute_code(language, preload, runner)
-        except CodeExecutionError as e:
-            raise e
-
+        response = cls.execute_code(language, preload, runner)
         return template_transformer.transform_response(response)

api/core/llm_generator/llm_generator.py

@@ -1,8 +1,8 @@
 import json
 import logging
 import re
-from collections.abc import Callable, Mapping, Sequence
-from typing import Any, Protocol, cast
+from collections.abc import Sequence
+from typing import Protocol, cast
 
 import json_repair
 
@@ -14,16 +14,10 @@ from core.llm_generator.prompts import (
     JAVASCRIPT_CODE_GENERATOR_PROMPT_TEMPLATE,
     LLM_MODIFY_CODE_SYSTEM,
     LLM_MODIFY_PROMPT_SYSTEM,
-    MEMORY_INSTRUCTION_EDIT_SYSTEM_PROMPT,
-    MEMORY_INSTRUCTION_GENERATION_SYSTEM_PROMPT,
-    MEMORY_TEMPLATE_EDIT_SYSTEM_PROMPT,
-    MEMORY_TEMPLATE_GENERATION_SYSTEM_PROMPT,
-    MEMORY_UPDATE_PROMPT,
     PYTHON_CODE_GENERATOR_PROMPT_TEMPLATE,
     SYSTEM_STRUCTURED_OUTPUT_GENERATE,
     WORKFLOW_RULE_CONFIG_PROMPT_GENERATE_TEMPLATE,
 )
-from core.memory.entities import MemoryBlock, MemoryBlockSpec
 from core.model_manager import ModelManager
 from core.model_runtime.entities.llm_entities import LLMResult
 from core.model_runtime.entities.message_entities import PromptMessage, SystemPromptMessage, UserPromptMessage
@@ -34,7 +28,6 @@ from core.ops.ops_trace_manager import TraceQueueManager, TraceTask
 from core.ops.utils import measure_time
 from core.prompt.utils.prompt_template_parser import PromptTemplateParser
 from core.workflow.entities.workflow_node_execution import WorkflowNodeExecutionMetadataKey
-from core.workflow.runtime import VariablePool
 from extensions.ext_database import db
 from extensions.ext_storage import storage
 from models import App, Message, WorkflowNodeExecutionModel
@@ -513,17 +506,16 @@ class LLMGenerator:
         node_type: str,
         ideal_output: str | None,
     ):
-        # Use unified variable injector
-        variable_providers = {
-            "last_run": lambda: json.dumps(last_run) if last_run else "null",
-            "current": lambda: current or "null",
-            "error_message": lambda: error_message or "null",
-        }
-
-        injected_instruction = LLMGenerator.__inject_variables(
-            instruction=instruction,
-            variable_providers=variable_providers
-        )
+        LAST_RUN = "{{#last_run#}}"
+        CURRENT = "{{#current#}}"
+        ERROR_MESSAGE = "{{#error_message#}}"
+        injected_instruction = instruction
+        if LAST_RUN in injected_instruction:
+            injected_instruction = injected_instruction.replace(LAST_RUN, json.dumps(last_run))
+        if CURRENT in injected_instruction:
+            injected_instruction = injected_instruction.replace(CURRENT, current or "null")
+        if ERROR_MESSAGE in injected_instruction:
+            injected_instruction = injected_instruction.replace(ERROR_MESSAGE, error_message or "null")
         model_instance = ModelManager().get_model_instance(
             tenant_id=tenant_id,
             model_type=ModelType.LLM,
@@ -570,424 +562,3 @@ class LLMGenerator:
                 "Failed to invoke LLM model, model: %s", json.dumps(model_config.get("name")), exc_info=True
             )
             return {"error": f"An unexpected error occurred: {str(e)}"}
-
-    @staticmethod
-    def update_memory_block(
-        tenant_id: str,
-        visible_history: Sequence[tuple[str, str]],
-        variable_pool: VariablePool,
-        memory_block: MemoryBlock,
-        memory_spec: MemoryBlockSpec
-    ) -> str:
-        model_instance = ModelManager().get_model_instance(
-            tenant_id=tenant_id,
-            provider=memory_spec.model.provider,
-            model=memory_spec.model.name,
-            model_type=ModelType.LLM,
-        )
-        formatted_history = ""
-        for sender, message in visible_history:
-            formatted_history += f"{sender}: {message}\n"
-        filled_instruction = variable_pool.convert_template(memory_spec.instruction).text
-        formatted_prompt = PromptTemplateParser(MEMORY_UPDATE_PROMPT).format(
-            inputs={
-                "formatted_history": formatted_history,
-                "current_value": memory_block.value,
-                "instruction": filled_instruction,
-            }
-        )
-        llm_result = model_instance.invoke_llm(
-            prompt_messages=[UserPromptMessage(content=formatted_prompt)],
-            model_parameters=memory_spec.model.completion_params,
-            stream=False,
-        )
-        return llm_result.message.get_text_content()
-
-    @staticmethod
-    def generate_memory_template(
-        tenant_id: str,
-        instruction: str,
-        model_config: dict,
-    ) -> dict:
-        """
-        Generate Memory Template
-
-        Uses MEMORY_TEMPLATE_GENERATION_SYSTEM_PROMPT
-        """
-        model_instance = ModelManager().get_model_instance(
-            tenant_id=tenant_id,
-            model_type=ModelType.LLM,
-            provider=model_config.get("provider", ""),
-            model=model_config.get("name", ""),
-        )
-
-        prompt_messages: list[PromptMessage] = [
-            SystemPromptMessage(content=MEMORY_TEMPLATE_GENERATION_SYSTEM_PROMPT),
-            UserPromptMessage(content=instruction),
-        ]
-
-        try:
-            response = model_instance.invoke_llm(
-                prompt_messages=prompt_messages,
-                model_parameters={"temperature": 0.7},
-                stream=False,
-            )
-
-            generated_template = response.message.get_text_content()
-            return {"template": generated_template}
-
-        except Exception as e:
-            logger.exception("Failed to generate memory template")
-            return {"error": f"Failed to generate memory template: {str(e)}"}
-
-    @staticmethod
-    def generate_memory_instruction(
-        tenant_id: str,
-        instruction: str,
-        model_config: dict,
-    ) -> dict:
-        """
-        Generate Memory Instruction
-
-        Uses MEMORY_INSTRUCTION_GENERATION_SYSTEM_PROMPT
-        """
-        model_instance = ModelManager().get_model_instance(
-            tenant_id=tenant_id,
-            model_type=ModelType.LLM,
-            provider=model_config.get("provider", ""),
-            model=model_config.get("name", ""),
-        )
-
-        prompt_messages: list[PromptMessage] = [
-            SystemPromptMessage(content=MEMORY_INSTRUCTION_GENERATION_SYSTEM_PROMPT),
-            UserPromptMessage(content=instruction),
-        ]
-
-        try:
-            response = model_instance.invoke_llm(
-                prompt_messages=prompt_messages,
-                model_parameters={"temperature": 0.7},
-                stream=False,
-            )
-
-            generated_instruction = response.message.get_text_content()
-            return {"instruction": generated_instruction}
-
-        except Exception as e:
-            logger.exception("Failed to generate memory instruction")
-            return {"error": f"Failed to generate memory instruction: {str(e)}"}
-
-    @staticmethod
-    def edit_memory_template(
-        tenant_id: str,
-        flow_id: str,
-        node_id: str | None,
-        current: str,
-        instruction: str,
-        model_config: dict,
-        ideal_output: str | None = None,
-    ) -> dict:
-        """
-        Edit Memory Template
-
-        Supports variable references: {{#history#}}, {{#system_prompt#}}
-        """
-        # Use unified variable injector
-        variable_providers = {
-            "history": lambda: LLMGenerator.__get_history_json(flow_id, node_id, tenant_id),
-            "system_prompt": lambda: json.dumps(
-                LLMGenerator.__get_system_prompt(flow_id, node_id, tenant_id),
-                ensure_ascii=False
-            ),
-        }
-
-        injected_instruction = LLMGenerator.__inject_variables(
-            instruction=instruction,
-            variable_providers=variable_providers
-        )
-
-        model_instance = ModelManager().get_model_instance(
-            tenant_id=tenant_id,
-            model_type=ModelType.LLM,
-            provider=model_config.get("provider", ""),
-            model=model_config.get("name", ""),
-        )
-
-        system_prompt = MEMORY_TEMPLATE_EDIT_SYSTEM_PROMPT
-        user_content = json.dumps({
-            "current_template": current,
-            "instruction": injected_instruction,
-            "ideal_output": ideal_output,
-        })
-
-        prompt_messages: list[PromptMessage] = [
-            SystemPromptMessage(content=system_prompt),
-            UserPromptMessage(content=user_content),
-        ]
-
-        try:
-            response = model_instance.invoke_llm(
-                prompt_messages=prompt_messages,
-                model_parameters={"temperature": 0.4},
-                stream=False,
-            )
-
-            generated_raw = response.message.get_text_content()
-            # Extract JSON
-            first_brace = generated_raw.find("{")
-            last_brace = generated_raw.rfind("}")
-            result = json.loads(generated_raw[first_brace : last_brace + 1])
-
-            return {
-                "modified": result.get("modified", ""),
-                "message": result.get("message", "Template updated successfully"),
-            }
-
-        except Exception as e:
-            logger.exception("Failed to edit memory template")
-            return {"error": f"Failed to edit memory template: {str(e)}"}
-
-    @staticmethod
-    def edit_memory_instruction(
-        tenant_id: str,
-        flow_id: str,
-        node_id: str | None,
-        current: str,
-        instruction: str,
-        model_config: dict,
-        ideal_output: str | None = None,
-    ) -> dict:
-        """
-        Edit Memory Instruction
-
-        Supports variable references: {{#history#}}, {{#system_prompt#}}
-        """
-        # Use unified variable injector
-        variable_providers = {
-            "history": lambda: LLMGenerator.__get_history_json(flow_id, node_id, tenant_id),
-            "system_prompt": lambda: json.dumps(
-                LLMGenerator.__get_system_prompt(flow_id, node_id, tenant_id),
-                ensure_ascii=False
-            ),
-        }
-
-        injected_instruction = LLMGenerator.__inject_variables(
-            instruction=instruction,
-            variable_providers=variable_providers
-        )
-
-        model_instance = ModelManager().get_model_instance(
-            tenant_id=tenant_id,
-            model_type=ModelType.LLM,
-            provider=model_config.get("provider", ""),
-            model=model_config.get("name", ""),
-        )
-
-        system_prompt = MEMORY_INSTRUCTION_EDIT_SYSTEM_PROMPT
-        user_content = json.dumps({
-            "current_instruction": current,
-            "instruction": injected_instruction,
-            "ideal_output": ideal_output,
-        })
-
-        prompt_messages: list[PromptMessage] = [
-            SystemPromptMessage(content=system_prompt),
-            UserPromptMessage(content=user_content),
-        ]
-
-        try:
-            response = model_instance.invoke_llm(
-                prompt_messages=prompt_messages,
-                model_parameters={"temperature": 0.4},
-                stream=False,
-            )
-
-            generated_raw = response.message.get_text_content()
-            # Extract JSON
-            first_brace = generated_raw.find("{")
-            last_brace = generated_raw.rfind("}")
-            result = json.loads(generated_raw[first_brace : last_brace + 1])
-
-            return {
-                "modified": result.get("modified", ""),
-                "message": result.get("message", "Instruction updated successfully"),
-            }
-
-        except Exception as e:
-            logger.exception("Failed to edit memory instruction")
-            return {"error": f"Failed to edit memory instruction: {str(e)}"}
-
-    # ==================== Unified variable injector (private method) ====================
-
-    @staticmethod
-    def __inject_variables(
-        instruction: str,
-        variable_providers: Mapping[str, Callable[[], str]]
-    ) -> str:
-        """
-        Unified variable injector (private method)
-
-        Replaces variable placeholders {{#variable_name#}} in instruction with actual values
-
-        Args:
-            instruction: User's original instruction
-            variable_providers: Mapping of variable name -> getter function
-                Example: {"last_run": lambda: json.dumps(data), "history": lambda: get_history()}
-
-        Returns:
-            Instruction with injected variables
-
-        Features:
-        1. Lazy loading: Only calls getter function when placeholder is present
-        2. Fault tolerance: Failure of one variable doesn't affect others
-        3. Extensible: New variables can be added through variable_providers parameter
-        """
-        injected = instruction
-
-        for var_name, provider_func in variable_providers.items():
-            placeholder = f"{{{{#{var_name}#}}}}"
-
-            if placeholder in injected:
-                try:
-                    # Lazy loading: only call when needed
-                    value = provider_func()
-                    injected = injected.replace(placeholder, value)
-                except Exception as e:
-                    logger.warning("Failed to inject variable '%s': %s", var_name, e)
-                    # Use default value on failure, don't block the request
-                    default_value = "[]" if var_name == "history" else '""'
-                    injected = injected.replace(placeholder, default_value)
-
-        return injected
-
-    @staticmethod
-    def __get_history_json(
-        flow_id: str,
-        node_id: str | None,
-        tenant_id: str
-    ) -> str:
-        """
-        Get conversation history as JSON string (private method)
-
-        Args:
-            flow_id: Application ID
-            node_id: Node ID (optional, None indicates APP level)
-            tenant_id: Tenant ID
-
-        Returns:
-            JSON array string in format: [{"role": "user", "content": "..."}, ...]
-            Returns "[]" if no history exists
-        """
-        from services.chatflow_history_service import ChatflowHistoryService
-
-        app = db.session.query(App).filter_by(id=flow_id).first()
-        if not app:
-            return "[]"
-
-        visible_messages = ChatflowHistoryService.get_latest_chat_history_for_app(
-            app_id=app.id,
-            tenant_id=tenant_id,
-            node_id=node_id or None
-        )
-
-        history_json = [
-            {"role": msg.role.value, "content": msg.content}
-            for msg in visible_messages
-        ]
-
-        return json.dumps(history_json, ensure_ascii=False)
-
-    @staticmethod
-    def __get_system_prompt(
-        flow_id: str,
-        node_id: str | None,
-        tenant_id: str
-    ) -> str:
-        """
-        Get system prompt (private method)
-
-        Args:
-            flow_id: Application ID
-            node_id: Node ID (optional)
-            tenant_id: Tenant ID
-
-        Returns:
-            System prompt string, returns "" if none exists
-        """
-        from services.workflow_service import WorkflowService
-
-        app = db.session.query(App).filter_by(id=flow_id).first()
-        if not app:
-            return ""
-
-        # Legacy app
-        if app.mode in {"chat", "completion"}:
-            try:
-                app_model_config = app.app_model_config_dict
-                return app_model_config.get("pre_prompt", "")
-            except Exception:
-                return ""
-
-        # Workflow app
-        try:
-            workflow = WorkflowService().get_draft_workflow(app_model=app)
-            if not workflow:
-                return ""
-
-            nodes = workflow.graph_dict.get("nodes", [])
-
-            if node_id:
-                # Get system prompt for specified node
-                node = next((n for n in nodes if n["id"] == node_id), None)
-                if not node or node["data"]["type"] not in ["llm", "agent"]:
-                    return ""
-
-                prompt_template = node["data"].get("prompt_template")
-                return LLMGenerator.__extract_system_prompt_from_template(prompt_template)
-            else:
-                # APP level: find the main LLM node (connected to END node)
-                edges = workflow.graph_dict.get("edges", [])
-                llm_nodes = [n for n in nodes if n["data"]["type"] in ["llm", "agent"]]
-
-                for edge in edges:
-                    if edge.get("target") == "end":
-                        source_node = next((n for n in llm_nodes if n["id"] == edge.get("source")), None)
-                        if source_node:
-                            prompt_template = source_node["data"].get("prompt_template")
-                            system_prompt = LLMGenerator.__extract_system_prompt_from_template(prompt_template)
-                            if system_prompt:
-                                return system_prompt
-
-                # Fallback: return system prompt from first LLM node
-                if llm_nodes:
-                    prompt_template = llm_nodes[0]["data"].get("prompt_template")
-                    return LLMGenerator.__extract_system_prompt_from_template(prompt_template)
-
-                return ""
-        except Exception as e:
-            logger.warning("Failed to get system prompt: %s", e)
-            return ""
-
-    @staticmethod
-    def __extract_system_prompt_from_template(prompt_template: Any) -> str:
-        """
-        Extract system prompt from prompt_template (private method)
-
-        Args:
-            prompt_template: LLM node's prompt_template (may be list or dict)
-
-        Returns:
-            System prompt string
-        """
-        if not prompt_template:
-            return ""
-
-        if isinstance(prompt_template, list):
-            # Chat model: [{"role": "system", "text": "..."}, ...]
-            system_msg = next((m for m in prompt_template if m.get("role") == "system"), None)
-            return system_msg.get("text", "") if system_msg else ""
-        elif isinstance(prompt_template, dict):
-            # Completion model: {"text": "..."}
-            return prompt_template.get("text", "")
-        else:
-            return ""

api/core/llm_generator/prompts.py

@@ -422,112 +422,3 @@ INSTRUCTION_GENERATE_TEMPLATE_PROMPT = """The output of this prompt is not as ex
 You should edit the prompt according to the IDEAL OUTPUT."""
 
