fix(async-context-compression): resolve race condition, update role to assistant, bump to v1.1.3

chore: update community stats 2026-01-11
docs: add Multi-Model Context Merger to plugin lists in READMEs
2026-01-12 01:45:58 +08:00 · 2026-01-11 17:06:52 +00:00 · 2026-01-12 00:30:55 +08:00 · 2026-01-12 00:30:09 +08:00 · 2026-01-12 00:28:41 +08:00 · 2026-01-12 00:22:22 +08:00
40 changed files with 2034 additions and 1041 deletions
--- a/.github/copilot-instructions.md
+++ b/.github/copilot-instructions.md
@@ -40,7 +40,7 @@ plugins/actions/export_to_docx/
    - 格式: `**Author:** [Fu-Jie](https://github.com/Fu-Jie) | **Version:** x.x.x | **Project:** [Awesome OpenWebUI](https://github.com/Fu-Jie/awesome-openwebui)`
    - **注意**: Author 和 Project 为固定值，仅需更新 Version 版本号
 3.  **描述 (Description)**: 一句话功能介绍
-4.  **最新更新 (What's New)**: **必须**放在描述之后，显著展示最新版本的变更点
+4.  **最新更新 (What's New)**: **必须**放在描述之后，显著展示最新版本的变更点 (仅展示最近 3 次更新)
 5.  **核心特性 (Key Features)**: 使用 Emoji + 粗体标题 + 描述格式
 6.  **使用方法 (How to Use)**: 按步骤说明
 7.  **配置参数 (Configuration/Valves)**: 使用表格格式，包含参数名、默认值、描述
@@ -96,7 +96,7 @@ example code or syntax here

 ### 文档内容要求 (Content Requirements)

- **新增功能**: 必须在 "What's New" 章节中明确列出，使用 Emoji + 粗体标题格式。
+- **新增功能**: 必须在 "What's New" 章节中明确列出，使用 Emoji + 粗体标题格式 (仅保留最近 3 个版本的更新记录)。
 - **双语**: 必须提供 `README.md` (英文) 和 `README_CN.md` (中文)。
 - **表格对齐**: 配置参数表格使用左对齐 `:---`。
 - **Emoji 规范**: 标题使用合适的 Emoji 增强可读性。
--- a/.github/workflows/publish_plugin.yml
+++ b/.github/workflows/publish_plugin.yml
@@ -1,6 +1,11 @@
 name: Publish Plugins to OpenWebUI Market

 on:
+  push:
+    branches:
+      - main
+    paths:
+      - 'plugins/**/*.py'
  release:
    types: [published]
  workflow_dispatch:
--- a/CONTRIBUTING.md
+++ b/CONTRIBUTING.md
@@ -1,87 +1,16 @@
-# 贡献指南 (Contributing Guide)
+# Contributing Guide

-感谢你对 **OpenWebUI Extras** 感兴趣！我们非常欢迎社区贡献更多的插件、提示词和创意。
+Thank you for your interest in **OpenWebUI Extras**!

-## 🤝 如何贡献
+## 🚀 How to Contribute

-### 1. 分享提示词 (Prompts)
+1. **Fork** this repository.
+2. **Add/Modify** the plugin file in the `plugins/` directory.
+3. **Submit PR**: We will review and merge it.

-如果你有一个好用的提示词：
-1. 在 `prompts/` 目录下找到合适的分类（如 `coding/`, `writing/`）。如果没有合适的，可以新建一个文件夹。
-2. 创建一个新的 `.md` 或 `.json` 文件。
-3. 提交 Pull Request (PR)。
+## 💡 Important

-### 2. 开发插件 (Plugins)
+- Ensure your plugin includes complete metadata (title, author, version, description).
+- If updating an existing plugin, please **increment the version number** (e.g., `0.1.0` -> `0.1.1`) to trigger the auto-update.

-如果你开发了一个新的 OpenWebUI 插件 (Function/Tool)：
-1. 确保你的插件代码包含完整的元数据（Frontmatter）：
-   ```python
-   """
-   title: 插件名称
-   author: 你的名字
-   version: 0.1.0
-   description: 简短描述插件的功能
-   """
-   ```
-2. 将插件文件放入 `plugins/` 目录下的合适位置：
-   - `plugins/actions/`: 用于添加按钮或修改消息的 Action 插件。
-   - `plugins/filters/`: 用于拦截请求或响应的 Filter 插件。
-   - `plugins/pipes/`: 用于自定义模型或 API 的 Pipe 插件。
-   - `plugins/tools/`: 用于 LLM 调用的 Tool 插件。
-3. 建议在 `docs/` 下添加一个简单的使用说明。
-
-### 3. 改进文档
-
-如果你发现文档有错误或可以改进的地方，直接提交 PR 即可。
-
-## 🛠️ 开发规范
-
- **代码风格**：Python 代码请遵循 PEP 8 规范。
- **注释**：关键逻辑请添加注释，方便他人理解。
- **测试**：提交前请在本地 OpenWebUI 环境中测试通过。
-
-## 📝 提交 PR
-
-1. Fork 本仓库。
-2. 创建一个新的分支 (`git checkout -b feature/AmazingFeature`)。
-3. 提交你的修改 (`git commit -m 'Add some AmazingFeature'`)。
-4. 推送到分支 (`git push origin feature/AmazingFeature`)。
-5. 开启一个 Pull Request。
-
-## 📦 版本更新与发布
-
-当你更新插件时，请遵循以下流程：
-
-### 1. 更新版本号
-
-在插件文件的 docstring 中更新版本号（遵循[语义化版本](https://semver.org/lang/zh-CN/)）：
-
-```python
-"""
-title: 我的插件
-version: 0.2.0  # 更新此处
-...
-"""
-```
-
-### 2. 更新更新日志
-
-在 `CHANGELOG.md` 的 `[Unreleased]` 部分添加你的更改：
-
-```markdown
-### Added / 新增
- 新功能描述
-
-### Fixed / 修复
- Bug 修复描述
-```
-
-### 3. 发布流程
-
-维护者会通过以下方式发布新版本：
- 手动触发 GitHub Actions 中的 "Plugin Release" 工作流
- 或创建版本标签 (`v*`)
-
-详细说明请参阅 [发布工作流文档](docs/release-workflow.zh.md)。
-
-再次感谢你的贡献！🚀
+Thank you! 🚀
--- a/CONTRIBUTING_CN.md
+++ b/CONTRIBUTING_CN.md
@@ -0,0 +1,16 @@
+# 贡献指南
+
+感谢你对 **OpenWebUI Extras** 感兴趣！
+
+## 🚀 贡献流程
+
+1. **Fork** 本仓库。
+2. **修改/添加** `plugins/` 目录下的插件文件。
+3. **提交 PR**: 我们会尽快审核并合并。
+
+## 💡 注意事项
+
+- 请确保插件包含完整的元数据（title, author, version, description）。
+- 如果是更新已有插件，请记得**增加版本号**（如 `0.1.0` -> `0.1.1`），这样系统会自动同步更新。
+
+再次感谢你的贡献！🚀
--- a/README.md
+++ b/README.md
@@ -7,26 +7,28 @@ A collection of enhancements, plugins, and prompts for [OpenWebUI](https://githu
 <!-- STATS_START -->
 ## 📊 Community Stats

-> 🕐 Auto-updated: 2026-01-09 20:14
+> 🕐 Auto-updated: 2026-01-12 01:06

 | 👤 Author | 👥 Followers | ⭐ Points | 🏆 Contributions |
 |:---:|:---:|:---:|:---:|
-| [Fu-Jie](https://openwebui.com/u/Fu-Jie) | **59** | **70** | **20** |
+| [Fu-Jie](https://openwebui.com/u/Fu-Jie) | **82** | **86** | **22** |

 | 📝 Posts | ⬇️ Downloads | 👁️ Views | 👍 Upvotes | 💾 Saves |
 |:---:|:---:|:---:|:---:|:---:|
-| **13** | **1016** | **10831** | **62** | **56** |
+| **14** | **1161** | **12713** | **76** | **73** |

 ### 🔥 Top 6 Popular Plugins

-| Rank | Plugin | Downloads | Views |
-|:---:|------|:---:|:---:|
-| 🥇 | [Smart Mind Map](https://openwebui.com/posts/turn_any_text_into_beautiful_mind_maps_3094c59a) | 323 | 2878 |
-| 🥈 | [Export to Excel](https://openwebui.com/posts/export_mulit_table_to_excel_244b8f9d) | 180 | 532 |
-| 🥉 | [Async Context Compression](https://openwebui.com/posts/async_context_compression_b1655bc8) | 121 | 1355 |
-| 4️⃣ | [📊 Smart Infographic (AntV)](https://openwebui.com/posts/smart_infographic_ad6f0c7f) | 106 | 1265 |
-| 5️⃣ | [Flash Card](https://openwebui.com/posts/flash_card_65a2ea8f) | 91 | 1665 |
-| 6️⃣ | [Export to Word (Enhanced)](https://openwebui.com/posts/export_to_word_enhanced_formatting_fca6a315) | 80 | 751 |
+> 🕐 Auto-updated: 2026-01-12 01:06
+
+| Rank | Plugin | Downloads | Views | Updated |
+|:---:|------|:---:|:---:|:---:|
+| 🥇 | [Smart Mind Map](https://openwebui.com/posts/turn_any_text_into_beautiful_mind_maps_3094c59a) | 368 | 3352 | 2026-01-07 |
+| 🥈 | [Export to Excel](https://openwebui.com/posts/export_mulit_table_to_excel_244b8f9d) | 184 | 590 | 2026-01-07 |
+| 🥉 | [📊 Smart Infographic (AntV)](https://openwebui.com/posts/smart_infographic_ad6f0c7f) | 136 | 1482 | 2026-01-11 |
+| 4️⃣ | [Async Context Compression](https://openwebui.com/posts/async_context_compression_b1655bc8) | 136 | 1510 | 2026-01-11 |
+| 5️⃣ | [Flash Card](https://openwebui.com/posts/flash_card_65a2ea8f) | 100 | 1833 | 2026-01-07 |
+| 6️⃣ | [Export to Word (Enhanced)](https://openwebui.com/posts/export_to_word_enhanced_formatting_fca6a315) | 96 | 880 | 2026-01-07 |

 *See full stats in [Community Stats Report](./docs/community-stats.md)*
 <!-- STATS_END -->
@@ -40,15 +42,18 @@ Located in the `plugins/` directory, containing Python-based enhancements:
 #### Actions
 - **Smart Mind Map** (`smart-mind-map`): Generates interactive mind maps from text.
 - **Smart Infographic** (`infographic`): Transforms text into professional infographics using AntV.
- **Knowledge Card** (`knowledge-card`): Creates beautiful flashcards for learning.
+- **Flash Card** (`flash-card`): Quickly generates beautiful flashcards for learning.
+- **Deep Dive** (`deep-dive`): A comprehensive thinking lens that dives deep into any content.
 - **Export to Excel** (`export_to_excel`): Exports chat history to Excel files.
 - **Export to Word** (`export_to_docx`): Exports chat history to Word documents.
- **Summary** (`summary`): Text summarization tool.

 #### Filters
 - **Async Context Compression** (`async-context-compression`): Optimizes token usage via context compression.
 - **Context Enhancement** (`context_enhancement_filter`): Enhances chat context.
 - **Gemini Manifold Companion** (`gemini_manifold_companion`): Companion filter for Gemini Manifold.
+- **Gemini Multimodal Filter** (`web_gemini_multimodel_filter`): Provides multimodal capabilities (PDF, Office, Video) for any model via Gemini.
+- **Markdown Normalizer** (`markdown_normalizer`): Fixes common Markdown formatting issues in LLM outputs.
+- **Multi-Model Context Merger** (`multi_model_context_merger`): Automatically merges and injects context from multiple model responses.


 #### Pipes
--- a/README_CN.md
+++ b/README_CN.md
@@ -7,26 +7,28 @@ OpenWebUI 增强功能集合。包含个人开发与收集的插件、提示词
 <!-- STATS_START -->
 ## 📊 社区统计

-> 🕐 自动更新于 2026-01-09 20:14
+> 🕐 自动更新于 2026-01-12 01:06

 | 👤 作者 | 👥 粉丝 | ⭐ 积分 | 🏆 贡献 |
 |:---:|:---:|:---:|:---:|
-| [Fu-Jie](https://openwebui.com/u/Fu-Jie) | **59** | **70** | **20** |
+| [Fu-Jie](https://openwebui.com/u/Fu-Jie) | **82** | **86** | **22** |

 | 📝 发布 | ⬇️ 下载 | 👁️ 浏览 | 👍 点赞 | 💾 收藏 |
 |:---:|:---:|:---:|:---:|:---:|
-| **13** | **1016** | **10831** | **62** | **56** |
+| **14** | **1161** | **12713** | **76** | **73** |

 ### 🔥 热门插件 Top 6

-| 排名 | 插件 | 下载 | 浏览 |
-|:---:|------|:---:|:---:|
-| 🥇 | [Smart Mind Map](https://openwebui.com/posts/turn_any_text_into_beautiful_mind_maps_3094c59a) | 323 | 2878 |
-| 🥈 | [Export to Excel](https://openwebui.com/posts/export_mulit_table_to_excel_244b8f9d) | 180 | 532 |
-| 🥉 | [Async Context Compression](https://openwebui.com/posts/async_context_compression_b1655bc8) | 121 | 1355 |
-| 4️⃣ | [📊 Smart Infographic (AntV)](https://openwebui.com/posts/smart_infographic_ad6f0c7f) | 106 | 1265 |
-| 5️⃣ | [Flash Card](https://openwebui.com/posts/flash_card_65a2ea8f) | 91 | 1665 |
-| 6️⃣ | [Export to Word (Enhanced)](https://openwebui.com/posts/export_to_word_enhanced_formatting_fca6a315) | 80 | 751 |
+> 🕐 自动更新于 2026-01-12 01:06
+
+| 排名 | 插件 | 下载 | 浏览 | 更新日期 |
+|:---:|------|:---:|:---:|:---:|
+| 🥇 | [Smart Mind Map](https://openwebui.com/posts/turn_any_text_into_beautiful_mind_maps_3094c59a) | 368 | 3352 | 2026-01-07 |
+| 🥈 | [Export to Excel](https://openwebui.com/posts/export_mulit_table_to_excel_244b8f9d) | 184 | 590 | 2026-01-07 |
+| 🥉 | [📊 Smart Infographic (AntV)](https://openwebui.com/posts/smart_infographic_ad6f0c7f) | 136 | 1482 | 2026-01-11 |
+| 4️⃣ | [Async Context Compression](https://openwebui.com/posts/async_context_compression_b1655bc8) | 136 | 1510 | 2026-01-11 |
+| 5️⃣ | [Flash Card](https://openwebui.com/posts/flash_card_65a2ea8f) | 100 | 1833 | 2026-01-07 |
+| 6️⃣ | [Export to Word (Enhanced)](https://openwebui.com/posts/export_to_word_enhanced_formatting_fca6a315) | 96 | 880 | 2026-01-07 |

 *完整统计请查看 [社区统计报告](./docs/community-stats.zh.md)*
 <!-- STATS_END -->
@@ -40,15 +42,18 @@ OpenWebUI 增强功能集合。包含个人开发与收集的插件、提示词
 #### Actions (交互增强)
 - **Smart Mind Map** (`smart-mind-map`): 智能分析文本并生成交互式思维导图。
 - **Smart Infographic** (`infographic`): 基于 AntV 的智能信息图生成工具。
- **Knowledge Card** (`knowledge-card`): 快速生成精美的学习记忆卡片。
+- **Flash Card** (`flash-card`): 快速生成精美的学习记忆卡片。
+- **Deep Dive** (`deep-dive`): 深度思考透镜，从背景、逻辑、洞察到行动路径的全方位分析。
 - **Export to Excel** (`export_to_excel`): 将对话内容导出为 Excel 文件。
 - **Export to Word** (`export_to_docx`): 将对话内容导出为 Word 文档。
- **Summary** (`summary`): 文本摘要生成工具。

 #### Filters (消息处理)
 - **Async Context Compression** (`async-context-compression`): 异步上下文压缩，优化 Token 使用。
 - **Context Enhancement** (`context_enhancement_filter`): 上下文增强过滤器。
 - **Gemini Manifold Companion** (`gemini_manifold_companion`): Gemini Manifold 配套增强。
+- **Gemini Multimodal Filter** (`web_gemini_multimodel_filter`): 为任意模型提供多模态能力（PDF、Office、视频等），支持智能路由和字幕精修。
+- **Markdown Normalizer** (`markdown_normalizer`): 修复 LLM 输出中常见的 Markdown 格式问题。
+- **Multi-Model Context Merger** (`multi_model_context_merger`): 自动合并并注入多模型回答的上下文。

 #### Pipes (模型管道)
 - **Gemini Manifold** (`gemini_mainfold`): 集成 Gemini 模型的管道。
@@ -105,4 +110,4 @@ OpenWebUI 增强功能集合。包含个人开发与收集的插件、提示词
 2. 将你的文件添加到对应的 `prompts/` 或 `plugins/` 目录。
 3. 提交 Pull Request。

-[贡献指南](./CONTRIBUTING.md) | [更新日志](./CHANGELOG.md)
+[贡献指南](./CONTRIBUTING_CN.md) | [更新日志](./CHANGELOG.md)
--- a/docs/community-stats.json
+++ b/docs/community-stats.json
@@ -1,14 +1,15 @@
 {
-  "total_posts": 13,
-  "total_downloads": 1016,
-  "total_views": 10831,
-  "total_upvotes": 62,
+  "total_posts": 14,
+  "total_downloads": 1161,
+  "total_views": 12713,
+  "total_upvotes": 76,
  "total_downvotes": 2,
-  "total_saves": 56,
-  "total_comments": 15,
+  "total_saves": 73,
+  "total_comments": 18,
  "by_type": {
    "action": 11,
-    "filter": 2
+    "filter": 2,
+    "unknown": 1
  },
  "posts": [
    {
@@ -18,11 +19,11 @@
      "version": "0.9.1",
      "author": "Fu-Jie",
      "description": "Intelligently analyzes text content and generates interactive mind maps to help users structure and visualize knowledge.",
-      "downloads": 323,
-      "views": 2878,
-      "upvotes": 10,
-      "saves": 17,
-      "comments": 10,
+      "downloads": 368,
+      "views": 3352,
+      "upvotes": 11,
+      "saves": 22,
+      "comments": 11,
      "created_at": "2025-12-30",
      "updated_at": "2026-01-07",
      "url": "https://openwebui.com/posts/turn_any_text_into_beautiful_mind_maps_3094c59a"
@@ -34,47 +35,47 @@
      "version": "0.3.7",
      "author": "Fu-Jie",
      "description": "Extracts tables from chat messages and exports them to Excel (.xlsx) files with smart formatting.",
-      "downloads": 180,
-      "views": 532,
+      "downloads": 184,
+      "views": 590,
      "upvotes": 3,
-      "saves": 3,
+      "saves": 4,
      "comments": 0,
      "created_at": "2025-05-30",
      "updated_at": "2026-01-07",
      "url": "https://openwebui.com/posts/export_mulit_table_to_excel_244b8f9d"
    },
-    {
-      "title": "Async Context Compression",
-      "slug": "async_context_compression_b1655bc8",
-      "type": "filter",
-      "version": "1.1.0",
-      "author": "Fu-Jie",
-      "description": "Reduces token consumption in long conversations while maintaining coherence through intelligent summarization and message compression.",
-      "downloads": 121,
-      "views": 1355,
-      "upvotes": 5,
-      "saves": 9,
-      "comments": 0,
-      "created_at": "2025-11-08",
-      "updated_at": "2026-01-07",
-      "url": "https://openwebui.com/posts/async_context_compression_b1655bc8"
-    },
    {
      "title": "📊 Smart Infographic (AntV)",
      "slug": "smart_infographic_ad6f0c7f",
      "type": "action",
-      "version": "1.4.1",
-      "author": "jeff",
+      "version": "1.4.9",
+      "author": "Fu-Jie",
      "description": "AI-powered infographic generator based on AntV Infographic. Supports professional templates, auto-icon matching, and SVG/PNG downloads.",
-      "downloads": 106,
-      "views": 1265,
-      "upvotes": 7,
+      "downloads": 136,
+      "views": 1482,
+      "upvotes": 8,
      "saves": 9,
      "comments": 2,
      "created_at": "2025-12-28",
-      "updated_at": "2026-01-07",
+      "updated_at": "2026-01-11",
      "url": "https://openwebui.com/posts/smart_infographic_ad6f0c7f"
    },
+    {
+      "title": "Async Context Compression",
+      "slug": "async_context_compression_b1655bc8",
+      "type": "filter",
+      "version": "1.1.2",
+      "author": "Fu-Jie",
+      "description": "Reduces token consumption in long conversations while maintaining coherence through intelligent summarization and message compression.",
+      "downloads": 136,
+      "views": 1510,
+      "upvotes": 6,
+      "saves": 10,
+      "comments": 0,
+      "created_at": "2025-11-08",
+      "updated_at": "2026-01-11",
+      "url": "https://openwebui.com/posts/async_context_compression_b1655bc8"
+    },
    {
      "title": "Flash Card",
      "slug": "flash_card_65a2ea8f",
@@ -82,10 +83,10 @@
      "version": "0.2.4",
      "author": "Fu-Jie",
      "description": "Quickly generates beautiful flashcards from text, extracting key points and categories.",
-      "downloads": 91,
-      "views": 1665,
+      "downloads": 100,
+      "views": 1833,
      "upvotes": 8,
-      "saves": 5,
+      "saves": 6,
      "comments": 2,
      "created_at": "2025-12-30",
      "updated_at": "2026-01-07",
@@ -98,10 +99,10 @@
      "version": "0.4.3",
      "author": "Fu-Jie",
      "description": "Export current conversation from Markdown to Word (.docx) with Mermaid diagrams rendered client-side (Mermaid.js, SVG+PNG), LaTeX math, real hyperlinks, improved tables, syntax highlighting, and blockquote support.",
-      "downloads": 80,
-      "views": 751,
-      "upvotes": 5,
-      "saves": 6,
+      "downloads": 96,
+      "views": 880,
+      "upvotes": 6,
+      "saves": 9,
      "comments": 0,
      "created_at": "2026-01-03",
      "updated_at": "2026-01-07",
@@ -111,16 +112,16 @@
      "title": "📊 智能信息图 (AntV Infographic)",
      "slug": "智能信息图_e04a48ff",
      "type": "action",
-      "version": "1.4.1",
-      "author": "jeff",
+      "version": "1.4.9",
+      "author": "Fu-Jie",
      "description": "基于 AntV Infographic 的智能信息图生成插件。支持多种专业模板，自动图标匹配，并提供 SVG/PNG 下载功能。",
      "downloads": 35,
-      "views": 473,
+      "views": 511,
      "upvotes": 3,
      "saves": 0,
      "comments": 0,
      "created_at": "2025-12-28",
-      "updated_at": "2026-01-07",
+      "updated_at": "2026-01-11",
      "url": "https://openwebui.com/posts/智能信息图_e04a48ff"
    },
    {
@@ -130,31 +131,15 @@
      "version": "0.4.3",
      "author": "Fu-Jie",
      "description": "将对话导出为 Word (.docx)，支持 Mermaid 图表 (客户端渲染 SVG+PNG)、LaTeX 数学公式、真实超链接、增强表格格式、代码高亮和引用块。",
-      "downloads": 30,
-      "views": 902,
-      "upvotes": 8,
+      "downloads": 35,
+      "views": 998,
+      "upvotes": 9,
      "saves": 2,
      "comments": 1,
      "created_at": "2026-01-04",
      "updated_at": "2026-01-07",
      "url": "https://openwebui.com/posts/导出为_word_支持公式流程图表格和代码块_8a6306c0"
    },
-    {
-      "title": "思维导图",
-      "slug": "智能生成交互式思维导图帮助用户可视化知识_8d4b097b",
-      "type": "action",
-      "version": "0.9.1",
-      "author": "Fu-Jie",
-      "description": "智能分析文本内容,生成交互式思维导图,帮助用户结构化和可视化知识。",
-      "downloads": 17,
-      "views": 295,
-      "upvotes": 2,
-      "saves": 1,
-      "comments": 0,
-      "created_at": "2025-12-31",
-      "updated_at": "2026-01-07",
-      "url": "https://openwebui.com/posts/智能生成交互式思维导图帮助用户可视化知识_8d4b097b"
-    },
    {
      "title": "Deep Dive",
      "slug": "deep_dive_c0b846e4",
@@ -162,15 +147,31 @@
      "version": "1.0.0",
      "author": "Fu-Jie",
      "description": "A comprehensive thinking lens that dives deep into any content - from context to logic, insights, and action paths.",
-      "downloads": 14,
-      "views": 167,
+      "downloads": 30,
+      "views": 307,
      "upvotes": 3,
-      "saves": 1,
+      "saves": 4,
      "comments": 0,
      "created_at": "2026-01-08",
      "updated_at": "2026-01-08",
      "url": "https://openwebui.com/posts/deep_dive_c0b846e4"
    },
+    {
+      "title": "思维导图",
+      "slug": "智能生成交互式思维导图帮助用户可视化知识_8d4b097b",
+      "type": "action",
+      "version": "0.9.1",
+      "author": "Fu-Jie",
+      "description": "智能分析文本内容,生成交互式思维导图,帮助用户结构化和可视化知识。",
+      "downloads": 18,
+      "views": 330,
+      "upvotes": 2,
+      "saves": 1,
+      "comments": 0,
+      "created_at": "2025-12-31",
+      "updated_at": "2026-01-07",
+      "url": "https://openwebui.com/posts/智能生成交互式思维导图帮助用户可视化知识_8d4b097b"
+    },
    {
      "title": "闪记卡 (Flash Card)",
      "slug": "闪记卡生成插件_4a31eac3",
@@ -179,7 +180,7 @@
      "author": "Fu-Jie",
      "description": "快速将文本提炼为精美的学习记忆卡片，支持核心要点提取与分类。",
      "downloads": 12,
-      "views": 339,
+      "views": 361,
      "upvotes": 4,
      "saves": 1,
      "comments": 0,
@@ -191,16 +192,16 @@
      "title": "异步上下文压缩",
      "slug": "异步上下文压缩_5c0617cb",
      "type": "filter",
-      "version": "1.1.0",
+      "version": "1.1.2",
      "author": "Fu-Jie",
      "description": "通过智能摘要和消息压缩，降低长对话的 token 消耗，同时保持对话连贯性。",
-      "downloads": 6,
-      "views": 148,
-      "upvotes": 2,
+      "downloads": 8,
+      "views": 211,
+      "upvotes": 4,
      "saves": 1,
      "comments": 0,
      "created_at": "2025-11-08",
-      "updated_at": "2026-01-07",
+      "updated_at": "2026-01-11",
      "url": "https://openwebui.com/posts/异步上下文压缩_5c0617cb"
    },
    {
@@ -210,14 +211,30 @@
      "version": "1.0.0",
      "author": "Fu-Jie",
      "description": "全方位的思维透镜 —— 从背景全景到逻辑脉络，从深度洞察到行动路径。",
-      "downloads": 1,
-      "views": 61,
+      "downloads": 3,
+      "views": 112,
      "upvotes": 2,
      "saves": 1,
      "comments": 0,
      "created_at": "2026-01-08",
      "updated_at": "2026-01-08",
      "url": "https://openwebui.com/posts/精读_99830b0f"
+    },
+    {
+      "title": " 🛠️ Debug Open WebUI Plugins in Your Browser",
+      "slug": "debug_open_webui_plugins_in_your_browser_81bf7960",
+      "type": "unknown",
+      "version": "",
+      "author": "",
+      "description": "",
+      "downloads": 0,
+      "views": 236,
+      "upvotes": 7,
+      "saves": 3,
+      "comments": 2,
+      "created_at": "2026-01-10",
+      "updated_at": "2026-01-10",
+      "url": "https://openwebui.com/posts/debug_open_webui_plugins_in_your_browser_81bf7960"
    }
  ],
  "user": {
@@ -225,11 +242,11 @@
    "name": "Fu-Jie",
    "profile_url": "https://openwebui.com/u/Fu-Jie",
    "profile_image": "https://community.s3.openwebui.com/uploads/users/b15d1348-4347-42b4-b815-e053342d6cb0/profile_d9510745-4bd4-4f8f-a997-4a21847d9300.webp",
-    "followers": 59,
+    "followers": 82,
    "following": 2,
-    "total_points": 70,
-    "post_points": 60,
-    "comment_points": 10,
-    "contributions": 20
+    "total_points": 86,
+    "post_points": 74,
+    "comment_points": 12,
+    "contributions": 22
  }
 }
--- a/docs/community-stats.md
+++ b/docs/community-stats.md
@@ -1,37 +1,39 @@
 # 📊 OpenWebUI Community Stats Report

