MemoryBear/api/app/version_info.json

{
  "v0.3.1": {
    "introduction": {
      "codeName": "无境",
      "releaseDate": "2026-4-22",
      "upgradePosition": "🐻 聚焦应用体验优化、记忆 API 开放与工作流可靠性提升，打破边界，自由流动",
      "coreUpgrades": [
        "1. 应用与模型增强<br>* 模型 Key 全删后自动关闭：避免无 Key 运行时错误<br>* 模型 JSON 格式化输出开关：支持旧工作流迁移的稳定 JSON 输出<br>* 配置导入覆盖：支持完整替换当前配置<br>* 导入时缺失资源清理：自动清空不存在的工具和知识库引用",
        "2. 记忆 API 与智能 📚<br>* 记忆读写 API 与 End-User Key 供给：支持第三方直接交互记忆层<br>* 记忆库 API 与配置更新：程序化控制记忆设置（提供顺序接口）<br>* End-User 元数据存储：丰富用户上下文持久化",
        "3. 工作流与体验优化 ⚙️<br>* 会话历史文件元数据：增加文件大小、名称和类型<br>* 迭代节点并行输入修复：恢复并发执行行为<br>* API Key 后四位展示：便于密钥识别<br>* 条件分支多文件子变量：更精细的条件逻辑<br>* Agent 模型配置重置接口：完善前后端契约<br>* 三级变量键盘导航：提升变量选择体验<br>* 应用标签页动态标题：动态显示应用名称<br>* 变量聚合三级勾选修复：修复勾选行为<br>* 工作流检查清单校验增强：工具必填和视觉变量必填<br>* 变量聚合器到参数提取器输出：修复输出变量获取",
        "4. 知识库与性能 ⚡<br>* 文档解析与 Graph 异步执行：提升文档摄入吞吐量",
        "5. 稳健性与缺陷修复 🔧<br>* 工具节点原始参数类型：修复类型不匹配问题<br>* 前端部署后资源过期导入错误：解决缓存资源导入失败<br>* 工作流工具节点必填校验：防止不完整配置发布",
        "<br>",
        "v0.3.1 是平台哲学演进中的关键时刻——边界的打破。记忆 API 开放和应用体验优化为社区用户提供更强大的集成能力。展望未来，我们将持续提升记忆智能管线的萃取精度与自适应遗忘策略，深化工作流引擎能力。破界而行，臻于无境。",
        "MemoryBear — 无境 🐻✨"
      ]
    },
    "introduction_en": {
      "codeName": "WuJing",
      "releaseDate": "2026-4-22",
      "upgradePosition": "🐻 Focused application improvements, memory API openness, and workflow reliability — dissolving boundaries, flowing freely",
      "coreUpgrades": [
        "1. Application & Model Enhancements<br>* Model Auto-Disable on Key Deletion: Prevents keyless runtime errors<br>* Model JSON Formatted Output Toggle: Stable JSON output for legacy workflow migration<br>* Configuration Import with Override: Full configuration replacement support<br>* Import Cleanup for Missing Resources: Auto-clears missing tool and knowledge base references",
        "2. Memory API & Intelligence 📚<br>* Memory Read/Write API with End-User Key Provisioning: Third-party memory layer interaction<br>* Memory Store API & Configuration Update: Programmatic memory settings control with sequential interface<br>* End-User Metadata Storage: Richer user context persistence",
        "3. Workflow & UX Improvements ⚙️<br>* Conversation History File Metadata: File size, name, and type labels<br>* Iteration Node Parallel Input Fix: Restored concurrent execution<br>* API Key Last Four Digits Display: Key identification without exposure<br>* Condition Branch Multi-File Sub-Variables: Granular conditional logic<br>* Agent Model Config Reset Endpoint: Completed frontend-backend contract<br>* Three-Level Variable Keyboard Navigation: Improved selection experience<br>* Dynamic Tab Title for Applications: Dynamic app name in browser tab<br>* Variable Aggregator Three-Level Checkbox Fix: Corrected checkbox behavior<br>* Workflow Checklist Validation Enhancements: Tool required and vision variable validation<br>* Variable Aggregator to Parameter Extractor Output: Fixed output variable access",
        "4. Knowledge Base & Performance ⚡<br>* Async Document Parsing & Graph Execution: Improved document ingestion throughput",
        "5. Robustness & Bug Fixes 🔧<br>* Tool Node Raw Parameter Types: Fixed type mismatch issues<br>* Stale Frontend Resource Import Error: Resolved cached resource import failure<br>* Workflow Tool Node Required Validation: Prevents incomplete configuration publishing",
        "<br>",
        "v0.3.1 marks a pivotal moment in the platform's evolution — the dissolution of boundaries. Memory API openness and application experience improvements provide community users with stronger integration capabilities. Looking ahead, we will continue improving extraction accuracy, adaptive forgetting strategies, and deepening workflow engine capabilities. Beyond boundaries — the boundless awaits.",
        "MemoryBear — The Boundless 🐻✨"
      ]
    }
  },
  "v0.3.0": {
    "introduction": {
      "codeName": "破晓",
      "releaseDate": "2026-4-15",
      "upgradePosition": "🐻 全面升级应用工作流、记忆智能与系统稳健性，引入版本化API、多模态记忆感知及大量工作流增强，打造更可靠、精准的 MemoryBear",
      "coreUpgrades": [
        "1. 应用与API增强<br>* 版本化API调用支持：对外服务API支持指定版本调用<br>* 工作流检查清单：新增结构化验证步骤<br>* 深度思考参数精准控制：仅向支持深度推理的模型发送思考参数<br>* 提示器模型返回优化：优化提示器模型响应处理",
        "2. 记忆智能 🧠<br>* 多模态记忆感知Agent：支持多模态记忆读取与写入<br>* OpenClaw内置工具：新增内置工具扩展Agent工具集",
        "3. 用户体验 🎨<br>* 流式渲染稳定性优化：解决LLM流式输出页面抖动问题<br>* 记忆中枢更名：「记忆相关」更名为「记忆中枢」",
        "4. 工作流改进 ⚙️<br>* 三级变量模板转换：支持三级变量解析<br>* VL模型Token统计：修复模型组合中VL模型Token未统计问题<br>* 导入工作流功能特性同步：正确同步开场白、引用等属性<br>* 会话变量名称唯一性校验：防止变量名冲突<br>* 文件类型提取修复：正确提取file.type信息<br>* 条件分支显示修复：值为0或会话变量时正确渲染<br>* Object/Array校验规则：防止JSON序列化错误<br>* HTTP请求Body字段修正：body字段从name改为key",
        "5. 知识库 📚<br>* Embedding Token截断安全边界：统一添加8000 token截断，优化Excel独立chunk处理",
        "6. 稳健性与缺陷修复 🔧<br>* 原子性更新与批量访问失败修复<br>* 对话别名提取错误修复<br>* 工作流别名提取修正（区分用户和AI回复）<br>* RAG记忆分页数据修复<br>* 隐式记忆详情显示修复<br>* 向量查询驱动关闭异常修复<br>* 用户管理启停异常修复<br>* 模型列表筛选不一致修复",
        "<br>",
        "v0.3.0 标志着 MemoryBear 向生产成熟度迈出坚实一步。后续版本将持续深化工作流表达力、记忆检索精度和跨模态理解能力，强化复杂Agent编排支持，稳固大规模生产部署基础。",
        "<br>",
        "MemoryBear — 破晓 🐻✨"
      ]
    },
    "introduction_en": {
      "codeName": "PoXiao",
      "releaseDate": "2026-4-15",
      "upgradePosition": "🐻 Comprehensive upgrades across application workflows, memory intelligence, and system robustness — introducing versioned APIs, multimodal memory perception, and extensive workflow enhancements for a more reliable MemoryBear",
      "coreUpgrades": [
