🔖 chore(release): v1.71.2 [skip ci]

### [Version 1.71.2](https://github.com/lobehub/lobe-chat/compare/v1.71.1...v1.71.2) <sup>Released on **2025-03-15**</sup> #### 🐛 Bug Fixes - **misc**: Fix knowledge base issue. <br/> <details> <summary><kbd>Improvements and Fixes</kbd></summary> #### What's fixed * **misc**: Fix knowledge base issue, closes [#6973](https://github.com/lobehub/lobe-chat/issues/6973) ([15f39ef](https://github.com/lobehub/lobe-chat/commit/15f39ef)) </details> <div align="right"> [![](https://img.shields.io/badge/-BACK_TO_TOP-151515?style=flat-square)](#readme-top) </div>
🐛 fix: fix knowledge base issue (#6973 )
2026-06-20 06:15:58 +00:00 · 2025-03-15 09:55:43 +00:00 · 2025-03-15 17:45:38 +08:00 · 2025-03-15 04:02:23 +00:00 · 2025-03-15 04:01:13 +00:00 · 2025-03-15 11:52:33 +08:00
236 changed files with 9029 additions and 1126 deletions
@@ -2,6 +2,7 @@ name: '🐛 Bug Report'
 description: 'Report an bug'
 title: '[Bug] '
 labels: ['🐛 Bug']
+type: Bug
 body:
  - type: dropdown
    attributes:
@@ -2,6 +2,7 @@ name: '🌠 Feature Request'
 description: 'Suggest an idea'
 title: '[Request] '
 labels: ['🌠 Feature Request']
+type: Feature
 body:
  - type: textarea
    attributes:
@@ -2,6 +2,7 @@ name: '🌠 功能需求'
 description: '提出需求或建议'
 title: '[Request] '
 labels: ['🌠 Feature Request']
+type: Feature
 body:
  - type: textarea
    attributes:
@@ -0,0 +1,25 @@
+name: Database Schema Visualization CI
+
+on:
+  push:
+    branches:
+      - main
+    paths:
+      - 'docs/developer/database-schema.dbml'
+
+jobs:
+  build:
+    runs-on: ubuntu-latest
+    steps:
+      - uses: actions/checkout@v4
+
+      - name: Install dbdocs
+        run: sudo npm install -g dbdocs
+
+      - name: Check dbdocs
+        run: dbdocs
+
+      - name: sync database schema to dbdocs
+        env:
+          DBDOCS_TOKEN: ${{ secrets.DBDOCS_TOKEN }}
+        run: npm run db:visualize
@@ -1,6 +1,7 @@
 lockfile=false
 resolution-mode=highest

+ignore-workspace-root-check=true
 enable-pre-post-scripts=true

 public-hoist-pattern[]=*@umijs/lint*
@@ -2,6 +2,425 @@

 # Changelog

+### [Version 1.71.2](https://github.com/lobehub/lobe-chat/compare/v1.71.1...v1.71.2)
+
+<sup>Released on **2025-03-15**</sup>
+
+#### 🐛 Bug Fixes
+
+- **misc**: Fix knowledge base issue.
+
+<br/>
+
+<details>
+<summary><kbd>Improvements and Fixes</kbd></summary>
+
+#### What's fixed
+
+- **misc**: Fix knowledge base issue, closes [#6973](https://github.com/lobehub/lobe-chat/issues/6973) ([15f39ef](https://github.com/lobehub/lobe-chat/commit/15f39ef))
+
+</details>
+
+<div align="right">
+
+[![](https://img.shields.io/badge/-BACK_TO_TOP-151515?style=flat-square)](#readme-top)
+
+</div>
+
+### [Version 1.71.1](https://github.com/lobehub/lobe-chat/compare/v1.71.0...v1.71.1)
+
+<sup>Released on **2025-03-15**</sup>
+
+#### 🐛 Bug Fixes
+
+- **misc**: Fix google gemini output relative issue.
+
+#### 💄 Styles
+
+- **misc**: Update Vertex AI models.
+
+<br/>
+
+<details>
+<summary><kbd>Improvements and Fixes</kbd></summary>
+
+#### What's fixed
+
+- **misc**: Fix google gemini output relative issue, closes [#6970](https://github.com/lobehub/lobe-chat/issues/6970) ([fdcaaf3](https://github.com/lobehub/lobe-chat/commit/fdcaaf3))
+
+#### Styles
+
+- **misc**: Update Vertex AI models, closes [#6967](https://github.com/lobehub/lobe-chat/issues/6967) ([d4432f1](https://github.com/lobehub/lobe-chat/commit/d4432f1))
+
+</details>
+
+<div align="right">
+
+[![](https://img.shields.io/badge/-BACK_TO_TOP-151515?style=flat-square)](#readme-top)
+
+</div>
+
+## [Version 1.71.0](https://github.com/lobehub/lobe-chat/compare/v1.70.11...v1.71.0)
+
+<sup>Released on **2025-03-14**</sup>
+
+#### ✨ Features
+
+- **misc**: Support gemini image output in chat.
+
+<br/>
+
+<details>
+<summary><kbd>Improvements and Fixes</kbd></summary>
+
+#### What's improved
+
+- **misc**: Support gemini image output in chat, closes [#6931](https://github.com/lobehub/lobe-chat/issues/6931) ([d4c0d1f](https://github.com/lobehub/lobe-chat/commit/d4c0d1f))
+
+</details>
+
+<div align="right">
+
+[![](https://img.shields.io/badge/-BACK_TO_TOP-151515?style=flat-square)](#readme-top)
+
+</div>
+
+### [Version 1.70.11](https://github.com/lobehub/lobe-chat/compare/v1.70.10...v1.70.11)
+
+<sup>Released on **2025-03-13**</sup>
+
+<br/>
+
+<details>
+<summary><kbd>Improvements and Fixes</kbd></summary>
+
+</details>
+
+<div align="right">
+
+[![](https://img.shields.io/badge/-BACK_TO_TOP-151515?style=flat-square)](#readme-top)
+
+</div>
+
+### [Version 1.70.10](https://github.com/lobehub/lobe-chat/compare/v1.70.9...v1.70.10)
+
+<sup>Released on **2025-03-12**</sup>
+
+#### 🐛 Bug Fixes
+
+- **misc**: The agent setting `-edit_agent` not work.
+
+<br/>
+
+<details>
+<summary><kbd>Improvements and Fixes</kbd></summary>
+
+#### What's fixed
+
+- **misc**: The agent setting `-edit_agent` not work, closes [#4609](https://github.com/lobehub/lobe-chat/issues/4609) ([7af0ec6](https://github.com/lobehub/lobe-chat/commit/7af0ec6))
+
+</details>
+
+<div align="right">
+
+[![](https://img.shields.io/badge/-BACK_TO_TOP-151515?style=flat-square)](#readme-top)
+
+</div>
+
+### [Version 1.70.9](https://github.com/lobehub/lobe-chat/compare/v1.70.8...v1.70.9)
+
+<sup>Released on **2025-03-12**</sup>
+
+<br/>
+
+<details>
+<summary><kbd>Improvements and Fixes</kbd></summary>
+
+</details>
+
+<div align="right">
+
+[![](https://img.shields.io/badge/-BACK_TO_TOP-151515?style=flat-square)](#readme-top)
+
+</div>
+
+### [Version 1.70.8](https://github.com/lobehub/lobe-chat/compare/v1.70.7...v1.70.8)
+
+<sup>Released on **2025-03-12**</sup>
+
+#### 🐛 Bug Fixes
+
+- **misc**: Fix theme flicking.
+
+<br/>
+
+<details>
+<summary><kbd>Improvements and Fixes</kbd></summary>
+
+#### What's fixed
+
+- **misc**: Fix theme flicking, closes [#6926](https://github.com/lobehub/lobe-chat/issues/6926) ([103c3e3](https://github.com/lobehub/lobe-chat/commit/103c3e3))
+
+</details>
+
+<div align="right">
+
+[![](https://img.shields.io/badge/-BACK_TO_TOP-151515?style=flat-square)](#readme-top)
+
+</div>
+
+### [Version 1.70.7](https://github.com/lobehub/lobe-chat/compare/v1.70.6...v1.70.7)
+
+<sup>Released on **2025-03-12**</sup>
+
+#### 🐛 Bug Fixes
+
+- **misc**: Fix crawl result for short content.
+
+<br/>
+
+<details>
+<summary><kbd>Improvements and Fixes</kbd></summary>
+
+#### What's fixed
+
+- **misc**: Fix crawl result for short content, closes [#6903](https://github.com/lobehub/lobe-chat/issues/6903) [#6904](https://github.com/lobehub/lobe-chat/issues/6904) ([d8fda65](https://github.com/lobehub/lobe-chat/commit/d8fda65))
+
+</details>
+
+<div align="right">
+
+[![](https://img.shields.io/badge/-BACK_TO_TOP-151515?style=flat-square)](#readme-top)
+
+</div>
+
+### [Version 1.70.6](https://github.com/lobehub/lobe-chat/compare/v1.70.5...v1.70.6)
+
+<sup>Released on **2025-03-11**</sup>
+
+#### 🐛 Bug Fixes
+
+- **misc**: Link jump in mobile terminal data statistics.
+
+<br/>
+
+<details>
+<summary><kbd>Improvements and Fixes</kbd></summary>
+
+#### What's fixed
+
+- **misc**: Link jump in mobile terminal data statistics, closes [#6893](https://github.com/lobehub/lobe-chat/issues/6893) ([505d24d](https://github.com/lobehub/lobe-chat/commit/505d24d))
+
+</details>
+
+<div align="right">
+
+[![](https://img.shields.io/badge/-BACK_TO_TOP-151515?style=flat-square)](#readme-top)
+
+</div>
+
+### [Version 1.70.5](https://github.com/lobehub/lobe-chat/compare/v1.70.4...v1.70.5)
+
+<sup>Released on **2025-03-11**</sup>
+
+#### 🐛 Bug Fixes
+
+- **misc**: Refactor the theme implement.
+
+<br/>
+
+<details>
+<summary><kbd>Improvements and Fixes</kbd></summary>
+
+#### What's fixed
+
+- **misc**: Refactor the theme implement, closes [#6844](https://github.com/lobehub/lobe-chat/issues/6844) ([e5c2161](https://github.com/lobehub/lobe-chat/commit/e5c2161))
+
+</details>
+
+<div align="right">
+
+[![](https://img.shields.io/badge/-BACK_TO_TOP-151515?style=flat-square)](#readme-top)
+
+</div>
+
+### [Version 1.70.4](https://github.com/lobehub/lobe-chat/compare/v1.70.3...v1.70.4)
+
+<sup>Released on **2025-03-11**</sup>
+
+#### 💄 Styles
+
+- **misc**: Support OpenRouter custom BaseURL.
+
+<br/>
+
+<details>
+<summary><kbd>Improvements and Fixes</kbd></summary>
+
+#### Styles
+
+- **misc**: Support OpenRouter custom BaseURL ([a8089ed](https://github.com/lobehub/lobe-chat/commit/a8089ed))
+
+</details>
+
+<div align="right">
+
+[![](https://img.shields.io/badge/-BACK_TO_TOP-151515?style=flat-square)](#readme-top)
+
+</div>
+
+### [Version 1.70.3](https://github.com/lobehub/lobe-chat/compare/v1.70.2...v1.70.3)
+
+<sup>Released on **2025-03-11**</sup>
+
+#### 💄 Styles
+
+- **spelling**: Correct "broswer" to "browser" across codebase.
+
+<br/>
+
+<details>
+<summary><kbd>Improvements and Fixes</kbd></summary>
+
+#### Styles
+
+- **spelling**: Correct "broswer" to "browser" across codebase, closes [#6876](https://github.com/lobehub/lobe-chat/issues/6876) ([8d677a2](https://github.com/lobehub/lobe-chat/commit/8d677a2))
+
+</details>
+
+<div align="right">
+
+[![](https://img.shields.io/badge/-BACK_TO_TOP-151515?style=flat-square)](#readme-top)
+
+</div>
+
+### [Version 1.70.2](https://github.com/lobehub/lobe-chat/compare/v1.70.1...v1.70.2)
+
+<sup>Released on **2025-03-10**</sup>
+
+#### 🐛 Bug Fixes
+
+- **misc**: Update cvpr cvf url rules.
+
+<br/>
+
+<details>
+<summary><kbd>Improvements and Fixes</kbd></summary>
+
+#### What's fixed
+
+- **misc**: Update cvpr cvf url rules, closes [#6860](https://github.com/lobehub/lobe-chat/issues/6860) ([c299067](https://github.com/lobehub/lobe-chat/commit/c299067))
+
+</details>
+
+<div align="right">
+
+[![](https://img.shields.io/badge/-BACK_TO_TOP-151515?style=flat-square)](#readme-top)
+
+</div>
+
+### [Version 1.70.1](https://github.com/lobehub/lobe-chat/compare/v1.70.0...v1.70.1)
+
+<sup>Released on **2025-03-10**</sup>
+
+#### 🐛 Bug Fixes
+
+- **misc**: Fix anthropic max tokens.
+
+<br/>
+
+<details>
+<summary><kbd>Improvements and Fixes</kbd></summary>
+
+#### What's fixed
+
+- **misc**: Fix anthropic max tokens, closes [#6859](https://github.com/lobehub/lobe-chat/issues/6859) ([35fbc6c](https://github.com/lobehub/lobe-chat/commit/35fbc6c))
+
+</details>
+
+<div align="right">
+
+[![](https://img.shields.io/badge/-BACK_TO_TOP-151515?style=flat-square)](#readme-top)
+
+</div>
+
+## [Version 1.70.0](https://github.com/lobehub/lobe-chat/compare/v1.69.6...v1.70.0)
+
+<sup>Released on **2025-03-09**</sup>
+
+#### ✨ Features
+
+- **misc**: Support no-fc models like deepseek r1 with online search.
+
+<br/>
+
+<details>
+<summary><kbd>Improvements and Fixes</kbd></summary>
+
+#### What's improved
+
+- **misc**: Support no-fc models like deepseek r1 with online search, closes [#6842](https://github.com/lobehub/lobe-chat/issues/6842) ([f284c25](https://github.com/lobehub/lobe-chat/commit/f284c25))
+
+</details>
+
+<div align="right">
+
+[![](https://img.shields.io/badge/-BACK_TO_TOP-151515?style=flat-square)](#readme-top)
+
+</div>
+
+### [Version 1.69.6](https://github.com/lobehub/lobe-chat/compare/v1.69.5...v1.69.6)
+
+<sup>Released on **2025-03-09**</sup>
+
+#### 🐛 Bug Fixes
+
+- **misc**: Fix context cache control and model builtin search switch.
+
+<br/>
+
+<details>
+<summary><kbd>Improvements and Fixes</kbd></summary>
+
+#### What's fixed
+
+- **misc**: Fix context cache control and model builtin search switch, closes [#6831](https://github.com/lobehub/lobe-chat/issues/6831) ([5c6b8ea](https://github.com/lobehub/lobe-chat/commit/5c6b8ea))
+
+</details>
+
+<div align="right">
+
+[![](https://img.shields.io/badge/-BACK_TO_TOP-151515?style=flat-square)](#readme-top)
+
+</div>
+
+### [Version 1.69.5](https://github.com/lobehub/lobe-chat/compare/v1.69.4...v1.69.5)
+
+<sup>Released on **2025-03-09**</sup>
+
+#### 💄 Styles
+
+- **chat**: Auto send message from URL.
+- **misc**: Support openrouter claude 3.7 sonnet reasoning.
+
+<br/>
+
+<details>
+<summary><kbd>Improvements and Fixes</kbd></summary>
+
+#### Styles
+
+- **chat**: Auto send message from URL, closes [#6497](https://github.com/lobehub/lobe-chat/issues/6497) ([30b2639](https://github.com/lobehub/lobe-chat/commit/30b2639))
+- **misc**: Support openrouter claude 3.7 sonnet reasoning, closes [#6806](https://github.com/lobehub/lobe-chat/issues/6806) ([f1ffc2c](https://github.com/lobehub/lobe-chat/commit/f1ffc2c))
+
+</details>
+
+<div align="right">
+
+[![](https://img.shields.io/badge/-BACK_TO_TOP-151515?style=flat-square)](#readme-top)
+
+</div>
+
 ### [Version 1.69.4](https://github.com/lobehub/lobe-chat/compare/v1.69.3...v1.69.4)

 <sup>Released on **2025-03-09**</sup>
@@ -330,7 +330,7 @@ In addition, these plugins are not limited to news aggregation, but can also ext
 | [Bing_websearch](https://lobechat.com/discover/plugin/Bingsearch-identifier)<br/><sup>By **FineHow** on **2024-12-22**</sup> | Search for information from the internet base BingApi<br/>`bingsearch`                                                  |
 | [PortfolioMeta](https://lobechat.com/discover/plugin/StockData)<br/><sup>By **portfoliometa** on **2024-12-22**</sup>        | Analyze stocks and get comprehensive real-time investment data and analytics.<br/>`stock`                               |

-> 📊 Total plugins: [<kbd>**47**</kbd>](https://lobechat.com/discover/plugins)
+> 📊 Total plugins: [<kbd>**46**</kbd>](https://lobechat.com/discover/plugins)

 <!-- PLUGIN LIST -->

@@ -364,12 +364,12 @@ Our marketplace is not just a showcase platform but also a collaborative space.

 | Recent Submits                                                                                                                                                                                        | Description                                                                                                                                                      |
 | ----------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------- | ---------------------------------------------------------------------------------------------------------------------------------------------------------------- |
+| [学术论文综述专家](https://lobechat.com/discover/assistant/academic-paper-overview)<br/><sup>By **[arvinxx](https://github.com/arvinxx)** on **2025-03-11**</sup>                                     | 擅长高质量文献检索与分析的学术研究助手<br/>`学术研究` `文献检索` `数据分析` `信息提取` `咨询`                                                                    |
 | [Cron Expression Assistant](https://lobechat.com/discover/assistant/crontab-generate)<br/><sup>By **[edgesider](https://github.com/edgesider)** on **2025-02-17**</sup>                               | Crontab Expression Generator<br/>`crontab` `time-expression` `trigger-time` `generator` `technical-assistance`                                                   |
 | [Xiao Zhi French Translation Assistant](https://lobechat.com/discover/assistant/xiao-zhi-french-translation-asst-v-1)<br/><sup>By **[WeR-Best](https://github.com/WeR-Best)** on **2025-02-10**</sup> | A friendly, professional, and empathetic AI assistant for French translation<br/>`ai-assistant` `french-translation` `cross-cultural-communication` `creativity` |
-| [Language Charm Learning Mentor](https://lobechat.com/discover/assistant/bad-language-helper)<br/><sup>By **[Guducat](https://github.com/Guducat)** on **2025-02-06**</sup>                           | Specializes in teaching the charm of language and witty responses<br/>`language-learning` `dialogue-examples`                                                    |
-| [Astrology Researcher](https://lobechat.com/discover/assistant/fate-researcher)<br/><sup>By **[Jack980506](https://github.com/Jack980506)** on **2025-02-06**</sup>                                   | Expert in BaZi astrology<br/>`astrology` `ba-zi` `traditional-culture`                                                                                           |
+| [Investment Assistant](https://lobechat.com/discover/assistant/graham-investmentassi)<br/><sup>By **[farsightlin](https://github.com/farsightlin)** on **2025-02-06**</sup>                           | Helps users calculate the data needed for valuation<br/>`investment` `valuation` `financial-analysis` `calculator`                                               |

-> 📊 Total agents: [<kbd>**487**</kbd> ](https://lobechat.com/discover/assistants)
+> 📊 Total agents: [<kbd>**488**</kbd> ](https://lobechat.com/discover/assistants)

 <!-- AGENT LIST -->

@@ -323,7 +323,7 @@ LobeChat 的插件生态系统是其核心功能的重要扩展，它极大地
 | [必应网页搜索](https://lobechat.com/discover/plugin/Bingsearch-identifier)<br/><sup>By **FineHow** on **2024-12-22**</sup> | 通过 BingApi 搜索互联网上的信息<br/>`bingsearch`                                   |
 | [PortfolioMeta](https://lobechat.com/discover/plugin/StockData)<br/><sup>By **portfoliometa** on **2024-12-22**</sup>      | 分析股票并获取全面的实时投资数据和分析。<br/>`股票`                                |

-> 📊 Total plugins: [<kbd>**47**</kbd>](https://lobechat.com/discover/plugins)
+> 📊 Total plugins: [<kbd>**46**</kbd>](https://lobechat.com/discover/plugins)