 INSTRUCTION_GENERATE_TEMPLATE_CODE = """Please fix the errors in the {{#error_message#}}."""
-
-MEMORY_UPDATE_PROMPT = """
-Based on the following conversation history, update the memory content:
-
-Conversation history:
-{{formatted_history}}
-
-Current memory:
-{{current_value}}
-
-Update instruction:
-{{instruction}}
-
-Please output only the updated memory content, no other text like greeting:
-"""
-
-MEMORY_TEMPLATE_GENERATION_SYSTEM_PROMPT = """
-You are a helpful assistant designed to extract structured template information from a long-term conversation. Your task is to generate a concise and complete MemoryBlock template based on the underlying purpose of the conversation.
-
-Each MemoryBlock represents a reusable schema that captures the key elements relevant to a specific task or goal (e.g., planning a trip, conducting a job interview, writing a blog post, etc.).
-
-When generating a template:
-1. Analyze the overall goal or purpose of the conversation described in the user's instruction.
-2. Identify essential information categories that would be relevant to track.
-3. Structure the template using Markdown format with clear sections and fields.
-4. Do not fill in actual user data — only describe the structure and purpose of each field.
-5. Be general enough to be reusable, but specific enough to serve the user's intent.
-
-Respond with only the template in Markdown format, with no additional explanation.
-
-Example format:
-# [Template Name]
-
-## Section 1
-- **Field 1:** Description of what should be captured here
-- **Field 2:** Description of what should be captured here
-
-## Section 2
-- **Field 3:** Description of what should be captured here
-"""  # noqa: E501
-
-MEMORY_INSTRUCTION_GENERATION_SYSTEM_PROMPT = """
-You are a prompt generation model.
-
-Your task is to generate an instruction for a downstream language model tasked with extracting structured memory blocks (MemoryBlock) from long, multi-turn conversations between a user and an assistant.
-
-The downstream model will receive:
-- A template describing the structure and fields of the memory block it should extract.
-- The historical conversation, serialized as plain text with message tags.
-- Optional context including the assistant's system prompt.
-
-You must generate a clear, specific, and instructional prompt that:
-1. Explains what a MemoryBlock is and its purpose.
-2. Instructs the model to extract only information relevant to the template fields.
-3. Emphasizes handling implicit information and scattered mentions across multiple turns.
-4. Instructs to ignore irrelevant or casual dialogue.
-5. Describes the expected output format (structured object matching the template).
-6. Uses placeholders {{#history#}} and {{#system_prompt#}} for runtime variable injection.
-
-The tone should be concise, instructional, and focused on task precision.
-
-Based on the user's description of the conversation context, generate the ideal extraction instruction.
-"""  # noqa: E501
-
-MEMORY_TEMPLATE_EDIT_SYSTEM_PROMPT = """
-You are an expert at refining memory templates for conversation tracking systems.
-
-You will receive:
-- current_template: The existing memory template
-- instruction: User's instruction for how to modify the template (may include {{#history#}} and {{#system_prompt#}} references)
-- ideal_output: Optional description of the desired result
-
-Your task:
-1. Analyze the current template structure
-2. Apply the requested modifications based on the instruction
-3. Ensure the modified template maintains proper Markdown structure
-4. Keep field descriptions clear and actionable
-
-Output format (JSON):
-{
-    "modified": "<the updated template in Markdown format>",
-    "message": "<brief explanation of changes made>"
-}
-
-Only output the JSON, no additional text.
-"""  # noqa: E501
-
-MEMORY_INSTRUCTION_EDIT_SYSTEM_PROMPT = """
-You are an expert at refining extraction instructions for memory systems.
-
-You will receive:
-- current_instruction: The existing extraction instruction
-- instruction: User's instruction for how to improve it (may include {{#history#}} and {{#system_prompt#}} references)
-- ideal_output: Optional description of the desired result
-
-Your task:
-1. Analyze the current instruction's effectiveness
-2. Apply the requested improvements based on the user's instruction
-3. Ensure the modified instruction is clear, specific, and actionable
-4. Maintain focus on structured extraction matching the template
-
-Output format (JSON):
-{
-    "modified": "<the improved instruction>",
-    "message": "<brief explanation of improvements>"
-}
-
-Only output the JSON, no additional text.
-"""

api/core/memory/entities.py

@@ -1,133 +0,0 @@
-from __future__ import annotations
-
-from enum import StrEnum
-from typing import Optional
-from uuid import uuid4
-
-from pydantic import BaseModel, Field, field_validator
-
-from core.app.app_config.entities import ModelConfig
-
-
-class MemoryScope(StrEnum):
-    """Memory scope determined by node_id field"""
-    APP = "app"  # node_id is None
-    NODE = "node"  # node_id is not None
-
-
-class MemoryTerm(StrEnum):
-    """Memory term determined by conversation_id field"""
-    SESSION = "session"  # conversation_id is not None
-    PERSISTENT = "persistent"  # conversation_id is None
-
-
-class MemoryStrategy(StrEnum):
-    ON_TURNS = "on_turns"
-
-
-class MemoryScheduleMode(StrEnum):
-    SYNC = "sync"
-    ASYNC = "async"
-
-
-class MemoryBlockSpec(BaseModel):
-    """Memory block specification for workflow configuration"""
-    id: str = Field(
-        default_factory=lambda: str(uuid4()),
-        description="Unique identifier for the memory block",
-    )
-    name: str = Field(description="Display name of the memory block")
-    description: str = Field(default="", description="Description of the memory block")
-    template: str = Field(description="Initial template content for the memory")
-    instruction: str = Field(description="Instructions for updating the memory")
-    scope: MemoryScope = Field(description="Scope of the memory (app or node level)")
-    term: MemoryTerm = Field(description="Term of the memory (session or persistent)")
-    strategy: MemoryStrategy = Field(description="Update strategy for the memory")
-    update_turns: int = Field(gt=0, description="Number of turns between updates")
-    preserved_turns: int = Field(gt=0, description="Number of conversation turns to preserve")
-    schedule_mode: MemoryScheduleMode = Field(description="Synchronous or asynchronous update mode")
-    model: ModelConfig = Field(description="Model configuration for memory updates")
-    end_user_visible: bool = Field(default=False, description="Whether memory is visible to end users")
-    end_user_editable: bool = Field(default=False, description="Whether memory is editable by end users")
-    node_id: str | None = Field(
-        default=None,
-        description="Node ID when scope is NODE. Must be None when scope is APP."
-    )
-
-    @field_validator('node_id')
-    @classmethod
-    def validate_node_id_with_scope(cls, v: str | None, info) -> str | None:
-        """Validate node_id consistency with scope"""
-        scope = info.data.get('scope')
-        if scope == MemoryScope.NODE and v is None:
-            raise ValueError("node_id is required when scope is NODE")
-        if scope == MemoryScope.APP and v is not None:
-            raise ValueError("node_id must be None when scope is APP")
-        return v
-
-
-class MemoryCreatedBy(BaseModel):
-    end_user_id: str | None = None
-    account_id: str | None = None
-
-
-class MemoryBlock(BaseModel):
-    """Runtime memory block instance
-
-    Design Rules:
-    - app_id = None: Global memory (future feature, not implemented yet)
-    - app_id = str: App-specific memory
-    - conversation_id = None: Persistent memory (cross-conversation)
-    - conversation_id = str: Session memory (conversation-specific)
-    - node_id = None: App-level scope
-    - node_id = str: Node-level scope
-
-    These rules implicitly determine scope and term without redundant storage.
-    """
-    spec: MemoryBlockSpec
-    tenant_id: str
-    value: str
-    app_id: str
-    conversation_id: Optional[str] = None
-    node_id: Optional[str] = None
-    edited_by_user: bool = False
-    created_by: MemoryCreatedBy
-    version: int = Field(description="Memory block version number")
-
-
-class MemoryValueData(BaseModel):
-    value: str
-    edited_by_user: bool = False
-
-
-class ChatflowConversationMetadata(BaseModel):
-    """Metadata for chatflow conversation with visible message count"""
-    type: str = "mutable_visible_window"
-    visible_count: int = Field(gt=0, description="Number of visible messages to keep")
-
-
-class MemoryBlockWithConversation(MemoryBlock):
-    """MemoryBlock with optional conversation metadata for session memories"""
-    conversation_metadata: ChatflowConversationMetadata = Field(
-        description="Conversation metadata, only present for session memories"
-    )
-
-    @classmethod
-    def from_memory_block(
-        cls,
-        memory_block: MemoryBlock,
-        conversation_metadata: ChatflowConversationMetadata
-    ) -> MemoryBlockWithConversation:
-        """Create MemoryBlockWithConversation from MemoryBlock"""
-        return cls(
-            spec=memory_block.spec,
-            tenant_id=memory_block.tenant_id,
-            value=memory_block.value,
-            app_id=memory_block.app_id,
-            conversation_id=memory_block.conversation_id,
-            node_id=memory_block.node_id,
-            edited_by_user=memory_block.edited_by_user,
-            created_by=memory_block.created_by,
-            version=memory_block.version,
-            conversation_metadata=conversation_metadata
-        )

api/core/memory/errors.py

@@ -1,6 +0,0 @@
-class MemorySyncTimeoutError(Exception):
-    def __init__(self, app_id: str, conversation_id: str):
-        self.app_id = app_id
-        self.conversation_id = conversation_id
-        self.message = "Memory synchronization timeout after 50 seconds"
-        super().__init__(self.message)

api/core/model_runtime/docs/en_US/customizable_model_scale_out.md

@@ -1,308 +0,0 @@
-## Custom Integration of Pre-defined Models
-
-### Introduction
-
-After completing the vendors integration, the next step is to connect the vendor's models. To illustrate the entire connection process, we will use Xinference as an example to demonstrate a complete vendor integration.
-
-It is important to note that for custom models, each model connection requires a complete vendor credential.
-
-Unlike pre-defined models, a custom vendor integration always includes the following two parameters, which do not need to be defined in the vendor YAML file.
-
-![](images/index/image-3.png)
-
-As mentioned earlier, vendors do not need to implement validate_provider_credential. The runtime will automatically call the corresponding model layer's validate_credentials to validate the credentials based on the model type and name selected by the user.
-
-### Writing the Vendor YAML
-
-First, we need to identify the types of models supported by the vendor we are integrating.
-
-Currently supported model types are as follows:
-
-- `llm` Text Generation Models
-
-- `text_embedding` Text Embedding Models
-
-- `rerank` Rerank Models
-
-- `speech2text` Speech-to-Text
-
-- `tts` Text-to-Speech
-
-- `moderation` Moderation
-
-Xinference supports LLM, Text Embedding, and Rerank. So we will start by writing xinference.yaml.
-
-```yaml
-provider: xinference #Define the vendor identifier
-label: # Vendor display name, supports both en_US (English) and zh_Hans (Simplified Chinese). If zh_Hans is not set, it will use en_US by default.
-  en_US: Xorbits Inference
-icon_small: # Small icon, refer to other vendors' icons stored in the _assets directory within the vendor implementation directory; follows the same language policy as the label
-  en_US: icon_s_en.svg
-icon_large: # Large icon
-  en_US: icon_l_en.svg
-help: # Help information
-  title:
-    en_US: How to deploy Xinference
-    zh_Hans: 如何部署 Xinference
-  url:
-    en_US: https://github.com/xorbitsai/inference
-supported_model_types: # Supported model types. Xinference supports LLM, Text Embedding, and Rerank
-- llm
-- text-embedding
-- rerank
-configurate_methods: # Since Xinference is a locally deployed vendor with no predefined models, users need to deploy whatever models they need according to Xinference documentation. Thus, it only supports custom models.
-- customizable-model
-provider_credential_schema:
-  credential_form_schemas:
-```
-
-Then, we need to determine what credentials are required to define a model in Xinference.
-
-- Since it supports three different types of models, we need to specify the model_type to denote the model type. Here is how we can define it:
-
-```yaml
-provider_credential_schema:
-  credential_form_schemas:
-  - variable: model_type
-    type: select
-    label:
-      en_US: Model type
-      zh_Hans: 模型类型
-    required: true
-    options:
-    - value: text-generation
-      label:
-        en_US: Language Model
-        zh_Hans: 语言模型
-    - value: embeddings
-      label:
-        en_US: Text Embedding
-    - value: reranking
-      label:
-        en_US: Rerank
-```
-
-- Next, each model has its own model_name, so we need to define that here:
-
-```yaml
-  - variable: model_name
-    type: text-input
-    label:
-      en_US: Model name
-      zh_Hans: 模型名称
-    required: true
-    placeholder:
-      zh_Hans: 填写模型名称
-      en_US: Input model name
-```
-
-- Specify the Xinference local deployment address:
-
-```yaml
-  - variable: server_url
-    label:
-      zh_Hans: 服务器 URL
-      en_US: Server url
-    type: text-input
-    required: true
-    placeholder:
-      zh_Hans: 在此输入 Xinference 的服务器地址，如 https://example.com/xxx
-      en_US: Enter the url of your Xinference, for example https://example.com/xxx
-```
-
-- Each model has a unique model_uid, so we also need to define that here:
-
-```yaml
-  - variable: model_uid
-    label:
-      zh_Hans: 模型 UID
-      en_US: Model uid
-    type: text-input
-    required: true
-    placeholder:
-      zh_Hans: 在此输入您的 Model UID
-      en_US: Enter the model uid
-```
-
-Now, we have completed the basic definition of the vendor.
-
-### Writing the Model Code
-
-Next, let's take the `llm` type as an example and write `xinference.llm.llm.py`.
-
-In `llm.py`, create a Xinference LLM class, we name it `XinferenceAILargeLanguageModel` (this can be arbitrary), inheriting from the `__base.large_language_model.LargeLanguageModel` base class, and implement the following methods:
-
-- LLM Invocation
-
-Implement the core method for LLM invocation, supporting both stream and synchronous responses.
-
-```python
-def _invoke(self, model: str, credentials: dict,
-            prompt_messages: list[PromptMessage], model_parameters: dict,
-            tools: Optional[list[PromptMessageTool]] = None, stop: Optional[list[str]] = None,
-            stream: bool = True, user: Optional[str] = None) \
-        -> Union[LLMResult, Generator]:
-    """
-    Invoke large language model
-    
-    :param model: model name
-	:param credentials: model credentials
-	:param prompt_messages: prompt messages
-	:param model_parameters: model parameters
-	:param tools: tools for tool usage
-	:param stop: stop words
-	:param stream: is the response a stream
-	:param user: unique user id
-	:return: full response or stream response chunk generator result
-	"""
-```
-
-When implementing, ensure to use two functions to return data separately for synchronous and stream responses. This is important because Python treats functions containing the `yield` keyword as generator functions, mandating them to return `Generator` types. Here’s an example (note that the example uses simplified parameters; in real implementation, use the parameter list as defined above):
-
-```python
-def _invoke(self, stream: bool, **kwargs) \
-        -> Union[LLMResult, Generator]:
-    if stream:
-          return self._handle_stream_response(**kwargs)
-    return self._handle_sync_response(**kwargs)
-
-def _handle_stream_response(self, **kwargs) -> Generator:
-    for chunk in response:
-          yield chunk
-def _handle_sync_response(self, **kwargs) -> LLMResult:
-    return LLMResult(**response)
-```
-
-- Pre-compute Input Tokens
-
-If the model does not provide an interface for pre-computing tokens, you can return 0 directly.
-
-```python
-def get_num_tokens(self, model: str, credentials: dict, prompt_messages: list[PromptMessage],tools: Optional[list[PromptMessageTool]] = None) -> int:
-  """
-  Get number of tokens for given prompt messages
-
-  :param model: model name
-  :param credentials: model credentials
-  :param prompt_messages: prompt messages
-  :param tools: tools for tool usage
-  :return: token count
-  """
-```
-
-Sometimes, you might not want to return 0 directly. In such cases, you can use `self._get_num_tokens_by_gpt2(text: str)` to get pre-computed tokens and ensure environment variable `PLUGIN_BASED_TOKEN_COUNTING_ENABLED` is set to `true`, This method is provided by the `AIModel` base class, and it uses GPT2's Tokenizer for calculation. However, it should be noted that this is only a substitute and may not be fully accurate.
-
-- Model Credentials Validation
-
-Similar to vendor credentials validation, this method validates individual model credentials.
-
-```python
-def validate_credentials(self, model: str, credentials: dict) -> None:
-    """
-    Validate model credentials
-    
-    :param model: model name
-	:param credentials: model credentials
-	:return: None
-	"""
-```
-
-- Model Parameter Schema
-
-Unlike custom types, since the YAML file does not define which parameters a model supports, we need to dynamically generate the model parameter schema.
-
-For instance, Xinference supports `max_tokens`, `temperature`, and `top_p` parameters.
-
-However, some vendors may support different parameters for different models. For example, the `OpenLLM` vendor supports `top_k`, but not all models provided by this vendor support `top_k`. Let's say model A supports `top_k` but model B does not. In such cases, we need to dynamically generate the model parameter schema, as illustrated below:
-
-```python
-    def get_customizable_model_schema(self, model: str, credentials: dict) -> Optional[AIModelEntity]:
-        """
-            used to define customizable model schema
-        """
-        rules = [
-            ParameterRule(
-                name='temperature', type=ParameterType.FLOAT,
-                use_template='temperature',
-                label=I18nObject(
-                    zh_Hans='温度', en_US='Temperature'
-                )
-            ),
-            ParameterRule(
-                name='top_p', type=ParameterType.FLOAT,
-                use_template='top_p',
-                label=I18nObject(
-                    zh_Hans='Top P', en_US='Top P'
-                )
-            ),
-            ParameterRule(
-                name='max_tokens', type=ParameterType.INT,
-                use_template='max_tokens',
-                min=1,
-                default=512,
-                label=I18nObject(
-                    zh_Hans='最大生成长度', en_US='Max Tokens'
-                )
-            )
-        ]
-
-        # if model is A, add top_k to rules
-        if model == 'A':
-            rules.append(
-                ParameterRule(
-                    name='top_k', type=ParameterType.INT,
-                    use_template='top_k',
-                    min=1,
-                    default=50,
-                    label=I18nObject(
-                        zh_Hans='Top K', en_US='Top K'
-                    )
-                )
-            )
-
-        """
-            some NOT IMPORTANT code here
-        """
-
-        entity = AIModelEntity(
-            model=model,
-            label=I18nObject(
-                en_US=model
-            ),
-            fetch_from=FetchFrom.CUSTOMIZABLE_MODEL,
-            model_type=model_type,
-            model_properties={ 
-                ModelPropertyKey.MODE:  ModelType.LLM,
-            },
-            parameter_rules=rules
-        )
-
-        return entity
-```
-
-- Exception Error Mapping
-
-When a model invocation error occurs, it should be mapped to the runtime's specified `InvokeError` type, enabling Dify to handle different errors appropriately.
-
-Runtime Errors:
-
-- `InvokeConnectionError` Connection error during invocation
-- `InvokeServerUnavailableError` Service provider unavailable
-- `InvokeRateLimitError` Rate limit reached
-- `InvokeAuthorizationError` Authorization failure
-- `InvokeBadRequestError` Invalid request parameters
-
-```python
-  @property
-  def _invoke_error_mapping(self) -> dict[type[InvokeError], list[type[Exception]]]:
-      """
-      Map model invoke error to unified error
-      The key is the error type thrown to the caller
-      The value is the error type thrown by the model,
-      which needs to be converted into a unified error type for the caller.
-  
-      :return: Invoke error mapping
-      """
-```
-
-For interface method details, see: [Interfaces](./interfaces.md). For specific implementations, refer to: [llm.py](https://github.com/langgenius/dify-runtime/blob/main/lib/model_providers/anthropic/llm/llm.py).