-> 📅 Updated: 2026-01-09 20:14
+> 📅 Updated: 2026-01-12 01:06

 ## 📈 Overview

 | Metric | Value |
 |------|------|
-| 📝 Total Posts | 13 |
-| ⬇️ Total Downloads | 1016 |
-| 👁️ Total Views | 10831 |
-| 👍 Total Upvotes | 62 |
-| 💾 Total Saves | 56 |
-| 💬 Total Comments | 15 |
+| 📝 Total Posts | 14 |
+| ⬇️ Total Downloads | 1161 |
+| 👁️ Total Views | 12713 |
+| 👍 Total Upvotes | 76 |
+| 💾 Total Saves | 73 |
+| 💬 Total Comments | 18 |

 ## 📂 By Type

 - **action**: 11
 - **filter**: 2
+- **unknown**: 1

 ## 📋 Posts List

 | Rank | Title | Type | Version | Downloads | Views | Upvotes | Saves | Updated |
 |:---:|------|:---:|:---:|:---:|:---:|:---:|:---:|:---:|
-| 1 | [Smart Mind Map](https://openwebui.com/posts/turn_any_text_into_beautiful_mind_maps_3094c59a) | action | 0.9.1 | 323 | 2878 | 10 | 17 | 2026-01-07 |
-| 2 | [Export to Excel](https://openwebui.com/posts/export_mulit_table_to_excel_244b8f9d) | action | 0.3.7 | 180 | 532 | 3 | 3 | 2026-01-07 |
-| 3 | [Async Context Compression](https://openwebui.com/posts/async_context_compression_b1655bc8) | filter | 1.1.0 | 121 | 1355 | 5 | 9 | 2026-01-07 |
-| 4 | [📊 Smart Infographic (AntV)](https://openwebui.com/posts/smart_infographic_ad6f0c7f) | action | 1.4.1 | 106 | 1265 | 7 | 9 | 2026-01-07 |
-| 5 | [Flash Card](https://openwebui.com/posts/flash_card_65a2ea8f) | action | 0.2.4 | 91 | 1665 | 8 | 5 | 2026-01-07 |
-| 6 | [Export to Word (Enhanced)](https://openwebui.com/posts/export_to_word_enhanced_formatting_fca6a315) | action | 0.4.3 | 80 | 751 | 5 | 6 | 2026-01-07 |
-| 7 | [📊 智能信息图 (AntV Infographic)](https://openwebui.com/posts/智能信息图_e04a48ff) | action | 1.4.1 | 35 | 473 | 3 | 0 | 2026-01-07 |
-| 8 | [导出为 Word (增强版)](https://openwebui.com/posts/导出为_word_支持公式流程图表格和代码块_8a6306c0) | action | 0.4.3 | 30 | 902 | 8 | 2 | 2026-01-07 |
-| 9 | [思维导图](https://openwebui.com/posts/智能生成交互式思维导图帮助用户可视化知识_8d4b097b) | action | 0.9.1 | 17 | 295 | 2 | 1 | 2026-01-07 |
-| 10 | [Deep Dive](https://openwebui.com/posts/deep_dive_c0b846e4) | action | 1.0.0 | 14 | 167 | 3 | 1 | 2026-01-08 |
-| 11 | [闪记卡 (Flash Card)](https://openwebui.com/posts/闪记卡生成插件_4a31eac3) | action | 0.2.4 | 12 | 339 | 4 | 1 | 2026-01-07 |
-| 12 | [异步上下文压缩](https://openwebui.com/posts/异步上下文压缩_5c0617cb) | filter | 1.1.0 | 6 | 148 | 2 | 1 | 2026-01-07 |
-| 13 | [精读](https://openwebui.com/posts/精读_99830b0f) | action | 1.0.0 | 1 | 61 | 2 | 1 | 2026-01-08 |
+| 1 | [Smart Mind Map](https://openwebui.com/posts/turn_any_text_into_beautiful_mind_maps_3094c59a) | action | 0.9.1 | 368 | 3352 | 11 | 22 | 2026-01-07 |
+| 2 | [Export to Excel](https://openwebui.com/posts/export_mulit_table_to_excel_244b8f9d) | action | 0.3.7 | 184 | 590 | 3 | 4 | 2026-01-07 |
+| 3 | [📊 Smart Infographic (AntV)](https://openwebui.com/posts/smart_infographic_ad6f0c7f) | action | 1.4.9 | 136 | 1482 | 8 | 9 | 2026-01-11 |
+| 4 | [Async Context Compression](https://openwebui.com/posts/async_context_compression_b1655bc8) | filter | 1.1.2 | 136 | 1510 | 6 | 10 | 2026-01-11 |
+| 5 | [Flash Card](https://openwebui.com/posts/flash_card_65a2ea8f) | action | 0.2.4 | 100 | 1833 | 8 | 6 | 2026-01-07 |
+| 6 | [Export to Word (Enhanced)](https://openwebui.com/posts/export_to_word_enhanced_formatting_fca6a315) | action | 0.4.3 | 96 | 880 | 6 | 9 | 2026-01-07 |
+| 7 | [📊 智能信息图 (AntV Infographic)](https://openwebui.com/posts/智能信息图_e04a48ff) | action | 1.4.9 | 35 | 511 | 3 | 0 | 2026-01-11 |
+| 8 | [导出为 Word (增强版)](https://openwebui.com/posts/导出为_word_支持公式流程图表格和代码块_8a6306c0) | action | 0.4.3 | 35 | 998 | 9 | 2 | 2026-01-07 |
+| 9 | [Deep Dive](https://openwebui.com/posts/deep_dive_c0b846e4) | action | 1.0.0 | 30 | 307 | 3 | 4 | 2026-01-08 |
+| 10 | [思维导图](https://openwebui.com/posts/智能生成交互式思维导图帮助用户可视化知识_8d4b097b) | action | 0.9.1 | 18 | 330 | 2 | 1 | 2026-01-07 |
+| 11 | [闪记卡 (Flash Card)](https://openwebui.com/posts/闪记卡生成插件_4a31eac3) | action | 0.2.4 | 12 | 361 | 4 | 1 | 2026-01-07 |
+| 12 | [异步上下文压缩](https://openwebui.com/posts/异步上下文压缩_5c0617cb) | filter | 1.1.2 | 8 | 211 | 4 | 1 | 2026-01-11 |
+| 13 | [精读](https://openwebui.com/posts/精读_99830b0f) | action | 1.0.0 | 3 | 112 | 2 | 1 | 2026-01-08 |
+| 14 | [ 🛠️ Debug Open WebUI Plugins in Your Browser](https://openwebui.com/posts/debug_open_webui_plugins_in_your_browser_81bf7960) | unknown |  | 0 | 236 | 7 | 3 | 2026-01-10 |
--- a/docs/community-stats.zh.md
+++ b/docs/community-stats.zh.md
@@ -1,37 +1,39 @@
 # 📊 OpenWebUI 社区统计报告

-> 📅 更新时间: 2026-01-09 20:14
+> 📅 更新时间: 2026-01-12 01:06

 ## 📈 总览

 | 指标 | 数值 |
 |------|------|
-| 📝 发布数量 | 13 |
-| ⬇️ 总下载量 | 1016 |
-| 👁️ 总浏览量 | 10831 |
-| 👍 总点赞数 | 62 |
-| 💾 总收藏数 | 56 |
-| 💬 总评论数 | 15 |
+| 📝 发布数量 | 14 |
+| ⬇️ 总下载量 | 1161 |
+| 👁️ 总浏览量 | 12713 |
+| 👍 总点赞数 | 76 |
+| 💾 总收藏数 | 73 |
+| 💬 总评论数 | 18 |

 ## 📂 按类型分类

 - **action**: 11
 - **filter**: 2
+- **unknown**: 1

 ## 📋 发布列表

 | 排名 | 标题 | 类型 | 版本 | 下载 | 浏览 | 点赞 | 收藏 | 更新日期 |
 |:---:|------|:---:|:---:|:---:|:---:|:---:|:---:|:---:|
-| 1 | [Smart Mind Map](https://openwebui.com/posts/turn_any_text_into_beautiful_mind_maps_3094c59a) | action | 0.9.1 | 323 | 2878 | 10 | 17 | 2026-01-07 |
-| 2 | [Export to Excel](https://openwebui.com/posts/export_mulit_table_to_excel_244b8f9d) | action | 0.3.7 | 180 | 532 | 3 | 3 | 2026-01-07 |
-| 3 | [Async Context Compression](https://openwebui.com/posts/async_context_compression_b1655bc8) | filter | 1.1.0 | 121 | 1355 | 5 | 9 | 2026-01-07 |
-| 4 | [📊 Smart Infographic (AntV)](https://openwebui.com/posts/smart_infographic_ad6f0c7f) | action | 1.4.1 | 106 | 1265 | 7 | 9 | 2026-01-07 |
-| 5 | [Flash Card](https://openwebui.com/posts/flash_card_65a2ea8f) | action | 0.2.4 | 91 | 1665 | 8 | 5 | 2026-01-07 |
-| 6 | [Export to Word (Enhanced)](https://openwebui.com/posts/export_to_word_enhanced_formatting_fca6a315) | action | 0.4.3 | 80 | 751 | 5 | 6 | 2026-01-07 |
-| 7 | [📊 智能信息图 (AntV Infographic)](https://openwebui.com/posts/智能信息图_e04a48ff) | action | 1.4.1 | 35 | 473 | 3 | 0 | 2026-01-07 |
-| 8 | [导出为 Word (增强版)](https://openwebui.com/posts/导出为_word_支持公式流程图表格和代码块_8a6306c0) | action | 0.4.3 | 30 | 902 | 8 | 2 | 2026-01-07 |
-| 9 | [思维导图](https://openwebui.com/posts/智能生成交互式思维导图帮助用户可视化知识_8d4b097b) | action | 0.9.1 | 17 | 295 | 2 | 1 | 2026-01-07 |
-| 10 | [Deep Dive](https://openwebui.com/posts/deep_dive_c0b846e4) | action | 1.0.0 | 14 | 167 | 3 | 1 | 2026-01-08 |
-| 11 | [闪记卡 (Flash Card)](https://openwebui.com/posts/闪记卡生成插件_4a31eac3) | action | 0.2.4 | 12 | 339 | 4 | 1 | 2026-01-07 |
-| 12 | [异步上下文压缩](https://openwebui.com/posts/异步上下文压缩_5c0617cb) | filter | 1.1.0 | 6 | 148 | 2 | 1 | 2026-01-07 |
-| 13 | [精读](https://openwebui.com/posts/精读_99830b0f) | action | 1.0.0 | 1 | 61 | 2 | 1 | 2026-01-08 |
+| 1 | [Smart Mind Map](https://openwebui.com/posts/turn_any_text_into_beautiful_mind_maps_3094c59a) | action | 0.9.1 | 368 | 3352 | 11 | 22 | 2026-01-07 |
+| 2 | [Export to Excel](https://openwebui.com/posts/export_mulit_table_to_excel_244b8f9d) | action | 0.3.7 | 184 | 590 | 3 | 4 | 2026-01-07 |
+| 3 | [📊 Smart Infographic (AntV)](https://openwebui.com/posts/smart_infographic_ad6f0c7f) | action | 1.4.9 | 136 | 1482 | 8 | 9 | 2026-01-11 |
+| 4 | [Async Context Compression](https://openwebui.com/posts/async_context_compression_b1655bc8) | filter | 1.1.2 | 136 | 1510 | 6 | 10 | 2026-01-11 |
+| 5 | [Flash Card](https://openwebui.com/posts/flash_card_65a2ea8f) | action | 0.2.4 | 100 | 1833 | 8 | 6 | 2026-01-07 |
+| 6 | [Export to Word (Enhanced)](https://openwebui.com/posts/export_to_word_enhanced_formatting_fca6a315) | action | 0.4.3 | 96 | 880 | 6 | 9 | 2026-01-07 |
+| 7 | [📊 智能信息图 (AntV Infographic)](https://openwebui.com/posts/智能信息图_e04a48ff) | action | 1.4.9 | 35 | 511 | 3 | 0 | 2026-01-11 |
+| 8 | [导出为 Word (增强版)](https://openwebui.com/posts/导出为_word_支持公式流程图表格和代码块_8a6306c0) | action | 0.4.3 | 35 | 998 | 9 | 2 | 2026-01-07 |
+| 9 | [Deep Dive](https://openwebui.com/posts/deep_dive_c0b846e4) | action | 1.0.0 | 30 | 307 | 3 | 4 | 2026-01-08 |
+| 10 | [思维导图](https://openwebui.com/posts/智能生成交互式思维导图帮助用户可视化知识_8d4b097b) | action | 0.9.1 | 18 | 330 | 2 | 1 | 2026-01-07 |
+| 11 | [闪记卡 (Flash Card)](https://openwebui.com/posts/闪记卡生成插件_4a31eac3) | action | 0.2.4 | 12 | 361 | 4 | 1 | 2026-01-07 |
+| 12 | [异步上下文压缩](https://openwebui.com/posts/异步上下文压缩_5c0617cb) | filter | 1.1.2 | 8 | 211 | 4 | 1 | 2026-01-11 |
+| 13 | [精读](https://openwebui.com/posts/精读_99830b0f) | action | 1.0.0 | 3 | 112 | 2 | 1 | 2026-01-08 |
+| 14 | [ 🛠️ Debug Open WebUI Plugins in Your Browser](https://openwebui.com/posts/debug_open_webui_plugins_in_your_browser_81bf7960) | unknown |  | 0 | 236 | 7 | 3 | 2026-01-10 |
--- a/docs/plugins/actions/index.md
+++ b/docs/plugins/actions/index.md
@@ -33,7 +33,7 @@ Actions are interactive plugins that:

    Transform text into professional infographics using AntV visualization engine with various templates.

-    **Version:** 1.4.1
+    **Version:** 1.4.9

    [:octicons-arrow-right-24: Documentation](smart-infographic.md)

--- a/docs/plugins/actions/index.zh.md
+++ b/docs/plugins/actions/index.zh.md
@@ -33,7 +33,7 @@ Actions 是交互式插件，能够：

    使用 AntV 可视化引擎，将文本转成专业的信息图。

-    **版本：** 1.4.1
+    **版本：** 1.4.9

    [:octicons-arrow-right-24: 查看文档](smart-infographic.md)

--- a/docs/plugins/actions/smart-infographic.md
+++ b/docs/plugins/actions/smart-infographic.md
@@ -1,7 +1,7 @@
 # Smart Infographic

 <span class="category-badge action">Action</span>
-<span class="version-badge">v1.4.0</span>
+<span class="version-badge">v1.4.9</span>

 An AntV Infographic engine powered plugin that transforms long text into professional, beautiful infographics with a single click.

@@ -14,8 +14,8 @@ The Smart Infographic plugin uses AI to analyze text content and generate profes
 ## Features

 - :material-robot: **AI-Powered Transformation**: Automatically analyzes text logic, extracts key points, and generates structured charts
- :material-palette: **Professional Templates**: Includes various AntV official templates: Lists, Trees, Mindmaps, Comparison Tables, Flowcharts, and Statistical Charts
- :material-magnify: **Auto-Icon Matching**: Built-in logic to search and match the most relevant Material Design Icons based on content
+- :material-palette: **70+ Professional Templates**: Includes various AntV official templates: Lists, Trees, Roadmaps, Timelines, Comparison Tables, SWOT, Quadrants, and Statistical Charts
+- :material-magnify: **Auto-Icon Matching**: Built-in logic to search and match the most relevant icons (Iconify) and illustrations (unDraw)
 - :material-download: **Multi-Format Export**: Download your infographics as **SVG**, **PNG**, or **Standalone HTML** file
 - :material-theme-light-dark: **Theme Support**: Supports Dark/Light modes, auto-adapts theme colors
 - :material-cellphone-link: **Responsive Design**: Generated charts look great on both desktop and mobile devices
@@ -37,10 +37,11 @@ The Smart Infographic plugin uses AI to analyze text content and generate profes

 | Category | Template Name | Use Case |
 |:---------|:--------------|:---------|
-| **Lists & Hierarchy** | `list-grid`, `tree-vertical`, `mindmap` | Features, Org Charts, Brainstorming |
-| **Sequence & Relation** | `sequence-roadmap`, `relation-circle` | Roadmaps, Circular Flows, Steps |
-| **Comparison & Analysis** | `compare-binary`, `compare-swot`, `quadrant-quarter` | Pros/Cons, SWOT, Quadrants |
-| **Charts & Data** | `chart-bar`, `chart-line`, `chart-pie` | Trends, Distributions, Metrics |
+| **Sequence** | `sequence-timeline-simple`, `sequence-roadmap-vertical-simple`, `sequence-snake-steps-compact-card` | Timelines, Roadmaps, Processes |
+| **Lists** | `list-grid-candy-card-lite`, `list-row-horizontal-icon-arrow`, `list-column-simple-vertical-arrow` | Features, Bullet Points, Lists |
+| **Comparison** | `compare-binary-horizontal-underline-text-vs`, `compare-swot`, `quadrant-quarter-simple-card` | Pros/Cons, SWOT, Quadrants |
+| **Hierarchy** | `hierarchy-tree-tech-style-capsule-item`, `hierarchy-structure` | Org Charts, Structures |
+| **Charts** | `chart-column-simple`, `chart-bar-plain-text`, `chart-line-plain-text`, `chart-wordcloud` | Trends, Distributions, Metrics |

 ---

--- a/docs/plugins/actions/smart-infographic.zh.md
+++ b/docs/plugins/actions/smart-infographic.zh.md
@@ -1,7 +1,7 @@
 # Smart Infographic（智能信息图）

 <span class="category-badge action">Action</span>
-<span class="version-badge">v1.4.0</span>
+<span class="version-badge">v1.4.9</span>

 基于 AntV 信息图引擎，将长文本一键转成专业、美观的信息图。

@@ -14,8 +14,8 @@ Smart Infographic 使用 AI 分析文本，并基于 AntV 可视化引擎生成
 ## 功能特性

 - :material-robot: **AI 转换**：自动分析文本逻辑，提取要点并生成结构化图表
- :material-palette: **专业模板**：内置 AntV 官方模板：列表、树、思维导图、对比表、流程图、统计图等
- :material-magnify: **自动匹配图标**：根据内容自动选择最合适的 Material Design Icons
+- :material-palette: **70+ 专业模板**：内置多种 AntV 官方模板，包括列表、树图、路线图、时间线、对比图、SWOT、象限图及统计图表等
+- :material-magnify: **自动匹配图标**：内置图标搜索逻辑，支持 Iconify 图标和 unDraw 插图自动匹配
 - :material-download: **多格式导出**：支持下载 **SVG**、**PNG**、**独立 HTML**
 - :material-theme-light-dark: **主题支持**：适配深色/浅色模式
 - :material-cellphone-link: **响应式**：桌面与移动端都能良好展示
@@ -37,10 +37,11 @@ Smart Infographic 使用 AI 分析文本，并基于 AntV 可视化引擎生成

 | 分类 | 模板名称 | 典型场景 |
 |:---------|:--------------|:---------|
-| **列表与层级** | `list-grid`, `tree-vertical`, `mindmap` | 特性列表、组织结构、头脑风暴 |
-| **序列与关系** | `sequence-roadmap`, `relation-circle` | 路线图、循环流程、步骤拆解 |
-| **对比与分析** | `compare-binary`, `compare-swot`, `quadrant-quarter` | 优劣势、SWOT、象限分析 |
-| **图表与数据** | `chart-bar`, `chart-line`, `chart-pie` | 趋势、分布、指标对比 |
+| **时序与流程** | `sequence-timeline-simple`, `sequence-roadmap-vertical-simple`, `sequence-snake-steps-compact-card` | 时间线、路线图、步骤说明 |
+| **列表与网格** | `list-grid-candy-card-lite`, `list-row-horizontal-icon-arrow`, `list-column-simple-vertical-arrow` | 功能亮点、要点列举、清单 |
+| **对比与分析** | `compare-binary-horizontal-underline-text-vs`, `compare-swot`, `quadrant-quarter-simple-card` | 优劣势对比、SWOT 分析、象限图 |
+| **层级与结构** | `hierarchy-tree-tech-style-capsule-item`, `hierarchy-structure` | 组织架构、层级关系 |
+| **图表与数据** | `chart-column-simple`, `chart-bar-plain-text`, `chart-line-plain-text`, `chart-wordcloud` | 数据趋势、比例分布、数值对比 |

 ---

--- a/docs/plugins/filters/async-context-compression.md
+++ b/docs/plugins/filters/async-context-compression.md
@@ -1,7 +1,7 @@
 # Async Context Compression

 <span class="category-badge filter">Filter</span>
-<span class="version-badge">v1.1.0</span>
+<span class="version-badge">v1.1.3</span>

 Reduces token consumption in long conversations through intelligent summarization while maintaining conversational coherence.

@@ -29,6 +29,11 @@ This is especially useful for:
 - :material-clock-fast: **Async Processing**: Non-blocking background compression
 - :material-memory: **Context Preservation**: Keeps important information
 - :material-currency-usd-off: **Cost Reduction**: Minimize token usage
+- :material-console: **Frontend Debugging**: Debug logs in browser console
+- :material-alert-circle-check: **Enhanced Error Reporting**: Clear error status notifications
+- :material-check-all: **Open WebUI v0.7.x Compatibility**: Dynamic DB session handling
+- :material-account-convert: **Improved Compatibility**: Summary role changed to `assistant`
+- :material-shield-check: **Enhanced Stability**: Resolved race conditions in state management

 ---

--- a/docs/plugins/filters/async-context-compression.zh.md
+++ b/docs/plugins/filters/async-context-compression.zh.md
@@ -1,7 +1,7 @@
 # Async Context Compression（异步上下文压缩）

 <span class="category-badge filter">Filter</span>
-<span class="version-badge">v1.1.0</span>
+<span class="version-badge">v1.1.3</span>

 通过智能摘要减少长对话的 token 消耗，同时保持对话连贯。

@@ -29,6 +29,11 @@ Async Context Compression 过滤器通过以下方式帮助管理长对话的 to
 - :material-clock-fast: **异步处理**：后台非阻塞压缩
 - :material-memory: **保留上下文**：尽量保留重要信息
 - :material-currency-usd-off: **降低成本**：减少 token 使用
+- :material-console: **前端调试**：支持浏览器控制台日志
+- :material-alert-circle-check: **增强错误报告**：清晰的错误状态通知
+- :material-check-all: **Open WebUI v0.7.x 兼容性**：动态数据库会话处理
+- :material-account-convert: **兼容性提升**：摘要角色改为 `assistant`
+- :material-shield-check: **稳定性增强**：解决状态管理竞态条件

 ---

--- a/docs/plugins/filters/index.md
+++ b/docs/plugins/filters/index.md
@@ -22,7 +22,7 @@ Filters act as middleware in the message pipeline:

    Reduces token consumption in long conversations through intelligent summarization while maintaining coherence.

