diff --git a/CHANGELOG.md b/CHANGELOG.md
index 82f4caaa..8a30a42a 100644
--- a/CHANGELOG.md
+++ b/CHANGELOG.md
@@ -2,6 +2,61 @@
All notable changes to this project will be documented in this file.
+## [0.3.6] - 2026-04-03
+
+### 🚀 New Features
+- **NEW**: ASR (Automatic Speech Recognition) — integrated ASR model support with audio file upload, in-document audio preview, and transcription capabilities; added ASR model connectivity check endpoint
+- **NEW**: Data Source Auto-Sync (Feishu) — complete data source management with CRUD operations, Feishu Wiki/Drive auto-sync (incremental and full), sync logs with polling, tenant isolation, and data source type icons
+- **NEW**: OIDC Authentication — OpenID Connect (OIDC) login support with auto-discovery, custom endpoint configuration, and user info field mapping
+- **NEW**: IM Quote/Reply Context — extract quoted messages in IM channels (WeCom) and inject QuotedContext into LLM prompts for contextual replies; anti-hallucination handling for non-text quotes and unprocessable media
+- **NEW**: Thread-Based IM Sessions — per-thread session mode for IM channels (Slack, Mattermost, Feishu, Telegram), enabling multi-user collaboration within message threads
+- **NEW**: Document Summarization — AI-generated document summaries with configurable max_input_chars, dedicated summary section in document detail view with loading states
+- **NEW**: Tavily Web Search Provider — added Tavily as a web search provider option; refactored web search provider architecture for extensibility
+- **NEW**: MCP Auto-Reconnection — automatic reconnection logic for MCP tool calls and tool listing when server connection is lost
+- **NEW**: Parallel Tool Calling — concurrent execution of multiple tool calls in agent mode via errgroup when ParallelToolCalls is enabled; sequential execution remains default
+- **NEW**: Agent @Mention Scope Restriction — restrict user @mentions to agent's allowed knowledge base scope, preventing unauthorized access to knowledge bases and knowledge entries
+
+### ⚡ Improvements
+- Refined parent-child chunk replacement logic to only apply to text chunks whose parent is a parent_text chunk
+- Optimized login page rendering performance: removed all backdrop-filter blur, reduced animated elements, added GPU compositing hints and prefers-reduced-motion support
+- Unified NVIDIA API for both chat and VLM model types
+- Prompt language fallback now uses WEKNORA_LANGUAGE environment variable instead of hardcoded zh-CN, with language propagated through document and image processing pipelines
+- Fixed enable_thinking for Aliyun Qwen models in streaming mode
+- Enhanced document processing with metadata extraction and handling
+- Added header tracking for Markdown tables during chunking to preserve table context
+- Elasticsearch ID field handling with dynamic .keyword suffix detection based on index mapping
+- Added DOCREADER_DOCX_MAX_PAGES environment variable to limit DOCX parsing for large documents
+- Knowledge tag batch update now includes authorization checks with agent-scoped KB access validation
+- System proxy support for remote API calls
+- DatabaseQueryTool enhanced with search scope filtering
+
+### 🐛 Bug Fixes
+- Fixed WeCom group chat @mention not being stripped from message text, causing all slash commands to fail
+- Fixed SSEReader returning errors.New("EOF") instead of io.EOF, causing silent stream termination without done response
+- Fixed extracted images not being deleted from storage when knowledge is removed, preventing orphan file accumulation
+- Fixed S3 provider scheme not recognized in frontend/backend allowlists; added auto path-style addressing for non-AWS S3-compatible endpoints
+- Fixed remote images in markdown files not being resolved during file upload (only base64/inline were handled)
+- Fixed SSRF validation lacking IPv6 support; added IPv6 address and CIDR handling in whitelist mechanism
+- Fixed web_fetch using removed IsSSRFSafeURL function; replaced with ValidateURLForSSRF
+- Fixed mermaid diagrams not rendering on page refresh
+- Fixed doc-content.vue renderer incompatible with marked v5+ token API
+- Fixed null reference error when rendering empty markdown code blocks
+- Fixed frontend using legacy storage_config instead of storage_provider_config, causing incorrect storage provider display
+- Fixed knowledge document category not deselectable by clicking again
+- Fixed duplicate click binding in frontend components
+- Fixed migration numbering errors and removed broken update_updated_at_column trigger
+- Fixed monkey patch for docx parse error handling
+
+### 📚 Documentation
+- Enhanced agent and knowledge base API documentation
+- Added data source import documentation with architecture overview and quick start guide
+- Updated README files with streamlined sections and feature overview across all languages
+- Updated architecture diagram
+
+### 🔧 Refactoring
+- Improved question generation prompt template with better guidelines and context handling
+- Simplified temperature option handling in chat request builders
+
## [0.3.5] - 2026-03-27
### 🚀 New Features
@@ -792,6 +847,7 @@ All notable changes to this project will be documented in this file.