 <!-- PLUGIN LIST -->

@@ -351,14 +351,14 @@ LobeChat 的插件生态系统是其核心功能的重要扩展，它极大地

 <!-- AGENT LIST -->

-| 最近新增                                                                                                                                                                         | 描述                                                                                   |
-| -------------------------------------------------------------------------------------------------------------------------------------------------------------------------------- | -------------------------------------------------------------------------------------- |
-| [Cron 表达式助手](https://lobechat.com/discover/assistant/crontab-generate)<br/><sup>By **[edgesider](https://github.com/edgesider)** on **2025-02-17**</sup>                    | Crontab 表达式生成<br/>`crontab` `时间表达` `触发时间` `生成器` `技术辅助`             |
-| [小智法语翻译助手](https://lobechat.com/discover/assistant/xiao-zhi-french-translation-asst-v-1)<br/><sup>By **[WeR-Best](https://github.com/WeR-Best)** on **2025-02-10**</sup> | 友好、专业、富有同理心的法语翻译 AI 助手<br/>`ai助手` `法语翻译` `跨文化交流` `创造力` |
-| [语言魅力学习导师](https://lobechat.com/discover/assistant/bad-language-helper)<br/><sup>By **[Guducat](https://github.com/Guducat)** on **2025-02-06**</sup>                    | 擅长教学语言的魅力与花样回复<br/>`语言学习` `对话示例`                                 |
-| [命理研究员](https://lobechat.com/discover/assistant/fate-researcher)<br/><sup>By **[Jack980506](https://github.com/Jack980506)** on **2025-02-06**</sup>                        | 精通八字命<br/>`命理学` `八字` `传统文化`                                              |
+| 最近新增                                                                                                                                                                         | 描述                                                                                          |
+| -------------------------------------------------------------------------------------------------------------------------------------------------------------------------------- | --------------------------------------------------------------------------------------------- |
+| [学术论文综述专家](https://lobechat.com/discover/assistant/academic-paper-overview)<br/><sup>By **[arvinxx](https://github.com/arvinxx)** on **2025-03-11**</sup>                | 擅长高质量文献检索与分析的学术研究助手<br/>`学术研究` `文献检索` `数据分析` `信息提取` `咨询` |
+| [Cron 表达式助手](https://lobechat.com/discover/assistant/crontab-generate)<br/><sup>By **[edgesider](https://github.com/edgesider)** on **2025-02-17**</sup>                    | Crontab 表达式生成<br/>`crontab` `时间表达` `触发时间` `生成器` `技术辅助`                    |
+| [小智法语翻译助手](https://lobechat.com/discover/assistant/xiao-zhi-french-translation-asst-v-1)<br/><sup>By **[WeR-Best](https://github.com/WeR-Best)** on **2025-02-10**</sup> | 友好、专业、富有同理心的法语翻译 AI 助手<br/>`ai助手` `法语翻译` `跨文化交流` `创造力`        |
+| [投资小助手](https://lobechat.com/discover/assistant/graham-investmentassi)<br/><sup>By **[farsightlin](https://github.com/farsightlin)** on **2025-02-06**</sup>                | 帮助用户计算估值所需的一些数据<br/>`投资` `估值` `财务分析` `计算器`                          |

-> 📊 Total agents: [<kbd>**487**</kbd> ](https://lobechat.com/discover/assistants)
+> 📊 Total agents: [<kbd>**488**</kbd> ](https://lobechat.com/discover/assistants)

 <!-- AGENT LIST -->

@@ -1,4 +1,111 @@
 [
+  {
+    "children": {
+      "fixes": ["Fix google gemini output relative issue."],
+      "improvements": ["Update Vertex AI models."]
+    },
+    "date": "2025-03-15",
+    "version": "1.71.1"
+  },
+  {
+    "children": {
+      "features": ["Support gemini image output in chat."]
+    },
+    "date": "2025-03-14",
+    "version": "1.71.0"
+  },
+  {
+    "children": {},
+    "date": "2025-03-13",
+    "version": "1.70.11"
+  },
+  {
+    "children": {
+      "fixes": ["The agent setting -edit_agent not work."]
+    },
+    "date": "2025-03-12",
+    "version": "1.70.10"
+  },
+  {
+    "children": {},
+    "date": "2025-03-12",
+    "version": "1.70.9"
+  },
+  {
+    "children": {
+      "fixes": ["Fix theme flicking."]
+    },
+    "date": "2025-03-12",
+    "version": "1.70.8"
+  },
+  {
+    "children": {
+      "fixes": ["Fix crawl result for short content."]
+    },
+    "date": "2025-03-12",
+    "version": "1.70.7"
+  },
+  {
+    "children": {
+      "fixes": ["Link jump in mobile terminal data statistics."]
+    },
+    "date": "2025-03-11",
+    "version": "1.70.6"
+  },
+  {
+    "children": {
+      "fixes": ["Refactor the theme implement."]
+    },
+    "date": "2025-03-11",
+    "version": "1.70.5"
+  },
+  {
+    "children": {
+      "improvements": ["Support OpenRouter custom BaseURL."]
+    },
+    "date": "2025-03-11",
+    "version": "1.70.4"
+  },
+  {
+    "children": {},
+    "date": "2025-03-11",
+    "version": "1.70.3"
+  },
+  {
+    "children": {
+      "fixes": ["Update cvpr cvf url rules."]
+    },
+    "date": "2025-03-10",
+    "version": "1.70.2"
+  },
+  {
+    "children": {
+      "fixes": ["Fix anthropic max tokens."]
+    },
+    "date": "2025-03-10",
+    "version": "1.70.1"
+  },
+  {
+    "children": {
+      "features": ["Support no-fc models like deepseek r1 with online search."]
+    },
+    "date": "2025-03-09",
+    "version": "1.70.0"
+  },
+  {
+    "children": {
+      "fixes": ["Fix context cache control and model builtin search switch."]
+    },
+    "date": "2025-03-09",
+    "version": "1.69.6"
+  },
+  {
+    "children": {
+      "improvements": ["Support openrouter claude 3.7 sonnet reasoning."]
+    },
+    "date": "2025-03-09",
+    "version": "1.69.5"
+  },
  {
    "children": {
      "fixes": ["Fix mistral can not chat."]
@@ -0,0 +1,569 @@
+table agents {
+  id text [pk, not null]
+  slug varchar(100) [unique]
+  title text
+  description text
+  tags jsonb [default: `[]`]
+  avatar text
+  background_color text
+  plugins jsonb [default: `[]`]
+  user_id text [not null]
+  chat_config jsonb
+  few_shots jsonb
+  model text
+  params jsonb [default: `{}`]
+  provider text
+  system_role text
+  tts jsonb
+  accessed_at "timestamp with time zone" [not null, default: `now()`]
+  created_at "timestamp with time zone" [not null, default: `now()`]
+  updated_at "timestamp with time zone" [not null, default: `now()`]
+}
+
+table agents_files {
+  file_id text [not null]
+  agent_id text [not null]
+  enabled boolean [default: true]
+  user_id text [not null]
+  accessed_at "timestamp with time zone" [not null, default: `now()`]
+  created_at "timestamp with time zone" [not null, default: `now()`]
+  updated_at "timestamp with time zone" [not null, default: `now()`]
+
+  indexes {
+    (file_id, agent_id, user_id) [pk]
+  }
+}
+
+table agents_knowledge_bases {
+  agent_id text [not null]
+  knowledge_base_id text [not null]
+  user_id text [not null]
+  enabled boolean [default: true]
+  accessed_at "timestamp with time zone" [not null, default: `now()`]
+  created_at "timestamp with time zone" [not null, default: `now()`]
+  updated_at "timestamp with time zone" [not null, default: `now()`]
+
+  indexes {
+    (agent_id, knowledge_base_id) [pk]
+  }
+}
+
+table ai_models {
+  id varchar(150) [not null]
+  display_name varchar(200)
+  description text
+  organization varchar(100)
+  enabled boolean
+  provider_id varchar(64) [not null]
+  type varchar(20) [not null, default: 'chat']
+  sort integer
+  user_id text [not null]
+  pricing jsonb
+  parameters jsonb [default: `{}`]
+  config jsonb
+  abilities jsonb [default: `{}`]
+  context_window_tokens integer
+  source varchar(20)
+  released_at varchar(10)
+  accessed_at "timestamp with time zone" [not null, default: `now()`]
+  created_at "timestamp with time zone" [not null, default: `now()`]
+  updated_at "timestamp with time zone" [not null, default: `now()`]
+
+  indexes {
+    (id, provider_id, user_id) [pk]
+  }
+}
+
+table ai_providers {
+  id varchar(64) [not null]
+  name text
+  user_id text [not null]
+  sort integer
+  enabled boolean
+  fetch_on_client boolean
+  check_model text
+  logo text
+  description text
+  key_vaults text
+  source varchar(20)
+  settings jsonb
+  accessed_at "timestamp with time zone" [not null, default: `now()`]
+  created_at "timestamp with time zone" [not null, default: `now()`]
+  updated_at "timestamp with time zone" [not null, default: `now()`]
+
+  indexes {
+    (id, user_id) [pk]
+  }
+}
+
+table async_tasks {
+  id uuid [pk, not null, default: `gen_random_uuid()`]
+  type text
+  status text
+  error jsonb
+  user_id text [not null]
+  duration integer
+  accessed_at "timestamp with time zone" [not null, default: `now()`]
+  created_at "timestamp with time zone" [not null, default: `now()`]
+  updated_at "timestamp with time zone" [not null, default: `now()`]
+}
+
+table files {
+  id text [pk, not null]
+  user_id text [not null]
+  file_type varchar(255) [not null]
+  file_hash varchar(64)
+  name text [not null]
+  size integer [not null]
+  url text [not null]
+  metadata jsonb
+  chunk_task_id uuid
+  embedding_task_id uuid
+  accessed_at "timestamp with time zone" [not null, default: `now()`]
+  created_at "timestamp with time zone" [not null, default: `now()`]
+  updated_at "timestamp with time zone" [not null, default: `now()`]
+}
+
+table global_files {
+  hash_id varchar(64) [pk, not null]
+  file_type varchar(255) [not null]
+  size integer [not null]
+  url text [not null]
+  metadata jsonb
+  created_at "timestamp with time zone" [not null, default: `now()`]
+  accessed_at "timestamp with time zone" [not null, default: `now()`]
+}
+
+table knowledge_base_files {
+  knowledge_base_id text [not null]
+  file_id text [not null]
+  created_at "timestamp with time zone" [not null, default: `now()`]
+
+  indexes {
+    (knowledge_base_id, file_id) [pk]
+  }
+}
+
+table knowledge_bases {
+  id text [pk, not null]
+  name text [not null]
+  description text
+  avatar text
+  type text
+  user_id text [not null]
+  is_public boolean [default: false]
+  settings jsonb
+  accessed_at "timestamp with time zone" [not null, default: `now()`]
+  created_at "timestamp with time zone" [not null, default: `now()`]
+  updated_at "timestamp with time zone" [not null, default: `now()`]
+}
+
+table message_chunks {
+  message_id text
+  chunk_id uuid
+
+  indexes {
+    (chunk_id, message_id) [pk]
+  }
+}
+
+table message_plugins {
+  id text [pk, not null]
+  tool_call_id text
+  type text [default: 'default']
+  api_name text
+  arguments text
+  identifier text
+  state jsonb
+  error jsonb
+}
+
+table message_queries {
+  id uuid [pk, not null, default: `gen_random_uuid()`]
+  message_id text [not null]
+  rewrite_query text
+  user_query text
+  embeddings_id uuid
+}
+
+table message_query_chunks {
+  id text
+  query_id uuid
+  chunk_id uuid
+  similarity "numeric(6, 5)"
+
+  indexes {
+    (chunk_id, id, query_id) [pk]
+  }
+}
+
+table message_tts {
+  id text [pk, not null]
+  content_md5 text
+  file_id text
+  voice text
+}
+
+table message_translates {
+  id text [pk, not null]
+  content text
+  from text
+  to text
+}
+
+table messages {
+  id text [pk, not null]
+  role text [not null]
+  content text
+  reasoning jsonb
+  search jsonb
+  metadata jsonb
+  model text
+  provider text
+  favorite boolean [default: false]
+  error jsonb
+  tools jsonb
+  trace_id text
+  observation_id text
+  client_id text
+  user_id text [not null]
+  session_id text
+  topic_id text
+  thread_id text
+  parent_id text
+  quota_id text
+  agent_id text
+  accessed_at "timestamp with time zone" [not null, default: `now()`]
+  created_at "timestamp with time zone" [not null, default: `now()`]
+  updated_at "timestamp with time zone" [not null, default: `now()`]
+
+  indexes {
+    created_at [name: 'messages_created_at_idx']
+    (client_id, user_id) [name: 'message_client_id_user_unique', unique]
+    topic_id [name: 'messages_topic_id_idx']
+    parent_id [name: 'messages_parent_id_idx']
+    quota_id [name: 'messages_quota_id_idx']
+  }
+}
+
+table messages_files {
+  file_id text [not null]
+  message_id text [not null]
+
+  indexes {
+    (file_id, message_id) [pk]
+  }
+}
+
+table nextauth_accounts {
+  access_token text
+  expires_at integer
+  id_token text
+  provider text [not null]
+  providerAccountId text [not null]
+  refresh_token text
+  scope text
+  session_state text
+  token_type text
+  type text [not null]
+  userId text [not null]
+
+  indexes {
+    (provider, providerAccountId) [pk]
+  }
+}
+
+table nextauth_authenticators {
+  counter integer [not null]
+  credentialBackedUp boolean [not null]
+  credentialDeviceType text [not null]
+  credentialID text [not null, unique]
+  credentialPublicKey text [not null]
+  providerAccountId text [not null]
+  transports text
+  userId text [not null]
+
+  indexes {
+    (userId, credentialID) [pk]
+  }
+}
+
+table nextauth_sessions {
+  expires timestamp [not null]
+  sessionToken text [pk, not null]
+  userId text [not null]
+}
+
+table nextauth_verificationtokens {
+  expires timestamp [not null]
+  identifier text [not null]
+  token text [not null]
+
+  indexes {
+    (identifier, token) [pk]
+  }
+}
+
+table chunks {
+  id uuid [pk, not null, default: `gen_random_uuid()`]
+  text text
+  abstract text
+  metadata jsonb
+  index integer
+  type varchar
+  user_id text
+  accessed_at "timestamp with time zone" [not null, default: `now()`]
+  created_at "timestamp with time zone" [not null, default: `now()`]
+  updated_at "timestamp with time zone" [not null, default: `now()`]
+}
+
+table embeddings {
+  id uuid [pk, not null, default: `gen_random_uuid()`]
+  chunk_id uuid [unique]
+  embeddings vector(1024)
+  model text
+  user_id text
+}
+
+table unstructured_chunks {
+  id uuid [pk, not null, default: `gen_random_uuid()`]
+  text text
+  metadata jsonb
+  index integer
+  type varchar
+  accessed_at "timestamp with time zone" [not null, default: `now()`]
+  created_at "timestamp with time zone" [not null, default: `now()`]
+  updated_at "timestamp with time zone" [not null, default: `now()`]
+  parent_id varchar
+  composite_id uuid
+  user_id text
+  file_id varchar
+}
+
+table rag_eval_dataset_records {
+  id integer [pk, not null]
+  dataset_id integer [not null]
+  ideal text
+  question text
+  reference_files text[]
+  metadata jsonb
+  user_id text
+  accessed_at "timestamp with time zone" [not null, default: `now()`]
+  created_at "timestamp with time zone" [not null, default: `now()`]
+  updated_at "timestamp with time zone" [not null, default: `now()`]
+}
+
+table rag_eval_datasets {
+  id integer [pk, not null]
+  description text
+  name text [not null]
+  knowledge_base_id text
+  user_id text
+  accessed_at "timestamp with time zone" [not null, default: `now()`]
+  created_at "timestamp with time zone" [not null, default: `now()`]
+  updated_at "timestamp with time zone" [not null, default: `now()`]
+}
+
+table rag_eval_evaluations {
+  id integer [pk, not null]
+  name text [not null]
+  description text
+  eval_records_url text
+  status text
+  error jsonb
+  dataset_id integer [not null]
+  knowledge_base_id text
+  language_model text
+  embedding_model text
+  user_id text
+  accessed_at "timestamp with time zone" [not null, default: `now()`]
+  created_at "timestamp with time zone" [not null, default: `now()`]
+  updated_at "timestamp with time zone" [not null, default: `now()`]
+}
+
+table rag_eval_evaluation_records {
+  id integer [pk, not null]
+  question text [not null]
+  answer text
+  context text[]
+  ideal text
+  status text
+  error jsonb
+  language_model text
+  embedding_model text
+  question_embedding_id uuid
+  duration integer
+  dataset_record_id integer [not null]
+  evaluation_id integer [not null]
+  user_id text
+  accessed_at "timestamp with time zone" [not null, default: `now()`]
+  created_at "timestamp with time zone" [not null, default: `now()`]
+  updated_at "timestamp with time zone" [not null, default: `now()`]
+}
+
+table agents_to_sessions {
+  agent_id text [not null]
+  session_id text [not null]
+
+  indexes {
+    (agent_id, session_id) [pk]
+  }
+}
+
+table file_chunks {
+  file_id varchar
+  chunk_id uuid
+  created_at "timestamp with time zone" [not null, default: `now()`]
+
+  indexes {
+    (file_id, chunk_id) [pk]
+  }
+}
+
+table files_to_sessions {
+  file_id text [not null]
+  session_id text [not null]
+
+  indexes {
+    (file_id, session_id) [pk]
+  }
+}
+
+table session_groups {
+  id text [pk, not null]
+  name text [not null]
+  sort integer
+  user_id text [not null]
+  client_id text
+  accessed_at "timestamp with time zone" [not null, default: `now()`]
+  created_at "timestamp with time zone" [not null, default: `now()`]
+  updated_at "timestamp with time zone" [not null, default: `now()`]
+
+  indexes {
+    (client_id, user_id) [name: 'session_group_client_id_user_unique', unique]
+  }
+}
+
+table sessions {
+  id text [pk, not null]
+  slug varchar(100) [not null]
+  title text
+  description text
+  avatar text
+  background_color text
+  type text [default: 'agent']
+  user_id text [not null]
+  group_id text
+  client_id text
+  pinned boolean [default: false]
+  accessed_at "timestamp with time zone" [not null, default: `now()`]
+  created_at "timestamp with time zone" [not null, default: `now()`]
+  updated_at "timestamp with time zone" [not null, default: `now()`]
+
+  indexes {
+    (slug, user_id) [name: 'slug_user_id_unique', unique]
+    (client_id, user_id) [name: 'sessions_client_id_user_id_unique', unique]
+  }
+}
+
+table threads {
+  id text [pk, not null]
+  title text
+  type text [not null]
+  status text [default: 'active']
+  topic_id text [not null]
+  source_message_id text [not null]
+  parent_thread_id text
+  user_id text [not null]
+  last_active_at "timestamp with time zone" [default: `now()`]
+  accessed_at "timestamp with time zone" [not null, default: `now()`]
+  created_at "timestamp with time zone" [not null, default: `now()`]
+  updated_at "timestamp with time zone" [not null, default: `now()`]
+}
+
+table topics {
+  id text [pk, not null]
+  title text
+  favorite boolean [default: false]
+  session_id text
+  user_id text [not null]
+  client_id text
+  history_summary text
+  metadata jsonb
+  accessed_at "timestamp with time zone" [not null, default: `now()`]
+  created_at "timestamp with time zone" [not null, default: `now()`]
+  updated_at "timestamp with time zone" [not null, default: `now()`]
+
+  indexes {
+    (client_id, user_id) [name: 'topic_client_id_user_id_unique', unique]
+  }
+}
+
+table user_installed_plugins {
+  user_id text [not null]
+  identifier text [not null]
+  type text [not null]
+  manifest jsonb
+  settings jsonb
+  custom_params jsonb
+  accessed_at "timestamp with time zone" [not null, default: `now()`]
+  created_at "timestamp with time zone" [not null, default: `now()`]
+  updated_at "timestamp with time zone" [not null, default: `now()`]
+
+  indexes {
+    (user_id, identifier) [pk]
+  }
+}
+
+table user_settings {
+  id text [pk, not null]
+  tts jsonb
+  key_vaults text
+  general jsonb
+  language_model jsonb
+  system_agent jsonb
+  default_agent jsonb
+  tool jsonb
+}
+
+table users {
+  id text [pk, not null]
+  username text [unique]
+  email text
+  avatar text
+  phone text
+  first_name text
+  last_name text
+  full_name text
+  is_onboarded boolean [default: false]
+  clerk_created_at "timestamp with time zone"
+  email_verified_at "timestamp with time zone"
+  preference jsonb
+  accessed_at "timestamp with time zone" [not null, default: `now()`]
+  created_at "timestamp with time zone" [not null, default: `now()`]
+  updated_at "timestamp with time zone" [not null, default: `now()`]
+}
+
+ref: agents_knowledge_bases.knowledge_base_id - knowledge_bases.id
+
+ref: agents_knowledge_bases.agent_id > agents.id
+
+ref: agents_to_sessions.session_id > sessions.id
+
+ref: agents_to_sessions.agent_id > agents.id
+
+ref: unstructured_chunks.file_id - files.id
+
+ref: files.embedding_task_id - async_tasks.id
+
+ref: messages.session_id - sessions.id
+
+ref: messages.parent_id - messages.id
+
+ref: messages.topic_id - topics.id
+
+ref: threads.source_message_id - messages.id
+
+ref: sessions.group_id - session_groups.id
+
+ref: topics.session_id - sessions.id
@@ -36,7 +36,7 @@ tags:

  <Image alt={'Clerk 添加 Webhooks 端点'} src={'https://github.com/lobehub/lobe-chat/assets/28616219/f50f47fb-5e8e-4930-bf4e-8cf6f5b8afb9'} />

-  在 endppint 中填写你的项目 URL，如 `https://your-project.com/api/webhooks/clerk`。然后在订阅事件（Subscribe to events）中，勾选 user 的三个事件（`user.created` 、`user.deleted`、`user.updated`），然后点击创建。
+  在 endpoint 中填写你的项目 URL，如 `https://your-project.com/api/webhooks/clerk`。然后在订阅事件（Subscribe to events）中，勾选 user 的三个事件（`user.created` 、`user.deleted`、`user.updated`），然后点击创建。

  <Callout type={'warning'}>URL 的`https://`不可缺失，须保持 URL 的完整性</Callout>

@@ -14,10 +14,10 @@ tags:

 LobeChat supports customizing the model list during deployment. This configuration is done in the environment for each [model provider](/docs/self-hosting/environment-variables/model-provider).