-    **Version:** 1.1.0
+    **Version:** 1.1.3

    [:octicons-arrow-right-24: Documentation](async-context-compression.md)

@@ -46,6 +46,16 @@ Filters act as middleware in the message pipeline:

    [:octicons-arrow-right-24: Documentation](gemini-manifold-companion.md)

+-   :material-format-paint:{ .lg .middle } **Markdown Normalizer**
+
+    ---
+
+    Fixes common Markdown formatting issues in LLM outputs, including Mermaid syntax, code blocks, and LaTeX formulas.
+
+    **Version:** 1.0.1
+
+    [:octicons-arrow-right-24: Documentation](markdown_normalizer.md)
+
 </div>

 ---
--- a/docs/plugins/filters/index.zh.md
+++ b/docs/plugins/filters/index.zh.md
@@ -22,7 +22,7 @@ Filter 充当消息管线中的中间件：

    通过智能总结减少长对话的 token 消耗，同时保持连贯性。

-    **版本：** 1.1.0
+    **版本：** 1.1.3

    [:octicons-arrow-right-24: 查看文档](async-context-compression.md)

@@ -46,6 +46,16 @@ Filter 充当消息管线中的中间件：

    [:octicons-arrow-right-24: 查看文档](gemini-manifold-companion.md)

+-   :material-format-paint:{ .lg .middle } **Markdown Normalizer**
+
+    ---
+
+    修复 LLM 输出中常见的 Markdown 格式问题，包括 Mermaid 语法、代码块和 LaTeX 公式。
+
+    **版本：** 1.0.1
+
+    [:octicons-arrow-right-24: 查看文档](markdown_normalizer.zh.md)
+
 </div>

 ---
--- a/docs/plugins/filters/markdown_normalizer.md
+++ b/docs/plugins/filters/markdown_normalizer.md
@@ -0,0 +1,46 @@
+# Markdown Normalizer Filter
+
+A production-grade content normalizer filter for Open WebUI that fixes common Markdown formatting issues in LLM outputs. It ensures that code blocks, LaTeX formulas, Mermaid diagrams, and other Markdown elements are rendered correctly.
+
+## Features
+
+*   **Mermaid Syntax Fix**: Automatically fixes common Mermaid syntax errors, such as unquoted node labels (including multi-line labels and citations) and unclosed subgraphs, ensuring diagrams render correctly.
+*   **Frontend Console Debugging**: Supports printing structured debug logs directly to the browser console (F12) for easier troubleshooting.
+*   **Code Block Formatting**: Fixes broken code block prefixes, suffixes, and indentation.
+*   **LaTeX Normalization**: Standardizes LaTeX formula delimiters (`\[` -> `$$`, `\(` -> `$`).
+*   **Thought Tag Normalization**: Unifies thought tags (`<think>`, `<thinking>` -> `<thought>`).
+*   **Escape Character Fix**: Cleans up excessive escape characters (`\\n`, `\\t`).
+*   **List Formatting**: Ensures proper newlines in list items.
+*   **Heading Fix**: Adds missing spaces in headings (`#Heading` -> `# Heading`).
+*   **Table Fix**: Adds missing closing pipes in tables.
+*   **XML Cleanup**: Removes leftover XML artifacts.
+
+## Usage
+
+1.  Install the plugin in Open WebUI.
+2.  Enable the filter globally or for specific models.
+3.  Configure the enabled fixes in the **Valves** settings.
+4.  (Optional) **Show Debug Log** is enabled by default in Valves. This prints structured logs to the browser console (F12).
+    > [!WARNING]
+    > As this is an initial version, some "negative fixes" might occur (e.g., breaking valid Markdown). If you encounter issues, please check the console logs, copy the "Original" vs "Normalized" content, and submit an issue.
+
+## Configuration (Valves)
+
+*   `priority`: Filter priority (default: 50).
+*   `enable_escape_fix`: Fix excessive escape characters.
+*   `enable_thought_tag_fix`: Normalize thought tags.
+*   `enable_code_block_fix`: Fix code block formatting.
+*   `enable_latex_fix`: Normalize LaTeX formulas.
+*   `enable_list_fix`: Fix list item newlines (Experimental).
+*   `enable_unclosed_block_fix`: Auto-close unclosed code blocks.
+*   `enable_fullwidth_symbol_fix`: Fix full-width symbols in code blocks.
+*   `enable_mermaid_fix`: Fix Mermaid syntax errors.
+*   `enable_heading_fix`: Fix missing space in headings.
+*   `enable_table_fix`: Fix missing closing pipe in tables.
+*   `enable_xml_tag_cleanup`: Cleanup leftover XML tags.
+*   `show_status`: Show status notification when fixes are applied.
+*   `show_debug_log`: Print debug logs to browser console.
+
+## License
+
+MIT
--- a/docs/plugins/filters/markdown_normalizer.zh.md
+++ b/docs/plugins/filters/markdown_normalizer.zh.md
@@ -0,0 +1,46 @@
+# Markdown 格式化过滤器 (Markdown Normalizer)
+
+这是一个用于 Open WebUI 的生产级内容格式化过滤器，旨在修复 LLM 输出中常见的 Markdown 格式问题。它能确保代码块、LaTeX 公式、Mermaid 图表和其他 Markdown 元素被正确渲染。
+
+## 功能特性
+
+*   **Mermaid 语法修复**: 自动修复常见的 Mermaid 语法错误，如未加引号的节点标签（支持多行标签和引用标记）和未闭合的子图 (Subgraph)，确保图表能正确渲染。
+*   **前端控制台调试**: 支持将结构化的调试日志直接打印到浏览器控制台 (F12)，方便排查问题。
+*   **代码块格式化**: 修复破损的代码块前缀、后缀和缩进问题。
+*   **LaTeX 规范化**: 标准化 LaTeX 公式定界符 (`\[` -> `$$`, `\(` -> `$`)。
+*   **思维标签规范化**: 统一思维链标签 (`<think>`, `<thinking>` -> `<thought>`)。
+*   **转义字符修复**: 清理过度的转义字符 (`\\n`, `\\t`)。
+*   **列表格式化**: 确保列表项有正确的换行。
+*   **标题修复**: 修复标题中缺失的空格 (`#标题` -> `# 标题`)。
+*   **表格修复**: 修复表格中缺失的闭合管道符。
+*   **XML 清理**: 移除残留的 XML 标签。
+
+## 使用方法
+
+1.  在 Open WebUI 中安装此插件。
+2.  全局启用或为特定模型启用此过滤器。
+3.  在 **Valves** 设置中配置需要启用的修复项。
+4.  (可选) **显示调试日志 (Show Debug Log)** 在 Valves 中默认开启。这会将结构化的日志打印到浏览器控制台 (F12)。
+    > [!WARNING]
+    > 由于这是初版，可能会出现“负向修复”的情况（例如破坏了原本正确的格式）。如果您遇到问题，请务必查看控制台日志，复制“原始 (Original)”与“规范化 (Normalized)”的内容对比，并提交 Issue 反馈。
+
+## 配置项 (Valves)
+
+*   `priority`: 过滤器优先级 (默认: 50)。
+*   `enable_escape_fix`: 修复过度的转义字符。
+*   `enable_thought_tag_fix`: 规范化思维标签。
+*   `enable_code_block_fix`: 修复代码块格式。
+*   `enable_latex_fix`: 规范化 LaTeX 公式。
+*   `enable_list_fix`: 修复列表项换行 (实验性)。
+*   `enable_unclosed_block_fix`: 自动闭合未闭合的代码块。
+*   `enable_fullwidth_symbol_fix`: 修复代码块中的全角符号。
+*   `enable_mermaid_fix`: 修复 Mermaid 语法错误。
+*   `enable_heading_fix`: 修复标题中缺失的空格。
+*   `enable_table_fix`: 修复表格中缺失的闭合管道符。
+*   `enable_xml_tag_cleanup`: 清理残留的 XML 标签。
+*   `show_status`: 应用修复时显示状态通知。
+*   `show_debug_log`: 在浏览器控制台打印调试日志。
+
+## 许可证
+
+MIT
--- a/docs/plugins/index.md
+++ b/docs/plugins/index.md
@@ -53,7 +53,6 @@ OpenWebUI supports four types of plugins, each serving a different purpose:
 | [Knowledge Card](actions/knowledge-card.md) | Action | Create beautiful learning flashcards | 0.2.0 |
 | [Export to Excel](actions/export-to-excel.md) | Action | Export chat history to Excel files | 1.0.0 |
 | [Export to Word](actions/export-to-word.md) | Action | Export chat content to Word (.docx) with formatting | 0.1.0 |
-| [Summary](actions/summary.md) | Action | Text summarization tool | 1.0.0 |
 | [Async Context Compression](filters/async-context-compression.md) | Filter | Intelligent context compression | 1.0.0 |
 | [Context Enhancement](filters/context-enhancement.md) | Filter | Enhance chat context | 1.0.0 |
 | [Gemini Manifold Companion](filters/gemini-manifold-companion.md) | Filter | Companion for Gemini Manifold | 1.0.0 |
--- a/docs/plugins/index.zh.md
+++ b/docs/plugins/index.zh.md
@@ -53,7 +53,6 @@ OpenWebUI 支持四种类型的插件，每种都有不同的用途：
 | [Knowledge Card（知识卡片）](actions/knowledge-card.md) | Action | 生成精美学习卡片 | 0.2.0 |
 | [Export to Excel（导出到 Excel）](actions/export-to-excel.md) | Action | 导出聊天记录为 Excel | 1.0.0 |
 | [Export to Word（导出为 Word）](actions/export-to-word.md) | Action | 将聊天内容导出为 Word (.docx) 并保留格式 | 0.1.0 |
-| [Summary（摘要）](actions/summary.md) | Action | 文本摘要工具 | 1.0.0 |
 | [Async Context Compression（异步上下文压缩）](filters/async-context-compression.md) | Filter | 智能上下文压缩 | 1.0.0 |
 | [Context Enhancement（上下文增强）](filters/context-enhancement.md) | Filter | 提升对话上下文 | 1.0.0 |
 | [Gemini Manifold Companion](filters/gemini-manifold-companion.md) | Filter | Gemini Manifold 伴侣 | 1.0.0 |
--- a/mkdocs.yml
+++ b/mkdocs.yml
@@ -187,7 +187,6 @@ nav:
      - Knowledge Card: plugins/actions/knowledge-card.md
      - Export to Excel: plugins/actions/export-to-excel.md
      - Export to Word: plugins/actions/export-to-word.md
-      - Summary: plugins/actions/summary.md
    - Filters:
      - plugins/filters/index.md
      - Async Context Compression: plugins/filters/async-context-compression.md
--- a/plugins/actions/infographic/README.md
+++ b/plugins/actions/infographic/README.md
@@ -1,11 +1,14 @@
 # 📊 Smart Infographic (AntV)

-**Author:** [Fu-Jie](https://github.com/Fu-Jie) | **Version:** 1.4.1 | **Project:** [Awesome OpenWebUI](https://github.com/Fu-Jie/awesome-openwebui)
+**Author:** [Fu-Jie](https://github.com/Fu-Jie) | **Version:** 1.4.9 | **Project:** [Awesome OpenWebUI](https://github.com/Fu-Jie/awesome-openwebui)

 An Open WebUI plugin powered by the AntV Infographic engine. It transforms long text into professional, beautiful infographics with a single click.

-## 🔥 What's New in v1.4.1
+## 🔥 What's New in v1.4.9

+- 🎨 **70+ Official Templates**: Integrated comprehensive AntV infographic template library.
+- 🖼️ **Iconify & unDraw Support**: Richer visuals with official icons and illustrations.
+- 📏 **Visual Optimization**: Improved text wrapping, adaptive sizing, and layout refinement.
 - ✨ **PNG Upload**: Infographics now upload as PNG format for better Word export compatibility.
 - 🔧 **Canvas Conversion**: Uses browser canvas for high-quality SVG to PNG conversion (2x scale).

@@ -17,8 +20,8 @@ An Open WebUI plugin powered by the AntV Infographic engine. It transforms long
 ## ✨ Key Features

 - 🚀 **AI-Powered Transformation**: Automatically analyzes text logic, extracts key points, and generates structured charts.
- 🎨 **Professional Templates**: Includes various AntV official templates: Lists, Trees, Mindmaps, Comparison Tables, Flowcharts, and Statistical Charts.
- 🔍 **Auto-Icon Matching**: Built-in logic to search and match the most relevant Material Design Icons based on content.
+- 🎨 **70+ Professional Templates**: Includes various AntV official templates: Lists, Trees, Roadmaps, Timelines, Comparison Tables, SWOT, Quadrants, and Statistical Charts.
+- 🔍 **Auto-Icon Matching**: Built-in logic to search and match the most relevant icons (Iconify) and illustrations (unDraw).
 - 📥 **Multi-Format Export**: Download your infographics as **SVG**, **PNG**, or a **Standalone HTML** file.
 - 🌈 **Highly Customizable**: Supports Dark/Light modes, auto-adapts theme colors, with bold titles and refined card layouts.
 - 📱 **Responsive Design**: Generated charts look great on both desktop and mobile devices.
@@ -47,10 +50,11 @@ You can adjust the following parameters in the plugin settings to optimize the g

 | Category | Template Name | Use Case |
 | :--- | :--- | :--- |
-| **Lists & Hierarchy** | `list-grid`, `tree-vertical`, `mindmap` | Features, Org Charts, Brainstorming |
-| **Sequence & Relation** | `sequence-roadmap`, `relation-circle` | Roadmaps, Circular Flows, Steps |
-| **Comparison & Analysis** | `compare-binary`, `compare-swot`, `quadrant-quarter` | Pros/Cons, SWOT, Quadrants |
-| **Charts & Data** | `chart-bar`, `chart-line`, `chart-pie` | Trends, Distributions, Metrics |
+| **Sequence** | `sequence-timeline-simple`, `sequence-roadmap-vertical-simple`, `sequence-snake-steps-compact-card` | Timelines, Roadmaps, Processes |
+| **Lists** | `list-grid-candy-card-lite`, `list-row-horizontal-icon-arrow`, `list-column-simple-vertical-arrow` | Features, Bullet Points, Lists |
+| **Comparison** | `compare-binary-horizontal-underline-text-vs`, `compare-swot`, `quadrant-quarter-simple-card` | Pros/Cons, SWOT, Quadrants |
+| **Hierarchy** | `hierarchy-tree-tech-style-capsule-item`, `hierarchy-structure` | Org Charts, Structures |
+| **Charts** | `chart-column-simple`, `chart-bar-plain-text`, `chart-line-plain-text`, `chart-wordcloud` | Trends, Distributions, Metrics |

 ## 📝 Syntax Example (For Advanced Users)

--- a/plugins/actions/infographic/README_CN.md
+++ b/plugins/actions/infographic/README_CN.md
@@ -1,11 +1,14 @@
 # 📊 智能信息图 (AntV Infographic)

-**Author:** [Fu-Jie](https://github.com/Fu-Jie) | **Version:** 1.4.1 | **Project:** [Awesome OpenWebUI](https://github.com/Fu-Jie/awesome-openwebui)
+**Author:** [Fu-Jie](https://github.com/Fu-Jie) | **Version:** 1.4.9 | **Project:** [Awesome OpenWebUI](https://github.com/Fu-Jie/awesome-openwebui)

 基于 AntV Infographic 引擎的 Open WebUI 插件，能够将长文本内容一键转换为专业、美观的信息图表。

-## 🔥 v1.4.1 更新日志
+## 🔥 v1.4.9 更新日志

+- 🎨 **70+ 官方模板**：全面集成 AntV 官方信息图模板库。
+- 🖼️ **图标与插图支持**：支持 Iconify 图标库与 unDraw 插图库，视觉效果更丰富。
+- 📏 **视觉优化**：改进文本换行逻辑，优化自适应尺寸，提升卡片布局精细度。
 - ✨ **PNG 上传**：信息图现在以 PNG 格式上传，与 Word 导出完美兼容。
 - 🔧 **Canvas 转换**：使用浏览器 Canvas 高质量转换 SVG 为 PNG（2倍缩放）。

@@ -17,8 +20,8 @@
 ## ✨ 核心特性

 - 🚀 **智能转换**：自动分析文本核心逻辑，提取关键点并生成结构化图表。
- 🎨 **专业模板**：内置多种 AntV 官方模板，包括列表、树图、思维导图、对比图、流程图及统计图表等。
- 🔍 **自动图标匹配**：内置图标搜索逻辑，根据内容自动匹配最相关的 Material Design Icons。
+- 🎨 **70+ 专业模板**：内置多种 AntV 官方模板，包括列表、树图、路线图、时间线、对比图、SWOT、象限图及统计图表等。
+- 🔍 **自动图标匹配**：内置图标搜索逻辑，支持 Iconify 图标和 unDraw 插图自动匹配。
 - 📥 **多格式导出**：支持一键下载为 **SVG**、**PNG** 或 **独立 HTML** 文件。
 - 🌈 **高度自定义**：支持深色/浅色模式，自动适配主题颜色，主标题加粗突出，卡片布局精美。
 - 📱 **响应式设计**：生成的图表在桌面端和移动端均有良好的展示效果。
@@ -47,10 +50,11 @@

 | 分类 | 模板名称 | 适用场景 |
 | :--- | :--- | :--- |
-| **列表与层级** | `list-grid`, `tree-vertical`, `mindmap` | 功能亮点、组织架构、思维导图 |
-| **顺序与关系** | `sequence-roadmap`, `relation-circle` | 发展历程、循环关系、步骤说明 |
-| **对比与分析** | `compare-binary`, `compare-swot`, `quadrant-quarter` | 优劣势对比、SWOT 分析、象限图 |
-| **图表与数据** | `chart-bar`, `chart-line`, `chart-pie` | 数据趋势、比例分布、数值对比 |
+| **时序与流程** | `sequence-timeline-simple`, `sequence-roadmap-vertical-simple`, `sequence-snake-steps-compact-card` | 时间线、路线图、步骤说明 |
+| **列表与网格** | `list-grid-candy-card-lite`, `list-row-horizontal-icon-arrow`, `list-column-simple-vertical-arrow` | 功能亮点、要点列举、清单 |
+| **对比与分析** | `compare-binary-horizontal-underline-text-vs`, `compare-swot`, `quadrant-quarter-simple-card` | 优劣势对比、SWOT 分析、象限图 |
+| **层级与结构** | `hierarchy-tree-tech-style-capsule-item`, `hierarchy-structure` | 组织架构、层级关系 |
+| **图表与数据** | `chart-column-simple`, `chart-bar-plain-text`, `chart-line-plain-text`, `chart-wordcloud` | 数据趋势、比例分布、数值对比 |

 ## 📝 语法示例 (高级用户)

--- a/plugins/actions/infographic/infographic.py
+++ b/plugins/actions/infographic/infographic.py
@@ -1,9 +1,9 @@
 """
 title: 📊 Smart Infographic (AntV)
-author: jeff
+author: Fu-Jie
 author_url: https://github.com/Fu-Jie/awesome-openwebui
 icon_url: data:image/svg+xml;base64,PHN2ZyB4bWxucz0iaHR0cDovL3d3dy53My5vcmcvMjAwMC9zdmciIHdpZHRoPSIyNCIgaGVpZ2h0PSIyNCIgdmlld0JveD0iMCAwIDI0IDI0IiBmaWxsPSJub25lIiBzdHJva2U9ImN1cnJlbnRDb2xvciIgc3Ryb2tlLXdpZHRoPSIyIiBzdHJva2UtbGluZWNhcD0icm91bmQiIHN0cm9rZS1saW5lam9pbj0icm91bmQiPgogIDxsaW5lIHgxPSIxMiIgeTE9IjIwIiB4Mj0iMTIiIHkyPSIxMCIgLz4KICA8bGluZSB4MT0iMTgiIHkxPSIyMCIgeDI9IjE4IiB5Mj0iNCIgLz4KICA8bGluZSB4MT0iNiIgeTE9IjIwIiB4Mj0iNiIgeTI9IjE2IiAvPgo8L3N2Zz4=
-version: 1.4.1
+version: 1.4.9
 openwebui_id: ad6f0c7f-c571-4dea-821d-8e71697274cf
 description: AI-powered infographic generator based on AntV Infographic. Supports professional templates, auto-icon matching, and SVG/PNG downloads.
 """
@@ -47,24 +47,63 @@ Infographic syntax is a Mermaid-like declarative syntax for describing infograph

 ### Template Library & Selection Guide

-Choose the most appropriate template based on the content structure:
+Choose the most appropriate template based on content structure.

-#### 1. List & Hierarchy
- **List**: `list-grid` (Grid Cards), `list-vertical` (Vertical List)
- **Tree**: `tree-vertical` (Vertical Tree), `tree-horizontal` (Horizontal Tree)
- **Mindmap**: `mindmap` (Mind Map)
+**Template Selection Guidelines (Official):**
+- Strict sequential order (processes/steps/trends) → `sequence-*` series
+  - Timeline → `sequence-timeline-simple`
+  - Roadmap → `sequence-roadmap-vertical-simple`
+  - Zigzag steps → `sequence-horizontal-zigzag-underline-text`
+  - Snake steps → `sequence-snake-steps-compact-card`
+- Listing viewpoints → `list-row-horizontal-icon-arrow` or `list-column-simple-vertical-arrow`
+- Comparative analysis (A vs B) → `compare-binary-horizontal-underline-text-vs`
+- SWOT analysis → `compare-swot`
+- Hierarchical structure (tree) → `hierarchy-tree-tech-style-capsule-item`
+- Data charts → `chart-*` series
+- Quadrant analysis → `quadrant-quarter-simple-card`
+- Grid lists (bullet points) → `list-grid-candy-card-lite`
+- Relationship display → `relation-circle-icon-badge`

-#### 2. Sequence & Relationship
- **Process**: `sequence-roadmap` (Roadmap), `sequence-zigzag` (Zigzag Process), `sequence-horizontal` (Horizontal Process)
- **Relationship**: `relation-sankey` (Sankey Diagram), `relation-circle` (Circular Relationship)
+**Available Templates:**

-#### 3. Comparison & Analysis
- **Comparison**: `compare-binary` (Binary Comparison), `list-grid` (Multi-item Grid Comparison)
- **Analysis**: `compare-swot` (SWOT Analysis), `quadrant-quarter` (Quadrant Chart)
+*Sequence (时序/流程):*
+`sequence-timeline-simple`, `sequence-roadmap-vertical-simple`, `sequence-horizontal-zigzag-underline-text`, 
+`sequence-snake-steps-compact-card`, `sequence-zigzag-steps-underline-text`, `sequence-circular-simple`,
+`sequence-pyramid-simple`, `sequence-ascending-steps`

-#### 4. Charts & Data
- **Statistics**: `statistic-card` (Statistic Cards)
- **Charts**: `chart-bar` (Bar Chart), `chart-column` (Column Chart), `chart-line` (Line Chart), `chart-pie` (Pie Chart), `chart-doughnut` (Doughnut Chart), `chart-area` (Area Chart)
+*List (列表):*
+`list-grid-candy-card-lite`, `list-grid-badge-card`, `list-row-horizontal-icon-arrow`,
+`list-column-simple-vertical-arrow`, `list-column-done-list`
+
+*Compare (对比):*
+`compare-binary-horizontal-underline-text-vs`, `compare-binary-horizontal-simple-fold`,
+`compare-hierarchy-left-right-circle-node-pill-badge`, `compare-swot`
+
+*Hierarchy (层级):*
+`hierarchy-tree-tech-style-capsule-item`, `hierarchy-tree-curved-line-rounded-rect-node`, `hierarchy-structure`
+
+*Chart (图表):*
+`chart-column-simple`, `chart-bar-plain-text`, `chart-line-plain-text`, 
+`chart-pie-plain-text`, `chart-pie-donut-plain-text`, `chart-wordcloud`
+
+*Other:*
+`quadrant-quarter-simple-card`, `relation-circle-icon-badge`
+
+**Text Capacity by Template Type:**
+- HIGH capacity (long descriptions OK): `list-column-*`, `compare-binary-*`, `sequence-timeline-*`
+- MEDIUM capacity: `list-row-*`, `sequence-roadmap-*`
+- LOW capacity (short text only): `list-grid-*`, `hierarchy-*`, `sequence-steps`
+
+### Icon and Illustration Resources
+
+**Icons (Iconify):**
+- Format: `<collection>/<icon-name>`, e.g., `mdi/rocket-launch`
+- Popular: `mdi/*` (Material Design), `fa/*` (Font Awesome), `bi/*` (Bootstrap)
+- Examples: `mdi/code-tags`, `mdi/chart-line`, `mdi/account-group`, `mdi/cloud`
+
+**Illustrations (unDraw):**
+- Format: filename without .svg, e.g., `coding`, `team-work`
+- Use `illus` field instead of `icon`

 ### Data Structure Examples

@@ -211,6 +250,12 @@ data
 - `children`: Nested items (for trees, SWOT, etc.)
 - `illus`: Illustration icon (specific to some templates like Quadrant)

+### Content Refinement Principles
+1. **Brevity is King**: Infographics are visual. Keep text to a minimum.
+2. **Title Limit**: Keep `label` (item titles) under 15 characters (approx. 10 Chinese characters).
+3. **Description Limit**: Keep `desc` (item descriptions) under 40 characters (approx. 20 Chinese characters / 2 lines).
+4. **Impact**: Use strong verbs and nouns. Avoid filler words.
+
 ## Output Requirements
 1. **Language**: Output content in the user's language.
 2. **Format**: Wrap output in ```infographic ... ```.
@@ -233,9 +278,18 @@ User Language: {user_language}

 Please select the most appropriate infographic template based on text characteristics and output standard infographic syntax. Pay attention to correct indentation format (two spaces).