        "1. Application & API Enhancements<br>* Versioned API Support: External APIs now support version-specific calls<br>* Workflow Checklist: Structured validation steps before deployment<br>* Deep Thinking Parameter Control: Only send thinking params to supported models<br>* Prompt Optimizer Return Optimization: Improved prompt optimizer response handling",
        "2. Memory Intelligence 🧠<br>* Multimodal Memory Perception Agent: Read/write multimodal memory<br>* OpenClaw Built-in Tool: New built-in tool for agent operations",
        "3. User Experience 🎨<br>* Streaming Render Stabilization: Eliminated page jitter during LLM output<br>* Memory Hub Renaming: Renamed to better reflect central memory role",
        "4. Workflow Improvements ⚙️<br>* Three-Level Variable Template Conversion: Support for three-level variable resolution<br>* VL Model Token Tracking: Fixed token tracking for VL models in model groups<br>* Imported Workflow Feature Sync: Properly sync opening messages, citations, etc.<br>* Session Variable Name Uniqueness: Prevent variable name conflicts<br>* File Type Extraction Fix: Correctly extract file.type information<br>* Condition Branch Display Fix: Correct rendering for value 0 or session variables<br>* Object/Array Validation Rules: Prevent JSON serialization save errors<br>* HTTP Request Body Key Fix: Body field uses key instead of name",
        "5. Knowledge Base 📚<br>* Embedding Token Truncation Safety: Unified 8000-token boundary, optimized Excel chunk processing",
        "6. Robustness & Bug Fixes 🔧<br>* Atomic update & batch access failure fixes<br>* Conversation alias extraction fix<br>* Workflow alias extraction correction (user vs AI distinction)<br>* RAG memory pagination fix<br>* Implicit memory detail display fix<br>* Vector query driver closed exception fix<br>* User management enable/disable fix<br>* Model list filter inconsistency fix",
        "<br>",
        "v0.3.0 marks a meaningful step toward production maturity for MemoryBear. Upcoming releases will deepen workflow expressiveness, memory retrieval precision, and cross-modal understanding while strengthening complex agent orchestration and large-scale deployment foundations.",
        "<br>",
        "MemoryBear — Daybreak 🐻✨"
      ]
    }
  },
  "v0.2.10": {
    "introduction": {
      "codeName": "炼剑",
      "releaseDate": "2026-4-8",
      "upgradePosition": "🐻 全面强化工作流引擎、引入 Agent 深度思考模式与多模态记忆读取，百炼成锋，剑指生产就绪",
      "coreUpgrades": [
        "1. 工作流引擎增强<br>* 会话变量文件格式支持：支持文件类型值及本地/远程默认值配置<br>* 列表操作节点：新增专用列表操作节点<br>* 模板转换支持 HTML：扩展富内容渲染能力<br>* 表单返回与提交：工作流返回交互式表单，前端支持提交<br>* HTTP 节点 XML 响应：拓宽企业级 API 集成兼容性<br>* 开场白与文件引用：支持配置开场白及附件引用<br>* 模板转换三级变量：支持深层嵌套变量访问<br>* 节点连线添加按钮：连线处新增内联添加按钮",
        "2. Agent 智能 🧠<br>* Agent 深度思考模式：支持更充分的推理以产出高质量回答<br>* 模型深度思考特性开关：模型级特性标识与应用级开关控制",
        "3. 记忆系统升级 📚<br>* 用户记忆库分页：支持大规模记忆集合分页浏览<br>* RAG 用户记忆数据结构刷新：后端 API 数据结构重新设计<br>* 多模态记忆读取：支持检索图像、音频等非文本记忆<br>* 语义剪枝阈值提示文案：显示描述性区间标签",
        "4. 前端与体验 🎨<br>* 技能工具删除状态展示：工具列表显示删除状态标识<br>* 仪表盘日环比数据：关键指标增加与昨日对比数据",
        "5. 稳健性与缺陷修复 🔧<br>* 参数提取空值处理：优雅处理缺失数据<br>* Token 消耗展示优化：确保用量报告准确<br>* 模型参数负值修复：明确参数范围定义<br>* 应用共享删除同步：正确更新所有共享记录<br>* 记忆写入任务排序：按时间戳顺序执行<br>* 多模态模型缺失优雅处理：不再中断感知记忆写入<br>* 自定义工具 Number 变量传递：解决类型转换问题<br>* 集群子代理保存后显示：修复未反显问题<br>* 记忆开启后流式输出修复：解决字符串序列化问题",
        "<br>",
        "v0.2.10 标志着平台向生产成熟度迈出的重要一步。深度思考、交互式表单工作流与多模态记忆的结合展现了平台从记忆存储向综合认知基础设施的演进。我们期待 4 月 17 日 v0.3.0 发布会，届时将带来更深层的 Agent 推理能力、多智能体协作功能及记忆智能管线的进一步优化。剑已炼成，只待出鞘。",
        "MemoryBear — 百炼成锋 🐻✨"
      ]
    },
    "introduction_en": {
      "codeName": "LianJian",
      "releaseDate": "2026-4-8",
      "upgradePosition": "🐻 Comprehensive workflow engine enhancements, Agent deep thinking mode, and multimodal memory reading — forging the blade for production readiness",
      "coreUpgrades": [
        "1. Workflow Engine Enhancements<br>* Session Variable File Support: File-type values with local/remote defaults<br>* List Operation Node: Dedicated node for array manipulation<br>* Template Conversion HTML Support: Rich-content rendering<br>* Form Return & Submission: Interactive forms in workflow conversations<br>* HTTP Node XML Response: Enterprise API integration compatibility<br>* Opening Remarks & File References: Configurable conversation openers<br>* Template Conversion Three-Level Variables: Deep nested variable access<br>* Node Connection Add Button: Inline add button on connections",
        "2. Agent Intelligence 🧠<br>* Agent Deep Thinking Mode: Thorough reasoning for complex queries<br>* Model Deep Thinking Feature Toggle: Model-level flag with per-app control",
        "3. Memory System Upgrades 📚<br>* User Memory Pagination: Paginated browsing for large collections<br>* RAG User Memory Data Structure Refresh: Redesigned backend API contracts<br>* Multimodal Memory Reading: Retrieval of image, audio, and non-text memory<br>* Semantic Pruning Threshold Hints: Descriptive range labels for configuration",
        "4. Frontend & Usability 🎨<br>* Skill Tool Deletion Status Display: Deletion indicators in tool list<br>* Dashboard Day-over-Day Comparison: Key metrics with yesterday comparison",
        "5. Robustness & Bug Fixes 🔧<br>* Parameter Extraction Null Handling: Graceful handling of missing data<br>* Token Consumption Display Optimization: Accurate usage reporting<br>* Model Parameter Negative Value Fix: Clear parameter range definitions<br>* App Share Deletion Sync: Correct update of all share records<br>* Memory Write Task Ordering: Chronological execution per end_user<br>* Multimodal Model Missing Graceful Handling: No more interrupted writes<br>* Custom Tool Number Variable Pass-through: Type coercion fix<br>* Cluster Sub-Agent Display After Save: Fixed UI reflection<br>* Memory-Enabled Streaming Output Fix: String serialization resolved",