-You can use `+` to add a model, `-` to hide a model, and use `model name=display name<extension configuration>` to customize the display name of a model, separated by English commas. The basic syntax is as follows:
+You can use `+` to add a model, `-` to hide a model, and use `model name->deploymentName=display name<extension configuration>` to customize the display name of a model, separated by English commas. The basic syntax is as follows:

 ```text
-id=displayName<maxToken:vision:reasoning:search:fc:file>,model2,model3
+id->deploymentName=displayName<maxToken:vision:reasoning:search:fc:file>,model2,model3
 ```

 For example: `+qwen-7b-chat,+glm-6b,-gpt-3.5-turbo,gpt-4-0125-preview=gpt-4-turbo`
@@ -29,7 +29,7 @@ In the above example, it adds `qwen-7b-chat` and `glm-6b` to the model list, rem
 Considering the diversity of model capabilities, we started to add extension configuration in version `0.147.8`, with the following rules:

 ```shell
-id=displayName<maxToken:vision:reasoning:search:fc:file>
+id->deploymentName=displayName<maxToken:vision:reasoning:search:fc:file>
 ```

 The first value in angle brackets is designated as the `maxToken` for this model. The second value and beyond are the model's extension capabilities, separated by colons `:`, and the order is not important.
@@ -13,10 +13,10 @@ tags:

 LobeChat 支持在部署时自定义模型列表，详情请参考 [模型提供商](/zh/docs/self-hosting/environment-variables/model-provider) 。

-你可以使用 `+` 增加一个模型，使用 `-` 来隐藏一个模型，使用 `模型名=展示名<扩展配置>` 来自定义模型的展示名，用英文逗号隔开。通过 `<>` 来添加扩展配置。基本语法如下：
+你可以使用 `+` 增加一个模型，使用 `-` 来隐藏一个模型，使用 `模型名->部署名=展示名<扩展配置>` 来自定义模型的展示名，用英文逗号隔开。通过 `<>` 来添加扩展配置。基本语法如下：

 ```text
-id=displayName<maxToken:vision:reasoning:search:fc:file>,model2,model3
+id->deploymentName=displayName<maxToken:vision:reasoning:search:fc:file>,model2,model3
 ```

 例如： `+qwen-7b-chat,+glm-6b,-gpt-3.5-turbo,gpt-4-0125-preview=gpt-4-turbo`
@@ -28,7 +28,7 @@ id=displayName<maxToken:vision:reasoning:search:fc:file>,model2,model3
 考虑到模型的能力多样性，我们在 `0.147.8` 版本开始增加扩展性配置，它的规则如下：

 ```shell
-id=displayName<maxToken:vision:reasoning:search:fc:file>
+id->deploymentName=displayName<maxToken:vision:reasoning:search:fc:file>
 ```

 尖括号第一个值约定为这个模型的 `maxToken` 。第二个及以后作为模型的扩展能力，能力与能力之间用冒号 `:` 作为分隔符，顺序不重要。
@@ -94,7 +94,7 @@ If you need to use Azure OpenAI to provide model services, you can refer to the
 ### `AZURE_MODEL_LIST`

 - Type: Optional
- Description: Used to control the model list, use `+` to add a model, use `-` to hide a model, use `id->deplymentName=displayName` to customize the display name of a model, separated by commas. Definition syntax rules see [model-list][model-list]
+- Description: Used to control the model list, use `+` to add a model, use `-` to hide a model, use `id->deploymentName=displayName` to customize the display name of a model, separated by commas. Definition syntax rules see [model-list][model-list]
 - Default: `-`
 - Example: `gpt-35-turbo->my-deploy=GPT 3.5 Turbo` 或 `gpt-4-turbo->my-gpt4=GPT 4 Turbo<128000:vision:fc>`

@@ -183,6 +183,13 @@ If you need to use Azure OpenAI to provide model services, you can refer to the
 - Default: -
 - Example: `sk-xxxxxx...xxxxxx`

+### `DEEPSEEK_MODEL_LIST`
+
+- Type: Optional
+- Description: Used to control the model list, use `+` to add a model, use `-` to hide a model, use `model_name=displayName` to customize the display name of a model, separated by commas. Definition syntax rules see [model-list][model-list]
+- Default: `-`
+- Example: `-all,+deepseek-reasoner`
+
 ## XAI

 ### `XAI_API_KEY`
@@ -425,6 +432,13 @@ If you need to use Azure OpenAI to provide model services, you can refer to the
 - Default: `-`
 - Example: `-all,+qwen-turbo-latest,+qwen-plus-latest`

+### `QWEN_PROXY_URL`
+
+- Type: Optional
+- Description: If you manually configure the Qwen API proxy, you can use this configuration item to override the default Qwen API request base URL
+- Default: `https://dashscope.aliyuncs.com/compatible-mode/v1`
+- Example: `https://my-qwen-proxy.com/v1`
+
 ## Stepfun AI

 ### `STEPFUN_API_KEY`
@@ -555,9 +569,9 @@ If you need to use Azure OpenAI to provide model services, you can refer to the
 ### `VOLCENGINE_MODEL_LIST`

 - Type: Optional
- Description: Used to control the model list, use `+` to add a model, use `-` to hide a model, use `model_name=display_name` to customize the display name of a model, separated by commas. Definition syntax rules see [model-list][model-list]
+- Description: Used to control the model list, use `+` to add a model, use `-` to hide a model, use `model_name->deploymentName=display_name` to customize the display name of a model, separated by commas. Definition syntax rules see [model-list][model-list]
 - Default: `-`
- Example: `-all,+deepseek-r1-250120,+deepseek-v3-241226,+doubao-1-5-pro-256k-250115,+doubao-1-5-pro-32k-250115,+doubao-1-5-lite-32k-250115`
+- Example: `-all,+deepseek-r1->deepseek-r1-250120,+deepseek-v3->deepseek-v3-241226,+doubao-1.5-pro-256k->doubao-1-5-pro-256k-250115,+doubao-1.5-pro-32k->doubao-1-5-pro-32k-250115,+doubao-1.5-lite-32k->doubao-1-5-lite-32k-250115`


 [model-list]: /docs/self-hosting/advanced/model-list
@@ -181,6 +181,13 @@ LobeChat 在部署时提供了丰富的模型服务商相关的环境变量，
 - 默认值：-
 - 示例：`sk-xxxxxx...xxxxxx`

+### `DEEPSEEK_MODEL_LIST`
+
+- 类型：可选
+- 描述：用来控制模型列表，使用 `+` 增加一个模型，使用 `-` 来隐藏一个模型，使用 `模型名=展示名<扩展配置>` 来自定义模型的展示名，用英文逗号隔开。模型定义语法规则见 [模型列表][model-list]
+- 默认值：`-`
+- 示例：`-all,+deepseek-reasoner`
+
 ## XAI

 ### `XAI_API_KEY`
@@ -423,6 +430,13 @@ LobeChat 在部署时提供了丰富的模型服务商相关的环境变量，
 - 默认值：`-`
 - 示例：`-all,+qwen-turbo-latest,+qwen-plus-latest`

+### `QWEN_PROXY_URL`
+
+- 类型：可选
+- 描述：如果你手动配置了 Qwen 接口代理，可以使用此配置项来覆盖默认的 Qwen API 请求基础 URL
+- 默认值：`https://dashscope.aliyuncs.com/compatible-mode/v1`
+- 示例：`https://my-qwen-proxy.com/v1`
+
 ## Stepfun AI

 ### `STEPFUN_API_KEY`
@@ -553,8 +567,8 @@ LobeChat 在部署时提供了丰富的模型服务商相关的环境变量，
 ### `VOLCENGINE_MODEL_LIST`

 - 类型：可选
- 描述：用来控制模型列表，使用 `+` 增加一个模型，使用 `-` 来隐藏一个模型，使用 `模型名=展示名<扩展配置>` 来自定义模型的展示名，用英文逗号隔开。模型定义语法规则见 [模型列表][model-list]
+- 描述：用来控制模型列表，使用 `+` 增加一个模型，使用 `-` 来隐藏一个模型，使用 `模型名->部署名=展示名<扩展配置>` 来自定义模型的展示名，用英文逗号隔开。模型定义语法规则见 [模型列表][model-list]
 - 默认值：`-`
- 示例：`-all,+deepseek-r1-250120,+deepseek-v3-241226,+doubao-1-5-pro-256k-250115,+doubao-1-5-pro-32k-250115,+doubao-1-5-lite-32k-250115`
+- 示例：`-all,+deepseek-r1->deepseek-r1-250120,+deepseek-v3->deepseek-v3-241226,+doubao-1.5-pro-256k->doubao-1-5-pro-256k-250115,+doubao-1.5-pro-32k->doubao-1-5-pro-32k-250115,+doubao-1.5-lite-32k->doubao-1-5-lite-32k-250115`

 [model-list]: /zh/docs/self-hosting/advanced/model-list
@@ -140,7 +140,7 @@ tags:

  <Image alt={'Clerk 添加 Webhooks 端点'} src={'https://github.com/lobehub/lobe-chat/assets/28616219/f50f47fb-5e8e-4930-bf4e-8cf6f5b8afb9'} />

-  在 endppint 中填写你的 Vercel 项目的 URL，如 `https://your-project.vercel.app/api/webhooks/clerk`。然后在订阅事件（Subscribe to events）中，勾选 user 的三个事件（`user.created` 、`user.deleted`、`user.updated`），然后点击创建。
+  在 endpoint 中填写你的 Vercel 项目的 URL，如 `https://your-project.vercel.app/api/webhooks/clerk`。然后在订阅事件（Subscribe to events）中，勾选 user 的三个事件（`user.created` 、`user.deleted`、`user.updated`），然后点击创建。