-**Important Note:** 
- If using `list-grid` format, ensure each card's `desc` description is limited to **maximum 30 Chinese characters** (or **approximately 60 English characters**) to maintain visual consistency with all descriptions fitting in 2 lines.
- Descriptions should be concise and highlight key points.
+**Visual Optimization Guide (MUST FOLLOW):**
+- **Point-based Generation:** Infographics are not articles. Extract KEYWORDS ONLY, avoid complete sentences.
+- **Main Title (`data.title`):** **MUST** be ≤ **15 Chinese characters** (or ≤30 English characters). Trim version numbers or details if needed.
+- **Subtitle (`data.desc`):** **MUST** be ≤ **20 Chinese characters** (or ≤40 English characters).
+- **Card Title (`label`):** **MUST** be ≤ **6 Chinese characters** (or ≤12 English characters). Use 2-4 keywords only.
+- **Card Description (`desc`):** **MUST** be ≤ **12 Chinese characters** (or ≤24 English characters). Use short phrases.
+
+⚠️ **CRITICAL**: If the original text is too long, you MUST rephrase and shorten it. Do NOT simply truncate with "...".
+Examples:
+- ❌ "多步任务与工具协作能力" → ✅ "多步任务协作"
+- ❌ "Open WebUI v0.7.x 重大版本更新" → ✅ "v0.7 核心更新"
+- ❌ "自动查找历史聊天记录" → ✅ "历史检索"
 """

 # =================================================================
@@ -340,8 +394,9 @@ CSS_TEMPLATE_INFOGRAPHIC = """
 .infographic-container-wrapper .infographic-render-container {
    border-radius: 8px;
    padding: 16px;
+    min-height: 600px;
    background: #fff;
-    overflow: visible; /* Ensure content is visible */
+    overflow: visible;
    transition: height 0.3s ease;
 }
 .infographic-render-container svg text {
@@ -349,35 +404,59 @@ CSS_TEMPLATE_INFOGRAPHIC = """
 }
 .infographic-render-container svg foreignObject {
    font-family: -apple-system, BlinkMacSystemFont, "Segoe UI", Roboto, "PingFang SC", "Hiragino Sans GB", "Microsoft YaHei", sans-serif !important;
-    line-height: 1.4 !important;
+    line-height: 1.3 !important;
+    overflow: visible !important;
 }
 /* Main title styles */
 .infographic-render-container svg foreignObject[data-element-type="title"] > * {
-    font-size: 1.5em !important;
-    font-weight: bold !important;
-    line-height: 1.4 !important;
-    white-space: nowrap !important;
+    font-size: 1.3em !important;
+    font-weight: 800 !important;
+    line-height: 1.3 !important;
+    white-space: normal !important;
+    word-break: break-word !important;
+    display: -webkit-box !important;
+    -webkit-line-clamp: 2 !important;
+    -webkit-box-orient: vertical !important;
    overflow: hidden !important;
    text-overflow: ellipsis !important;
+    text-align: center !important;
 }
-/* Page subtitle and card title styles */
-.infographic-render-container svg foreignObject[data-element-type="desc"] > *,
-.infographic-render-container svg foreignObject[data-element-type="item-label"] > * {
-    font-size: 0.6em !important;
-    line-height: 1.4 !important;
-    white-space: nowrap !important;
-    overflow: hidden !important;
-    text-overflow: ellipsis !important;
-}
-/* Card title with extra bottom spacing */
-.infographic-render-container svg foreignObject[data-element-type="item-label"] > * {
-    padding-bottom: 8px !important;
+/* Page subtitle styles */
+.infographic-render-container svg foreignObject[data-element-type="desc"] > * {
+    font-size: 0.85em !important;
+    line-height: 1.3 !important;
+    white-space: normal !important;
+    word-break: break-word !important;
+    overflow: visible !important;
+    text-align: center !important;
    display: block !important;
+    color: var(--ig-muted-text-color) !important;
 }
-/* Card description text keeps normal wrapping */
+/* Card title styles */
+.infographic-render-container svg foreignObject[data-element-type="item-label"] > * {
+    font-size: 0.9em !important;
+    font-weight: 600 !important;
+    line-height: 1.3 !important;
+    white-space: normal !important;
+    word-break: break-word !important;
+    display: -webkit-box !important;
+    -webkit-line-clamp: 2 !important;
+    -webkit-box-orient: vertical !important;
+    overflow: hidden !important;
+    text-overflow: ellipsis !important;
+    padding-bottom: 2px !important;
+}
+/* Card description text */
 .infographic-render-container svg foreignObject[data-element-type="item-desc"] > * {
+    font-size: 0.8em !important;
    line-height: 1.4 !important;
    white-space: normal !important;
+    word-break: break-word !important;
+    display: -webkit-box !important;
+    -webkit-line-clamp: 2 !important;
+    -webkit-box-orient: vertical !important;
+    overflow: hidden !important;
+    text-overflow: ellipsis !important;
 }
 .infographic-container-wrapper .download-area {
    text-align: center;
@@ -533,37 +612,41 @@ SCRIPT_TEMPLATE_INFOGRAPHIC = """
            }}
        }}

-        // 2. Template Mapping Configuration
+        // 2. Template Mapping Configuration (Official AntV Structure IDs)
        const TEMPLATE_MAPPING = {{
-            // List & Hierarchy
+            // List & Hierarchy - map short names to full template names
            'list-grid': 'list-grid-compact-card',
+            'list-column': 'list-column-simple-vertical-arrow',
+            'list-row': 'list-row-simple-horizontal-arrow',
+            'hierarchy-tree': 'hierarchy-tree-tech-style-capsule-item',
+            
+            // Sequence & Timeline
+            'sequence-roadmap-vertical': 'sequence-roadmap-vertical-simple',
+            'sequence-timeline': 'sequence-timeline-simple',
+            'sequence-steps': 'sequence-steps-simple',
+            'sequence-horizontal-zigzag': 'sequence-horizontal-zigzag-simple',
+            
+            // Comparison
+            'compare-binary-horizontal': 'compare-binary-horizontal-simple-vs',
+            'compare-hierarchy-row': 'compare-hierarchy-row-simple',
+            
+            // Charts
+            'chart-column': 'chart-column-simple',
+            'quadrant': 'quadrant-quarter-simple-card',
+            
+            // Legacy mappings for backward compatibility
            'list-vertical': 'list-column-simple-vertical-arrow',
            'tree-vertical': 'hierarchy-tree-tech-style-capsule-item',
-            'tree-horizontal': 'hierarchy-tree-lr-tech-style-capsule-item',
-            'mindmap': 'hierarchy-mindmap-branch-gradient-capsule-item',
-            
-            // Sequence & Relationship
            'sequence-roadmap': 'sequence-roadmap-vertical-simple',
            'sequence-zigzag': 'sequence-horizontal-zigzag-simple',
-            'sequence-horizontal': 'sequence-horizontal-zigzag-simple',
-            'relation-sankey': 'relation-sankey-simple',
-            'relation-circle': 'relation-circle-icon-badge',
-            
-            // Comparison & Analysis
            'compare-binary': 'compare-binary-horizontal-simple-vs',
-            'compare-swot': 'compare-swot',
-            'quadrant-quarter': 'quadrant-quarter-simple-card',
-            
-            // Charts & Data
-            'statistic-card': 'list-grid-compact-card',
            'chart-bar': 'chart-bar-plain-text',
-            'chart-column': 'chart-column-simple',
            'chart-line': 'chart-line-plain-text',
-            'chart-area': 'chart-area-simple',
            'chart-pie': 'chart-pie-plain-text',
            'chart-doughnut': 'chart-pie-donut-plain-text'
        }};

+
        // 3. Apply Mapping Strategy
        for (const [key, value] of Object.entries(TEMPLATE_MAPPING)) {{
            const regex = new RegExp(`infographic\\\\s+${{key}}(?=\\\\s|$)`, 'i');
@@ -629,10 +712,48 @@ SCRIPT_TEMPLATE_INFOGRAPHIC = """
            containerEl.dataset.infographicRendered = 'true';
            console.log('[Infographic] Rendering complete');

-            // Auto-adjust height
+            // Auto-adjust height and tag elements
            setTimeout(() => {
                const svg = containerEl.querySelector('svg');
                if (svg) {
+                    // 1. Tag elements for CSS styling
+                    const fos = Array.from(svg.querySelectorAll('foreignObject'));
+                    let titleFound = false;
+                    let descFound = false;
+                    
+                    fos.forEach((fo) => {
+                        const text = fo.textContent.trim();
+                        if (!text || fo.querySelector('i') || (fo.querySelector('svg') && fo.querySelectorAll('*').length < 5)) {
+                            fo.setAttribute('data-element-type', 'icon');
+                            return;
+                        }
+                        
+                        // Dynamically increase height and width to accommodate wrapped text
+                        const currentHeight = parseInt(fo.getAttribute('height') || '0');
+                        if (currentHeight > 0 && currentHeight < 200) {
+                            fo.setAttribute('height', Math.round(currentHeight * 1.8).toString());
+                        }
+                        const currentWidth = parseInt(fo.getAttribute('width') || '0');
+                        if (currentWidth > 0 && currentWidth < 300) {
+                            fo.setAttribute('width', Math.max(Math.round(currentWidth * 1.2), 180).toString());
+                        }
+
+                        if (!titleFound) {
+                            fo.setAttribute('data-element-type', 'title');
+                            titleFound = true;
+                        } else if (!descFound) {
+                            fo.setAttribute('data-element-type', 'desc');
+                            descFound = true;
+                        } else {
+                            if (fo.querySelector('strong') || fo.style.fontWeight === 'bold' || text.length < 15) {
+                                fo.setAttribute('data-element-type', 'item-label');
+                            } else {
+                                fo.setAttribute('data-element-type', 'item-desc');
+                            }
+                        }
+                    });
+
+                    // 2. Adjust height
                    const bbox = svg.getBoundingClientRect();
                    let contentHeight = bbox.height;
                    if (svg.viewBox && svg.viewBox.baseVal && svg.viewBox.baseVal.height) {
--- a/plugins/actions/infographic/infographic_cn.py
+++ b/plugins/actions/infographic/infographic_cn.py
@@ -1,9 +1,9 @@
 """
 title: 📊 智能信息图 (AntV Infographic)
-author: jeff
+author: Fu-Jie
 author_url: https://github.com/Fu-Jie/awesome-openwebui
 icon_url: data:image/svg+xml;base64,PHN2ZyB4bWxucz0iaHR0cDovL3d3dy53My5vcmcvMjAwMC9zdmciIHdpZHRoPSIyNCIgaGVpZ2h0PSIyNCIgdmlld0JveD0iMCAwIDI0IDI0IiBmaWxsPSJub25lIiBzdHJva2U9ImN1cnJlbnRDb2xvciIgc3Ryb2tlLXdpZHRoPSIyIiBzdHJva2UtbGluZWNhcD0icm91bmQiIHN0cm9rZS1saW5lam9pbj0icm91bmQiPgogIDxsaW5lIHgxPSIxMiIgeTE9IjIwIiB4Mj0iMTIiIHkyPSIxMCIgLz4KICA8bGluZSB4MT0iMTgiIHkxPSIyMCIgeDI9IjE4IiB5Mj0iNCIgLz4KICA8bGluZSB4MT0iNiIgeTE9IjIwIiB4Mj0iNiIgeTI9IjE2IiAvPgo8L3N2Zz4=
-version: 1.4.1
+version: 1.4.9
 openwebui_id: e04a48ff-23ee-4a41-8ea7-66c19524e7c8
 description: 基于 AntV Infographic 的智能信息图生成插件。支持多种专业模板，自动图标匹配，并提供 SVG/PNG 下载功能。
 """
@@ -45,32 +45,61 @@ Infographic syntax is a Mermaid-like declarative syntax for describing infograph
 - ❌ Wrong: `children:` `items:` `data:` (with colons)
 - ✅ Correct: `children` `items` `data` (without colons)

-### Template Library & Selection Guide
+### 模板库与选择指南

-#### 1. List & Hierarchy (Text-heavy)
-   **Linear & Short (Steps/Phases)** -> `list-row-horizontal-icon-arrow`
-   **Linear & Long (Rankings/Details)** -> `list-vertical`
-   **Grouped / Parallel (Features/Catalog)** -> `list-grid`
-   **Hierarchical (Org Chart/Taxonomy)** -> `tree-vertical` or `tree-horizontal`
-   **Central Idea (Brainstorming)** -> `mindmap`
+根据内容结构选择最合适的模板。

-#### 2. Sequence & Relationship (Flow-based)
-   **Time-based (History/Plan)** -> `sequence-roadmap-vertical-simple`
-   **Process Flow (Complex)** -> `sequence-zigzag` or `sequence-horizontal`
-   **Resource Flow / Distribution** -> `relation-sankey`
-   **Circular Relationship** -> `relation-circle`
+**模板选择指南 (官方):**
+- 严格时序 (流程/步骤/趋势) → `sequence-*` 系列
+  - 时间线 → `sequence-timeline-simple`
+  - 路线图 → `sequence-roadmap-vertical-simple`
+  - 折线步骤 → `sequence-horizontal-zigzag-underline-text`
+  - 蛇形步骤 → `sequence-snake-steps-compact-card`
+- 列举要点 → `list-row-horizontal-icon-arrow` 或 `list-column-simple-vertical-arrow`
+- 对比分析 (A vs B) → `compare-binary-horizontal-underline-text-vs`
+- SWOT 分析 → `compare-swot`
+- 层级结构 (树状图) → `hierarchy-tree-tech-style-capsule-item`
+- 数据图表 → `chart-*` 系列
+- 象限分析 → `quadrant-quarter-simple-card`
+- 网格列表 → `list-grid-candy-card-lite`
+- 关系展示 → `relation-circle-icon-badge`

-#### 3. Comparison & Analysis
-   **Binary Comparison (A vs B)** -> `compare-binary`
-   **SWOT Analysis** -> `compare-swot`
-   **Quadrant Analysis (Importance vs Urgency)** -> `quadrant-quarter`
-   **Multi-item Grid Comparison** -> `list-grid` (use for comparing multiple items)
+**可用模板:**

-#### 4. Charts & Data (Metric-heavy)
-   **Key Metrics / Data Cards** -> `statistic-card`
-   **Distribution / Comparison** -> `chart-bar` or `chart-column`
-   **Trend over Time** -> `chart-line` or `chart-area`
-   **Proportion / Part-to-Whole** -> `chart-pie` or `chart-doughnut`
+*Sequence (时序/流程):*
+`sequence-timeline-simple`, `sequence-roadmap-vertical-simple`, `sequence-horizontal-zigzag-underline-text`, 
+`sequence-snake-steps-compact-card`, `sequence-zigzag-steps-underline-text`, `sequence-circular-simple`
+
+*List (列表):*
+`list-grid-candy-card-lite`, `list-grid-badge-card`, `list-row-horizontal-icon-arrow`,
+`list-column-simple-vertical-arrow`, `list-column-done-list`
+
+*Compare (对比):*
+`compare-binary-horizontal-underline-text-vs`, `compare-swot`
+
+*Hierarchy (层级):*
+`hierarchy-tree-tech-style-capsule-item`, `hierarchy-structure`
+
+*Chart (图表):*
+`chart-column-simple`, `chart-bar-plain-text`, `chart-pie-plain-text`, `chart-wordcloud`
+
+*Other:*
+`quadrant-quarter-simple-card`, `relation-circle-icon-badge`
+
+**按容量分类:**
+- 高容量 (长描述): `list-column-*`, `compare-binary-*`, `sequence-timeline-*`
+- 中容量: `list-row-*`, `sequence-roadmap-*`
+- 低容量 (短文本): `list-grid-*`, `hierarchy-*`
+
+### 图标和插图资源
+
+**图标 (Iconify):**
+- 格式: `<集合>/<图标名>`, 如 `mdi/rocket-launch`
+- 常用: `mdi/*`, `fa/*`, `bi/*`
+
+**插图 (unDraw):**
+- 格式: 文件名 (不含 .svg), 如 `coding`, `team-work`
+- 使用 `illus` 字段

 ### Infographic Syntax Guide

@@ -203,6 +232,12 @@ data
      desc Plan for next sprint
      illus mdi/star

+### Content Refinement Principles
+1. **Brevity is King**: Infographics are visual. Keep text to a minimum.
+2. **Title Limit**: Keep `label` (item titles) under 15 characters.
+3. **Description Limit**: Keep `desc` (item descriptions) under 25 characters (approx. 2 lines).
+4. **Impact**: Use strong verbs and nouns. Avoid filler words.
+
 ### Output Rules
 1.  **Strict Syntax**: Follow the indentation and formatting rules exactly.
 2.  **No Explanations**: Output ONLY the syntax code block.
@@ -224,9 +259,11 @@ USER_PROMPT_GENERATE_INFOGRAPHIC = """

 请根据文本特点选择最合适的信息图模板，并输出规范的 infographic 语法。注意保持正确的缩进格式（两个空格）。

-**重要提示：** 
- 如果使用 `list-grid` 格式，请确保每个卡片的 `desc` 描述文字控制在 **30个汉字**（或约60个英文字符）**以内**，以保证所有卡片描述都只占用2行，维持视觉一致性。
- 描述应简洁精炼，突出核心要点。
+**视觉优化指南：** 
+- **要点化生成：** 信息图不是文章。请将内容转化为“关键词+短语”的形式，严禁生成长难句。
+- **标题限制：** 每个卡片的 `label`（标题）请控制在 **8个汉字**以内。
+- **描述限制：** 每个卡片的 `desc`（描述）请控制在 **15个汉字**以内，确保即使在小屏幕上也能完整显示。
+- **结构化思维：** 优先使用并列、递进或对比结构，使信息一目了然。
 """

 # =================================================================
@@ -333,7 +370,7 @@ CSS_TEMPLATE_INFOGRAPHIC = """
    padding: 16px;
    min-height: 600px;
    background: #fff;
-    overflow: visible; /* Ensure content is visible */
+    overflow: visible;
    transition: height 0.3s ease;
 }
 .infographic-render-container svg text {
@@ -341,35 +378,58 @@ CSS_TEMPLATE_INFOGRAPHIC = """
 }
 .infographic-render-container svg foreignObject {
    font-family: -apple-system, BlinkMacSystemFont, "Segoe UI", Roboto, "PingFang SC", "Hiragino Sans GB", "Microsoft YaHei", sans-serif !important;
-    line-height: 1.4 !important;
+    line-height: 1.3 !important;
+    overflow: visible !important;
 }
 /* 主标题样式 */
 .infographic-render-container svg foreignObject[data-element-type="title"] > * {
-    font-size: 1.5em !important;
-    font-weight: bold !important;
-    line-height: 1.4 !important;
-    white-space: nowrap !important;
-    overflow: hidden !important;
-    text-overflow: ellipsis !important;
-}
-/* 页面副标题和卡片标题样式 */
-.infographic-render-container svg foreignObject[data-element-type="desc"] > *,
-.infographic-render-container svg foreignObject[data-element-type="item-label"] > * {
-    font-size: 0.6em !important;
-    line-height: 1.4 !important;
-    white-space: nowrap !important;
-    overflow: hidden !important;
-    text-overflow: ellipsis !important;
-}
-/* 卡片标题额外增加底部间距 */
-.infographic-render-container svg foreignObject[data-element-type="item-label"] > * {
-    padding-bottom: 8px !important;
-    display: block !important;
-}
-/* 卡片描述文字保持正常换行 */
-.infographic-render-container svg foreignObject[data-element-type="item-desc"] > * {
-    line-height: 1.4 !important;
+    font-size: 1.3em !important;
+    font-weight: 800 !important;
+    line-height: 1.3 !important;
    white-space: normal !important;
+    word-break: break-word !important;
+    display: -webkit-box !important;
+    -webkit-line-clamp: 2 !important;
+    -webkit-box-orient: vertical !important;
+    overflow: hidden !important;
+    text-overflow: ellipsis !important;
+    text-align: center !important;
+}
+/* 页面副标题样式 */
+.infographic-render-container svg foreignObject[data-element-type="desc"] > * {
+    font-size: 0.85em !important;
+    line-height: 1.3 !important;
+    white-space: nowrap !important;
+    overflow: hidden !important;
+    text-overflow: ellipsis !important;
+    text-align: center !important;
+    display: block !important;
+    color: var(--ig-muted-text-color) !important;
+}
+/* 卡片标题样式 */
+.infographic-render-container svg foreignObject[data-element-type="item-label"] > * {
+    font-size: 0.9em !important;
+    font-weight: 600 !important;
+    line-height: 1.3 !important;
+    white-space: normal !important;
+    word-break: break-word !important;
+    display: -webkit-box !important;
+    -webkit-line-clamp: 2 !important;
+    -webkit-box-orient: vertical !important;
+    overflow: hidden !important;
+    text-overflow: ellipsis !important;
+    padding-bottom: 2px !important;
+}
+/* 卡片描述文字 */
+.infographic-render-container svg foreignObject[data-element-type="item-desc"] > * {
+    font-size: 0.82em !important;
+    line-height: 1.3 !important;
+    white-space: normal !important;
+    display: -webkit-box !important;
+    -webkit-line-clamp: 2 !important;
+    -webkit-box-orient: vertical !important;
+    overflow: hidden !important;
+    text-overflow: ellipsis !important;
 }
 .infographic-container-wrapper .download-area {
    text-align: center;
@@ -537,34 +597,36 @@ SCRIPT_TEMPLATE_INFOGRAPHIC = """
            }
        }

-        // 2. 模板映射配置
-        // 2. 模板映射配置
+        // 2. 模板映射配置 (官方 AntV 结构 ID)
        const TEMPLATE_MAPPING = {
-            // 列表与层级
+            // 列表与层级 - 短名称映射到完整模板名
            'list-grid': 'list-grid-compact-card',
+            'list-column': 'list-column-simple-vertical-arrow',
+            'list-row': 'list-row-simple-horizontal-arrow',
+            'hierarchy-tree': 'hierarchy-tree-tech-style-capsule-item',
+            
+            // 时序与时间线
+            'sequence-roadmap-vertical': 'sequence-roadmap-vertical-simple',
+            'sequence-timeline': 'sequence-timeline-simple',
+            'sequence-steps': 'sequence-steps-simple',
+            'sequence-horizontal-zigzag': 'sequence-horizontal-zigzag-simple',
+            
+            // 对比
+            'compare-binary-horizontal': 'compare-binary-horizontal-simple-vs',
+            'compare-hierarchy-row': 'compare-hierarchy-row-simple',
+            
+            // 图表
+            'chart-column': 'chart-column-simple',
+            'quadrant': 'quadrant-quarter-simple-card',
+            
+            // 向后兼容的旧映射
            'list-vertical': 'list-column-simple-vertical-arrow',
            'tree-vertical': 'hierarchy-tree-tech-style-capsule-item',
-            'tree-horizontal': 'hierarchy-tree-lr-tech-style-capsule-item',
-            'mindmap': 'hierarchy-mindmap-branch-gradient-capsule-item',
-            
-            // 顺序与关系
            'sequence-roadmap': 'sequence-roadmap-vertical-simple',
            'sequence-zigzag': 'sequence-horizontal-zigzag-simple',
-            'sequence-horizontal': 'sequence-horizontal-zigzag-simple',
-            'relation-sankey': 'relation-sankey-simple', // 暂无直接对应，保留原值或需移除
-            'relation-circle': 'relation-circle-icon-badge',
-            
-            // 对比与分析
            'compare-binary': 'compare-binary-horizontal-simple-vs',
-            'compare-swot': 'compare-swot',
-            'quadrant-quarter': 'quadrant-quarter-simple-card',
-            
-            // 图表与数据
-            'statistic-card': 'list-grid-compact-card',
            'chart-bar': 'chart-bar-plain-text',
-            'chart-column': 'chart-column-simple',
            'chart-line': 'chart-line-plain-text',
-            'chart-area': 'chart-area-simple', // 暂无直接对应
            'chart-pie': 'chart-pie-plain-text',
            'chart-doughnut': 'chart-pie-donut-plain-text'
        };
@@ -657,10 +719,48 @@ SCRIPT_TEMPLATE_INFOGRAPHIC = """
            containerEl.dataset.infographicRendered = 'true';
            console.log('[Infographic] 渲染完成');

-            // 自动调整高度
+            // 自动调整高度与元素标记
            setTimeout(() => {
                const svg = containerEl.querySelector('svg');
                if (svg) {
+                    // 1. 标记元素以便 CSS 应用样式
+                    const fos = Array.from(svg.querySelectorAll('foreignObject'));
+                    let titleFound = false;
+                    let descFound = false;
+                    
+                    fos.forEach((fo) => {
+                        const text = fo.textContent.trim();
+                        if (!text || fo.querySelector('i') || (fo.querySelector('svg') && fo.querySelectorAll('*').length < 5)) {
+                            fo.setAttribute('data-element-type', 'icon');
+                            return;
+                        }
+                        
+                        // 动态增加高度和宽度，容纳换行后的文字
+                        const currentHeight = parseInt(fo.getAttribute('height') || '0');
+                        if (currentHeight > 0 && currentHeight < 200) {
+                            fo.setAttribute('height', Math.round(currentHeight * 1.8).toString());
+                        }
+                        const currentWidth = parseInt(fo.getAttribute('width') || '0');
+                        if (currentWidth > 0 && currentWidth < 300) {
+                            fo.setAttribute('width', Math.max(Math.round(currentWidth * 1.2), 180).toString());
+                        }
+
+                        if (!titleFound) {
+                            fo.setAttribute('data-element-type', 'title');
+                            titleFound = true;
+                        } else if (!descFound) {
+                            fo.setAttribute('data-element-type', 'desc');
+                            descFound = true;
+                        } else {
+                            if (fo.querySelector('strong') || fo.style.fontWeight === 'bold' || text.length < 15) {
+                                fo.setAttribute('data-element-type', 'item-label');
+                            } else {
+                                fo.setAttribute('data-element-type', 'item-desc');
+                            }
+                        }
+                    });
+
+                    // 2. 调整高度
                    const bbox = svg.getBoundingClientRect();
                    let contentHeight = bbox.height;
                    if (svg.viewBox && svg.viewBox.baseVal && svg.viewBox.baseVal.height) {
--- a/plugins/filters/async-context-compression/README.md
+++ b/plugins/filters/async-context-compression/README.md
@@ -1,15 +1,26 @@
 # Async Context Compression Filter

-**Author:** [Fu-Jie](https://github.com/Fu-Jie) | **Version:** 1.1.0 | **License:** MIT
+**Author:** [Fu-Jie](https://github.com/Fu-Jie) | **Version:** 1.1.3 | **License:** MIT

 This filter reduces token consumption in long conversations through intelligent summarization and message compression while keeping conversations coherent.

-## What's new in 1.1.0 
+## What's new in 1.1.3
+- **Improved Compatibility**: Changed summary injection role from `user` to `assistant` for better compatibility across different LLMs.
+- **Enhanced Stability**: Fixed a race condition in state management that could cause "inlet state not found" warnings in high-concurrency scenarios.
+- **Bug Fixes**: Corrected default model handling to prevent misleading logs when no model is specified.
+
+## What's new in 1.1.2
+
+- **Open WebUI v0.7.x Compatibility**: Resolved a critical database session binding error affecting Open WebUI v0.7.x users. The plugin now dynamically discovers the database engine and session context, ensuring compatibility across versions.
+- **Enhanced Error Reporting**: Errors during background summary generation are now reported via both the status bar and browser console.
+- **Robust Model Handling**: Improved handling of missing or invalid model IDs to prevent crashes.
+
+## What's new in 1.1.1
+
+- **Frontend Debugging**: Added `show_debug_log` option to print debug info to the browser console (F12).
+- **Optimized Compression**: Improved token calculation logic to prevent aggressive truncation of history, ensuring more context is retained.
+

- Reuses Open WebUI's shared database connection by default (no custom engine or env vars required).
- Token-based thresholds (`compression_threshold_tokens`, `max_context_tokens`) for safer long-context handling.
- Per-model overrides via `model_thresholds` for mixed-model workflows.
- Documentation now mirrors the latest async workflow and retention-first injection.

 ---

@@ -54,6 +65,7 @@ It is recommended to keep this filter early in the chain so it runs before filte
 | `summary_temperature`          | `0.3`    | Randomness for summary generation. Lower is more deterministic.                                                                                                       |
 | `model_thresholds`             | `{}`     | Per-model overrides for `compression_threshold_tokens` and `max_context_tokens` (useful for mixed models).                                                            |
 | `debug_mode`                   | `true`   | Log verbose debug info. Set to `false` in production.                                                                                                                 |
+| `show_debug_log`               | `false`  | Print debug logs to browser console (F12). Useful for frontend debugging.                                                                                             |

 ---

--- a/plugins/filters/async-context-compression/README_CN.md
+++ b/plugins/filters/async-context-compression/README_CN.md
@@ -1,17 +1,28 @@
 # 异步上下文压缩过滤器

-**作者:** [Fu-Jie](https://github.com/Fu-Jie) | **版本:** 1.2.0 | **许可证:** MIT
+**作者:** [Fu-Jie](https://github.com/Fu-Jie) | **版本:** 1.1.3 | **许可证:** MIT

 > **重要提示**：为了确保所有过滤器的可维护性和易用性，每个过滤器都应附带清晰、完整的文档，以确保其功能、配置和使用方法得到充分说明。

 本过滤器通过智能摘要和消息压缩技术，在保持对话连贯性的同时，显著降低长对话的 Token 消耗。

-## 1.1.0 版本更新
+## 1.1.3 版本更新
+- **兼容性提升**: 将摘要注入角色从 `user` 改为 `assistant`，以提高在不同 LLM 之间的兼容性。
+- **稳定性增强**: 修复了状态管理中的竞态条件，解决了高并发场景下可能出现的“无法获取 inlet 状态”警告。
+- **Bug 修复**: 修正了默认模型处理逻辑，防止在未指定模型时产生误导性日志。
+
+## 1.1.2 版本更新
+
+- **Open WebUI v0.7.x 兼容性**: 修复了影响 Open WebUI v0.7.x 用户的严重数据库会话绑定错误。插件现在动态发现数据库引擎和会话上下文，确保跨版本兼容性。
+- **增强错误报告**: 后台摘要生成过程中的错误现在会通过状态栏和浏览器控制台同时报告。
+- **健壮的模型处理**: 改进了对缺失或无效模型 ID 的处理，防止程序崩溃。
+
+## 1.1.1 版本更新
+
+- **前端调试**: 新增 `show_debug_log` 选项，支持在浏览器控制台 (F12) 打印调试信息。
+- **压缩优化**: 优化 Token 计算逻辑，防止历史记录被过度截断，保留更多上下文。
+

- 默认复用 OpenWebUI 内置数据库连接，无需自建引擎、无需配置 `DATABASE_URL`。
- 基于 Token 的阈值控制（`compression_threshold_tokens`、`max_context_tokens`），长上下文更安全。
- 支持 `model_thresholds` 为不同模型设置专属阈值，适合混用多模型场景。
- 文档同步最新异步工作流与“先保留再注入”策略。

 ---

@@ -94,6 +105,11 @@
 - **默认值**: `true`
 - **描述**: 是否在 Open WebUI 的控制台日志中打印详细的调试信息（如 Token 计数、压缩进度、数据库操作等）。生产环境建议设为 `false`。

+#### `show_debug_log`
+
+- **默认值**: `false`
+- **描述**: 是否在浏览器控制台 (F12) 打印调试日志。便于前端调试。
+
 ---

 ## 故障排除
--- a/plugins/filters/async-context-compression/async_context_compression.py
+++ b/plugins/filters/async-context-compression/async_context_compression.py
@@ -5,7 +5,7 @@ author: Fu-Jie
 author_url: https://github.com/Fu-Jie
 funding_url: https://github.com/Fu-Jie/awesome-openwebui
 description: Reduces token consumption in long conversations while maintaining coherence through intelligent summarization and message compression.
-version: 1.1.0
+version: 1.1.3
 openwebui_id: b1655bc8-6de9-4cad-8cb5-a6f7829a02ce
 license: MIT

@@ -139,6 +139,10 @@ debug_mode
  Default: true
  Description: Prints detailed debug information to the log. Recommended to set to `false` in production.

