[Chore/Refactor] Switch from MyPy to Basedpyright for type checking (#25047)

Signed-off-by: -LAN- <laipz8200@outlook.com>

.github/workflows/api-tests.yml

@@ -62,14 +62,8 @@ jobs:
       - name: Run dify config tests
         run: uv run --project api dev/pytest/pytest_config_tests.py
 
-      - name: MyPy Cache
+      - name: Run Basedpyright Checks
-        uses: actions/cache@v4
+        run: dev/basedpyright-check
-        with:
-          path: api/.mypy_cache
-          key: mypy-${{ matrix.python-version }}-${{ runner.os }}-${{ hashFiles('api/uv.lock') }}
-
-      - name: Run MyPy Checks
-        run: dev/mypy-check
 
       - name: Set up dotenvs
         run: |

.gitignore

@@ -123,7 +123,7 @@ venv.bak/
 # mkdocs documentation
 /site
 
-# mypy
+# type checking
 .mypy_cache/
 .dmypy.json
 dmypy.json
@@ -195,7 +195,6 @@ sdks/python-client/dify_client.egg-info
 .vscode/*
 !.vscode/launch.json.template
 !.vscode/README.md
-pyrightconfig.json
 api/.vscode
 # vscode Code History Extension
 .history

CLAUDE.md

@@ -32,7 +32,7 @@ uv run --project api pytest tests/integration_tests/  # Integration tests
 ./dev/reformat                    # Run all formatters and linters
 uv run --project api ruff check --fix ./    # Fix linting issues
 uv run --project api ruff format ./         # Format code
-uv run --project api mypy .                 # Type checking
+uv run --directory api basedpyright         # Type checking
 ```
 
 ### Frontend (Web)

api/README.md

@@ -108,5 +108,5 @@ uv run celery -A app.celery beat
    ../dev/reformat               # Run all formatters and linters
    uv run ruff check --fix ./    # Fix linting issues
    uv run ruff format ./         # Format code
-   uv run mypy .                 # Type checking
+   uv run basedpyright .         # Type checking
    ```

api/commands.py

@@ -571,7 +571,7 @@ def old_metadata_migration():
         for document in documents:
             if document.doc_metadata:
                 doc_metadata = document.doc_metadata
-                for key, value in doc_metadata.items():
+                for key in doc_metadata:
                     for field in BuiltInField:
                         if field.value == key:
                             break

api/configs/remote_settings_sources/nacos/__init__.py

@@ -29,7 +29,7 @@ class NacosSettingsSource(RemoteSettingsSource):
         try:
             content = NacosHttpClient().http_request("/nacos/v1/cs/configs", method="GET", headers={}, params=params)
             self.remote_configs = self._parse_config(content)
-        except Exception as e:
+        except Exception:
             logger.exception("[get-access-token] exception occurred")
             raise
 

api/configs/remote_settings_sources/nacos/http_request.py

@@ -77,6 +77,6 @@ class NacosHttpClient:
             self.token = response_data.get("accessToken")
             self.token_ttl = response_data.get("tokenTtl", 18000)
             self.token_expire_time = current_time + self.token_ttl - 10
-        except Exception as e:
+        except Exception:
             logger.exception("[get-access-token] exception occur")
             raise

api/controllers/console/auth/login.py

@@ -130,7 +130,7 @@ class ResetPasswordSendEmailApi(Resource):
             language = "en-US"
         try:
             account = AccountService.get_user_through_email(args["email"])
-        except AccountRegisterError as are:
+        except AccountRegisterError:
             raise AccountInFreezeError()
 
         if account is None:
@@ -162,7 +162,7 @@ class EmailCodeLoginSendEmailApi(Resource):
             language = "en-US"
         try:
             account = AccountService.get_user_through_email(args["email"])
-        except AccountRegisterError as are:
+        except AccountRegisterError:
             raise AccountInFreezeError()
 
         if account is None:
@@ -200,7 +200,7 @@ class EmailCodeLoginApi(Resource):
         AccountService.revoke_email_code_login_token(args["token"])
         try:
             account = AccountService.get_user_through_email(user_email)
-        except AccountRegisterError as are:
+        except AccountRegisterError:
             raise AccountInFreezeError()
         if account:
             tenants = TenantService.get_join_tenants(account)
@@ -223,7 +223,7 @@ class EmailCodeLoginApi(Resource):
                 )
             except WorkSpaceNotAllowedCreateError:
                 raise NotAllowedCreateWorkspace()
-            except AccountRegisterError as are:
+            except AccountRegisterError:
                 raise AccountInFreezeError()
             except WorkspacesLimitExceededError:
                 raise WorkspacesLimitExceeded()

api/controllers/service_api/app/file_preview.py

@@ -59,7 +59,7 @@ class FilePreviewApi(Resource):
         args = file_preview_parser.parse_args()
 
         # Validate file ownership and get file objects
-        message_file, upload_file = self._validate_file_ownership(file_id, app_model.id)
+        _, upload_file = self._validate_file_ownership(file_id, app_model.id)
 
         # Get file content generator
         try:

api/controllers/service_api/dataset/document.py

@@ -410,7 +410,7 @@ class DocumentUpdateByFileApi(DatasetApiResource):
         DocumentService.document_create_args_validate(knowledge_config)
 
         try:
-            documents, batch = DocumentService.save_document_with_dataset_id(
+            documents, _ = DocumentService.save_document_with_dataset_id(
                 dataset=dataset,
                 knowledge_config=knowledge_config,
                 account=dataset.created_by_account,

api/core/app/app_config/features/more_like_this/manager.py

@@ -26,7 +26,7 @@ class MoreLikeThisConfigManager:
     def validate_and_set_defaults(cls, config: dict) -> tuple[dict, list[str]]:
         try:
             return AppConfigModel.model_validate(config).model_dump(), ["more_like_this"]
-        except ValidationError as e:
+        except ValidationError:
             raise ValueError(
                 "more_like_this must be of dict type and enabled in more_like_this must be of boolean type"
             )

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

@@ -310,13 +310,8 @@ class AdvancedChatAppGenerateTaskPipeline:
             err = self._base_task_pipeline._handle_error(event=event, session=session, message_id=self._message_id)
         yield self._base_task_pipeline._error_to_stream_response(err)
 
-    def _handle_workflow_started_event(
+    def _handle_workflow_started_event(self, **kwargs) -> Generator[StreamResponse, None, None]:
-        self, event: QueueWorkflowStartedEvent, *, graph_runtime_state: Optional[GraphRuntimeState] = None, **kwargs
-    ) -> Generator[StreamResponse, None, None]:
         """Handle workflow started events."""