- Docker Compose for quick startup and service orchestration.
- MCP server support for integrating with MCP-compatible clients.
+[0.3.6]: https://github.com/Tencent/WeKnora/tree/v0.3.6
[0.3.5]: https://github.com/Tencent/WeKnora/tree/v0.3.5
[0.3.4]: https://github.com/Tencent/WeKnora/tree/v0.3.4
[0.3.3]: https://github.com/Tencent/WeKnora/tree/v0.3.3
diff --git a/README.md b/README.md
index 64b325a6..e42816b3 100644
--- a/README.md
+++ b/README.md
@@ -22,7 +22,7 @@
-
+
@@ -52,6 +52,20 @@ The framework supports auto-syncing knowledge from Feishu (more data sources com
## ✨ Latest Updates
+**v0.3.6 Highlights:**
+
+- **ASR (Automatic Speech Recognition)**: Integrated ASR model support with audio file upload, in-document audio preview, and transcription capabilities
+- **Data Source Auto-Sync (Feishu)**: Complete data source management with Feishu Wiki/Drive auto-sync, incremental and full sync, sync logs, and tenant isolation
+- **OIDC Authentication**: OpenID Connect login support with auto-discovery, custom endpoints, and user info mapping
+- **IM Quote/Reply Context**: Quoted messages extracted in IM channels and injected into LLM prompts for contextual replies; anti-hallucination for non-text quotes
+- **Thread-Based IM Sessions**: Per-thread session mode for IM channels (Slack, Mattermost, Feishu, Telegram), enabling multi-user collaboration within threads
+- **Document Summarization**: AI-generated document summaries with configurable input limits and a dedicated summary section in document detail view
+- **Tavily Web Search**: Added Tavily as a web search provider; refactored web search provider architecture for extensibility
+- **MCP Auto-Reconnection**: Automatic reconnection for MCP tool calls when server connection is lost
+- **Parallel Tool Calling**: Concurrent execution of multiple agent tool calls via errgroup for faster complex task handling
+- **Agent @Mention Scope Restriction**: User @mentions restricted to agent's allowed knowledge base scope, preventing unauthorized access
+- **Login Page Performance**: Removed all backdrop-filter blur effects, reduced animations, added GPU compositing hints for faster page load
+
**v0.3.5 Highlights:**
- **Telegram, DingTalk & Mattermost IM Integration**: Added Telegram bot (webhook/long-polling, streaming via editMessageText), DingTalk bot (webhook/Stream mode, AI Card streaming), and Mattermost adapter; IM channel coverage now includes WeCom, Feishu, Slack, Telegram, DingTalk, and Mattermost