+show_debug_log
+  Default: false
+  Description: Print debug logs to browser console (F12). Useful for frontend debugging.
+
 🔧 Deployment
 ═══════════════════════════════════════════════════════

@@ -245,6 +249,7 @@ import asyncio
 import json
 import hashlib
 import time
+import contextlib

 # Open WebUI built-in imports
 from open_webui.utils.chat import generate_chat_completion
@@ -253,9 +258,10 @@ from fastapi.requests import Request
 from open_webui.main import app as webui_app

 # Open WebUI internal database (re-use shared connection)
-from open_webui.internal.db import engine as owui_engine
-from open_webui.internal.db import Session as owui_Session
-from open_webui.internal.db import Base as owui_Base
+try:
+    from open_webui.internal import db as owui_db
+except ModuleNotFoundError:  # pragma: no cover - filter runs inside Open WebUI
+    owui_db = None

 # Try to import tiktoken
 try:
@@ -265,14 +271,91 @@ except ImportError:

 # Database imports
 from sqlalchemy import Column, String, Text, DateTime, Integer, inspect
+from sqlalchemy.orm import declarative_base, sessionmaker
+from sqlalchemy.engine import Engine
 from datetime import datetime


+def _discover_owui_engine(db_module: Any) -> Optional[Engine]:
+    """Discover the Open WebUI SQLAlchemy engine via provided db module helpers."""
+    if db_module is None:
+        return None
+
+    db_context = getattr(db_module, "get_db_context", None) or getattr(
+        db_module, "get_db", None
+    )
+    if callable(db_context):
+        try:
+            with db_context() as session:
+                try:
+                    return session.get_bind()
+                except AttributeError:
+                    return getattr(session, "bind", None) or getattr(
+                        session, "engine", None
+                    )
+        except Exception as exc:
+            print(f"[DB Discover] get_db_context failed: {exc}")
+
+    for attr in ("engine", "ENGINE", "bind", "BIND"):
+        candidate = getattr(db_module, attr, None)
+        if candidate is not None:
+            return candidate
+
+    return None
+
+
+def _discover_owui_schema(db_module: Any) -> Optional[str]:
+    """Discover the Open WebUI database schema name if configured."""
+    if db_module is None:
+        return None
+
+    try:
+        base = getattr(db_module, "Base", None)
+        metadata = getattr(base, "metadata", None) if base is not None else None
+        candidate = getattr(metadata, "schema", None) if metadata is not None else None
+        if isinstance(candidate, str) and candidate.strip():
+            return candidate.strip()
+    except Exception as exc:
+        print(f"[DB Discover] Base metadata schema lookup failed: {exc}")
+
+    try:
+        metadata_obj = getattr(db_module, "metadata_obj", None)
+        candidate = (
+            getattr(metadata_obj, "schema", None) if metadata_obj is not None else None
+        )
+        if isinstance(candidate, str) and candidate.strip():
+            return candidate.strip()
+    except Exception as exc:
+        print(f"[DB Discover] metadata_obj schema lookup failed: {exc}")
+
+    try:
+        from open_webui import env as owui_env
+
+        candidate = getattr(owui_env, "DATABASE_SCHEMA", None)
+        if isinstance(candidate, str) and candidate.strip():
+            return candidate.strip()
+    except Exception as exc:
+        print(f"[DB Discover] env schema lookup failed: {exc}")
+
+    return None
+
+
+owui_engine = _discover_owui_engine(owui_db)
+owui_schema = _discover_owui_schema(owui_db)
+owui_Base = getattr(owui_db, "Base", None) if owui_db is not None else None
+if owui_Base is None:
+    owui_Base = declarative_base()
+
+
 class ChatSummary(owui_Base):
    """Chat Summary Storage Table"""

    __tablename__ = "chat_summary"
-    __table_args__ = {"extend_existing": True}
+    __table_args__ = (
+        {"extend_existing": True, "schema": owui_schema}
+        if owui_schema
+        else {"extend_existing": True}
+    )

    id = Column(Integer, primary_key=True, autoincrement=True)
    chat_id = Column(String(255), unique=True, nullable=False, index=True)
@@ -285,14 +368,69 @@ class ChatSummary(owui_Base):
 class Filter:
    def __init__(self):
        self.valves = self.Valves()
+        self._owui_db = owui_db
        self._db_engine = owui_engine
-        self._SessionLocal = owui_Session
-        self.temp_state = {}  # Used to pass temporary data between inlet and outlet
+        self._db_engine = owui_engine
+        self._fallback_session_factory = (
+            sessionmaker(bind=self._db_engine) if self._db_engine else None
+        )
+        self._fallback_session_factory = (
+            sessionmaker(bind=self._db_engine) if self._db_engine else None
+        )
        self._init_database()

+    @contextlib.contextmanager
+    def _db_session(self):
+        """Yield a database session using Open WebUI helpers with graceful fallbacks."""
+        db_module = self._owui_db
+        db_context = None
+        if db_module is not None:
+            db_context = getattr(db_module, "get_db_context", None) or getattr(
+                db_module, "get_db", None
+            )
+
+        if callable(db_context):
+            with db_context() as session:
+                yield session
+                return
+
+        factory = None
+        if db_module is not None:
+            factory = getattr(db_module, "SessionLocal", None) or getattr(
+                db_module, "ScopedSession", None
+            )
+        if callable(factory):
+            session = factory()
+            try:
+                yield session
+            finally:
+                close = getattr(session, "close", None)
+                if callable(close):
+                    close()
+            return
+
+        if self._fallback_session_factory is None:
+            raise RuntimeError(
+                "Open WebUI database session is unavailable. Ensure Open WebUI's database layer is initialized."
+            )
+
+        session = self._fallback_session_factory()
+        try:
+            yield session
+        finally:
+            try:
+                session.close()
+            except Exception as exc:  # pragma: no cover - best-effort cleanup
+                print(f"[Database] ⚠️ Failed to close fallback session: {exc}")
+
    def _init_database(self):
        """Initializes the database table using Open WebUI's shared connection."""
        try:
+            if self._db_engine is None:
+                raise RuntimeError(
+                    "Open WebUI database engine is unavailable. Ensure Open WebUI is configured with a valid DATABASE_URL."
+                )
+
            # Check if table exists using SQLAlchemy inspect
            inspector = inspect(self._db_engine)
            if not inspector.has_table("chat_summary"):
@@ -355,11 +493,14 @@ class Filter:
        debug_mode: bool = Field(
            default=True, description="Enable detailed logging for debugging."
        )
+        show_debug_log: bool = Field(
+            default=False, description="Print debug logs to browser console (F12)"
+        )

    def _save_summary(self, chat_id: str, summary: str, compressed_count: int):
        """Saves the summary to the database."""
        try:
-            with self._SessionLocal() as session:
+            with self._db_session() as session:
                # Find existing record
                existing = session.query(ChatSummary).filter_by(chat_id=chat_id).first()

@@ -399,7 +540,7 @@ class Filter:
    def _load_summary_record(self, chat_id: str) -> Optional[ChatSummary]:
        """Loads the summary record object from the database."""
        try:
-            with self._SessionLocal() as session:
+            with self._db_session() as session:
                record = session.query(ChatSummary).filter_by(chat_id=chat_id).first()
                if record:
                    # Detach the object from the session so it can be used after session close
@@ -480,41 +621,121 @@ class Filter:
            "max_context_tokens": self.valves.max_context_tokens,
        }

-    def _inject_summary_to_first_message(self, message: dict, summary: str) -> dict:
-        """Injects the summary into the first message (prepended to content)."""
-        content = message.get("content", "")
-        summary_block = f"【Historical Conversation Summary】\n{summary}\n\n---\nBelow is the recent conversation:\n\n"
+    def _extract_chat_id(self, body: dict, metadata: Optional[dict]) -> str:
+        """Extract chat_id from body or metadata."""
+        if isinstance(body, dict):
+            chat_id = body.get("chat_id")
+            if isinstance(chat_id, str) and chat_id.strip():
+                return chat_id.strip()

-        # Handle different content types
-        if isinstance(content, list):  # Multimodal content
-            # Find the first text part and insert the summary before it
-            new_content = []
-            summary_inserted = False
+            body_metadata = body.get("metadata", {})
+            if isinstance(body_metadata, dict):
+                chat_id = body_metadata.get("chat_id")
+                if isinstance(chat_id, str) and chat_id.strip():
+                    return chat_id.strip()

-            for part in content:
-                if (
-                    isinstance(part, dict)
-                    and part.get("type") == "text"
-                    and not summary_inserted
-                ):
-                    # Prepend summary to the first text part
-                    new_content.append(
-                        {"type": "text", "text": summary_block + part.get("text", "")}
-                    )
-                    summary_inserted = True
-                else:
-                    new_content.append(part)
+        if isinstance(metadata, dict):
+            chat_id = metadata.get("chat_id")
+            if isinstance(chat_id, str) and chat_id.strip():
+                return chat_id.strip()

-            # If no text part, insert at the beginning
-            if not summary_inserted:
-                new_content.insert(0, {"type": "text", "text": summary_block})
+        return ""

-            message["content"] = new_content
+    async def _emit_debug_log(
+        self,
+        __event_call__,
+        chat_id: str,
+        original_count: int,
+        compressed_count: int,
+        summary_length: int,
+        kept_first: int,
+        kept_last: int,
+    ):
+        """Emit debug log to browser console via JS execution"""
+        if not self.valves.show_debug_log or not __event_call__:
+            return

-        elif isinstance(content, str):  # Plain text
-            message["content"] = summary_block + content
+        try:
+            # Prepare data for JS
+            log_data = {
+                "chatId": chat_id,
+                "originalCount": original_count,
+                "compressedCount": compressed_count,
+                "summaryLength": summary_length,
+                "keptFirst": kept_first,
+                "keptLast": kept_last,
+                "ratio": (
+                    f"{(1 - compressed_count/original_count)*100:.1f}%"
+                    if original_count > 0
+                    else "0%"
+                ),
+            }

-        return message
+            # Construct JS code
+            js_code = f"""
+                (async function() {{
+                    console.group("🗜️ Async Context Compression Debug");
+                    console.log("Chat ID:", {json.dumps(chat_id)});
+                    console.log("Messages:", {original_count} + " -> " + {compressed_count});
+                    console.log("Compression Ratio:", {json.dumps(log_data['ratio'])});
+                    console.log("Summary Length:", {summary_length} + " chars");
+                    console.log("Configuration:", {{
+                        "Keep First": {kept_first},
+                        "Keep Last": {kept_last}
+                    }});
+                    console.groupEnd();
+                }})();
+            """
+
+            await __event_call__(
+                {
+                    "type": "execute",
+                    "data": {"code": js_code},
+                }
+            )
+        except Exception as e:
+            print(f"Error emitting debug log: {e}")
+
+    async def _log(self, message: str, type: str = "info", event_call=None):
+        """Unified logging to both backend (print) and frontend (console.log)"""
+        # Backend logging
+        if self.valves.debug_mode:
+            print(message)
+
+        # Frontend logging
+        if self.valves.show_debug_log and event_call:
+            try:
+                css = "color: #3b82f6;"  # Blue default
+                if type == "error":
+                    css = "color: #ef4444; font-weight: bold;"  # Red
+                elif type == "warning":
+                    css = "color: #f59e0b;"  # Orange
+                elif type == "success":
+                    css = "color: #10b981; font-weight: bold;"  # Green
+
+                # Clean message for frontend: remove separators and extra newlines
+                lines = message.split("\n")
+                # Keep lines that don't start with lots of equals or hyphens
+                filtered_lines = [
+                    line
+                    for line in lines
+                    if not line.strip().startswith("====")
+                    and not line.strip().startswith("----")
+                ]
+                clean_message = "\n".join(filtered_lines).strip()
+
+                if not clean_message:
+                    return
+
+                # Escape quotes in message for JS string
+                safe_message = clean_message.replace('"', '\\"').replace("\n", "\\n")
+
+                js_code = f"""
+                    console.log("%c[Compression] {safe_message}", "{css}");
+                """
+                await event_call({"type": "execute", "data": {"code": js_code}})
+            except Exception as e:
+                print(f"Failed to emit log to frontend: {e}")

    async def inlet(
        self,
@@ -522,36 +743,41 @@ class Filter:
        __user__: Optional[dict] = None,
        __metadata__: dict = None,
        __event_emitter__: Callable[[Any], Awaitable[None]] = None,
+        __event_call__: Callable[[Any], Awaitable[None]] = None,
    ) -> dict:
        """
        Executed before sending to the LLM.
        Compression Strategy: Only responsible for injecting existing summaries, no Token calculation.
        """
        messages = body.get("messages", [])
-        chat_id = __metadata__["chat_id"]
+        chat_id = self._extract_chat_id(body, __metadata__)

-        if self.valves.debug_mode:
-            print(f"\n{'='*60}")
-            print(f"[Inlet] Chat ID: {chat_id}")
-            print(f"[Inlet] Received {len(messages)} messages")
+        if not chat_id:
+            await self._log(
+                "[Inlet] ❌ Missing chat_id in metadata, skipping compression",
+                type="error",
+                event_call=__event_call__,
+            )
+            return body
+
+        if self.valves.debug_mode or self.valves.show_debug_log:
+            await self._log(
+                f"\n{'='*60}\n[Inlet] Chat ID: {chat_id}\n[Inlet] Received {len(messages)} messages",
+                event_call=__event_call__,
+            )

        # Record the target compression progress for the original messages, for use in outlet
        # Target is to compress up to the (total - keep_last) message
        target_compressed_count = max(0, len(messages) - self.valves.keep_last)

-        # [Optimization] Simple state cleanup check
-        if chat_id in self.temp_state:
-            if self.valves.debug_mode:
-                print(
-                    f"[Inlet] ⚠️ Overwriting unconsumed old state (Chat ID: {chat_id})"
-                )
+        # Record the target compression progress for the original messages, for use in outlet
+        # Target is to compress up to the (total - keep_last) message
+        target_compressed_count = max(0, len(messages) - self.valves.keep_last)

-        self.temp_state[chat_id] = target_compressed_count
-
-        if self.valves.debug_mode:
-            print(
-                f"[Inlet] Recorded target compression progress: {target_compressed_count}"
-            )
+        await self._log(
+            f"[Inlet] Recorded target compression progress: {target_compressed_count}",
+            event_call=__event_call__,
+        )

        # Load summary record
        summary_record = await asyncio.to_thread(self._load_summary_record, chat_id)
@@ -579,7 +805,7 @@ class Filter:
                f"---\n"
                f"Below is the recent conversation:"
            )
-            summary_msg = {"role": "user", "content": summary_content}
+            summary_msg = {"role": "assistant", "content": summary_content}

            # 3. Tail messages (Tail) - All messages starting from the last compression point
            # Note: Must ensure head messages are not duplicated
@@ -600,19 +826,32 @@ class Filter:
                    }
                )

-            if self.valves.debug_mode:
-                print(
-                    f"[Inlet] Applied summary: Head({len(head_messages)}) + Summary + Tail({len(tail_messages)})"
-                )
+            await self._log(
+                f"[Inlet] Applied summary: Head({len(head_messages)}) + Summary + Tail({len(tail_messages)})",
+                type="success",
+                event_call=__event_call__,
+            )
+
+            # Emit debug log to frontend (Keep the structured log as well)
+            await self._emit_debug_log(
+                __event_call__,
+                chat_id,
+                len(messages),
+                len(final_messages),
+                len(summary_record.summary),
+                self.valves.keep_first,
+                self.valves.keep_last,
+            )
        else:
            # No summary, use original messages
            final_messages = messages

        body["messages"] = final_messages

-        if self.valves.debug_mode:
-            print(f"[Inlet] Final send: {len(body['messages'])} messages")
-            print(f"{'='*60}\n")
+        await self._log(
+            f"[Inlet] Final send: {len(body['messages'])} messages\n{'='*60}\n",
+            event_call=__event_call__,
+        )

        return body

@@ -622,29 +861,50 @@ class Filter:
        __user__: Optional[dict] = None,
        __metadata__: dict = None,
        __event_emitter__: Callable[[Any], Awaitable[None]] = None,
+        __event_call__: Callable[[Any], Awaitable[None]] = None,
    ) -> dict:
        """
        Executed after the LLM response is complete.
        Calculates Token count in the background and triggers summary generation (does not block current response, does not affect content output).
        """
-        chat_id = __metadata__["chat_id"]
-        model = body.get("model", "gpt-3.5-turbo")
+        chat_id = self._extract_chat_id(body, __metadata__)
+        if not chat_id:
+            await self._log(
+                "[Outlet] ❌ Missing chat_id in metadata, skipping compression",
+                type="error",
+                event_call=__event_call__,
+            )
+            return body
+        model = body.get("model") or ""

-        if self.valves.debug_mode:
-            print(f"\n{'='*60}")
-            print(f"[Outlet] Chat ID: {chat_id}")
-            print(f"[Outlet] Response complete")
+        # Calculate target compression progress directly
+        # Assuming body['messages'] in outlet contains the full history (including new response)
+        messages = body.get("messages", [])
+        target_compressed_count = max(0, len(messages) - self.valves.keep_last)
+
+        if self.valves.debug_mode or self.valves.show_debug_log:
+            await self._log(
+                f"\n{'='*60}\n[Outlet] Chat ID: {chat_id}\n[Outlet] Response complete\n[Outlet] Calculated target compression progress: {target_compressed_count} (Messages: {len(messages)})",
+                event_call=__event_call__,
+            )

        # Process Token calculation and summary generation asynchronously in the background (do not wait for completion, do not affect output)
        asyncio.create_task(
            self._check_and_generate_summary_async(
-                chat_id, model, body, __user__, __event_emitter__
+                chat_id,
+                model,
+                body,
+                __user__,
+                target_compressed_count,
+                __event_emitter__,
+                __event_call__,
            )
        )

-        if self.valves.debug_mode:
-            print(f"[Outlet] Background processing started")
-            print(f"{'='*60}\n")
+        await self._log(
+            f"[Outlet] Background processing started\n{'='*60}\n",
+            event_call=__event_call__,
+        )

        return body

@@ -654,7 +914,9 @@ class Filter:
        model: str,
        body: dict,
        user_data: Optional[dict],
+        target_compressed_count: Optional[int],
        __event_emitter__: Callable[[Any], Awaitable[None]] = None,
+        __event_call__: Callable[[Any], Awaitable[None]] = None,
    ):
        """
        Background processing: Calculates Token count and generates summary (does not block response).
@@ -668,36 +930,58 @@ class Filter:
                "compression_threshold_tokens", self.valves.compression_threshold_tokens
            )

-            if self.valves.debug_mode:
-                print(f"\n[🔍 Background Calculation] Starting Token count...")
+            await self._log(
+                f"\n[🔍 Background Calculation] Starting Token count...",
+                event_call=__event_call__,
+            )

            # Calculate Token count in a background thread
            current_tokens = await asyncio.to_thread(
                self._calculate_messages_tokens, messages
            )

-            if self.valves.debug_mode:
-                print(f"[🔍 Background Calculation] Token count: {current_tokens}")
+            await self._log(
+                f"[🔍 Background Calculation] Token count: {current_tokens}",
+                event_call=__event_call__,
+            )

            # Check if compression is needed
            if current_tokens >= compression_threshold_tokens:
-                if self.valves.debug_mode:
-                    print(
-                        f"[🔍 Background Calculation] ⚡ Compression threshold triggered (Token: {current_tokens} >= {compression_threshold_tokens})"
-                    )
+                await self._log(
+                    f"[🔍 Background Calculation] ⚡ Compression threshold triggered (Token: {current_tokens} >= {compression_threshold_tokens})",
+                    type="warning",
+                    event_call=__event_call__,
+                )

                # Proceed to generate summary
                await self._generate_summary_async(
-                    messages, chat_id, body, user_data, __event_emitter__
+                    messages,
+                    chat_id,
+                    body,
+                    user_data,
+                    target_compressed_count,
+                    __event_emitter__,
+                    __event_call__,
                )
            else:
-                if self.valves.debug_mode:
-                    print(
-                        f"[🔍 Background Calculation] Compression threshold not reached (Token: {current_tokens} < {compression_threshold_tokens})"
-                    )
+                await self._log(
+                    f"[🔍 Background Calculation] Compression threshold not reached (Token: {current_tokens} < {compression_threshold_tokens})",
+                    event_call=__event_call__,
+                )

        except Exception as e:
-            print(f"[🔍 Background Calculation] ❌ Error: {str(e)}")
+            await self._log(
+                f"[🔍 Background Calculation] ❌ Error: {str(e)}",
+                type="error",
+                event_call=__event_call__,
+            )
+
+    def _clean_model_id(self, model_id: Optional[str]) -> Optional[str]:
+        """Cleans the model ID by removing whitespace and quotes."""
+        if not model_id:
+            return None
+        cleaned = model_id.strip().strip('"').strip("'")
+        return cleaned if cleaned else None

    async def _generate_summary_async(
        self,
@@ -705,7 +989,9 @@ class Filter:
        chat_id: str,
        body: dict,
        user_data: Optional[dict],
+        target_compressed_count: Optional[int],
        __event_emitter__: Callable[[Any], Awaitable[None]] = None,
+        __event_call__: Callable[[Any], Awaitable[None]] = None,
    ):
        """
        Generates summary asynchronously (runs in background, does not block response).
@@ -715,18 +1001,19 @@ class Filter:
        3. Generate summary for the remaining middle messages.
        """
        try:
-            if self.valves.debug_mode:
-                print(f"\n[🤖 Async Summary Task] Starting...")
+            await self._log(
+                f"\n[🤖 Async Summary Task] Starting...", event_call=__event_call__
+            )

            # 1. Get target compression progress
-            # Prioritize getting from temp_state (calculated by inlet). If unavailable (e.g., after restart), assume current is full history.
-            target_compressed_count = self.temp_state.pop(chat_id, None)
+            # If target_compressed_count is not passed (should not happen with new logic), estimate it
            if target_compressed_count is None:
                target_compressed_count = max(0, len(messages) - self.valves.keep_last)
-                if self.valves.debug_mode:
-                    print(
-                        f"[🤖 Async Summary Task] ⚠️ Could not get inlet state, estimating progress using current message count: {target_compressed_count}"
-                    )
+                await self._log(
+                    f"[🤖 Async Summary Task] ⚠️ target_compressed_count is None, estimating: {target_compressed_count}",
+                    type="warning",
+                    event_call=__event_call__,
+                )

            # 2. Determine the range of messages to compress (Middle)
            start_index = self.valves.keep_first
@@ -736,25 +1023,33 @@ class Filter:

            # Ensure indices are valid
            if start_index >= end_index:
-                if self.valves.debug_mode:
-                    print(
-                        f"[🤖 Async Summary Task] Middle messages empty (Start: {start_index}, End: {end_index}), skipping"
-                    )
+                await self._log(
+                    f"[🤖 Async Summary Task] Middle messages empty (Start: {start_index}, End: {end_index}), skipping",
+                    event_call=__event_call__,
+                )
                return

            middle_messages = messages[start_index:end_index]

-            if self.valves.debug_mode:
-                print(
-                    f"[🤖 Async Summary Task] Middle messages to process: {len(middle_messages)}"
-                )
+            await self._log(
+                f"[🤖 Async Summary Task] Middle messages to process: {len(middle_messages)}",
+                event_call=__event_call__,
+            )

            # 3. Check Token limit and truncate (Max Context Truncation)
            # [Optimization] Use the summary model's (if any) threshold to decide how many middle messages can be processed
            # This allows using a long-window model (like gemini-flash) to compress history exceeding the current model's window
-            summary_model_id = self.valves.summary_model or body.get(
-                "model", "gpt-3.5-turbo"
-            )
+            summary_model_id = self._clean_model_id(
+                self.valves.summary_model
+            ) or self._clean_model_id(body.get("model"))
+
+            if not summary_model_id:
+                await self._log(
+                    "[🤖 Async Summary Task] ⚠️ Summary model does not exist, skipping compression",
+                    type="warning",
+                    event_call=__event_call__,
+                )
+                return

            thresholds = self._get_model_thresholds(summary_model_id)
            # Note: Using the summary model's max context limit here
@@ -762,22 +1057,26 @@ class Filter:
                "max_context_tokens", self.valves.max_context_tokens
            )

-            if self.valves.debug_mode:
-                print(
-                    f"[🤖 Async Summary Task] Using max limit for model {summary_model_id}: {max_context_tokens} Tokens"
-                )
-
-            # Calculate current total Tokens (using summary model for counting)
-            total_tokens = await asyncio.to_thread(
-                self._calculate_messages_tokens, messages
+            await self._log(
+                f"[🤖 Async Summary Task] Using max limit for model {summary_model_id}: {max_context_tokens} Tokens",
+                event_call=__event_call__,
            )

-            if total_tokens > max_context_tokens:
-                excess_tokens = total_tokens - max_context_tokens
-                if self.valves.debug_mode:
-                    print(
-                        f"[🤖 Async Summary Task] ⚠️ Total Tokens ({total_tokens}) exceed summary model limit ({max_context_tokens}), need to remove approx {excess_tokens} Tokens"
-                    )
+            # Calculate tokens for middle messages only (plus buffer for prompt)
+            # We only send middle_messages to the summary model, so we shouldn't count the full history against its limit.
+            middle_tokens = await asyncio.to_thread(
+                self._calculate_messages_tokens, middle_messages
+            )
+            # Add buffer for prompt and output (approx 2000 tokens)
+            estimated_input_tokens = middle_tokens + 2000
+
+            if estimated_input_tokens > max_context_tokens:
+                excess_tokens = estimated_input_tokens - max_context_tokens
+                await self._log(
+                    f"[🤖 Async Summary Task] ⚠️ Middle messages ({middle_tokens} Tokens) + Buffer exceed summary model limit ({max_context_tokens}), need to remove approx {excess_tokens} Tokens",
+                    type="warning",
+                    event_call=__event_call__,
+                )

                # Remove from the head of middle_messages
                removed_tokens = 0
@@ -785,20 +1084,22 @@ class Filter:

                while removed_tokens < excess_tokens and middle_messages:
                    msg_to_remove = middle_messages.pop(0)
-                    msg_tokens = self._count_tokens(str(msg_to_remove.get("content", "")))
+                    msg_tokens = self._count_tokens(
+                        str(msg_to_remove.get("content", ""))
+                    )
                    removed_tokens += msg_tokens
                    removed_count += 1