        "<br>",
        "v0.2.10 marks a significant step toward production maturity. The combination of deep thinking, interactive form workflows, and multimodal memory demonstrates the platform's evolution from memory storage to comprehensive cognitive infrastructure. We look forward to the v0.3.0 launch on April 17, bringing deeper agent reasoning, multi-agent collaboration, and further memory intelligence refinements. The blade has been forged — now it's time to wield it.",
        "MemoryBear — Forging the Blade 🐻✨"
      ]
    }
  },
  "v0.2.8": {
    "introduction": {
      "codeName": "景玉",
      "releaseDate": "2026-3-20",
      "upgradePosition": "🐻 MemoryBear v0.2.8 社区版全面升级应用共享、多模态交互与平台基础设施，引入语音交互、感知记忆和云端存储，打造更强大的开放 AI 记忆平台",
      "coreUpgrades": [
        "1. 应用共享与发布<br>* 应用共享（Agent、工作流、Agent 集群）：全类型应用共享至其他空间<br>* 分享应用默认开启记忆功能：发布分享后记忆默认开启，关闭时提醒<br>* 工作流记忆分享规则：按记忆配置自动控制分享页记忆开关<br>* 分享会话联网搜索修复：恢复分享应用的联网搜索能力",
        "2. 多模态与交互 💬<br>* 语音输入：模型接口和应用支持语音输入<br>* 语音回复：应用支持语音回复模态<br>* 多模态感知记忆：记忆系统支持视觉、音频、图片和文件的感知记忆<br>* 对话框文件展示：试运行和体验分享中正确展示上传文件",
        "3. 平台与基础设施 ⚙️<br>* i18n 国际化：全面多语言多地区支持<br>* 云端文件存储（OSS + S3）：支持阿里云 OSS 和 S3 云端上传<br>* Flower 容器监控：Celery 异步任务监控与管理",
        "4. EndUser 身份迁移 🔐<br>* EndUser 从 app_id 迁移至 workspace_id：身份从应用级迁移至工作空间级",
        "5. 情景记忆 🧠<br>* 情景记忆聚类算法：基于社区图谱的聚类算法，支持老用户图谱生成",
        "6. 稳健性与缺陷修复 🔧<br>* MCP 服务删除后工具 404：修复删除 MCP 服务后接口报错<br>* 应用导出配置不一致：导出已保存配置而非画布状态<br>* 工作流节点 ID 重复：修复复制节点后 ID 冲突<br>* 条件分支连线错误：修复保存刷新后连线错乱<br>* 回复节点内容丢失：修复点击画布后内容消失<br>* 连接桩规则优化：禁止非法连接方向<br>* 知识库状态列宽度：锁定或自适应宽度<br>* 等待中文档预览：支持未完成解析文档预览<br>* 知识库关联修复：统一修复关联问题<br>* 多模态对话连续性：修复多模态内容后无法继续对话<br>* 时区统一：环境变量统一控制存储和任务时区<br>* 遗忘强度精度：修复小数显示过长",
        "<br>",
        "v0.2.8 社区版在应用共享和多模态交互方面实现重大升级，感知记忆扩展了平台的认知维度。后续将深化多智能体协作、情景记忆聚类，并持续优化平台稳定性与开放生态。",
        "MemoryBear —— 让 AI 拥有记忆 🐻✨"
      ]
    },
    "introduction_en": {
      "codeName": "JingYu",
      "releaseDate": "2026-3-20",
      "upgradePosition": "🐻 MemoryBear v0.2.8 Community delivers multimodal interaction, perceptual memory, cloud storage, and workspace-level identity for a more capable open AI memory platform",
      "coreUpgrades": [
        "1. Application Sharing & Publishing<br>* Application Sharing (Agent, Workflow, Agent Cluster): Full sharing across all app types<br>* Memory Enabled by Default: Memory auto-enabled on shared apps with disable reminder<br>* Workflow Memory Sharing Rules: Auto-controlled based on memory configuration<br>* Shared Session Web Search Fix: Restored web search for shared apps",
        "2. Multimodal & Interaction 💬<br>* Voice Input: Model interfaces and apps support voice input<br>* Voice Reply: Apps support voice reply modality<br>* Multimodal Perceptual Memory: Memory system supports visual, audio, image, and file perception<br>* File Display in Chat: Uploaded files display correctly in dry-run and sharing",
        "3. Platform & Infrastructure ⚙️<br>* i18n Internationalization: Full multi-language multi-region support<br>* Cloud File Storage (OSS + S3): Alibaba Cloud OSS and S3 cloud uploads<br>* Flower Container Monitoring: Celery async task monitoring and management",
        "4. EndUser Identity Migration 🔐<br>* EndUser Migration from app_id to workspace_id: Identity migrated to workspace level",
        "5. Episodic Memory 🧠<br>* Episodic Memory Clustering: Community-graph-based clustering with legacy user support",
        "6. Robustness & Bug Fixes 🔧<br>* MCP Service Deletion 404: Fixed tool endpoint error after MCP removal<br>* App Export Config Mismatch: Exports saved config instead of canvas state<br>* Workflow Duplicate Node ID: Fixed ID conflict on node duplication<br>* Conditional Branch Wiring: Fixed wiring reset after save/refresh<br>* Reply Node Content Loss: Fixed content disappearing on canvas click<br>* Port Connection Rules: Prohibited invalid connection directions<br>* Knowledge Base Status Width: Locked or adaptive column width<br>* Pending Document Preview: Preview support for unparsed documents<br>* Knowledge Base Association Fixes: Consolidated association fixes<br>* Multimodal Conversation Continuity: Fixed single-round limit after multimodal input<br>* Timezone Unification: Env-var controlled unified timezone<br>* Forgetting Strength Precision: Fixed excessive decimal display",
        "<br>",
        "v0.2.8 Community delivers major upgrades in application sharing and multimodal interaction, with perceptual memory expanding the platform's cognitive dimensions. Multi-agent collaboration, episodic clustering, and continued platform stability improvements are ahead.",
        "MemoryBear — Give AI Memory 🐻✨"
      ]
    }
  },
  "v0.2.7": {
    "introduction": {
      "codeName": "武陵",
      "releaseDate": "2026-3-13",
      "upgradePosition": "🐻 应用可移植性、工具生态扩展与记忆智能精细化",
      "coreUpgrades": [
        "1. 应用管理与可移植性<br>* 应用导入/导出：全面支持 Agent 配置和工作流定义的导入导出，实现跨环境无缝迁移、备份和共享",
        "2. 工具生态扩展 🔌<br>* MCP 广场集成：工具管理接入 MCP 广场，提供集中式工具发现、浏览和集成枢纽",
        "3. 工作流增强 📝<br>* 备注节点：新增备注节点类型，支持工作流图中的内联文档和上下文说明，提升协作效率",
        "4. 记忆智能精细化 🧠<br>* 隐性记忆与情绪记忆生成逻辑优化：含数据存在性校验、时间轴筛选和兴趣分布缓存校验<br>* 兴趣分布生成逻辑改进：优化算法产生更准确的用户兴趣画像",
        "5. 用户体验改进 🎨<br>* 知识库分享加载状态：增加加载指示器，改善感知响应速度",