-        # Override graph runtime state - this is a side effect but necessary
-        graph_runtime_state = event.graph_runtime_state
-
         with self._database_session() as session:
             workflow_execution = self._workflow_cycle_manager.handle_workflow_run_start()
             self._workflow_run_id = workflow_execution.id_
@@ -337,15 +332,14 @@ class AdvancedChatAppGenerateTaskPipeline:
         """Handle node retry events."""
         self._ensure_workflow_initialized()
 
-        with self._database_session() as session:
+        workflow_node_execution = self._workflow_cycle_manager.handle_workflow_node_execution_retried(
-            workflow_node_execution = self._workflow_cycle_manager.handle_workflow_node_execution_retried(
+            workflow_execution_id=self._workflow_run_id, event=event
-                workflow_execution_id=self._workflow_run_id, event=event
+        )
-            )
+        node_retry_resp = self._workflow_response_converter.workflow_node_retry_to_stream_response(
-            node_retry_resp = self._workflow_response_converter.workflow_node_retry_to_stream_response(
+            event=event,
-                event=event,
+            task_id=self._application_generate_entity.task_id,
-                task_id=self._application_generate_entity.task_id,
+            workflow_node_execution=workflow_node_execution,
-                workflow_node_execution=workflow_node_execution,
+        )
-            )
 
         if node_retry_resp:
             yield node_retry_resp
@@ -379,13 +373,12 @@ class AdvancedChatAppGenerateTaskPipeline:
                 self._workflow_response_converter.fetch_files_from_node_outputs(event.outputs or {})
             )
 
-        with self._database_session() as session:
+        workflow_node_execution = self._workflow_cycle_manager.handle_workflow_node_execution_success(event=event)
-            workflow_node_execution = self._workflow_cycle_manager.handle_workflow_node_execution_success(event=event)
+        node_finish_resp = self._workflow_response_converter.workflow_node_finish_to_stream_response(
-            node_finish_resp = self._workflow_response_converter.workflow_node_finish_to_stream_response(
+            event=event,
-                event=event,
+            task_id=self._application_generate_entity.task_id,
-                task_id=self._application_generate_entity.task_id,
+            workflow_node_execution=workflow_node_execution,
-                workflow_node_execution=workflow_node_execution,
+        )
-            )
 
         self._save_output_for_event(event, workflow_node_execution.id)
 

api/core/app/apps/base_app_queue_manager.py

@@ -159,7 +159,7 @@ class AppQueueManager:
     def _check_for_sqlalchemy_models(self, data: Any):
         # from entity to dict or list
         if isinstance(data, dict):
-            for key, value in data.items():
+            for value in data.values():
                 self._check_for_sqlalchemy_models(value)
         elif isinstance(data, list):
             for item in data:

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

@@ -300,16 +300,15 @@ class WorkflowAppGenerateTaskPipeline:
         """Handle node retry events."""
         self._ensure_workflow_initialized()
 
-        with self._database_session() as session:
+        workflow_node_execution = self._workflow_cycle_manager.handle_workflow_node_execution_retried(
-            workflow_node_execution = self._workflow_cycle_manager.handle_workflow_node_execution_retried(
+            workflow_execution_id=self._workflow_run_id,
-                workflow_execution_id=self._workflow_run_id,
+            event=event,
-                event=event,
+        )
-            )
+        response = self._workflow_response_converter.workflow_node_retry_to_stream_response(
-            response = self._workflow_response_converter.workflow_node_retry_to_stream_response(
+            event=event,
-                event=event,
+            task_id=self._application_generate_entity.task_id,
-                task_id=self._application_generate_entity.task_id,
+            workflow_node_execution=workflow_node_execution,
-                workflow_node_execution=workflow_node_execution,
+        )
-            )
 
         if response:
             yield response

api/core/app/entities/app_invoke_entities.py

@@ -1,5 +1,5 @@
 from collections.abc import Mapping, Sequence
-from enum import Enum
+from enum import StrEnum
 from typing import Any, Optional
 
 from pydantic import BaseModel, ConfigDict, Field, ValidationInfo, field_validator
@@ -11,7 +11,7 @@ from core.file import File, FileUploadConfig
 from core.model_runtime.entities.model_entities import AIModelEntity
 
 
-class InvokeFrom(Enum):
+class InvokeFrom(StrEnum):
     """
     Invoke From.
     """

api/core/app/task_pipeline/message_cycle_manager.py

@@ -101,7 +101,7 @@ class MessageCycleManager:
                 try:
                     name = LLMGenerator.generate_conversation_name(app_model.tenant_id, query)
                     conversation.name = name
-                except Exception as e:
+                except Exception:
                     if dify_config.DEBUG:
                         logger.exception("generate conversation name failed, conversation_id: %s", conversation_id)
                     pass

api/core/callback_handler/index_tool_callback_handler.py

@@ -67,7 +67,7 @@ class DatasetIndexToolCallbackHandler:
                     )
                     child_chunk = db.session.scalar(child_chunk_stmt)
                     if child_chunk:
-                        segment = (
+                        _ = (
                             db.session.query(DocumentSegment)
                             .where(DocumentSegment.id == child_chunk.segment_id)
                             .update(

api/core/extension/extensible.py

@@ -91,7 +91,7 @@ class Extensible:
 
                 # Find extension class
                 extension_class = None
-                for name, obj in vars(mod).items():
+                for obj in vars(mod).values():
                     if isinstance(obj, type) and issubclass(obj, cls) and obj != cls:
                         extension_class = obj
                         break
@@ -123,7 +123,7 @@ class Extensible:
                     )
                 )
 
-        except Exception as e:
+        except Exception:
             logger.exception("Error scanning extensions")
             raise
 

api/core/extension/extension.py

@@ -41,9 +41,3 @@ class Extension:
         assert module_extension.extension_class is not None
         t: type = module_extension.extension_class
         return t
-
-    def validate_form_schema(self, module: ExtensionModule, extension_name: str, config: dict) -> None:
-        module_extension = self.module_extension(module, extension_name)
-        form_schema = module_extension.form_schema
-
-        # TODO validate form_schema

api/core/external_data_tool/factory.py

@@ -22,7 +22,6 @@ class ExternalDataToolFactory:
         :param config: the form config data
         :return:
         """
-        code_based_extension.validate_form_schema(ExtensionModule.EXTERNAL_DATA_TOOL, name, config)
         extension_class = code_based_extension.extension_class(ExtensionModule.EXTERNAL_DATA_TOOL, name)
         # FIXME mypy issue here, figure out how to fix it
         extension_class.validate_config(tenant_id, config)  # type: ignore

api/core/helper/marketplace.py

@@ -42,7 +42,7 @@ def batch_fetch_plugin_manifests_ignore_deserialization_error(
     for plugin in response.json()["data"]["plugins"]:
         try:
             result.append(MarketplacePluginDeclaration(**plugin))
-        except Exception as e:
+        except Exception:
             pass
 
     return result

api/core/indexing_runner.py

@@ -5,7 +5,7 @@ import re
 import threading
 import time
 import uuid
-from typing import Any, Optional, cast
+from typing import Any, Optional
 
 from flask import current_app
 from sqlalchemy import select
@@ -397,7 +397,6 @@ class IndexingRunner:
         )
 
         # replace doc id to document model id
-        text_docs = cast(list[Document], text_docs)
         for text_doc in text_docs:
             if text_doc.metadata is not None:
                 text_doc.metadata["document_id"] = dataset_document.id

api/core/llm_generator/llm_generator.py

@@ -66,7 +66,7 @@ class LLMGenerator:
         try:
             result_dict = json.loads(cleaned_answer)
             answer = result_dict["Your Output"]
-        except json.JSONDecodeError as e:
+        except json.JSONDecodeError:
             logger.exception("Failed to generate name after answer, use query instead")
             answer = query
         name = answer.strip()

api/core/mcp/auth/auth_flow.py

@@ -101,7 +101,7 @@ def handle_callback(state_key: str, authorization_code: str) -> OAuthCallbackSta
 
 def check_support_resource_discovery(server_url: str) -> tuple[bool, str]:
     """Check if the server supports OAuth 2.0 Resource Discovery."""