  <Callout type={'warning'}>URL 的`https://`不可缺失，须保持 URL 的完整性</Callout>

@@ -64,6 +64,9 @@
    "stop": "توقف",
    "warp": "تغيير السطر"
  },
+  "intentUnderstanding": {
+    "title": "جارٍ فهم وتحليل نواياك..."
+  },
  "knowledgeBase": {
    "all": "جميع المحتويات",
    "allFiles": "جميع الملفات",
@@ -144,7 +147,6 @@
        "desc": "تحديد ما إذا كان من الضروري البحث بناءً على محتوى المحادثة",
        "title": "الاتصال الذكي"
      },
-      "disable": "النموذج الحالي لا يدعم استدعاء الوظائف، لذا لا يمكن استخدام وظيفة الاتصال الذكي",
      "off": {
        "desc": "استخدام المعرفة الأساسية للنموذج فقط، دون إجراء بحث عبر الإنترنت",
        "title": "إيقاف الاتصال"
@@ -155,6 +157,10 @@
      },
      "useModelBuiltin": "استخدام محرك البحث المدمج في النموذج"
    },
+    "searchModel": {
+      "desc": "النموذج الحالي لا يدعم استدعاء الدوال، لذا يجب استخدام نموذج يدعم استدعاء الدوال للبحث عبر الإنترنت",
+      "title": "نموذج البحث المساعد"
+    },
    "title": "بحث عبر الإنترنت"
  },
  "searchAgentPlaceholder": "مساعد البحث...",
@@ -76,6 +76,7 @@
      "custom": "نموذج مخصص، الإعداد الافتراضي يدعم الاستدعاء الوظيفي والتعرف البصري، يرجى التحقق من قدرة النموذج على القيام بذلك بناءً على الحالة الفعلية",
      "file": "يدعم هذا النموذج قراءة وتعرف الملفات المرفوعة",
      "functionCall": "يدعم هذا النموذج استدعاء الوظائف",
+      "imageOutput": "يدعم هذا النموذج إنشاء الصور",
      "reasoning": "يدعم هذا النموذج التفكير العميق",
      "search": "يدعم هذا النموذج البحث عبر الإنترنت",
      "tokens": "يدعم هذا النموذج حتى {{tokens}} رمزًا في جلسة واحدة",
@@ -85,6 +86,8 @@
  },
  "ModelSwitchPanel": {
    "emptyModel": "لا توجد نماذج ممكن تمكينها، يرجى الانتقال إلى الإعدادات لتمكينها",
+    "emptyProvider": "لا توجد مزودات مفعلة، يرجى الذهاب إلى الإعدادات لتفعيلها",
+    "goToSettings": "اذهب إلى الإعدادات",
    "provider": "مزود"
  },
  "OllamaSetupGuide": {
@@ -506,6 +506,9 @@
  "anthropic/claude-3.5-sonnet": {
    "description": "Claude 3.5 Sonnet يقدم قدرات تتجاوز Opus وسرعة أكبر من Sonnet، مع الحفاظ على نفس السعر. يتميز Sonnet بمهارات خاصة في البرمجة وعلوم البيانات ومعالجة الصور والمهام الوكيلة."
  },
+  "anthropic/claude-3.7-sonnet": {
+    "description": "Claude 3.7 Sonnet هو أكثر النماذج ذكاءً من Anthropic حتى الآن، وهو أيضًا أول نموذج مختلط للتفكير في السوق. يمكن لـ Claude 3.7 Sonnet إنتاج استجابات شبه فورية أو تفكير تدريجي ممتد، حيث يمكن للمستخدمين رؤية هذه العمليات بوضوح. يتميز Sonnet بشكل خاص في البرمجة، وعلوم البيانات، ومعالجة الصور، والمهام الوكيلة."
+  },
  "aya": {
    "description": "Aya 23 هو نموذج متعدد اللغات أطلقته Cohere، يدعم 23 لغة، مما يسهل التطبيقات اللغوية المتنوعة."
  },
@@ -830,6 +833,12 @@
  "gemini-2.0-flash-001": {
    "description": "Gemini 2.0 Flash يقدم ميزات وتحسينات من الجيل التالي، بما في ذلك سرعة فائقة، واستخدام أدوات أصلية، وتوليد متعدد الوسائط، ونافذة سياق تصل إلى 1M توكن."
  },
+  "gemini-2.0-flash-exp": {
+    "description": "نموذج جمنيس 2.0 فلاش، تم تحسينه لتحقيق أهداف مثل الكفاءة من حيث التكلفة وانخفاض الكمون."
+  },
+  "gemini-2.0-flash-exp-image-generation": {
+    "description": "نموذج تجريبي Gemini 2.0 Flash، يدعم توليد الصور"
+  },
  "gemini-2.0-flash-lite": {
    "description": "نموذج جمنّي 2.0 فلاش هو نسخة معدلة، تم تحسينها لتحقيق الكفاءة من حيث التكلفة والحد من التأخير."
  },
@@ -32,6 +32,7 @@
    "title": "قائمة المواضيع"
  },
  "searchPlaceholder": "ابحث عن موضوع...",
+  "searchResultEmpty": "لا توجد نتائج للبحث",
  "temp": "مؤقت",
  "title": "موضوع"
 }
@@ -64,6 +64,9 @@
    "stop": "Спри",
    "warp": "Нов ред"
  },
+  "intentUnderstanding": {
+    "title": "Разбирам и анализирам вашето намерение..."
+  },
  "knowledgeBase": {
    "all": "Всички съдържания",
    "allFiles": "Всички файлове",
@@ -144,7 +147,6 @@
        "desc": "Интелигентно определяне на необходимостта от търсене въз основа на съдържанието на разговора",
        "title": "Интелигентно свързване"
      },
-      "disable": "Текущият модел не поддържа извикване на функции, затова не може да се използва интелигентно свързване",
      "off": {
        "desc": "Използва само основните знания на модела, без интернет търсене",
        "title": "Изключване на свързването"
@@ -155,6 +157,10 @@
      },
      "useModelBuiltin": "Използване на вградената търсачка на модела"
    },
+    "searchModel": {
+      "desc": "Текущият модел не поддържа извикване на функции, затова е необходимо да се комбинира с модел, който поддържа извикване на функции, за да се извърши търсене в интернет",
+      "title": "Модел за търсене на помощ"
+    },
    "title": "Търсене в интернет"
  },
  "searchAgentPlaceholder": "Търсач на помощ...",
@@ -76,6 +76,7 @@
      "custom": "Потребителски модел, по подразбиране поддържа функционалност за функционални обаждания и визуално разпознаване, моля, потвърдете наличието на тези възможности спрямо реалните условия",
      "file": "Този модел поддържа качване на файлове и разпознаване",
      "functionCall": "Този модел поддържа функционални обаждания (Function Call)",
+      "imageOutput": "Този модел поддържа генериране на изображения",
      "reasoning": "Този модел поддържа дълбочинно мислене",
      "search": "Този модел поддържа търсене в мрежата",
      "tokens": "Този модел поддържа до {{tokens}} токена за една сесия",
@@ -85,6 +86,8 @@
  },
  "ModelSwitchPanel": {
    "emptyModel": "Няма активирани модели, моля, посетете настройките и ги активирайте",
+    "emptyProvider": "Няма активиран доставчик на услуги, моля, отидете в настройките, за да го активирате",
+    "goToSettings": "Отидете в настройките",
    "provider": "Доставчик"
  },
  "OllamaSetupGuide": {
@@ -506,6 +506,9 @@
  "anthropic/claude-3.5-sonnet": {
    "description": "Claude 3.5 Sonnet предлага способности, надхвърлящи Opus, и по-бърза скорост в сравнение с Sonnet, като същевременно запазва същата цена. Sonnet е особено силен в програмирането, науката за данни, визуалната обработка и агентските задачи."
  },
+  "anthropic/claude-3.7-sonnet": {
+    "description": "Claude 3.7 Sonnet е най-интелигентният модел на Anthropic до момента и е първият хибриден модел за разсъждение на пазара. Claude 3.7 Sonnet може да генерира почти мигновени отговори или удължено стъпково мислене, което позволява на потребителите ясно да видят тези процеси. Sonnet е особено добър в програмирането, науката за данни, визуалната обработка и агентските задачи."
+  },
  "aya": {
    "description": "Aya 23 е многозначен модел, представен от Cohere, поддържащ 23 езика, предоставяйки удобство за многоезични приложения."
  },
@@ -830,6 +833,12 @@
  "gemini-2.0-flash-001": {
    "description": "Gemini 2.0 Flash предлага следващо поколение функции и подобрения, включително изключителна скорост, нативна употреба на инструменти, многомодално генериране и контекстен прозорец от 1M токена."
  },
+  "gemini-2.0-flash-exp": {
+    "description": "Gemini 2.0 Flash моделна вариация, оптимизирана за икономичност и ниска латентност."
+  },
+  "gemini-2.0-flash-exp-image-generation": {
+    "description": "Gemini 2.0 Flash експериментален модел, който поддържа генериране на изображения"
+  },
  "gemini-2.0-flash-lite": {
    "description": "Gemini 2.0 Flash е вариант на модела, оптимизиран за икономичност и ниска латентност."
  },
@@ -32,6 +32,7 @@
    "title": "Списък с теми"
  },
  "searchPlaceholder": "Търсене на теми...",
+  "searchResultEmpty": "Няма намерени резултати",
  "temp": "Временен",
  "title": "Тема"
 }
@@ -64,6 +64,9 @@
    "stop": "Stoppen",
    "warp": "Zeilenumbruch"
  },
+  "intentUnderstanding": {
+    "title": "Verstehe und analysiere gerade Ihre Absicht..."
+  },
  "knowledgeBase": {
    "all": "Alle Inhalte",
    "allFiles": "Alle Dateien",
@@ -144,7 +147,6 @@
        "desc": "Intelligente Beurteilung, ob eine Suche basierend auf dem Gesprächsinhalt erforderlich ist",
        "title": "Intelligente Vernetzung"
      },
-      "disable": "Das aktuelle Modell unterstützt keine Funktionsaufrufe, daher kann die intelligente Vernetzungsfunktion nicht verwendet werden",
      "off": {
        "desc": "Verwendet nur das Grundwissen des Modells, ohne Netzsuche",
        "title": "Vernetzung deaktivieren"
@@ -155,6 +157,10 @@
      },
      "useModelBuiltin": "Verwenden Sie die integrierte Suchmaschine des Modells"
    },
+    "searchModel": {
+      "desc": "Das aktuelle Modell unterstützt keine Funktionsaufrufe, daher muss es mit einem Modell kombiniert werden, das Funktionsaufrufe unterstützt, um online zu suchen",
+      "title": "Suchunterstützungsmodell"
+    },
    "title": "Netzwerksuche"
  },
  "searchAgentPlaceholder": "Suchassistent...",
@@ -76,6 +76,7 @@
      "custom": "Benutzerdefiniertes Modell, standardmäßig unterstützt es sowohl Funktionsaufrufe als auch visuelle Erkennung. Bitte überprüfen Sie die Verfügbarkeit dieser Fähigkeiten basierend auf den tatsächlichen Gegebenheiten.",
      "file": "Dieses Modell unterstützt das Hochladen von Dateien und deren Erkennung.",
      "functionCall": "Dieses Modell unterstützt Funktionsaufrufe.",
+      "imageOutput": "Dieses Modell unterstützt die Generierung von Bildern",
      "reasoning": "Dieses Modell unterstützt tiefes Denken",
      "search": "Dieses Modell unterstützt die Online-Suche",
      "tokens": "Dieses Modell unterstützt maximal {{tokens}} Tokens pro Sitzung.",
@@ -85,6 +86,8 @@
  },
  "ModelSwitchPanel": {
    "emptyModel": "Kein aktiviertes Modell. Bitte gehen Sie zu den Einstellungen, um es zu aktivieren.",
+    "emptyProvider": "Es sind keine aktiven Anbieter vorhanden, bitte gehen Sie zu den Einstellungen, um sie zu aktivieren",
+    "goToSettings": "Zu den Einstellungen gehen",
    "provider": "Anbieter"
  },
  "OllamaSetupGuide": {
@@ -506,6 +506,9 @@
  "anthropic/claude-3.5-sonnet": {
    "description": "Claude 3.5 Sonnet bietet Fähigkeiten, die über Opus hinausgehen, und eine schnellere Geschwindigkeit als Sonnet, während es den gleichen Preis wie Sonnet beibehält. Sonnet ist besonders gut in Programmierung, Datenwissenschaft, visueller Verarbeitung und Agentenaufgaben."
  },
+  "anthropic/claude-3.7-sonnet": {
+    "description": "Claude 3.7 Sonnet ist das intelligenteste Modell von Anthropic bis heute und das erste hybride Inferenzmodell auf dem Markt. Claude 3.7 Sonnet kann nahezu sofortige Antworten oder verlängerte, schrittweise Überlegungen erzeugen, wobei die Benutzer diesen Prozess klar nachvollziehen können. Sonnet ist besonders gut in den Bereichen Programmierung, Datenwissenschaft, visuelle Verarbeitung und Agentenaufgaben."
+  },
  "aya": {
    "description": "Aya 23 ist ein mehrsprachiges Modell von Cohere, das 23 Sprachen unterstützt und die Anwendung in einer Vielzahl von Sprachen erleichtert."
  },
@@ -830,6 +833,12 @@
  "gemini-2.0-flash-001": {
    "description": "Gemini 2.0 Flash bietet nächste Generation Funktionen und Verbesserungen, einschließlich außergewöhnlicher Geschwindigkeit, nativer Werkzeugnutzung, multimodaler Generierung und einem Kontextfenster von 1M Tokens."
  },
+  "gemini-2.0-flash-exp": {
+    "description": "Gemini 2.0 Flash-Modellvariante, die auf Kosteneffizienz und niedrige Latenz optimiert ist."
+  },
+  "gemini-2.0-flash-exp-image-generation": {
+    "description": "Gemini 2.0 Flash Experimentmodell, das die Bildgenerierung unterstützt"
+  },
  "gemini-2.0-flash-lite": {
    "description": "Gemini 2.0 Flash ist eine Modellvariante, die auf Kosteneffizienz und niedrige Latenz optimiert ist."
  },
@@ -32,6 +32,7 @@
    "title": "Themenliste"
  },
  "searchPlaceholder": "Themen suchen...",
+  "searchResultEmpty": "Keine Suchergebnisse vorhanden",
  "temp": "Vorübergehend",
  "title": "Thema"
 }
@@ -64,6 +64,9 @@
    "stop": "Stop",
    "warp": "New Line"
  },
+  "intentUnderstanding": {
+    "title": "Understanding and analyzing your intent..."
+  },
  "knowledgeBase": {
    "all": "All Content",
    "allFiles": "All Files",
@@ -144,7 +147,6 @@
        "desc": "Intelligently determine whether a search is needed based on the conversation content",
        "title": "Smart Online Search"
      },
-      "disable": "The current model does not support function calls, so the smart online search feature is unavailable",
      "off": {
        "desc": "Use only the model's basic knowledge without performing a web search",
        "title": "Disable Online Search"
@@ -155,6 +157,10 @@
      },
      "useModelBuiltin": "Use the model's built-in search engine"
    },
+    "searchModel": {
+      "desc": "The current model does not support function calls, so it needs to be paired with a model that does support function calls for online searching.",
+      "title": "Search Assistant Model"
+    },
    "title": "Online Search"
  },
  "searchAgentPlaceholder": "Search assistants...",
@@ -76,6 +76,7 @@
      "custom": "Custom model, by default, supports both function call and visual recognition. Please verify the availability of the above capabilities based on actual situations.",
      "file": "This model supports file upload for reading and recognition.",
      "functionCall": "This model supports function call.",
+      "imageOutput": "This model supports image generation",
      "reasoning": "This model supports deep thinking",
      "search": "This model supports online search",
      "tokens": "This model supports up to {{tokens}} tokens in a single session.",
@@ -85,6 +86,8 @@
  },
  "ModelSwitchPanel": {
    "emptyModel": "No enabled model. Please go to settings to enable.",
+    "emptyProvider": "No enabled providers. Please go to settings to enable one.",
+    "goToSettings": "Go to settings",
    "provider": "Provider"
  },
  "OllamaSetupGuide": {
@@ -506,6 +506,9 @@
  "anthropic/claude-3.5-sonnet": {
    "description": "Claude 3.5 Sonnet offers capabilities that surpass Opus and faster speeds than Sonnet, while maintaining the same pricing as Sonnet. Sonnet excels particularly in programming, data science, visual processing, and agent tasks."
  },
+  "anthropic/claude-3.7-sonnet": {
+    "description": "Claude 3.7 Sonnet is Anthropic's most advanced model to date and the first hybrid reasoning model on the market. Claude 3.7 Sonnet can generate near-instant responses or extended step-by-step reasoning, allowing users to clearly observe these processes. Sonnet excels particularly in programming, data science, visual processing, and agent tasks."
+  },
  "aya": {
    "description": "Aya 23 is a multilingual model launched by Cohere, supporting 23 languages, facilitating diverse language applications."
  },
@@ -830,6 +833,12 @@
  "gemini-2.0-flash-001": {
    "description": "Gemini 2.0 Flash offers next-generation features and improvements, including exceptional speed, native tool usage, multimodal generation, and a 1M token context window."
  },
+  "gemini-2.0-flash-exp": {
+    "description": "Gemini 2.0 Flash model variant optimized for cost-effectiveness and low latency."
+  },
+  "gemini-2.0-flash-exp-image-generation": {
+    "description": "Gemini 2.0 Flash experimental model, supports image generation"
+  },
  "gemini-2.0-flash-lite": {
    "description": "Gemini 2.0 Flash is a variant of the model optimized for cost-effectiveness and low latency."
  },
@@ -32,6 +32,7 @@
    "title": "Topic List"
  },
  "searchPlaceholder": "Search Topics...",
+  "searchResultEmpty": "No search results found.",
  "temp": "Temporary",
  "title": "Topic"
 }
@@ -64,6 +64,9 @@
    "stop": "Detener",
    "warp": "Salto de línea"
  },
+  "intentUnderstanding": {
+    "title": "Entendiendo y analizando su intención..."
+  },
  "knowledgeBase": {
    "all": "Todo el contenido",
    "allFiles": "Todos los archivos",
@@ -144,7 +147,6 @@
        "desc": "Determina inteligentemente si se necesita buscar según el contenido de la conversación",
        "title": "Conexión inteligente"
      },
-      "disable": "El modelo actual no admite llamadas a funciones, por lo que no se puede utilizar la función de conexión inteligente",
      "off": {
        "desc": "Utiliza solo el conocimiento básico del modelo, sin realizar búsquedas en línea",
        "title": "Desactivar conexión"
@@ -155,6 +157,10 @@
      },
      "useModelBuiltin": "Utilizar el motor de búsqueda integrado del modelo"
    },
+    "searchModel": {
+      "desc": "El modelo actual no admite llamadas a funciones, por lo que se necesita combinarlo con un modelo que admita llamadas a funciones para realizar búsquedas en línea",
+      "title": "Modelo de búsqueda auxiliar"
+    },
    "title": "Búsqueda en línea"
  },
  "searchAgentPlaceholder": "Asistente de búsqueda...",
@@ -76,6 +76,7 @@
      "custom": "Modelo personalizado: admite llamadas de función y reconocimiento visual. Verifique la disponibilidad de estas capacidades según sea necesario.",
      "file": "Este modelo admite la carga y reconocimiento de archivos.",
      "functionCall": "Este modelo admite llamadas de función.",
+      "imageOutput": "Este modelo admite la generación de imágenes",
      "reasoning": "Este modelo admite un pensamiento profundo",
      "search": "Este modelo admite búsqueda en línea",
      "tokens": "Este modelo admite un máximo de {{tokens}} tokens por sesión.",
@@ -85,6 +86,8 @@
  },
  "ModelSwitchPanel": {
    "emptyModel": "No hay modelos habilitados. Vaya a la configuración para habilitarlos.",
+    "emptyProvider": "No hay proveedores habilitados, por favor ve a la configuración para activarlos",
+    "goToSettings": "Ir a la configuración",
    "provider": "Proveedor"
  },
  "OllamaSetupGuide": {
@@ -506,6 +506,9 @@
  "anthropic/claude-3.5-sonnet": {
    "description": "Claude 3.5 Sonnet ofrece capacidades que superan a Opus y una velocidad más rápida que Sonnet, manteniendo el mismo precio que Sonnet. Sonnet es especialmente hábil en programación, ciencia de datos, procesamiento visual y tareas de agente."
  },
+  "anthropic/claude-3.7-sonnet": {
+    "description": "Claude 3.7 Sonnet es el modelo más inteligente de Anthropic hasta la fecha y el primer modelo de razonamiento híbrido en el mercado. Claude 3.7 Sonnet puede generar respuestas casi instantáneas o un pensamiento prolongado y gradual, permitiendo a los usuarios observar claramente estos procesos. Sonnet es especialmente hábil en programación, ciencia de datos, procesamiento visual y tareas de agente."
+  },
  "aya": {
    "description": "Aya 23 es un modelo multilingüe lanzado por Cohere, que admite 23 idiomas, facilitando aplicaciones de lenguaje diversas."
  },
@@ -830,6 +833,12 @@
  "gemini-2.0-flash-001": {
    "description": "Gemini 2.0 Flash ofrece funciones y mejoras de próxima generación, incluyendo velocidad excepcional, uso de herramientas nativas, generación multimodal y una ventana de contexto de 1M tokens."
  },
+  "gemini-2.0-flash-exp": {
+    "description": "Variante del modelo Gemini 2.0 Flash, optimizada para objetivos como la rentabilidad y la baja latencia."
+  },
+  "gemini-2.0-flash-exp-image-generation": {
+    "description": "Modelo experimental Gemini 2.0 Flash, que admite la generación de imágenes"
+  },
  "gemini-2.0-flash-lite": {
    "description": "Variante del modelo Gemini 2.0 Flash, optimizada para objetivos como la rentabilidad y la baja latencia."
  },
@@ -32,6 +32,7 @@
    "title": "Lista de temas"
  },
  "searchPlaceholder": "Buscar temas...",
+  "searchResultEmpty": "No hay resultados de búsqueda disponibles",
  "temp": "Temporal",
  "title": "Tema"
 }
@@ -64,6 +64,9 @@
    "stop": "توقف",
    "warp": "خط جدید"
  },
+  "intentUnderstanding": {
+    "title": "در حال درک و تحلیل نیت شما..."
+  },
  "knowledgeBase": {
    "all": "همه محتوا",
    "allFiles": "همه فایل‌ها",
@@ -144,7 +147,6 @@
        "desc": "به طور هوشمندانه بر اساس محتوای گفتگو تشخیص می‌دهد که آیا نیاز به جستجو است",
        "title": "اتصال هوشمند"
      },
-      "disable": "مدل فعلی از فراخوانی توابع پشتیبانی نمی‌کند، بنابراین نمی‌توان از ویژگی اتصال هوشمند استفاده کرد",
      "off": {
        "desc": "فقط از دانش پایه مدل استفاده می‌کند و جستجوی اینترنتی انجام نمی‌دهد",
        "title": "قطع اتصال"
@@ -155,6 +157,10 @@
      },
      "useModelBuiltin": "استفاده از موتور جستجوی داخلی مدل"
    },
+    "searchModel": {
+      "desc": "مدل فعلی از فراخوانی توابع پشتیبانی نمی‌کند، بنابراین نیاز است که با مدلی که از فراخوانی توابع پشتیبانی می‌کند، برای جستجوی آنلاین ترکیب شود",
+      "title": "مدل جستجوی کمکی"
+    },
    "title": "جستجوی متصل"
  },
  "searchAgentPlaceholder": "جستجوی دستیار...",
@@ -76,6 +76,7 @@
      "custom": "مدل سفارشی، تنظیمات پیش‌فرض از فراخوانی توابع و تشخیص بصری پشتیبانی می‌کند، لطفاً قابلیت‌های فوق را بر اساس شرایط واقعی بررسی کنید",
      "file": "این مدل از بارگذاری و شناسایی فایل‌ها پشتیبانی می‌کند",
      "functionCall": "این مدل از فراخوانی توابع (Function Call) پشتیبانی می‌کند",
+      "imageOutput": "این مدل از تولید تصویر پشتیبانی می‌کند",
      "reasoning": "این مدل از تفکر عمیق پشتیبانی می‌کند",
      "search": "این مدل از جستجوی آنلاین پشتیبانی می‌کند",
      "tokens": "این مدل در هر جلسه حداکثر از {{tokens}} توکن پشتیبانی می‌کند",
@@ -85,6 +86,8 @@
  },
  "ModelSwitchPanel": {
    "emptyModel": "هیچ مدلی فعال نیست، لطفاً به تنظیمات بروید و آن را فعال کنید",
+    "emptyProvider": "هیچ ارائه‌دهنده‌ای فعال نیست، لطفاً به تنظیمات بروید و آن را فعال کنید",
+    "goToSettings": "به تنظیمات بروید",
    "provider": "ارائه‌دهنده"
  },
  "OllamaSetupGuide": {
@@ -506,6 +506,9 @@
  "anthropic/claude-3.5-sonnet": {
    "description": "Claude 3.5 Sonnet توانایی‌هایی فراتر از Opus ارائه می‌دهد و سرعتی سریع‌تر از Sonnet دارد، در حالی که قیمت آن با Sonnet یکسان است. Sonnet به‌ویژه در برنامه‌نویسی، علم داده، پردازش بصری و وظایف نمایندگی مهارت دارد."
  },
+  "anthropic/claude-3.7-sonnet": {
+    "description": "Claude 3.7 Sonnet هو هوش مصنوعی پیشرفته‌ترین مدل Anthropic است و همچنین اولین مدل استدلال ترکیبی در بازار به شمار می‌رود. Claude 3.7 Sonnet می‌تواند پاسخ‌های تقریباً آنی یا تفکر تدریجی و طولانی‌تری تولید کند که کاربران می‌توانند این فرآیندها را به وضوح مشاهده کنند. Sonnet به‌ویژه در برنامه‌نویسی، علم داده، پردازش بصری و وظایف نمایندگی مهارت دارد."
+  },
  "aya": {
    "description": "Aya 23 یک مدل چندزبانه است که توسط Cohere ارائه شده و از 23 زبان پشتیبانی می‌کند و برای برنامه‌های چندزبانه تسهیلات فراهم می‌آورد."
  },
@@ -830,6 +833,12 @@
  "gemini-2.0-flash-001": {
    "description": "Gemini 2.0 Flash ویژگی‌ها و بهبودهای نسل بعدی را ارائه می‌دهد، از جمله سرعت عالی، استفاده از ابزارهای بومی، تولید چندرسانه‌ای و پنجره متن 1M توکن."
  },
+  "gemini-2.0-flash-exp": {
+    "description": "مدل متغیر Gemini 2.0 Flash که برای بهینه‌سازی هزینه و تأخیر کم طراحی شده است."
+  },
+  "gemini-2.0-flash-exp-image-generation": {
+    "description": "مدل آزمایشی Gemini 2.0 Flash، از تولید تصویر پشتیبانی می‌کند"
+  },
  "gemini-2.0-flash-lite": {
    "description": "مدل متغیر Gemini 2.0 Flash برای بهینه‌سازی هزینه و تأخیر کم طراحی شده است."
  },
@@ -289,7 +289,7 @@
      "title": "زبان تشخیص گفتار"