api/core/model_runtime/docs/en_US/interfaces.md

@@ -1,701 +0,0 @@
-# Interface Methods
-
-This section describes the interface methods and parameter explanations that need to be implemented by providers and various model types.
-
-## Provider
-
-Inherit the `__base.model_provider.ModelProvider` base class and implement the following interfaces:
-
-```python
-def validate_provider_credentials(self, credentials: dict) -> None:
-    """
-    Validate provider credentials
-    You can choose any validate_credentials method of model type or implement validate method by yourself,
-    such as: get model list api
-
-    if validate failed, raise exception
-
-    :param credentials: provider credentials, credentials form defined in `provider_credential_schema`.
-    """
-```
-
-- `credentials` (object) Credential information
-
-  The parameters of credential information are defined by the `provider_credential_schema` in the provider's YAML configuration file. Inputs such as `api_key` are included.
-
-If verification fails, throw the `errors.validate.CredentialsValidateFailedError` error.
-
-## Model
-
-Models are divided into 5 different types, each inheriting from different base classes and requiring the implementation of different methods.
-
-All models need to uniformly implement the following 2 methods:
-
-- Model Credential Verification
-
-  Similar to provider credential verification, this step involves verification for an individual model.
-
-  ```python
-  def validate_credentials(self, model: str, credentials: dict) -> None:
-      """
-      Validate model credentials
-
-      :param model: model name
-      :param credentials: model credentials
-      :return:
-      """
-  ```
-
-  Parameters:
-
-  - `model` (string) Model name
-
-  - `credentials` (object) Credential information
-
-    The parameters of credential information are defined by either the `provider_credential_schema` or `model_credential_schema` in the provider's YAML configuration file. Inputs such as `api_key` are included.
-
-  If verification fails, throw the `errors.validate.CredentialsValidateFailedError` error.
-
-- Invocation Error Mapping Table
-
-  When there is an exception in model invocation, it needs to be mapped to the `InvokeError` type specified by Runtime. This facilitates Dify's ability to handle different errors with appropriate follow-up actions.
-
-  Runtime Errors:
-
-  - `InvokeConnectionError` Invocation connection error
-  - `InvokeServerUnavailableError` Invocation service provider unavailable
-  - `InvokeRateLimitError` Invocation reached rate limit
-  - `InvokeAuthorizationError` Invocation authorization failure
-  - `InvokeBadRequestError` Invocation parameter error
-
-  ```python
-  @property
-  def _invoke_error_mapping(self) -> dict[type[InvokeError], list[type[Exception]]]:
-      """
-      Map model invoke error to unified error
-      The key is the error type thrown to the caller
-      The value is the error type thrown by the model,
-      which needs to be converted into a unified error type for the caller.
-
-      :return: Invoke error mapping
-      """
-  ```
-
-​ You can refer to OpenAI's `_invoke_error_mapping` for an example.
-
-### LLM
-
-Inherit the `__base.large_language_model.LargeLanguageModel` base class and implement the following interfaces:
-
-- LLM Invocation
-
-  Implement the core method for LLM invocation, which can support both streaming and synchronous returns.
-
-  ```python
-  def _invoke(self, model: str, credentials: dict,
-              prompt_messages: list[PromptMessage], model_parameters: dict,
-              tools: Optional[list[PromptMessageTool]] = None, stop: Optional[List[str]] = None,
-              stream: bool = True, user: Optional[str] = None) \
-          -> Union[LLMResult, Generator]:
-      """
-      Invoke large language model
-
-      :param model: model name
-      :param credentials: model credentials
-      :param prompt_messages: prompt messages
-      :param model_parameters: model parameters
-      :param tools: tools for tool calling
-      :param stop: stop words
-      :param stream: is stream response
-      :param user: unique user id
-      :return: full response or stream response chunk generator result
-      """
-  ```
-
-  - Parameters:
-
-    - `model` (string) Model name
-
-    - `credentials` (object) Credential information
-
-      The parameters of credential information are defined by either the `provider_credential_schema` or `model_credential_schema` in the provider's YAML configuration file. Inputs such as `api_key` are included.
-
-    - `prompt_messages` (array\[[PromptMessage](#PromptMessage)\]) List of prompts
-
-      If the model is of the `Completion` type, the list only needs to include one [UserPromptMessage](#UserPromptMessage) element;
-
-      If the model is of the `Chat` type, it requires a list of elements such as [SystemPromptMessage](#SystemPromptMessage), [UserPromptMessage](#UserPromptMessage), [AssistantPromptMessage](#AssistantPromptMessage), [ToolPromptMessage](#ToolPromptMessage) depending on the message.
-
-    - `model_parameters` (object) Model parameters
-
-      The model parameters are defined by the `parameter_rules` in the model's YAML configuration.
-
-    - `tools` (array\[[PromptMessageTool](#PromptMessageTool)\]) [optional] List of tools, equivalent to the `function` in `function calling`.
-
-      That is, the tool list for tool calling.
-
-    - `stop` (array[string]) [optional] Stop sequences
-
-      The model output will stop before the string defined by the stop sequence.
-
-    - `stream` (bool) Whether to output in a streaming manner, default is True
-
-      Streaming output returns Generator\[[LLMResultChunk](#LLMResultChunk)\], non-streaming output returns [LLMResult](#LLMResult).
-
-    - `user` (string) [optional] Unique identifier of the user
-
-      This can help the provider monitor and detect abusive behavior.
-
-  - Returns
-
-    Streaming output returns Generator\[[LLMResultChunk](#LLMResultChunk)\], non-streaming output returns [LLMResult](#LLMResult).
-
-- Pre-calculating Input Tokens
-
-  If the model does not provide a pre-calculated tokens interface, you can directly return 0.
-
-  ```python
-  def get_num_tokens(self, model: str, credentials: dict, prompt_messages: list[PromptMessage],
-                     tools: Optional[list[PromptMessageTool]] = None) -> int:
-      """
-      Get number of tokens for given prompt messages
-
-      :param model: model name
-      :param credentials: model credentials
-      :param prompt_messages: prompt messages
-      :param tools: tools for tool calling
-      :return:
-      """
-  ```
-
-  For parameter explanations, refer to the above section on `LLM Invocation`.
-
-- Fetch Custom Model Schema [Optional]
-
-  ```python
-  def get_customizable_model_schema(self, model: str, credentials: dict) -> Optional[AIModelEntity]:
-      """
-      Get customizable model schema
-
-      :param model: model name
-      :param credentials: model credentials
-      :return: model schema
-      """
-  ```
-
-  When the provider supports adding custom LLMs, this method can be implemented to allow custom models to fetch model schema. The default return null.
-
-### TextEmbedding
-
-Inherit the `__base.text_embedding_model.TextEmbeddingModel` base class and implement the following interfaces:
-
-- Embedding Invocation
-
-  ```python
-  def _invoke(self, model: str, credentials: dict,
-              texts: list[str], user: Optional[str] = None) \
-          -> TextEmbeddingResult:
-      """
-      Invoke large language model
-
-      :param model: model name
-      :param credentials: model credentials
-      :param texts: texts to embed
-      :param user: unique user id
-      :return: embeddings result
-      """
-  ```
-
-  - Parameters:
-
-    - `model` (string) Model name
-
-    - `credentials` (object) Credential information
-
-      The parameters of credential information are defined by either the `provider_credential_schema` or `model_credential_schema` in the provider's YAML configuration file. Inputs such as `api_key` are included.
-
-    - `texts` (array[string]) List of texts, capable of batch processing
-
-    - `user` (string) [optional] Unique identifier of the user
-
-      This can help the provider monitor and detect abusive behavior.
-
-  - Returns:
-
-    [TextEmbeddingResult](#TextEmbeddingResult) entity.
-
-- Pre-calculating Tokens
-
-  ```python
-  def get_num_tokens(self, model: str, credentials: dict, texts: list[str]) -> int:
-      """
-      Get number of tokens for given prompt messages
-
-      :param model: model name
-      :param credentials: model credentials
-      :param texts: texts to embed
-      :return:
-      """
-  ```
-
-  For parameter explanations, refer to the above section on `Embedding Invocation`.
-
-### Rerank
-
-Inherit the `__base.rerank_model.RerankModel` base class and implement the following interfaces:
-
-- Rerank Invocation
-
-  ```python
-  def _invoke(self, model: str, credentials: dict,
-              query: str, docs: list[str], score_threshold: Optional[float] = None, top_n: Optional[int] = None,
-              user: Optional[str] = None) \
-          -> RerankResult:
-      """
-      Invoke rerank model
-
-      :param model: model name
-      :param credentials: model credentials
-      :param query: search query
-      :param docs: docs for reranking
-      :param score_threshold: score threshold
-      :param top_n: top n
-      :param user: unique user id
-      :return: rerank result
-      """
-  ```
-
-  - Parameters:
-
-    - `model` (string) Model name
-
-    - `credentials` (object) Credential information
-
-      The parameters of credential information are defined by either the `provider_credential_schema` or `model_credential_schema` in the provider's YAML configuration file. Inputs such as `api_key` are included.
-
-    - `query` (string) Query request content
-
-    - `docs` (array[string]) List of segments to be reranked
-
-    - `score_threshold` (float) [optional] Score threshold
-
-    - `top_n` (int) [optional] Select the top n segments
-
-    - `user` (string) [optional] Unique identifier of the user
-
-      This can help the provider monitor and detect abusive behavior.
-
-  - Returns:
-
-    [RerankResult](#RerankResult) entity.
-
-### Speech2text
-
-Inherit the `__base.speech2text_model.Speech2TextModel` base class and implement the following interfaces:
-
-- Invoke Invocation
-
-  ```python
-  def _invoke(self, model: str, credentials: dict, file: IO[bytes], user: Optional[str] = None) -> str:
-      """
-      Invoke large language model
-
-      :param model: model name
-      :param credentials: model credentials
-      :param file: audio file
-      :param user: unique user id
-      :return: text for given audio file
-      """	
-  ```
-
-  - Parameters:
-
-    - `model` (string) Model name
-
-    - `credentials` (object) Credential information
-
-      The parameters of credential information are defined by either the `provider_credential_schema` or `model_credential_schema` in the provider's YAML configuration file. Inputs such as `api_key` are included.
-
-    - `file` (File) File stream
-
-    - `user` (string) [optional] Unique identifier of the user
-
-      This can help the provider monitor and detect abusive behavior.
-
-  - Returns:
-
-    The string after speech-to-text conversion.
-
-### Text2speech
-
-Inherit the `__base.text2speech_model.Text2SpeechModel` base class and implement the following interfaces:
-
-- Invoke Invocation
-
-  ```python
-  def _invoke(self, model: str, credentials: dict, content_text: str, streaming: bool, user: Optional[str] = None):
-      """
-      Invoke large language model
-
-      :param model: model name
-      :param credentials: model credentials
-      :param content_text: text content to be translated
-      :param streaming: output is streaming
-      :param user: unique user id
-      :return: translated audio file
-      """	
-  ```
-
-  - Parameters：
-
-    - `model` (string) Model name
-
-    - `credentials` (object) Credential information
-
-      The parameters of credential information are defined by either the `provider_credential_schema` or `model_credential_schema` in the provider's YAML configuration file. Inputs such as `api_key` are included.
-
-    - `content_text` (string) The text content that needs to be converted
-
-    - `streaming` (bool) Whether to stream output
-
-    - `user` (string) [optional] Unique identifier of the user
-
-      This can help the provider monitor and detect abusive behavior.
-
-  - Returns：
-
-    Text converted speech stream.
-
-### Moderation
-
-Inherit the `__base.moderation_model.ModerationModel` base class and implement the following interfaces:
-
-- Invoke Invocation
-
-  ```python
-  def _invoke(self, model: str, credentials: dict,
-              text: str, user: Optional[str] = None) \
-          -> bool:
-      """
-      Invoke large language model
-
-      :param model: model name
-      :param credentials: model credentials
-      :param text: text to moderate
-      :param user: unique user id
-      :return: false if text is safe, true otherwise
-      """
-  ```
-
-  - Parameters:
-
-    - `model` (string) Model name
-
-    - `credentials` (object) Credential information
-
-      The parameters of credential information are defined by either the `provider_credential_schema` or `model_credential_schema` in the provider's YAML configuration file. Inputs such as `api_key` are included.
-
-    - `text` (string) Text content
-
-    - `user` (string) [optional] Unique identifier of the user
-
-      This can help the provider monitor and detect abusive behavior.
-
-  - Returns:
-
-    False indicates that the input text is safe, True indicates otherwise.
-
-## Entities
-
-### PromptMessageRole
-
-Message role
-
-```python
-class PromptMessageRole(Enum):
-    """
-    Enum class for prompt message.
-    """
-    SYSTEM = "system"
-    USER = "user"
-    ASSISTANT = "assistant"
-    TOOL = "tool"
-```
-
-### PromptMessageContentType
-
-Message content types, divided into text and image.
-
-```python
-class PromptMessageContentType(Enum):
-    """
-    Enum class for prompt message content type.
-    """
-    TEXT = 'text'
-    IMAGE = 'image'
-```
-
-### PromptMessageContent
-
-Message content base class, used only for parameter declaration and cannot be initialized.
-
-```python
-class PromptMessageContent(BaseModel):
-    """
-    Model class for prompt message content.
-    """
-    type: PromptMessageContentType
-    data: str
-```
-
-Currently, two types are supported: text and image. It's possible to simultaneously input text and multiple images.
-
-You need to initialize `TextPromptMessageContent` and `ImagePromptMessageContent` separately for input.
-
-### TextPromptMessageContent
-
-```python
-class TextPromptMessageContent(PromptMessageContent):
-    """
-    Model class for text prompt message content.
-    """
-    type: PromptMessageContentType = PromptMessageContentType.TEXT
-```
-
-If inputting a combination of text and images, the text needs to be constructed into this entity as part of the `content` list.
-
-### ImagePromptMessageContent
-
-```python
-class ImagePromptMessageContent(PromptMessageContent):
-    """
-    Model class for image prompt message content.
-    """
-    class DETAIL(Enum):
-        LOW = 'low'
-        HIGH = 'high'
-
-    type: PromptMessageContentType = PromptMessageContentType.IMAGE
-    detail: DETAIL = DETAIL.LOW  # Resolution
-```
-
-If inputting a combination of text and images, the images need to be constructed into this entity as part of the `content` list.
-
-`data` can be either a `url` or a `base64` encoded string of the image.
-
-### PromptMessage
-
-The base class for all Role message bodies, used only for parameter declaration and cannot be initialized.
-
-```python
-class PromptMessage(BaseModel):
-    """
-    Model class for prompt message.
-    """
-    role: PromptMessageRole
-    content: Optional[str | list[PromptMessageContent]] = None  # Supports two types: string and content list. The content list is designed to meet the needs of multimodal inputs. For more details, see the PromptMessageContent explanation.
-    name: Optional[str] = None
-```
-
-### UserPromptMessage
-
-UserMessage message body, representing a user's message.
-
-```python
-class UserPromptMessage(PromptMessage):
-    """
-    Model class for user prompt message.
-    """
-    role: PromptMessageRole = PromptMessageRole.USER
-```
-
-### AssistantPromptMessage
-
-Represents a message returned by the model, typically used for `few-shots` or inputting chat history.
-
-```python
-class AssistantPromptMessage(PromptMessage):
-    """
-    Model class for assistant prompt message.
-    """
-    class ToolCall(BaseModel):
-        """
-        Model class for assistant prompt message tool call.
-        """
-        class ToolCallFunction(BaseModel):
-            """
-            Model class for assistant prompt message tool call function.
-            """
-            name: str  # tool name
-            arguments: str  # tool arguments
-
-        id: str  # Tool ID, effective only in OpenAI tool calls. It's the unique ID for tool invocation and the same tool can be called multiple times.
-        type: str  # default: function
-        function: ToolCallFunction  # tool call information
-
-    role: PromptMessageRole = PromptMessageRole.ASSISTANT
-    tool_calls: list[ToolCall] = []  # The result of tool invocation in response from the model (returned only when tools are input and the model deems it necessary to invoke a tool).
-```
-
-Where `tool_calls` are the list of `tool calls` returned by the model after invoking the model with the `tools` input.
-
-### SystemPromptMessage
-
-Represents system messages, usually used for setting system commands given to the model.
-
-```python
-class SystemPromptMessage(PromptMessage):
-    """
-    Model class for system prompt message.
-    """
-    role: PromptMessageRole = PromptMessageRole.SYSTEM
-```
-
-### ToolPromptMessage
-
-Represents tool messages, used for conveying the results of a tool execution to the model for the next step of processing.
-
-```python
-class ToolPromptMessage(PromptMessage):
-    """
-    Model class for tool prompt message.
-    """
-    role: PromptMessageRole = PromptMessageRole.TOOL
-    tool_call_id: str  # Tool invocation ID. If OpenAI tool call is not supported, the name of the tool can also be inputted.
-```
-
-The base class's `content` takes in the results of tool execution.
-
-### PromptMessageTool
-
-```python
-class PromptMessageTool(BaseModel):
-    """
-    Model class for prompt message tool.
-    """
-    name: str
-    description: str
-    parameters: dict
-```
-
-______________________________________________________________________
-
-### LLMResult
-
-```python
-class LLMResult(BaseModel):
-    """
-    Model class for llm result.
-    """
-    model: str  # Actual used modele
-    prompt_messages: list[PromptMessage]  # prompt messages
-    message: AssistantPromptMessage  # response message
-    usage: LLMUsage  # usage info
-    system_fingerprint: Optional[str] = None  # request fingerprint, refer to OpenAI definition
-```
-
-### LLMResultChunkDelta
-
-In streaming returns, each iteration contains the `delta` entity.
-
-```python
-class LLMResultChunkDelta(BaseModel):
-    """
-    Model class for llm result chunk delta.
-    """
-    index: int
-    message: AssistantPromptMessage  # response message
-    usage: Optional[LLMUsage] = None  # usage info
-    finish_reason: Optional[str] = None  # finish reason, only the last one returns
-```
-
-### LLMResultChunk
-
-Each iteration entity in streaming returns.
-
-```python
-class LLMResultChunk(BaseModel):
-    """
-    Model class for llm result chunk.
-    """
-    model: str  # Actual used modele
-    prompt_messages: list[PromptMessage]  # prompt messages
-    system_fingerprint: Optional[str] = None  # request fingerprint, refer to OpenAI definition
-    delta: LLMResultChunkDelta
-```
-
-### LLMUsage
-
-```python
-class LLMUsage(ModelUsage):
-    """
-    Model class for LLM usage.
-    """
-    prompt_tokens: int  # Tokens used for prompt
-    prompt_unit_price: Decimal  # Unit price for prompt
-    prompt_price_unit: Decimal  # Price unit for prompt, i.e., the unit price based on how many tokens
-    prompt_price: Decimal  # Cost for prompt
-    completion_tokens: int  # Tokens used for response
-    completion_unit_price: Decimal  # Unit price for response
-    completion_price_unit: Decimal  # Price unit for response, i.e., the unit price based on how many tokens
-    completion_price: Decimal  # Cost for response
-    total_tokens: int  # Total number of tokens used
-    total_price: Decimal  # Total cost
-    currency: str  # Currency unit
-    latency: float  # Request latency (s)
-```
-
-______________________________________________________________________
-
-### TextEmbeddingResult
-
-```python
-class TextEmbeddingResult(BaseModel):
-    """
-    Model class for text embedding result.
-    """
-    model: str  # Actual model used
-    embeddings: list[list[float]]  # List of embedding vectors, corresponding to the input texts list
-    usage: EmbeddingUsage  # Usage information
-```
-
-### EmbeddingUsage
-
-```python
-class EmbeddingUsage(ModelUsage):
-    """
-    Model class for embedding usage.
-    """
-    tokens: int  # Number of tokens used
-    total_tokens: int  # Total number of tokens used
-    unit_price: Decimal  # Unit price
-    price_unit: Decimal  # Price unit, i.e., the unit price based on how many tokens
-    total_price: Decimal  # Total cost
-    currency: str  # Currency unit
-    latency: float  # Request latency (s)
-```
-
-______________________________________________________________________
-
-### RerankResult
-
-```python
-class RerankResult(BaseModel):
-    """
-    Model class for rerank result.
-    """
-    model: str  # Actual model used
-    docs: list[RerankDocument]  # Reranked document list	
-```
-
-### RerankDocument
-
-```python
-class RerankDocument(BaseModel):
-    """
-    Model class for rerank document.
-    """
-    index: int  # original index
-    text: str
-    score: float
-```