-    b_scheme, b_netloc, b_path, b_params, b_query, b_fragment = urlparse(server_url, "", True)
+    b_scheme, b_netloc, b_path, _, b_query, b_fragment = urlparse(server_url, "", True)
     url_for_resource_discovery = f"{b_scheme}://{b_netloc}/.well-known/oauth-protected-resource{b_path}"
     if b_query:
         url_for_resource_discovery += f"?{b_query}"
@@ -117,7 +117,7 @@ def check_support_resource_discovery(server_url: str) -> tuple[bool, str]:
             else:
                 return False, ""
         return False, ""
-    except httpx.RequestError as e:
+    except httpx.RequestError:
         # Not support resource discovery, fall back to well-known OAuth metadata
         return False, ""
 

api/core/mcp/mcp_client.py

@@ -2,7 +2,7 @@ import logging
 from collections.abc import Callable
 from contextlib import AbstractContextManager, ExitStack
 from types import TracebackType
-from typing import Any, Optional, cast
+from typing import Any, Optional
 from urllib.parse import urlparse
 
 from core.mcp.client.sse_client import sse_client
@@ -116,8 +116,7 @@ class MCPClient:
 
             self._session_context = ClientSession(*streams)
             self._session = self._exit_stack.enter_context(self._session_context)
-            session = cast(ClientSession, self._session)
+            self._session.initialize()
-            session.initialize()
             return
 
         except MCPAuthError:

api/core/moderation/factory.py

@@ -20,7 +20,6 @@ class ModerationFactory:
         :param config: the form config data
         :return:
         """
-        code_based_extension.validate_form_schema(ExtensionModule.MODERATION, name, config)
         extension_class = code_based_extension.extension_class(ExtensionModule.MODERATION, name)
         # FIXME: mypy error, try to fix it instead of using type: ignore
         extension_class.validate_config(tenant_id, config)  # type: ignore

api/core/moderation/output_moderation.py

@@ -135,7 +135,7 @@ class OutputModeration(BaseModel):
 
             result: ModerationOutputsResult = moderation_factory.moderation_for_outputs(moderation_buffer)
             return result
-        except Exception as e:
+        except Exception:
             logger.exception("Moderation Output error, app_id: %s", app_id)
 
         return None

api/core/ops/ops_trace_manager.py

@@ -849,7 +849,7 @@ class TraceQueueManager:
             if self.trace_instance:
                 trace_task.app_id = self.app_id
                 trace_manager_queue.put(trace_task)
-        except Exception as e:
+        except Exception:
             logger.exception("Error adding trace task, trace_type %s", trace_task.trace_type)
         finally:
             self.start_timer()
@@ -868,7 +868,7 @@ class TraceQueueManager:
             tasks = self.collect_tasks()
             if tasks:
                 self.send_to_celery(tasks)
-        except Exception as e:
+        except Exception:
             logger.exception("Error processing trace tasks")
 
     def start_timer(self):

api/core/plugin/utils/chunk_merger.py

@@ -1,6 +1,6 @@
 from collections.abc import Generator
 from dataclasses import dataclass, field
-from typing import TypeVar, Union, cast
+from typing import TypeVar, Union
 
 from core.agent.entities import AgentInvokeMessage
 from core.tools.entities.tool_entities import ToolInvokeMessage
@@ -85,7 +85,7 @@ def merge_blob_chunks(
                     message=ToolInvokeMessage.BlobMessage(blob=files[chunk_id].data[: files[chunk_id].bytes_written]),
                     meta=resp.meta,
                 )
-                yield cast(MessageType, merged_message)
+                yield merged_message
                 # Clean up the buffer
                 del files[chunk_id]
         else:

api/core/rag/datasource/vdb/analyticdb/analyticdb_vector_sql.py

@@ -228,7 +228,7 @@ class AnalyticdbVectorBySql:
             )
             documents = []
             for record in cur:
-                id, vector, score, page_content, metadata = record
+                _, vector, score, page_content, metadata = record
                 if score >= score_threshold:
                     metadata["score"] = score
                     doc = Document(
@@ -260,7 +260,7 @@ class AnalyticdbVectorBySql:
             )
             documents = []
             for record in cur:
-                id, vector, page_content, metadata, score = record
+                _, vector, page_content, metadata, score = record
                 metadata["score"] = score
                 doc = Document(
                     page_content=page_content,

api/core/rag/datasource/vdb/clickzetta/clickzetta_vector.py

@@ -701,7 +701,7 @@ class ClickzettaVector(BaseVector):
                         len(data_rows),
                         vector_dimension,
                     )
-                except (RuntimeError, ValueError, TypeError, ConnectionError) as e:
+                except (RuntimeError, ValueError, TypeError, ConnectionError):
                     logger.exception("Parameterized SQL execution failed for %d documents", len(data_rows))
                     logger.exception("SQL template: %s", insert_sql)
                     logger.exception("Sample data row: %s", data_rows[0] if data_rows else "None")
@@ -787,7 +787,7 @@ class ClickzettaVector(BaseVector):
         document_ids_filter = kwargs.get("document_ids_filter")
 
         # Handle filter parameter from canvas (workflow)
-        filter_param = kwargs.get("filter", {})
+        _ = kwargs.get("filter", {})
 
         # Build filter clause
         filter_clauses = []
@@ -879,7 +879,7 @@ class ClickzettaVector(BaseVector):
         document_ids_filter = kwargs.get("document_ids_filter")
 
         # Handle filter parameter from canvas (workflow)
-        filter_param = kwargs.get("filter", {})
+        _ = kwargs.get("filter", {})
 
         # Build filter clause
         filter_clauses = []
@@ -938,7 +938,7 @@ class ClickzettaVector(BaseVector):
                                     metadata = {}
                             else:
                                 metadata = {}
-                        except (json.JSONDecodeError, TypeError) as e:
+                        except (json.JSONDecodeError, TypeError):
                             logger.exception("JSON parsing failed")
                             # Fallback: extract document_id with regex
 
@@ -956,7 +956,7 @@ class ClickzettaVector(BaseVector):
                         metadata["score"] = 1.0  # Clickzetta doesn't provide relevance scores
                         doc = Document(page_content=row[1], metadata=metadata)
                         documents.append(doc)
-                except (RuntimeError, ValueError, TypeError, ConnectionError) as e:
+                except (RuntimeError, ValueError, TypeError, ConnectionError):
                     logger.exception("Full-text search failed")
                     # Fallback to LIKE search if full-text search fails
                     return self._search_by_like(query, **kwargs)
@@ -978,7 +978,7 @@ class ClickzettaVector(BaseVector):
         document_ids_filter = kwargs.get("document_ids_filter")
 
         # Handle filter parameter from canvas (workflow)
-        filter_param = kwargs.get("filter", {})
+        _ = kwargs.get("filter", {})
 
         # Build filter clause
         filter_clauses = []

api/core/rag/datasource/vdb/couchbase/couchbase_vector.py

@@ -212,10 +212,10 @@ class CouchbaseVector(BaseVector):
 
         documents_to_insert = [
             {"text": text, "embedding": vector, "metadata": metadata}
-            for id, text, vector, metadata in zip(uuids, texts, embeddings, metadatas)
+            for _, text, vector, metadata in zip(uuids, texts, embeddings, metadatas)
         ]
         for doc, id in zip(documents_to_insert, uuids):
-            result = self._scope.collection(self._collection_name).upsert(id, doc)
+            _ = self._scope.collection(self._collection_name).upsert(id, doc)
 
         doc_ids.extend(uuids)
 
@@ -241,7 +241,7 @@ class CouchbaseVector(BaseVector):
             """
         try:
             self._cluster.query(query, named_parameters={"doc_ids": ids}).execute()
-        except Exception as e:
+        except Exception:
             logger.exception("Failed to delete documents, ids: %s", ids)
 
     def delete_by_document_id(self, document_id: str):

api/core/rag/datasource/vdb/matrixone/matrixone_vector.py

@@ -99,7 +99,7 @@ class MatrixoneVector(BaseVector):
                 return client
             try:
                 client.create_full_text_index()
-            except Exception as e:
+            except Exception:
                 logger.exception("Failed to create full text index")
             redis_client.set(collection_exist_cache_key, 1, ex=3600)
             return client

api/core/rag/datasource/vdb/opensearch/opensearch_vector.py

@@ -197,7 +197,7 @@ class OpenSearchVector(BaseVector):
 
         try:
             response = self._client.search(index=self._collection_name.lower(), body=query)
-        except Exception as e:
+        except Exception:
             logger.exception("Error executing vector search, query: %s", query)
             raise
 

api/core/rag/datasource/vdb/tablestore/tablestore_vector.py

@@ -71,7 +71,7 @@ class TableStoreVector(BaseVector):
         table_result = result.get_result_by_table(self._table_name)
         for item in table_result:
             if item.is_ok and item.row:
-                kv = {k: v for k, v, t in item.row.attribute_columns}
+                kv = {k: v for k, v, _ in item.row.attribute_columns}
                 docs.append(
                     Document(
                         page_content=kv[Field.CONTENT_KEY.value], metadata=json.loads(kv[Field.METADATA_KEY.value])

api/core/rag/extractor/unstructured/unstructured_doc_extractor.py

@@ -23,7 +23,7 @@ class UnstructuredWordExtractor(BaseExtractor):
         unstructured_version = tuple(int(x) for x in __unstructured_version__.split("."))
