v0.4.11

Release Notes - Version 0.4.11

This release supersedes v0.4.10. Please use v0.4.11 for all desktop downloads.

Desktop Release Packaging:

• Fixed the Windows desktop package startup failure caused by missing packaged runtime dependencies such as numpy.
• Fixed the workflow editor node palette in packaged desktop builds. The left sidebar now correctly shows the workflow nodes instead of displaying "No matching nodes found" / "没有匹配的节点".
• Added release build safeguards so GitHub Actions fails immediately if the packaged workflow editor bundle is missing node registrations.
• Added packaging checks for backend runtime dependencies, PyInstaller hidden imports, lockfile groups, and frontend workflow editor assets to reduce the chance of publishing unusable desktop packages.
• The Windows, macOS, and Linux desktop packages for this release were built and published by GitHub Actions.

Workflow Branching:

• The Conditional node supports ordered multi-branch matching, so a single node can route different inputs into different downstream paths.
• Only the matched branch continues execution. Unmatched branches and their downstream nodes are marked as skipped instead of continuing to run.
• Added backend branch resolution and regression tests to cover branch matching, skip propagation, and downstream execution control.

Run Status & Debugging:

• Fixed workflow use pages so outputs on skipped branches no longer remain stuck in loading state after the matched branch has already finished.
• Fixed workflow completion settlement after branch execution so the run button no longer stays in a running state when the workflow has already ended.
• Debug and run-record views now show skipped nodes as skipped instead of rendering a green success header and misleading execution time.
• Fixed fast branch-run status polling so check-status no longer gets stuck on stale 202 responses in this scenario.

Model Defaults:

• Updated the default MiniMax API base URL.

工作流分支:

• Conditional 条件判断节点现已支持按顺序匹配多个分支，一个节点即可根据不同输入分流到不同下游路径。
• 只有命中的分支会继续执行，未命中的分支及其下游节点现在会被明确标记为“已跳过”，不再继续运行。
• 补充了后端分支解析与回归测试，覆盖分支命中、跳过传播和下游执行控制等场景。

运行状态与调试:

• 修复工作流使用页中被跳过分支的输出节点仍然卡在 loading 的问题，命中分支完成后页面状态可以正常收口。
• 修复分支执行结束后运行按钮仍停留在“运行中”的问题，工作流完成状态现在可以正确结束。
• 调试视图和运行记录中的被跳过节点现在会显示为“已跳过”，不再错误显示绿色成功头和误导性的运行时间。
• 修复快速分支运行场景下 check-status 轮询可能卡在过期 202 响应的问题。

桌面端发布包:

• 修复 Windows 桌面发布包启动时报缺少 numpy 等运行时依赖的问题。
• 修复打包后的桌面端工作流编辑器左侧节点面板为空、显示“没有匹配的节点”的问题。
• 新增发布构建守卫：如果 GitHub Actions 构建出的工作流编辑器前端 bundle 缺少节点注册，会立即失败，不再发布坏包。
• 新增后端运行时依赖、PyInstaller hidden import、锁文件分组和前端节点注册等发布校验，降低发布不可用桌面包的风险。
• 本版本 Windows、macOS、Linux 桌面包均由 GitHub Actions 自动构建并发布。

模型默认配置:

• 更新 MiniMax 默认 API 地址。

Full Changelog: v0.4.6...v0.4.11

v0.4.10 (superseded - do not use)

⚠️ Superseded Release - Do Not Use

This release has been superseded by v0.4.11.

Known issue:

• The packaged desktop workflow editor can show an empty left node palette with "No matching nodes found" / "没有匹配的节点" because the production frontend bundle was missing workflow node registrations.

Please download v0.4.11 or newer instead:
https://github.com/AndersonBY/vector-vein/releases/tag/v0.4.11

Full Changelog: v0.4.9...v0.4.10

v0.4.6

Release Notes - Version 0.4.6

Workflow Branching:

• The Conditional node now supports ordered multi-branch matching, so a single node can route different inputs into different downstream paths.
• Only the matched branch continues execution. Unmatched branches and their downstream nodes are now marked as skipped instead of continuing to run.
• Added backend branch resolution and regression tests to cover branch matching, skip propagation, and downstream execution control.