api/core/model_runtime/docs/en_US/predefined_model_scale_out.md

@@ -1,176 +0,0 @@
-## Predefined Model Integration
-
-After completing the vendor integration, the next step is to integrate the models from the vendor.
-
-First, we need to determine the type of model to be integrated and create the corresponding model type `module` under the respective vendor's directory.
-
-Currently supported model types are:
-
-- `llm` Text Generation Model
-- `text_embedding` Text Embedding Model
-- `rerank` Rerank Model
-- `speech2text` Speech-to-Text
-- `tts` Text-to-Speech
-- `moderation` Moderation
-
-Continuing with `Anthropic` as an example, `Anthropic` only supports LLM, so create a `module` named `llm` under `model_providers.anthropic`.
-
-For predefined models, we first need to create a YAML file named after the model under the `llm` `module`, such as `claude-2.1.yaml`.
-
-### Prepare Model YAML
-
-```yaml
-model: claude-2.1  # Model identifier
-# Display name of the model, which can be set to en_US English or zh_Hans Chinese. If zh_Hans is not set, it will default to en_US.
-# This can also be omitted, in which case the model identifier will be used as the label
-label:
-  en_US: claude-2.1
-model_type: llm  # Model type, claude-2.1 is an LLM
-features:  # Supported features, agent-thought supports Agent reasoning, vision supports image understanding
-- agent-thought
-model_properties:  # Model properties
-  mode: chat  # LLM mode, complete for text completion models, chat for conversation models
-  context_size: 200000  # Maximum context size
-parameter_rules:  # Parameter rules for the model call; only LLM requires this
-- name: temperature  # Parameter variable name
-  # Five default configuration templates are provided: temperature/top_p/max_tokens/presence_penalty/frequency_penalty
-  # The template variable name can be set directly in use_template, which will use the default configuration in entities.defaults.PARAMETER_RULE_TEMPLATE
-  # Additional configuration parameters will override the default configuration if set
-  use_template: temperature
-- name: top_p
-  use_template: top_p
-- name: top_k
-  label:  # Display name of the parameter
-    zh_Hans: 取样数量
-    en_US: Top k
-  type: int  # Parameter type, supports float/int/string/boolean
-  help:  # Help information, describing the parameter's function
-    zh_Hans: 仅从每个后续标记的前 K 个选项中采样。
-    en_US: Only sample from the top K options for each subsequent token.
-  required: false  # Whether the parameter is mandatory; can be omitted
-- name: max_tokens_to_sample
-  use_template: max_tokens
-  default: 4096  # Default value of the parameter
-  min: 1  # Minimum value of the parameter, applicable to float/int only
-  max: 4096  # Maximum value of the parameter, applicable to float/int only
-pricing:  # Pricing information
-  input: '8.00'  # Input unit price, i.e., prompt price
-  output: '24.00'  # Output unit price, i.e., response content price
-  unit: '0.000001'  # Price unit, meaning the above prices are per 100K
-  currency: USD  # Price currency
-```
-
-It is recommended to prepare all model configurations before starting the implementation of the model code.
-
-You can also refer to the YAML configuration information under the corresponding model type directories of other vendors in the `model_providers` directory. For the complete YAML rules, refer to: [Schema](schema.md#aimodelentity).
-
-### Implement the Model Call Code
-
-Next, create a Python file named `llm.py` under the `llm` `module` to write the implementation code.
-
-Create an Anthropic LLM class named `AnthropicLargeLanguageModel` (or any other name), inheriting from the `__base.large_language_model.LargeLanguageModel` base class, and implement the following methods:
-
-- LLM Call
-
-Implement the core method for calling the LLM, supporting both streaming and synchronous responses.
-
-```python
-  def _invoke(self, model: str, credentials: dict,
-              prompt_messages: list[PromptMessage], model_parameters: dict,
-              tools: Optional[list[PromptMessageTool]] = None, stop: Optional[list[str]] = None,
-              stream: bool = True, user: Optional[str] = None) \
-          -> Union[LLMResult, Generator]:
-      """
-      Invoke large language model
-  
-      :param model: model name
-      :param credentials: model credentials
-      :param prompt_messages: prompt messages
-      :param model_parameters: model parameters
-      :param tools: tools for tool calling
-      :param stop: stop words
-      :param stream: is stream response
-      :param user: unique user id
-      :return: full response or stream response chunk generator result
-      """
-```
-
-Ensure to use two functions for returning data, one for synchronous returns and the other for streaming returns, because Python identifies functions containing the `yield` keyword as generator functions, fixing the return type to `Generator`. Thus, synchronous and streaming returns need to be implemented separately, as shown below (note that the example uses simplified parameters, for actual implementation follow the above parameter list):
-
-```python
-  def _invoke(self, stream: bool, **kwargs) \
-          -> Union[LLMResult, Generator]:
-      if stream:
-            return self._handle_stream_response(**kwargs)
-      return self._handle_sync_response(**kwargs)
-
-  def _handle_stream_response(self, **kwargs) -> Generator:
-      for chunk in response:
-            yield chunk
-  def _handle_sync_response(self, **kwargs) -> LLMResult:
-      return LLMResult(**response)
-```
-
-- Pre-compute Input Tokens
-
-If the model does not provide an interface to precompute tokens, return 0 directly.
-
-```python
-  def get_num_tokens(self, model: str, credentials: dict, prompt_messages: list[PromptMessage],
-                     tools: Optional[list[PromptMessageTool]] = None) -> int:
-      """
-      Get number of tokens for given prompt messages
-
-      :param model: model name
-      :param credentials: model credentials
-      :param prompt_messages: prompt messages
-      :param tools: tools for tool calling
-      :return:
-      """
-```
-
-- Validate Model Credentials
-
-Similar to vendor credential validation, but specific to a single model.
-
-```python
-  def validate_credentials(self, model: str, credentials: dict) -> None:
-      """
-      Validate model credentials
-  
-      :param model: model name
-      :param credentials: model credentials
-      :return:
-      """
-```
-
-- Map Invoke Errors
-
-When a model call fails, map it to a specific `InvokeError` type as required by Runtime, allowing Dify to handle different errors accordingly.
-
-Runtime Errors:
-
-- `InvokeConnectionError` Connection error
-
-- `InvokeServerUnavailableError` Service provider unavailable
-
-- `InvokeRateLimitError` Rate limit reached
-
-- `InvokeAuthorizationError` Authorization failed
-
-- `InvokeBadRequestError` Parameter error
-
-```python
-  @property
-  def _invoke_error_mapping(self) -> dict[type[InvokeError], list[type[Exception]]]:
-      """
-      Map model invoke error to unified error
-      The key is the error type thrown to the caller
-      The value is the error type thrown by the model,
-      which needs to be converted into a unified error type for the caller.
-  
-      :return: Invoke error mapping
-      """
-```
-
-For interface method explanations, see: [Interfaces](./interfaces.md). For detailed implementation, refer to: [llm.py](https://github.com/langgenius/dify-runtime/blob/main/lib/model_providers/anthropic/llm/llm.py).

api/core/model_runtime/docs/en_US/provider_scale_out.md

@@ -1,266 +0,0 @@
-## Adding a New Provider
-
-Providers support three types of model configuration methods:
-
-- `predefined-model` Predefined model
-
-  This indicates that users only need to configure the unified provider credentials to use the predefined models under the provider.
-
-- `customizable-model` Customizable model
-
-  Users need to add credential configurations for each model.
-
-- `fetch-from-remote` Fetch from remote
-
-  This is consistent with the `predefined-model` configuration method. Only unified provider credentials need to be configured, and models are obtained from the provider through credential information.
-
-These three configuration methods **can coexist**, meaning a provider can support `predefined-model` + `customizable-model` or `predefined-model` + `fetch-from-remote`, etc. In other words, configuring the unified provider credentials allows the use of predefined and remotely fetched models, and if new models are added, they can be used in addition to the custom models.
-
-## Getting Started
-
-Adding a new provider starts with determining the English identifier of the provider, such as `anthropic`, and using this identifier to create a `module` in `model_providers`.
-
-Under this `module`, we first need to prepare the provider's YAML configuration.
-
-### Preparing Provider YAML
-
-Here, using `Anthropic` as an example, we preset the provider's basic information, supported model types, configuration methods, and credential rules.
-
-```YAML
-provider: anthropic  # Provider identifier
-label:  # Provider display name, can be set in en_US English and zh_Hans Chinese, zh_Hans will default to en_US if not set.
-  en_US: Anthropic
-icon_small:  # Small provider icon, stored in the _assets directory under the corresponding provider implementation directory, same language strategy as label
-  en_US: icon_s_en.png
-icon_large:  # Large provider icon, stored in the _assets directory under the corresponding provider implementation directory, same language strategy as label
-  en_US: icon_l_en.png
-supported_model_types:  # Supported model types, Anthropic only supports LLM
-- llm
-configurate_methods:  # Supported configuration methods, Anthropic only supports predefined models
-- predefined-model
-provider_credential_schema:  # Provider credential rules, as Anthropic only supports predefined models, unified provider credential rules need to be defined
-  credential_form_schemas:  # List of credential form items
-  - variable: anthropic_api_key  # Credential parameter variable name
-    label:  # Display name
-      en_US: API Key
-    type: secret-input  # Form type, here secret-input represents an encrypted information input box, showing masked information when editing.
-    required: true  # Whether required
-    placeholder:  # Placeholder information
-      zh_Hans: Enter your API Key here
-      en_US: Enter your API Key
-  - variable: anthropic_api_url
-    label:
-      en_US: API URL
-    type: text-input  # Form type, here text-input represents a text input box
-    required: false
-    placeholder:
-      zh_Hans: Enter your API URL here
-      en_US: Enter your API URL
-```
-
-You can also refer to the YAML configuration information under other provider directories in `model_providers`. The complete YAML rules are available at: [Schema](schema.md#provider).
-
-### Implementing Provider Code
-
-Providers need to inherit the `__base.model_provider.ModelProvider` base class and implement the `validate_provider_credentials` method for unified provider credential verification. For reference, see [AnthropicProvider](https://github.com/langgenius/dify-runtime/blob/main/lib/model_providers/anthropic/anthropic.py).
-
-> If the provider is the type of `customizable-model`, there is no need to implement the `validate_provider_credentials` method.
-
-```python
-def validate_provider_credentials(self, credentials: dict) -> None:
-    """
-    Validate provider credentials
-    You can choose any validate_credentials method of model type or implement validate method by yourself,
-    such as: get model list api
-
-    if validate failed, raise exception
-
-    :param credentials: provider credentials, credentials form defined in `provider_credential_schema`.
-    """
-```
-
-Of course, you can also preliminarily reserve the implementation of `validate_provider_credentials` and directly reuse it after the model credential verification method is implemented.
-
-______________________________________________________________________
-
-### Adding Models
-
-After the provider integration is complete, the next step is to integrate models under the provider.
-
-First, we need to determine the type of the model to be integrated and create a `module` for the corresponding model type in the provider's directory.
-
-The currently supported model types are as follows:
-
-- `llm` Text generation model
-- `text_embedding` Text Embedding model
-- `rerank` Rerank model
-- `speech2text` Speech to text
-- `tts` Text to speech
-- `moderation` Moderation
-
-Continuing with `Anthropic` as an example, since `Anthropic` only supports LLM, we create a `module` named `llm` in `model_providers.anthropic`.
-
-For predefined models, we first need to create a YAML file named after the model, such as `claude-2.1.yaml`, under the `llm` `module`.
-
-#### Preparing Model YAML
-
-```yaml
-model: claude-2.1  # Model identifier
-# Model display name, can be set in en_US English and zh_Hans Chinese, zh_Hans will default to en_US if not set.
-# Alternatively, if the label is not set, use the model identifier content.
-label:
-  en_US: claude-2.1
-model_type: llm  # Model type, claude-2.1 is an LLM
-features:  # Supported features, agent-thought for Agent reasoning, vision for image understanding
-- agent-thought
-model_properties:  # Model properties
-  mode: chat  # LLM mode, complete for text completion model, chat for dialogue model
-  context_size: 200000  # Maximum supported context size
-parameter_rules:  # Model invocation parameter rules, only required for LLM
-- name: temperature  # Invocation parameter variable name
-  # Default preset with 5 variable content configuration templates: temperature/top_p/max_tokens/presence_penalty/frequency_penalty
-  # Directly set the template variable name in use_template, which will use the default configuration in entities.defaults.PARAMETER_RULE_TEMPLATE
-  # If additional configuration parameters are set, they will override the default configuration
-  use_template: temperature
-- name: top_p
-  use_template: top_p
-- name: top_k
-  label:  # Invocation parameter display name
-    zh_Hans: Sampling quantity
-    en_US: Top k
-  type: int  # Parameter type, supports float/int/string/boolean
-  help:  # Help information, describing the role of the parameter
-    zh_Hans: Only sample from the top K options for each subsequent token.
-    en_US: Only sample from the top K options for each subsequent token.
-  required: false  # Whether required, can be left unset
-- name: max_tokens_to_sample
-  use_template: max_tokens
-  default: 4096  # Default parameter value
-  min: 1  # Minimum parameter value, only applicable for float/int
-  max: 4096  # Maximum parameter value, only applicable for float/int
-pricing:  # Pricing information
-  input: '8.00'  # Input price, i.e., Prompt price
-  output: '24.00'  # Output price, i.e., returned content price
-  unit: '0.000001'  # Pricing unit, i.e., the above prices are per 100K
-  currency: USD  # Currency
-```
-
-It is recommended to prepare all model configurations before starting the implementation of the model code.
-
-Similarly, you can also refer to the YAML configuration information for corresponding model types of other providers in the `model_providers` directory. The complete YAML rules can be found at: [Schema](schema.md#AIModel).
-
-#### Implementing Model Invocation Code
-
-Next, you need to create a python file named `llm.py` under the `llm` `module` to write the implementation code.
-
-In `llm.py`, create an Anthropic LLM class, which we name `AnthropicLargeLanguageModel` (arbitrarily), inheriting the `__base.large_language_model.LargeLanguageModel` base class, and implement the following methods:
-
-- LLM Invocation
-
-  Implement the core method for LLM invocation, which can support both streaming and synchronous returns.
-
-  ```python
-  def _invoke(self, model: str, credentials: dict,
-              prompt_messages: list[PromptMessage], model_parameters: dict,
-              tools: Optional[list[PromptMessageTool]] = None, stop: Optional[list[str]] = None,
-              stream: bool = True, user: Optional[str] = None) \
-          -> Union[LLMResult, Generator]:
-      """
-      Invoke large language model
-
-      :param model: model name
-      :param credentials: model credentials
-      :param prompt_messages: prompt messages
-      :param model_parameters: model parameters
-      :param tools: tools for tool calling
-      :param stop: stop words
-      :param stream: is stream response
-      :param user: unique user id
-      :return: full response or stream response chunk generator result
-      """
-  ```
-
-- Pre-calculating Input Tokens
-
-  If the model does not provide a pre-calculated tokens interface, you can directly return 0.
-
-  ```python
-  def get_num_tokens(self, model: str, credentials: dict, prompt_messages: list[PromptMessage],
-                   tools: Optional[list[PromptMessageTool]] = None) -> int:
-    """
-    Get number of tokens for given prompt messages
-
-    :param model: model name
-    :param credentials: model credentials
-    :param prompt_messages: prompt messages
-    :param tools: tools for tool calling
-    :return:
-    """
-  ```
-
-- Model Credential Verification
-
-  Similar to provider credential verification, this step involves verification for an individual model.
-
-  ```python
-  def validate_credentials(self, model: str, credentials: dict) -> None:
-      """
-      Validate model credentials
-
-      :param model: model name
-      :param credentials: model credentials
-      :return:
-      """
-  ```
-
-- Invocation Error Mapping Table
-
-  When there is an exception in model invocation, it needs to be mapped to the `InvokeError` type specified by Runtime. This facilitates Dify's ability to handle different errors with appropriate follow-up actions.
-
-  Runtime Errors:
-
-  - `InvokeConnectionError` Invocation connection error
-  - `InvokeServerUnavailableError` Invocation service provider unavailable
-  - `InvokeRateLimitError` Invocation reached rate limit
-  - `InvokeAuthorizationError` Invocation authorization failure
-  - `InvokeBadRequestError` Invocation parameter error
-
-  ```python
-  @property
-  def _invoke_error_mapping(self) -> dict[type[InvokeError], list[type[Exception]]]:
-      """
-      Map model invoke error to unified error
-      The key is the error type thrown to the caller
-      The value is the error type thrown by the model,
-      which needs to be converted into a unified error type for the caller.
-
-      :return: Invoke error mapping
-      """
-  ```
-
-For details on the interface methods, see: [Interfaces](interfaces.md). For specific implementations, refer to: [llm.py](https://github.com/langgenius/dify-runtime/blob/main/lib/model_providers/anthropic/llm/llm.py).
-
-### Testing
-
-To ensure the availability of integrated providers/models, each method written needs corresponding integration test code in the `tests` directory.
-
-Continuing with `Anthropic` as an example:
-
-Before writing test code, you need to first add the necessary credential environment variables for the test provider in `.env.example`, such as: `ANTHROPIC_API_KEY`.
-
-Before execution, copy `.env.example` to `.env` and then execute.
-
-#### Writing Test Code
-
-Create a `module` with the same name as the provider in the `tests` directory: `anthropic`, and continue to create `test_provider.py` and test py files for the corresponding model types within this module, as shown below:
-
-```shell
-.
-├── __init__.py
-├── anthropic
-│   ├── __init__.py
-│   ├── test_llm.py       # LLM Testing
-│   └── test_provider.py  # Provider Testing
-```
-
-Write test code for all the various cases implemented above and submit the code after passing the tests.