    },
    "sttService": {
-      "desc": "در این میان، broswer به سرویس تشخیص گفتار بومی مرورگر اشاره دارد",
+      "desc": "در این میان، browser به سرویس تشخیص گفتار بومی مرورگر اشاره دارد",
      "title": "سرویس تشخیص گفتار"
    },
    "title": "سرویس‌های گفتاری",
@@ -32,6 +32,7 @@
    "title": "لیست موضوعات"
  },
  "searchPlaceholder": "جستجوی موضوع...",
+  "searchResultEmpty": "نتیجه‌ای برای جستجو یافت نشد",
  "temp": "موقت",
  "title": "موضوع"
 }
@@ -64,6 +64,9 @@
    "stop": "Arrêter",
    "warp": "Saut de ligne"
  },
+  "intentUnderstanding": {
+    "title": "En train de comprendre et d'analyser votre intention..."
+  },
  "knowledgeBase": {
    "all": "Tout le contenu",
    "allFiles": "Tous les fichiers",
@@ -144,7 +147,6 @@
        "desc": "Détermine intelligemment si une recherche est nécessaire en fonction du contenu de la conversation",
        "title": "Connexion intelligente"
      },
-      "disable": "Le modèle actuel ne prend pas en charge l'appel de fonctions, donc la fonctionnalité de connexion intelligente est indisponible",
      "off": {
        "desc": "Utilise uniquement les connaissances de base du modèle, sans recherche en ligne",
        "title": "Déconnexion"
@@ -155,6 +157,10 @@
      },
      "useModelBuiltin": "Utiliser le moteur de recherche intégré du modèle"
    },
+    "searchModel": {
+      "desc": "Le modèle actuel ne prend pas en charge les appels de fonction, il doit donc être associé à un modèle prenant en charge les appels de fonction pour effectuer une recherche en ligne",
+      "title": "Modèle d'assistance à la recherche"
+    },
    "title": "Recherche en ligne"
  },
  "searchAgentPlaceholder": "Assistant de recherche...",
@@ -76,6 +76,7 @@
      "custom": "Modèle personnalisé par défaut prenant en charge à la fois les appels de fonction et la reconnaissance visuelle. Veuillez vérifier la disponibilité de ces capacités en fonction de vos besoins réels.",
      "file": "Ce modèle prend en charge la lecture et la reconnaissance de fichiers téléchargés.",
      "functionCall": "Ce modèle prend en charge les appels de fonction.",
+      "imageOutput": "Ce modèle prend en charge la génération d'images",
      "reasoning": "Ce modèle prend en charge une réflexion approfondie",
      "search": "Ce modèle prend en charge la recherche en ligne",
      "tokens": "Ce modèle prend en charge jusqu'à {{tokens}} jetons par session.",
@@ -85,6 +86,8 @@
  },
  "ModelSwitchPanel": {
    "emptyModel": "Aucun modèle activé. Veuillez vous rendre dans les paramètres pour l'activer.",
+    "emptyProvider": "Aucun fournisseur activé, veuillez aller dans les paramètres pour l'activer",
+    "goToSettings": "Aller aux paramètres",
    "provider": "Fournisseur"
  },
  "OllamaSetupGuide": {
@@ -506,6 +506,9 @@
  "anthropic/claude-3.5-sonnet": {
    "description": "Claude 3.5 Sonnet offre des capacités supérieures à celles d'Opus et une vitesse plus rapide que Sonnet, tout en maintenant le même prix que Sonnet. Sonnet excelle particulièrement dans la programmation, la science des données, le traitement visuel et les tâches d'agent."
  },
+  "anthropic/claude-3.7-sonnet": {
+    "description": "Claude 3.7 Sonnet est le modèle le plus intelligent d'Anthropic à ce jour, et le premier modèle de raisonnement hybride sur le marché. Claude 3.7 Sonnet peut produire des réponses quasi instantanées ou un raisonnement prolongé, permettant aux utilisateurs de voir clairement ces processus. Sonnet excelle particulièrement dans la programmation, la science des données, le traitement visuel et les tâches d'agent."
+  },
  "aya": {
    "description": "Aya 23 est un modèle multilingue lancé par Cohere, prenant en charge 23 langues, facilitant les applications linguistiques diversifiées."
  },
@@ -830,6 +833,12 @@
  "gemini-2.0-flash-001": {
    "description": "Gemini 2.0 Flash propose des fonctionnalités et des améliorations de nouvelle génération, y compris une vitesse exceptionnelle, l'utilisation d'outils natifs, la génération multimodale et une fenêtre de contexte de 1M tokens."
  },
+  "gemini-2.0-flash-exp": {
+    "description": "Modèle variant Gemini 2.0 Flash, optimisé pour des objectifs tels que le rapport coût-efficacité et la faible latence."
+  },
+  "gemini-2.0-flash-exp-image-generation": {
+    "description": "Modèle expérimental Gemini 2.0 Flash, prenant en charge la génération d'images"
+  },
  "gemini-2.0-flash-lite": {
    "description": "Une variante du modèle Gemini 2.0 Flash, optimisée pour des objectifs tels que le rapport coût-efficacité et la faible latence."
  },
@@ -32,6 +32,7 @@
    "title": "Liste des sujets"
  },
  "searchPlaceholder": "Rechercher des sujets...",
+  "searchResultEmpty": "Aucun résultat de recherche disponible",
  "temp": "Temporaire",
  "title": "Sujet"
 }
@@ -64,6 +64,9 @@
    "stop": "Ferma",
    "warp": "A capo"
  },
+  "intentUnderstanding": {
+    "title": "Stiamo comprendendo e analizzando la tua intenzione..."
+  },
  "knowledgeBase": {
    "all": "Tutti i contenuti",
    "allFiles": "Tutti i file",
@@ -144,7 +147,6 @@
        "desc": "Determina intelligentemente se è necessario cercare in base al contenuto della conversazione",
        "title": "Collegamento intelligente"
      },
-      "disable": "Il modello attuale non supporta le chiamate di funzione, quindi non è possibile utilizzare la funzionalità di collegamento intelligente",
      "off": {
        "desc": "Utilizza solo la conoscenza di base del modello, senza effettuare ricerche online",
        "title": "Disattiva collegamento"
@@ -155,6 +157,10 @@
      },
      "useModelBuiltin": "Utilizza il motore di ricerca integrato del modello"
    },
+    "searchModel": {
+      "desc": "Il modello attuale non supporta le chiamate di funzione, quindi è necessario utilizzarlo insieme a un modello che supporti le chiamate di funzione per cercare online",
+      "title": "Modello di ricerca assistita"
+    },
    "title": "Ricerca online"
  },
  "searchAgentPlaceholder": "Assistente di ricerca...",
@@ -76,6 +76,7 @@
      "custom": "Modello personalizzato: di default supporta sia la chiamata di funzioni che il riconoscimento visivo. Verifica l'effettiva disponibilità di tali funzionalità.",
      "file": "Questo modello supporta il caricamento e il riconoscimento di file.",
      "functionCall": "Questo modello supporta la chiamata di funzioni.",
+      "imageOutput": "Questo modello supporta la generazione di immagini",
      "reasoning": "Questo modello supporta un pensiero profondo",
      "search": "Questo modello supporta la ricerca online",
      "tokens": "Questo modello supporta un massimo di {{tokens}} token per sessione.",
@@ -85,6 +86,8 @@
  },
  "ModelSwitchPanel": {
    "emptyModel": "Nessun modello attivo. Vai alle impostazioni per attivarne uno.",
+    "emptyProvider": "Nessun fornitore attivo, vai alle impostazioni per attivarlo",
+    "goToSettings": "Vai alle impostazioni",
    "provider": "Provider"
  },
  "OllamaSetupGuide": {
@@ -506,6 +506,9 @@
  "anthropic/claude-3.5-sonnet": {
    "description": "Claude 3.5 Sonnet offre capacità superiori rispetto a Opus e una velocità maggiore rispetto a Sonnet, mantenendo lo stesso prezzo di Sonnet. Sonnet è particolarmente abile in programmazione, scienza dei dati, elaborazione visiva e compiti di agenzia."
  },
+  "anthropic/claude-3.7-sonnet": {
+    "description": "Claude 3.7 Sonnet è il modello più intelligente di Anthropic fino ad oggi ed è il primo modello di ragionamento ibrido sul mercato. Claude 3.7 Sonnet può generare risposte quasi istantanee o pensieri prolungati e graduali, consentendo agli utenti di vedere chiaramente questi processi. Sonnet è particolarmente abile nella programmazione, nella scienza dei dati, nell'elaborazione visiva e nei compiti di agenzia."
+  },
  "aya": {
    "description": "Aya 23 è un modello multilingue lanciato da Cohere, supporta 23 lingue, facilitando applicazioni linguistiche diversificate."
  },
@@ -830,6 +833,12 @@
  "gemini-2.0-flash-001": {
    "description": "Gemini 2.0 Flash offre funzionalità e miglioramenti di nuova generazione, tra cui velocità eccezionale, utilizzo di strumenti nativi, generazione multimodale e una finestra di contesto di 1M token."
  },
+  "gemini-2.0-flash-exp": {
+    "description": "Gemini 2.0 Flash è una variante del modello ottimizzata per obiettivi come il rapporto costo-efficacia e la bassa latenza."
+  },
+  "gemini-2.0-flash-exp-image-generation": {
+    "description": "Modello sperimentale Gemini 2.0 Flash, supporta la generazione di immagini"
+  },
  "gemini-2.0-flash-lite": {
    "description": "Gemini 2.0 Flash è una variante del modello Flash, ottimizzata per obiettivi come il rapporto costo-efficacia e la bassa latenza."
  },
@@ -32,6 +32,7 @@
    "title": "Elenco dei temi"
  },
  "searchPlaceholder": "Cerca temi...",
+  "searchResultEmpty": "Nessun risultato trovato",
  "temp": "Temporaneo",
  "title": "Tema"
 }
@@ -64,6 +64,9 @@
    "stop": "停止",
    "warp": "改行"
  },
+  "intentUnderstanding": {
+    "title": "あなたの意図を理解し、分析しています..."
+  },
  "knowledgeBase": {
    "all": "すべてのコンテンツ",
    "allFiles": "すべてのファイル",
@@ -144,7 +147,6 @@
        "desc": "会話の内容に基づいて、検索が必要かどうかを自動的に判断します",
        "title": "インテリジェント接続"
      },
-      "disable": "現在のモデルは関数呼び出しをサポートしていないため、インテリジェント接続機能は使用できません",
      "off": {
        "desc": "モデルの基本知識のみを使用し、ネット検索は行いません",
        "title": "接続をオフ"
@@ -155,6 +157,10 @@
      },
      "useModelBuiltin": "モデル内蔵の検索エンジンを使用"
    },
+    "searchModel": {
+      "desc": "現在のモデルは関数呼び出しをサポートしていないため、関数呼び出しをサポートするモデルと組み合わせてネット検索を行う必要があります",
+      "title": "検索補助モデル"
+    },
    "title": "ネット接続検索"
  },
  "searchAgentPlaceholder": "検索アシスタント...",
@@ -76,6 +76,7 @@
      "custom": "カスタムモデル、デフォルトでは関数呼び出しとビジョン認識の両方をサポートしています。上記機能の有効性を確認してください。",
      "file": "このモデルはファイルのアップロードと認識をサポートしています。",
      "functionCall": "このモデルは関数呼び出し（Function Call）をサポートしています。",
+      "imageOutput": "このモデルは画像生成をサポートしています",
      "reasoning": "このモデルは深い思考をサポートしています",
      "search": "このモデルはオンライン検索をサポートしています",
      "tokens": "このモデルは1つのセッションあたり最大{{tokens}}トークンをサポートしています。",
@@ -85,6 +86,8 @@
  },
  "ModelSwitchPanel": {
    "emptyModel": "有効なモデルがありません。設定に移動して有効にしてください。",
+    "emptyProvider": "有効なサービスプロバイダーがありません。設定に移動して有効にしてください。",
+    "goToSettings": "設定に移動",
    "provider": "プロバイダー"
  },
  "OllamaSetupGuide": {
@@ -506,6 +506,9 @@
  "anthropic/claude-3.5-sonnet": {
    "description": "Claude 3.5 SonnetはOpusを超える能力を提供し、Sonnetよりも速い速度を持ちながら、Sonnetと同じ価格を維持します。Sonnetは特にプログラミング、データサイエンス、視覚処理、代理タスクに優れています。"
  },
+  "anthropic/claude-3.7-sonnet": {
+    "description": "Claude 3.7 Sonnetは、Anthropicがこれまでに開発した最も知能の高いモデルであり、市場で初めての混合推論モデルです。Claude 3.7 Sonnetは、ほぼ瞬時の応答や段階的な思考を生成することができ、ユーザーはこれらのプロセスを明確に見ることができます。Sonnetは特にプログラミング、データサイエンス、視覚処理、代理タスクに優れています。"
+  },
  "aya": {
    "description": "Aya 23は、Cohereが提供する多言語モデルであり、23の言語をサポートし、多様な言語アプリケーションを便利にします。"
  },
@@ -830,6 +833,12 @@
  "gemini-2.0-flash-001": {
    "description": "Gemini 2.0 Flashは、卓越した速度、ネイティブツールの使用、マルチモーダル生成、1Mトークンのコンテキストウィンドウを含む次世代の機能と改善を提供します。"
  },
+  "gemini-2.0-flash-exp": {
+    "description": "Gemini 2.0 Flash モデルのバリアントで、コスト効率と低遅延などの目標に最適化されています。"
+  },
+  "gemini-2.0-flash-exp-image-generation": {
+    "description": "Gemini 2.0 Flash 実験モデル、画像生成をサポート"
+  },
  "gemini-2.0-flash-lite": {
    "description": "Gemini 2.0 Flashモデルのバリアントで、コスト効率と低遅延などの目標に最適化されています。"
  },
@@ -32,6 +32,7 @@
    "title": "トピックリスト"
  },
  "searchPlaceholder": "トピックを検索...",
+  "searchResultEmpty": "検索結果はありません",
  "temp": "一時的",
  "title": "トピック"
 }
@@ -64,6 +64,9 @@
    "stop": "중지",
    "warp": "줄바꿈"
  },
+  "intentUnderstanding": {
+    "title": "귀하의 의도를 이해하고 분석하는 중입니다..."
+  },
  "knowledgeBase": {
    "all": "모든 내용",
    "allFiles": "모든 파일",
@@ -144,7 +147,6 @@
        "desc": "대화 내용을 기반으로 검색 필요성을 스마트하게 판단",
        "title": "스마트 연결"
      },
-      "disable": "현재 모델은 함수 호출을 지원하지 않으므로 스마트 연결 기능을 사용할 수 없습니다",
      "off": {
        "desc": "모델의 기본 지식만 사용하고 네트워크 검색을 수행하지 않음",
        "title": "연결 끄기"
@@ -155,6 +157,10 @@
      },
      "useModelBuiltin": "모델 내장 검색 엔진 사용"
    },
+    "searchModel": {
+      "desc": "현재 모델은 함수 호출을 지원하지 않으므로 함수 호출을 지원하는 모델과 함께 사용해야 인터넷 검색이 가능합니다.",
+      "title": "검색 보조 모델"
+    },
    "title": "연결 검색"
  },
  "searchAgentPlaceholder": "검색 도우미...",
@@ -76,6 +76,7 @@
      "custom": "사용자 정의 모델, 기본적으로 함수 호출 및 시각 인식을 모두 지원하며, 실제 기능을 확인하세요",
      "file": "이 모델은 파일 업로드 및 인식을 지원합니다",
      "functionCall": "이 모델은 함수 호출을 지원합니다",
+      "imageOutput": "이 모델은 이미지를 생성하는 기능을 지원합니다.",
      "reasoning": "이 모델은 깊이 있는 사고를 지원합니다.",
      "search": "이 모델은 온라인 검색을 지원합니다.",
      "tokens": "이 모델은 단일 세션당 최대 {{tokens}} 토큰을 지원합니다",
@@ -85,6 +86,8 @@
  },
  "ModelSwitchPanel": {
    "emptyModel": "활성화된 모델이 없습니다. 설정으로 이동하여 활성화하세요",
+    "emptyProvider": "활성화된 서비스 제공자가 없습니다. 설정으로 가서 활성화하세요.",
+    "goToSettings": "설정으로 가기",
    "provider": "제공자"
  },
  "OllamaSetupGuide": {
@@ -506,6 +506,9 @@
  "anthropic/claude-3.5-sonnet": {
    "description": "Claude 3.5 Sonnet은 Opus를 초월하는 능력과 Sonnet보다 더 빠른 속도를 제공하며, Sonnet과 동일한 가격을 유지합니다. Sonnet은 프로그래밍, 데이터 과학, 비주얼 처리 및 에이전트 작업에 특히 강합니다."
  },
+  "anthropic/claude-3.7-sonnet": {
+    "description": "Claude 3.7 Sonnet은 Anthropic이 지금까지 개발한 가장 지능적인 모델로, 시장에서 최초의 혼합 추론 모델입니다. Claude 3.7 Sonnet은 거의 즉각적인 응답이나 연장된 단계적 사고를 생성할 수 있으며, 사용자는 이러한 과정을 명확하게 볼 수 있습니다. Sonnet은 프로그래밍, 데이터 과학, 시각 처리, 대리 작업에 특히 뛰어납니다."
+  },
  "aya": {
    "description": "Aya 23은 Cohere에서 출시한 다국어 모델로, 23개 언어를 지원하여 다양한 언어 응용에 편리함을 제공합니다."
  },
@@ -830,6 +833,12 @@
  "gemini-2.0-flash-001": {
    "description": "Gemini 2.0 Flash는 뛰어난 속도, 원주율 도구 사용, 다중 모달 생성 및 1M 토큰 문맥 창을 포함한 차세대 기능과 개선 사항을 제공합니다."
  },
+  "gemini-2.0-flash-exp": {
+    "description": "Gemini 2.0 Flash 모델 변형으로, 비용 효율성과 저지연 등의 목표를 위해 최적화되었습니다."
+  },
+  "gemini-2.0-flash-exp-image-generation": {
+    "description": "Gemini 2.0 Flash 실험 모델, 이미지 생성을 지원합니다."
+  },
  "gemini-2.0-flash-lite": {
    "description": "Gemini 2.0 플래시 모델 변형으로, 비용 효율성과 낮은 지연 시간 등의 목표를 위해 최적화되었습니다."
  },
@@ -32,6 +32,7 @@
    "title": "주제 목록"
  },
  "searchPlaceholder": "주제 검색...",
+  "searchResultEmpty": "검색 결과가 없습니다.",
  "temp": "임시",
  "title": "주제"
 }
@@ -64,6 +64,9 @@
    "stop": "Stoppen",
    "warp": "Nieuwe regel"
  },
+  "intentUnderstanding": {
+    "title": "Bezig met het begrijpen en analyseren van uw intentie..."
+  },
  "knowledgeBase": {
    "all": "Alle inhoud",
    "allFiles": "Alle bestanden",
@@ -144,7 +147,6 @@
        "desc": "Intelligente beoordeling of er gezocht moet worden op basis van de gesprekinhoud",
        "title": "Slimme verbinding"
      },
-      "disable": "Het huidige model ondersteunt geen functieaanroepen, dus de slimme verbindingsfunctie kan niet worden gebruikt",
      "off": {
        "desc": "Gebruik alleen de basiskennis van het model, zonder online zoekopdrachten",
        "title": "Verbinding uitschakelen"
@@ -155,6 +157,10 @@
      },
      "useModelBuiltin": "Gebruik de ingebouwde zoekmachine van het model"
    },
+    "searchModel": {
+      "desc": "Het huidige model ondersteunt geen functieaanroepen, dus het moet worden gecombineerd met een model dat functieaanroepen ondersteunt om online te zoeken",
+      "title": "Zoekhulpmiddel model"
+    },
    "title": "Online zoeken"
  },
  "searchAgentPlaceholder": "Zoekassistent...",
@@ -76,6 +76,7 @@
      "custom": "Custom model, by default, supports both function call and visual recognition. Please verify the availability of the above capabilities based on actual needs.",
      "file": "This model supports file upload for reading and recognition.",
      "functionCall": "This model supports function call.",
+      "imageOutput": "Dit model ondersteunt het genereren van afbeeldingen",
      "reasoning": "Dit model ondersteunt diepgaand denken",
      "search": "Dit model ondersteunt online zoeken",
      "tokens": "This model supports up to {{tokens}} tokens in a single session.",
@@ -85,6 +86,8 @@
  },
  "ModelSwitchPanel": {
    "emptyModel": "No enabled model, please go to settings to enable.",
+    "emptyProvider": "Geen ingeschakelde provider, ga naar instellingen om deze in te schakelen",
+    "goToSettings": "Ga naar instellingen",
    "provider": "Provider"
  },
  "OllamaSetupGuide": {
@@ -506,6 +506,9 @@
  "anthropic/claude-3.5-sonnet": {
    "description": "Claude 3.5 Sonnet biedt mogelijkheden die verder gaan dan Opus en een snellere snelheid dan Sonnet, terwijl het dezelfde prijs als Sonnet behoudt. Sonnet is bijzonder goed in programmeren, datawetenschap, visuele verwerking en agenttaken."
  },
+  "anthropic/claude-3.7-sonnet": {
+    "description": "Claude 3.7 Sonnet is het meest geavanceerde model van Anthropic tot nu toe en het eerste hybride redeneermodel op de markt. Claude 3.7 Sonnet kan bijna onmiddellijke reacties of uitgebreide stapsgewijze overpeinzingen genereren, waarbij gebruikers deze processen duidelijk kunnen volgen. Sonnet is bijzonder goed in programmeren, datawetenschap, visuele verwerking en agenttaken."
+  },
  "aya": {
    "description": "Aya 23 is een meertalig model van Cohere, ondersteunt 23 talen en biedt gemak voor diverse taaltoepassingen."
  },
@@ -830,6 +833,12 @@
  "gemini-2.0-flash-001": {
    "description": "Gemini 2.0 Flash biedt next-gen functies en verbeteringen, waaronder uitstekende snelheid, native toolgebruik, multimodale generatie en een contextvenster van 1M tokens."
  },
+  "gemini-2.0-flash-exp": {
+    "description": "Gemini 2.0 Flash modelvariant, geoptimaliseerd voor kosteneffectiviteit en lage latentie."
+  },
+  "gemini-2.0-flash-exp-image-generation": {
+    "description": "Gemini 2.0 Flash experimenteel model, ondersteunt afbeeldingsgeneratie"
+  },
  "gemini-2.0-flash-lite": {
    "description": "Gemini 2.0 Flash is een modelvariant die is geoptimaliseerd voor kosteneffectiviteit en lage latentie."
  },
@@ -32,6 +32,7 @@
    "title": "Onderwerpenlijst"
  },
  "searchPlaceholder": "Zoek onderwerpen...",
+  "searchResultEmpty": "Geen zoekresultaten gevonden",
  "temp": "Tijdelijk",
  "title": "Onderwerp"
 }
@@ -64,6 +64,9 @@
    "stop": "Zatrzymaj",
    "warp": "Złamanie wiersza"
  },
+  "intentUnderstanding": {
+    "title": "Rozumiemy i analizujemy Twoje intencje..."
+  },
  "knowledgeBase": {
    "all": "Wszystkie treści",
    "allFiles": "Wszystkie pliki",
@@ -144,7 +147,6 @@
        "desc": "Inteligentne określenie, czy potrzebne jest wyszukiwanie na podstawie treści rozmowy",
        "title": "Inteligentne połączenie"
      },
-      "disable": "Aktualny model nie obsługuje wywołań funkcji, więc nie można korzystać z inteligentnego połączenia",
      "off": {
        "desc": "Używaj tylko podstawowej wiedzy modelu, bez wyszukiwania w sieci",
        "title": "Wyłącz połączenie"
@@ -155,6 +157,10 @@
      },
      "useModelBuiltin": "Użyj wbudowanej wyszukiwarki modelu"
    },
+    "searchModel": {
+      "desc": "Aktualny model nie obsługuje wywołań funkcji, dlatego wymaga współpracy z modelem obsługującym wywołania funkcji, aby móc przeszukiwać sieć",
+      "title": "Model wspomagający wyszukiwanie"
+    },
    "title": "Wyszukiwanie w sieci"
  },
  "searchAgentPlaceholder": "Wyszukaj pomocnika...",
@@ -76,6 +76,7 @@
      "custom": "Niestandardowy model, domyślnie obsługujący zarówno wywołania funkcji, jak i rozpoznawanie wizualne. Proszę zweryfikować możliwość użycia tych funkcji w praktyce.",
      "file": "Ten model obsługuje wczytywanie plików i rozpoznawanie",
      "functionCall": "Ten model obsługuje wywołania funkcji (Function Call).",
+      "imageOutput": "Ten model wspiera generowanie obrazów",
      "reasoning": "Ten model wspiera głębokie myślenie",
      "search": "Ten model wspiera wyszukiwanie w sieci",
      "tokens": "Ten model obsługuje maksymalnie {{tokens}} tokenów w pojedynczej sesji.",
@@ -85,6 +86,8 @@
  },
  "ModelSwitchPanel": {
    "emptyModel": "Brak włączonych modeli, przejdź do ustawień i włącz je",
+    "emptyProvider": "Nie ma aktywnego dostawcy usług, przejdź do ustawień, aby go włączyć",
+    "goToSettings": "Przejdź do ustawień",
    "provider": "Dostawca"
  },
  "OllamaSetupGuide": {
@@ -506,6 +506,9 @@
  "anthropic/claude-3.5-sonnet": {
    "description": "Claude 3.5 Sonnet oferuje możliwości przewyższające Opus oraz szybsze tempo niż Sonnet, zachowując tę samą cenę. Sonnet szczególnie dobrze radzi sobie z programowaniem, nauką o danych, przetwarzaniem wizualnym i zadaniami agenta."
  },
+  "anthropic/claude-3.7-sonnet": {
+    "description": "Claude 3.7 Sonnet to najinteligentniejszy model stworzony przez Anthropic, a także pierwszy na rynku model mieszanej dedukcji. Claude 3.7 Sonnet potrafi generować niemal natychmiastowe odpowiedzi lub wydłużone, krok po kroku myślenie, które użytkownicy mogą wyraźnie obserwować. Sonnet szczególnie dobrze radzi sobie z programowaniem, nauką o danych, przetwarzaniem wizualnym oraz zadaniami agenta."
+  },
  "aya": {
    "description": "Aya 23 to model wielojęzyczny wydany przez Cohere, wspierający 23 języki, ułatwiający różnorodne zastosowania językowe."
  },
@@ -830,6 +833,12 @@
  "gemini-2.0-flash-001": {
    "description": "Gemini 2.0 Flash oferuje funkcje i ulepszenia nowej generacji, w tym doskonałą prędkość, natywne korzystanie z narzędzi, generowanie multimodalne oraz okno kontekstowe o długości 1M tokenów."
  },
+  "gemini-2.0-flash-exp": {
+    "description": "Gemini 2.0 Flash to wariant modelu, zoptymalizowany pod kątem efektywności kosztowej i niskiego opóźnienia."
+  },
+  "gemini-2.0-flash-exp-image-generation": {
+    "description": "Model eksperymentalny Gemini 2.0 Flash, wspierający generowanie obrazów"
+  },
  "gemini-2.0-flash-lite": {
    "description": "Gemini 2.0 Flash to wariant modelu, zoptymalizowany pod kątem efektywności kosztowej i niskiego opóźnienia."
  },
@@ -32,6 +32,7 @@
    "title": "Lista tematów"
  },
  "searchPlaceholder": "Szukaj tematów...",
+  "searchResultEmpty": "Brak wyników wyszukiwania",
  "temp": "Tymczasowy",
  "title": "Temat"
 }
@@ -64,6 +64,9 @@
    "stop": "Parar",
    "warp": "Quebrar linha"
  },
+  "intentUnderstanding": {
+    "title": "Entendendo e analisando sua intenção..."
+  },
  "knowledgeBase": {
    "all": "Todo conteúdo",
    "allFiles": "Todos os arquivos",
@@ -144,7 +147,6 @@
        "desc": "Determina inteligentemente se é necessário pesquisar com base no conteúdo da conversa",
        "title": "Conexão Inteligente"
      },
-      "disable": "O modelo atual não suporta chamadas de função, portanto, a funcionalidade de conexão inteligente não está disponível",
      "off": {
        "desc": "Usa apenas o conhecimento básico do modelo, sem realizar pesquisas na web",
        "title": "Desativar Conexão"
@@ -155,6 +157,10 @@
      },
      "useModelBuiltin": "Usar o mecanismo de busca embutido no modelo"
    },
+    "searchModel": {
