kexsh/dify
1
0
Fork 0
Code Issues Pull Requests Actions 1 Packages Projects Releases Wiki Activity

ruff check preview (#25653)

Browse Source 
Co-authored-by: autofix-ci[bot] <114827586+autofix-ci[bot]@users.noreply.github.com>
This commit is contained in:
Asuka Minato
2025-09-16 13:58:12 +09:00
committed by GitHub
parent a0c7713494
commit bdd85b36a4
42 changed files with 224 additions and 342 deletions
Download Patch File Download Diff File Expand all files Collapse all files

3
api/.ruff.toml
View File

@@ -5,7 +5,7 @@ line-length = 120
quote-style = "double"
[lint]
preview = false
preview = true
select = [
"B", # flake8-bugbear rules
"C4", # flake8-comprehensions
@@ -65,6 +65,7 @@ ignore = [
"B006", # mutable-argument-default
"B007", # unused-loop-control-variable
"B026", # star-arg-unpacking-after-keyword-arg
"B901", # allow return in yield
"B903", # class-as-data-structure
"B904", # raise-without-from-inside-except
"B905", # zip-without-explicit-strict

5
api/commands.py
View File

@@ -1,6 +1,7 @@
import base64
import json
import logging
import operator
import secrets
from typing import Any
@@ -953,7 +954,7 @@ def clear_orphaned_file_records(force: bool):
click.echo(click.style("- Deleting orphaned message_files records", fg="white"))
query = "DELETE FROM message_files WHERE id IN :ids"
with db.engine.begin() as conn:
conn.execute(sa.text(query), {"ids": tuple([record["id"] for record in orphaned_message_files])})
conn.execute(sa.text(query), {"ids": tuple(record["id"] for record in orphaned_message_files)})
click.echo(
click.style(f"Removed {len(orphaned_message_files)} orphaned message_files records.", fg="green")
)
@@ -1307,7 +1308,7 @@ def cleanup_orphaned_draft_variables(
if dry_run:
logger.info("DRY RUN: Would delete the following:")
for app_id, count in sorted(stats["orphaned_by_app"].items(), key=lambda x: x[1], reverse=True)[
for app_id, count in sorted(stats["orphaned_by_app"].items(), key=operator.itemgetter(1), reverse=True)[
:10
]: # Show top 10
logger.info(" App %s: %s variables", app_id, count)

4
api/core/ops/aliyun_trace/aliyun_trace.py
View File

@@ -355,8 +355,8 @@ class AliyunDataTrace(BaseTraceInstance):
GEN_AI_FRAMEWORK: "dify",
TOOL_NAME: node_execution.title,
TOOL_DESCRIPTION: json.dumps(tool_des, ensure_ascii=False),
TOOL_PARAMETERS: json.dumps(node_execution.inputs if node_execution.inputs else {}, ensure_ascii=False),
INPUT_VALUE: json.dumps(node_execution.inputs if node_execution.inputs else {}, ensure_ascii=False),
TOOL_PARAMETERS: json.dumps(node_execution.inputs or {}, ensure_ascii=False),
INPUT_VALUE: json.dumps(node_execution.inputs or {}, ensure_ascii=False),
OUTPUT_VALUE: json.dumps(node_execution.outputs, ensure_ascii=False),
},
status=self.get_workflow_node_status(node_execution),

8
api/core/ops/langfuse_trace/langfuse_trace.py
View File

@@ -144,13 +144,13 @@ class LangFuseDataTrace(BaseTraceInstance):
if node_type == NodeType.LLM:
inputs = node_execution.process_data.get("prompts", {}) if node_execution.process_data else {}
else:
inputs = node_execution.inputs if node_execution.inputs else {}
outputs = node_execution.outputs if node_execution.outputs else {}
inputs = node_execution.inputs or {}
outputs = node_execution.outputs or {}
created_at = node_execution.created_at or datetime.now()
elapsed_time = node_execution.elapsed_time
finished_at = created_at + timedelta(seconds=elapsed_time)
execution_metadata = node_execution.metadata if node_execution.metadata else {}
execution_metadata = node_execution.metadata or {}
metadata = {str(k): v for k, v in execution_metadata.items()}
metadata.update(
{
@@ -163,7 +163,7 @@ class LangFuseDataTrace(BaseTraceInstance):
"status": status,
}
)
process_data = node_execution.process_data if node_execution.process_data else {}
process_data = node_execution.process_data or {}
model_provider = process_data.get("model_provider", None)
model_name = process_data.get("model_name", None)
if model_provider is not None and model_name is not None:

8
api/core/ops/langsmith_trace/langsmith_trace.py
View File

@@ -167,13 +167,13 @@ class LangSmithDataTrace(BaseTraceInstance):
if node_type == NodeType.LLM:
inputs = node_execution.process_data.get("prompts", {}) if node_execution.process_data else {}
else:
inputs = node_execution.inputs if node_execution.inputs else {}
outputs = node_execution.outputs if node_execution.outputs else {}
inputs = node_execution.inputs or {}
outputs = node_execution.outputs or {}
created_at = node_execution.created_at or datetime.now()
elapsed_time = node_execution.elapsed_time
finished_at = created_at + timedelta(seconds=elapsed_time)
execution_metadata = node_execution.metadata if node_execution.metadata else {}
execution_metadata = node_execution.metadata or {}
node_total_tokens = execution_metadata.get(WorkflowNodeExecutionMetadataKey.TOTAL_TOKENS) or 0
metadata = {str(key): value for key, value in execution_metadata.items()}
metadata.update(
@@ -188,7 +188,7 @@ class LangSmithDataTrace(BaseTraceInstance):
}
)
process_data = node_execution.process_data if node_execution.process_data else {}
process_data = node_execution.process_data or {}
if process_data and process_data.get("model_mode") == "chat":
run_type = LangSmithRunType.llm

8
api/core/ops/opik_trace/opik_trace.py
View File

@@ -182,13 +182,13 @@ class OpikDataTrace(BaseTraceInstance):
if node_type == NodeType.LLM:
inputs = node_execution.process_data.get("prompts", {}) if node_execution.process_data else {}
else:
inputs = node_execution.inputs if node_execution.inputs else {}
outputs = node_execution.outputs if node_execution.outputs else {}
inputs = node_execution.inputs or {}
outputs = node_execution.outputs or {}
created_at = node_execution.created_at or datetime.now()
elapsed_time = node_execution.elapsed_time
finished_at = created_at + timedelta(seconds=elapsed_time)
execution_metadata = node_execution.metadata if node_execution.metadata else {}
execution_metadata = node_execution.metadata or {}
metadata = {str(k): v for k, v in execution_metadata.items()}
metadata.update(
{
@@ -202,7 +202,7 @@ class OpikDataTrace(BaseTraceInstance):
}
)
process_data = node_execution.process_data if node_execution.process_data else {}
process_data = node_execution.process_data or {}
provider = None
model = None

5
api/core/ops/ops_trace_manager.py
View File

@@ -1,3 +1,4 @@
import collections
import json
import logging
import os
@@ -40,7 +41,7 @@ from tasks.ops_trace_task import process_trace_tasks
logger = logging.getLogger(__name__)
class OpsTraceProviderConfigMap(dict[str, dict[str, Any]]):
class OpsTraceProviderConfigMap(collections.UserDict[str, dict[str, Any]]):
def __getitem__(self, provider: str) -> dict[str, Any]:
match provider:
case TracingProviderEnum.LANGFUSE:
@@ -121,7 +122,7 @@ class OpsTraceProviderConfigMap(dict[str, dict[str, Any]]):
raise KeyError(f"Unsupported tracing provider: {provider}")
provider_config_map: dict[str, dict[str, Any]] = OpsTraceProviderConfigMap()
provider_config_map = OpsTraceProviderConfigMap()
class OpsTraceManager:

8
api/core/ops/weave_trace/weave_trace.py
View File

@@ -169,13 +169,13 @@ class WeaveDataTrace(BaseTraceInstance):
if node_type == NodeType.LLM:
inputs = node_execution.process_data.get("prompts", {}) if node_execution.process_data else {}
else:
inputs = node_execution.inputs if node_execution.inputs else {}
outputs = node_execution.outputs if node_execution.outputs else {}
inputs = node_execution.inputs or {}
outputs = node_execution.outputs or {}
created_at = node_execution.created_at or datetime.now()
elapsed_time = node_execution.elapsed_time
finished_at = created_at + timedelta(seconds=elapsed_time)
execution_metadata = node_execution.metadata if node_execution.metadata else {}
execution_metadata = node_execution.metadata or {}
node_total_tokens = execution_metadata.get(WorkflowNodeExecutionMetadataKey.TOTAL_TOKENS) or 0
attributes = {str(k): v for k, v in execution_metadata.items()}
attributes.update(
@@ -190,7 +190,7 @@ class WeaveDataTrace(BaseTraceInstance):
}
)
process_data = node_execution.process_data if node_execution.process_data else {}
process_data = node_execution.process_data or {}
if process_data and process_data.get("model_mode") == "chat":
attributes.update(
{