-                if self.valves.debug_mode:
-                    print(
-                        f"[🤖 Async Summary Task] Removed {removed_count} messages, totaling {removed_tokens} Tokens"
-                    )
+                await self._log(
+                    f"[🤖 Async Summary Task] Removed {removed_count} messages, totaling {removed_tokens} Tokens",
+                    event_call=__event_call__,
+                )

            if not middle_messages:
-                if self.valves.debug_mode:
-                    print(
-                        f"[🤖 Async Summary Task] Middle messages empty after truncation, skipping summary generation"
-                    )
+                await self._log(
+                    f"[🤖 Async Summary Task] Middle messages empty after truncation, skipping summary generation",
+                    event_call=__event_call__,
+                )
                return

            # 4. Build conversation text
@@ -820,14 +1121,26 @@ class Filter:
                )

            new_summary = await self._call_summary_llm(
-                None, conversation_text, body, user_data
+                None,
+                conversation_text,
+                {**body, "model": summary_model_id},
+                user_data,
+                __event_call__,
            )

-            # 6. Save new summary
-            if self.valves.debug_mode:
-                print(
-                    "[Optimization] Saving summary in a background thread to avoid blocking the event loop."
+            if not new_summary:
+                await self._log(
+                    "[🤖 Async Summary Task] ⚠️ Summary generation returned empty result, skipping save",
+                    type="warning",
+                    event_call=__event_call__,
                )
+                return
+
+            # 6. Save new summary
+            await self._log(
+                "[Optimization] Saving summary in a background thread to avoid blocking the event loop.",
+                event_call=__event_call__,
+            )

            await asyncio.to_thread(
                self._save_summary, chat_id, new_summary, target_compressed_count
@@ -845,16 +1158,34 @@ class Filter:
                    }
                )

-            if self.valves.debug_mode:
-                print(
-                    f"[🤖 Async Summary Task] ✅ Complete! New summary length: {len(new_summary)} characters"
-                )
-                print(
-                    f"[🤖 Async Summary Task] Progress update: Compressed up to original message {target_compressed_count}"
-                )
+            await self._log(
+                f"[🤖 Async Summary Task] ✅ Complete! New summary length: {len(new_summary)} characters",
+                type="success",
+                event_call=__event_call__,
+            )
+            await self._log(
+                f"[🤖 Async Summary Task] Progress update: Compressed up to original message {target_compressed_count}",
+                event_call=__event_call__,
+            )

        except Exception as e:
-            print(f"[🤖 Async Summary Task] ❌ Error: {str(e)}")
+            await self._log(
+                f"[🤖 Async Summary Task] ❌ Error: {str(e)}",
+                type="error",
+                event_call=__event_call__,
+            )
+
+            if __event_emitter__:
+                await __event_emitter__(
+                    {
+                        "type": "status",
+                        "data": {
+                            "description": f"Summary Error: {str(e)[:100]}...",
+                            "done": True,
+                        },
+                    }
+                )
+
            import traceback

            traceback.print_exc()
@@ -891,12 +1222,15 @@ class Filter:
        new_conversation_text: str,
        body: dict,
        user_data: dict,
+        __event_call__: Callable[[Any], Awaitable[None]] = None,
    ) -> str:
        """
        Calls the LLM to generate a summary using Open WebUI's built-in method.
        """
-        if self.valves.debug_mode:
-            print(f"[🤖 LLM Call] Using Open WebUI's built-in method")
+        await self._log(
+            f"[🤖 LLM Call] Using Open WebUI's built-in method",
+            event_call=__event_call__,
+        )

        # Build summary prompt (Optimized)
        summary_prompt = f"""
@@ -933,10 +1267,19 @@ This conversation may contain previous summaries (as system messages or text) an
 Based on the content above, generate the summary:
 """
        # Determine the model to use
-        model = self.valves.summary_model or body.get("model", "")
+        model = self._clean_model_id(self.valves.summary_model) or self._clean_model_id(
+            body.get("model")
+        )

-        if self.valves.debug_mode:
-            print(f"[🤖 LLM Call] Model: {model}")
+        if not model:
+            await self._log(
+                "[🤖 LLM Call] ⚠️ Summary model does not exist, skipping summary generation",
+                type="warning",
+                event_call=__event_call__,
+            )
+            return ""
+
+        await self._log(f"[🤖 LLM Call] Model: {model}", event_call=__event_call__)

        # Build payload
        payload = {
@@ -954,18 +1297,19 @@ Based on the content above, generate the summary:
                raise ValueError("Could not get user ID")

            # [Optimization] Get user object in a background thread to avoid blocking the event loop.
-            if self.valves.debug_mode:
-                print(
-                    "[Optimization] Getting user object in a background thread to avoid blocking the event loop."
-                )
+            await self._log(
+                "[Optimization] Getting user object in a background thread to avoid blocking the event loop.",
+                event_call=__event_call__,
+            )
            user = await asyncio.to_thread(Users.get_user_by_id, user_id)

            if not user:
                raise ValueError(f"Could not find user: {user_id}")

-            if self.valves.debug_mode:
-                print(f"[🤖 LLM Call] User: {user.email}")
-                print(f"[🤖 LLM Call] Sending request...")
+            await self._log(
+                f"[🤖 LLM Call] User: {user.email}\n[🤖 LLM Call] Sending request...",
+                event_call=__event_call__,
+            )

            # Create Request object
            request = Request(scope={"type": "http", "app": webui_app})
@@ -978,20 +1322,31 @@ Based on the content above, generate the summary:

            summary = response["choices"][0]["message"]["content"].strip()

-            if self.valves.debug_mode:
-                print(f"[🤖 LLM Call] ✅ Successfully received summary")
+            await self._log(
+                f"[🤖 LLM Call] ✅ Successfully received summary",
+                type="success",
+                event_call=__event_call__,
+            )

            return summary

        except Exception as e:
-            error_message = f"Error occurred while calling LLM ({model}) to generate summary: {str(e)}"
+            error_msg = str(e)
+            # Handle specific error messages
+            if "Model not found" in error_msg:
+                error_message = f"Summary model '{model}' not found."
+            else:
+                error_message = f"Summary LLM Error ({model}): {error_msg}"
            if not self.valves.summary_model:
                error_message += (
                    "\n[Hint] You did not specify a summary_model, so the filter attempted to use the current conversation's model. "
                    "If this is a pipeline (Pipe) model or an incompatible model, please specify a compatible summary model (e.g., 'gemini-2.5-flash') in the configuration."
                )

-            if self.valves.debug_mode:
-                print(f"[🤖 LLM Call] ❌ {error_message}")
+            await self._log(
+                f"[🤖 LLM Call] ❌ {error_message}",
+                type="error",
+                event_call=__event_call__,
+            )

            raise Exception(error_message)
--- a/plugins/filters/async-context-compression/async_context_compression_cn.py
+++ b/plugins/filters/async-context-compression/async_context_compression_cn.py
@@ -5,7 +5,7 @@ author: Fu-Jie
 author_url: https://github.com/Fu-Jie
 funding_url: https://github.com/Fu-Jie/awesome-openwebui
 description: 通过智能摘要和消息压缩，降低长对话的 token 消耗，同时保持对话连贯性。
-version: 1.1.0
+version: 1.1.3
 openwebui_id: 5c0617cb-a9e4-4bd6-a440-d276534ebd18
 license: MIT

@@ -138,6 +138,10 @@ debug_mode (调试模式)
  默认: true
  说明: 在日志中打印详细的调试信息。生产环境建议设为 `false`。

+show_debug_log (前端调试日志)
+  默认: false
+  说明: 在浏览器控制台打印调试日志 (F12)。便于前端调试。
+
 🔧 部署配置
 ═══════════════════════════════════════════════════════

@@ -286,7 +290,8 @@ class Filter:
        self.valves = self.Valves()
        self._db_engine = owui_engine
        self._SessionLocal = owui_Session
-        self.temp_state = {}  # 用于在 inlet 和 outlet 之间传递临时数据
+        self._SessionLocal = owui_Session
+        self._init_database()
        self._init_database()

    def _init_database(self):
@@ -345,6 +350,9 @@ class Filter:
            default=0.1, ge=0.0, le=2.0, description="摘要生成的温度参数"
        )
        debug_mode: bool = Field(default=True, description="调试模式，打印详细日志")
+        show_debug_log: bool = Field(
+            default=False, description="在浏览器控制台打印调试日志 (F12)"
+        )

    def _save_summary(self, chat_id: str, summary: str, compressed_count: int):
        """保存摘要到数据库"""
@@ -426,9 +434,7 @@ class Filter:
        # 回退策略：粗略估算 (1 token ≈ 4 chars)
        return len(text) // 4

-    def _calculate_messages_tokens(
-        self, messages: List[Dict]
-    ) -> int:
+    def _calculate_messages_tokens(self, messages: List[Dict]) -> int:
        """计算消息列表的总 Token 数"""
        total_tokens = 0
        for msg in messages:
@@ -466,41 +472,101 @@ class Filter:
            "max_context_tokens": self.valves.max_context_tokens,
        }

-    def _inject_summary_to_first_message(self, message: dict, summary: str) -> dict:
-        """将摘要注入到第一条消息中（追加到内容前面）"""
-        content = message.get("content", "")
-        summary_block = f"【历史对话摘要】\n{summary}\n\n---\n以下是最近的对话：\n\n"
+    async def _emit_debug_log(
+        self,
+        __event_call__,
+        chat_id: str,
+        original_count: int,
+        compressed_count: int,
+        summary_length: int,
+        kept_first: int,
+        kept_last: int,
+    ):
+        """Emit debug log to browser console via JS execution"""
+        if not self.valves.show_debug_log or not __event_call__:
+            return

-        # 处理不同内容类型
-        if isinstance(content, list):  # 多模态内容
-            # 查找第一个文本部分并在其前面插入摘要
-            new_content = []
-            summary_inserted = False
+        try:
+            # Prepare data for JS
+            log_data = {
+                "chatId": chat_id,
+                "originalCount": original_count,
+                "compressedCount": compressed_count,
+                "summaryLength": summary_length,
+                "keptFirst": kept_first,
+                "keptLast": kept_last,
+                "ratio": (
+                    f"{(1 - compressed_count/original_count)*100:.1f}%"
+                    if original_count > 0
+                    else "0%"
+                ),
+            }

-            for part in content:
-                if (
-                    isinstance(part, dict)
-                    and part.get("type") == "text"
-                    and not summary_inserted
-                ):
-                    # 在第一个文本部分前插入摘要
-                    new_content.append(
-                        {"type": "text", "text": summary_block + part.get("text", "")}
-                    )
-                    summary_inserted = True
-                else:
-                    new_content.append(part)
+            # Construct JS code
+            js_code = f"""
+                (async function() {{
+                    console.group("🗜️ Async Context Compression Debug");
+                    console.log("Chat ID:", {json.dumps(chat_id)});
+                    console.log("Messages:", {original_count} + " -> " + {compressed_count});
+                    console.log("Compression Ratio:", {json.dumps(log_data['ratio'])});
+                    console.log("Summary Length:", {summary_length} + " chars");
+                    console.log("Configuration:", {{
+                        "Keep First": {kept_first},
+                        "Keep Last": {kept_last}
+                    }});
+                    console.groupEnd();
+                }})();
+            """

-            # 如果没有文本部分，在开头插入
-            if not summary_inserted:
-                new_content.insert(0, {"type": "text", "text": summary_block})
+            await __event_call__(
+                {
+                    "type": "execute",
+                    "data": {"code": js_code},
+                }
+            )
+        except Exception as e:
+            print(f"Error emitting debug log: {e}")

-            message["content"] = new_content
+    async def _log(self, message: str, type: str = "info", event_call=None):
+        """统一日志输出到后端 (print) 和前端 (console.log)"""
+        # 后端日志
+        if self.valves.debug_mode:
+            print(message)

-        elif isinstance(content, str):  # 纯文本
-            message["content"] = summary_block + content
+        # 前端日志
+        if self.valves.show_debug_log and event_call:
+            try:
+                css = "color: #3b82f6;"  # 默认蓝色
+                if type == "error":
+                    css = "color: #ef4444; font-weight: bold;"  # 红色
+                elif type == "warning":
+                    css = "color: #f59e0b;"  # 橙色
+                elif type == "success":
+                    css = "color: #10b981; font-weight: bold;"  # 绿色

-        return message
+                # 清理前端消息：移除分隔符和多余换行
+                lines = message.split("\n")
+                # 保留不以大量等号或连字符开头的行
+                filtered_lines = [
+                    line
+                    for line in lines
+                    if not line.strip().startswith("====")
+                    and not line.strip().startswith("----")
+                ]
+                clean_message = "\n".join(filtered_lines).strip()
+
+                if not clean_message:
+                    return
+
+                # 转义消息中的引号和换行符
+                safe_message = clean_message.replace('"', '\\"').replace("\n", "\\n")
+
+                js_code = f"""
+                    console.log("%c[压缩] {safe_message}", "{css}");
+                """
+                await event_call({"type": "execute", "data": {"code": js_code}})
+            except Exception as e:
+                print(f"发送前端日志失败: {e}")

    async def inlet(
        self,
@@ -508,6 +574,7 @@ class Filter:
        __user__: Optional[dict] = None,
        __metadata__: dict = None,
        __event_emitter__: Callable[[Any], Awaitable[None]] = None,
+        __event_call__: Callable[[Any], Awaitable[None]] = None,
    ) -> dict:
        """
        在发送到 LLM 之前执行
@@ -516,24 +583,24 @@ class Filter:
        messages = body.get("messages", [])
        chat_id = __metadata__["chat_id"]

-        if self.valves.debug_mode:
-            print(f"\n{'='*60}")
-            print(f"[Inlet] Chat ID: {chat_id}")
-            print(f"[Inlet] 收到 {len(messages)} 条消息")
+        if self.valves.debug_mode or self.valves.show_debug_log:
+            await self._log(
+                f"\n{'='*60}\n[Inlet] Chat ID: {chat_id}\n[Inlet] 收到 {len(messages)} 条消息",
+                event_call=__event_call__,
+            )

        # 记录原始消息的目标压缩进度，供 outlet 使用
        # 目标是压缩到倒数第 keep_last 条之前
        target_compressed_count = max(0, len(messages) - self.valves.keep_last)

-        # [优化] 简单的状态清理检查
-        if chat_id in self.temp_state:
-            if self.valves.debug_mode:
-                print(f"[Inlet] ⚠️ 覆盖未消费的旧状态 (Chat ID: {chat_id})")
+        # 记录原始消息的目标压缩进度，供 outlet 使用
+        # 目标是压缩到倒数第 keep_last 条之前
+        target_compressed_count = max(0, len(messages) - self.valves.keep_last)

-        self.temp_state[chat_id] = target_compressed_count
-
-        if self.valves.debug_mode:
-            print(f"[Inlet] 记录目标压缩进度: {target_compressed_count}")
+        await self._log(
+            f"[Inlet] 记录目标压缩进度: {target_compressed_count}",
+            event_call=__event_call__,
+        )

        # 加载摘要记录
        summary_record = await asyncio.to_thread(self._load_summary_record, chat_id)
@@ -561,7 +628,7 @@ class Filter:
                f"---\n"
                f"以下是最近的对话："
            )
-            summary_msg = {"role": "user", "content": summary_content}
+            summary_msg = {"role": "assistant", "content": summary_content}

            # 3. 尾部消息 (Tail) - 从上次压缩点开始的所有消息
            # 注意：这里必须确保不重复包含头部消息
@@ -582,19 +649,32 @@ class Filter:
                    }
                )

-            if self.valves.debug_mode:
-                print(
-                    f"[Inlet] 应用摘要: Head({len(head_messages)}) + Summary + Tail({len(tail_messages)})"
-                )
+            await self._log(
+                f"[Inlet] 应用摘要: Head({len(head_messages)}) + Summary + Tail({len(tail_messages)})",
+                type="success",
+                event_call=__event_call__,
+            )
+
+            # Emit debug log to frontend (Keep the structured log as well)
+            await self._emit_debug_log(
+                __event_call__,
+                chat_id,
+                len(messages),
+                len(final_messages),
+                len(summary_record.summary),
+                self.valves.keep_first,
+                self.valves.keep_last,
+            )
        else:
            # 没有摘要，使用原始消息
            final_messages = messages

        body["messages"] = final_messages

-        if self.valves.debug_mode:
-            print(f"[Inlet] 最终发送: {len(body['messages'])} 条消息")
-            print(f"{'='*60}\n")
+        await self._log(
+            f"[Inlet] 最终发送: {len(body['messages'])} 条消息\n{'='*60}\n",
+            event_call=__event_call__,
+        )

        return body

@@ -604,29 +684,43 @@ class Filter:
        __user__: Optional[dict] = None,
        __metadata__: dict = None,
        __event_emitter__: Callable[[Any], Awaitable[None]] = None,
+        __event_call__: Callable[[Any], Awaitable[None]] = None,
    ) -> dict:
        """
        在 LLM 响应完成后执行
        在后台计算 Token 数并触发摘要生成（不阻塞当前响应，不影响内容输出）
        """
        chat_id = __metadata__["chat_id"]
-        model = body.get("model", "gpt-3.5-turbo")
+        model = body.get("model") or ""

-        if self.valves.debug_mode:
-            print(f"\n{'='*60}")
-            print(f"[Outlet] Chat ID: {chat_id}")
-            print(f"[Outlet] 响应完成")
+        # 直接计算目标压缩进度
+        # 假设 outlet 中的 body['messages'] 包含完整历史（包括新响应）
+        messages = body.get("messages", [])
+        target_compressed_count = max(0, len(messages) - self.valves.keep_last)
+
+        if self.valves.debug_mode or self.valves.show_debug_log:
+            await self._log(
+                f"\n{'='*60}\n[Outlet] Chat ID: {chat_id}\n[Outlet] 响应完成\n[Outlet] 计算目标压缩进度: {target_compressed_count} (消息数: {len(messages)})",
+                event_call=__event_call__,
+            )

        # 在后台异步处理 Token 计算和摘要生成（不等待完成，不影响输出）
        asyncio.create_task(
            self._check_and_generate_summary_async(
-                chat_id, model, body, __user__, __event_emitter__
+                chat_id,
+                model,
+                body,
+                __user__,
+                target_compressed_count,
+                __event_emitter__,
+                __event_call__,
            )
        )

-        if self.valves.debug_mode:
-            print(f"[Outlet] 后台处理已启动")
-            print(f"{'='*60}\n")
+        await self._log(
+            f"[Outlet] 后台处理已启动\n{'='*60}\n",
+            event_call=__event_call__,
+        )

        return body

@@ -636,7 +730,9 @@ class Filter:
        model: str,
        body: dict,
        user_data: Optional[dict],
+        target_compressed_count: Optional[int],
        __event_emitter__: Callable[[Any], Awaitable[None]] = None,
+        __event_call__: Callable[[Any], Awaitable[None]] = None,
    ):
        """
        后台处理：计算 Token 数并生成摘要（不阻塞响应）
@@ -650,36 +746,58 @@ class Filter:
                "compression_threshold_tokens", self.valves.compression_threshold_tokens
            )

-            if self.valves.debug_mode:
-                print(f"\n[🔍 后台计算] 开始 Token 计数...")
+            await self._log(
+                f"\n[🔍 后台计算] 开始 Token 计数...",
+                event_call=__event_call__,
+            )

            # 在后台线程中计算 Token 数
            current_tokens = await asyncio.to_thread(
                self._calculate_messages_tokens, messages
            )

-            if self.valves.debug_mode:
-                print(f"[🔍 后台计算] Token 数: {current_tokens}")
+            await self._log(
+                f"[🔍 后台计算] Token 数: {current_tokens}",
+                event_call=__event_call__,
+            )

            # 检查是否需要压缩
            if current_tokens >= compression_threshold_tokens:
-                if self.valves.debug_mode:
-                    print(
-                        f"[🔍 后台计算] ⚡ 触发压缩阈值 (Token: {current_tokens} >= {compression_threshold_tokens})"
-                    )
+                await self._log(
+                    f"[🔍 后台计算] ⚡ 触发压缩阈值 (Token: {current_tokens} >= {compression_threshold_tokens})",
+                    type="warning",
+                    event_call=__event_call__,
+                )

                # 继续生成摘要
                await self._generate_summary_async(
-                    messages, chat_id, body, user_data, __event_emitter__
+                    messages,
+                    chat_id,
+                    body,
+                    user_data,
+                    target_compressed_count,
+                    __event_emitter__,
+                    __event_call__,
                )
            else:
-                if self.valves.debug_mode:
-                    print(
-                        f"[🔍 后台计算] 未触发压缩阈值 (Token: {current_tokens} < {compression_threshold_tokens})"
-                    )
+                await self._log(
+                    f"[🔍 后台计算] 未触发压缩阈值 (Token: {current_tokens} < {compression_threshold_tokens})",
+                    event_call=__event_call__,
+                )

        except Exception as e:
-            print(f"[🔍 后台计算] ❌ 错误: {str(e)}")
+            await self._log(
+                f"[🔍 后台计算] ❌ 错误: {str(e)}",
+                type="error",
+                event_call=__event_call__,
+            )
+
+    def _clean_model_id(self, model_id: Optional[str]) -> Optional[str]:
+        """Cleans the model ID by removing whitespace and quotes."""
+        if not model_id:
+            return None
+        cleaned = model_id.strip().strip('"').strip("'")
+        return cleaned if cleaned else None

    async def _generate_summary_async(
        self,
@@ -687,7 +805,9 @@ class Filter:
        chat_id: str,
        body: dict,
        user_data: Optional[dict],
+        target_compressed_count: Optional[int],
        __event_emitter__: Callable[[Any], Awaitable[None]] = None,
+        __event_call__: Callable[[Any], Awaitable[None]] = None,
    ):
        """
        异步生成摘要（后台执行，不阻塞响应）
@@ -697,18 +817,17 @@ class Filter:
        3. 对剩余的中间消息生成摘要。
        """
        try:
-            if self.valves.debug_mode:
-                print(f"\n[🤖 异步摘要任务] 开始...")
+            await self._log(f"\n[🤖 异步摘要任务] 开始...", event_call=__event_call__)

            # 1. 获取目标压缩进度
-            # 优先从 temp_state 获取（由 inlet 计算），如果获取不到（例如重启后），则假设当前是完整历史
-            target_compressed_count = self.temp_state.pop(chat_id, None)
+            # 如果未传递 target_compressed_count（新逻辑下不应发生），则进行估算
            if target_compressed_count is None:
                target_compressed_count = max(0, len(messages) - self.valves.keep_last)
-                if self.valves.debug_mode:
-                    print(
-                        f"[🤖 异步摘要任务] ⚠️ 无法获取 inlet 状态，使用当前消息数估算进度: {target_compressed_count}"
-                    )
+                await self._log(
+                    f"[🤖 异步摘要任务] ⚠️ target_compressed_count 为 None，进行估算: {target_compressed_count}",
+                    type="warning",
+                    event_call=__event_call__,
+                )

            # 2. 确定待压缩的消息范围 (Middle)
            start_index = self.valves.keep_first
@@ -718,21 +837,33 @@ class Filter:

            # 确保索引有效
            if start_index >= end_index:
-                if self.valves.debug_mode:
-                    print(
-                        f"[🤖 异步摘要任务] 中间消息为空 (Start: {start_index}, End: {end_index})，跳过"
-                    )
+                await self._log(
+                    f"[🤖 异步摘要任务] 中间消息为空 (Start: {start_index}, End: {end_index})，跳过",
+                    event_call=__event_call__,
+                )
                return

            middle_messages = messages[start_index:end_index]

-            if self.valves.debug_mode:
-                print(f"[🤖 异步摘要任务] 待处理中间消息: {len(middle_messages)} 条")
+            await self._log(
+                f"[🤖 异步摘要任务] 待处理中间消息: {len(middle_messages)} 条",
+                event_call=__event_call__,
+            )

            # 3. 检查 Token 上限并截断 (Max Context Truncation)
            # [优化] 使用摘要模型(如果有)的阈值来决定能处理多少中间消息
            # 这样可以用长窗口模型(如 gemini-flash)来压缩超过当前模型窗口的历史记录
-            summary_model_id = self.valves.summary_model or body.get("model")
+            summary_model_id = self._clean_model_id(
+                self.valves.summary_model
+            ) or self._clean_model_id(body.get("model"))
+
+            if not summary_model_id:
+                await self._log(
+                    "[🤖 异步摘要任务] ⚠️ 摘要模型不存在，跳过压缩",
+                    type="warning",
+                    event_call=__event_call__,
+                )
+                return

            thresholds = self._get_model_thresholds(summary_model_id)
            # 注意：这里使用的是摘要模型的最大上下文限制
@@ -740,22 +871,26 @@ class Filter:
                "max_context_tokens", self.valves.max_context_tokens
            )

-            if self.valves.debug_mode:
-                print(
-                    f"[🤖 异步摘要任务] 使用模型 {summary_model_id} 的上限: {max_context_tokens} Tokens"
-                )
-
-            # 计算当前总 Token (使用摘要模型进行计数)
-            total_tokens = await asyncio.to_thread(
-                self._calculate_messages_tokens, messages
+            await self._log(
+                f"[🤖 异步摘要任务] 使用模型 {summary_model_id} 的上限: {max_context_tokens} Tokens",
+                event_call=__event_call__,
            )

-            if total_tokens > max_context_tokens:
-                excess_tokens = total_tokens - max_context_tokens
-                if self.valves.debug_mode:
-                    print(
-                        f"[🤖 异步摘要任务] ⚠️ 总 Token ({total_tokens}) 超过摘要模型上限 ({max_context_tokens})，需要移除约 {excess_tokens} Token"
-                    )
+            # 计算中间消息的 Token (加上提示词的缓冲)
+            # 我们只把 middle_messages 发送给摘要模型，所以不应该把完整历史计入限制
+            middle_tokens = await asyncio.to_thread(
+                self._calculate_messages_tokens, middle_messages
+            )
+            # 增加提示词和输出的缓冲 (约 2000 Tokens)
+            estimated_input_tokens = middle_tokens + 2000
+
+            if estimated_input_tokens > max_context_tokens:
+                excess_tokens = estimated_input_tokens - max_context_tokens
+                await self._log(
+                    f"[🤖 异步摘要任务] ⚠️ 中间消息 ({middle_tokens} Tokens) + 缓冲超过摘要模型上限 ({max_context_tokens})，需要移除约 {excess_tokens} Token",
+                    type="warning",
+                    event_call=__event_call__,
+                )

                # 从 middle_messages 头部开始移除
                removed_tokens = 0
@@ -769,14 +904,16 @@ class Filter:
                    removed_tokens += msg_tokens
                    removed_count += 1

-                if self.valves.debug_mode:
-                    print(
-                        f"[🤖 异步摘要任务] 已移除 {removed_count} 条消息，共 {removed_tokens} Token"
-                    )
+                await self._log(
+                    f"[🤖 异步摘要任务] 已移除 {removed_count} 条消息，共 {removed_tokens} Token",
+                    event_call=__event_call__,
+                )

            if not middle_messages:
-                if self.valves.debug_mode:
-                    print(f"[🤖 异步摘要任务] 截断后中间消息为空，跳过摘要生成")
+                await self._log(
+                    f"[🤖 异步摘要任务] 截断后中间消息为空，跳过摘要生成",
+                    event_call=__event_call__,
+                )
                return

            # 4. 构建对话文本
@@ -798,12 +935,26 @@ class Filter:
                )

            new_summary = await self._call_summary_llm(
-                None, conversation_text, body, user_data
+                None,
+                conversation_text,
+                {**body, "model": summary_model_id},
+                user_data,
+                __event_call__,
            )

+            if not new_summary:
+                await self._log(
+                    "[🤖 异步摘要任务] ⚠️ 摘要生成返回空结果，跳过保存",
+                    type="warning",
+                    event_call=__event_call__,
+                )
+                return
+
            # 6. 保存新摘要
-            if self.valves.debug_mode:
-                print("[优化] 正在后台线程中保存摘要，以避免阻塞事件循环。")
+            await self._log(
+                "[优化] 在后台线程中保存摘要以避免阻塞事件循环。",
+                event_call=__event_call__,
+            )

            await asyncio.to_thread(
                self._save_summary, chat_id, new_summary, target_compressed_count
@@ -815,32 +966,52 @@ class Filter:
                    {
                        "type": "status",
                        "data": {
-                            "description": f"上下文摘要已更新 (已压缩 {len(middle_messages)} 条消息)",
+                            "description": f"上下文摘要已更新 (压缩了 {len(middle_messages)} 条消息)",
                            "done": True,
                        },
                    }
                )

-            if self.valves.debug_mode:
-                print(f"[🤖 异步摘要任务] ✅ 完成！新摘要长度: {len(new_summary)} 字符")
-                print(
-                    f"[🤖 异步摘要任务] 进度更新: 已压缩至原始第 {target_compressed_count} 条消息"
-                )
+            await self._log(
+                f"[🤖 异步摘要任务] ✅ 完成！新摘要长度: {len(new_summary)} 字符",
+                type="success",
+                event_call=__event_call__,
+            )
+            await self._log(
+                f"[🤖 异步摘要任务] 进度更新: 已压缩至原始消息 {target_compressed_count}",
+                event_call=__event_call__,
+            )

        except Exception as e:
-            print(f"[🤖 异步摘要任务] ❌ 错误: {str(e)}")
+            await self._log(
+                f"[🤖 异步摘要任务] ❌ 错误: {str(e)}",
+                type="error",
+                event_call=__event_call__,
+            )
+
+            if __event_emitter__:
+                await __event_emitter__(
+                    {
+                        "type": "status",
+                        "data": {
+                            "description": f"摘要生成错误: {str(e)[:100]}...",
+                            "done": True,
+                        },
+                    }
+                )
+
            import traceback

            traceback.print_exc()

    def _format_messages_for_summary(self, messages: list) -> str:
-        """格式化消息用于摘要"""
+        """Formats messages for summarization."""
        formatted = []
        for i, msg in enumerate(messages, 1):
            role = msg.get("role", "unknown")
            content = msg.get("content", "")

-            # 处理多模态内容
+            # Handle multimodal content
            if isinstance(content, list):
                text_parts = []
                for part in content:
@@ -848,10 +1019,10 @@ class Filter:
                        text_parts.append(part.get("text", ""))
                content = " ".join(text_parts)

-            # 处理角色名称
-            role_name = {"user": "用户", "assistant": "助手"}.get(role, role)
+            # Handle role name
+            role_name = {"user": "User", "assistant": "Assistant"}.get(role, role)

-            # 限制每条消息的长度，避免过长
+            # Limit length of each message to avoid excessive length
            if len(content) > 500:
                content = content[:500] + "..."