        "6. 稳健性与缺陷修复 🔧<br>* 应用调试终端用户管理：修复调试会话错误创建 end_user 记录问题<br>* 知识库数据集创建流程：解决创建数据集后无法进入下一步的缺陷<br>* RAG 空间记忆生成失败：修复记忆生成失败和存储中断的关键问题<br>* 应用字符限制强制执行：增加条件校验防止过长输入<br>* 语义剪枝情绪/兴趣保留：优化剪枝逻辑防止误删情绪和兴趣片段<br>* 语义剪枝效果优化：增强算法平衡记忆压缩与信息保留",
        "<br>",
        "v0.2.8 及更远的未来将引入多模态记忆能力，实现知识库和模型的分服务部署，为应用增加语音输入支持，并扩展应用能力至语音回复、BI 可视化、PPT 生成和直接生图。应用会话分享和联网搜索功能将得到修复和增强。记忆检索基准测试和情景记忆聚类算法将增强上下文召回和时序推理能力。通往真正智能、多模态、上下文感知应用的旅程仍在继续。",
        "记忆熊，智慧致远 🐻✨"
      ]
    },
    "introduction_en": {
      "codeName": "WuLing",
      "releaseDate": "2026-3-13",
      "upgradePosition": "🐻 Application portability, tool ecosystem expansion, and memory intelligence refinement",
      "coreUpgrades": [
        "1. Application Management & Portability<br>* Application Import/Export: Full support for importing and exporting agent configurations and workflow definitions, enabling seamless cross-environment migration, backup, and sharing",
        "2. Tool Ecosystem Expansion 🔌<br>* MCP Marketplace Integration: Tool management now includes MCP Marketplace access for centralized tool discovery, browsing, and integration",
        "3. Workflow Enhancements 📝<br>* Annotation Node: Introduced annotation node type for inline documentation and contextual notes within workflow graphs, improving collaboration",
        "4. Memory Intelligence Refinement 🧠<br>* Implicit & Emotional Memory Generation Logic: Comprehensive optimization including data existence validation, timeline filtering, and interest distribution cache validation<br>* Interest Distribution Generation Logic: Refined algorithm for more accurate user interest profiles",
        "5. User Experience Improvements 🎨<br>* Knowledge Base Sharing Loading State: Added loading indicators to improve perceived responsiveness",
        "6. Robustness & Bug Fixes 🔧<br>* End User Management in App Debugging: Fixed incorrect end_user record creation during debugging sessions<br>* Knowledge Base Dataset Creation Flow: Resolved bug preventing next step after dataset creation<br>* RAG Space Memory Generation Failure: Fixed critical memory generation and storage interruption issue<br>* Application Character Limit Enforcement: Added conditional validation to prevent excessively long input<br>* Semantic Pruning Emotion/Interest Preservation: Optimized pruning logic to prevent incorrect deletion of emotional and interest fragments<br>* Semantic Pruning Effectiveness: Enhanced algorithm balance between memory compression and information retention",
        "<br>",
        "Looking forward to v0.2.8 and beyond, we will introduce multimodal memory capabilities with distributed service deployment for knowledge bases and models, enabling voice input for applications and expanding application capabilities with voice responses, BI visualizations, PPT generation, and direct image creation. Application conversation sharing and web search functionality will be restored and enhanced. Memory retrieval benchmarking and episodic memory clustering algorithms will enhance contextual recall and temporal reasoning. The journey toward truly intelligent, multimodal, context-aware applications continues.",
        "MemoryBear, Wisdom Reaching Far 🐻✨"
      ]
    }
  },
  "v0.2.6": {
    "introduction": {
      "codeName": "听剑",
      "releaseDate": "2026-3-6",
      "upgradePosition": "🐻 多模态交互全面升级，记忆剪枝与工作流迁移双线并进，锋芒初露，兼收并蓄",
      "coreUpgrades": [
        "1. 工作流与应用框架<br>* 工作流导入适配（Dify）：支持 Dify 工作流定义无缝迁移<br>* 字段字数限制与校验规则：可配置字符限制与产品级校验<br>* 应用复制（Agent、工作流、集群）：一键复制完整应用配置<br>* 对话变量（调试+分享）：支持有状态多轮交互<br>* Chat 接口流式输出 message_id：流式响应包含消息追踪标识",
        "2. 多模态与交互 💬<br>* 音频输入与输出：应用支持音频模态<br>* 文件类型输入支持：扩展支持语音、文件、视频上传",
        "3. 模型与智能 🧠<br>* 模型视觉与 Omni 区分：精确区分视觉与 Omni 模型能力<br>* 教育记忆与陪伴玩具场景预设：垂直领域本体配置开箱即用<br>* 本体配置默认标识：支持基线配置标记<br>* 记忆配置默认标识：自动应用默认记忆设置",
        "4. 记忆智能 🔬<br>* 记忆剪枝模块：智能裁剪冗余低价值记忆<br>* RAG 快速检索集成记忆：深度思考与正常回复双模式检索",
        "5. 稳健性与缺陷修复 🔧<br>* 模型管理：修复自定义模型 API Key 批量配置错误<br>* 知识库管理：修复非源文档下载原始内容接口错误，更新分享停用提示文案<br>* 用户记忆：优化档案提取准确性（姓名、职业、兴趣分布）<br>* 长期记忆：修复情景记忆卡片重复和用户归属错误<br>* 工作空间首页：修复知识库数量、应用数量、总记忆容量、API 调用次数、知识库类型分布等数据不一致问题<br>* 基础设施：修正 Celery 环境变量配置，修复数据库连接池 idle-in-transaction 泄漏",
        "<br>",
        "v0.2.6 标志着 MemoryBear 在多模态交互、跨平台工作流迁移和智能记忆管理方面的重要突破。下一版本将聚焦 A2A 协议支持实现多智能体协作、多模态记忆能力扩展至语音与视觉领域，以及应用导入导出功能支持跨环境便携部署。",
        "MemoryBear，让记忆有熊力 🐻✨"
      ]
    },
    "introduction_en": {
      "codeName": "TingJian",
      "releaseDate": "2026-3-6",
      "upgradePosition": "🐻 Full multimodal interaction upgrade with memory pruning and workflow migration — sharpened edge, broader reach",
      "coreUpgrades": [
        "1. Workflow & Application Framework<br>* Workflow Import Adaptation (Dify): Seamless Dify workflow migration<br>* Field Character Limits & Validation: Configurable limits with product-defined rules<br>* Application Cloning (Agent, Workflow, Cluster): One-click full config duplication<br>* Conversation Variables (Debug + Share): Stateful multi-turn interactions<br>* Streaming message_id in Chat API: Message tracking in streaming responses",
        "2. Multimodal & Interaction 💬<br>* Audio Input & Output: Audio modality support for applications<br>* File Type Input Support: Voice, file, and video upload support",
        "3. Model & Intelligence 🧠<br>* Model Vision & Omni Differentiation: Precise capability routing<br>* Education Memory & Companion Toy Presets: Domain-specific ontology configs<br>* Ontology Default Identifier: Baseline configuration flagging<br>* Memory Configuration Default Identifier: Auto-apply default settings",