         # check the file extension
         try:
-            import magic  # noqa: F401
+            import magic  # noqa: F401  # pyright: ignore[reportUnusedImport]
 
             is_doc = detect_filetype(self._file_path) == FileType.DOC
         except ImportError:

api/core/rag/index_processor/processor/qa_index_processor.py

@@ -113,7 +113,7 @@ class QAIndexProcessor(BaseIndexProcessor):
             # Skip the first row
             df = pd.read_csv(file)
             text_docs = []
-            for index, row in df.iterrows():
+            for _, row in df.iterrows():
                 data = Document(page_content=row.iloc[0], metadata={"answer": row.iloc[1]})
                 text_docs.append(data)
             if len(text_docs) == 0:
@@ -183,7 +183,7 @@ class QAIndexProcessor(BaseIndexProcessor):
                         qa_document.metadata["doc_hash"] = hash
                     qa_documents.append(qa_document)
                 format_documents.extend(qa_documents)
-            except Exception as e:
+            except Exception:
                 logger.exception("Failed to format qa document")
 
             all_qa_documents.extend(format_documents)

api/core/rag/retrieval/dataset_retrieval.py

@@ -9,7 +9,6 @@ from typing import Any, Optional, Union, cast
 from flask import Flask, current_app
 from sqlalchemy import Float, and_, or_, select, text
 from sqlalchemy import cast as sqlalchemy_cast
-from sqlalchemy.orm import Session
 
 from core.app.app_config.entities import (
     DatasetEntity,
@@ -526,7 +525,7 @@ class DatasetRetrieval:
                         )
                         child_chunk = db.session.scalar(child_chunk_stmt)
                         if child_chunk:
-                            segment = (
+                            _ = (
                                 db.session.query(DocumentSegment)
                                 .where(DocumentSegment.id == child_chunk.segment_id)
                                 .update(
@@ -593,9 +592,8 @@ class DatasetRetrieval:
         metadata_condition: Optional[MetadataCondition] = None,
     ):
         with flask_app.app_context():
-            with Session(db.engine) as session:
+            dataset_stmt = select(Dataset).where(Dataset.id == dataset_id)
-                dataset_stmt = select(Dataset).where(Dataset.id == dataset_id)
+            dataset = db.session.scalar(dataset_stmt)
-                dataset = session.scalar(dataset_stmt)
 
             if not dataset:
                 return []
@@ -987,7 +985,7 @@ class DatasetRetrieval:
             )
 
             # handle invoke result
-            result_text, usage = self._handle_invoke_result(invoke_result=invoke_result)
+            result_text, _ = self._handle_invoke_result(invoke_result=invoke_result)
 
             result_text_json = parse_and_check_json_markdown(result_text, [])
             automatic_metadata_filters = []
@@ -1002,7 +1000,7 @@ class DatasetRetrieval:
                                 "condition": item.get("comparison_operator"),
                             }
                         )
-        except Exception as e:
+        except Exception:
             return None
         return automatic_metadata_filters
 

api/core/rag/retrieval/output_parser/structured_chat.py

@@ -19,5 +19,5 @@ class StructuredChatOutputParser:
                     return ReactAction(response["action"], response.get("action_input", {}), text)
             else:
                 return ReactFinish({"output": text}, text)
-        except Exception as e:
+        except Exception:
             raise ValueError(f"Could not parse LLM output: {text}")

api/core/rag/retrieval/router/multi_dataset_function_call_router.py

@@ -38,5 +38,5 @@ class FunctionCallMultiDatasetRouter:
                 # get retrieval model config
                 return result.message.tool_calls[0].function.name
             return None
-        except Exception as e:
+        except Exception:
             return None

api/core/rag/retrieval/router/multi_dataset_react_route.py

@@ -77,7 +77,7 @@ class ReactMultiDatasetRouter:
                 user_id=user_id,
                 tenant_id=tenant_id,
             )
-        except Exception as e:
+        except Exception:
             return None
 
     def _react_invoke(
@@ -120,7 +120,7 @@ class ReactMultiDatasetRouter:
             memory=None,
             model_config=model_config,
         )
-        result_text, usage = self._invoke_llm(
+        result_text, _ = self._invoke_llm(
             completion_param=model_config.parameters,
             model_instance=model_instance,
             prompt_messages=prompt_messages,

api/core/repositories/celery_workflow_execution_repository.py

@@ -119,7 +119,7 @@ class CeleryWorkflowExecutionRepository(WorkflowExecutionRepository):
 
             logger.debug("Queued async save for workflow execution: %s", execution.id_)
 
-        except Exception as e:
+        except Exception:
             logger.exception("Failed to queue save operation for execution %s", execution.id_)
             # In case of Celery failure, we could implement a fallback to synchronous save
             # For now, we'll re-raise the exception

api/core/repositories/celery_workflow_node_execution_repository.py

@@ -142,7 +142,7 @@ class CeleryWorkflowNodeExecutionRepository(WorkflowNodeExecutionRepository):
 
             logger.debug("Cached and queued async save for workflow node execution: %s", execution.id)
 
-        except Exception as e:
+        except Exception:
             logger.exception("Failed to cache or queue save operation for node execution %s", execution.id)
             # In case of Celery failure, we could implement a fallback to synchronous save
             # For now, we'll re-raise the exception
@@ -185,6 +185,6 @@ class CeleryWorkflowNodeExecutionRepository(WorkflowNodeExecutionRepository):
             logger.debug("Retrieved %d workflow node executions for run %s from cache", len(result), workflow_run_id)
             return result
 
-        except Exception as e:
+        except Exception:
             logger.exception("Failed to get workflow node executions for run %s from cache", workflow_run_id)
             return []

api/core/repositories/sqlalchemy_workflow_node_execution_repository.py

@@ -250,7 +250,7 @@ class SQLAlchemyWorkflowNodeExecutionRepository(WorkflowNodeExecutionRepository)
                 logger.debug("Updating cache for node_execution_id: %s", db_model.node_execution_id)
                 self._node_execution_cache[db_model.node_execution_id] = db_model
 
-        except Exception as e:
+        except Exception:
             logger.exception("Failed to save workflow node execution after all retries")
             raise
 

api/core/tools/custom_tool/provider.py

@@ -191,7 +191,7 @@ class ApiToolProviderController(ToolProviderController):
         self.tools = tools
         return tools
 
-    def get_tool(self, tool_name: str):
+    def get_tool(self, tool_name: str) -> ApiTool:
         """
         get tool by name
 

api/core/tools/entities/values.py

@@ -107,5 +107,5 @@ default_tool_label_dict = {
     ),
 }
 
-default_tool_labels = [v for k, v in default_tool_label_dict.items()]
+default_tool_labels = list(default_tool_label_dict.values())
 default_tool_label_name_list = [label.name for label in default_tool_labels]

api/core/tools/tool_manager.py

@@ -303,16 +303,13 @@ class ToolManager:
                 tenant_id=tenant_id,
                 controller=api_provider,
             )
-            return cast(