@@ -865,12 +1036,15 @@ class Filter:
        new_conversation_text: str,
        body: dict,
        user_data: dict,
+        __event_call__: Callable[[Any], Awaitable[None]] = None,
    ) -> str:
        """
-        使用 Open WebUI 内置方法调用 LLM 生成摘要
+        调用 LLM 生成摘要，使用 Open Web UI 的内置方法。
        """
-        if self.valves.debug_mode:
-            print(f"[🤖 LLM 调用] 使用 Open WebUI 内置方法")
+        await self._log(
+            f"[🤖 LLM 调用] 使用 Open Web UI 内置方法",
+            event_call=__event_call__,
+        )

        # 构建摘要提示词 (优化版)
        summary_prompt = f"""
@@ -907,10 +1081,19 @@ class Filter:
 请根据上述内容，生成摘要：
 """
        # 确定使用的模型
-        model = self.valves.summary_model or body.get("model", "")
+        model = self._clean_model_id(self.valves.summary_model) or self._clean_model_id(
+            body.get("model")
+        )

-        if self.valves.debug_mode:
-            print(f"[🤖 LLM 调用] 模型: {model}")
+        if not model:
+            await self._log(
+                "[🤖 LLM 调用] ⚠️ 摘要模型不存在，跳过摘要生成",
+                type="warning",
+                event_call=__event_call__,
+            )
+            return ""
+
+        await self._log(f"[🤖 LLM 调用] 模型: {model}", event_call=__event_call__)

        # 构建 payload
        payload = {
@@ -927,17 +1110,20 @@ class Filter:
            if not user_id:
                raise ValueError("无法获取用户 ID")

-            # [优化] 在后台线程中获取用户对象，以避免阻塞事件循环
-            if self.valves.debug_mode:
-                print("[优化] 正在后台线程中获取用户对象，以避免阻塞事件循环。")
+            # [优化] 在后台线程中获取用户对象以避免阻塞事件循环
+            await self._log(
+                "[优化] 在后台线程中获取用户对象以避免阻塞事件循环。",
+                event_call=__event_call__,
+            )
            user = await asyncio.to_thread(Users.get_user_by_id, user_id)

            if not user:
                raise ValueError(f"无法找到用户: {user_id}")

-            if self.valves.debug_mode:
-                print(f"[🤖 LLM 调用] 用户: {user.email}")
-                print(f"[🤖 LLM 调用] 发送请求...")
+            await self._log(
+                f"[🤖 LLM 调用] 用户: {user.email}\n[🤖 LLM 调用] 发送请求...",
+                event_call=__event_call__,
+            )

            # 创建 Request 对象
            request = Request(scope={"type": "http", "app": webui_app})
@@ -950,20 +1136,31 @@ class Filter:

            summary = response["choices"][0]["message"]["content"].strip()

-            if self.valves.debug_mode:
-                print(f"[🤖 LLM 调用] ✅ 成功获取摘要")
+            await self._log(
+                f"[🤖 LLM 调用] ✅ 成功接收摘要",
+                type="success",
+                event_call=__event_call__,
+            )

            return summary

        except Exception as e:
-            error_message = f"调用 LLM ({model}) 生成摘要时发生错误: {str(e)}"
+            error_msg = str(e)
+            # Handle specific error messages
+            if "Model not found" in error_msg:
+                error_message = f"摘要模型 '{model}' 不存在。"
+            else:
+                error_message = f"摘要 LLM 错误 ({model}): {error_msg}"
            if not self.valves.summary_model:
                error_message += (
-                    "\n[提示] 您没有指定摘要模型 (summary_model)，因此尝试使用当前对话的模型。"
-                    "如果这是一个流水线（Pipe）模型或不兼容的模型，请在配置中指定一个兼容的摘要模型（如 'gemini-2.5-flash'）。"
+                    "\n[提示] 您未指定 summary_model，因此过滤器尝试使用当前对话的模型。"
+                    "如果这是流水线 (Pipe) 模型或不兼容的模型，请在配置中指定兼容的摘要模型 (例如 'gemini-2.5-flash')。"
                )

-            if self.valves.debug_mode:
-                print(f"[🤖 LLM 调用] ❌ {error_message}")
+            await self._log(
+                f"[🤖 LLM 调用] ❌ {error_message}",
+                type="error",
+                event_call=__event_call__,
+            )

            raise Exception(error_message)
--- a/plugins/filters/context_enhancement_filter/context_enhancement_filter.py
+++ b/plugins/filters/context_enhancement_filter/context_enhancement_filter.py
@@ -1,12 +1,9 @@
 """
 title: Context & Model Enhancement Filter
-author: Fu-Jie
-author_url: https://github.com/Fu-Jie
-funding_url: https://github.com/Fu-Jie/awesome-openwebui
-version: 0.2
+version: 0.3

 description:
-    一个功能全面的 Filter 插件，用于增强请求上下文和优化模型功能。提供四大核心功能：
+    一个专注于增强请求上下文和优化模型功能的 Filter 插件。提供三大核心功能：

    1. 环境变量注入：在每条用户消息前自动注入用户环境变量（用户名、时间、时区、语言等）
       - 支持纯文本、图片、多模态消息
@@ -24,222 +21,24 @@ description:
       - 动态模型重定向
       - 智能化的模型识别和适配

-    4. 智能内容规范化：生产级的内容清洗与修复系统
-       - 智能修复损坏的代码块（前缀、后缀、缩进）
-       - 规范化 LaTeX 公式格式（行内/块级）
-       - 优化思维链标签（</thought>）格式
-       - 自动闭合未结束的代码块
-       - 智能列表格式修复
-       - 清理冗余的 XML 标签
-       - 可配置的规则系统
-
 features:
    - 自动化环境变量管理
    - 智能模型功能适配
    - 异步状态反馈
    - 幂等性保证
    - 多模型支持
-    - 智能内容清洗与规范化
 """

 from pydantic import BaseModel, Field
-from typing import Optional, List, Callable
+from typing import Optional
 import re
 import logging
-from dataclasses import dataclass, field
+import asyncio


 # 配置日志
 logger = logging.getLogger(__name__)

-@dataclass
-class NormalizerConfig:
-    """规范化配置类,用于动态启用/禁用特定规则"""
-    enable_escape_fix: bool = True          # 修复转义字符
-    enable_thought_tag_fix: bool = True     # 修复思考链标签
-    enable_code_block_fix: bool = True      # 修复代码块格式
-    enable_latex_fix: bool = True           # 修复 LaTeX 公式格式
-    enable_list_fix: bool = False            # 修复列表换行
-    enable_unclosed_block_fix: bool = True  # 修复未闭合代码块
-    enable_fullwidth_symbol_fix: bool = False # 修复代码内的全角符号
-    enable_xml_tag_cleanup: bool = True     # 清理 XML 残留标签
-    
-    # 自定义清理函数列表（高级扩展用）
-    custom_cleaners: List[Callable[[str], str]] = field(default_factory=list)
-
-class ContentNormalizer:
-    """LLM 输出内容规范化器 - 生产级实现"""
-    
-    # --- 1. 预编译正则表达式（性能优化） ---
-    _PATTERNS = {
-        # 代码块前缀：如果 ``` 前面不是行首也不是换行符
-        'code_block_prefix': re.compile(r'(?<!^)(?<!\n)(```)', re.MULTILINE),
-        
-        # 代码块后缀：匹配 ```语言名 后面紧跟非空白字符(没有换行)
-        # 匹配 ```python code 这种情况，但不匹配 ```python 或 ```python\n
-        'code_block_suffix': re.compile(r'(```[\w\+\-\.]*)[ \t]+([^\n\r])'),
-        
-        # 代码块缩进：行首的空白字符 + ```
-        'code_block_indent': re.compile(r'^[ \t]+(```)', re.MULTILINE),
-        
-        # 思考链标签：</thought> 后可能跟空格或换行
-        'thought_tag': re.compile(r'</thought>[ \t]*\n*'),
-        
-        # LaTeX 块级公式：\[ ... \]
-        'latex_bracket_block': re.compile(r'\\\[(.+?)\\\]', re.DOTALL),
-        # LaTeX 行内公式：\( ... \)
-        'latex_paren_inline': re.compile(r'\\\((.+?)\\\)'),
-        
-        # 列表项：非换行符 + 数字 + 点 + 空格 (e.g. "Text1. Item")
-        'list_item': re.compile(r'([^\n])(\d+\. )'),
-        
-        # XML 残留标签 (如 Claude 的 artifacts)
-        'xml_artifacts': re.compile(r'</?(?:antArtifact|antThinking|artifact)[^>]*>', re.IGNORECASE),
-    }
-    
-    def __init__(self, config: Optional[NormalizerConfig] = None):
-        self.config = config or NormalizerConfig()
-        self.applied_fixes = []
-    
-    def normalize(self, content: str) -> str:
-        """主入口：按顺序应用所有规范化规则"""
-        self.applied_fixes = []
-        if not content:
-            return content
-        
-        try:
-            # 1. 转义字符修复（必须最先执行，否则影响后续正则）
-            if self.config.enable_escape_fix:
-                original = content
-                content = self._fix_escape_characters(content)
-                if content != original:
-                    self.applied_fixes.append("修复转义字符")
-            
-            # 2. 思考链标签规范化
-            if self.config.enable_thought_tag_fix:
-                original = content
-                content = self._fix_thought_tags(content)
-                if content != original:
-                    self.applied_fixes.append("规范化思考链")
-            
-            # 3. 代码块格式修复
-            if self.config.enable_code_block_fix:
-                original = content
-                content = self._fix_code_blocks(content)
-                if content != original:
-                    self.applied_fixes.append("修复代码块格式")
-            
-            # 4. LaTeX 公式规范化
-            if self.config.enable_latex_fix:
-                original = content
-                content = self._fix_latex_formulas(content)
-                if content != original:
-                    self.applied_fixes.append("规范化 LaTeX 公式")
-            
-            # 5. 列表格式修复
-            if self.config.enable_list_fix:
-                original = content
-                content = self._fix_list_formatting(content)
-                if content != original:
-                    self.applied_fixes.append("修复列表格式")
-            
-            # 6. 未闭合代码块检测与修复
-            if self.config.enable_unclosed_block_fix:
-                original = content
-                content = self._fix_unclosed_code_blocks(content)
-                if content != original:
-                    self.applied_fixes.append("闭合未结束代码块")
-            
-            # 7. 全角符号转半角（仅代码块内）
-            if self.config.enable_fullwidth_symbol_fix:
-                original = content
-                content = self._fix_fullwidth_symbols_in_code(content)
-                if content != original:
-                    self.applied_fixes.append("全角符号转半角")
-            
-            # 8. XML 标签残留清理
-            if self.config.enable_xml_tag_cleanup:
-                original = content
-                content = self._cleanup_xml_tags(content)
-                if content != original:
-                    self.applied_fixes.append("清理 XML 标签")
-            
-            # 9. 执行自定义清理函数
-            for cleaner in self.config.custom_cleaners:
-                original = content
-                content = cleaner(content)
-                if content != original:
-                    self.applied_fixes.append("执行自定义清理")
-            
-            return content
-            
-        except Exception as e:
-            # 生产环境保底机制：如果清洗过程报错，返回原始内容，避免阻断服务
-            logger.error(f"内容规范化失败: {e}", exc_info=True)
-            return content
-    
-    def _fix_escape_characters(self, content: str) -> str:
-        """修复过度转义的字符"""
-        # 注意：先处理具体的转义序列，再处理通用的双反斜杠
-        content = content.replace("\\r\\n", "\n")
-        content = content.replace("\\n", "\n")
-        content = content.replace("\\t", "\t")
-        # 修复过度转义的反斜杠 (例如路径 C:\\Users)
-        content = content.replace("\\\\", "\\")
-        return content
-    
-    def _fix_thought_tags(self, content: str) -> str:
-        """规范化 </thought> 标签，统一为空两行"""
-        return self._PATTERNS['thought_tag'].sub("</thought>\n\n", content)
-    
-    def _fix_code_blocks(self, content: str) -> str:
-        """修复代码块格式（独占行、换行、去缩进）"""
-        # C: 移除代码块前的缩进（必须先执行，否则影响下面的判断）
-        content = self._PATTERNS['code_block_indent'].sub(r"\1", content)
-        # A: 确保 ``` 前有换行
-        content = self._PATTERNS['code_block_prefix'].sub(r"\n\1", content)
-        # B: 确保 ```语言标识 后有换行
-        content = self._PATTERNS['code_block_suffix'].sub(r"\1\n\2", content)
-        return content
-    
-    def _fix_latex_formulas(self, content: str) -> str:
-        """规范化 LaTeX 公式：\[ -> $$ (块级), \( -> $ (行内)"""
-        content = self._PATTERNS['latex_bracket_block'].sub(r"$$\1$$", content)
-        content = self._PATTERNS['latex_paren_inline'].sub(r"$\1$", content)
-        return content
-    
-    def _fix_list_formatting(self, content: str) -> str:
-        """修复列表项缺少换行的问题 (如 'text1. item' -> 'text\\n1. item')"""
-        return self._PATTERNS['list_item'].sub(r"\1\n\2", content)
-    
-    def _fix_unclosed_code_blocks(self, content: str) -> str:
-        """检测并修复未闭合的代码块"""
-        if content.count("```") % 2 != 0:
-            logger.warning("检测到未闭合的代码块，自动补全")
-            content += "\n```"
-        return content
-    
-    def _fix_fullwidth_symbols_in_code(self, content: str) -> str:
-        """在代码块内将全角符号转为半角（精细化操作）"""
-        # 常见误用的全角符号映射
-        FULLWIDTH_MAP = {
-            '，': ',', '。': '.', '（': '(', '）': ')',
-            '【': '[', '】': ']', '；': ';', '：': ':',
-            '？': '?', '！': '!', '"': '"', '"': '"',
-            ''': "'", ''': "'",
-        }
-        
-        parts = content.split("```")
-        # 代码块内容位于索引 1, 3, 5... (奇数位)
-        for i in range(1, len(parts), 2):
-            for full, half in FULLWIDTH_MAP.items():
-                parts[i] = parts[i].replace(full, half)
-        
-        return "```".join(parts)
-    
-    def _cleanup_xml_tags(self, content: str) -> str:
-        """移除无关的 XML 标签"""
-        return self._PATTERNS['xml_artifacts'].sub("", content)

 class Filter:
    class Valves(BaseModel):
@@ -349,13 +148,9 @@ class Filter:
                body["model"] = body["model"] + "-search"
                features["web_search"] = False
                search_enabled_for_model = True
-            if user_email == "yi204o@qq.com":
-                features["web_search"] = False

        # 如果启用了模型本身的搜索能力，发送状态提示
        if search_enabled_for_model and __event_emitter__:
-            import asyncio
-
            try:
                asyncio.create_task(
                    self._emit_search_status(__event_emitter__, model_name)
@@ -464,8 +259,6 @@ class Filter:

            # 环境变量注入成功后，发送状态提示给用户
            if env_injected and __event_emitter__:
-                import asyncio
-
                try:
                    # 如果在异步环境中，使用 await
                    asyncio.create_task(self._emit_env_status(__event_emitter__))
@@ -506,67 +299,3 @@ class Filter:
            )
        except Exception as e:
            print(f"发送搜索状态提示时出错: {e}")
-
-    async def _emit_normalization_status(self, __event_emitter__, applied_fixes: List[str] = None):
-        """
-        发送内容规范化完成的状态提示
-        """
-        description = "✓ 内容已自动规范化"
-        if applied_fixes:
-            description += f"：{', '.join(applied_fixes)}"
-
-        try:
-            await __event_emitter__(
-                {
-                    "type": "status",
-                    "data": {
-                        "description": description,
-                        "done": True,
-                    },
-                }
-            )
-        except Exception as e:
-            print(f"发送规范化状态提示时出错: {e}")
-
-    def _contains_html(self, content: str) -> bool:
-        """
-        检测内容是否包含 HTML 标签
-        """
-        # 匹配常见的 HTML 标签
-        pattern = r"<\s*/?\s*(?:html|head|body|div|span|p|br|hr|ul|ol|li|table|thead|tbody|tfoot|tr|td|th|img|a|b|i|strong|em|code|pre|blockquote|h[1-6]|script|style|form|input|button|label|select|option|iframe|link|meta|title)\b"
-        return bool(re.search(pattern, content, re.IGNORECASE))
-
-    def outlet(self, body: dict, __user__: Optional[dict] = None, __event_emitter__=None) -> dict:
-        """
-        处理传出响应体，通过修改最后一条助手消息的内容。
-        使用 ContentNormalizer 进行全面的内容规范化。
-        """
-        if "messages" in body and body["messages"]:
-            last = body["messages"][-1]
-            content = last.get("content", "") or ""
-            
-            if last.get("role") == "assistant" and isinstance(content, str):
-                # 如果包含 HTML，跳过规范化，为了防止错误格式化
-                if self._contains_html(content):
-                    return body
-
-                # 初始化规范化器
-                normalizer = ContentNormalizer()
-                
-                # 执行规范化
-                new_content = normalizer.normalize(content)
-                
-                # 更新内容
-                if new_content != content:
-                    last["content"] = new_content
-                    # 如果内容发生了改变，发送状态提示
-                    if __event_emitter__:
-                        import asyncio
-                        try:
-                            # 传入 applied_fixes
-                            asyncio.create_task(self._emit_normalization_status(__event_emitter__, normalizer.applied_fixes))
-                        except RuntimeError:
-                            # 假如不在循环中，则忽略
-                            pass
-        
-        return body
--- a/plugins/filters/markdown_normalizer/FEATURES_CN.md
+++ b/plugins/filters/markdown_normalizer/FEATURES_CN.md
@@ -0,0 +1,162 @@
+# Markdown Normalizer 功能详解
+
+本插件旨在修复 LLM 输出中常见的 Markdown 格式问题，确保在 Open WebUI 中完美渲染。以下是支持的修复功能列表及示例。
+
+## 1. 代码块修复 (Code Block Fixes)
+
+### 1.1 去除代码块缩进
+LLM 有时会在代码块前添加空格缩进，导致渲染失效。本插件会自动移除这些缩进。
+
+**Before:**
+   ```python
+   print("hello")
+   ```
+
+**After:**
+```python
+print("hello")
+```
+
+### 1.2 补全代码块前后换行
+代码块标记 ` ``` ` 必须独占一行。如果 LLM 将其与文本混在一行，插件会自动修复。
+
+**Before:**
+Here is code:```python
+print("hello")```
+
+**After:**
+Here is code:
+```python
+print("hello")
+```
+
+### 1.3 修复语言标识符后的换行
+有时 LLM 会忘记在语言标识符（如 `python`）后换行。
+
+**Before:**
+```python print("hello")
+```
+
+**After:**
+```python
+print("hello")
+```
+
+### 1.4 自动闭合代码块
+如果输出被截断或 LLM 忘记闭合代码块，插件会自动添加结尾的 ` ``` `。
+
+**Before:**
+```python
+print("unfinished code...")
+
+**After:**
+```python
+print("unfinished code...")
+```
+
+## 2. LaTeX 公式规范化 (LaTeX Normalization)
+
+Open WebUI 使用 MathJax/KaTeX 渲染公式，通常需要 `$$` 或 `$` 包裹。本插件会将常见的 LaTeX 括号语法转换为标准格式。
+
+**Before:**
+块级公式：\[ E = mc^2 \]
+行内公式：\( a^2 + b^2 = c^2 \)
+
+**After:**
+块级公式：$$ E = mc^2 $$
+行内公式：$ a^2 + b^2 = c^2 $
+
+## 3. 转义字符清理 (Escape Character Fix)
+
+修复过度转义的字符，这常见于某些 API 返回的原始字符串中。
+
+**Before:**
+Line 1\\nLine 2\\tTabbed
+
+**After:**
+Line 1
+Line 2	Tabbed
+
+## 4. 思维链标签规范化 (Thought Tag Fix)
+**功能**: 
+1.  确保 `</thought>` 标签后有足够的空行，防止思维链内容与正文粘连。
+2.  **标准化标签**: 将 `<think>` (DeepSeek 等模型常用) 或 `<thinking>` 统一转换为 Open WebUI 标准的 `<thought>` 标签，以便正确触发 UI 的折叠功能。
+
+**默认**: 开启 (`enable_thought_tag_fix = True`)
+
+**示例**:
+*   **Before**: `<think>Thinking...</think>Response starts here.`
+*   **After**: 
+    ```xml
+    <thought>Thinking...</thought>
+
+    Response starts here.
+    ```
+
+## 5. 列表格式修复 (List Formatting Fix)
+
+*默认关闭，需在设置中开启*
+
+修复列表项缺少换行的问题。
+
+**Before:**
+Header1. Item 1
+
+**After:**
+Header
+1. Item 1
+
+## 6. 全角符号转半角 (Full-width Symbol Fix)
+
+*默认关闭，需在设置中开启*
+
+仅在**代码块内部**将全角符号转换为半角符号，防止代码因符号问题无法运行。
+
+**Before:**
+```python
+if x == 1：
+    print（"hello"）
+```
+
+**After:**
+```python
+if x == 1:
+    print("hello")
+```
+
+## 7. Mermaid 语法修复 (Mermaid Syntax Fix)
+**功能**: 修复 Mermaid 图表中常见的语法错误，特别是未加引号的标签包含特殊字符的情况。
+**默认**: 开启 (`enable_mermaid_fix = True`)
+**示例**:
+*   **Before**:
+    ```mermaid
+    graph TD
+    A[Label with (parens)] --> B(Label with [brackets])
+    ```
+*   **After**:
+    ```mermaid
+    graph TD
+    A["Label with (parens)"] --> B("Label with [brackets]")
+    ```
+
+## 8. XML 标签清理 (XML Cleanup)
+
+移除 LLM 输出中残留的无用 XML 标签（如 Claude 的 artifact 标签）。
+
+**Before:**
+Here is the result <antArtifact>hidden metadata</antArtifact>.
+
+**After:**
+## 9. 标题格式修复 (Heading Format Fix)
+**功能**: 修复标题标记 `#` 后缺少空格的问题。
+**默认**: 开启 (`enable_heading_fix = True`)
+**示例**:
+*   **Before**: `#Heading 1`
+*   **After**: `# Heading 1`
+
+## 10. 表格格式修复 (Table Format Fix)
+**功能**: 修复表格行末尾缺少管道符 `|` 的问题。
+**默认**: 开启 (`enable_table_fix = True`)
+**示例**:
+*   **Before**: `| Col 1 | Col 2`
+*   **After**: `| Col 1 | Col 2 |`
--- a/plugins/filters/markdown_normalizer/README.md
+++ b/plugins/filters/markdown_normalizer/README.md
@@ -0,0 +1,46 @@
+# Markdown Normalizer Filter
+
+A production-grade content normalizer filter for Open WebUI that fixes common Markdown formatting issues in LLM outputs. It ensures that code blocks, LaTeX formulas, Mermaid diagrams, and other Markdown elements are rendered correctly.
+
+## Features
+
+*   **Mermaid Syntax Fix**: Automatically fixes common Mermaid syntax errors, such as unquoted node labels (including multi-line labels and citations) and unclosed subgraphs, ensuring diagrams render correctly.
+*   **Frontend Console Debugging**: Supports printing structured debug logs directly to the browser console (F12) for easier troubleshooting.
+*   **Code Block Formatting**: Fixes broken code block prefixes, suffixes, and indentation.
+*   **LaTeX Normalization**: Standardizes LaTeX formula delimiters (`\[` -> `$$`, `\(` -> `$`).
+*   **Thought Tag Normalization**: Unifies thought tags (`<think>`, `<thinking>` -> `<thought>`).
+*   **Escape Character Fix**: Cleans up excessive escape characters (`\\n`, `\\t`).
+*   **List Formatting**: Ensures proper newlines in list items.
+*   **Heading Fix**: Adds missing spaces in headings (`#Heading` -> `# Heading`).
+*   **Table Fix**: Adds missing closing pipes in tables.
+*   **XML Cleanup**: Removes leftover XML artifacts.
+
+## Usage
+
+1.  Install the plugin in Open WebUI.
+2.  Enable the filter globally or for specific models.
+3.  Configure the enabled fixes in the **Valves** settings.
+4.  (Optional) **Show Debug Log** is enabled by default in Valves. This prints structured logs to the browser console (F12).
+    > [!WARNING]
+    > As this is an initial version, some "negative fixes" might occur (e.g., breaking valid Markdown). If you encounter issues, please check the console logs, copy the "Original" vs "Normalized" content, and submit an issue.
+
+## Configuration (Valves)
+
+*   `priority`: Filter priority (default: 50).
+*   `enable_escape_fix`: Fix excessive escape characters.
+*   `enable_thought_tag_fix`: Normalize thought tags.
+*   `enable_code_block_fix`: Fix code block formatting.
+*   `enable_latex_fix`: Normalize LaTeX formulas.
+*   `enable_list_fix`: Fix list item newlines (Experimental).
+*   `enable_unclosed_block_fix`: Auto-close unclosed code blocks.
+*   `enable_fullwidth_symbol_fix`: Fix full-width symbols in code blocks.
+*   `enable_mermaid_fix`: Fix Mermaid syntax errors.
+*   `enable_heading_fix`: Fix missing space in headings.
+*   `enable_table_fix`: Fix missing closing pipe in tables.
+*   `enable_xml_tag_cleanup`: Cleanup leftover XML tags.
+*   `show_status`: Show status notification when fixes are applied.
+*   `show_debug_log`: Print debug logs to browser console.
+
+## License
+
+MIT
--- a/plugins/filters/markdown_normalizer/README_CN.md
+++ b/plugins/filters/markdown_normalizer/README_CN.md
@@ -0,0 +1,46 @@
+# Markdown 格式化过滤器 (Markdown Normalizer)
+
+这是一个用于 Open WebUI 的生产级内容格式化过滤器，旨在修复 LLM 输出中常见的 Markdown 格式问题。它能确保代码块、LaTeX 公式、Mermaid 图表和其他 Markdown 元素被正确渲染。
+
+## 功能特性
+
+*   **Mermaid 语法修复**: 自动修复常见的 Mermaid 语法错误，如未加引号的节点标签（支持多行标签和引用标记）和未闭合的子图 (Subgraph)，确保图表能正确渲染。
+*   **前端控制台调试**: 支持将结构化的调试日志直接打印到浏览器控制台 (F12)，方便排查问题。
+*   **代码块格式化**: 修复破损的代码块前缀、后缀和缩进问题。
+*   **LaTeX 规范化**: 标准化 LaTeX 公式定界符 (`\[` -> `$$`, `\(` -> `$`)。
+*   **思维标签规范化**: 统一思维链标签 (`<think>`, `<thinking>` -> `<thought>`)。
+*   **转义字符修复**: 清理过度的转义字符 (`\\n`, `\\t`)。
+*   **列表格式化**: 确保列表项有正确的换行。
+*   **标题修复**: 修复标题中缺失的空格 (`#标题` -> `# 标题`)。
+*   **表格修复**: 修复表格中缺失的闭合管道符。
+*   **XML 清理**: 移除残留的 XML 标签。
+
+## 使用方法
+
+1.  在 Open WebUI 中安装此插件。
+2.  全局启用或为特定模型启用此过滤器。
+3.  在 **Valves** 设置中配置需要启用的修复项。
+4.  (可选) **显示调试日志 (Show Debug Log)** 在 Valves 中默认开启。这会将结构化的日志打印到浏览器控制台 (F12)。
+    > [!WARNING]
+    > 由于这是初版，可能会出现“负向修复”的情况（例如破坏了原本正确的格式）。如果您遇到问题，请务必查看控制台日志，复制“原始 (Original)”与“规范化 (Normalized)”的内容对比，并提交 Issue 反馈。
+
+## 配置项 (Valves)
+
+*   `priority`: 过滤器优先级 (默认: 50)。
+*   `enable_escape_fix`: 修复过度的转义字符。
+*   `enable_thought_tag_fix`: 规范化思维标签。
+*   `enable_code_block_fix`: 修复代码块格式。
+*   `enable_latex_fix`: 规范化 LaTeX 公式。
+*   `enable_list_fix`: 修复列表项换行 (实验性)。
+*   `enable_unclosed_block_fix`: 自动闭合未闭合的代码块。
+*   `enable_fullwidth_symbol_fix`: 修复代码块中的全角符号。
+*   `enable_mermaid_fix`: 修复 Mermaid 语法错误。
+*   `enable_heading_fix`: 修复标题中缺失的空格。
+*   `enable_table_fix`: 修复表格中缺失的闭合管道符。
+*   `enable_xml_tag_cleanup`: 清理残留的 XML 标签。
+*   `show_status`: 应用修复时显示状态通知。
+*   `show_debug_log`: 在浏览器控制台打印调试日志。
+
+## 许可证
+
+MIT
--- a/plugins/filters/markdown_normalizer/markdown_normalizer.png
+++ b/plugins/filters/markdown_normalizer/markdown_normalizer.png
--- a/plugins/filters/markdown_normalizer/markdown_normalizer.py
+++ b/plugins/filters/markdown_normalizer/markdown_normalizer.py
@@ -3,7 +3,7 @@ title: Markdown Normalizer
 author: Fu-Jie
 author_url: https://github.com/Fu-Jie
 funding_url: https://github.com/Fu-Jie/awesome-openwebui
-version: 1.0.0
+version: 1.0.1
 description: A production-grade content normalizer filter that fixes common Markdown formatting issues in LLM outputs, such as broken code blocks, LaTeX formulas, and list formatting.
 """