api/core/model_runtime/docs/en_US/schema.md

@@ -1,208 +0,0 @@
-# Configuration Rules
-
-- Provider rules are based on the [Provider](#Provider) entity.
-- Model rules are based on the [AIModelEntity](#AIModelEntity) entity.
-
-> All entities mentioned below are based on `Pydantic BaseModel` and can be found in the `entities` module.
-
-### Provider
-
-- `provider` (string) Provider identifier, e.g., `openai`
-- `label` (object) Provider display name, i18n, with `en_US` English and `zh_Hans` Chinese language settings
-  - `zh_Hans` (string) [optional] Chinese label name, if `zh_Hans` is not set, `en_US` will be used by default.
-  - `en_US` (string) English label name
-- `description` (object) Provider description, i18n
-  - `zh_Hans` (string) [optional] Chinese description
-  - `en_US` (string) English description
-- `icon_small` (string) [optional] Small provider ICON, stored in the `_assets` directory under the corresponding provider implementation directory, with the same language strategy as `label`
-  - `zh_Hans` (string) Chinese ICON
-  - `en_US` (string) English ICON
-- `icon_large` (string) [optional] Large provider ICON, stored in the `_assets` directory under the corresponding provider implementation directory, with the same language strategy as `label`
-  - `zh_Hans` (string) Chinese ICON
-  - `en_US` (string) English ICON
-- `background` (string) [optional] Background color value, e.g., #FFFFFF, if empty, the default frontend color value will be displayed.
-- `help` (object) [optional] help information
-  - `title` (object) help title, i18n
-    - `zh_Hans` (string) [optional] Chinese title
-    - `en_US` (string) English title
-  - `url` (object) help link, i18n
-    - `zh_Hans` (string) [optional] Chinese link
-    - `en_US` (string) English link
-- `supported_model_types` (array\[[ModelType](#ModelType)\]) Supported model types
-- `configurate_methods` (array\[[ConfigurateMethod](#ConfigurateMethod)\]) Configuration methods
-- `provider_credential_schema` ([ProviderCredentialSchema](#ProviderCredentialSchema)) Provider credential specification
-- `model_credential_schema` ([ModelCredentialSchema](#ModelCredentialSchema)) Model credential specification
-
-### AIModelEntity
-
-- `model` (string) Model identifier, e.g., `gpt-3.5-turbo`
-- `label` (object) [optional] Model display name, i18n, with `en_US` English and `zh_Hans` Chinese language settings
-  - `zh_Hans` (string) [optional] Chinese label name
-  - `en_US` (string) English label name
-- `model_type` ([ModelType](#ModelType)) Model type
-- `features` (array\[[ModelFeature](#ModelFeature)\]) [optional] Supported feature list
-- `model_properties` (object) Model properties
-  - `mode` ([LLMMode](#LLMMode)) Mode (available for model type `llm`)
-  - `context_size` (int) Context size (available for model types `llm`, `text-embedding`)
-  - `max_chunks` (int) Maximum number of chunks (available for model types `text-embedding`, `moderation`)
-  - `file_upload_limit` (int) Maximum file upload limit, in MB (available for model type `speech2text`)
-  - `supported_file_extensions` (string) Supported file extension formats, e.g., mp3, mp4 (available for model type `speech2text`)
-  - `default_voice` (string) default voice, e.g.：alloy,echo,fable,onyx,nova,shimmer（available for model type `tts`）
-  - `voices` (list) List of available voice.（available for model type `tts`）
-    - `mode` (string) voice model.（available for model type `tts`）
-    - `name` (string) voice model display name.（available for model type `tts`）
-    - `language` (string) the voice model supports languages.（available for model type `tts`）
-  - `word_limit` (int) Single conversion word limit, paragraph-wise by default（available for model type `tts`）
-  - `audio_type` (string) Support audio file extension format, e.g.：mp3,wav（available for model type `tts`）
-  - `max_workers` (int) Number of concurrent workers supporting text and audio conversion（available for model type`tts`）
-  - `max_characters_per_chunk` (int) Maximum characters per chunk (available for model type `moderation`)
-- `parameter_rules` (array\[[ParameterRule](#ParameterRule)\]) [optional] Model invocation parameter rules
-- `pricing` ([PriceConfig](#PriceConfig)) [optional] Pricing information
-- `deprecated` (bool) Whether deprecated. If deprecated, the model will no longer be displayed in the list, but those already configured can continue to be used. Default False.
-
-### ModelType
-
-- `llm` Text generation model
-- `text-embedding` Text Embedding model
-- `rerank` Rerank model
-- `speech2text` Speech to text
-- `tts` Text to speech
-- `moderation` Moderation
-
-### ConfigurateMethod
-
-- `predefined-model` Predefined model
-
-  Indicates that users can use the predefined models under the provider by configuring the unified provider credentials.
-
-- `customizable-model` Customizable model
-
-  Users need to add credential configuration for each model.
-
-- `fetch-from-remote` Fetch from remote
-
-  Consistent with the `predefined-model` configuration method, only unified provider credentials need to be configured, and models are obtained from the provider through credential information.
-
-### ModelFeature
-
-- `agent-thought` Agent reasoning, generally over 70B with thought chain capability.
-- `vision` Vision, i.e., image understanding.
-- `tool-call`
-- `multi-tool-call`
-- `stream-tool-call`
-
-### FetchFrom
-
-- `predefined-model` Predefined model
-- `fetch-from-remote` Remote model
-
-### LLMMode
-
-- `complete` Text completion
-- `chat` Dialogue
-
-### ParameterRule
-
-- `name` (string) Actual model invocation parameter name
-
-- `use_template` (string) [optional] Using template
-
-  By default, 5 variable content configuration templates are preset:
-
-  - `temperature`
-  - `top_p`
-  - `frequency_penalty`
-  - `presence_penalty`
-  - `max_tokens`
-
-  In use_template, you can directly set the template variable name, which will use the default configuration in entities.defaults.PARAMETER_RULE_TEMPLATE
-  No need to set any parameters other than `name` and `use_template`. If additional configuration parameters are set, they will override the default configuration.
-  Refer to `openai/llm/gpt-3.5-turbo.yaml`.
-
-- `label` (object) [optional] Label, i18n
-
-  - `zh_Hans`(string) [optional] Chinese label name
-  - `en_US` (string) English label name
-
-- `type`(string) [optional] Parameter type
-
-  - `int` Integer
-  - `float` Float
-  - `string` String
-  - `boolean` Boolean
-
-- `help` (string) [optional] Help information
-
-  - `zh_Hans` (string) [optional] Chinese help information
-  - `en_US` (string) English help information
-
-- `required` (bool) Required, default False.
-
-- `default`(int/float/string/bool) [optional] Default value
-
-- `min`(int/float) [optional] Minimum value, applicable only to numeric types
-
-- `max`(int/float) [optional] Maximum value, applicable only to numeric types
-
-- `precision`(int) [optional] Precision, number of decimal places to keep, applicable only to numeric types
-
-- `options` (array[string]) [optional] Dropdown option values, applicable only when `type` is `string`, if not set or null, option values are not restricted
-
-### PriceConfig
-
-- `input` (float) Input price, i.e., Prompt price
-- `output` (float) Output price, i.e., returned content price
-- `unit` (float) Pricing unit, e.g., if the price is measured in 1M tokens, the corresponding token amount for the unit price is `0.000001`.
-- `currency` (string) Currency unit
-
-### ProviderCredentialSchema
-
-- `credential_form_schemas` (array\[[CredentialFormSchema](#CredentialFormSchema)\]) Credential form standard
-
-### ModelCredentialSchema
-
-- `model` (object) Model identifier, variable name defaults to `model`
-  - `label` (object) Model form item display name
-    - `en_US` (string) English
-    - `zh_Hans`(string) [optional] Chinese
-  - `placeholder` (object) Model prompt content
-    - `en_US`(string) English
-    - `zh_Hans`(string) [optional] Chinese
-- `credential_form_schemas` (array\[[CredentialFormSchema](#CredentialFormSchema)\]) Credential form standard
-
-### CredentialFormSchema
-
-- `variable` (string) Form item variable name
-- `label` (object) Form item label name
-  - `en_US`(string) English
-  - `zh_Hans` (string) [optional] Chinese
-- `type` ([FormType](#FormType)) Form item type
-- `required` (bool) Whether required
-- `default`(string) Default value
-- `options` (array\[[FormOption](#FormOption)\]) Specific property of form items of type `select` or `radio`, defining dropdown content
-- `placeholder`(object) Specific property of form items of type `text-input`, placeholder content
-  - `en_US`(string) English
-  - `zh_Hans` (string) [optional] Chinese
-- `max_length` (int) Specific property of form items of type `text-input`, defining maximum input length, 0 for no limit.
-- `show_on` (array\[[FormShowOnObject](#FormShowOnObject)\]) Displayed when other form item values meet certain conditions, displayed always if empty.
-
-### FormType
-
-- `text-input` Text input component
-- `secret-input` Password input component
-- `select` Single-choice dropdown
-- `radio` Radio component
-- `switch` Switch component, only supports `true` and `false` values
-
-### FormOption
-
-- `label` (object) Label
-  - `en_US`(string) English
-  - `zh_Hans`(string) [optional] Chinese
-- `value` (string) Dropdown option value
-- `show_on` (array\[[FormShowOnObject](#FormShowOnObject)\]) Displayed when other form item values meet certain conditions, displayed always if empty.
-
-### FormShowOnObject
-
-- `variable` (string) Variable name of other form items
-- `value` (string) Variable value of other form items

api/core/model_runtime/docs/zh_Hans/customizable_model_scale_out.md

@@ -1,304 +0,0 @@
-## 自定义预定义模型接入
-
-### 介绍
-
-供应商集成完成后，接下来为供应商下模型的接入，为了帮助理解整个接入过程，我们以`Xinference`为例，逐步完成一个完整的供应商接入。
-
-需要注意的是，对于自定义模型，每一个模型的接入都需要填写一个完整的供应商凭据。
-
-而不同于预定义模型，自定义供应商接入时永远会拥有如下两个参数，不需要在供应商 yaml 中定义。
-
-![Alt text](images/index/image-3.png)
-
-在前文中，我们已经知道了供应商无需实现`validate_provider_credential`，Runtime 会自行根据用户在此选择的模型类型和模型名称调用对应的模型层的`validate_credentials`来进行验证。
-
-### 编写供应商 yaml
-
-我们首先要确定，接入的这个供应商支持哪些类型的模型。
-
-当前支持模型类型如下：
-
-- `llm` 文本生成模型
-- `text_embedding` 文本 Embedding 模型
-- `rerank` Rerank 模型
-- `speech2text` 语音转文字
-- `tts` 文字转语音
-- `moderation` 审查
-
-`Xinference`支持`LLM`和`Text Embedding`和 Rerank，那么我们开始编写`xinference.yaml`。
-
-```yaml
-provider: xinference #确定供应商标识
-label: # 供应商展示名称，可设置 en_US 英文、zh_Hans 中文两种语言，zh_Hans 不设置将默认使用 en_US。
-  en_US: Xorbits Inference
-icon_small: # 小图标，可以参考其他供应商的图标，存储在对应供应商实现目录下的 _assets 目录，中英文策略同 label
-  en_US: icon_s_en.svg
-icon_large: # 大图标
-  en_US: icon_l_en.svg
-help: # 帮助
-  title:
-    en_US: How to deploy Xinference
-    zh_Hans: 如何部署 Xinference
-  url:
-    en_US: https://github.com/xorbitsai/inference
-supported_model_types: # 支持的模型类型，Xinference 同时支持 LLM/Text Embedding/Rerank
-- llm
-- text-embedding
-- rerank
-configurate_methods: # 因为 Xinference 为本地部署的供应商，并且没有预定义模型，需要用什么模型需要根据 Xinference 的文档自己部署，所以这里只支持自定义模型
-- customizable-model
-provider_credential_schema:
-  credential_form_schemas:
-```
-
-随后，我们需要思考在 Xinference 中定义一个模型需要哪些凭据
-
-- 它支持三种不同的模型，因此，我们需要有`model_type`来指定这个模型的类型，它有三种类型，所以我们这么编写
-
-```yaml
-provider_credential_schema:
-  credential_form_schemas:
-  - variable: model_type
-    type: select
-    label:
-      en_US: Model type
-      zh_Hans: 模型类型
-    required: true
-    options:
-    - value: text-generation
-      label:
-        en_US: Language Model
-        zh_Hans: 语言模型
-    - value: embeddings
-      label:
-        en_US: Text Embedding
-    - value: reranking
-      label:
-        en_US: Rerank
-```
-
-- 每一个模型都有自己的名称`model_name`，因此需要在这里定义
-
-```yaml
-  - variable: model_name
-    type: text-input
-    label:
-      en_US: Model name
-      zh_Hans: 模型名称
-    required: true
-    placeholder:
-      zh_Hans: 填写模型名称
-      en_US: Input model name
-```
-
-- 填写 Xinference 本地部署的地址
-
-```yaml
-  - variable: server_url
-    label:
-      zh_Hans: 服务器 URL
-      en_US: Server url
-    type: text-input
-    required: true
-    placeholder:
-      zh_Hans: 在此输入 Xinference 的服务器地址，如 https://example.com/xxx
-      en_US: Enter the url of your Xinference, for example https://example.com/xxx
-```
-
-- 每个模型都有唯一的 model_uid，因此需要在这里定义
-
-```yaml
-  - variable: model_uid
-    label:
-      zh_Hans: 模型 UID
-      en_US: Model uid
-    type: text-input
-    required: true
-    placeholder:
-      zh_Hans: 在此输入您的 Model UID
-      en_US: Enter the model uid
-```
-
-现在，我们就完成了供应商的基础定义。
-
-### 编写模型代码
-
-然后我们以`llm`类型为例，编写`xinference.llm.llm.py`
-
-在 `llm.py` 中创建一个 Xinference LLM 类，我们取名为 `XinferenceAILargeLanguageModel`（随意），继承 `__base.large_language_model.LargeLanguageModel` 基类，实现以下几个方法：
-
-- LLM 调用
-
-  实现 LLM 调用的核心方法，可同时支持流式和同步返回。
-
-  ```python
-  def _invoke(self, model: str, credentials: dict,
-              prompt_messages: list[PromptMessage], model_parameters: dict,
-              tools: Optional[list[PromptMessageTool]] = None, stop: Optional[list[str]] = None,
-              stream: bool = True, user: Optional[str] = None) \
-          -> Union[LLMResult, Generator]:
-      """
-      Invoke large language model
-
-      :param model: model name
-      :param credentials: model credentials
-      :param prompt_messages: prompt messages
-      :param model_parameters: model parameters
-      :param tools: tools for tool calling
-      :param stop: stop words
-      :param stream: is stream response
-      :param user: unique user id
-      :return: full response or stream response chunk generator result
-      """
-  ```
-
-  在实现时，需要注意使用两个函数来返回数据，分别用于处理同步返回和流式返回，因为 Python 会将函数中包含 `yield` 关键字的函数识别为生成器函数，返回的数据类型固定为 `Generator`，因此同步和流式返回需要分别实现，就像下面这样（注意下面例子使用了简化参数，实际实现时需要按照上面的参数列表进行实现）：
-
-  ```python
-  def _invoke(self, stream: bool, **kwargs) \
-          -> Union[LLMResult, Generator]:
-      if stream:
-            return self._handle_stream_response(**kwargs)
-      return self._handle_sync_response(**kwargs)
-
-  def _handle_stream_response(self, **kwargs) -> Generator:
-      for chunk in response:
-            yield chunk
-  def _handle_sync_response(self, **kwargs) -> LLMResult:
-      return LLMResult(**response)
-  ```
-
-- 预计算输入 tokens
-
-  若模型未提供预计算 tokens 接口，可直接返回 0。
-
-  ```python
-  def get_num_tokens(self, model: str, credentials: dict, prompt_messages: list[PromptMessage],
-                   tools: Optional[list[PromptMessageTool]] = None) -> int:
-    """
-    Get number of tokens for given prompt messages
-
-    :param model: model name
-    :param credentials: model credentials
-    :param prompt_messages: prompt messages
-    :param tools: tools for tool calling
-    :return:
-    """
-  ```
-
-  有时候，也许你不需要直接返回 0，所以你可以使用`self._get_num_tokens_by_gpt2(text: str)`来获取预计算的 tokens，并确保环境变量`PLUGIN_BASED_TOKEN_COUNTING_ENABLED`设置为`true`，这个方法位于`AIModel`基类中，它会使用 GPT2 的 Tokenizer 进行计算，但是只能作为替代方法，并不完全准确。
-
-- 模型凭据校验
-
-  与供应商凭据校验类似，这里针对单个模型进行校验。
-
-  ```python
-  def validate_credentials(self, model: str, credentials: dict) -> None:
-      """
-      Validate model credentials
-
-      :param model: model name
-      :param credentials: model credentials
-      :return:
-      """
-  ```
-
-- 模型参数 Schema
-
-  与自定义类型不同，由于没有在 yaml 文件中定义一个模型支持哪些参数，因此，我们需要动态时间模型参数的 Schema。
-
-  如 Xinference 支持`max_tokens` `temperature` `top_p` 这三个模型参数。
-
-  但是有的供应商根据不同的模型支持不同的参数，如供应商`OpenLLM`支持`top_k`，但是并不是这个供应商提供的所有模型都支持`top_k`，我们这里举例 A 模型支持`top_k`，B 模型不支持`top_k`，那么我们需要在这里动态生成模型参数的 Schema，如下所示：
-
-  ```python
-  def get_customizable_model_schema(self, model: str, credentials: dict) -> Optional[AIModelEntity]:
-      """
-          used to define customizable model schema
-      """
-      rules = [
-          ParameterRule(
-              name='temperature', type=ParameterType.FLOAT,
-              use_template='temperature',
-              label=I18nObject(
-                  zh_Hans='温度', en_US='Temperature'
-              )
-          ),
-          ParameterRule(
-              name='top_p', type=ParameterType.FLOAT,
-              use_template='top_p',
-              label=I18nObject(
-                  zh_Hans='Top P', en_US='Top P'
-              )
-          ),
-          ParameterRule(
-              name='max_tokens', type=ParameterType.INT,
-              use_template='max_tokens',
-              min=1,
-              default=512,
-              label=I18nObject(
-                  zh_Hans='最大生成长度', en_US='Max Tokens'
-              )
-          )
-      ]
-
-      # if model is A, add top_k to rules
-      if model == 'A':
-          rules.append(
-              ParameterRule(
-                  name='top_k', type=ParameterType.INT,
-                  use_template='top_k',
-                  min=1,
-                  default=50,
-                  label=I18nObject(
-                      zh_Hans='Top K', en_US='Top K'
-                  )
-              )
-          )
-
-      """
-          some NOT IMPORTANT code here
-      """
-
-      entity = AIModelEntity(
-          model=model,
-          label=I18nObject(
-              en_US=model
-          ),
-          fetch_from=FetchFrom.CUSTOMIZABLE_MODEL,
-          model_type=model_type,
-          model_properties={ 
-              ModelPropertyKey.MODE:  ModelType.LLM,
-          },
-          parameter_rules=rules
-      )
-
-      return entity
-  ```
-
-- 调用异常错误映射表
-
-  当模型调用异常时需要映射到 Runtime 指定的 `InvokeError` 类型，方便 Dify 针对不同错误做不同后续处理。
-
-  Runtime Errors:
-
-  - `InvokeConnectionError` 调用连接错误
-  - `InvokeServerUnavailableError ` 调用服务方不可用
-  - `InvokeRateLimitError ` 调用达到限额
-  - `InvokeAuthorizationError` 调用鉴权失败
-  - `InvokeBadRequestError ` 调用传参有误
-
-  ```python
-  @property
-  def _invoke_error_mapping(self) -> dict[type[InvokeError], list[type[Exception]]]:
-      """
-      Map model invoke error to unified error
-      The key is the error type thrown to the caller
-      The value is the error type thrown by the model,
-      which needs to be converted into a unified error type for the caller.
-
-      :return: Invoke error mapping
-      """
-  ```
-
-接口方法说明见：[Interfaces](./interfaces.md)，具体实现可参考：[llm.py](https://github.com/langgenius/dify-runtime/blob/main/lib/model_providers/anthropic/llm/llm.py)。