@@ -63,6 +77,9 @@ The framework supports auto-syncing knowledge from Feishu (more data sources com
- **Channel Tracking**: Knowledge entries and messages record source channel (web/api/im/browser_extension) for traceability
- **Bug Fixes**: Fixed agent empty response when no knowledge base is configured, UTF-8 truncation in summaries for Chinese/emoji documents, API key encryption loss on tenant settings update, vLLM streaming reasoning content propagation, and rerank empty passage errors
+
+Earlier Releases
+
**v0.3.4 Highlights:**
- **IM Bot Integration**: WeCom, Feishu, and Slack IM channel support with WebSocket/Webhook modes, streaming, and knowledge base integration
@@ -76,9 +93,6 @@ The framework supports auto-syncing knowledge from Feishu (more data sources com
- **Hybrid Search Optimization**: Grouped targets and reused query embeddings for better retrieval performance
- **Final Answer Tool**: New final_answer tool with agent duration tracking for improved agent workflows
-
-Earlier Releases
-
**v0.3.3 Highlights:**
- **Parent-Child Chunking**: Hierarchical parent-child chunking strategy for enhanced context management and more accurate retrieval
diff --git a/README_CN.md b/README_CN.md
index 96f9341b..61900914 100644
--- a/README_CN.md
+++ b/README_CN.md
@@ -22,7 +22,7 @@
-
+
@@ -52,6 +52,20 @@ WeKnora 提供**快速问答**与**智能推理**两种问答模式。快速问
## ✨ 最新更新
+**v0.3.6 版本亮点:**
+
+- **ASR 语音识别**:集成 ASR 模型,支持音频文件上传、文档内音频预览和语音转写能力
+- **数据源自动同步(飞书)**:完整的数据源管理功能,支持飞书 Wiki/云文档自动同步(增量/全量),同步日志与租户隔离
+- **OIDC 统一认证**:支持 OpenID Connect 登录,自动发现端点、自定义端点配置及用户信息字段映射
+- **IM 引用回复上下文**:IM 频道中提取引用消息并注入 LLM 提示词,实现上下文关联回复;非文本引用防幻觉处理
+- **IM 线程会话模式**:IM 频道支持按线程维度独立会话(Slack、Mattermost、飞书、Telegram),线程内多用户协作
+- **文档自动摘要**:AI 生成文档摘要,可配置最大输入长度,文档详情页展示专属摘要区域
+- **Tavily 网页搜索**:新增 Tavily 搜索引擎;重构 Web Search Provider 架构,提升可扩展性
+- **MCP 自动重连**:MCP 工具调用断线自动重连
+- **并行工具调用**:Agent 模式支持通过 errgroup 并发执行多个工具调用,加速复杂任务处理
+- **Agent @提及范围限制**:用户 @提及限制在 Agent 授权的知识库范围内,防止越权访问
+- **登录页性能优化**:移除全部 backdrop-filter blur,精简动画元素,新增 GPU 合成加速提示
+
**v0.3.5 版本亮点:**
- **Telegram、钉钉 & Mattermost IM集成**:新增Telegram机器人(webhook/长轮询,流式editMessageText回复)、钉钉机器人(webhook/Stream模式,AI卡片流式输出)和Mattermost适配器;IM频道现已覆盖企业微信、飞书、Slack、Telegram、钉钉、Mattermost共6个平台
@@ -63,6 +77,9 @@ WeKnora 提供**快速问答**与**智能推理**两种问答模式。快速问
- **来源频道标记**:知识条目和消息新增channel字段,记录来源(web/api/im/browser_extension),便于追溯
- **重要修复**:修复无知识库时Agent空响应、中文/emoji文档摘要UTF-8截断、租户设置更新时API密钥加密丢失、vLLM流式推理内容缺失、Rerank空段落过滤等问题
+
+更早版本
+
**v0.3.4 版本亮点:**
- **IM机器人集成**:支持企业微信、飞书、Slack IM频道,WebSocket/Webhook双模式,流式回复与知识库集成