+      "desc": "O modelo atual não suporta chamadas de função, portanto, é necessário combiná-lo com um modelo que suporte chamadas de função para realizar buscas na internet",
+      "title": "Modelo de busca auxiliar"
+    },
    "title": "Pesquisa Conectada"
  },
  "searchAgentPlaceholder": "Assistente de busca...",
@@ -76,6 +76,7 @@
      "custom": "Modelo personalizado, por padrão, suporta chamadas de função e reconhecimento visual. Por favor, verifique a disponibilidade dessas capacidades de acordo com a situação real.",
      "file": "Este modelo suporta leitura e reconhecimento de arquivos enviados.",
      "functionCall": "Este modelo suporta chamadas de função.",
+      "imageOutput": "Este modelo suporta a geração de imagens",
      "reasoning": "Este modelo suporta pensamento profundo",
      "search": "Este modelo suporta pesquisa online",
      "tokens": "Este modelo suporta no máximo {{tokens}} tokens por sessão.",
@@ -85,6 +86,8 @@
  },
  "ModelSwitchPanel": {
    "emptyModel": "Nenhum modelo habilitado. Por favor, vá para as configurações e habilite um.",
+    "emptyProvider": "Nenhum provedor ativado, por favor vá para as configurações para ativar",
+    "goToSettings": "Ir para as configurações",
    "provider": "Fornecedor"
  },
  "OllamaSetupGuide": {
@@ -506,6 +506,9 @@
  "anthropic/claude-3.5-sonnet": {
    "description": "Claude 3.5 Sonnet oferece capacidades que vão além do Opus e uma velocidade superior ao Sonnet, mantendo o mesmo preço do Sonnet. O Sonnet é especialmente habilidoso em programação, ciência de dados, processamento visual e tarefas de agente."
  },
+  "anthropic/claude-3.7-sonnet": {
+    "description": "Claude 3.7 Sonnet é o modelo mais inteligente da Anthropic até agora e é o primeiro modelo de raciocínio misto do mercado. Claude 3.7 Sonnet pode gerar respostas quase instantâneas ou um pensamento gradual prolongado, permitindo que os usuários vejam claramente esses processos. Sonnet é especialmente habilidoso em programação, ciência de dados, processamento visual e tarefas de agente."
+  },
  "aya": {
    "description": "Aya 23 é um modelo multilíngue lançado pela Cohere, suportando 23 idiomas, facilitando aplicações linguísticas diversificadas."
  },
@@ -830,6 +833,12 @@
  "gemini-2.0-flash-001": {
    "description": "Gemini 2.0 Flash oferece funcionalidades e melhorias de próxima geração, incluindo velocidade excepcional, uso nativo de ferramentas, geração multimodal e uma janela de contexto de 1M tokens."
  },
+  "gemini-2.0-flash-exp": {
+    "description": "Variante do modelo Gemini 2.0 Flash, otimizada para custo-benefício e baixa latência."
+  },
+  "gemini-2.0-flash-exp-image-generation": {
+    "description": "Modelo experimental Gemini 2.0 Flash, suporta geração de imagens"
+  },
  "gemini-2.0-flash-lite": {
    "description": "Variante do modelo Gemini 2.0 Flash, otimizada para custo-benefício e baixa latência."
  },
@@ -32,6 +32,7 @@
    "title": "Lista de tópicos"
  },
  "searchPlaceholder": "Pesquisar tópicos...",
+  "searchResultEmpty": "Nenhum resultado encontrado",
  "temp": "Temporário",
  "title": "Tópico"
 }
@@ -64,6 +64,9 @@
    "stop": "Остановить",
    "warp": "Перенос строки"
  },
+  "intentUnderstanding": {
+    "title": "Мы понимаем и анализируем ваше намерение..."
+  },
  "knowledgeBase": {
    "all": "Все содержимое",
    "allFiles": "Все файлы",
@@ -144,7 +147,6 @@
        "desc": "Интеллектуально определяет необходимость поиска на основе содержания диалога",
        "title": "Интеллектуальное подключение к сети"
      },
-      "disable": "Текущая модель не поддерживает вызовы функций, поэтому функция интеллектуального подключения к сети недоступна",
      "off": {
        "desc": "Использует только базовые знания модели, без сетевого поиска",
        "title": "Отключить подключение к сети"
@@ -155,6 +157,10 @@
      },
      "useModelBuiltin": "Использовать встроенный поисковый движок модели"
    },
+    "searchModel": {
+      "desc": "Текущая модель не поддерживает вызов функций, поэтому необходимо использовать модель, поддерживающую вызов функций, для поиска в интернете",
+      "title": "Модель поиска"
+    },
    "title": "Поиск в сети"
  },
  "searchAgentPlaceholder": "Поиск помощника...",
@@ -76,6 +76,7 @@
      "custom": "Пользовательская модель по умолчанию поддерживает как вызов функций, так и распознавание изображений. Пожалуйста, проверьте доступность указанных возможностей в вашем случае",
      "file": "Эта модель поддерживает загрузку и распознавание файлов",
      "functionCall": "Эта модель поддерживает вызов функций",
+      "imageOutput": "Эта модель поддерживает генерацию изображений",
      "reasoning": "Эта модель поддерживает глубокое мышление",
      "search": "Эта модель поддерживает поиск в интернете",
      "tokens": "Эта модель поддерживает до {{tokens}} токенов в одной сессии",
@@ -85,6 +86,8 @@
  },
  "ModelSwitchPanel": {
    "emptyModel": "Нет активированных моделей. Пожалуйста, перейдите в настройки и включите модель",
+    "emptyProvider": "Нет активных провайдеров, пожалуйста, перейдите в настройки для их включения",
+    "goToSettings": "Перейти в настройки",
    "provider": "Поставщик"
  },
  "OllamaSetupGuide": {
@@ -506,6 +506,9 @@
  "anthropic/claude-3.5-sonnet": {
    "description": "Claude 3.5 Sonnet предлагает возможности, превосходящие Opus, и скорость, превышающую Sonnet, при этом сохраняя ту же цену. Sonnet особенно хорошо справляется с программированием, наукой о данных, визуальной обработкой и агентскими задачами."
  },
+  "anthropic/claude-3.7-sonnet": {
+    "description": "Claude 3.7 Sonnet — это самая умная модель от Anthropic на сегодняшний день и первая в мире смешанная модель вывода. Claude 3.7 Sonnet может генерировать почти мгновенные ответы или длительные пошаговые размышления, позволяя пользователям четко видеть эти процессы. Sonnet особенно хорошо справляется с программированием, научными данными, визуальной обработкой и агентскими задачами."
+  },
  "aya": {
    "description": "Aya 23 — это многоязычная модель, выпущенная Cohere, поддерживающая 23 языка, обеспечивая удобство для многоязычных приложений."
  },
@@ -830,6 +833,12 @@
  "gemini-2.0-flash-001": {
    "description": "Gemini 2.0 Flash предлагает функции следующего поколения и улучшения, включая выдающуюся скорость, использование встроенных инструментов, многомодальную генерацию и контекстное окно на 1M токенов."
  },
+  "gemini-2.0-flash-exp": {
+    "description": "Модельный вариант Gemini 2.0 Flash, оптимизированный для достижения таких целей, как экономическая эффективность и низкая задержка."
+  },
+  "gemini-2.0-flash-exp-image-generation": {
+    "description": "Экспериментальная модель Gemini 2.0 Flash, поддерживающая генерацию изображений"
+  },
  "gemini-2.0-flash-lite": {
    "description": "Модельный вариант Gemini 2.0 Flash, оптимизированный для достижения таких целей, как экономическая эффективность и низкая задержка."
  },
@@ -32,6 +32,7 @@
    "title": "Список тем"
  },
  "searchPlaceholder": "Поиск тем...",
+  "searchResultEmpty": "Нет результатов поиска",
  "temp": "Временный",
  "title": "Тема"
 }
@@ -64,6 +64,9 @@
    "stop": "Dur",
    "warp": "Satır atla"
  },
+  "intentUnderstanding": {
+    "title": "Niyetinizi anlama ve analiz etme aşamasındayız..."
+  },
  "knowledgeBase": {
    "all": "Tüm İçerik",
    "allFiles": "Tüm Dosyalar",
@@ -144,7 +147,6 @@
        "desc": "Sohbet içeriğine göre akıllıca arama gerekip gerekmediğini belirler",
        "title": "Akıllı Bağlantı"
      },
-      "disable": "Mevcut model fonksiyon çağrısını desteklemediği için akıllı bağlantı özelliği kullanılamaz",
      "off": {
        "desc": "Sadece modelin temel bilgilerini kullanır, ağ araması yapmaz",
        "title": "Bağlantıyı Kapat"
@@ -155,6 +157,10 @@
      },
      "useModelBuiltin": "Modelin yerleşik arama motorunu kullan"
    },
+    "searchModel": {
+      "desc": "Mevcut model fonksiyon çağrısını desteklemiyor, bu nedenle çevrimiçi arama yapmak için fonksiyon çağrısını destekleyen bir model ile birlikte kullanılması gerekiyor",
+      "title": "Arama Yardımcı Modeli"
+    },
    "title": "Ağ Araması"
  },
  "searchAgentPlaceholder": "Arama Asistanı...",
@@ -76,6 +76,7 @@
      "custom": "Özel model, varsayılan olarak hem fonksiyon çağrısını hem de görüntü tanımayı destekler, yukarıdaki yeteneklerin kullanılabilirliğini doğrulamak için lütfen gerçek durumu kontrol edin",
      "file": "Bu model dosya yükleme ve tanımayı destekler",
      "functionCall": "Bu model fonksiyon çağrısını destekler",
+      "imageOutput": "Bu model resim oluşturmayı destekler",
      "reasoning": "Bu model derin düşünmeyi destekler",
      "search": "Bu model çevrimiçi aramayı destekler",
      "tokens": "Bu model tek bir oturumda en fazla {{tokens}} Token destekler",
@@ -85,6 +86,8 @@
  },
  "ModelSwitchPanel": {
    "emptyModel": "Etkinleştirilmiş model bulunmamaktadır, lütfen ayarlara giderek açın",
+    "emptyProvider": "Etkinleştirilmiş bir sağlayıcı yok, lütfen ayarlara gidin",
+    "goToSettings": "Ayrıntılara git",
    "provider": "Sağlayıcı"
  },
  "OllamaSetupGuide": {
@@ -506,6 +506,9 @@
  "anthropic/claude-3.5-sonnet": {
    "description": "Claude 3.5 Sonnet, Opus'tan daha fazla yetenek ve Sonnet'ten daha hızlı bir hız sunar; aynı zamanda Sonnet ile aynı fiyatı korur. Sonnet, programlama, veri bilimi, görsel işleme ve ajan görevlerinde özellikle başarılıdır."
  },
+  "anthropic/claude-3.7-sonnet": {
+    "description": "Claude 3.7 Sonnet, Anthropic'in şimdiye kadarki en akıllı modeli ve piyasadaki ilk karma akıl yürütme modelidir. Claude 3.7 Sonnet, neredeyse anlık yanıtlar veya uzatılmış adım adım düşünme süreçleri üretebilir; kullanıcılar bu süreçleri net bir şekilde görebilir. Sonnet, programlama, veri bilimi, görsel işleme ve temsilci görevlerde özellikle yeteneklidir."
+  },
  "aya": {
    "description": "Aya 23, Cohere tarafından sunulan çok dilli bir modeldir, 23 dili destekler ve çok dilli uygulamalar için kolaylık sağlar."
  },
@@ -830,6 +833,12 @@
  "gemini-2.0-flash-001": {
    "description": "Gemini 2.0 Flash, mükemmel hız, yerel araç kullanımı, çok modlu üretim ve 1M token bağlam penceresi dahil olmak üzere bir sonraki nesil özellikler ve iyileştirmeler sunar."
  },
+  "gemini-2.0-flash-exp": {
+    "description": "Gemini 2.0 Flash modeli varyantı, maliyet etkinliği ve düşük gecikme gibi hedefler için optimize edilmiştir."
+  },
+  "gemini-2.0-flash-exp-image-generation": {
+    "description": "Gemini 2.0 Flash deneysel modeli, görüntü oluşturmayı destekler"
+  },
  "gemini-2.0-flash-lite": {
    "description": "Gemini 2.0 Flash model varyantı, maliyet etkinliği ve düşük gecikme gibi hedefler için optimize edilmiştir."
  },
@@ -32,6 +32,7 @@
    "title": "Konu Listesi"
  },
  "searchPlaceholder": "Konuları Ara...",
+  "searchResultEmpty": "Hiçbir arama sonucu bulunamadı",
  "temp": "Geçici",
  "title": "Konu"
 }
@@ -64,6 +64,9 @@
    "stop": "Dừng",
    "warp": "Xuống dòng"
  },
+  "intentUnderstanding": {
+    "title": "Đang hiểu và phân tích ý định của bạn..."
+  },
  "knowledgeBase": {
    "all": "Tất cả nội dung",
    "allFiles": "Tất cả tệp",
@@ -144,7 +147,6 @@
        "desc": "Thông minh xác định xem có cần tìm kiếm dựa trên nội dung cuộc trò chuyện",
        "title": "Kết nối thông minh"
      },
-      "disable": "Mô hình hiện tại không hỗ trợ gọi hàm, do đó không thể sử dụng chức năng kết nối thông minh",
      "off": {
        "desc": "Chỉ sử dụng kiến thức cơ bản của mô hình, không thực hiện tìm kiếm trên mạng",
        "title": "Tắt kết nối"
@@ -155,6 +157,10 @@
      },
      "useModelBuiltin": "Sử dụng công cụ tìm kiếm tích hợp của mô hình"
    },
+    "searchModel": {
+      "desc": "Mô hình hiện tại không hỗ trợ gọi hàm, vì vậy cần kết hợp với mô hình hỗ trợ gọi hàm để tìm kiếm trực tuyến",
+      "title": "Mô hình hỗ trợ tìm kiếm"
+    },
    "title": "Tìm kiếm trực tuyến"
  },
  "searchAgentPlaceholder": "Trợ lý tìm kiếm...",
@@ -76,6 +76,7 @@
      "custom": "Mô hình tùy chỉnh, mặc định hỗ trợ cả cuộc gọi hàm và nhận diện hình ảnh, vui lòng xác minh khả năng sử dụng của chúng theo tình hình cụ thể",
      "file": "Mô hình này hỗ trợ tải lên và nhận diện tệp",
      "functionCall": "Mô hình này hỗ trợ cuộc gọi hàm (Function Call)",
+      "imageOutput": "Mô hình này hỗ trợ tạo ra hình ảnh",
      "reasoning": "Mô hình này hỗ trợ tư duy sâu sắc",
      "search": "Mô hình này hỗ trợ tìm kiếm trực tuyến",
      "tokens": "Mỗi phiên của mô hình này hỗ trợ tối đa {{tokens}} Tokens",
@@ -85,6 +86,8 @@
  },
  "ModelSwitchPanel": {
    "emptyModel": "Không có mô hình nào được kích hoạt, vui lòng điều chỉnh trong cài đặt",
+    "emptyProvider": "Không có nhà cung cấp nào được kích hoạt, vui lòng vào cài đặt để bật",
+    "goToSettings": "Đi đến cài đặt",
    "provider": "Nhà cung cấp"
  },
  "OllamaSetupGuide": {
@@ -506,6 +506,9 @@
  "anthropic/claude-3.5-sonnet": {
    "description": "Claude 3.5 Sonnet cung cấp khả năng vượt trội hơn Opus và tốc độ nhanh hơn Sonnet, trong khi vẫn giữ giá tương tự. Sonnet đặc biệt xuất sắc trong lập trình, khoa học dữ liệu, xử lý hình ảnh và các nhiệm vụ đại lý."
  },
+  "anthropic/claude-3.7-sonnet": {
+    "description": "Claude 3.7 Sonnet là mô hình thông minh nhất của Anthropic cho đến nay, và cũng là mô hình suy luận hỗn hợp đầu tiên trên thị trường. Claude 3.7 Sonnet có khả năng tạo ra phản hồi gần như ngay lập tức hoặc suy nghĩ từng bước kéo dài, cho phép người dùng thấy rõ những quá trình này. Sonnet đặc biệt xuất sắc trong lập trình, khoa học dữ liệu, xử lý hình ảnh và các nhiệm vụ đại diện."
+  },
  "aya": {
    "description": "Aya 23 là mô hình đa ngôn ngữ do Cohere phát hành, hỗ trợ 23 ngôn ngữ, tạo điều kiện thuận lợi cho các ứng dụng ngôn ngữ đa dạng."
  },
@@ -830,6 +833,12 @@
  "gemini-2.0-flash-001": {
    "description": "Gemini 2.0 Flash cung cấp các tính năng và cải tiến thế hệ tiếp theo, bao gồm tốc độ vượt trội, sử dụng công cụ bản địa, tạo đa phương tiện và cửa sổ ngữ cảnh 1M token."
  },
+  "gemini-2.0-flash-exp": {
+    "description": "Biến thể mô hình Gemini 2.0 Flash, được tối ưu hóa cho hiệu quả chi phí và độ trễ thấp."
+  },
+  "gemini-2.0-flash-exp-image-generation": {
+    "description": "Mô hình thử nghiệm Gemini 2.0 Flash, hỗ trợ tạo hình ảnh"
+  },
  "gemini-2.0-flash-lite": {
    "description": "Biến thể mô hình Gemini 2.0 Flash được tối ưu hóa cho hiệu quả chi phí và độ trễ thấp."
  },
@@ -32,6 +32,7 @@
    "title": "Danh sách chủ đề"
  },
  "searchPlaceholder": "Tìm kiếm chủ đề...",
+  "searchResultEmpty": "Không có kết quả tìm kiếm nào",
  "temp": "Tạm thời",
  "title": "Chủ đề"
 }
@@ -64,6 +64,9 @@
    "stop": "停止",
    "warp": "换行"
  },
+  "intentUnderstanding": {
+    "title": "正在理解并分析您的意图..."
+  },
  "knowledgeBase": {
    "all": "所有内容",
    "allFiles": "所有文件",
@@ -144,7 +147,6 @@
        "desc": "根据对话内容智能判断是否需要搜索",
        "title": "智能联网"
      },
-      "disable": "当前模型不支持函数调用，因此无法使用智能联网功能",
      "off": {
        "desc": "仅使用模型的基础知识，不进行网络搜索",
        "title": "关闭联网"
@@ -155,6 +157,10 @@
      },
      "useModelBuiltin": "使用模型内置搜索引擎"
    },
+    "searchModel": {
+      "desc": "当前模型不支持函数调用，因此需要搭配支持函数调用的模型才能联网搜索",
+      "title": "搜索辅助模型"
+    },
    "title": "联网搜索"
  },
  "searchAgentPlaceholder": "搜索助手...",
@@ -76,6 +76,7 @@
      "custom": "自定义模型，默认设定同时支持函数调用与视觉识别，请根据实际情况验证上述能力的可用性",
      "file": "该模型支持上传文件读取与识别",
      "functionCall": "该模型支持函数调用（Function Call）",
+      "imageOutput": "该模型支持生成图片",
      "reasoning": "该模型支持深度思考",
      "search": "该模型支持联网搜索",
      "tokens": "该模型单个会话最多支持 {{tokens}} Tokens",
@@ -85,7 +86,9 @@
  },
  "ModelSwitchPanel": {
    "emptyModel": "没有启用的模型，请前往设置开启",
-    "provider": "提供商"
+    "emptyProvider": "没有启用的服务商，请前往设置开启",
+    "goToSettings": "前往设置",
+    "provider": "服务商"
  },
  "OllamaSetupGuide": {
    "cors": {
@@ -506,6 +506,9 @@
  "anthropic/claude-3.5-sonnet": {
    "description": "Claude 3.5 Sonnet 提供了超越 Opus 的能力和比 Sonnet 更快的速度，同时保持与 Sonnet 相同的价格。Sonnet 特别擅长编程、数据科学、视觉处理、代理任务。"
  },
+  "anthropic/claude-3.7-sonnet": {
+    "description": "Claude 3.7 Sonnet 是 Anthropic 迄今为止最智能的模型，也是市场上首个混合推理模型。Claude 3.7 Sonnet 可以产生近乎即时的响应或延长的逐步思考，用户可以清晰地看到这些过程。Sonnet 特别擅长编程、数据科学、视觉处理、代理任务。"
+  },
  "aya": {
    "description": "Aya 23 是 Cohere 推出的多语言模型，支持 23 种语言，为多元化语言应用提供便利。"
  },
@@ -830,6 +833,12 @@
  "gemini-2.0-flash-001": {
    "description": "Gemini 2.0 Flash 提供下一代功能和改进，包括卓越的速度、原生工具使用、多模态生成和1M令牌上下文窗口。"
  },
+  "gemini-2.0-flash-exp": {
+    "description": "Gemini 2.0 Flash 模型变体，针对成本效益和低延迟等目标进行了优化。"
+  },
+  "gemini-2.0-flash-exp-image-generation": {
+    "description": "Gemini 2.0 Flash 实验模型，支持图像生成"
+  },
  "gemini-2.0-flash-lite": {
    "description": "Gemini 2.0 Flash 模型变体，针对成本效益和低延迟等目标进行了优化。"
  },
@@ -289,7 +289,7 @@
      "title": "语音识别语种"
    },
    "sttService": {
-      "desc": "其中 broswer 为浏览器原生的语音识别服务",
+      "desc": "其中 browser 为浏览器原生的语音识别服务",
      "title": "语音识别服务"
    },
    "title": "语音服务",
@@ -32,6 +32,7 @@
    "title": "话题列表"
  },
  "searchPlaceholder": "搜索话题...",
+  "searchResultEmpty": "暂无搜索结果",
  "temp": "临时",
  "title": "话题"
-}
+}
@@ -64,6 +64,9 @@
    "stop": "停止",
    "warp": "換行"
  },
+  "intentUnderstanding": {
+    "title": "正在理解並分析您的意圖..."
+  },
  "knowledgeBase": {
    "all": "所有內容",
    "allFiles": "所有檔案",
@@ -144,7 +147,6 @@
        "desc": "根據對話內容智能判斷是否需要搜尋",
        "title": "智能連網"
      },
-      "disable": "當前模型不支持函數調用，因此無法使用智能連網功能",
      "off": {
        "desc": "僅使用模型的基礎知識，不進行網路搜尋",
        "title": "關閉連網"
@@ -155,6 +157,10 @@
      },
      "useModelBuiltin": "使用模型內建搜尋引擎"
    },
+    "searchModel": {
+      "desc": "當前模型不支持函數調用，因此需要搭配支持函數調用的模型才能聯網搜索",
+      "title": "搜索輔助模型"
+    },
    "title": "連網搜尋"
  },
  "searchAgentPlaceholder": "搜尋助手...",
@@ -76,6 +76,7 @@
      "custom": "自訂模型，預設支援函式呼叫與視覺辨識，請根據實際情況驗證上述能力的可用性",
      "file": "該模型支援上傳檔案讀取與辨識",
      "functionCall": "該模型支援函式呼叫（Function Call）",
+      "imageOutput": "該模型支援生成圖片",
      "reasoning": "該模型支持深度思考",
      "search": "該模型支援聯網搜尋",
      "tokens": "該模型單一會話最多支援 {{tokens}} Tokens",
@@ -85,6 +86,8 @@
  },
  "ModelSwitchPanel": {
    "emptyModel": "沒有啟用的模型，請前往設定開啟",
+    "emptyProvider": "沒有啟用的服務商，請前往設定開啟",
+    "goToSettings": "前往設定",
    "provider": "提供商"
  },
  "OllamaSetupGuide": {
@@ -506,6 +506,9 @@
  "anthropic/claude-3.5-sonnet": {
    "description": "Claude 3.5 Sonnet 提供了超越 Opus 的能力和比 Sonnet 更快的速度，同時保持與 Sonnet 相同的價格。Sonnet 特別擅長程式設計、數據科學、視覺處理、代理任務。"
  },
+  "anthropic/claude-3.7-sonnet": {
+    "description": "Claude 3.7 Sonnet 是 Anthropic 迄今為止最智能的模型，也是市場上首個混合推理模型。Claude 3.7 Sonnet 可以產生近乎即時的回應或延長的逐步思考，使用者可以清晰地看到這些過程。Sonnet 特別擅長程式設計、數據科學、視覺處理、代理任務。"
+  },
  "aya": {
    "description": "Aya 23 是 Cohere 推出的多語言模型，支持 23 種語言，為多元化語言應用提供便利。"
  },
@@ -830,6 +833,12 @@
  "gemini-2.0-flash-001": {
    "description": "Gemini 2.0 Flash 提供下一代功能和改進，包括卓越的速度、原生工具使用、多模態生成和1M令牌上下文窗口。"
  },
+  "gemini-2.0-flash-exp": {
+    "description": "Gemini 2.0 Flash 模型變體，針對成本效益和低延遲等目標進行了優化。"
+  },
+  "gemini-2.0-flash-exp-image-generation": {
+    "description": "Gemini 2.0 Flash 實驗模型，支持圖像生成"
+  },
  "gemini-2.0-flash-lite": {
    "description": "Gemini 2.0 Flash 模型變體，針對成本效益和低延遲等目標進行了優化。"
  },
@@ -289,7 +289,7 @@
      "title": "語音識別語種"
    },
    "sttService": {
-      "desc": "其中 broswer 為瀏覽器原生的語音識別服務",
+      "desc": "其中 browser 為瀏覽器原生的語音識別服務",
      "title": "語音識別服務"
    },
    "title": "語音服務",
@@ -32,6 +32,7 @@
    "title": "話題列表"
  },
  "searchPlaceholder": "搜尋話題...",
+  "searchResultEmpty": "目前沒有搜尋結果",
  "temp": "臨時",
  "title": "話題"
 }
@@ -25,7 +25,6 @@ const nextConfig: NextConfig = {
      '@lobehub/ui',
      'gpt-tokenizer',
    ],
-    reactCompiler: true,
    webVitalsAttribution: ['CLS', 'LCP'],
    webpackMemoryOptimizations: true,
  },
@@ -1,6 +1,6 @@
 {
  "name": "@lobehub/chat",
-  "version": "1.69.4",
+  "version": "1.71.2",
  "description": "Lobe Chat - an open-source, high-performance chatbot framework that supports speech synthesis, multimodal, and extensible Function Call plugin system. Supports one-click free deployment of your private ChatGPT/LLM web application.",
  "keywords": [
    "framework",
@@ -35,12 +35,13 @@
    "build-sitemap": "tsx ./scripts/buildSitemapIndex/index.ts",
    "build:analyze": "ANALYZE=true next build",
    "build:docker": "DOCKER=true next build && npm run build-sitemap",
-    "db:generate": "drizzle-kit generate && npm run db:generate-client",
+    "db:generate": "drizzle-kit generate && npm run db:generate-client && npm run workflow:dbml",
    "db:generate-client": "tsx ./scripts/migrateClientDB/compile-migrations.ts",
    "db:migrate": "MIGRATION_DB=1 tsx ./scripts/migrateServerDB/index.ts",
    "db:push": "drizzle-kit push",
    "db:push-test": "NODE_ENV=test drizzle-kit push",
    "db:studio": "drizzle-kit studio",
+    "db:visualize": "dbdocs build docs/developer/database-schema.dbml --project lobe-chat",
    "db:z-pull": "drizzle-kit introspect",
    "dev": "next dev --turbopack -p 3010",
    "docs:i18n": "lobe-i18n md && npm run lint:md && npm run lint:mdx",
@@ -72,6 +73,7 @@
    "workflow:cdn": "tsx ./scripts/cdnWorkflow/index.ts",
    "workflow:changelog": "tsx ./scripts/changelogWorkflow/index.ts",
    "workflow:countCharters": "tsx scripts/countEnWord.ts",
+    "workflow:dbml": "tsx ./scripts/dbmlWorkflow/index.ts",
    "workflow:docs": "tsx ./scripts/docsWorkflow/index.ts",
    "workflow:i18n": "tsx ./scripts/i18nWorkflow/index.ts",
    "workflow:mdx": "tsx ./scripts/mdxWorkflow/index.ts",
@@ -120,7 +122,7 @@
    "@clerk/themes": "^2.2.4",
    "@codesandbox/sandpack-react": "^2.19.10",
    "@cyntler/react-doc-viewer": "^1.17.0",
-    "@electric-sql/pglite": "0.2.13",
+    "@electric-sql/pglite": "0.2.17",
    "@google-cloud/vertexai": "^1.9.2",
    "@google/generative-ai": "^0.24.0",
    "@huggingface/inference": "^2.8.1",
@@ -286,12 +288,13 @@
    "@types/ws": "^8.5.13",
    "@vitest/coverage-v8": "~1.2.2",
    "ajv-keywords": "^5.1.0",
-    "babel-plugin-react-compiler": "19.0.0-beta-21e868a-20250216",
    "commitlint": "^19.6.1",
    "consola": "^3.3.3",
    "crypto-js": "^4.2.0",
+    "dbdocs": "^0.14.3",
    "dotenv": "^16.4.7",
    "dpdm-fast": "^1.0.7",
+    "drizzle-dbml-generator": "^0.10.0",
    "drizzle-kit": "^0.30.1",
    "eslint": "^8.57.1",
    "eslint-plugin-mdx": "^3.1.5",
@@ -327,7 +330,7 @@
    "vitest": "~1.2.2",
    "vitest-canvas-mock": "^0.3.3"
  },
-  "packageManager": "pnpm@9.15.6",
+  "packageManager": "pnpm@9.15.7",
  "publishConfig": {
    "access": "public",
    "registry": "https://registry.npmjs.org"
@@ -5,7 +5,7 @@
  "main": "src/index.ts",
  "types": "src/index.ts",
  "dependencies": {
-    "@mozilla/readability": "^0.5.0",
+    "@mozilla/readability": "^0.6.0",
    "happy-dom": "^17.0.0",
    "node-html-markdown": "^1.3.0",
    "query-string": "^9.1.1",
@@ -23,7 +23,7 @@ describe('Crawler', () => {