Run Status & Debugging:

• Fixed workflow use pages so outputs on skipped branches no longer remain stuck in loading state after the matched branch has already finished.
• Fixed workflow completion settlement after branch execution so the run button no longer stays in a running state when the workflow has already ended.
• Debug and run-record views now show skipped nodes as skipped instead of rendering a green success header and misleading execution time.
• Fixed fast branch-run status polling so check-status no longer gets stuck on stale 202 responses in this scenario.

工作流分支:

• Conditional 条件判断节点现已支持按顺序匹配多个分支，一个节点即可根据不同输入分流到不同下游路径。
• 只有命中的分支会继续执行，未命中的分支及其下游节点现在会被明确标记为“已跳过”，不再继续运行。
• 补充了后端分支解析与回归测试，覆盖分支命中、跳过传播和下游执行控制等场景。

运行状态与调试:

• 修复工作流使用页中被跳过分支的输出节点仍然卡在 loading 的问题，命中分支完成后页面状态可以正常收口。
• 修复分支执行结束后运行按钮仍停留在“运行中”的问题，工作流完成状态现在可以正确结束。
• 调试视图和运行记录中的被跳过节点现在会显示为“已跳过”，不再错误显示绿色成功头和误导性的运行时间。
• 修复快速分支运行场景下 check-status 轮询可能卡在过期 202 响应的问题。

Full Changelog: v0.4.5...v0.4.6

v0.4.5

Release Notes - Version 0.4.5

Workflow & Automation:

• Added workflow scheduling support with cron expressions, scheduled run management, and a dedicated schedule manager page.
• Added ScheduleTrigger, WorkflowSelector, and HumanFeedback nodes to support scheduled execution, workflow branching, and human-in-the-loop approval flows.
• Added workflow trash management and richer run record filtering for web, schedule, API, workflow, and chat initiated runs.

Models & AI Configuration:

• Expanded model configuration with a centralized model catalog, endpoint-aware backend settings, and custom family mapping.
• Added CustomModel and UniversalLlm nodes for more flexible provider and endpoint integration.
• Added new provider integrations and node options including Baidu Wenxin, StepFun, and xAI.
• Expanded embedding backend settings to support configurable providers, models, protocols, dimensions, and endpoint mapping.

Data & Document Processing:

• Added a document conversion node to support more document processing workflows.
• Added a vector search test page for local vector databases to make retrieval debugging and verification easier.
• Improved vector search task handling and Qdrant access flow to make search execution more stable.

Workspace & UX:

• Reworked workspace routing and management views across workflow, agent, data, and settings sections.
• Refreshed workflow home, empty states, run records, and related management panels for clearer navigation and status visibility.
• Improved settings organization for LLM, embedding, endpoint, and shortcut related configuration.

Release Engineering:

• Added a GitHub Actions tagged release workflow so version tags can automatically build and publish Windows, macOS, and Linux desktop packages.
• Added version consistency validation and hardened the desktop packaging script for cross-platform builds.

工作流与自动化:

• 新增工作流调度能力，支持 Cron 表达式、调度任务管理和独立的调度管理页面。
• 新增 ScheduleTrigger、WorkflowSelector、HumanFeedback 节点，用于定时触发、工作流分支选择和人工确认审批流程。
• 新增工作流回收站，并增强运行记录筛选能力，可区分 WEB、调度、API、工作流联动、聊天等触发来源。

模型与 AI 配置:

• 重构模型配置体系，新增统一模型目录、基于 Endpoint 的后端配置能力，以及自定义模型族映射。
• 新增 CustomModel 和 UniversalLlm 节点，便于接入自定义模型和统一 LLM Endpoint。
• 新增 Baidu Wenxin、StepFun、xAI 等模型提供方及节点选项。
• 扩展 Embedding 后端设置，支持配置提供方、模型、协议、向量维度和 Endpoint 映射。

数据与文档处理:

• 新增文档转换节点，支持更多文档处理工作流。
• 新增本地向量库检索测试页面，方便调试和验证召回结果。
• 改进向量检索任务处理和 Qdrant 访问链路，提升检索执行稳定性。

工作区与体验:

• 重构工作区路由与管理视图，覆盖工作流、Agent、数据空间和设置等模块。
• 更新工作流首页、空状态、运行记录抽屉和相关管理面板，使导航与状态展示更清晰。
• 优化设置页结构，增强 LLM、Embedding、Endpoint 和快捷键等配置项的组织方式。

发布工程:

• 新增 GitHub Actions tag 自动发布工作流，推送版本 tag 后可自动构建并发布 Windows、macOS、Linux 三个平台的桌面包。
• 增加版本一致性校验，并增强桌面端打包脚本的跨平台稳定性。

v0.4.2

Release Notes - Version 0.4.2

New Features:

• Frontend: added Qwen Vision node.
• Models: added new models.

Improvements:

• LLMs: improved handling of "thinking" models.
• Backend: refined chat server model handling.
• Backend: modularized media_processing into provider modules.
• Backend: exposed native dialogs earlier in flow.
• Backend: updated media/text utilities.
• Frontend: updated locales and model lists.
• Frontend: updated LLM and vision node options.

新特性:

• 前端：新增 Qwen Vision 节点。
• 模型：新增若干模型。

改进:

• LLM：改进对“思维链/思考类”模型的处理。
• 后端：优化聊天服务的模型处理逻辑。
• 后端：将 media_processing 模块化为多个提供者模块。
• 后端：更早暴露原生对话框（native dialogs）。
• 后端：更新媒体/文本工具方法。
• 前端：更新多语言本地化与模型列表。
• 前端：更新大模型与视觉节点的选项配置。

v0.4.0

Release Notes - Version 0.4.0

Major Architecture Updates:

• FastAPI + Celery Backend Refactor:
  • Complete backend architecture overhaul with FastAPI server integration for improved performance and
    scalability
  • Added Celery worker integration for enhanced task management and background processing
• Local API Support:
  • Introduced comprehensive local API access functionality for workflow automation
  • Added REST API endpoints for programmatic workflow execution and management
  • Enhanced API documentation and examples for better developer experience

New Features:

• Enhanced Task Management:
  • Integrated workflow tasks into Celery for better async processing
  • Added robust task status tracking and caching mechanisms
  • Improved workflow execution reliability and error handling
• Model Support Expansion:
  • Added new Qwen3 models with enhanced configurations
  • Updated model handling in WebSocketServer and BaseLLMTask
  • Improved non-local chat model options with revised labels
• UI/UX Improvements:
  • Enhanced BaseNode component with editable title feature
  • Integrated data prop across various node types for better data flow
  • Improved component consistency and user interaction

Technical Improvements:

• PyWebView Upgrade:
  • Updated PyWebView to version 6.0 for improved desktop application performance and stability
  • Enhanced file dialog handling and API integration capabilities
• Development Experience:
  • Updated backend development commands for new architecture
  • Added Celery integration hooks for development workflow
  • Improved error handling and logging across components

主要架构更新:

• FastAPI + Celery 后端重构:
  • 完全重构后端架构，集成 FastAPI 服务器以提高性能和可扩展性
  • 添加 Celery 工作器集成，增强任务管理和后台处理能力
• 本地 API 支持:
  • 引入全面的本地 API 访问功能，支持工作流自动化
  • 添加 REST API 端点，支持编程式工作流执行和管理
  • 增强 API 文档和示例，提供更好的开发者体验

新特性:

• 增强的任务管理:
  • 将工作流任务集成到 Celery，实现更好的异步处理
  • 添加强大的任务状态跟踪和缓存机制
  • 提高工作流执行可靠性和错误处理能力
• 模型支持扩展:
  • 添加新的 Qwen3 模型和增强配置
  • 更新 WebSocketServer 和 BaseLLMTask 中的模型处理
  • 改进非本地聊天模型选项和标签
• 界面/体验改进:
  • 增强 BaseNode 组件的可编辑标题功能
  • 在各种节点类型中集成数据属性，改善数据流
  • 提高组件一致性和用户交互体验