api/core/model_runtime/docs/zh_Hans/interfaces.md

@@ -1,744 +0,0 @@
-# 接口方法
-
-这里介绍供应商和各模型类型需要实现的接口方法和参数说明。
-
-## 供应商
-
-继承 `__base.model_provider.ModelProvider` 基类，实现以下接口：
-
-```python
-def validate_provider_credentials(self, credentials: dict) -> None:
-    """
-    Validate provider credentials
-    You can choose any validate_credentials method of model type or implement validate method by yourself,
-    such as: get model list api
-
-    if validate failed, raise exception
-
-    :param credentials: provider credentials, credentials form defined in `provider_credential_schema`.
-    """
-```
-
-- `credentials` (object) 凭据信息
-
-  凭据信息的参数由供应商 YAML 配置文件的 `provider_credential_schema` 定义，传入如：`api_key` 等。
-
-验证失败请抛出 `errors.validate.CredentialsValidateFailedError` 错误。
-
-**注：预定义模型需完整实现该接口，自定义模型供应商只需要如下简单实现即可**
-
-```python
-class XinferenceProvider(Provider):
-    def validate_provider_credentials(self, credentials: dict) -> None:
-        pass
-```
-
-## 模型
-
-模型分为 5 种不同的模型类型，不同模型类型继承的基类不同，需要实现的方法也不同。
-
-### 通用接口
-
-所有模型均需要统一实现下面 2 个方法：
-
-- 模型凭据校验
-
-  与供应商凭据校验类似，这里针对单个模型进行校验。
-
-  ```python
-  def validate_credentials(self, model: str, credentials: dict) -> None:
-      """
-      Validate model credentials
-
-      :param model: model name
-      :param credentials: model credentials
-      :return:
-      """
-  ```
-
-  参数：
-
-  - `model` (string) 模型名称
-
-  - `credentials` (object) 凭据信息
-
-    凭据信息的参数由供应商 YAML 配置文件的 `provider_credential_schema` 或 `model_credential_schema` 定义，传入如：`api_key` 等。
-
-  验证失败请抛出 `errors.validate.CredentialsValidateFailedError` 错误。
-
-- 调用异常错误映射表
-
-  当模型调用异常时需要映射到 Runtime 指定的 `InvokeError` 类型，方便 Dify 针对不同错误做不同后续处理。
-
-  Runtime Errors:
-
-  - `InvokeConnectionError` 调用连接错误
-  - `InvokeServerUnavailableError ` 调用服务方不可用
-  - `InvokeRateLimitError ` 调用达到限额
-  - `InvokeAuthorizationError` 调用鉴权失败
-  - `InvokeBadRequestError ` 调用传参有误
-
-  ```python
-  @property
-  def _invoke_error_mapping(self) -> dict[type[InvokeError], list[type[Exception]]]:
-      """
-      Map model invoke error to unified error
-      The key is the error type thrown to the caller
-      The value is the error type thrown by the model,
-      which needs to be converted into a unified error type for the caller.
-
-      :return: Invoke error mapping
-      """
-  ```
-
-  也可以直接抛出对应 Errors，并做如下定义，这样在之后的调用中可以直接抛出`InvokeConnectionError`等异常。
-
-  ```python
-  @property
-  def _invoke_error_mapping(self) -> dict[type[InvokeError], list[type[Exception]]]:
-      return {
-          InvokeConnectionError: [
-            InvokeConnectionError
-          ],
-          InvokeServerUnavailableError: [
-            InvokeServerUnavailableError
-          ],
-          InvokeRateLimitError: [
-            InvokeRateLimitError
-          ],
-          InvokeAuthorizationError: [
-            InvokeAuthorizationError
-          ],
-          InvokeBadRequestError: [
-            InvokeBadRequestError
-          ],
-      }
-  ```
-
-​ 可参考 OpenAI `_invoke_error_mapping`。
-
-### LLM
-
-继承 `__base.large_language_model.LargeLanguageModel` 基类，实现以下接口：
-
-- LLM 调用
-
-  实现 LLM 调用的核心方法，可同时支持流式和同步返回。
-
-  ```python
-  def _invoke(self, model: str, credentials: dict,
-              prompt_messages: list[PromptMessage], model_parameters: dict,
-              tools: Optional[list[PromptMessageTool]] = None, stop: Optional[list[str]] = None,
-              stream: bool = True, user: Optional[str] = None) \
-          -> Union[LLMResult, Generator]:
-      """
-      Invoke large language model
-
-      :param model: model name
-      :param credentials: model credentials
-      :param prompt_messages: prompt messages
-      :param model_parameters: model parameters
-      :param tools: tools for tool calling
-      :param stop: stop words
-      :param stream: is stream response
-      :param user: unique user id
-      :return: full response or stream response chunk generator result
-      """
-  ```
-
-  - 参数：
-
-    - `model` (string) 模型名称
-
-    - `credentials` (object) 凭据信息
-
-      凭据信息的参数由供应商 YAML 配置文件的 `provider_credential_schema` 或 `model_credential_schema` 定义，传入如：`api_key` 等。
-
-    - `prompt_messages` (array\[[PromptMessage](#PromptMessage)\]) Prompt 列表
-
-      若模型为 `Completion` 类型，则列表只需要传入一个 [UserPromptMessage](#UserPromptMessage) 元素即可；
-
-      若模型为 `Chat` 类型，需要根据消息不同传入 [SystemPromptMessage](#SystemPromptMessage), [UserPromptMessage](#UserPromptMessage), [AssistantPromptMessage](#AssistantPromptMessage), [ToolPromptMessage](#ToolPromptMessage) 元素列表
-
-    - `model_parameters` (object) 模型参数
-
-      模型参数由模型 YAML 配置的 `parameter_rules` 定义。
-
-    - `tools` (array\[[PromptMessageTool](#PromptMessageTool)\]) [optional] 工具列表，等同于 `function calling` 中的 `function`。
-
-      即传入 tool calling 的工具列表。
-
-    - `stop` (array[string]) [optional] 停止序列
-
-      模型返回将在停止序列定义的字符串之前停止输出。
-
-    - `stream` (bool) 是否流式输出，默认 True
-
-      流式输出返回 Generator\[[LLMResultChunk](#LLMResultChunk)\]，非流式输出返回 [LLMResult](#LLMResult)。
-
-    - `user` (string) [optional] 用户的唯一标识符
-
-      可以帮助供应商监控和检测滥用行为。
-
-  - 返回
-
-    流式输出返回 Generator\[[LLMResultChunk](#LLMResultChunk)\]，非流式输出返回 [LLMResult](#LLMResult)。
-
-- 预计算输入 tokens
-
-  若模型未提供预计算 tokens 接口，可直接返回 0。
-
-  ```python
-  def get_num_tokens(self, model: str, credentials: dict, prompt_messages: list[PromptMessage],
-                     tools: Optional[list[PromptMessageTool]] = None) -> int:
-      """
-      Get number of tokens for given prompt messages
-
-      :param model: model name
-      :param credentials: model credentials
-      :param prompt_messages: prompt messages
-      :param tools: tools for tool calling
-      :return:
-      """
-  ```
-
-  参数说明见上述 `LLM 调用`。
-
-  该接口需要根据对应`model`选择合适的`tokenizer`进行计算，如果对应模型没有提供`tokenizer`，可以使用`AIModel`基类中的`_get_num_tokens_by_gpt2(text: str)`方法进行计算。
-
-- 获取自定义模型规则 [可选]
-
-  ```python
-  def get_customizable_model_schema(self, model: str, credentials: dict) -> Optional[AIModelEntity]:
-      """
-      Get customizable model schema
-
-      :param model: model name
-      :param credentials: model credentials
-      :return: model schema
-      """
-  ```
-
-​当供应商支持增加自定义 LLM 时，可实现此方法让自定义模型可获取模型规则，默认返回 None。
-
-对于`OpenAI`供应商下的大部分微调模型，可以通过其微调模型名称获取到其基类模型，如`gpt-3.5-turbo-1106`，然后返回基类模型的预定义参数规则，参考[openai](https://github.com/langgenius/dify/blob/feat/model-runtime/api/core/model_runtime/model_providers/openai/llm/llm.py#L801)
-的具体实现
-
-### TextEmbedding
-
-继承 `__base.text_embedding_model.TextEmbeddingModel` 基类，实现以下接口：
-
-- Embedding 调用
-
-  ```python
-  def _invoke(self, model: str, credentials: dict,
-              texts: list[str], user: Optional[str] = None) \
-          -> TextEmbeddingResult:
-      """
-      Invoke large language model
-
-      :param model: model name
-      :param credentials: model credentials
-      :param texts: texts to embed
-      :param user: unique user id
-      :return: embeddings result
-      """
-  ```
-
-  - 参数：
-
-    - `model` (string) 模型名称
-
-    - `credentials` (object) 凭据信息
-
-      凭据信息的参数由供应商 YAML 配置文件的 `provider_credential_schema` 或 `model_credential_schema` 定义，传入如：`api_key` 等。
-
-    - `texts` (array[string]) 文本列表，可批量处理
-
-    - `user` (string) [optional] 用户的唯一标识符
-
-      可以帮助供应商监控和检测滥用行为。
-
-  - 返回：
-
-    [TextEmbeddingResult](#TextEmbeddingResult) 实体。
-
-- 预计算 tokens
-
-  ```python
-  def get_num_tokens(self, model: str, credentials: dict, texts: list[str]) -> int:
-      """
-      Get number of tokens for given prompt messages
-
-      :param model: model name
-      :param credentials: model credentials
-      :param texts: texts to embed
-      :return:
-      """
-  ```
-
-  参数说明见上述 `Embedding 调用`。
-
-  同上述`LargeLanguageModel`，该接口需要根据对应`model`选择合适的`tokenizer`进行计算，如果对应模型没有提供`tokenizer`，可以使用`AIModel`基类中的`_get_num_tokens_by_gpt2(text: str)`方法进行计算。
-
-### Rerank
-
-继承 `__base.rerank_model.RerankModel` 基类，实现以下接口：
-
-- rerank 调用
-
-  ```python
-  def _invoke(self, model: str, credentials: dict,
-              query: str, docs: list[str], score_threshold: Optional[float] = None, top_n: Optional[int] = None,
-              user: Optional[str] = None) \
-          -> RerankResult:
-      """
-      Invoke rerank model
-
-      :param model: model name
-      :param credentials: model credentials
-      :param query: search query
-      :param docs: docs for reranking
-      :param score_threshold: score threshold
-      :param top_n: top n
-      :param user: unique user id
-      :return: rerank result
-      """
-  ```
-
-  - 参数：
-
-    - `model` (string) 模型名称
-
-    - `credentials` (object) 凭据信息
-
-      凭据信息的参数由供应商 YAML 配置文件的 `provider_credential_schema` 或 `model_credential_schema` 定义，传入如：`api_key` 等。
-
-    - `query` (string) 查询请求内容
-
-    - `docs` (array[string]) 需要重排的分段列表
-
-    - `score_threshold` (float) [optional] Score 阈值
-
-    - `top_n` (int) [optional] 取前 n 个分段
-
-    - `user` (string) [optional] 用户的唯一标识符
-
-      可以帮助供应商监控和检测滥用行为。
-
-  - 返回：
-
-    [RerankResult](#RerankResult) 实体。
-
-### Speech2text
-
-继承 `__base.speech2text_model.Speech2TextModel` 基类，实现以下接口：
-
-- Invoke 调用
-
-  ```python
-  def _invoke(self, model: str, credentials: dict,
-              file: IO[bytes], user: Optional[str] = None) \
-          -> str:
-      """
-      Invoke large language model
-
-      :param model: model name
-      :param credentials: model credentials
-      :param file: audio file
-      :param user: unique user id
-      :return: text for given audio file
-      """	
-  ```
-
-  - 参数：
-
-    - `model` (string) 模型名称
-
-    - `credentials` (object) 凭据信息
-
-      凭据信息的参数由供应商 YAML 配置文件的 `provider_credential_schema` 或 `model_credential_schema` 定义，传入如：`api_key` 等。
-
-    - `file` (File) 文件流
-
-    - `user` (string) [optional] 用户的唯一标识符
-
-      可以帮助供应商监控和检测滥用行为。
-
-  - 返回：
-
-    语音转换后的字符串。
-
-### Text2speech
-
-继承 `__base.text2speech_model.Text2SpeechModel` 基类，实现以下接口：
-
-- Invoke 调用
-
-  ```python
-  def _invoke(self, model: str, credentials: dict, content_text: str, streaming: bool, user: Optional[str] = None):
-      """
-      Invoke large language model
-
-      :param model: model name
-      :param credentials: model credentials
-      :param content_text: text content to be translated
-      :param streaming: output is streaming
-      :param user: unique user id
-      :return: translated audio file
-      """	
-  ```
-
-  - 参数：
-
-    - `model` (string) 模型名称
-
-    - `credentials` (object) 凭据信息
-
-      凭据信息的参数由供应商 YAML 配置文件的 `provider_credential_schema` 或 `model_credential_schema` 定义，传入如：`api_key` 等。
-
-    - `content_text` (string) 需要转换的文本内容
-
-    - `streaming` (bool) 是否进行流式输出
-
-    - `user` (string) [optional] 用户的唯一标识符
-
-      可以帮助供应商监控和检测滥用行为。
-
-  - 返回：
-
-    文本转换后的语音流。
-
-### Moderation
-
-继承 `__base.moderation_model.ModerationModel` 基类，实现以下接口：
-
-- Invoke 调用
-
-  ```python
-  def _invoke(self, model: str, credentials: dict,
-              text: str, user: Optional[str] = None) \
-          -> bool:
-      """
-      Invoke large language model
-
-      :param model: model name
-      :param credentials: model credentials
-      :param text: text to moderate
-      :param user: unique user id
-      :return: false if text is safe, true otherwise
-      """
-  ```
-
-  - 参数：
-
-    - `model` (string) 模型名称
-
-    - `credentials` (object) 凭据信息
-
-      凭据信息的参数由供应商 YAML 配置文件的 `provider_credential_schema` 或 `model_credential_schema` 定义，传入如：`api_key` 等。
-
-    - `text` (string) 文本内容
-
-    - `user` (string) [optional] 用户的唯一标识符
-
-      可以帮助供应商监控和检测滥用行为。
-
-  - 返回：
-
-    False 代表传入的文本安全，True 则反之。
-
-## 实体
-
-### PromptMessageRole
-
-消息角色
-
-```python
-class PromptMessageRole(Enum):
-    """
-    Enum class for prompt message.
-    """
-    SYSTEM = "system"
-    USER = "user"
-    ASSISTANT = "assistant"
-    TOOL = "tool"
-```
-
-### PromptMessageContentType
-
-消息内容类型，分为纯文本和图片。
-
-```python
-class PromptMessageContentType(Enum):
-    """
-    Enum class for prompt message content type.
-    """
-    TEXT = 'text'
-    IMAGE = 'image'
-```
-
-### PromptMessageContent
-
-消息内容基类，仅作为参数声明用，不可初始化。
-
-```python
-class PromptMessageContent(BaseModel):
-    """
-    Model class for prompt message content.
-    """
-    type: PromptMessageContentType
-    data: str  # 内容数据
-```
-
-当前支持文本和图片两种类型，可支持同时传入文本和多图。
-
-需要分别初始化 `TextPromptMessageContent` 和 `ImagePromptMessageContent` 传入。
-
-### TextPromptMessageContent
-
-```python
-class TextPromptMessageContent(PromptMessageContent):
-    """
-    Model class for text prompt message content.
-    """
-    type: PromptMessageContentType = PromptMessageContentType.TEXT
-```
-
-若传入图文，其中文字需要构造此实体作为 `content` 列表中的一部分。
-
-### ImagePromptMessageContent
-
-```python
-class ImagePromptMessageContent(PromptMessageContent):
-    """
-    Model class for image prompt message content.
-    """
-    class DETAIL(Enum):
-        LOW = 'low'
-        HIGH = 'high'
-
-    type: PromptMessageContentType = PromptMessageContentType.IMAGE
-    detail: DETAIL = DETAIL.LOW  # 分辨率
-```
-
-若传入图文，其中图片需要构造此实体作为 `content` 列表中的一部分
-
-`data` 可以为 `url` 或者图片 `base64` 加密后的字符串。
-
-### PromptMessage
-
-所有 Role 消息体的基类，仅作为参数声明用，不可初始化。
-
-```python
-class PromptMessage(BaseModel):
-    """
-    Model class for prompt message.
-    """
-    role: PromptMessageRole  # 消息角色
-    content: Optional[str | list[PromptMessageContent]] = None  # 支持两种类型，字符串和内容列表，内容列表是为了满足多模态的需要，可详见 PromptMessageContent 说明。
-    name: Optional[str] = None  # 名称，可选。
-```
-
-### UserPromptMessage
-
-UserMessage 消息体，代表用户消息。
-
-```python
-class UserPromptMessage(PromptMessage):
-    """
-    Model class for user prompt message.
-    """
-    role: PromptMessageRole = PromptMessageRole.USER
-```
-
-### AssistantPromptMessage
-
-代表模型返回消息，通常用于 `few-shots` 或聊天历史传入。
-
-```python
-class AssistantPromptMessage(PromptMessage):
-    """
-    Model class for assistant prompt message.
-    """
-    class ToolCall(BaseModel):
-        """
-        Model class for assistant prompt message tool call.
-        """
-        class ToolCallFunction(BaseModel):
-            """
-            Model class for assistant prompt message tool call function.
-            """
-            name: str  # 工具名称
-            arguments: str  # 工具参数
-
-        id: str  # 工具 ID，仅在 OpenAI tool call 生效，为工具调用的唯一 ID，同一个工具可以调用多次
-        type: str  # 默认 function
-        function: ToolCallFunction  # 工具调用信息
-
-    role: PromptMessageRole = PromptMessageRole.ASSISTANT
-    tool_calls: list[ToolCall] = []  # 模型回复的工具调用结果（仅当传入 tools，并且模型认为需要调用工具时返回）
-```
-
-其中 `tool_calls` 为调用模型传入 `tools` 后，由模型返回的 `tool call` 列表。
-
-### SystemPromptMessage
-
-代表系统消息，通常用于设定给模型的系统指令。
-
-```python
-class SystemPromptMessage(PromptMessage):
-    """
-    Model class for system prompt message.
-    """
-    role: PromptMessageRole = PromptMessageRole.SYSTEM
-```
-
-### ToolPromptMessage
-
-代表工具消息，用于工具执行后将结果交给模型进行下一步计划。
-
-```python
-class ToolPromptMessage(PromptMessage):
-    """
-    Model class for tool prompt message.
-    """
-    role: PromptMessageRole = PromptMessageRole.TOOL
-    tool_call_id: str  # 工具调用 ID，若不支持 OpenAI tool call，也可传入工具名称
-```
-
-基类的 `content` 传入工具执行结果。
-
-### PromptMessageTool
-
-```python
-class PromptMessageTool(BaseModel):
-    """
-    Model class for prompt message tool.
-    """
-    name: str  # 工具名称
-    description: str  # 工具描述
-    parameters: dict  # 工具参数 dict
-```
-
-______________________________________________________________________
-
-### LLMResult
-
-```python
-class LLMResult(BaseModel):
-    """
-    Model class for llm result.
-    """
-    model: str  # 实际使用模型
-    prompt_messages: list[PromptMessage]  # prompt 消息列表
-    message: AssistantPromptMessage  # 回复消息
-    usage: LLMUsage  # 使用的 tokens 及费用信息
-    system_fingerprint: Optional[str] = None  # 请求指纹，可参考 OpenAI 该参数定义
-```
-
-### LLMResultChunkDelta
-
-流式返回中每个迭代内部 `delta` 实体
-
-```python
-class LLMResultChunkDelta(BaseModel):
-    """
-    Model class for llm result chunk delta.
-    """
-    index: int  # 序号
-    message: AssistantPromptMessage  # 回复消息
-    usage: Optional[LLMUsage] = None  # 使用的 tokens 及费用信息，仅最后一条返回
-    finish_reason: Optional[str] = None  # 结束原因，仅最后一条返回
-```
-
-### LLMResultChunk
-
-流式返回中每个迭代实体
-
-```python
-class LLMResultChunk(BaseModel):
-    """
-    Model class for llm result chunk.
-    """
-    model: str  # 实际使用模型
-    prompt_messages: list[PromptMessage]  # prompt 消息列表
-    system_fingerprint: Optional[str] = None  # 请求指纹，可参考 OpenAI 该参数定义
-    delta: LLMResultChunkDelta  # 每个迭代存在变化的内容
-```
-
-### LLMUsage
-
-```python
-class LLMUsage(ModelUsage):
-    """
-    Model class for llm usage.
-    """
-    prompt_tokens: int  # prompt 使用 tokens
-    prompt_unit_price: Decimal  # prompt 单价
-    prompt_price_unit: Decimal  # prompt 价格单位，即单价基于多少 tokens 
-    prompt_price: Decimal  # prompt 费用
-    completion_tokens: int  # 回复使用 tokens
-    completion_unit_price: Decimal  # 回复单价
-    completion_price_unit: Decimal  # 回复价格单位，即单价基于多少 tokens 
-    completion_price: Decimal  # 回复费用
-    total_tokens: int  # 总使用 token 数
-    total_price: Decimal  # 总费用
-    currency: str  # 货币单位
-    latency: float  # 请求耗时 (s)
-```
-
-______________________________________________________________________
-
-### TextEmbeddingResult
-
-```python
-class TextEmbeddingResult(BaseModel):
-    """
-    Model class for text embedding result.
-    """
-    model: str  # 实际使用模型
-    embeddings: list[list[float]]  # embedding 向量列表，对应传入的 texts 列表
-    usage: EmbeddingUsage  # 使用信息
-```
-
-### EmbeddingUsage
-
-```python
-class EmbeddingUsage(ModelUsage):
-    """
-    Model class for embedding usage.
-    """
-    tokens: int  # 使用 token 数
-    total_tokens: int  # 总使用 token 数
-    unit_price: Decimal  # 单价
-    price_unit: Decimal  # 价格单位，即单价基于多少 tokens
-    total_price: Decimal  # 总费用
-    currency: str  # 货币单位
-    latency: float  # 请求耗时 (s)
-```
-
-______________________________________________________________________
-
-### RerankResult
-
-```python
-class RerankResult(BaseModel):
-    """
-    Model class for rerank result.
-    """
-    model: str  # 实际使用模型
-    docs: list[RerankDocument]  # 重排后的分段列表	
-```
-
-### RerankDocument
-
-```python
-class RerankDocument(BaseModel):
-    """
-    Model class for rerank document.
-    """
-    index: int  # 原序号
-    text: str  # 分段文本内容
-    score: float  # 分数
-```