@@ -74,6 +74,7 @@ class ContentNormalizer:
        # Fix "reverse optimization": Must precisely match shape delimiters to avoid breaking structure
        # Priority: Longer delimiters match first
        "mermaid_node": re.compile(
+            r'("[^"\\]*(?:\\.[^"\\]*)*")|'  # Match quoted strings first (Group 1)
            r"(\w+)\s*(?:"
            r"(\(\(\()(?![\"])(.*?)(?<![\"])(\)\)\))|"  # (((...))) Double Circle
            r"(\(\()(?![\"])(.*?)(?<![\"])(\)\))|"  # ((...)) Circle
@@ -90,6 +91,8 @@ class ContentNormalizer:
            r"(\{)(?![\"])(.*?)(?<![\"])(\})|"  # {...} Rhombus
            r"(>)(?![\"])(.*?)(?<![\"])(\])"  # >...] Asymmetric
            r")"
+            r"(\s*\[\d+\])?",  # Capture optional citation [1]
+            re.DOTALL,
        ),
        # Heading: #Heading -> # Heading
        "heading_space": re.compile(r"^(#+)([^ \n#])", re.MULTILINE),
@@ -281,19 +284,28 @@ class ContentNormalizer:
        """Fix common Mermaid syntax errors while preserving node shapes"""

        def replacer(match):
-            # Group 1 is ID
-            id_str = match.group(1)
+            # Group 1 is Quoted String (if matched)
+            if match.group(1):
+                return match.group(1)
+
+            # Group 2 is ID
+            id_str = match.group(2)

            # Find matching shape group
-            # Groups start at index 2, each shape has 3 groups (Open, Content, Close)
-            # We iterate to find the non-None one
            groups = match.groups()
-            for i in range(1, len(groups), 3):
+            citation = groups[-1] or ""  # Last group is citation
+
+            # Iterate over shape groups (excluding the last citation group)
+            for i in range(2, len(groups) - 1, 3):
                if groups[i] is not None:
                    open_char = groups[i]
                    content = groups[i + 1]
                    close_char = groups[i + 2]

+                    # Append citation to content if present
+                    if citation:
+                        content += citation
+
                    # Escape quotes in content
                    content = content.replace('"', '\\"')

@@ -392,7 +404,7 @@ class Filter:
            default=True, description="Show status notification when fixes are applied"
        )
        show_debug_log: bool = Field(
-            default=False, description="Print debug logs to browser console (F12)"
+            default=True, description="Print debug logs to browser console (F12)"
        )

    def __init__(self):
--- a/plugins/filters/markdown_normalizer/markdown_normalizer_cn.png
+++ b/plugins/filters/markdown_normalizer/markdown_normalizer_cn.png
--- a/plugins/filters/markdown_normalizer/markdown_normalizer_cn.py
+++ b/plugins/filters/markdown_normalizer/markdown_normalizer_cn.py
@@ -3,7 +3,7 @@ title: Markdown 格式修复器 (Markdown Normalizer)
 author: Fu-Jie
 author_url: https://github.com/Fu-Jie
 funding_url: https://github.com/Fu-Jie/awesome-openwebui
-version: 1.0.0
+version: 1.0.1
 description: 生产级内容规范化过滤器，修复 LLM 输出中常见的 Markdown 格式问题，如损坏的代码块、LaTeX 公式、Mermaid 图表和列表格式。
 """

@@ -69,6 +69,7 @@ class ContentNormalizer:
        # 修复"反向优化"问题：必须精确匹配各种形状的定界符，避免破坏形状结构
        # 优先级：长定界符优先匹配
        "mermaid_node": re.compile(
+            r'("[^"\\]*(?:\\.[^"\\]*)*")|'  # Match quoted strings first (Group 1)
            r"(\w+)\s*(?:"
            r"(\(\(\()(?![\"])(.*?)(?<![\"])(\)\)\))|"  # (((...))) Double Circle
            r"(\(\()(?![\"])(.*?)(?<![\"])(\)\))|"  # ((...)) Circle
@@ -85,6 +86,8 @@ class ContentNormalizer:
            r"(\{)(?![\"])(.*?)(?<![\"])(\})|"  # {...} Rhombus
            r"(>)(?![\"])(.*?)(?<![\"])(\])"  # >...] Asymmetric
            r")"
+            r"(\s*\[\d+\])?",  # Capture optional citation [1]
+            re.DOTALL,
        ),
        # Heading: #Heading -> # Heading
        "heading_space": re.compile(r"^(#+)([^ \n#])", re.MULTILINE),
@@ -276,19 +279,28 @@ class ContentNormalizer:
        """修复常见的 Mermaid 语法错误，同时保留节点形状"""

        def replacer(match):
-            # Group 1 是 ID
-            id_str = match.group(1)
+            # Group 1 is Quoted String (if matched)
+            if match.group(1):
+                return match.group(1)

-            # 查找匹配的形状组
-            # 组从索引 2 开始，每个形状有 3 个组 (Open, Content, Close)
-            # 我们遍历找到非 None 的那一组
+            # Group 2 is ID
+            id_str = match.group(2)
+
+            # Find matching shape group
            groups = match.groups()
-            for i in range(1, len(groups), 3):
+            citation = groups[-1] or ""  # Last group is citation
+
+            # Iterate over shape groups (excluding the last citation group)
+            for i in range(2, len(groups) - 1, 3):
                if groups[i] is not None:
                    open_char = groups[i]
                    content = groups[i + 1]
                    close_char = groups[i + 2]

+                    # Append citation to content if present
+                    if citation:
+                        content += citation
+
                    # 如果内容包含引号，进行转义
                    content = content.replace('"', '\\"')

@@ -392,7 +404,7 @@ class Filter:
        )
        show_status: bool = Field(default=True, description="应用修复时显示状态通知")
        show_debug_log: bool = Field(
-            default=False, description="在浏览器控制台打印调试日志 (F12)"
+            default=True, description="在浏览器控制台打印调试日志 (F12)"
        )

    def __init__(self):
--- a/scripts/openwebui_community_client.py
+++ b/scripts/openwebui_community_client.py
@@ -253,7 +253,24 @@ class OpenWebUICommunityClient:
            是否成功
        """
        url = f"{self.BASE_URL}/posts/{post_id}/update"
-        response = requests.post(url, headers=self.headers, json=post_data)
+
+        # 仅发送允许更新的字段，避免 422 错误
+        allowed_keys = ["title", "content", "type", "data", "media"]
+        payload = {k: v for k, v in post_data.items() if k in allowed_keys}
+
+        response = requests.post(url, headers=self.headers, json=payload)
+
+        if response.status_code != 200:
+            try:
+                error_detail = response.json()
+                print(
+                    f"  Error: Update failed ({response.status_code}): {json.dumps(error_detail, indent=2)}"
+                )
+            except Exception:
+                print(
+                    f"  Error: Update failed ({response.status_code}): {response.text[:500]}"
+                )
+
        response.raise_for_status()
        return True

@@ -282,37 +299,54 @@ class OpenWebUICommunityClient:
        if not post_data:
            return False

-        # 确保结构存在
-        if "data" not in post_data:
-            post_data["data"] = {}
-        if "function" not in post_data["data"]:
-            post_data["data"]["function"] = {}
-        if "meta" not in post_data["data"]["function"]:
-            post_data["data"]["function"]["meta"] = {}
-        if "manifest" not in post_data["data"]["function"]["meta"]:
-            post_data["data"]["function"]["meta"]["manifest"] = {}
+        # 严格重建 data 结构，避免包含只读字段（如 data.function.id）
+        current_function = post_data.get("data", {}).get("function", {})

-        # 更新源代码
-        post_data["data"]["function"]["content"] = source_code
+        # 过滤 metadata，移除 openwebui_id 等系统字段
+        clean_metadata = {
+            k: v
+            for k, v in (metadata or {}).items()
+            if k not in ["openwebui_id", "post_id"]
+        }
+
+        function_data = {
+            "id": current_function.get("id", ""),
+            "name": metadata.get("title", current_function.get("name", "Plugin")),
+            "type": current_function.get("type", "action"),
+            "content": source_code,
+            "meta": {
+                "description": metadata.get(
+                    "description",
+                    current_function.get("meta", {}).get("description", ""),
+                ),
+                "manifest": clean_metadata,
+            },
+        }
+
+        post_data["data"] = {"function": function_data}
+        post_data["type"] = "function"

        # 更新 README（社区页面展示内容）
        if readme_content:
            post_data["content"] = readme_content

-        # 更新元数据
-        if metadata:
-            post_data["data"]["function"]["meta"]["manifest"].update(metadata)
-            if "title" in metadata:
-                post_data["title"] = metadata["title"]
-                post_data["data"]["function"]["name"] = metadata["title"]
-            if "description" in metadata:
-                post_data["data"]["function"]["meta"]["description"] = metadata[
-                    "description"
-                ]
+        # 更新标题
+        if metadata and "title" in metadata:
+            post_data["title"] = metadata["title"]

        # 更新图片
        if media_urls:
-            post_data["media"] = media_urls
+            # 将字符串 URL 转换为字典格式 (API 要求)
+            media_list = []
+            for item in media_urls:
+                if isinstance(item, str):
+                    media_list.append({"url": item})
+                elif isinstance(item, dict):
+                    media_list.append(item)
+            post_data["media"] = media_list
+        else:
+            # 如果没有新图片，保留原有的（如果有）
+            pass

        return self.update_post(post_id, post_data)

@@ -469,10 +503,42 @@ class OpenWebUICommunityClient:
                return True, f"Created new post (ID: {new_post_id})"
            return False, "Failed to create new post"

+        # 获取远程帖子信息（只需获取一次）
+        remote_post = None
+        if post_id:
+            remote_post = self.get_post(post_id)
+
        # 版本检查（仅对更新有效）
-        if not force and local_version:
-            if not self.version_needs_update(post_id, local_version):
-                return True, f"Skipped: version {local_version} matches remote"
+        if not force and local_version and remote_post:
+            remote_version = (
+                remote_post.get("data", {})
+                .get("function", {})
+                .get("meta", {})
+                .get("manifest", {})
+                .get("version")
+            )
+
+            version_changed = local_version != remote_version
+
+            # 检查 README 是否变化
+            readme_changed = False
+            remote_content = remote_post.get("content", "")
+            local_content = readme_content or metadata.get("description", "")
+
+            # 简单的内容比较 (去除首尾空白)
+            if (local_content or "").strip() != (remote_content or "").strip():
+                readme_changed = True
+
+            if not version_changed and not readme_changed:
+                return (
+                    True,
+                    f"Skipped: version {local_version} matches remote and no README changes",
+                )
+
+            if readme_changed and not version_changed:
+                print(
+                    f"  ℹ️  Version match ({local_version}) but README changed. Updating..."
+                )

        # 更新
        success = self.update_plugin(
@@ -484,7 +550,9 @@ class OpenWebUICommunityClient:
        )

        if success:
-            return True, f"Updated to version {local_version}"
+            if local_version:
+                return True, f"Updated to version {local_version}"
+            return True, "Updated plugin"
        return False, "Update failed"

    def _parse_frontmatter(self, content: str) -> Dict[str, str]:
--- a/scripts/openwebui_stats.py
+++ b/scripts/openwebui_stats.py
@@ -157,7 +157,10 @@ class OpenWebUIStats:
            stats["total_comments"] += post.get("commentCount", 0)

            # 解析 data 字段 - 正确路径: data.function.meta
-            function_data = post.get("data", {}).get("function", {})
+            function_data = post.get("data", {})
+            if function_data is None:
+                function_data = {}
+            function_data = function_data.get("function", {})
            meta = function_data.get("meta", {})
            manifest = meta.get("manifest", {})
            post_type = meta.get("type", function_data.get("type", "unknown"))
@@ -411,7 +414,8 @@ class OpenWebUIStats:
                "author_header": "| 👤 作者 | 👥 粉丝 | ⭐ 积分 | 🏆 贡献 |",
                "header": "| 📝 发布 | ⬇️ 下载 | 👁️ 浏览 | 👍 点赞 | 💾 收藏 |",
                "top6_title": "### 🔥 热门插件 Top 6",
-                "top6_header": "| 排名 | 插件 | 下载 | 浏览 |",
+                "top6_updated": f"> 🕐 自动更新于 {get_beijing_time().strftime('%Y-%m-%d %H:%M')}",
+                "top6_header": "| 排名 | 插件 | 下载 | 浏览 | 更新日期 |",
                "full_stats": "*完整统计请查看 [社区统计报告](./docs/community-stats.zh.md)*",
            },
            "en": {
@@ -420,7 +424,8 @@ class OpenWebUIStats:
                "author_header": "| 👤 Author | 👥 Followers | ⭐ Points | 🏆 Contributions |",
                "header": "| 📝 Posts | ⬇️ Downloads | 👁️ Views | 👍 Upvotes | 💾 Saves |",
                "top6_title": "### 🔥 Top 6 Popular Plugins",
-                "top6_header": "| Rank | Plugin | Downloads | Views |",
+                "top6_updated": f"> 🕐 Auto-updated: {get_beijing_time().strftime('%Y-%m-%d %H:%M')}",
+                "top6_header": "| Rank | Plugin | Downloads | Views | Updated |",
                "full_stats": "*See full stats in [Community Stats Report](./docs/community-stats.md)*",
            },
        }
@@ -459,14 +464,16 @@ class OpenWebUIStats:
        # Top 6 热门插件
        lines.append(t["top6_title"])
        lines.append("")
+        lines.append(t["top6_updated"])
+        lines.append("")
        lines.append(t["top6_header"])
-        lines.append("|:---:|------|:---:|:---:|")
+        lines.append("|:---:|------|:---:|:---:|:---:|")

        medals = ["🥇", "🥈", "🥉", "4️⃣", "5️⃣", "6️⃣"]
        for i, post in enumerate(top_plugins):
            medal = medals[i] if i < len(medals) else str(i + 1)
            lines.append(
-                f"| {medal} | [{post['title']}]({post['url']}) | {post['downloads']} | {post['views']} |"
+                f"| {medal} | [{post['title']}]({post['url']}) | {post['downloads']} | {post['views']} | {post['updated_at']} |"
            )

        lines.append("")
Author	SHA1	Message	Date
fujie	34b2c3d6cf	fix(async-context-compression): resolve race condition, update role to assistant, bump to v1.1.3	2026-01-12 01:45:58 +08:00
github-actions[bot]	d5c099dd15	chore: update community stats 2026-01-11	2026-01-11 17:06:52 +00:00
fujie	8810223693	docs: add Multi-Model Context Merger to plugin lists in READMEs	2026-01-12 00:30:55 +08:00
fujie	84974a2fb9	docs: add Gemini Multimodal Filter to plugin lists in READMEs	2026-01-12 00:30:09 +08:00
fujie	af847293af	docs: correct plugin lists in READMEs (rename Knowledge Card, remove Summary, add Deep Dive)	2026-01-12 00:28:41 +08:00
fujie	a44e80ce5b	fix: resolve syntax error in community client and refine error logging	2026-01-12 00:22:22 +08:00
fujie	c2815e13e9	chore: cleanup debug logs in community client	2026-01-12 00:22:05 +08:00
fujie	56bfa3a3ef	fix: provide function id in update payload to resolve 400 error	2026-01-12 00:18:58 +08:00
fujie	a13c915f27	fix: revert _find_images to _find_image to ensure API compatibility	2026-01-12 00:17:03 +08:00
fujie	fb2d35237e	fix: revert to single image support as API does not support multiple images	2026-01-12 00:16:47 +08:00
fujie	3f19ecfd20	feat: support multiple images and improve error logging for plugin updates	2026-01-12 00:13:32 +08:00
fujie	2fd96f07aa	fix: robust payload cleaning for plugin updates to resolve 422 error	2026-01-12 00:12:56 +08:00
fujie	a1c1ed9840	fix: resolve 422 error in plugin update by cleaning payload and fixing media format	2026-01-12 00:07:10 +08:00
fujie	c63701d05f	docs: update infographic plugin documentation to v1.4.9	2026-01-12 00:01:28 +08:00
fujie	863805dc68	feat: release markdown_normalizer v1.0.1 with enhanced mermaid support and debug logging	2026-01-11 23:58:23 +08:00
github-actions[bot]	98f7dff458	chore: update community stats 2026-01-11	2026-01-11 11:06:46 +00:00
fujie	08c0dd984c	docs: add 'Updated' column for each plugin in Top 6 table	2026-01-11 18:05:01 +08:00
fujie	e870ad8823	docs: add last updated time to Top 6 plugins section and update stats script	2026-01-11 17:59:08 +08:00
fujie	d687fffdb5	docs: further simplify contributing guides to focus on plugin files	2026-01-11 17:56:37 +08:00
fujie	d534d8b319	docs: split contributing guide into English and Chinese and remove docs requirement	2026-01-11 17:55:47 +08:00
fujie	d5c5158726	docs: simplify and bilingualize contributing guide	2026-01-11 17:54:49 +08:00
fujie	888026876f	ci: auto-trigger plugin publishing on main branch push	2026-01-11 17:51:34 +08:00
Jeff	06e8d30900	Merge pull request #20 from Fu-Jie/copilot/fix-session-alias-errors Harden async context compression against new DB session alias and runtime edge cases	2026-01-11 17:26:03 +08:00
fujie	cbf2ff7f93	chore: release async-context-compression v1.1.2 - Enhanced error reporting via status bar and console - Robust model ID handling - Open WebUI v0.7.x compatibility (dynamic DB session) - Updated documentation and version bumps	2026-01-11 17:25:07 +08:00
copilot-swe-agent[bot]	abbe3fb248	chore: centralize chat_id extraction helper Co-authored-by: Fu-Jie <33599649+Fu-Jie@users.noreply.github.com>	2026-01-11 08:36:13 +00:00
copilot-swe-agent[bot]	7e44dde979	chore: add discovery docstrings Co-authored-by: Fu-Jie <33599649+Fu-Jie@users.noreply.github.com>	2026-01-11 08:31:10 +00:00
copilot-swe-agent[bot]	3649d75539	chore: add discovery debug logs Co-authored-by: Fu-Jie <33599649+Fu-Jie@users.noreply.github.com>	2026-01-11 08:30:02 +00:00
copilot-swe-agent[bot]	d3b4219a9a	chore: refine db session discovery messaging Co-authored-by: Fu-Jie <33599649+Fu-Jie@users.noreply.github.com>	2026-01-11 08:28:52 +00:00
copilot-swe-agent[bot]	9e98d55e11	fix: make async compression db session discovery robust Co-authored-by: Fu-Jie <33599649+Fu-Jie@users.noreply.github.com>	2026-01-11 08:27:36 +00:00
copilot-swe-agent[bot]	4b8515f682	fix: ensure empty summary model skips compression Co-authored-by: Fu-Jie <33599649+Fu-Jie@users.noreply.github.com>	2026-01-11 08:25:33 +00:00
copilot-swe-agent[bot]	d2f35ce396	fix: harden async compression compatibility Co-authored-by: Fu-Jie <33599649+Fu-Jie@users.noreply.github.com>	2026-01-11 08:24:56 +00:00
copilot-swe-agent[bot]	f479f23b38	Initial plan	2026-01-11 08:19:33 +00:00
github-actions[bot]	51048f9e5d	chore: update community stats 2026-01-10	2026-01-10 18:11:03 +00:00
github-actions[bot]	1118ae34c4	chore: update community stats 2026-01-10	2026-01-10 14:07:43 +00:00
github-actions[bot]	7a5e1a4e12	chore: update community stats 2026-01-10	2026-01-10 12:12:24 +00:00
fujie	8e377e1794	Update Copilot instructions: Limit What's New section to latest 3 updates	2026-01-10 19:09:09 +08:00
fujie	d66360b02d	Update READMEs with v1.1.1 release notes	2026-01-10 19:07:49 +08:00
fujie	1ece648006	Update Async Context Compression docs to v1.1.1 and improve plugin update logic to detect README changes	2026-01-10 19:07:49 +08:00
github-actions[bot]	a262a716a3	chore: update community stats 2026-01-10	2026-01-10 11:06:57 +00:00
fujie	06fdfee182	Update context enhancement filter	2026-01-10 18:47:35 +08:00
fujie	7085e794a3	Update Async Context Compression to v1.1.1: Add frontend debug logging and optimize token calculation	2026-01-10 18:47:35 +08:00
github-actions[bot]	a9cae535eb	chore: update community stats 2026-01-10	2026-01-10 09:08:08 +00:00
github-actions[bot]	bdbd0d98be	chore: update community stats 2026-01-10	2026-01-10 08:24:17 +00:00
fujie	51612ea783	Fix AttributeError in stats script: handle NoneType data field	2026-01-10 16:19:44 +08:00
fujie	baf364a85f	Fix mkdocs build warnings: remove references to missing summary.md	2026-01-10 16:09:42 +08:00
fujie	f78e703a99	Fix Mermaid syntax normalization: preserve quoted strings and prevent false positives	2026-01-10 16:07:19 +08:00
fujie	aabb24c9cd	docs: update READMEs for markdown normalizer	2026-01-10 15:53:36 +08:00