+            return api_provider.get_tool(tool_name).fork_tool_runtime(
-                ApiTool,
+                runtime=ToolRuntime(
-                api_provider.get_tool(tool_name).fork_tool_runtime(
+                    tenant_id=tenant_id,
-                    runtime=ToolRuntime(
+                    credentials=encrypter.decrypt(credentials),
-                        tenant_id=tenant_id,
+                    invoke_from=invoke_from,
-                        credentials=encrypter.decrypt(credentials),
+                    tool_invoke_from=tool_invoke_from,
-                        invoke_from=invoke_from,
+                )
-                        tool_invoke_from=tool_invoke_from,
-                    )
-                ),
             )
         elif provider_type == ToolProviderType.WORKFLOW:
             workflow_provider_stmt = select(WorkflowToolProvider).where(

api/core/workflow/nodes/answer/answer_stream_processor.py

@@ -68,7 +68,7 @@ class AnswerStreamProcessor(StreamProcessor):
 
     def reset(self) -> None:
         self.route_position = {}
-        for answer_node_id, route_chunks in self.generate_routes.answer_generate_route.items():
+        for answer_node_id, _ in self.generate_routes.answer_generate_route.items():
             self.route_position[answer_node_id] = 0
         self.rest_node_ids = self.graph.node_ids.copy()
         self.current_stream_chunk_generating_node_ids = {}

api/core/workflow/nodes/document_extractor/node.py

@@ -5,7 +5,7 @@ import logging
 import os
 import tempfile
 from collections.abc import Mapping, Sequence
-from typing import Any, Optional, cast
+from typing import Any, Optional
 
 import chardet
 import docx
@@ -428,9 +428,9 @@ def _download_file_content(file: File) -> bytes:
                 raise FileDownloadError("Missing URL for remote file")
             response = ssrf_proxy.get(file.remote_url)
             response.raise_for_status()
-            return cast(bytes, response.content)
+            return response.content
         else:
-            return cast(bytes, file_manager.download(file))
+            return file_manager.download(file)
     except Exception as e:
         raise FileDownloadError(f"Error downloading file: {str(e)}") from e
 

api/core/workflow/nodes/knowledge_retrieval/knowledge_retrieval_node.py

@@ -571,7 +571,7 @@ class KnowledgeRetrievalNode(BaseNode):
                                 "condition": item.get("comparison_operator"),
                             }
                         )
-        except Exception as e:
+        except Exception:
             return []
         return automatic_metadata_filters
 

api/core/workflow/nodes/loop/loop_node.py

@@ -324,7 +324,7 @@ class LoopNode(BaseNode):
 
                 # Process conditions if at least one variable is available
                 if available_conditions:
-                    input_conditions, group_result, check_break_result = condition_processor.process_conditions(
+                    _, _, check_break_result = condition_processor.process_conditions(
                         variable_pool=self.graph_runtime_state.variable_pool,
                         conditions=available_conditions,
                         operator=logical_operator,

api/core/workflow/nodes/parameter_extractor/entities.py

@@ -43,10 +43,6 @@ def _validate_type(parameter_type: str) -> SegmentType:
     return SegmentType(parameter_type)
 
 
-class _ParameterConfigError(Exception):
-    pass
-
-
 class ParameterConfig(BaseModel):
     """
     Parameter Config.

api/core/workflow/nodes/variable_assigner/common/helpers.py

@@ -25,7 +25,7 @@ _T = TypeVar("_T", bound=MutableMapping[str, Any])
 def variable_to_processed_data(selector: Sequence[str], seg: Segment) -> UpdatedVariable:
     if len(selector) < SELECTORS_LENGTH:
         raise Exception("selector too short")
-    node_id, var_name = selector[:2]
+    _, var_name = selector[:2]
     return UpdatedVariable(
         name=var_name,
         selector=list(selector[:2]),

api/events/event_handlers/__init__.py

@@ -1,12 +1,30 @@
-from .clean_when_dataset_deleted import handle
+from .clean_when_dataset_deleted import handle as handle_clean_when_dataset_deleted
-from .clean_when_document_deleted import handle
+from .clean_when_document_deleted import handle as handle_clean_when_document_deleted
-from .create_document_index import handle
+from .create_document_index import handle as handle_create_document_index
-from .create_installed_app_when_app_created import handle
+from .create_installed_app_when_app_created import handle as handle_create_installed_app_when_app_created
-from .create_site_record_when_app_created import handle
+from .create_site_record_when_app_created import handle as handle_create_site_record_when_app_created
-from .delete_tool_parameters_cache_when_sync_draft_workflow import handle
+from .delete_tool_parameters_cache_when_sync_draft_workflow import (
-from .update_app_dataset_join_when_app_model_config_updated import handle
+    handle as handle_delete_tool_parameters_cache_when_sync_draft_workflow,
-from .update_app_dataset_join_when_app_published_workflow_updated import handle
+)
+from .update_app_dataset_join_when_app_model_config_updated import (
+    handle as handle_update_app_dataset_join_when_app_model_config_updated,
+)
+from .update_app_dataset_join_when_app_published_workflow_updated import (
+    handle as handle_update_app_dataset_join_when_app_published_workflow_updated,
+)
 
 # Consolidated handler replaces both deduct_quota_when_message_created and
 # update_provider_last_used_at_when_message_created
-from .update_provider_when_message_created import handle
+from .update_provider_when_message_created import handle as handle_update_provider_when_message_created
+
+__all__ = [
+    "handle_clean_when_dataset_deleted",
+    "handle_clean_when_document_deleted",
+    "handle_create_document_index",
+    "handle_create_installed_app_when_app_created",
+    "handle_create_site_record_when_app_created",
+    "handle_delete_tool_parameters_cache_when_sync_draft_workflow",
+    "handle_update_app_dataset_join_when_app_model_config_updated",
+    "handle_update_app_dataset_join_when_app_published_workflow_updated",
+    "handle_update_provider_when_message_created",
+]

api/events/event_handlers/update_app_dataset_join_when_app_published_workflow_updated.py

@@ -61,7 +61,7 @@ def get_dataset_ids_from_workflow(published_workflow: Workflow) -> set[str]:
         try:
             node_data = KnowledgeRetrievalNodeData(**node.get("data", {}))
             dataset_ids.update(dataset_id for dataset_id in node_data.dataset_ids)
-        except Exception as e:
+        except Exception:
             continue
 
     return dataset_ids

api/events/event_handlers/update_provider_when_message_created.py

@@ -204,7 +204,7 @@ def _calculate_quota_usage(
         elif quota_unit == QuotaUnit.TIMES:
             return 1
         return None
-    except Exception as e:
+    except Exception:
         logger.exception("Failed to calculate quota usage")
         return None
 

api/extensions/ext_sentry.py

@@ -15,7 +15,7 @@ def init_app(app: DifyApp):
 
         def before_send(event, hint):
             if "exc_info" in hint:
-                exc_type, exc_value, tb = hint["exc_info"]
+                _, exc_value, _ = hint["exc_info"]
                 if parse_error.defaultErrorResponse in str(exc_value):
                     return None
 

api/extensions/storage/clickzetta_volume/clickzetta_volume_storage.py

@@ -139,7 +139,7 @@ class ClickZettaVolumeStorage(BaseStorage):