api/core/model_runtime/docs/zh_Hans/predefined_model_scale_out.md

@@ -1,172 +0,0 @@
-## 预定义模型接入
-
-供应商集成完成后，接下来为供应商下模型的接入。
-
-我们首先需要确定接入模型的类型，并在对应供应商的目录下创建对应模型类型的 `module`。
-
-当前支持模型类型如下：
-
-- `llm` 文本生成模型
-- `text_embedding` 文本 Embedding 模型
-- `rerank` Rerank 模型
-- `speech2text` 语音转文字
-- `tts` 文字转语音
-- `moderation` 审查
-
-依旧以 `Anthropic` 为例，`Anthropic` 仅支持 LLM，因此在 `model_providers.anthropic` 创建一个 `llm` 为名称的 `module`。
-
-对于预定义的模型，我们首先需要在 `llm` `module` 下创建以模型名为文件名称的 YAML 文件，如：`claude-2.1.yaml`。
-
-### 准备模型 YAML
-
-```yaml
-model: claude-2.1  # 模型标识
-# 模型展示名称，可设置 en_US 英文、zh_Hans 中文两种语言，zh_Hans 不设置将默认使用 en_US。
-# 也可不设置 label，则使用 model 标识内容。
-label:
-  en_US: claude-2.1
-model_type: llm  # 模型类型，claude-2.1 为 LLM
-features:  # 支持功能，agent-thought 为支持 Agent 推理，vision 为支持图片理解
-- agent-thought
-model_properties:  # 模型属性
-  mode: chat  # LLM 模式，complete 文本补全模型，chat 对话模型
-  context_size: 200000  # 支持最大上下文大小
-parameter_rules:  # 模型调用参数规则，仅 LLM 需要提供
-- name: temperature  # 调用参数变量名
-  # 默认预置了 5 种变量内容配置模板，temperature/top_p/max_tokens/presence_penalty/frequency_penalty
-  # 可在 use_template 中直接设置模板变量名，将会使用 entities.defaults.PARAMETER_RULE_TEMPLATE 中的默认配置
-  # 若设置了额外的配置参数，将覆盖默认配置
-  use_template: temperature
-- name: top_p
-  use_template: top_p
-- name: top_k
-  label:  # 调用参数展示名称
-    zh_Hans: 取样数量
-    en_US: Top k
-  type: int  # 参数类型，支持 float/int/string/boolean
-  help:  # 帮助信息，描述参数作用
-    zh_Hans: 仅从每个后续标记的前 K 个选项中采样。
-    en_US: Only sample from the top K options for each subsequent token.
-  required: false  # 是否必填，可不设置
-- name: max_tokens_to_sample
-  use_template: max_tokens
-  default: 4096  # 参数默认值
-  min: 1  # 参数最小值，仅 float/int 可用
-  max: 4096  # 参数最大值，仅 float/int 可用
-pricing:  # 价格信息
-  input: '8.00'  # 输入单价，即 Prompt 单价
-  output: '24.00'  # 输出单价，即返回内容单价
-  unit: '0.000001'  # 价格单位，即上述价格为每 100K 的单价
-  currency: USD  # 价格货币
-```
-
-建议将所有模型配置都准备完毕后再开始模型代码的实现。
-
-同样，也可以参考 `model_providers` 目录下其他供应商对应模型类型目录下的 YAML 配置信息，完整的 YAML 规则见：[Schema](schema.md#aimodelentity)。
-
-### 实现模型调用代码
-
-接下来需要在 `llm` `module` 下创建一个同名的 python 文件 `llm.py` 来编写代码实现。
-
-在 `llm.py` 中创建一个 Anthropic LLM 类，我们取名为 `AnthropicLargeLanguageModel`（随意），继承 `__base.large_language_model.LargeLanguageModel` 基类，实现以下几个方法：
-
-- LLM 调用
-
-  实现 LLM 调用的核心方法，可同时支持流式和同步返回。
-
-  ```python
-  def _invoke(self, model: str, credentials: dict,
-              prompt_messages: list[PromptMessage], model_parameters: dict,
-              tools: Optional[list[PromptMessageTool]] = None, stop: Optional[list[str]] = None,
-              stream: bool = True, user: Optional[str] = None) \
-          -> Union[LLMResult, Generator]:
-      """
-      Invoke large language model
-
-      :param model: model name
-      :param credentials: model credentials
-      :param prompt_messages: prompt messages
-      :param model_parameters: model parameters
-      :param tools: tools for tool calling
-      :param stop: stop words
-      :param stream: is stream response
-      :param user: unique user id
-      :return: full response or stream response chunk generator result
-      """
-  ```
-
-  在实现时，需要注意使用两个函数来返回数据，分别用于处理同步返回和流式返回，因为 Python 会将函数中包含 `yield` 关键字的函数识别为生成器函数，返回的数据类型固定为 `Generator`，因此同步和流式返回需要分别实现，就像下面这样（注意下面例子使用了简化参数，实际实现时需要按照上面的参数列表进行实现）：
-
-  ```python
-  def _invoke(self, stream: bool, **kwargs) \
-          -> Union[LLMResult, Generator]:
-      if stream:
-            return self._handle_stream_response(**kwargs)
-      return self._handle_sync_response(**kwargs)
-
-  def _handle_stream_response(self, **kwargs) -> Generator:
-      for chunk in response:
-            yield chunk
-  def _handle_sync_response(self, **kwargs) -> LLMResult:
-      return LLMResult(**response)
-  ```
-
-- 预计算输入 tokens
-
-  若模型未提供预计算 tokens 接口，可直接返回 0。
-
-  ```python
-  def get_num_tokens(self, model: str, credentials: dict, prompt_messages: list[PromptMessage],
-                     tools: Optional[list[PromptMessageTool]] = None) -> int:
-      """
-      Get number of tokens for given prompt messages
-
-      :param model: model name
-      :param credentials: model credentials
-      :param prompt_messages: prompt messages
-      :param tools: tools for tool calling
-      :return:
-      """
-  ```
-
-- 模型凭据校验
-
-  与供应商凭据校验类似，这里针对单个模型进行校验。
-
-  ```python
-  def validate_credentials(self, model: str, credentials: dict) -> None:
-      """
-      Validate model credentials
-
-      :param model: model name
-      :param credentials: model credentials
-      :return:
-      """
-  ```
-
-- 调用异常错误映射表
-
-  当模型调用异常时需要映射到 Runtime 指定的 `InvokeError` 类型，方便 Dify 针对不同错误做不同后续处理。
-
-  Runtime Errors:
-
-  - `InvokeConnectionError` 调用连接错误
-  - `InvokeServerUnavailableError ` 调用服务方不可用
-  - `InvokeRateLimitError ` 调用达到限额
-  - `InvokeAuthorizationError` 调用鉴权失败
-  - `InvokeBadRequestError ` 调用传参有误
-
-  ```python
-  @property
-  def _invoke_error_mapping(self) -> dict[type[InvokeError], list[type[Exception]]]:
-      """
-      Map model invoke error to unified error
-      The key is the error type thrown to the caller
-      The value is the error type thrown by the model,
-      which needs to be converted into a unified error type for the caller.
-
-      :return: Invoke error mapping
-      """
-  ```
-
-接口方法说明见：[Interfaces](./interfaces.md)，具体实现可参考：[llm.py](https://github.com/langgenius/dify-runtime/blob/main/lib/model_providers/anthropic/llm/llm.py)。

api/core/model_runtime/docs/zh_Hans/provider_scale_out.md

@@ -1,192 +0,0 @@
-## 增加新供应商
-
-供应商支持三种模型配置方式：
-
-- `predefined-model  ` 预定义模型
-
-  表示用户只需要配置统一的供应商凭据即可使用供应商下的预定义模型。
-
-- `customizable-model` 自定义模型
-
-  用户需要新增每个模型的凭据配置，如 Xinference，它同时支持 LLM 和 Text Embedding，但是每个模型都有唯一的**model_uid**，如果想要将两者同时接入，就需要为每个模型配置一个**model_uid**。
-
-- `fetch-from-remote` 从远程获取
-
-  与 `predefined-model` 配置方式一致，只需要配置统一的供应商凭据即可，模型通过凭据信息从供应商获取。
-
-  如 OpenAI，我们可以基于 gpt-turbo-3.5 来 Fine Tune 多个模型，而他们都位于同一个**api_key**下，当配置为 `fetch-from-remote` 时，开发者只需要配置统一的**api_key**即可让 DifyRuntime 获取到开发者所有的微调模型并接入 Dify。
-
-这三种配置方式**支持共存**，即存在供应商支持 `predefined-model` + `customizable-model` 或 `predefined-model` + `fetch-from-remote` 等，也就是配置了供应商统一凭据可以使用预定义模型和从远程获取的模型，若新增了模型，则可以在此基础上额外使用自定义的模型。
-
-## 开始
-
-### 介绍
-
-#### 名词解释
-
-- `module`: 一个`module`即为一个 Python Package，或者通俗一点，称为一个文件夹，里面包含了一个`__init__.py`文件，以及其他的`.py`文件。
-
-#### 步骤
-
-新增一个供应商主要分为几步，这里简单列出，帮助大家有一个大概的认识，具体的步骤会在下面详细介绍。
-
-- 创建供应商 yaml 文件，根据[ProviderSchema](./schema.md#provider)编写
-- 创建供应商代码，实现一个`class`。
-- 根据模型类型，在供应商`module`下创建对应的模型类型 `module`，如`llm`或`text_embedding`。
-- 根据模型类型，在对应的模型`module`下创建同名的代码文件，如`llm.py`，并实现一个`class`。
-- 如果有预定义模型，根据模型名称创建同名的 yaml 文件在模型`module`下，如`claude-2.1.yaml`，根据[AIModelEntity](./schema.md#aimodelentity)编写。
-- 编写测试代码，确保功能可用。
-
-### 开始吧
-
-增加一个新的供应商需要先确定供应商的英文标识，如 `anthropic`，使用该标识在 `model_providers` 创建以此为名称的 `module`。
-
-在此 `module` 下，我们需要先准备供应商的 YAML 配置。
-
-#### 准备供应商 YAML
-
-此处以 `Anthropic` 为例，预设了供应商基础信息、支持的模型类型、配置方式、凭据规则。
-
-```YAML
-provider: anthropic  # 供应商标识
-label:  # 供应商展示名称，可设置 en_US 英文、zh_Hans 中文两种语言，zh_Hans 不设置将默认使用 en_US。
-  en_US: Anthropic
-icon_small:  # 供应商小图标，存储在对应供应商实现目录下的 _assets 目录，中英文策略同 label
-  en_US: icon_s_en.png
-icon_large:  # 供应商大图标，存储在对应供应商实现目录下的 _assets 目录，中英文策略同 label
-  en_US: icon_l_en.png
-supported_model_types:  # 支持的模型类型，Anthropic 仅支持 LLM
-- llm
-configurate_methods:  # 支持的配置方式，Anthropic 仅支持预定义模型
-- predefined-model
-provider_credential_schema:  # 供应商凭据规则，由于 Anthropic 仅支持预定义模型，则需要定义统一供应商凭据规则
-  credential_form_schemas:  # 凭据表单项列表
-  - variable: anthropic_api_key  # 凭据参数变量名
-    label:  # 展示名称
-      en_US: API Key
-    type: secret-input  # 表单类型，此处 secret-input 代表加密信息输入框，编辑时只展示屏蔽后的信息。
-    required: true  # 是否必填
-    placeholder:  # PlaceHolder 信息
-      zh_Hans: 在此输入您的 API Key
-      en_US: Enter your API Key
-  - variable: anthropic_api_url
-    label:
-      en_US: API URL
-    type: text-input  # 表单类型，此处 text-input 代表文本输入框
-    required: false
-    placeholder:
-      zh_Hans: 在此输入您的 API URL
-      en_US: Enter your API URL
-```
-
-如果接入的供应商提供自定义模型，比如`OpenAI`提供微调模型，那么我们就需要添加[`model_credential_schema`](./schema.md#modelcredentialschema)，以`OpenAI`为例：
-
-```yaml
-model_credential_schema:
-  model: # 微调模型名称
-    label:
-      en_US: Model Name
-      zh_Hans: 模型名称
-    placeholder:
-      en_US: Enter your model name
-      zh_Hans: 输入模型名称
-  credential_form_schemas:
-  - variable: openai_api_key
-    label:
-      en_US: API Key
-    type: secret-input
-    required: true
-    placeholder:
-      zh_Hans: 在此输入您的 API Key
-      en_US: Enter your API Key
-  - variable: openai_organization
-    label:
-        zh_Hans: 组织 ID
-        en_US: Organization
-    type: text-input
-    required: false
-    placeholder:
-      zh_Hans: 在此输入您的组织 ID
-      en_US: Enter your Organization ID
-  - variable: openai_api_base
-    label:
-      zh_Hans: API Base
-      en_US: API Base
-    type: text-input
-    required: false
-    placeholder:
-      zh_Hans: 在此输入您的 API Base
-      en_US: Enter your API Base
-```
-
-也可以参考 `model_providers` 目录下其他供应商目录下的 YAML 配置信息，完整的 YAML 规则见：[Schema](schema.md#provider)。
-
-#### 实现供应商代码
-
-我们需要在`model_providers`下创建一个同名的 python 文件，如`anthropic.py`，并实现一个`class`，继承`__base.provider.Provider`基类，如`AnthropicProvider`。
-
-##### 自定义模型供应商
-
-当供应商为 Xinference 等自定义模型供应商时，可跳过该步骤，仅创建一个空的`XinferenceProvider`类即可，并实现一个空的`validate_provider_credentials`方法，该方法并不会被实际使用，仅用作避免抽象类无法实例化。
-
-```python
-class XinferenceProvider(Provider):
-    def validate_provider_credentials(self, credentials: dict) -> None:
-        pass
-```
-
-##### 预定义模型供应商
-
-供应商需要继承 `__base.model_provider.ModelProvider` 基类，实现 `validate_provider_credentials` 供应商统一凭据校验方法即可，可参考 [AnthropicProvider](https://github.com/langgenius/dify-runtime/blob/main/lib/model_providers/anthropic/anthropic.py)。
-
-```python
-def validate_provider_credentials(self, credentials: dict) -> None:
-    """
-    Validate provider credentials
-    You can choose any validate_credentials method of model type or implement validate method by yourself,
-    such as: get model list api
-
-    if validate failed, raise exception
-
-    :param credentials: provider credentials, credentials form defined in `provider_credential_schema`.
-    """
-```
-
-当然也可以先预留 `validate_provider_credentials` 实现，在模型凭据校验方法实现后直接复用。
-
-#### 增加模型
-
-#### [增加预定义模型 👈🏻](./predefined_model_scale_out.md)
-
-对于预定义模型，我们可以通过简单定义一个 yaml，并通过实现调用代码来接入。
-
-#### [增加自定义模型 👈🏻](./customizable_model_scale_out.md)
-
-对于自定义模型，我们只需要实现调用代码即可接入，但是它需要处理的参数可能会更加复杂。
-
-______________________________________________________________________
-
-### 测试
-
-为了保证接入供应商/模型的可用性，编写后的每个方法均需要在 `tests` 目录中编写对应的集成测试代码。
-
-依旧以 `Anthropic` 为例。
-
-在编写测试代码前，需要先在 `.env.example` 新增测试供应商所需要的凭据环境变量，如：`ANTHROPIC_API_KEY`。
-
-在执行前需要将 `.env.example` 复制为 `.env` 再执行。
-
-#### 编写测试代码
-
-在 `tests` 目录下创建供应商同名的 `module`: `anthropic`，继续在此模块中创建 `test_provider.py` 以及对应模型类型的 test py 文件，如下所示：
-
-```shell
-.
-├── __init__.py
-├── anthropic
-│   ├── __init__.py
-│   ├── test_llm.py       # LLM 测试
-│   └── test_provider.py  # 供应商测试
-```
-
-针对上面实现的代码的各种情况进行测试代码编写，并测试通过后提交代码。