@@ -76,9 +93,6 @@ WeKnora 提供**快速问答**与**智能推理**两种问答模式。快速问
- **混合检索优化**:按目标分组并复用查询向量,提升检索性能
- **Final Answer工具**:新增final_answer工具及Agent耗时跟踪,优化Agent工作流
-
-更早版本
-
**v0.3.3 版本亮点:**
- **父子分块策略**:层级化的父子分块策略,增强上下文管理和检索精度
diff --git a/README_JA.md b/README_JA.md
index 1aa50e85..875a8e2a 100644
--- a/README_JA.md
+++ b/README_JA.md
@@ -22,7 +22,7 @@
-
+
@@ -52,6 +52,20 @@ Feishuなどの外部プラットフォームからのナレッジ自動同期
## ✨ 最新アップデート
+**v0.3.6 バージョンのハイライト:**
+
+- **ASR(自動音声認識)**:ASRモデルを統合し、音声ファイルのアップロード、ドキュメント内音声プレビュー、音声文字起こし機能をサポート
+- **データソース自動同期(Feishu)**:完全なデータソース管理機能、Feishu Wiki/ドライブの自動同期(増分/全量)、同期ログ、テナント分離
+- **OIDC認証**:OpenID Connectログインをサポート、自動ディスカバリ、カスタムエンドポイント設定、ユーザー情報マッピング
+- **IM引用返信コンテキスト**:IMチャネルで引用メッセージを抽出してLLMプロンプトに注入し、文脈に基づく回答を実現。非テキスト引用の幻覚防止処理
+- **IMスレッドベースセッション**:IMチャネル(Slack、Mattermost、Feishu、Telegram)でスレッド単位のセッションモードをサポート、スレッド内でのマルチユーザーコラボレーション
+- **ドキュメント自動要約**:AI生成のドキュメント要約、入力サイズの設定が可能、ドキュメント詳細画面に専用の要約セクション
+- **Tavily Web検索**:Tavilyを新しいWeb検索プロバイダーとして追加、Web検索プロバイダーアーキテクチャを拡張性向上のためリファクタリング
+- **MCP自動再接続**:サーバー接続断絶時のMCPツール呼び出しの自動再接続ロジック
+- **並列ツール呼び出し**:Agentモードでerrgroupを使用して複数のツール呼び出しを並行実行、複雑なタスク処理を高速化
+- **Agent @メンション範囲制限**:ユーザーの@メンションをAgentが許可されたナレッジベースの範囲内に制限、不正アクセスを防止
+- **ログインページパフォーマンス**:backdrop-filter blurをすべて削除、アニメーション要素を削減、GPUコンポジティングヒントを追加
+
**v0.3.5 バージョンのハイライト:**
- **Telegram、DingTalk & Mattermost IM統合**:Telegramボット(webhook/ロングポーリング、editMessageTextストリーミング)、DingTalkボット(webhook/Streamモード、AIカードストリーミング)、Mattermost アダプターを新規追加。IMチャネルはWeChat Work、Feishu、Slack、Telegram、DingTalk、Mattermost の6プラットフォームをカバー
@@ -63,6 +77,9 @@ Feishuなどの外部プラットフォームからのナレッジ自動同期
- **チャネルトラッキング**:ナレッジエントリとメッセージにchannelフィールド追加(web/api/im/browser_extension)
- **重要バグ修正**:ナレッジベース未設定時のAgent空レスポンス、中国語/絵文字ドキュメントのUTF-8切り詰め、テナント設定更新時のAPIキー暗号化消失、vLLMストリーミング推論コンテンツ欠落、Rerankの空パッセージエラーを修正
+
+過去のリリース
+
**v0.3.4 バージョンのハイライト:**
- **IMボット統合**:企業WeChat、Feishu、SlackのIMチャネルをサポート、WebSocket/Webhookモード、ストリーミング対応、ナレッジベース統合
@@ -76,9 +93,6 @@ Feishuなどの外部プラットフォームからのナレッジ自動同期
- **ハイブリッド検索最適化**:ターゲットのグループ化とクエリ埋め込みの再利用で検索性能を向上
- **Final Answerツール**:新しいfinal_answerツールとAgentの所要時間追跡でワークフローを改善
-
-過去のリリース
-
**v0.3.3 バージョンのハイライト:**
- **親子チャンキング**:階層型の親子チャンキング戦略により、コンテキスト管理と検索精度を強化
diff --git a/README_KO.md b/README_KO.md
index b99024c6..e7a8b612 100644
--- a/README_KO.md
+++ b/README_KO.md
@@ -22,7 +22,7 @@
-
+
@@ -52,6 +52,20 @@ Feishu 등 외부 플랫폼에서 지식 자동 동기화를 지원하며(추가
## ✨ 최신 업데이트
+**v0.3.6 하이라이트:**
+
+- **ASR(자동 음성 인식)**: ASR 모델 통합으로 오디오 파일 업로드, 문서 내 오디오 미리보기, 음성 전사 기능 지원