        "4. Memory Intelligence 🔬<br>* Memory Pruning Module: Intelligent trimming of redundant memories<br>* RAG Quick Retrieval with Memory: Deep think and normal reply dual-mode retrieval",
        "5. Robustness & Bug Fixes 🔧<br>* Model Management: Fixed custom model API key batch configuration error<br>* Knowledge Base: Fixed download original content API error for non-source documents, updated share disable prompt text<br>* User Memory: Improved profile extraction accuracy (name, occupation, interests)<br>* Long-Term Memory: Fixed duplicate episodic memory cards and wrong user attribution<br>* Dashboard: Fixed data inconsistencies in knowledge count, app count, memory capacity, API calls, and knowledge type distribution<br>* Infrastructure: Corrected Celery environment variables, fixed database connection pool idle-in-transaction leak",
        "<br>",
        "v0.2.6 marks a significant milestone for MemoryBear in multimodal interaction, cross-platform workflow migration, and intelligent memory management. The next release will focus on A2A protocol support for multi-agent collaboration, multimodal memory extending extraction to voice and visual domains, and application import/export for portable cross-environment deployment.",
        "MemoryBear, Memory with Bear Power 🐻✨"
      ]
    }
  },
  "v0.2.5": {
    "introduction": {
      "codeName": "行云",
      "releaseDate": "2026-2-26",
      "upgradePosition": "🐻 精炼根基，优化核心用户体验与系统稳定性",
      "coreUpgrades": [
        "1. 用户体验与国际化 🎨<br>* 语言参数修复：语言偏好现正确保留<br>* 邮箱修改支持：用户可直接在用户管理系统中修改邮箱地址",
        "2. 工作流可视化增强 💬<br>* 循环与迭代节点输出展示：实时显示执行进度和中间输出，便于调试复杂迭代过程<br>* 变量支持回车选择：支持回车键确认变量选择，简化工作流配置流程",
        "3. 优化模型管理 ⚙️<br>* 模型广场移除自定义模型，优化模型使用体验",
        "4. 稳健性与缺陷修复 🔧<br>* 知识图谱构建修复：解决知识图谱构建流程稳定性问题，确保更可靠的实体提取和关系映射",
        "<br>",
        "版本 0.2.5 通过解决国际化边界情况和改进工作流透明度，构建更具生产就绪性的平台。工作流可视化改进为更复杂的调试和监控能力奠定基础。未来将继续深化企业就绪性，扩展用户管理功能、优化知识图谱智能和增强工作流编排能力，在可观测性、性能优化和无缝集成模式方面持续改进。",
        "智慧致远 🐻✨"
      ]
    },
    "introduction_en": {
      "codeName": "Flowing Clouds",
      "releaseDate": "2026-2-26",
      "upgradePosition": "🐻 Refined foundations with enhanced user experience and system stability",
      "coreUpgrades": [
        "1. User Experience & Internationalization 🎨<br>* Language parameter fix: language preferences are now correctly retained<br>* Email Update Support: Users can now modify email addresses directly in user management system",
        "2. Workflow Visualization Enhancements 💬<br>* Loop & Iteration Node Output Display: Real-time display of execution progress and intermediate outputs for easier debugging<br>* Variable Selection with Enter Key: Enabled Enter key confirmation for streamlined variable assignment",
        "3. Optimized Model Management ⚙️<br>* Custom models have been removed from the Model marketplace to optimize the model usage experience",
        "4. Robustness & Bug Fixes 🔧<br>* Knowledge Graph Construction Fix: Addressed stability issues in knowledge graph pipeline for more reliable entity extraction and relationship mapping",
        "<br>",
        "Version 0.2.5 matures MemoryBear's operational foundations by addressing internationalization edge cases and improving workflow transparency. The workflow visualization improvements lay groundwork for sophisticated debugging and monitoring capabilities. Looking forward, we will deepen enterprise readiness by expanding user management features, refining knowledge graph intelligence, and enhancing workflow orchestration with continued improvements in observability, performance optimization, and seamless integration patterns.",
        "Intelligent Resilience 🐻✨"
      ]
    }
  },
  "v0.2.4": {
    "introduction": {
      "codeName": "智远",
      "releaseDate": "2026-2-11",
      "upgradePosition": "🐻 生产级稳健性升级版本，智慧致远，从容应对复杂场景",
      "coreUpgrades": [
        "1. Skills 技能框架 🛠️<br>* Skills 支持：引入全新的Skills技能系统，支持可扩展的能力模块，可在Agent和工作流中动态加载与编排",
        "2. 多模态与交互 💬<br>* 文件多模态支持：全面支持消息输入、LLM处理和输出渲染中的多模态文件处理，实现更丰富的媒体感知对话<br>* 语音交互：语音交互功能正在积极开发中，为免提对话体验奠定基础（开发中）",
        "3. 知识库集成 📚<br>* 飞书知识库：无缝对接飞书文档库，支持企业知识检索<br>* 语雀知识库：原生连接语雀文档平台，扩展对国内企业工具生态的覆盖<br>* Web站点知识库：通用Web站点抓取与索引，支持从公开网页内容构建知识库<br>* 视觉模型选择优化：知识库视觉模型配置现已支持LLM和Chat两种模型类型，移除了此前仅限Chat类型的限制",
        "4. 记忆智能 🧠<br>* 本体工程（二期）：基于本体工程的高级记忆场景分类与萃取，实现结构化、领域感知的记忆组织，提升分类准确性<br>* 默认模型配置：情绪分析、反思和记忆萃取模块现默认使用空间级模型，确保开箱即用的一致性行为<br>* 智能模型回退：当已配置的情绪或反思模型为空或不可用时，系统自动回退至空间默认模型，避免静默失败<br>* 记忆模型回退兜底：当记忆中配置的模型为空或不可用时，系统优雅降级至空间默认模型",
        "5. 性能与扩展 ⚡<br>* 模型并发（model_api_keys）：支持并发模型API Key管理，实现并行模型调用，提升高负载场景下的吞吐能力",
        "6. 稳健性与缺陷修复 🔧<br>* 记忆配置版本固定：修复用户记忆配置未跟随应用版本发布固定的问题，消除跨部署的行为不一致<br>* 空间默认记忆保护：空间级默认记忆配置现不可删除；用户级配置仍可删除<br>* Agent与工作流配置兜底：解决Agent和工作流节点中记忆配置可能为空、或已选择但未配置的边界情况——全面的回退处理现可防止运行时错误<br>* 隐形记忆字段重命名：将隐形记忆接口JSON响应中的user_id修正为end_user_id，与规范数据模型对齐<br>* 记忆配置ID迁移：将Agent和工作流记忆配置中的memory_content重命名为memory_config_id，保持API一致性<br>* Worker-Memory告警解决：解决worker-memory服务中的告警级别问题，提升运维监控清晰度<br>* 双语接口修复：修复记忆相关API接口的中英文不一致问题<br>* 新用户记忆配置自动回填：新创建的EndUser若memory_config_id为None，系统自动从最新Release获取memory_config_id并回填<br>* 存量用户记忆配置自动回填：已有EndUser若memory_config_id为None，系统同样从最新Release获取并回填，确保向后兼容，无需手动迁移",
        "<br>",
        "Memory Bear v0.2.4 向生产级稳健性迈进，Skills框架与多模态支持开启认知平台新篇章。",
        "记忆熊，智慧致远，从容应对真实世界的多样性。🐻✨"
      ]
    },
    "introduction_en": {
      "codeName": "ZhiYuan",
      "releaseDate": "2026-2-11",
      "upgradePosition": "🐻 Production-grade resilience release — Wisdom Reaching Far, gracefully handling complex scenarios",
      "coreUpgrades": [