  it('should crawl successfully with default impls', async () => {
    const mockResult = {
-      content: 'test content',
+      content: 'test content'.padEnd(101, ' '), // Ensure content length > 100
      contentType: 'text' as const,
      url: 'https://example.com',
    };
@@ -45,7 +45,7 @@ describe('Crawler', () => {

  it('should use user provided impls', async () => {
    const mockResult = {
-      content: 'test content',
+      content: 'test content'.padEnd(101, ' '), // Ensure content length > 100
      contentType: 'text' as const,
      url: 'https://example.com',
    };
@@ -93,7 +93,7 @@ describe('Crawler', () => {

  it('should handle transformed urls', async () => {
    const mockResult = {
-      content: 'test content',
+      content: 'test content'.padEnd(101, ' '), // Ensure content length > 100
      contentType: 'text' as const,
      url: 'https://transformed.example.com',
    };
@@ -121,7 +121,7 @@ describe('Crawler', () => {

  it('should merge filter options correctly', async () => {
    const mockResult = {
-      content: 'test content',
+      content: 'test content'.padEnd(101, ' '), // Ensure content length > 100
      contentType: 'text' as const,
      url: 'https://example.com',
    };
@@ -150,7 +150,7 @@ describe('Crawler', () => {

  it('should use rule impls when provided', async () => {
    const mockResult = {
-      content: 'test content',
+      content: 'test content'.padEnd(101, ' '), // Ensure content length > 100
      contentType: 'text' as const,
      url: 'https://example.com',
    };
@@ -176,4 +176,32 @@ describe('Crawler', () => {
      transformedUrl: undefined,
    });
  });
+
+  it('should skip results with content length <= 100', async () => {
+    const mockResult = {
+      content: 'short content', // Content length <= 100
+      contentType: 'text' as const,
+      url: 'https://example.com',
+    };
+
+    const { crawlImpls } = await import('../crawImpl');
+    vi.mocked(crawlImpls.naive).mockResolvedValue(mockResult);
+    vi.mocked(crawlImpls.jina).mockResolvedValue(mockResult);
+    vi.mocked(crawlImpls.browserless).mockResolvedValue(mockResult);
+
+    const result = await crawler.crawl({
+      url: 'https://example.com',
+    });
+
+    expect(result).toEqual({
+      crawler: undefined,
+      data: {
+        content: 'Fail to crawl the page. Error type: UnknownError, error message: undefined',
+        errorMessage: undefined,
+        errorType: 'UnknownError',
+      },
+      originalUrl: 'https://example.com',
+      transformedUrl: undefined,
+    });
+  });
 });
@@ -67,7 +67,7 @@ describe('browserless', () => {
      contentType: 'text',
      description: expect.any(String),
      length: expect.any(Number),
-      siteName: null,
+      siteName: undefined,
      title: 'Test Title',
      url: 'https://example.com',
    });
@@ -48,7 +48,7 @@ export const browserless: CrawlImpl = async (url, { filterOptions }) => {
      return {
        content: result.content,
        contentType: 'text',
-        description: result?.excerpt,
+        description: result?.description,
        length: result.length,
        siteName: result?.siteName,
        title: result?.title,
@@ -75,11 +75,19 @@ export const naive: CrawlImpl = async (url, { filterOptions }) => {
  const type = res.headers.get('content-type');

  if (type?.includes('application/json')) {
-    const json = await res.json();
+    let content: string;
+
+    try {
+      const json = await res.clone().json();
+      content = JSON.stringify(json, null, 2);
+    } catch {
+      content = await res.text();
+    }
+
    return {
-      content: JSON.stringify(json, null, 2),
+      content: content,
      contentType: 'json',
-      length: json.length,
+      length: content.length,
      url,
    } satisfies CrawlSuccessResult;
  }
@@ -103,7 +111,7 @@ export const naive: CrawlImpl = async (url, { filterOptions }) => {
    return {
      content: result.content,
      contentType: 'text',
-      description: result?.excerpt,
+      description: result?.description,
      length: result.length,
      siteName: result?.siteName,
      title: result?.title,
@@ -3,8 +3,18 @@ import { CrawlUrlRule } from './type';
 import { crawUrlRules } from './urlRules';
 import { applyUrlRules } from './utils/appUrlRules';

+interface CrawlOptions {
+  impls?: string[];
+}
+
 export class Crawler {
-  impls = ['naive', 'jina', 'browserless'] as const;
+  impls: CrawlImplType[];
+
+  constructor(options: CrawlOptions = {}) {
+    this.impls = !!options.impls?.length
+      ? (options.impls.filter((impl) => Object.keys(crawlImpls).includes(impl)) as CrawlImplType[])
+      : (['naive', 'jina', 'browserless'] as const);
+  }

  /**
   * 爬取网页内容
@@ -46,7 +56,7 @@ export class Crawler {
      try {
        const res = await crawlImpls[impl](transformedUrl, { filterOptions: mergedFilterOptions });