                 schema=self._config.schema_name,
             )
             logger.debug("ClickZetta connection established")
-        except Exception as e:
+        except Exception:
             logger.exception("Failed to connect to ClickZetta")
             raise
 
@@ -150,7 +150,7 @@ class ClickZettaVolumeStorage(BaseStorage):
                 self._connection, self._config.volume_type, self._config.volume_name
             )
             logger.debug("Permission manager initialized")
-        except Exception as e:
+        except Exception:
             logger.exception("Failed to initialize permission manager")
             raise
 
@@ -213,7 +213,7 @@ class ClickZettaVolumeStorage(BaseStorage):
                 if fetch:
                     return cursor.fetchall()
                 return None
-        except Exception as e:
+        except Exception:
             logger.exception("SQL execution failed: %s", sql)
             raise
 
@@ -349,7 +349,7 @@ class ClickZettaVolumeStorage(BaseStorage):
 
             # Find the downloaded file (may be in subdirectories)
             downloaded_file = None
-            for root, dirs, files in os.walk(temp_dir):
+            for root, _, files in os.walk(temp_dir):
                 for file in files:
                     if file == filename or file == os.path.basename(filename):
                         downloaded_file = Path(root) / file
@@ -524,6 +524,6 @@ class ClickZettaVolumeStorage(BaseStorage):
             logger.debug("Scanned %d items in path %s", len(result), path)
             return result
 
-        except Exception as e:
+        except Exception:
             logger.exception("Error scanning path %s", path)
             return []

api/extensions/storage/clickzetta_volume/file_lifecycle.py

@@ -145,7 +145,7 @@ class FileLifecycleManager:
             logger.info("File %s saved with lifecycle management, version %s", filename, new_version)
             return file_metadata
 
-        except Exception as e:
+        except Exception:
             logger.exception("Failed to save file with lifecycle")
             raise
 
@@ -163,7 +163,7 @@ class FileLifecycleManager:
             if filename in metadata_dict:
                 return FileMetadata.from_dict(metadata_dict[filename])
             return None
-        except Exception as e:
+        except Exception:
             logger.exception("Failed to get file metadata for %s", filename)
             return None
 
@@ -192,7 +192,7 @@ class FileLifecycleManager:
                         # Parse version number
                         version_str = file_path.split(".v")[-1].split(".")[0]
                         try:
-                            version_num = int(version_str)
+                            _ = int(version_str)
                             # Simplified processing here, should actually read metadata from version file
                             # Temporarily create basic metadata information
                         except ValueError:
@@ -203,7 +203,7 @@ class FileLifecycleManager:
 
             return sorted(versions, key=lambda x: x.version or 0, reverse=True)
 
-        except Exception as e:
+        except Exception:
             logger.exception("Failed to list file versions for %s", filename)
             return []
 
@@ -237,7 +237,7 @@ class FileLifecycleManager:
             self.save_with_lifecycle(filename, version_data, {"restored_from": str(version)})
             return True
 
-        except Exception as e:
+        except Exception:
             logger.exception("Failed to restore %s to version %s", filename, version)
             return False
 
@@ -270,7 +270,7 @@ class FileLifecycleManager:
             logger.info("File %s archived successfully", filename)
             return True
 
-        except Exception as e:
+        except Exception:
             logger.exception("Failed to archive file %s", filename)
             return False
 
@@ -314,7 +314,7 @@ class FileLifecycleManager:
             logger.info("File %s soft deleted successfully", filename)
             return True
 
-        except Exception as e:
+        except Exception:
             logger.exception("Failed to soft delete file %s", filename)
             return False
 
@@ -372,7 +372,7 @@ class FileLifecycleManager:
 
             return cleaned_count
 
-        except Exception as e:
+        except Exception:
             logger.exception("Failed to cleanup old versions")
             return 0
 
@@ -427,7 +427,7 @@ class FileLifecycleManager:
 
             return stats
 
-        except Exception as e:
+        except Exception:
             logger.exception("Failed to get storage statistics")
             return {}
 
@@ -465,7 +465,7 @@ class FileLifecycleManager:
             metadata_content = json.dumps(metadata_dict, indent=2, ensure_ascii=False)
             self._storage.save(self._metadata_file, metadata_content.encode("utf-8"))
             logger.debug("Metadata saved successfully")
-        except Exception as e:
+        except Exception:
             logger.exception("Failed to save metadata")
             raise
 
@@ -508,7 +508,7 @@ class FileLifecycleManager:
             result = self._permission_manager.validate_operation(mapped_operation, self._dataset_id)
             return bool(result)
 
-        except Exception as e:
+        except Exception:
             logger.exception("Permission check failed for %s operation %s", filename, operation)
             # Safe default: deny access when permission check fails
             return False

api/extensions/storage/clickzetta_volume/volume_permissions.py

@@ -84,7 +84,7 @@ class VolumePermissionManager:
                 logger.warning("Unknown volume type: %s", self._volume_type)
                 return False
 
-        except Exception as e:
+        except Exception:
             logger.exception("Permission check failed")
             return False
 
@@ -119,7 +119,7 @@ class VolumePermissionManager:
                     )
                     return False
 
-        except Exception as e:
+        except Exception:
             logger.exception("User Volume permission check failed")
             # For User Volume, if permission check fails, it might be a configuration issue, provide friendlier error message
             logger.info("User Volume permission check failed, but permission checking is disabled in this version")
@@ -158,7 +158,7 @@ class VolumePermissionManager:
 
             return has_permission
 
-        except Exception as e:
+        except Exception:
             logger.exception("Table volume permission check failed for %s", table_name)
             return False
 
@@ -216,7 +216,7 @@ class VolumePermissionManager:
 
             return has_permission
 
-        except Exception as e:
+        except Exception:
             logger.exception("External volume permission check failed for %s", self._volume_name)
             logger.info("External Volume permission check failed, but permission checking is disabled in this version")
             return False
@@ -292,7 +292,7 @@ class VolumePermissionManager:
                 if result:
                     self._current_username = result[0]
                     return str(self._current_username)
-        except Exception as e:
+        except Exception:
             logger.exception("Failed to get current username")
 
         return "unknown"
@@ -316,7 +316,7 @@ class VolumePermissionManager:
                 for grant in grants:
                     if len(grant) >= 3:  # Typical format: (privilege, object_type, object_name, ...)