        "1. Skills Framework 🛠️<br>* Skills Support: Introduced a new Skills system, enabling extensible capability modules that can be dynamically loaded and orchestrated within agents and workflows",
        "2. Multimodal & Interaction 💬<br>* File Multimodal Support: Full multimodal file handling across message input, LLM processing, and output rendering — supporting richer, media-aware conversations<br>* Voice Interaction: Voice-based interaction capabilities are under active development, laying the groundwork for hands-free conversational experiences (In Progress)",
        "3. Knowledge Base Integration 📚<br>* Feishu Knowledge Base: Seamless integration with Feishu (Lark) document repositories for enterprise knowledge retrieval<br>* Yuque Knowledge Base: Native connector for Yuque documentation platforms, expanding coverage of Chinese enterprise tooling<br>* Web Site Knowledge Base: General-purpose web site crawling and indexing for knowledge base construction from public web content<br>* Visual Model Selection: Knowledge base visual model configuration now supports both LLM and Chat model types, removing the previous restriction to Chat-only selection",
        "4. Memory Intelligence 🧠<br>* Ontology Engineering (Phase 2): Advanced memory scene classification and extraction powered by ontology engineering — enabling structured, domain-aware memory organization with improved categorization accuracy<br>* Default Model Configuration: Emotion analysis, reflection, and memory extraction modules now default to the space-level model, ensuring consistent behavior out of the box<br>* Intelligent Model Fallback: If configured emotion or reflection models are empty or unavailable, the system automatically falls back to the space default model — preventing silent failures<br>* Memory Config Fallback for Models: When any memory-configured model is empty or unavailable, the system gracefully degrades to the space default model",
        "5. Performance & Scalability ⚡<br>* Model Concurrency (model_api_keys): Support for concurrent model API key management, enabling parallel model invocations and improved throughput for high-load scenarios",
        "6. Robustness & Bug Fixes 🔧<br>* Memory Config Version Pinning: Fixed an issue where user memory configurations were not pinned to application release versions, causing inconsistent behavior across deployments<br>* Space Default Memory Protection: Space-level default memory configurations are now protected from deletion; user-level configurations remain deletable<br>* Agent & Workflow Config Fallback: Resolved edge cases in Agent and Workflow nodes where memory config could be empty or selected but unconfigured — comprehensive fallback handling now prevents runtime errors<br>* Implicit Memory Field Rename: Corrected user_id to end_user_id in JSON responses from implicit memory interfaces, aligning with the canonical data model<br>* Memory Config ID Migration: Renamed memory_content to memory_config_id in Agent and Workflow memory configurations for API consistency<br>* Worker-Memory Alerts: Resolved warning-level alerts in the worker-memory service, improving operational monitoring clarity<br>* Bilingual Interface Fixes: Fixed Chinese/English language inconsistencies across memory-related API interfaces<br>* EndUser Memory Config Auto-Backfill (New Users): When a newly created EndUser has memory_config_id as None, the system automatically fetches the latest release's memory_config_id and backfills it<br>* EndUser Memory Config Auto-Backfill (Existing Users): For existing EndUsers with memory_config_id as None, the system similarly retrieves and backfills from the latest release — ensuring backward compatibility without manual migration",
        "<br>",
        "Memory Bear v0.2.4 advances toward production-grade resilience, with the Skills framework and multimodal support opening a new chapter for the cognitive platform.",
        "MemoryBear — Wisdom Reaching Far, gracefully handling real-world variability. 🐻✨"
      ]
    }
  },
  "v0.2.3": {
    "introduction": {
      "codeName": "归墟",
      "releaseDate": "2026-2-6",
      "upgradePosition": "🐻 稳定性与细节打磨版本，万流归墟，静水流深",
      "coreUpgrades": [
        "1. 智能与记忆 🧠<br>* 提示词工程模块：新增专用提示词工程能力<br>* 长短期记忆整合：增强短期与长期记忆生命周期管理<br>* 双语记忆支持：解决情景记忆、显性记忆的双语问题",
        "2. 系统架构 ⚙️<br>* 反思任务调度器：新增 worker-periodic 容器<br>* 模型配置降级：记忆管理正确降级使用空间模型",
        "3. 问题修复 🔧<br>* 工作流分享：修复多轮对话产生多个conversation<br>* 流式输出：修复chat结尾缺少end标记<br>* 实体详情：移除未知类型记忆<br>* 提示词模板路径：修复jinja2路径解析错误<br>* 知识库字段：strategy更名为retrieve_type<br>* 空间头像：优化频繁调用模型接口<br>* 记忆仪表盘：修复end_users接口无返回",
        "<br>",
        "v0.2.4 将继续完善工作流代码执行功能，并推出本体工程+记忆配置入口。",
        "记忆熊，记得更牢，用得更好。🐻✨"
      ]
    },
    "introduction_en": {
      "codeName": "Settle",
      "releaseDate": "2026-2-6",
      "upgradePosition": "🐻 Stability and refinement release — still waters run deep",
      "coreUpgrades": [
        "1. Intelligence & Memory 🧠<br>* Prompt Engineering Module: New dedicated prompt engineering capabilities<br>* Long-term & Short-term Memory Integration: Enhanced memory lifecycle management<br>* Bilingual Memory Support: Resolved dual-language issues in episodic and explicit memory",
        "2. System Architecture ⚙️<br>* Reflection Task Worker: Added worker-periodic container for scheduled tasks<br>* Model Configuration Fallback: Memory management properly falls back to workspace model",
