feat(deepdata): 引入修改密码、文件预览组件与清洗算子增强，deepflow 改名为 deep-flow

本次同步 09-12 至 09-28 的代码变更，主要内容：新增功能 - 修改密码：后端新增 ChangePasswordRequest DTO 与UserController/UserService 对应接口，前端新增 ChangePasswordDialog 并在 Header 接入入口 - 文件预览组件重构：file-preview 目录拆分出 VideoPreview（支持 blobUrl 直传）、 ImagePreview、AudioPreview，index.tsx 统一调度各类型预览器 - 新增 my_ops 算子模块：markitdown_parser、mineru_pdf_parser、text_quality_evaluator - 新增 tools/minio-file-server MinIO 文件服务功能增强 - 数据清洗：cleaning_task_service/scheduler/routes 重构， data_juicer_executor 与 wrapper 增强，OperatorTable/LogsTable/TaskDetail 同步调整 - 数据标注：annotation sync.py、project.py 接口与schema 更新 - 数据采集、算子市场、首页与菜单路由相关页面调整 - DataJuicer 算子接入（useOperatorOperations、dj_ops_schema）结构调整 - deepflow/ 更名为 deep-flow/（419 个文件重命名） - 新增 helm 部署编排、GitHub Actions 之外的自建镜像构建脚本未纳入本次提交 - scripts-backup/、runtime/python-executor-backup/、components_backup/（备份目录） - *.backup*、__pycache__ 产物 - zh_core_web_sm-3.8.0-py3-none-any.whl（46MB 构建产物） - DataX/（内嵌独立仓库，远程亦未收录其源码）
2026-10-03 22:44:56 +08:00
parent cbb1048e18
commit ff22ed3a8b
1156 changed files with 129912 additions and 21716 deletions
@@ -0,0 +1,168 @@
+# Copyright (c) 2025 Bytedance Ltd. and/or its affiliates
+# SPDX-License-Identifier: MIT
+
+from unittest.mock import AsyncMock, MagicMock, patch
+
+import pytest
+from fastapi import HTTPException
+from pydantic import ValidationError
+
+import src.server.mcp_utils as mcp_utils  # Assuming mcp_utils is the module to test
+from src.config.report_style import ReportStyle
+from src.rag.retriever import Resource
+from src.server.chat_request import (
+    ChatMessage,
+    ChatRequest,
+    ContentItem,
+    EnhancePromptRequest,
+    GeneratePodcastRequest,
+    GeneratePPTRequest,
+    GenerateProseRequest,
+    TTSRequest,
+)
+
+
+def test_content_item_text_and_image():
+    item_text = ContentItem(type="text", text="hello")
+    assert item_text.type == "text"
+    assert item_text.text == "hello"
+    assert item_text.image_url is None
+
+    item_image = ContentItem(type="image", image_url="http://img.com/1.png")
+    assert item_image.type == "image"
+    assert item_image.text is None
+    assert item_image.image_url == "http://img.com/1.png"
+
+
+def test_chat_message_with_string_content():
+    msg = ChatMessage(role="user", content="Hello!")
+    assert msg.role == "user"
+    assert msg.content == "Hello!"
+
+
+def test_chat_message_with_content_items():
+    items = [ContentItem(type="text", text="hi")]
+    msg = ChatMessage(role="assistant", content=items)
+    assert msg.role == "assistant"
+    assert isinstance(msg.content, list)
+    assert msg.content[0].type == "text"
+
+
+def test_chat_request_defaults():
+    req = ChatRequest()
+    assert req.messages == []
+    assert req.resources == []
+    assert req.debug is False
+    assert req.thread_id == "__default__"
+    assert req.max_plan_iterations == 1
+    assert req.max_step_num == 3
+    assert req.max_search_results == 3
+    assert req.auto_accepted_plan is False
+    assert req.interrupt_feedback is None
+    assert req.mcp_settings is None
+    assert req.enable_background_investigation is True
+    assert req.report_style == ReportStyle.ACADEMIC
+
+
+def test_chat_request_with_values():
+    resource = Resource(
+        name="test", type="doc", uri="some-uri-value", title="some-title-value"
+    )
+    msg = ChatMessage(role="user", content="hi")
+    req = ChatRequest(
+        messages=[msg],
+        resources=[resource],
+        debug=True,
+        thread_id="tid",
+        max_plan_iterations=2,
+        max_step_num=5,
+        max_search_results=10,
+        auto_accepted_plan=True,
+        interrupt_feedback="stop",
+        mcp_settings={"foo": "bar"},
+        enable_background_investigation=False,
+        report_style="academic",
+    )
+    assert req.messages[0].role == "user"
+    assert req.debug is True
+    assert req.thread_id == "tid"
+    assert req.max_plan_iterations == 2
+    assert req.max_step_num == 5
+    assert req.max_search_results == 10
+    assert req.auto_accepted_plan is True
+    assert req.interrupt_feedback == "stop"
+    assert req.mcp_settings == {"foo": "bar"}
+    assert req.enable_background_investigation is False
+    assert req.report_style == ReportStyle.ACADEMIC
+
+
+def test_tts_request_defaults():
+    req = TTSRequest(text="hello")
+    assert req.text == "hello"
+    assert req.voice_type == "BV700_V2_streaming"
+    assert req.encoding == "mp3"
+    assert req.speed_ratio == 1.0
+    assert req.volume_ratio == 1.0
+    assert req.pitch_ratio == 1.0
+    assert req.text_type == "plain"
+    assert req.with_frontend == 1
+    assert req.frontend_type == "unitTson"
+
+
+def test_generate_podcast_request():
+    req = GeneratePodcastRequest(content="Podcast content")
+    assert req.content == "Podcast content"
+
+
+def test_generate_ppt_request():
+    req = GeneratePPTRequest(content="PPT content")
+    assert req.content == "PPT content"
+
+
+def test_generate_prose_request():
+    req = GenerateProseRequest(prompt="Write a poem", option="poet", command="rhyme")
+    assert req.prompt == "Write a poem"
+    assert req.option == "poet"
+    assert req.command == "rhyme"
+
+    req2 = GenerateProseRequest(prompt="Write", option="short")
+    assert req2.command == ""
+
+
+def test_enhance_prompt_request_defaults():
+    req = EnhancePromptRequest(prompt="Improve this")
+    assert req.prompt == "Improve this"
+    assert req.context == ""
+    assert req.report_style == "academic"
+
+
+def test_content_item_validation_error():
+    with pytest.raises(ValidationError):
+        ContentItem()  # missing required 'type'
+
+
+def test_chat_message_validation_error():
+    with pytest.raises(ValidationError):
+        ChatMessage(role="user")  # missing content
+
+
+def test_tts_request_validation_error():
+    with pytest.raises(ValidationError):
+        TTSRequest()  # missing required 'text'
+
+
+@pytest.mark.asyncio
+@patch("src.server.mcp_utils._get_tools_from_client_session", new_callable=AsyncMock)
+@patch("src.server.mcp_utils.StdioServerParameters")
+@patch("src.server.mcp_utils.stdio_client")
+async def test_load_mcp_tools_exception_handling(
+    mock_stdio_client, mock_StdioServerParameters, mock_get_tools
+):  # Changed to async def
+    mock_get_tools.side_effect = Exception("unexpected error")
+    mock_StdioServerParameters.return_value = MagicMock()
+    mock_stdio_client.return_value = MagicMock()
+
+    with pytest.raises(HTTPException) as exc:
+        await mcp_utils.load_mcp_tools(server_type="stdio", command="foo")  # Use await
+    assert exc.value.status_code == 500
+    assert "unexpected error" in exc.value.detail