                         privilege = grant[0].upper()
-                        object_type = grant[1].upper() if len(grant) > 1 else ""
+                        _ = grant[1].upper() if len(grant) > 1 else ""
 
                         # Collect all relevant permissions
                         if privilege in ["SELECT", "INSERT", "UPDATE", "DELETE", "ALL"]:
@@ -521,7 +521,7 @@ class VolumePermissionManager:
                 logger.warning("Unknown volume type for permission inheritance: %s", self._volume_type)
                 return False
 
-        except Exception as e:
+        except Exception:
             logger.exception("Permission inheritance check failed")
             return False
 

api/libs/helper.py

@@ -185,7 +185,7 @@ def timezone(timezone_string):
 def generate_string(n):
     letters_digits = string.ascii_letters + string.digits
     result = ""
-    for i in range(n):
+    for _ in range(n):
         result += secrets.choice(letters_digits)
 
     return result

api/libs/sendgrid.py

@@ -33,15 +33,15 @@ class SendGridClient:
             logger.debug(response.body)
             logger.debug(response.headers)
 
-        except TimeoutError as e:
+        except TimeoutError:
             logger.exception("SendGridClient Timeout occurred while sending email")
             raise
-        except (UnauthorizedError, ForbiddenError) as e:
+        except (UnauthorizedError, ForbiddenError):
             logger.exception(
                 "SendGridClient Authentication failed. "
                 "Verify that your credentials and the 'from' email address are correct"
             )
             raise
-        except Exception as e:
+        except Exception:
             logger.exception("SendGridClient Unexpected error occurred while sending email to %s", _to)
             raise

api/libs/smtp.py

@@ -45,13 +45,13 @@ class SMTPClient:
             msg.attach(MIMEText(mail["html"], "html"))
 
             smtp.sendmail(self._from, mail["to"], msg.as_string())
-        except smtplib.SMTPException as e:
+        except smtplib.SMTPException:
             logger.exception("SMTP error occurred")
             raise
-        except TimeoutError as e:
+        except TimeoutError:
             logger.exception("Timeout occurred while sending email")
             raise
-        except Exception as e:
+        except Exception:
             logger.exception("Unexpected error occurred while sending email to %s", mail["to"])
             raise
         finally:

api/models/dataset.py

@@ -915,7 +915,7 @@ class DatasetKeywordTable(Base):
                 if keyword_table_text:
                     return json.loads(keyword_table_text.decode("utf-8"), cls=SetDecoder)
                 return None
-            except Exception as e:
+            except Exception:
                 logger.exception("Failed to load keyword table from file: %s", file_key)
                 return None
 

api/pyproject.toml

@@ -111,7 +111,7 @@ dev = [
     "faker~=32.1.0",
     "lxml-stubs~=0.5.1",
     "ty~=0.0.1a19",
-    "mypy~=1.17.1",
+    "basedpyright~=1.31.0",
     "ruff~=0.12.3",
     "pytest~=8.3.2",
     "pytest-benchmark~=4.0.0",
@@ -218,4 +218,3 @@ vdb = [
     "xinference-client~=1.2.2",
     "mo-vector~=0.1.13",
 ]
-

api/pyrightconfig.json

@@ -0,0 +1,48 @@
+{
+  "include": ["."],
+  "exclude": ["tests/", "migrations/", ".venv/"],
+  "typeCheckingMode": "strict",
+  "pythonVersion": "3.11",
+  "pythonPlatform": "All",
+  "reportMissingTypeStubs": false,
+  "reportGeneralTypeIssues": "none",
+  "reportOptionalMemberAccess": "none",
+  "reportOptionalIterable": "none",
+  "reportOptionalOperand": "none",
+  "reportOptionalSubscript": "none",
+  "reportTypedDictNotRequiredAccess": "none",
+  "reportPrivateImportUsage": "none",
+  "reportUnsupportedDunderAll": "none",
+  "reportUnnecessaryTypeIgnoreComment": "none",
+  "reportMatchNotExhaustive": "none",
+  "reportImplicitOverride": "none",
+  "reportCallInDefaultInitializer": "none",
+  "reportUnnecessaryIsInstance": "none",
+  "reportUnnecessaryComparison": "none",
+  "reportUnknownParameterType": "none",
+  "reportMissingParameterType": "none",
+  "reportUnknownArgumentType": "none",
+  "reportUnknownVariableType": "none",
+  "reportUnknownMemberType": "none",
+  "reportMissingTypeArgument": "none",
+  "reportUntypedFunctionDecorator": "none",
+  "reportUnknownLambdaType": "none",
+  "reportPrivateUsage": "none",
+  "reportConstantRedefinition": "none",
+  "reportIncompatibleMethodOverride": "none",
+  "reportIncompatibleVariableOverride": "none",
+  "reportOverlappingOverload": "none",
+  "reportPossiblyUnboundVariable": "none",
+  "reportUnusedImport": "none",
+  "reportUnusedFunction": "none",
+  "reportArgumentType": "none",
+  "reportAssignmentType": "none",
+  "reportAttributeAccessIssue": "none",
+  "reportCallIssue": "none",
+  "reportIndexIssue": "none",
+  "reportRedeclaration": "none",
+  "reportReturnType": "none",
+  "reportOperatorIssue": "none",
+  "reportTypeCommentUsage": "none",
+  "reportDeprecated": "none"
+}

api/repositories/sqlalchemy_api_workflow_run_repository.py

@@ -22,7 +22,7 @@ Implementation Notes:
 import logging
 from collections.abc import Sequence
 from datetime import datetime
-from typing import Optional, cast
+from typing import Optional
 
 from sqlalchemy import delete, select
 from sqlalchemy.orm import Session, sessionmaker
@@ -117,7 +117,7 @@ class DifyAPISQLAlchemyWorkflowRunRepository(APIWorkflowRunRepository):
                 WorkflowRun.app_id == app_id,
                 WorkflowRun.id == run_id,
             )
-            return cast(Optional[WorkflowRun], session.scalar(stmt))
+            return session.scalar(stmt)
 
     def get_expired_runs_batch(
         self,
@@ -137,7 +137,7 @@ class DifyAPISQLAlchemyWorkflowRunRepository(APIWorkflowRunRepository):
                 )
                 .limit(batch_size)
             )
-            return cast(Sequence[WorkflowRun], session.scalars(stmt).all())
+            return session.scalars(stmt).all()
 
     def delete_runs_by_ids(
         self,
@@ -154,7 +154,7 @@ class DifyAPISQLAlchemyWorkflowRunRepository(APIWorkflowRunRepository):
             result = session.execute(stmt)
             session.commit()
 
-            deleted_count = cast(int, result.rowcount)
+            deleted_count = result.rowcount
             logger.info("Deleted %s workflow runs by IDs", deleted_count)
             return deleted_count
 

api/schedule/clean_workflow_runlogs_precise.py

@@ -77,7 +77,7 @@ def clean_workflow_runlogs_precise():
 
         logger.info("Cleanup completed: %s expired workflow run logs deleted", total_deleted)
 
-    except Exception as e:
+    except Exception:
         db.session.rollback()
         logger.exception("Unexpected error in workflow log cleanup")
         raise
@@ -149,7 +149,7 @@ def _delete_batch_with_retry(workflow_run_ids: list[str], attempt_count: int) ->
         db.session.commit()
         return True
 
-    except Exception as e:
+    except Exception:
         db.session.rollback()
         logger.exception("Batch deletion failed (attempt %s)", attempt_count + 1)
         return False

api/schedule/queue_monitor_task.py

@@ -63,10 +63,10 @@ def queue_monitor_task():