+- **데이터 소스 자동 동기화(Feishu)**: 완전한 데이터 소스 관리 기능, Feishu Wiki/드라이브 자동 동기화(증분/전체), 동기화 로그 및 테넌트 격리
+- **OIDC 인증**: OpenID Connect 로그인 지원, 자동 디스커버리, 커스텀 엔드포인트 설정, 사용자 정보 매핑
+- **IM 인용 답장 컨텍스트**: IM 채널에서 인용 메시지를 추출해 LLM 프롬프트에 주입하여 맥락 기반 답변 실현; 비텍스트 인용의 환각 방지 처리
+- **IM 스레드 기반 세션**: IM 채널(Slack, Mattermost, Feishu, Telegram)에서 스레드 단위 세션 모드를 지원, 스레드 내 다중 사용자 협업
+- **문서 자동 요약**: AI 생성 문서 요약, 최대 입력 크기 설정 가능, 문서 상세 페이지에 전용 요약 섹션
+- **Tavily 웹 검색**: Tavily를 새로운 웹 검색 프로바이더로 추가; 웹 검색 프로바이더 아키텍처를 확장성 향상을 위해 리팩토링
+- **MCP 자동 재연결**: 서버 연결 끊김 시 MCP 도구 호출 자동 재연결 로직
+- **병렬 도구 호출**: Agent 모드에서 errgroup을 사용한 다중 도구 호출 병렬 실행으로 복잡한 작업 처리 속도 향상
+- **Agent @멘션 범위 제한**: 사용자 @멘션을 Agent 허용 지식베이스 범위로 제한하여 무단 접근 방지
+- **로그인 페이지 성능**: backdrop-filter blur 전체 제거, 애니메이션 요소 축소, GPU 합성 힌트 추가
+
**v0.3.5 하이라이트:**
- **Telegram, DingTalk & Mattermost IM 통합**: Telegram 봇(webhook/롱폴링, editMessageText 스트리밍), DingTalk 봇(webhook/Stream 모드, AI 카드 스트리밍), Mattermost 어댑터를 신규 추가. IM 채널이 기업WeChat, Feishu, Slack, Telegram, DingTalk, Mattermost 6개 플랫폼으로 확대
@@ -63,6 +77,9 @@ Feishu 등 외부 플랫폼에서 지식 자동 동기화를 지원하며(추가
- **채널 추적**: 지식 항목과 메시지에 channel 필드 추가(web/api/im/browser_extension)로 출처 추적 가능
- **주요 버그 수정**: 지식베이스 미설정 시 Agent 빈 응답, 한국어/이모지 문서 요약의 UTF-8 잘림, 테넌트 설정 업데이트 시 API 키 암호화 손실, vLLM 스트리밍 추론 콘텐츠 누락, Rerank 빈 패시지 오류 수정
+
+이전 릴리스
+
**v0.3.4 하이라이트:**
- **IM 봇 통합**: 기업WeChat, Feishu, Slack IM 채널 지원, WebSocket/Webhook 모드, 스트리밍 및 지식베이스 통합
@@ -76,9 +93,6 @@ Feishu 등 외부 플랫폼에서 지식 자동 동기화를 지원하며(추가
- **하이브리드 검색 최적화**: 타겟 그룹화 및 쿼리 임베딩 재사용으로 검색 성능 향상
- **Final Answer 도구**: 새로운 final_answer 도구 및 Agent 소요 시간 추적으로 워크플로우 개선
-
-이전 릴리스
-
**v0.3.3 하이라이트:**
- **부모-자식 청킹**: 계층적 부모-자식 청킹 전략으로 컨텍스트 관리 및 검색 정확도 강화
diff --git a/VERSION b/VERSION
index c2c0004f..449d7e73 100644
--- a/VERSION
+++ b/VERSION
@@ -1 +1 @@
-0.3.5
+0.3.6
diff --git a/frontend/package.json b/frontend/package.json
index 1d4dfdf8..db93c78c 100644
--- a/frontend/package.json
+++ b/frontend/package.json
@@ -1,6 +1,6 @@
{
"name": "knowledage-base",
- "version": "0.3.4",
+ "version": "0.3.6",
"private": true,
"type": "module",
"scripts": {
diff --git a/helm/Chart.yaml b/helm/Chart.yaml
index 600dfd01..4152371f 100644
--- a/helm/Chart.yaml
+++ b/helm/Chart.yaml
@@ -5,7 +5,7 @@ description: |
with document parsing, vector search, and LLM integration.
type: application
version: 0.1.0
-appVersion: "v0.3.5"
+appVersion: "v0.3.6"
kubeVersion: ">=1.25.0-0"
home: https://github.com/Tencent/WeKnora
icon: https://raw.githubusercontent.com/Tencent/WeKnora/main/docs/images/logo.png