From 0a3acf446d5f86a3f41381cb4926183e4e6a8275 Mon Sep 17 00:00:00 2001
From: Timebomb2018 <18868801967@163.com>
Date: Sat, 7 Mar 2026 04:19:35 +0200
Subject: [PATCH] fix(version): Version 0.2.6 Release Notes
---
api/app/version_info.json | 32 ++++++++++++++++++++++++++++++++
1 file changed, 32 insertions(+)
diff --git a/api/app/version_info.json b/api/app/version_info.json
index 7d82eabc..bbaffc17 100644
--- a/api/app/version_info.json
+++ b/api/app/version_info.json
@@ -1,4 +1,36 @@
{
+ "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
* 工作流导入适配（Dify）：支持 Dify 工作流定义无缝迁移
* 字段字数限制与校验规则：可配置字符限制与产品级校验
* 应用复制（Agent、工作流、集群）：一键复制完整应用配置
* 对话变量（调试+分享）：支持有状态多轮交互
* 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 💬
* 音频输入与输出：应用支持音频模态
* 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 🧠
* 模型视觉与 Omni 区分：精确区分视觉与 Omni 模型能力
* 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
* 本体配置默认标识：支持基线配置标记
* 记忆配置默认标识：自动应用默认记忆设置",
+ "4. 记忆智能 🔬
* 记忆剪枝模块：智能裁剪冗余低价值记忆
* 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 🔧
* 模型管理：修复自定义模型 API Key 批量配置错误
* 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
* 用户记忆：优化档案提取准确性（姓名、职业、兴趣分布）
* 长期记忆：修复情景记忆卡片重复和用户归属错误
* 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
* 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",
+ "
",
+ "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
* Workflow Import Adaptation (Dify): Seamless Dify workflow migration
* Field Character Limits & Validation: Configurable limits with product-defined rules
* Application Cloning (Agent, Workflow, Cluster): One-click full config duplication
* Conversation Variables (Debug + Share): Stateful multi-turn interactions
* Streaming message_id in Chat API: Message tracking in streaming responses",
+ "2. Multimodal & Interaction 💬
* Audio Input & Output: Audio modality support for applications
* File Type Input Support: Voice, file, and video upload support",
+ "3. Model & Intelligence 🧠
* Model Vision & Omni Differentiation: Precise capability routing
* Education Memory & Companion Toy Presets: Domain-specific ontology configs
* Ontology Default Identifier: Baseline configuration flagging
* Memory Configuration Default Identifier: Auto-apply default settings",
+ "4. Memory Intelligence 🔬
* Memory Pruning Module: Intelligent trimming of redundant memories
* RAG Quick Retrieval with Memory: Deep think and normal reply dual-mode retrieval",
+ "5. Robustness & Bug Fixes 🔧
* Model Management: Fixed custom model API key batch configuration error
* Knowledge Base: Fixed download original content API error for non-source documents, updated share disable prompt text
* User Memory: Improved profile extraction accuracy (name, occupation, interests)
* Long-Term Memory: Fixed duplicate episodic memory cards and wrong user attribution
* Dashboard: Fixed data inconsistencies in knowledge count, app count, memory capacity, API calls, and knowledge type distribution
* Infrastructure: Corrected Celery environment variables, fixed database connection pool idle-in-transaction leak",
+ "
",
+ "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",