        "3. Bug Fixes 🔧<br>* Workflow Sharing: Fixed multiple conversations created during multi-turn dialogues<br>* Streaming Output: Resolved missing end marker in chat streaming<br>* Entity Details: Removed unknown type memories from All view<br>* Prompt Template Paths: Fixed jinja2 path resolution errors<br>* Knowledge Base Schema: Renamed strategy to retrieve_type<br>* Workspace Avatar: Optimized frequent model API calls<br>* Memory Dashboard: Fixed end_users endpoint empty responses",
        "<br>",
        "v0.2.4 will continue with workflow code execution enhancements and the ontology engineering + memory configuration portal.",
        "MemoryBear — remember better, work smarter. 🐻✨"
      ]
    }
  },
  "v0.2.2": {
    "introduction": {
      "codeName": "淬锋（Temper）",
      "releaseDate": "2026-1-31",
      "upgradePosition": "本次发布聚焦平台稳定性和性能优化。正如\"淬锋\"之名——千锤百炼，淬火成锋，我们通过严格测试和修复打磨系统品质。引入 Agent 工作流的代码执行能力、改进模型并发管理，并修复了记忆系统的多个关键问题。",
      "coreUpgrades": [
        "1. Agent平台增强<br>* 模型并发管理：优化模型广场的并发请求处理和资源分配能力。",
        "2. 记忆系统优化<br>* Celery 队列修复：解决任务队列问题，提升异步记忆处理的可靠性<br>* 记忆 Agent 优化：提升记忆 Agent 的性能和效率<br>* 接口响应速度优化：优化记忆接口响应时间，加快操作速度。",
        "3. 情绪记忆与识别升级<br>* 情绪记忆角色识别修复：解决情绪记忆上下文中的角色/人物识别问题<br>* 角色识别增强：提升对话记忆中的角色/人物识别准确性。",
        "<br>",
        "MemoryBear 持续致力于为 AI 应用提供类人记忆能力。本次以稳定性为核心的发布，进一步夯实了「感知→精炼→关联→遗忘」范式的基础。",
        "未来版本将在此坚实基础上，扩展 Agent 能力并深化记忆智能特性。"
      ]
    },
    "introduction_en": {
      "codeName": "Temper (淬锋)",
      "releaseDate": "2026-1-31",
      "upgradePosition": "This release focuses on platform stability and performance optimization — true to its codename \"淬锋\" (tempered blade), we've refined the system through rigorous testing and fixes. Introducing Python code execution for Agent workflows, improved model concurrency management, and critical fixes across the memory system.",
      "coreUpgrades": [
        "1. Agent Platform Enhancements<br>* Model Concurrency Management: Enhanced Model Plaza with improved concurrent model request handling and resource allocation.",
        "2. Memory System Improvements<br>* Celery Queue Fix: Resolved task queue issues for more reliable asynchronous memory processing<br>* Memory Agent Optimization: Improved memory Agent performance and efficiency<br>* API Response Speed: Optimized memory interface response times for faster operations.",
        "3. Emotional Memory & Recognition Upgrades<br>* Emotion Memory Role Recognition Fix: Resolved issues with role/character identification in emotional memory contexts<br>* Role Recognition Enhancement: Improved character/role identification accuracy in conversation memory.",
        "<br>",
        "MemoryBear continues advancing toward human-like memory capabilities for AI applications. This stability-focused release strengthens the foundation for our Perception → Refinement → Association → Forgetting paradigm.",
        "Future releases will build on this solid base with expanded Agent capabilities and deeper memory intelligence features."
      ]
    }
  },
  "v0.2.1": {
    "introduction": {
      "codeName": "启知",
      "releaseDate": "2026-1-23",
      "upgradePosition": "\uD83D\uDC3B 本次更新主要优化使用体验和修复已知问题，让系统更稳定、更好用。",
      "coreUpgrades": [
        "1. 工作流更好用了<br>* 界面更清晰，一眼看懂怎么配置<br>* 新增节点输出变量展示，方便其他节点引用<br>* 修复了几个影响体验的bug",
        "2. 智能体配置更简单<br>* 提示词和变量联动更顺畅<br>* 配置界面重新整理，找功能更方便",
        "3. 记忆系统更稳定<br>* 优化了情绪记忆和隐性记忆的缓存更新<br>* 修复了记忆配置页面的报错问题<br>* 现在能自动识别用户和AI的身份了",
        "4. 知识库体验提升<br>* 修复了文档解析异常的问题<br>* 上传文档时能看到处理进度了<br>* 取消了操作也不会报错了",
        "5. 系统整体更可靠<br>* 修复了新用户访问跳转问题<br>* 流式接口更稳定，长对话不断线<br>* 调整了菜单顺序，操作更顺手",
        "<br>",
        "这次更新虽然不大，但让记忆熊的基础更扎实、体验更流畅。我们继续努力，让AI记忆更好用！",
        "记忆熊，记得更牢，用得更好。\uD83D\uDC3B✨"
      ]
    },
    "introduction_en": {
      "codeName": "Qizhi",
      "releaseDate": "2026-1-23",
      "upgradePosition": "\uD83D\uDC3B This update focuses on improving usability and fixing known issues, making the system more stable and easier to use overall.",
      "coreUpgrades": [
        "1. Improved Workflow Experience<br>* Cleaner, more intuitive UI for easier configuration at a glance<br>* Added visibility of node output variables, making them easier to reference in downstream nodes<br>* Fixed several usability-related bugs that affected the workflow experience",
        "2. Simpler Agent Configuration<br>* Smoother linkage between prompts and variables<br>* Reorganized configuration layout for easier navigation and better clarity",
        "3. More Stable Memory System<br>* Optimized cache refresh for emotional memory and implicit memory<br>* Fixed error issues on the memory configuration page<br>* The system can now automatically distinguish between user and AI roles",
        "4. Enhanced Knowledge Base Experience<br>* Fixed issues with document parsing failures<br>* Upload progress is now displayed during document processing<br>* Canceling an upload no longer triggers errors",
        "5. Overall System Reliability Improvements<br>* Fixed redirect issues affecting new users<br>* Improved stability of streaming APIs to prevent interruptions during long conversations<br>* Adjusted menu ordering for a smoother and more intuitive workflow",
        "<br>",
        "Although this is a relatively small update, it strengthens MemoryBear’s foundation and delivers a noticeably smoother experience. We’ll keep refining the system to make AI memory more powerful and easier to use.",
        "MemoryBear — remember better, work smarter. \uD83D\uDC3B✨"
      ]
    }
  },
  "v0.2.0": {
    "introduction": {
      "codeName": "启知",