技术改进:

• PyWebView 升级:
  • 升级 PyWebView 至 6.0 版本，提高桌面应用性能和稳定性
  • 增强文件对话框处理和 API 集成能力
• 开发体验:
  • 更新后端开发命令以适应新架构
  • 添加 Celery 集成钩子，优化开发工作流
  • 改进组件间的错误处理和日志记录

v0.3.6

Release Notes - Version 0.3.6

New Features:

• Model-Specific Endpoint Management:
  • Added support for managing endpoints specific to different models, improving flexibility in model deployment and usage.
• Gemini Model Updates:
  • Updated Gemini API endpoint and model configurations, including the addition of the latest experimental models.
• Message Regeneration and Deletion:
  • Implemented UI and API methods for message regeneration and deletion, enhancing user control over chat interactions.

Improvements:

• User Interface Enhancements:
  • Increased the width of the model selection modal to 850px for better visibility.
  • Added tooltips for endpoint selection in LLM settings, improving user guidance.

新特性:

• 模型特定端点管理:
  • 添加了对不同模型特定端点的管理支持，提高了模型部署和使用的灵活性。
• Gemini 模型更新:
  • 更新了 Gemini API 端点和模型配置，包括添加最新的实验模型。
• 消息重新生成和删除:
  • 实现了消息重新生成和删除的 UI 和 API 方法，增强了用户对聊天交互的控制。

改进:

• 用户界面增强:
  • 将模型选择模态框的宽度增加到 850px，以提高可见性。
  • 在 LLM 设置中添加了端点选择的工具提示，改善了用户指导。

v0.3.5

Release Notes - Version 0.3.5

New Features:

• LLM Component Enhancement:
  • Added a new LLM component structure, now supporting streaming output, system prompts, topP and other parameters.
  • Added inference content field to ModelOutput for deepseek inference models.
  • Added new models to the system.

Improvements:

• User Interface Updates:
  • Fixed a bug where the return-to-top floating button was not displayed.
• Performance and Stability:
  • Updated VectorVein dependency version.

Other Updates:

• Improved Markdown text segmentation for enhanced rendering.
• Updated Gemini model options for enhanced capabilities.

新特性:

• LLM 组件增强:
  • 添加了新的 LLM 组件结构，现在支持流式输出、系统提示词、topP 等参数。
  • 为 deepseek 推理模型添加了推理内容字段到 ModelOutput。
  • 添加了新模型到系统中。

改进:

• 用户界面更新:
  • 修复了返回顶部浮动按钮不显示的 bug。
• 性能和稳定性:
  • 更新了 VectorVein 依赖版本。

其他更新:

• 改进了 Markdown 文本分割以提升渲染效果。
• 更新了 Gemini 模型选项以增强功能。

v0.3.4

Release Notes - Version 0.3.4

New Features:

• Text Replacement:
  • Added text replacement feature and node for enhanced text processing capabilities.

Improvements:

• Security and Performance:
  • Fixed httpx proxy parameter issues after version 0.28.0.
  • Simplified embedding requests for improved performance.
• Database Enhancements:
  • Enhanced database query for primary key retrieval.
  • Added primary key to table data for better data organization.

Other Updates:

• Updated LLM models.

新特性:

• 文本替换:
  • 添加文本替换功能和节点，增强文本处理能力。

改进:

• 安全性和性能:
  • 修复 httpx 代理参数问题，解决版本 0.28.0 后的兼容性问题。
  • 简化嵌入请求，提升性能。
• 数据库增强:
  • 增强数据库查询，优化主键检索。
  • 为主键数据添加主键，提升数据组织效率。

其他更新:

• 更新 LLM 模型。

v0.3.3

Release Notes - Version 0.3.3

New Features:

• Bing Search Configuration:
  • Enhanced Bing search configuration with endpoint support.

Bug Fixes:

• Upload Functionality:
  • Fixed an issue with file upload.

新特性:

• Bing 搜索配置:
  • 增强 Bing 搜索配置，支持端点配置。

修复:

• 上传功能:
  • 修复文件上传问题。