-        if (res)
+        if (res && res.content && res.content?.length > 100)
          return {
            crawler: impl,
            data: res,
@@ -67,4 +67,15 @@ export const crawUrlRules: CrawlUrlRule[] = [
    impls: ['jina'],
    urlPattern: 'https://developer.mozilla.org(.*)',
  },
+  // cvpr thecvf
+  {
+    impls: ['jina'],
+    urlPattern: 'https://cvpr.thecvf.com(.*)',
+  },
+  // 飞书用 jina
+  // https://github.com/lobehub/lobe-chat/issues/6879
+  {
+    impls: ['jina'],
+    urlPattern: 'https://(.*).feishu.cn/(.*)',
+  },
 ];
--- a/Show More
+++ b/Show More
Author	SHA1	Message	Date
semantic-release-bot	6857d85043	🔖 chore(release): v1.71.2 [skip ci] ### [Version 1.71.2](https://github.com/lobehub/lobe-chat/compare/v1.71.1...v1.71.2) <sup>Released on 2025-03-15</sup> #### 🐛 Bug Fixes - misc: Fix knowledge base issue. <br/> <details> <summary><kbd>Improvements and Fixes</kbd></summary> #### What's fixed * misc: Fix knowledge base issue, closes [#6973](https://github.com/lobehub/lobe-chat/issues/6973) ([`15f39ef`](https://github.com/lobehub/lobe-chat/commit/15f39ef)) </details> <div align="right"> [![](https://img.shields.io/badge/-BACK_TO_TOP-151515?style=flat-square)](#readme-top) </div>	2025-03-15 09:55:43 +00:00
Arvin Xu	15f39efc19	🐛 fix: fix knowledge base issue (#6973 ) * refactor agent runtime * fix KnowledgeBase search issue * fix tests	2025-03-15 17:45:38 +08:00
lobehubbot	829ebc7177	📝 docs(bot): Auto sync agents & plugin to readme	2025-03-15 04:02:23 +00:00
semantic-release-bot	707b2eea5e	🔖 chore(release): v1.71.1 [skip ci] ### [Version 1.71.1](https://github.com/lobehub/lobe-chat/compare/v1.71.0...v1.71.1) <sup>Released on 2025-03-15</sup> #### 🐛 Bug Fixes - misc: Fix google gemini output relative issue. #### 💄 Styles - misc: Update Vertex AI models. <br/> <details> <summary><kbd>Improvements and Fixes</kbd></summary> #### What's fixed * misc: Fix google gemini output relative issue, closes [#6970](https://github.com/lobehub/lobe-chat/issues/6970) ([`fdcaaf3`](https://github.com/lobehub/lobe-chat/commit/fdcaaf3)) #### Styles * misc: Update Vertex AI models, closes [#6967](https://github.com/lobehub/lobe-chat/issues/6967) ([`d4432f1`](https://github.com/lobehub/lobe-chat/commit/d4432f1)) </details> <div align="right"> [![](https://img.shields.io/badge/-BACK_TO_TOP-151515?style=flat-square)](#readme-top) </div>	2025-03-15 04:01:13 +00:00
Koell	d4432f1f5e	💄 style: Update Vertex AI models (#6967 ) * Add Gemini 2.0 Flash Lite model * Update Vertex AI model prices	2025-03-15 11:52:33 +08:00
Arvin Xu	fdcaaf34fa	🐛 fix: fix google gemini output relative issue (#6970 ) * fix google streaming * add ability * fix instruction * fix tests * update i18n	2025-03-15 11:52:20 +08:00
lobehubbot	59cafa0bc3	📝 docs(bot): Auto sync agents & plugin to readme	2025-03-14 13:17:45 +00:00
semantic-release-bot	1f08511ca6	🔖 chore(release): v1.71.0 [skip ci] ## [Version 1.71.0](https://github.com/lobehub/lobe-chat/compare/v1.70.11...v1.71.0) <sup>Released on 2025-03-14</sup> #### ✨ Features - misc: Support gemini image output in chat. <br/> <details> <summary><kbd>Improvements and Fixes</kbd></summary> #### What's improved * misc: Support gemini image output in chat, closes [#6931](https://github.com/lobehub/lobe-chat/issues/6931) ([`d4c0d1f`](https://github.com/lobehub/lobe-chat/commit/d4c0d1f)) </details> <div align="right"> [![](https://img.shields.io/badge/-BACK_TO_TOP-151515?style=flat-square)](#readme-top) </div>	2025-03-14 13:16:36 +00:00
gru-agent[bot]	d4c0d1f8fb	✨ feat: support gemini image output in chat (#6931 ) Co-authored-by: gru-agent[bot] <185149714+gru-agent[bot]@users.noreply.github.com>	2025-03-14 21:08:02 +08:00
Arvin Xu	af0243cc15	✨ feat: support gemini image output in chat (#6956 ) * support gemini image * fix lint * fix * fix upload bug * support google token count * update credit * update i18n	2025-03-14 20:52:37 +08:00
Arvin Xu	849584479a	🔨 chore: visualize db schema with dbdocs (#6950 ) * test db schema * Update sync-database-schema.yml * Update sync-database-schema.yml * Update sync-database-schema.yml * Update package.json * Update sync-database-schema.yml * Delete docs/developer/database-schema.dbml * update workflow * Update sync-database-schema.yml	2025-03-14 14:24:39 +08:00
lobehubbot	a7e92b3b5b	📝 docs(bot): Auto sync agents & plugin to readme	2025-03-13 17:02:47 +00:00
semantic-release-bot	9f695332c8	🔖 chore(release): v1.70.11 [skip ci] ### [Version 1.70.11](https://github.com/lobehub/lobe-chat/compare/v1.70.10...v1.70.11) <sup>Released on 2025-03-13</sup> <br/> <details> <summary><kbd>Improvements and Fixes</kbd></summary> </details> <div align="right"> [![](https://img.shields.io/badge/-BACK_TO_TOP-151515?style=flat-square)](#readme-top) </div>	2025-03-13 17:01:43 +00:00
Arvin Xu	c9a17fbff8	⚡️ perf: fix improve topic relative performance (#6937 )	2025-03-14 00:53:14 +08:00
BrandonStudio	30b13088a3	🔨 chore: Add types for issue templates (#6940 )	2025-03-13 18:06:46 +08:00
lobehubbot	b7051a0ab7	📝 docs(bot): Auto sync agents & plugin to readme	2025-03-12 18:06:10 +00:00
semantic-release-bot	0b871ecc89	🔖 chore(release): v1.70.10 [skip ci] ### [Version 1.70.10](https://github.com/lobehub/lobe-chat/compare/v1.70.9...v1.70.10) <sup>Released on 2025-03-12</sup> #### 🐛 Bug Fixes - misc: The agent setting `-edit_agent` not work. <br/> <details> <summary><kbd>Improvements and Fixes</kbd></summary> #### What's fixed * misc: The agent setting `-edit_agent` not work, closes [#4609](https://github.com/lobehub/lobe-chat/issues/4609) ([`7af0ec6`](https://github.com/lobehub/lobe-chat/commit/7af0ec6)) </details> <div align="right"> [![](https://img.shields.io/badge/-BACK_TO_TOP-151515?style=flat-square)](#readme-top) </div>	2025-03-12 18:05:03 +00:00
mushan0x0	7af0ec6161	🐛 fix: the agent setting `-edit_agent` not work (#4609 ) * 🐛 fix: the agent setting `-edit_agent` not work * Update index.tsx	2025-03-13 01:56:19 +08:00
lobehubbot	64caf2ebd2	📝 docs(bot): Auto sync agents & plugin to readme	2025-03-12 16:35:13 +00:00
semantic-release-bot	a9e572b48e	🔖 chore(release): v1.70.9 [skip ci] ### [Version 1.70.9](https://github.com/lobehub/lobe-chat/compare/v1.70.8...v1.70.9) <sup>Released on 2025-03-12</sup> <br/> <details> <summary><kbd>Improvements and Fixes</kbd></summary> </details> <div align="right"> [![](https://img.shields.io/badge/-BACK_TO_TOP-151515?style=flat-square)](#readme-top) </div>	2025-03-12 16:34:08 +00:00
Arvin Xu	f7d6021e4a	⚡️ perf: fix topic search performance (#6912 ) * update * fix lint * fix tests * fix tests * update locale	2025-03-13 00:25:17 +08:00
lobehubbot	9a9d98fdec	📝 docs(bot): Auto sync agents & plugin to readme	2025-03-12 15:44:40 +00:00
semantic-release-bot	b3894ba19d	🔖 chore(release): v1.70.8 [skip ci] ### [Version 1.70.8](https://github.com/lobehub/lobe-chat/compare/v1.70.7...v1.70.8) <sup>Released on 2025-03-12</sup> #### 🐛 Bug Fixes - misc: Fix theme flicking. <br/> <details> <summary><kbd>Improvements and Fixes</kbd></summary> #### What's fixed * misc: Fix theme flicking, closes [#6926](https://github.com/lobehub/lobe-chat/issues/6926) ([`103c3e3`](https://github.com/lobehub/lobe-chat/commit/103c3e3)) </details> <div align="right"> [![](https://img.shields.io/badge/-BACK_TO_TOP-151515?style=flat-square)](#readme-top) </div>	2025-03-12 15:43:37 +00:00
Arvin Xu	103c3e3696	🐛 fix: fix theme flicking (#6926 )	2025-03-12 23:34:49 +08:00
lobehubbot	210920f4b6	📝 docs(bot): Auto sync agents & plugin to readme	2025-03-12 11:28:53 +00:00
semantic-release-bot	2770a8b9a6	🔖 chore(release): v1.70.7 [skip ci] ### [Version 1.70.7](https://github.com/lobehub/lobe-chat/compare/v1.70.6...v1.70.7) <sup>Released on 2025-03-12</sup> #### 🐛 Bug Fixes - misc: Fix crawl result for short content. <br/> <details> <summary><kbd>Improvements and Fixes</kbd></summary> #### What's fixed * misc: Fix crawl result for short content, closes [#6903](https://github.com/lobehub/lobe-chat/issues/6903) [#6904](https://github.com/lobehub/lobe-chat/issues/6904) ([`d8fda65`](https://github.com/lobehub/lobe-chat/commit/d8fda65)) </details> <div align="right"> [![](https://img.shields.io/badge/-BACK_TO_TOP-151515?style=flat-square)](#readme-top) </div>	2025-03-12 11:27:51 +00:00
Arvin Xu	d8fda65d33	🐛 fix: fix crawl result for short content (#6903 ) * fix impl for short content * Add test to skip results with content length less than or equal to 100 in crawler. (#6904) Co-authored-by: gru-agent[bot] <185149714+gru-agent[bot]@users.noreply.github.com> --------- Co-authored-by: gru-agent[bot] <185149714+gru-agent[bot]@users.noreply.github.com>	2025-03-12 19:19:06 +08:00
lobehubbot	c7170c0e06	📝 docs(bot): Auto sync agents & plugin to readme	2025-03-11 17:59:56 +00:00
semantic-release-bot	dd6086a3a3	🔖 chore(release): v1.70.6 [skip ci] ### [Version 1.70.6](https://github.com/lobehub/lobe-chat/compare/v1.70.5...v1.70.6) <sup>Released on 2025-03-11</sup> #### 🐛 Bug Fixes - misc: Link jump in mobile terminal data statistics. <br/> <details> <summary><kbd>Improvements and Fixes</kbd></summary> #### What's fixed * misc: Link jump in mobile terminal data statistics, closes [#6893](https://github.com/lobehub/lobe-chat/issues/6893) ([`505d24d`](https://github.com/lobehub/lobe-chat/commit/505d24d)) </details> <div align="right"> [![](https://img.shields.io/badge/-BACK_TO_TOP-151515?style=flat-square)](#readme-top) </div>	2025-03-11 17:58:51 +00:00
XiaoBa	505d24d8d6	🐛 fix: Link jump in mobile terminal data statistics (#6893 ) Co-authored-by: Xiaoba Yu <xb1823725853@gmail.com>	2025-03-12 01:50:06 +08:00
lobehubbot	b6a9126506	📝 docs(bot): Auto sync agents & plugin to readme	2025-03-11 15:49:14 +00:00
semantic-release-bot	fff6c71f71	🔖 chore(release): v1.70.5 [skip ci] ### [Version 1.70.5](https://github.com/lobehub/lobe-chat/compare/v1.70.4...v1.70.5) <sup>Released on 2025-03-11</sup> #### 🐛 Bug Fixes - misc: Refactor the theme implement. <br/> <details> <summary><kbd>Improvements and Fixes</kbd></summary> #### What's fixed * misc: Refactor the theme implement, closes [#6844](https://github.com/lobehub/lobe-chat/issues/6844) ([`e5c2161`](https://github.com/lobehub/lobe-chat/commit/e5c2161)) </details> <div align="right"> [![](https://img.shields.io/badge/-BACK_TO_TOP-151515?style=flat-square)](#readme-top) </div>	2025-03-11 15:48:12 +00:00
Arvin Xu	e5c2161288	🐛 fix: refactor the theme implement (#6844 ) * refactor theme * Refactor systemStatus selectors tests to improve coverage and organization. * improve cookie issue * fix theme * Add unit tests for global store actions in general.test.ts --------- Co-authored-by: gru-agent[bot] <185149714+gru-agent[bot]@users.noreply.github.com>	2025-03-11 23:39:31 +08:00
semantic-release-bot	41a1f2af2e	🔖 chore(release): v1.70.4 [skip ci] ### [Version 1.70.4](https://github.com/lobehub/lobe-chat/compare/v1.70.3...v1.70.4) <sup>Released on 2025-03-11</sup> #### 💄 Styles - misc: Support OpenRouter custom BaseURL. <br/> <details> <summary><kbd>Improvements and Fixes</kbd></summary> #### Styles * misc: Support OpenRouter custom BaseURL ([`a8089ed`](https://github.com/lobehub/lobe-chat/commit/a8089ed)) </details> <div align="right"> [![](https://img.shields.io/badge/-BACK_TO_TOP-151515?style=flat-square)](#readme-top) </div>	2025-03-11 04:20:58 +00:00
Arvin Xu	a3099cfdc6	Merge pull request #6732 from bbbugg/patch-1 🐛fix: customize logo not display in About page and update DOCS about "deploymentName"	2025-03-11 12:12:13 +08:00
Arvin Xu	6267b76153	Merge pull request #6864 from BrandonStudio/dev/openrouter-baseurl 💄 style: Support OpenRouter custom BaseURL	2025-03-11 12:10:48 +08:00
Arvin Xu	6f4d280481	Merge pull request #6886 from lobehub/refactor/code ♻️ refactor: refactor user plugins model name	2025-03-11 12:09:47 +08:00
Arvin Xu	5d7007f37b	fix json issue	2025-03-11 03:29:48 +00:00
Arvin Xu	65102d60ec	update	2025-03-11 03:26:51 +00:00
Arvin Xu	96a4c4a42f	refactor code	2025-03-11 03:17:45 +00:00
lobehubbot	a28165b2f5	📝 docs(bot): Auto sync agents & plugin to readme	2025-03-11 02:46:06 +00:00
Arvin Xu	265e9b3c07	Merge pull request #6882 from lobehub/gru/src-store-aiInfra-slices-aiProvider-selectors-ts-1741658283737 ✅ test: add unit test for src/store/aiInfra/slices/aiProvider/selectors.ts	2025-03-11 10:37:23 +08:00
gru-agent[bot]	8eb7a04fd4	Add unit tests for aiProvider selectors in selectors.test.ts file.	2025-03-11 01:58:11 +00:00
semantic-release-bot	08f8073580	🔖 chore(release): v1.70.3 [skip ci] ### [Version 1.70.3](https://github.com/lobehub/lobe-chat/compare/v1.70.2...v1.70.3) <sup>Released on 2025-03-11</sup> #### 💄 Styles - spelling: Correct "broswer" to "browser" across codebase. <br/> <details> <summary><kbd>Improvements and Fixes</kbd></summary> #### Styles * spelling: Correct "broswer" to "browser" across codebase, closes [#6876](https://github.com/lobehub/lobe-chat/issues/6876) ([`8d677a2`](https://github.com/lobehub/lobe-chat/commit/8d677a2)) </details> <div align="right"> [![](https://img.shields.io/badge/-BACK_TO_TOP-151515?style=flat-square)](#readme-top) </div>	2025-03-11 01:47:09 +00:00
KurtisAsia	8d677a2feb	💄 style(spelling): correct "broswer" to "browser" across codebase (#6876 ) fix(spelling): correct "broswer" to "browser" across codebase - Fix typo in modelConfig.ts and modelConfig.test.ts - Correct spelling in aiProvider/selectors.ts - Fix spelling in localization files (setting.ts, setting.json) - Update spelling in modelProviders/index.ts - Corrected in multiple locales (zh-TW, zh-CN, fa-IR)	2025-03-11 09:38:31 +08:00
BrandonStudio	a8089edc06	💄 style: Support OpenRouter custom BaseURL	2025-03-10 08:30:02 +00:00
lobehubbot	76e132722f	📝 docs(bot): Auto sync agents & plugin to readme	2025-03-10 05:40:38 +00:00
semantic-release-bot	c3a0dc0965	🔖 chore(release): v1.70.2 [skip ci] ### [Version 1.70.2](https://github.com/lobehub/lobe-chat/compare/v1.70.1...v1.70.2) <sup>Released on 2025-03-10</sup> #### 🐛 Bug Fixes - misc: Update cvpr cvf url rules. <br/> <details> <summary><kbd>Improvements and Fixes</kbd></summary> #### What's fixed * misc: Update cvpr cvf url rules, closes [#6860](https://github.com/lobehub/lobe-chat/issues/6860) ([`c299067`](https://github.com/lobehub/lobe-chat/commit/c299067)) </details> <div align="right"> [![](https://img.shields.io/badge/-BACK_TO_TOP-151515?style=flat-square)](#readme-top) </div>	2025-03-10 05:39:37 +00:00
Arvin Xu	c299067cb6	🐛 fix: update cvpr cvf url rules (#6860 )	2025-03-10 13:31:05 +08:00
lobehubbot	981bb08029	📝 docs(bot): Auto sync agents & plugin to readme	2025-03-10 03:31:09 +00:00
semantic-release-bot	bb21eb3efd	🔖 chore(release): v1.70.1 [skip ci] ### [Version 1.70.1](https://github.com/lobehub/lobe-chat/compare/v1.70.0...v1.70.1) <sup>Released on 2025-03-10</sup> #### 🐛 Bug Fixes - misc: Fix anthropic max tokens. <br/> <details> <summary><kbd>Improvements and Fixes</kbd></summary> #### What's fixed * misc: Fix anthropic max tokens, closes [#6859](https://github.com/lobehub/lobe-chat/issues/6859) ([`35fbc6c`](https://github.com/lobehub/lobe-chat/commit/35fbc6c)) </details> <div align="right"> [![](https://img.shields.io/badge/-BACK_TO_TOP-151515?style=flat-square)](#readme-top) </div>	2025-03-10 03:30:06 +00:00
Arvin Xu	35fbc6c0d5	🐛 fix: fix anthropic max tokens (#6859 ) * fix anthropic * update i18n	2025-03-10 11:21:32 +08:00
wzdnzd	dfee9b2b13	🔨 chore: typo fixed for zh-CN (#6856 )	2025-03-10 11:04:40 +08:00
Arvin Xu	1841fee733	Merge branch 'main' into patch-1	2025-03-10 02:52:49 +08:00
lobehubbot	cc9f793ec3	📝 docs(bot): Auto sync agents & plugin to readme	2025-03-09 18:45:41 +00:00
semantic-release-bot	df0886ebf3	🔖 chore(release): v1.70.0 [skip ci] ## [Version 1.70.0](https://github.com/lobehub/lobe-chat/compare/v1.69.6...v1.70.0) <sup>Released on 2025-03-09</sup> #### ✨ Features - misc: Support no-fc models like deepseek r1 with online search. <br/> <details> <summary><kbd>Improvements and Fixes</kbd></summary> #### What's improved * misc: Support no-fc models like deepseek r1 with online search, closes [#6842](https://github.com/lobehub/lobe-chat/issues/6842) ([`f284c25`](https://github.com/lobehub/lobe-chat/commit/f284c25)) </details> <div align="right"> [![](https://img.shields.io/badge/-BACK_TO_TOP-151515?style=flat-square)](#readme-top) </div>	2025-03-09 18:44:41 +00:00
Arvin Xu	f284c25606	✨ feat: support no-fc models like deepseek r1 with online search (#6842 ) * update crawler rule * feat: 完成联网集成 * update i18n * update tests * update tests * fix tests * improve performance * fix error issue * fix signal issue and improve implement * fix pricing in CNY * fix tests * filter empty providers * fix tests * improve search crawler env * fix search crawler env * fix documents	2025-03-10 02:35:52 +08:00
bbbugg	0cf39c535d	Merge branch 'lobehub:main' into patch-1	2025-03-09 22:21:06 +08:00
lobehubbot	23a26a9563	📝 docs(bot): Auto sync agents & plugin to readme	2025-03-09 14:01:53 +00:00
semantic-release-bot	8039186493	🔖 chore(release): v1.69.6 [skip ci] ### [Version 1.69.6](https://github.com/lobehub/lobe-chat/compare/v1.69.5...v1.69.6) <sup>Released on 2025-03-09</sup> #### 🐛 Bug Fixes - misc: Fix context cache control and model builtin search switch. <br/> <details> <summary><kbd>Improvements and Fixes</kbd></summary> #### What's fixed * misc: Fix context cache control and model builtin search switch, closes [#6831](https://github.com/lobehub/lobe-chat/issues/6831) ([`5c6b8ea`](https://github.com/lobehub/lobe-chat/commit/5c6b8ea)) </details> <div align="right"> [![](https://img.shields.io/badge/-BACK_TO_TOP-151515?style=flat-square)](#readme-top) </div>	2025-03-09 14:00:43 +00:00
Arvin Xu	5c6b8eaf8a	🐛 fix: fix context cache control and model builtin search switch (#6831 ) * upgrade readability * improve openai performance * improve model select * upgrade pglite to 0.2.17 * fix google builtin search config * fix tests * fix claude max output tokens and context caching config * fix context caching config * update i18n * fix tests	2025-03-09 21:52:12 +08:00
renovate[bot]	dde299312e	Update pnpm to v9.15.7 (#6819 ) Co-authored-by: renovate[bot] <29139614+renovate[bot]@users.noreply.github.com>	2025-03-09 21:19:05 +08:00
lobehubbot	0aa47d024c	📝 docs(bot): Auto sync agents & plugin to readme	2025-03-09 11:18:04 +00:00
semantic-release-bot	b86d86782a	🔖 chore(release): v1.69.5 [skip ci] ### [Version 1.69.5](https://github.com/lobehub/lobe-chat/compare/v1.69.4...v1.69.5) <sup>Released on 2025-03-09</sup> #### 💄 Styles - chat: Auto send message from URL. - misc: Support openrouter claude 3.7 sonnet reasoning. <br/> <details> <summary><kbd>Improvements and Fixes</kbd></summary> #### Styles * chat: Auto send message from URL, closes [#6497](https://github.com/lobehub/lobe-chat/issues/6497) ([`30b2639`](https://github.com/lobehub/lobe-chat/commit/30b2639)) * misc: Support openrouter claude 3.7 sonnet reasoning, closes [#6806](https://github.com/lobehub/lobe-chat/issues/6806) ([`f1ffc2c`](https://github.com/lobehub/lobe-chat/commit/f1ffc2c)) </details> <div align="right"> [![](https://img.shields.io/badge/-BACK_TO_TOP-151515?style=flat-square)](#readme-top) </div>	2025-03-09 11:16:40 +00:00
Eridanus Sora	6006175c5d	⚡️ perf: improve performace of refreshModelProviderList (#6672 )	2025-03-09 19:07:42 +08:00
bbbugg	c0f1532ca4	新增 QWEN_PROXY_URL 配置项并更新 VOLCENGINE_MODEL_LIST 描述语法(加入了部署名)	2025-03-08 16:22:08 +08:00
bbbugg	9bad484252	DEEPSEEK_MODEL_LIST 移除 deploymentName描述	2025-03-08 16:04:41 +08:00
bbbugg	8c1412a5a1	修复：更新 logo 组件默认类型处理并移除type={'flat'}	2025-03-08 15:57:15 +08:00
bbbugg	de12fcf896	Merge branch 'lobehub:main' into patch-1	2025-03-08 08:24:44 +08:00
bbbugg	c2d0ee8c96	Merge branch 'main' into patch-1	2025-03-07 16:51:12 +08:00
bbbugg	ebf5fb1ff9	fix previous "deplymentName" to "deploymentName"	2025-03-07 16:41:04 +08:00
bbbugg	e0b554fbe5	Add the "deploymentName" parameter in the Model List environment variable	2025-03-07 16:36:21 +08:00
bbbugg	008c7b5f67	Add the "deploymentName" parameter in the Model List environment variable	2025-03-07 16:35:33 +08:00
bbbugg	05a384edb3	Add the description of "DEEPSEEK_MODEL_LIST"	2025-03-07 16:21:46 +08:00
bbbugg	2ec4f03b07	Add the description of "DEEPSEEK_MODEL_LIST"	2025-03-07 16:20:28 +08:00
bbbugg	da04eef212	fix: customize logo not display in About page Fix customize logo not display in About page. Previously, custom icons were not displayed.	2025-03-05 20:48:53 +08:00