      "releaseDate": "2026-1-16",
      "upgradePosition": "本次为架构升级，核心目标是把\"被动存储\"升级为\"主动认知\"，让系统具备情绪感知、情景理解与类人记忆机制，为后续多智能体协作与专业场景落地奠定底座。",
      "coreUpgrades": [
        "1. 记忆详情：拟人记忆——情绪引擎、情景记忆、短期记忆、工作记忆、感知记忆、显性记忆、隐性记忆，并配套类脑遗忘机制，实现从感知→情绪→情景→长期沉淀的完整人类记忆闭环",
        "2. 可视化工作流：拖拽式节点编排（LLM、知识库、逻辑、工具），业务落地周期由天缩至小时。",
        "3. 多模态知识处理：PDF、PPT、MP3、MP4 一键解析，时间感知检索准确率 94.3%，问答对数据即插即用。",
        "4. Agent集群内置\"记忆-知识-工具-审核\"四类角色模板，用户一键生成；主控Agent把复杂任务拆为子任务并行分发，再靠情景记忆统一消解冲突、校验一致性，输出完整报告。"
      ]
    },
    "introduction_en": {
      "codeName": "Qizhi",
      "releaseDate": "2026-1-16",
      "upgradePosition": "This release marks a foundational upgrade to the system’s cognitive architecture. The core objective is to evolve the platform from passive information storage into active cognitive intelligence—enabling emotional awareness, situational understanding, and human-like memory mechanisms. This upgrade lays the groundwork for future multi-agent collaboration and domain-specific, production-grade AI applications.",
      "coreUpgrades": [
        "1. Human-Like Memory Architecture: A comprehensive, human-inspired memory system is introduced, encompassing emotional processing, situational memory, short-term and working memory, perceptual memory, as well as explicit and implicit memory. Combined with brain-inspired forgetting mechanisms, the system now supports a complete cognitive loop—from perception → emotion → context → long-term consolidation, closely mirroring human memory formation.",
        "2. Visual Workflow Orchestration: A fully visual, drag-and-drop workflow enables modular composition of LLMs, knowledge bases, logic, and tools. This dramatically reduces the time required to move from experimentation to production—from days to hours.",
        "3. Multimodal Knowledge Processing: The system now supports one-click parsing and ingestion of PDF, PPT, MP3, and MP4 content. With time-aware retrieval accuracy reaching 94.3%, structured Q&A data becomes instantly usable for downstream reasoning and generation.",
        "4. Built-in Agent Clusters: Predefined role templates across four categories—Memory, Knowledge, Tools, and Review—can be generated with a single click. A Coordinator Agent decomposes complex tasks into parallel subtasks, while situational memory is used to resolve conflicts, validate consistency, and synthesize outputs into a coherent, end-to-end report."
      ]
    }
  },
  "v0.1.0": {
    "introduction": {
      "codeName": "初心",
      "releaseDate": "2025-12-01",
      "upgradePosition": "这是一款专注于管理和利用AI记忆的工具，支持RAG和知识图谱两种主流存储方式，旨在为AI应用提供持久化、结构化的\"记忆\"能力。",
      "coreUpgrades": [
        "1. 记忆空间：用户可以创建独立的空间来隔离不同记忆，并灵活选择存储方式。",
        "2. 记忆配置：简化了配置流程，内置自动提取关键信息的\"记忆萃取\"和管理生命周期的\"遗忘\"引擎。",
        "3. 知识检索：提供语义、分词和混合三种检索模式，并支持多种参数微调和结果重排序，以提升召回效果。",
        "4. 全局管理：支持统一设置默认检索参数，并可一键应用到所有知识库。",
        "5. 测试与调试：内置\"召回测试\"功能，方便用户实时验证检索效果并调整参数，支持通过分享码与他人协作。",
        "6. 记忆洞察：可查看详细的对话记录、用户画像和分析报告，帮助理解AI的\"记忆\"内容。",
        "7. 集成与管理：提供API Key用于系统集成，并包含基本的用户管理功能。",
        "8. 界面与体验：采用现代化的卡片式布局和渐变色设计，注重交互的流畅性和视觉美感。",
        "9. 起步与使用：文档中提供了清晰的基础使用流程，引导用户从创建空间、配置记忆到测试检索快速上手。",
        "10. 版本说明与限制: 记忆熊 v0.1.0 版本\"初心\"囊括智能记忆管理的核心思路和基础能力，为后续开发奠定了基础。",
        "<br>",
        "文档资源：用户手册、API文档、FAQ",
        "问题反馈：GitHub Issues、邮件支持",
        "致谢：感谢所有参与测试和提供反馈的用户！"
      ]
    },
    "introduction_en": {
      "codeName": "Original Intent",
      "releaseDate": "2025-12-01",
      "upgradePosition": "A tool focused on managing and utilizing AI memory, supporting both RAG and knowledge graph storage methods, aiming to provide persistent and structured 'memory' capabilities for AI applications.",
      "coreUpgrades": [
        "1. Memory Space: Users can create independent spaces to isolate different memories and flexibly choose storage methods.",
        "2. Memory Configuration: Simplified configuration process with built-in 'memory extraction' for automatic key information extraction and 'forgetting' engine for lifecycle management.",
        "3. Knowledge Retrieval: Provides semantic, tokenization, and hybrid retrieval modes with various parameter tuning and result reranking to improve recall.",
        "4. Global Management: Supports unified default retrieval parameter settings with one-click application to all knowledge bases.",
        "5. Testing & Debugging: Built-in 'recall testing' for real-time verification of retrieval effects and parameter adjustment, with sharing code support for collaboration.",
        "6. Memory Insights: View detailed conversation records, user profiles, and analysis reports to understand AI 'memory' content.",
        "7. Integration & Management: Provides API Key for system integration with basic user management features.",
        "8. Interface & Experience: Modern card-based layout with gradient design, focusing on interaction fluidity and visual aesthetics.",
        "9. Getting Started: Documentation provides clear basic usage flow, guiding users from creating spaces, configuring memory to testing retrieval.",
        "10. Version Notes: MemoryBear v0.1.0 'Original Intent' encompasses core concepts and basic capabilities of intelligent memory management, laying foundation for future development.",
        "<br>",
        "Documentation: User Manual, API Documentation, FAQ",
        "Feedback: GitHub Issues, Email Support",
        "Acknowledgments: Thanks to all users who participated in testing and provided feedback!"
      ]
    }
  }
}