2
api/core/rag/datasource/vdb/clickzetta/clickzetta_vector.py
View File

@@ -641,7 +641,7 @@ class ClickzettaVector(BaseVector):
for doc, embedding in zip(batch_docs, batch_embeddings):
# Optimized: minimal checks for common case, fallback for edge cases
metadata = doc.metadata if doc.metadata else {}
metadata = doc.metadata or {}
if not isinstance(metadata, dict):
metadata = {}

2
api/core/rag/datasource/vdb/matrixone/matrixone_vector.py
View File

@@ -103,7 +103,7 @@ class MatrixoneVector(BaseVector):
self.client = self._get_client(len(embeddings[0]), True)
assert self.client is not None
ids = []
for _, doc in enumerate(documents):
for doc in documents:
if doc.metadata is not None:
doc_id = doc.metadata.get("doc_id", str(uuid.uuid4()))
ids.append(doc_id)

2
api/core/rag/datasource/vdb/opensearch/opensearch_vector.py
View File

@@ -104,7 +104,7 @@ class OpenSearchVector(BaseVector):
},
}
# See https://github.com/langchain-ai/langchainjs/issues/4346#issuecomment-1935123377
if self._client_config.aws_service not in ["aoss"]:
if self._client_config.aws_service != "aoss":
action["_id"] = uuid4().hex
actions.append(action)

2
api/core/repositories/sqlalchemy_workflow_execution_repository.py
View File

@@ -159,7 +159,7 @@ class SQLAlchemyWorkflowExecutionRepository(WorkflowExecutionRepository):
else None
)
db_model.status = domain_model.status
db_model.error = domain_model.error_message if domain_model.error_message else None
db_model.error = domain_model.error_message or None
db_model.total_tokens = domain_model.total_tokens
db_model.total_steps = domain_model.total_steps
db_model.exceptions_count = domain_model.exceptions_count

2
api/core/workflow/nodes/agent/agent_node.py
View File

@@ -320,7 +320,7 @@ class AgentNode(BaseNode):
memory = self._fetch_memory(model_instance)
if memory:
prompt_messages = memory.get_history_prompt_messages(
message_limit=node_data.memory.window.size if node_data.memory.window.size else None
message_limit=node_data.memory.window.size or None
)
history_prompt_messages = [
prompt_message.model_dump(mode="json") for prompt_message in prompt_messages

4
api/extensions/ext_celery.py
View File

@@ -141,9 +141,7 @@ def init_app(app: DifyApp) -> Celery:
imports.append("schedule.queue_monitor_task")
beat_schedule["datasets-queue-monitor"] = {
"task": "schedule.queue_monitor_task.queue_monitor_task",
"schedule": timedelta(
minutes=dify_config.QUEUE_MONITOR_INTERVAL if dify_config.QUEUE_MONITOR_INTERVAL else 30
),
"schedule": timedelta(minutes=dify_config.QUEUE_MONITOR_INTERVAL or 30),
}
if dify_config.ENABLE_CHECK_UPGRADABLE_PLUGIN_TASK and dify_config.MARKETPLACE_ENABLED:
imports.append("schedule.check_upgradable_plugin_task")

3
api/extensions/storage/clickzetta_volume/file_lifecycle.py
View File

@@ -7,6 +7,7 @@ Supports complete lifecycle management for knowledge base files.
import json
import logging
import operator
from dataclasses import asdict, dataclass
from datetime import datetime
from enum import StrEnum, auto
@@ -356,7 +357,7 @@ class FileLifecycleManager:
# Cleanup old versions for each file
for base_filename, versions in file_versions.items():
# Sort by version number
versions.sort(key=lambda x: x[0], reverse=True)
versions.sort(key=operator.itemgetter(0), reverse=True)
# Keep the newest max_versions versions, delete the rest
if len(versions) > max_versions:

6
api/tasks/process_tenant_plugin_autoupgrade_check_task.py
View File

@@ -1,3 +1,4 @@
import operator
import traceback
import typing
@@ -118,7 +119,7 @@ def process_tenant_plugin_autoupgrade_check_task(
current_version = version
latest_version = manifest.latest_version
def fix_only_checker(latest_version, current_version):
def fix_only_checker(latest_version: str, current_version: str):
latest_version_tuple = tuple(int(val) for val in latest_version.split("."))
current_version_tuple = tuple(int(val) for val in current_version.split("."))
@@ -130,8 +131,7 @@ def process_tenant_plugin_autoupgrade_check_task(
return False
version_checker = {
TenantPluginAutoUpgradeStrategy.StrategySetting.LATEST: lambda latest_version,
current_version: latest_version != current_version,
TenantPluginAutoUpgradeStrategy.StrategySetting.LATEST: operator.ne,
TenantPluginAutoUpgradeStrategy.StrategySetting.FIX_ONLY: fix_only_checker,
}