                                 "alert_time": current_time,
                             },
                         )
-                    except Exception as e:
+                    except Exception:
                         logger.exception(click.style("Exception occurred during sending email", fg="red"))
 
-    except Exception as e:
+    except Exception:
         logger.exception(click.style("Exception occurred during queue monitoring", fg="red"))
     finally:
         if db.session.is_active:

api/services/annotation_service.py

@@ -330,7 +330,7 @@ class AppAnnotationService:
             # Skip the first row
             df = pd.read_csv(file, dtype=str)
             result = []
-            for index, row in df.iterrows():
+            for _, row in df.iterrows():
                 content = {"question": row.iloc[0], "answer": row.iloc[1]}
                 result.append(content)
             if len(result) == 0:

api/services/app_generate_service.py

@@ -227,7 +227,7 @@ class AppGenerateService:
         # If workflow_id is specified, get the specific workflow version
         if workflow_id:
             try:
-                workflow_uuid = uuid.UUID(workflow_id)
+                _ = uuid.UUID(workflow_id)
             except ValueError:
                 raise WorkflowIdFormatError(f"Invalid workflow_id format: '{workflow_id}'. ")
             workflow = workflow_service.get_published_workflow_by_id(app_model=app_model, workflow_id=workflow_id)

api/services/app_service.py

@@ -96,7 +96,7 @@ class AppService:
                 )
             except (ProviderTokenNotInitError, LLMBadRequestError):
                 model_instance = None
-            except Exception as e:
+            except Exception:
                 logger.exception("Get default model instance failed, tenant_id: %s", tenant_id)
                 model_instance = None
 
@@ -201,7 +201,7 @@ class AppService:
 
                     # override tool parameters
                     tool["tool_parameters"] = masked_parameter
-                except Exception as e:
+                except Exception:
                     pass
 
             # override agent mode

api/services/external_knowledge_service.py

@@ -89,7 +89,7 @@ class ExternalDatasetService:
                 raise ValueError(f"invalid endpoint: {endpoint}")
         try:
             response = httpx.post(endpoint, headers={"Authorization": f"Bearer {api_key}"})
-        except Exception as e:
+        except Exception:
             raise ValueError(f"failed to connect to the endpoint: {endpoint}")
         if response.status_code == 502:
             raise ValueError(f"Bad Gateway: failed to connect to the endpoint: {endpoint}")

api/services/plugin/data_migration.py

@@ -175,7 +175,7 @@ limit 1000"""
                         # update jina to langgenius/jina_tool/jina etc.
                         updated_value = provider_cls(provider_name).to_string()
                         batch_updates.append((updated_value, record_id))
-                    except Exception as e:
+                    except Exception:
                         failed_ids.append(record_id)
                         click.echo(
                             click.style(

api/services/tools/tools_transform_service.py

@@ -128,7 +128,7 @@ class ToolTransformService:
             )
         }
 
-        for name, value in schema.items():
+        for name in schema:
             if result.masked_credentials:
                 result.masked_credentials[name] = ""
 

api/tasks/annotation/delete_annotation_index_task.py

@@ -38,7 +38,7 @@ def delete_annotation_index_task(annotation_id: str, app_id: str, tenant_id: str
             logger.exception("Delete annotation index failed when annotation deleted.")
         end_at = time.perf_counter()
         logger.info(click.style(f"App annotations index deleted : {app_id} latency: {end_at - start_at}", fg="green"))
-    except Exception as e:
+    except Exception:
         logger.exception("Annotation deleted index failed")
     finally:
         db.session.close()

api/tasks/batch_create_segment_to_index_task.py

@@ -79,7 +79,7 @@ def batch_create_segment_to_index_task(
                 # Skip the first row
                 df = pd.read_csv(file_path)
                 content = []
-                for index, row in df.iterrows():
+                for _, row in df.iterrows():
                     if dataset_document.doc_form == "qa_model":
                         data = {"content": row.iloc[0], "answer": row.iloc[1]}
                     else:

api/tasks/clean_dataset_task.py

@@ -75,7 +75,7 @@ def clean_dataset_task(
             index_processor = IndexProcessorFactory(doc_form).init_index_processor()
             index_processor.clean(dataset, None, with_keywords=True, delete_child_chunks=True)
             logger.info(click.style(f"Successfully cleaned vector database for dataset: {dataset_id}", fg="green"))
-        except Exception as index_cleanup_error:
+        except Exception:
             logger.exception(click.style(f"Failed to clean vector database for dataset {dataset_id}", fg="red"))
             # Continue with document and segment deletion even if vector cleanup fails
             logger.info(
@@ -145,7 +145,7 @@ def clean_dataset_task(
         try:
             db.session.rollback()
             logger.info(click.style(f"Rolled back database session for dataset: {dataset_id}", fg="yellow"))
-        except Exception as rollback_error:
+        except Exception:
             logger.exception("Failed to rollback database session")
 
         logger.exception("Cleaned dataset when dataset deleted failed")

api/tasks/delete_account_task.py

@@ -15,7 +15,7 @@ def delete_account_task(account_id):
     account = db.session.query(Account).where(Account.id == account_id).first()
     try:
         BillingService.delete_account(account_id)
-    except Exception as e:
+    except Exception:
         logger.exception("Failed to delete account %s from billing service.", account_id)
         raise
 

api/tasks/process_tenant_plugin_autoupgrade_check_task.py

@@ -146,7 +146,7 @@ def process_tenant_plugin_autoupgrade_check_task(
                                 fg="green",
                             )
                         )
-                        task_start_resp = manager.upgrade_plugin(
+                        _ = manager.upgrade_plugin(
                             tenant_id,
                             original_unique_identifier,
                             new_unique_identifier,

dev/basedpyright-check

@@ -0,0 +1,9 @@
+#!/bin/bash
+
+set -x
+
+SCRIPT_DIR="$(dirname "$(realpath "$0")")"
+cd "$SCRIPT_DIR/.."
+
+# run basedpyright checks
+uv --directory api run basedpyright

dev/reformat

@@ -14,5 +14,5 @@ uv run --directory api --dev ruff format ./
 # run dotenv-linter linter
 uv run --project api --dev dotenv-linter ./api/.env.example ./web/.env.example
 
-# run mypy check
+# run basedpyright check
-dev/mypy-check
+dev/basedpyright-check

web/.husky/pre-commit

@@ -35,7 +35,6 @@ if $api_modified; then
 
     status=${status:-0}
 
-
     if [ $status -ne 0 ]; then
       echo "Ruff linter on api module error, exit code: $status"
       echo "Please run 'dev/reformat' to fix the fixable linting errors."