api/core/model_runtime/docs/zh_Hans/schema.md

@@ -1,209 +0,0 @@
-# 配置规则
-
-- 供应商规则基于 [Provider](#Provider) 实体。
-
-- 模型规则基于 [AIModelEntity](#AIModelEntity) 实体。
-
-> 以下所有实体均基于 `Pydantic BaseModel`，可在 `entities` 模块中找到对应实体。
-
-### Provider
-
-- `provider` (string) 供应商标识，如：`openai`
-- `label` (object) 供应商展示名称，i18n，可设置 `en_US` 英文、`zh_Hans` 中文两种语言
-  - `zh_Hans ` (string) [optional] 中文标签名，`zh_Hans` 不设置将默认使用 `en_US`。
-  - `en_US` (string) 英文标签名
-- `description` (object) [optional] 供应商描述，i18n
-  - `zh_Hans` (string) [optional] 中文描述
-  - `en_US` (string) 英文描述
-- `icon_small` (string) [optional] 供应商小 ICON，存储在对应供应商实现目录下的 `_assets` 目录，中英文策略同 `label`
-  - `zh_Hans` (string) [optional] 中文 ICON
-  - `en_US` (string) 英文 ICON
-- `icon_large` (string) [optional] 供应商大 ICON，存储在对应供应商实现目录下的 \_assets 目录，中英文策略同 label
-  - `zh_Hans `(string) [optional] 中文 ICON
-  - `en_US` (string) 英文 ICON
-- `background` (string) [optional] 背景颜色色值，例：#FFFFFF，为空则展示前端默认色值。
-- `help` (object) [optional] 帮助信息
-  - `title` (object) 帮助标题，i18n
-    - `zh_Hans` (string) [optional] 中文标题
-    - `en_US` (string) 英文标题
-  - `url` (object) 帮助链接，i18n
-    - `zh_Hans` (string) [optional] 中文链接
-    - `en_US` (string) 英文链接
-- `supported_model_types` (array\[[ModelType](#ModelType)\]) 支持的模型类型
-- `configurate_methods` (array\[[ConfigurateMethod](#ConfigurateMethod)\]) 配置方式
-- `provider_credential_schema` ([ProviderCredentialSchema](#ProviderCredentialSchema)) 供应商凭据规格
-- `model_credential_schema` ([ModelCredentialSchema](#ModelCredentialSchema)) 模型凭据规格
-
-### AIModelEntity
-
-- `model` (string) 模型标识，如：`gpt-3.5-turbo`
-- `label` (object) [optional] 模型展示名称，i18n，可设置 `en_US` 英文、`zh_Hans` 中文两种语言
-  - `zh_Hans `(string) [optional] 中文标签名
-  - `en_US` (string) 英文标签名
-- `model_type` ([ModelType](#ModelType)) 模型类型
-- `features` (array\[[ModelFeature](#ModelFeature)\]) [optional] 支持功能列表
-- `model_properties` (object) 模型属性
-  - `mode` ([LLMMode](#LLMMode)) 模式 (模型类型 `llm` 可用)
-  - `context_size` (int) 上下文大小 (模型类型 `llm` `text-embedding` 可用)
-  - `max_chunks` (int) 最大分块数量 (模型类型 `text-embedding ` `moderation` 可用)
-  - `file_upload_limit` (int) 文件最大上传限制，单位：MB。（模型类型 `speech2text` 可用）
-  - `supported_file_extensions` (string) 支持文件扩展格式，如：mp3,mp4（模型类型 `speech2text` 可用）
-  - `default_voice` (string) 缺省音色，必选：alloy,echo,fable,onyx,nova,shimmer（模型类型 `tts` 可用）
-  - `voices` (list) 可选音色列表。
-    - `mode` (string) 音色模型。（模型类型 `tts` 可用）
-    - `name` (string) 音色模型显示名称。（模型类型 `tts` 可用）
-    - `language` (string) 音色模型支持语言。（模型类型 `tts` 可用）
-  - `word_limit` (int) 单次转换字数限制，默认按段落分段（模型类型 `tts` 可用）
-  - `audio_type` (string) 支持音频文件扩展格式，如：mp3,wav（模型类型 `tts` 可用）
-  - `max_workers` (int) 支持文字音频转换并发任务数（模型类型 `tts` 可用）
-  - `max_characters_per_chunk` (int) 每块最大字符数 (模型类型 `moderation` 可用)
-- `parameter_rules` (array\[[ParameterRule](#ParameterRule)\]) [optional] 模型调用参数规则
-- `pricing` ([PriceConfig](#PriceConfig)) [optional] 价格信息
-- `deprecated` (bool) 是否废弃。若废弃，模型列表将不再展示，但已经配置的可以继续使用，默认 False。
-
-### ModelType
-
-- `llm` 文本生成模型
-- `text-embedding` 文本 Embedding 模型
-- `rerank` Rerank 模型
-- `speech2text` 语音转文字
-- `tts` 文字转语音
-- `moderation` 审查
-
-### ConfigurateMethod
-
-- `predefined-model  ` 预定义模型
-
-  表示用户只需要配置统一的供应商凭据即可使用供应商下的预定义模型。
-
-- `customizable-model` 自定义模型
-
-  用户需要新增每个模型的凭据配置。
-
-- `fetch-from-remote` 从远程获取
-
-  与 `predefined-model` 配置方式一致，只需要配置统一的供应商凭据即可，模型通过凭据信息从供应商获取。
-
-### ModelFeature
-
-- `agent-thought` Agent 推理，一般超过 70B 有思维链能力。
-- `vision` 视觉，即：图像理解。
-- `tool-call` 工具调用
-- `multi-tool-call` 多工具调用
-- `stream-tool-call` 流式工具调用
-
-### FetchFrom
-
-- `predefined-model` 预定义模型
-- `fetch-from-remote` 远程模型
-
-### LLMMode
-
-- `completion` 文本补全
-- `chat` 对话
-
-### ParameterRule
-
-- `name` (string) 调用模型实际参数名
-
-- `use_template` (string) [optional] 使用模板
-
-  默认预置了 5 种变量内容配置模板：
-
-  - `temperature`
-  - `top_p`
-  - `frequency_penalty`
-  - `presence_penalty`
-  - `max_tokens`
-
-  可在 use_template 中直接设置模板变量名，将会使用 entities.defaults.PARAMETER_RULE_TEMPLATE 中的默认配置
-  不用设置除 `name` 和 `use_template` 之外的所有参数，若设置了额外的配置参数，将覆盖默认配置。
-  可参考 `openai/llm/gpt-3.5-turbo.yaml`。
-
-- `label` (object) [optional] 标签，i18n
-
-  - `zh_Hans`(string) [optional] 中文标签名
-  - `en_US` (string) 英文标签名
-
-- `type`(string) [optional] 参数类型
-
-  - `int` 整数
-  - `float` 浮点数
-  - `string` 字符串
-  - `boolean` 布尔型
-
-- `help` (string) [optional] 帮助信息
-
-  - `zh_Hans` (string) [optional] 中文帮助信息
-  - `en_US` (string) 英文帮助信息
-
-- `required` (bool) 是否必填，默认 False。
-
-- `default`(int/float/string/bool) [optional] 默认值
-
-- `min`(int/float) [optional] 最小值，仅数字类型适用
-
-- `max`(int/float) [optional] 最大值，仅数字类型适用
-
-- `precision`(int) [optional] 精度，保留小数位数，仅数字类型适用
-
-- `options` (array[string]) [optional] 下拉选项值，仅当 `type` 为 `string` 时适用，若不设置或为 null 则不限制选项值
-
-### PriceConfig
-
-- `input` (float) 输入单价，即 Prompt 单价
-- `output` (float) 输出单价，即返回内容单价
-- `unit` (float) 价格单位，如以 1M tokens 计价，则单价对应的单位 token 数为 `0.000001`
-- `currency` (string) 货币单位
-
-### ProviderCredentialSchema
-
-- `credential_form_schemas` (array\[[CredentialFormSchema](#CredentialFormSchema)\]) 凭据表单规范
-
-### ModelCredentialSchema
-
-- `model` (object) 模型标识，变量名默认 `model`
-  - `label` (object) 模型表单项展示名称
-    - `en_US` (string) 英文
-    - `zh_Hans`(string) [optional] 中文
-  - `placeholder` (object) 模型提示内容
-    - `en_US`(string) 英文
-    - `zh_Hans`(string) [optional] 中文
-- `credential_form_schemas` (array\[[CredentialFormSchema](#CredentialFormSchema)\]) 凭据表单规范
-
-### CredentialFormSchema
-
-- `variable` (string) 表单项变量名
-- `label` (object) 表单项标签名
-  - `en_US`(string) 英文
-  - `zh_Hans` (string) [optional] 中文
-- `type` ([FormType](#FormType)) 表单项类型
-- `required` (bool) 是否必填
-- `default`(string) 默认值
-- `options` (array\[[FormOption](#FormOption)\]) 表单项为 `select` 或 `radio` 专有属性，定义下拉内容
-- `placeholder`(object) 表单项为 `text-input `专有属性，表单项 PlaceHolder
-  - `en_US`(string) 英文
-  - `zh_Hans` (string) [optional] 中文
-- `max_length` (int) 表单项为`text-input`专有属性，定义输入最大长度，0 为不限制。
-- `show_on` (array\[[FormShowOnObject](#FormShowOnObject)\]) 当其他表单项值符合条件时显示，为空则始终显示。
-
-### FormType
-
-- `text-input` 文本输入组件
-- `secret-input` 密码输入组件
-- `select` 单选下拉
-- `radio` Radio 组件
-- `switch` 开关组件，仅支持 `true` 和 `false`
-
-### FormOption
-
-- `label` (object) 标签
-  - `en_US`(string) 英文
-  - `zh_Hans`(string) [optional] 中文
-- `value` (string) 下拉选项值
-- `show_on` (array\[[FormShowOnObject](#FormShowOnObject)\]) 当其他表单项值符合条件时显示，为空则始终显示。
-
-### FormShowOnObject
-
-- `variable` (string) 其他表单项变量名
-- `value` (string) 其他表单项变量值

api/core/ops/tencent_trace/span_builder.py

@@ -222,6 +222,59 @@ class TencentSpanBuilder:
             links=links,
         )
 
+    @staticmethod
+    def build_message_llm_span(
+        trace_info: MessageTraceInfo, trace_id: int, parent_span_id: int, user_id: str
+    ) -> SpanData:
+        """Build LLM span for message traces with detailed LLM attributes."""
+        status = Status(StatusCode.OK)
+        if trace_info.error:
+            status = Status(StatusCode.ERROR, trace_info.error)
+
+        # Extract model information from `metadata`` or `message_data`
+        trace_metadata = trace_info.metadata or {}
+        message_data = trace_info.message_data or {}
+
+        model_provider = trace_metadata.get("ls_provider") or (
+            message_data.get("model_provider", "") if isinstance(message_data, dict) else ""
+        )
+        model_name = trace_metadata.get("ls_model_name") or (
+            message_data.get("model_id", "") if isinstance(message_data, dict) else ""
+        )
+
+        inputs_str = str(trace_info.inputs or "")
+        outputs_str = str(trace_info.outputs or "")
+
+        attributes = {
+            GEN_AI_SESSION_ID: trace_metadata.get("conversation_id", ""),
+            GEN_AI_USER_ID: str(user_id),
+            GEN_AI_SPAN_KIND: GenAISpanKind.GENERATION.value,
+            GEN_AI_FRAMEWORK: "dify",
+            GEN_AI_MODEL_NAME: str(model_name),
+            GEN_AI_PROVIDER: str(model_provider),
+            GEN_AI_USAGE_INPUT_TOKENS: str(trace_info.message_tokens or 0),
+            GEN_AI_USAGE_OUTPUT_TOKENS: str(trace_info.answer_tokens or 0),
+            GEN_AI_USAGE_TOTAL_TOKENS: str(trace_info.total_tokens or 0),
+            GEN_AI_PROMPT: inputs_str,
+            GEN_AI_COMPLETION: outputs_str,
+            INPUT_VALUE: inputs_str,
+            OUTPUT_VALUE: outputs_str,
+        }
+
+        if trace_info.is_streaming_request:
+            attributes[GEN_AI_IS_STREAMING_REQUEST] = "true"
+
+        return SpanData(
+            trace_id=trace_id,
+            parent_span_id=parent_span_id,
+            span_id=TencentTraceUtils.convert_to_span_id(trace_info.message_id, "llm"),
+            name="GENERATION",
+            start_time=TencentSpanBuilder._get_time_nanoseconds(trace_info.start_time),
+            end_time=TencentSpanBuilder._get_time_nanoseconds(trace_info.end_time),
+            attributes=attributes,
+            status=status,
+        )
+
     @staticmethod
     def build_tool_span(trace_info: ToolTraceInfo, trace_id: int, parent_span_id: int) -> SpanData:
         """Build tool span."""

api/core/ops/tencent_trace/tencent_trace.py

@@ -107,9 +107,13 @@ class TencentDataTrace(BaseTraceInstance):
                 links.append(TencentTraceUtils.create_link(trace_info.trace_id))
 
             message_span = TencentSpanBuilder.build_message_span(trace_info, trace_id, str(user_id), links)
-
             self.trace_client.add_span(message_span)
 
+            # Add LLM child span with detailed attributes
+            parent_span_id = TencentTraceUtils.convert_to_span_id(trace_info.message_id, "message")
+            llm_span = TencentSpanBuilder.build_message_llm_span(trace_info, trace_id, parent_span_id, str(user_id))
+            self.trace_client.add_span(llm_span)
+
             self._record_message_llm_metrics(trace_info)
 
             # Record trace duration for entry span

api/core/prompt/entities/advanced_prompt_entities.py

@@ -44,7 +44,7 @@ class MemoryConfig(BaseModel):
 
         enabled: bool
         size: int | None = None
-    mode: Literal["linear", "block"] | None = "linear"
+
     role_prefix: RolePrefix | None = None
     window: WindowConfig
     query_prompt_template: str | None = None

api/core/rag/datasource/keyword/jieba/jieba_keyword_table_handler.py

@@ -1,20 +1,110 @@
 import re
+from operator import itemgetter
 from typing import cast
 
 
 class JiebaKeywordTableHandler:
     def __init__(self):
+        from core.rag.datasource.keyword.jieba.stopwords import STOPWORDS
+
+        tfidf = self._load_tfidf_extractor()
+        tfidf.stop_words = STOPWORDS  # type: ignore[attr-defined]
+        self._tfidf = tfidf
+
+    def _load_tfidf_extractor(self):
+        """
+        Load jieba TFIDF extractor with fallback strategy.
+
+        Loading Flow:
+        ┌─────────────────────────────────────────────────────────────────────┐
+        │                      jieba.analyse.default_tfidf                    │
+        │                              exists?                                │
+        └─────────────────────────────────────────────────────────────────────┘
+                           │                              │
+                          YES                            NO
+                           │                              │
+                           ▼                              ▼
+                ┌──────────────────┐       ┌──────────────────────────────────┐
+                │  Return default  │       │   jieba.analyse.TFIDF exists?    │
+                │      TFIDF       │       └──────────────────────────────────┘
+                └──────────────────┘                │                │
+                                                   YES              NO
+                                                    │                │
+                                                    │                ▼
+                                                    │   ┌────────────────────────────┐
+                                                    │   │  Try import from          │
+                                                    │   │  jieba.analyse.tfidf.TFIDF │
+                                                    │   └────────────────────────────┘
+                                                    │          │            │
+                                                    │        SUCCESS      FAILED
+                                                    │          │            │
+                                                    ▼          ▼            ▼
+                                        ┌────────────────────────┐    ┌─────────────────┐
+                                        │  Instantiate TFIDF()   │    │  Build fallback │
+                                        │  & cache to default    │    │  _SimpleTFIDF   │
+                                        └────────────────────────┘    └─────────────────┘
+        """
         import jieba.analyse  # type: ignore
 
+        tfidf = getattr(jieba.analyse, "default_tfidf", None)
+        if tfidf is not None:
+            return tfidf
+
+        tfidf_class = getattr(jieba.analyse, "TFIDF", None)
+        if tfidf_class is None:
+            try:
+                from jieba.analyse.tfidf import TFIDF  # type: ignore
+
+                tfidf_class = TFIDF
+            except Exception:
+                tfidf_class = None
+
+        if tfidf_class is not None:
+            tfidf = tfidf_class()
+            jieba.analyse.default_tfidf = tfidf  # type: ignore[attr-defined]
+            return tfidf
+
+        return self._build_fallback_tfidf()
+
+    @staticmethod
+    def _build_fallback_tfidf():
+        """Fallback lightweight TFIDF for environments missing jieba's TFIDF."""
+        import jieba  # type: ignore
+
         from core.rag.datasource.keyword.jieba.stopwords import STOPWORDS
 
-        jieba.analyse.default_tfidf.stop_words = STOPWORDS  # type: ignore
+        class _SimpleTFIDF:
+            def __init__(self):
+                self.stop_words = STOPWORDS
+                self._lcut = getattr(jieba, "lcut", None)
+
+            def extract_tags(self, sentence: str, top_k: int | None = 20, **kwargs):
+                # Basic frequency-based keyword extraction as a fallback when TF-IDF is unavailable.
+                top_k = kwargs.pop("topK", top_k)
+                cut = getattr(jieba, "cut", None)
+                if self._lcut:
+                    tokens = self._lcut(sentence)
+                elif callable(cut):
+                    tokens = list(cut(sentence))
+                else:
+                    tokens = re.findall(r"\w+", sentence)
+
+                words = [w for w in tokens if w and w not in self.stop_words]
+                freq: dict[str, int] = {}
+                for w in words:
+                    freq[w] = freq.get(w, 0) + 1
+
+                sorted_words = sorted(freq.items(), key=itemgetter(1), reverse=True)
+                if top_k is not None:
+                    sorted_words = sorted_words[:top_k]
+
+                return [item[0] for item in sorted_words]
+
+        return _SimpleTFIDF()
 
     def extract_keywords(self, text: str, max_keywords_per_chunk: int | None = 10) -> set[str]:
         """Extract keywords with JIEBA tfidf."""
-        import jieba.analyse  # type: ignore
-
-        keywords = jieba.analyse.extract_tags(
+        keywords = self._tfidf.extract_tags(
             sentence=text,
             topK=max_keywords_per_chunk,
         )

api/core/rag/datasource/vdb/oracle/oraclevector.py

@@ -302,8 +302,7 @@ class OracleVector(BaseVector):
                     nltk.data.find("tokenizers/punkt")
                     nltk.data.find("corpora/stopwords")
                 except LookupError:
-                    nltk.download("punkt")
-                    nltk.download("stopwords")
+                    raise LookupError("Unable to find the required NLTK data package: punkt and stopwords")
                 e_str = re.sub(r"[^\w ]", "", query)
                 all_tokens = nltk.word_tokenize(e_str)
                 stop_words = stopwords.words("english")

api/core/rag/datasource/vdb/weaviate/weaviate_vector.py

@@ -167,13 +167,18 @@ class WeaviateVector(BaseVector):
 
             try:
                 if not self._client.collections.exists(self._collection_name):
+                    tokenization = (
+                        wc.Tokenization(dify_config.WEAVIATE_TOKENIZATION)
+                        if dify_config.WEAVIATE_TOKENIZATION
+                        else wc.Tokenization.WORD
+                    )
                     self._client.collections.create(
                         name=self._collection_name,
                         properties=[
                             wc.Property(
                                 name=Field.TEXT_KEY.value,
                                 data_type=wc.DataType.TEXT,
-                                tokenization=wc.Tokenization.WORD,
+                                tokenization=tokenization,
                             ),
                             wc.Property(name="document_id", data_type=wc.DataType.TEXT),
                             wc.Property(name="doc_id", data_type=wc.DataType.TEXT),

api/core/rag/embedding/cached_embedding.py

@@ -1,5 +1,6 @@
 import base64
 import logging
+import pickle
 from typing import Any, cast
 
 import numpy as np
@@ -89,8 +90,8 @@ class CacheEmbedding(Embeddings):
                                 model_name=self._model_instance.model,
                                 hash=hash,
                                 provider_name=self._model_instance.provider,
+                                embedding=pickle.dumps(n_embedding, protocol=pickle.HIGHEST_PROTOCOL),
                             )
-                            embedding_cache.set_embedding(n_embedding)
                             db.session.add(embedding_cache)
                             cache_embeddings.append(hash)
                     db.session.commit()

api/core/tools/entities/tool_bundle.py

@@ -1,4 +1,6 @@
-from pydantic import BaseModel
+from collections.abc import Mapping
+
+from pydantic import BaseModel, Field
 
 from core.tools.entities.tool_entities import ToolParameter
 
@@ -25,3 +27,5 @@ class ApiToolBundle(BaseModel):
     icon: str | None = None
     # openapi operation
     openapi: dict
+    # output schema
+    output_schema: Mapping[str, object] = Field(default_factory=dict)

api/core/tools/utils/workflow_configuration_sync.py

@@ -3,6 +3,7 @@ from typing import Any
 
 from core.app.app_config.entities import VariableEntity
 from core.tools.entities.tool_entities import WorkflowToolParameterConfiguration
+from core.workflow.nodes.base.entities import OutputVariableEntity
 
 
 class WorkflowToolConfigurationUtils:
@@ -24,6 +25,31 @@ class WorkflowToolConfigurationUtils:
 
         return [VariableEntity.model_validate(variable) for variable in start_node.get("data", {}).get("variables", [])]
 
+    @classmethod
+    def get_workflow_graph_output(cls, graph: Mapping[str, Any]) -> Sequence[OutputVariableEntity]:
+        """
+        get workflow graph output
+        """
+        nodes = graph.get("nodes", [])
+        outputs_by_variable: dict[str, OutputVariableEntity] = {}
+        variable_order: list[str] = []
+
+        for node in nodes:
+            if node.get("data", {}).get("type") != "end":
+                continue
+
+            for output in node.get("data", {}).get("outputs", []):
+                entity = OutputVariableEntity.model_validate(output)
+                variable = entity.variable
+
+                if variable not in variable_order:
+                    variable_order.append(variable)
+
+                # Later end nodes override duplicated variable definitions.
+                outputs_by_variable[variable] = entity
+
+        return [outputs_by_variable[variable] for variable in variable_order]
+
     @classmethod
     def check_is_synced(
         cls, variables: list[VariableEntity], tool_configurations: list[WorkflowToolParameterConfiguration]

api/core/tools/workflow_as_tool/provider.py

@@ -141,6 +141,7 @@ class WorkflowToolProviderController(ToolProviderController):
                         form=parameter.form,
                         llm_description=parameter.description,
                         required=variable.required,
+                        default=variable.default,
                         options=options,
                         placeholder=I18nObject(en_US="", zh_Hans=""),
                     )
@@ -161,6 +162,20 @@ class WorkflowToolProviderController(ToolProviderController):
             else:
                 raise ValueError("variable not found")
 
+        # get output schema from workflow
+        outputs = WorkflowToolConfigurationUtils.get_workflow_graph_output(graph)
+
+        reserved_keys = {"json", "text", "files"}
+
+        properties = {}
+        for output in outputs:
+            if output.variable not in reserved_keys:
+                properties[output.variable] = {
+                    "type": output.value_type,
+                    "description": "",
+                }
+        output_schema = {"type": "object", "properties": properties}
+
         return WorkflowTool(
             workflow_as_tool_id=db_provider.id,
             entity=ToolEntity(
@@ -176,6 +191,7 @@ class WorkflowToolProviderController(ToolProviderController):
                     llm=db_provider.description,
                 ),
                 parameters=workflow_tool_parameters,
+                output_schema=output_schema,
             ),
             runtime=ToolRuntime(
                 tenant_id=db_provider.tenant_id,