4
api/tests/integration_tests/storage/test_clickzetta_volume.py
View File

@@ -3,6 +3,7 @@
import os
import tempfile
import unittest
from pathlib import Path
import pytest
@@ -60,8 +61,7 @@ class TestClickZettaVolumeStorage(unittest.TestCase):
# Test download
with tempfile.NamedTemporaryFile() as temp_file:
storage.download(test_filename, temp_file.name)
with open(temp_file.name, "rb") as f:
downloaded_content = f.read()
downloaded_content = Path(temp_file.name).read_bytes()
assert downloaded_content == test_content
# Test scan

12
api/tests/test_containers_integration_tests/tasks/test_batch_create_segment_to_index_task.py
View File

@@ -12,6 +12,7 @@ and realistic testing scenarios with actual PostgreSQL and Redis instances.
import uuid
from datetime import datetime
from pathlib import Path
from unittest.mock import MagicMock, patch
import pytest
@@ -276,8 +277,7 @@ class TestBatchCreateSegmentToIndexTask:
mock_storage = mock_external_service_dependencies["storage"]
def mock_download(key, file_path):
with open(file_path, "w", encoding="utf-8") as f:
f.write(csv_content)
Path(file_path).write_text(csv_content, encoding="utf-8")
mock_storage.download.side_effect = mock_download
@@ -505,7 +505,7 @@ class TestBatchCreateSegmentToIndexTask:
db.session.commit()
# Test each unavailable document
for i, document in enumerate(test_cases):
for document in test_cases:
job_id = str(uuid.uuid4())
batch_create_segment_to_index_task(
job_id=job_id,
@@ -601,8 +601,7 @@ class TestBatchCreateSegmentToIndexTask:
mock_storage = mock_external_service_dependencies["storage"]
def mock_download(key, file_path):
with open(file_path, "w", encoding="utf-8") as f:
f.write(empty_csv_content)
Path(file_path).write_text(empty_csv_content, encoding="utf-8")
mock_storage.download.side_effect = mock_download
@@ -684,8 +683,7 @@ class TestBatchCreateSegmentToIndexTask:
mock_storage = mock_external_service_dependencies["storage"]
def mock_download(key, file_path):
with open(file_path, "w", encoding="utf-8") as f:
f.write(csv_content)
Path(file_path).write_text(csv_content, encoding="utf-8")
mock_storage.download.side_effect = mock_download

2
api/tests/test_containers_integration_tests/tasks/test_clean_dataset_task.py
View File

@@ -362,7 +362,7 @@ class TestCleanDatasetTask:
# Create segments for each document
segments = []
for i, document in enumerate(documents):
for document in documents:
segment = self._create_test_segment(db_session_with_containers, account, tenant, dataset, document)
segments.append(segment)

2
api/tests/unit_tests/core/tools/utils/test_web_reader_tool.py
View File

@@ -15,7 +15,7 @@ class FakeResponse:
self.status_code = status_code
self.headers = headers or {}
self.content = content
self.text = text if text else content.decode("utf-8", errors="ignore")
self.text = text or content.decode("utf-8", errors="ignore")
# ---------------------------

17
api/tests/unit_tests/services/test_metadata_bug_complete.py
View File

@@ -1,3 +1,4 @@
from pathlib import Path
from unittest.mock import Mock, create_autospec, patch
import pytest
@@ -146,19 +147,17 @@ class TestMetadataBugCompleteValidation:
# Console API create
console_create_file = "api/controllers/console/datasets/metadata.py"
if os.path.exists(console_create_file):
with open(console_create_file) as f:
content = f.read()
# Should contain nullable=False, not nullable=True
assert "nullable=True" not in content.split("class DatasetMetadataCreateApi")[1].split("class")[0]
content = Path(console_create_file).read_text()
# Should contain nullable=False, not nullable=True
assert "nullable=True" not in content.split("class DatasetMetadataCreateApi")[1].split("class")[0]
# Service API create
service_create_file = "api/controllers/service_api/dataset/metadata.py"
if os.path.exists(service_create_file):
with open(service_create_file) as f:
content = f.read()
# Should contain nullable=False, not nullable=True
create_api_section = content.split("class DatasetMetadataCreateServiceApi")[1].split("class")[0]
assert "nullable=True" not in create_api_section
content = Path(service_create_file).read_text()
# Should contain nullable=False, not nullable=True
create_api_section = content.split("class DatasetMetadataCreateServiceApi")[1].split("class")[0]
assert "nullable=True" not in create_api_section
class TestMetadataValidationSummary: