Open
Conversation
* try new build * improve
Co-authored-by: claude[bot] <41898282+claude[bot]@users.noreply.github.com> Co-authored-by: Claude Sonnet 4.5 <noreply@anthropic.com>
Replace `overflow: 'hidden'` with `overflowX: 'hidden', overflowY: 'auto'` on the topic list container so users can scroll through topics that exceed the viewport height on mobile devices. Closes #12029
Add end-user info on OpenAI Responses API call
### [Version 2.1.21](v2.1.20...v2.1.21) <sup>Released on **2026-02-08**</sup> #### 🐛 Bug Fixes - **misc**: Add end-user info on OpenAI Responses API call, enable vertical scrolling for topic list on mobile. <br/> <details> <summary><kbd>Improvements and Fixes</kbd></summary> #### What's fixed * **misc**: Add end-user info on OpenAI Responses API call, closes [#12134](#12134) ([72a85ac](72a85ac)) * **misc**: Enable vertical scrolling for topic list on mobile, closes [#12157](#12157) [#12029](#12029) ([bd4e253](bd4e253)) </details> <div align="right"> [](#readme-top) </div>
…ovider (#12190) * 🌐 chore: translate non-English comments to English in siliconcloud provider Co-Authored-By: Claude Sonnet 4.5 <noreply@anthropic.com> * ✅ test: update siliconcloud test to match translated error message Co-Authored-By: Claude Opus 4.6 <noreply@anthropic.com> --------- Co-authored-by: claude[bot] <41898282+claude[bot]@users.noreply.github.com> Co-authored-by: Claude Sonnet 4.5 <noreply@anthropic.com> Co-authored-by: arvinxx <arvinx@foxmail.com>
* refactor Notebook Executor * 🐛 fix: register Notebook tool in server runtime Notebook tool (lobe-notebook) was only registered on the client side, causing server-side tool calls to fail with "not implemented" error. - Add NotebookRuntimeService wrapping DocumentModel/TopicDocumentModel - Add notebook server runtime registration - Pass context to runtime methods for topicId passthrough - Add tests for NotebookRuntimeService and runtime registration Resolves LOBE-4880 Co-Authored-By: Claude Opus 4.6 <noreply@anthropic.com> --------- Co-authored-by: Claude Opus 4.6 <noreply@anthropic.com>
### [Version 2.1.22](v2.1.21...v2.1.22) <sup>Released on **2026-02-08**</sup> #### 🐛 Bug Fixes - **misc**: Register Notebook tool in server runtime. <br/> <details> <summary><kbd>Improvements and Fixes</kbd></summary> #### What's fixed * **misc**: Register Notebook tool in server runtime, closes [#12203](#12203) ([be6da39](be6da39)) </details> <div align="right"> [](#readme-top) </div>
* fix editor issue * add virtual block plugin * snapshot case * fix task Render issue
### [Version 2.1.23](v2.1.22...v2.1.23) <sup>Released on **2026-02-08**</sup> #### 🐛 Bug Fixes - **misc**: Fix editor content missing when send error. <br/> <details> <summary><kbd>Improvements and Fixes</kbd></summary> #### What's fixed * **misc**: Fix editor content missing when send error, closes [#12205](#12205) ([ee7ae5b](ee7ae5b)) </details> <div align="right"> [](#readme-top) </div>
### [Version 2.1.23](v2.1.22...v2.1.23) <sup>Released on **2026-02-08**</sup> #### 🐛 Bug Fixes - **misc**: Fix editor content missing when send error. <br/> <details> <summary><kbd>Improvements and Fixes</kbd></summary> #### What's fixed * **misc**: Fix editor content missing when send error, closes [#12205](#12205) ([ee7ae5b](ee7ae5b)) </details> <div align="right"> [](#readme-top) </div>
💄 style: update i18n Co-authored-by: canisminor1990 <17870709+canisminor1990@users.noreply.github.com>
…on-client-ipc and packages/edge-config (#11926) Co-authored-by: claude[bot] <41898282+claude[bot]@users.noreply.github.com> Co-authored-by: Claude Sonnet 4.5 <noreply@anthropic.com>
* 🐛 fix: use custom avatar for group chat in sidebar When a group chat has a custom avatar set, the sidebar was always showing the member composition avatar instead. This fix: - Queries chatGroups.avatar and chatGroups.backgroundColor in HomeRepository - Prioritizes custom avatar (string) over member avatars (array) in data layer - Replaces GroupAvatar with AgentGroupAvatar in AgentGroupItem for proper avatar type detection (custom vs member composition) Closes LOBE-4883 * ✅ test: add DB tests for group chat custom avatar in sidebar Add 6 test cases covering the custom avatar fix for chat groups: getSidebarAgentList: - should return custom avatar when chat group has one set - should return member avatars when chat group has no custom avatar - should prioritize custom avatar over member avatars searchAgents: - should return custom avatar for chat groups with custom avatar in search - should return member avatars for chat groups without custom avatar in search - should prioritize custom avatar over member avatars in search
### [Version 2.1.23](v2.1.22...v2.1.23) <sup>Released on **2026-02-09**</sup> #### 🐛 Bug Fixes - **swr**: Prevent useActionSWR isValidating from getting stuck. - **misc**: Fix editor content missing when send error, use custom avatar for group chat in sidebar. #### 💄 Styles - **misc**: Update i18n. <br/> <details> <summary><kbd>Improvements and Fixes</kbd></summary> #### What's fixed * **swr**: Prevent useActionSWR isValidating from getting stuck, closes [#12059](#12059) ([8877bc1](8877bc1)) * **misc**: Fix editor content missing when send error, closes [#12205](#12205) ([ee7ae5b](ee7ae5b)) * **misc**: Use custom avatar for group chat in sidebar, closes [#12208](#12208) ([31145c9](31145c9)) #### Styles * **misc**: Update i18n, closes [#12025](#12025) ([c12d022](c12d022)) </details> <div align="right"> [](#readme-top) </div>
* improve auto workflow * add auto workflow
…ies for identity when no entries present (#12217)
Co-authored-by: claude[bot] <41898282+claude[bot]@users.noreply.github.com> Co-authored-by: Claude Sonnet 4.5 <noreply@anthropic.com>
* 🌐 chore: translate non-English comments to English in src/libs Co-Authored-By: Claude Sonnet 4.5 <noreply@anthropic.com> * 🐛 fix: update test to match translated error message --------- Co-authored-by: claude[bot] <41898282+claude[bot]@users.noreply.github.com> Co-authored-by: Claude Sonnet 4.5 <noreply@anthropic.com> Co-authored-by: arvinxx <arvinx@foxmail.com>
✨ feat: add Straico model provider integration and environment variable support
- Add gemini-3.1-pro-preview to Google, Vertex AI, and LobeHub providers - Add thinkingLevel3 extend param type (low/medium/high) - Create ThinkingLevel3Slider component for 3-level thinking control - Fix thinkingLevel2/3 not passing values to API due to form field name mismatch - Add medium to GoogleThinkingLevel and ChatStreamPayload thinkingLevel types - Update planCardModels to use gemini-3.1-pro-preview
#### 💻 Change Type <!-- For change type, change [ ] to [x]. --> - [ ] ✨ feat - [ ] 🐛 fix - [ ] ♻️ refactor - [X] 💄 style - [ ] 👷 build - [ ] ⚡️ perf - [ ] ✅ test - [ ] 📝 docs - [ ] 🔨 chore #### 🔗 Related Issue Closes #10346 <!-- Link to the issue that is fixed by this PR --> <!-- Example: Fixes #xxx, Closes #xxx, Related to #xxx --> #### 🔀 Description of Change 1. 更新的文生图，图生图模型列表，`z-image` `wan2.5` `wan2.6` `qwen-image-plus/max` `qwen-image-edit-plus/max` 2. 新增 `image2image` endpoint，为老版本图生图模型进行兼容 3. 默认使用 `multimodal-generation` endpoint（新模型目前调研下来都是用这个了，同时支持图生图和文生图） 4. 支持多区域 Dashscope URL，跟随 baseUrl 参数，自动切分 `/compatible-mode/v1` 默认北京区域 北京 https://dashscope.aliyuncs.com 新加坡 https://dashscope-intl.aliyuncs.com 弗吉尼亚 https://dashscope-us.aliyuncs.com |Endpoint|| |-|-| |`multimodal-generation`|<img width="826" height="547" alt="image" src="https://github.com/user-attachments/assets/38206851-94bc-48cc-8a57-24ed7155782f" /><img width="521" height="383" alt="image" src="https://github.com/user-attachments/assets/40fe0ed0-35fd-443d-868f-3ae2c27352f9" /><img width="681" height="557" alt="image" src="https://github.com/user-attachments/assets/8101b0f1-81c8-4892-a6e2-b51b5b0e0235" />| |`text2image`|<img width="600" height="564" alt="image" src="https://github.com/user-attachments/assets/39e82a4f-5305-4f30-ae4d-e5339f401e6d" />| <!-- Thank you for your Pull Request. Please provide a description above. --> #### 🧪 How to Test <!-- Please describe how you tested your changes --> <!-- For AI features, please include test prompts or scenarios --> - [ ] Tested locally - [ ] Added/updated tests - [ ] No tests needed #### 📸 Screenshots / Videos <!-- If this PR includes UI changes, please provide screenshots or videos --> | Before | After | | ------ | ----- | | ... | ... | #### 📝 Additional Information ref: https://help.aliyun.com/zh/model-studio/newly-released-models ref: https://bailian.console.aliyun.com/cn-beijing/?tab=doc#/doc/?type=model&url=2987148 <!-- Add any other context about the Pull Request here. --> <!-- Breaking changes? Migration guide? Performance impact? --> ## Summary by Sourcery Extend Qwen image generation support to cover new text-to-image and image-to-image models while routing legacy models via dedicated text2image/image2image endpoints and defaulting other models to the multimodal-generation API. New Features: - Add model metadata and configuration for new Qwen image models including Z-Image Turbo, Qwen Image Edit Max/Plus, Qwen Image Max/Plus, and Wanxiang 2.5/2.6 variants. - Introduce explicit handling of legacy text-to-image and image-to-image Qwen models via separate async text2image and image2image endpoints. Enhancements: - Update the Qwen image creation flow to prefer the multimodal-generation endpoint for newer models and improve error messaging and logging across image workflows. - Reformat select Qwen chat model descriptions for consistency without changing behavior. Tests: - Adjust Qwen image creation tests to align with the new multimodal-generation behavior and removed strict input validation on qwen-image-edit-specific image URL requirements.
* add eval benchmark database * fix types * remove regions
fix: fix embdding chunk_size limit for qwen apply suggestion Co-authored-by: sourcery-ai[bot] <58596630+sourcery-ai[bot]@users.noreply.github.com> fix: fix embdding chunk_size limit for qwen fix: fix embdding chunk_size limit for qwen
* ✨ feat: 添加 Gemini 3.1 Pro Preview 模型及其相关参数 * ✨ feat: 更新 Anthropic 模型 * ✨ feat: 移除过时的 Gemini 2.5 Flash 和 Imagen 4 预览模型 * ✨ feat: 添加 Qwen3 Coder Next 模型并更新 Anthropic 测试用例中的模型版本
…2400) contentBlocksToString() was prepending APP_URL via urlJoin() to item.data, but item.data already contained the full URL after processContentBlocks() uploaded to S3. This caused URLs like: https://example.com/https://example.com/f/uuid Co-authored-by: Claude Opus 4.6 <noreply@anthropic.com>
style: add `qwen3.5` series support
…gic (#12375) ✨ feat: add Claude Sonnet 4.6 model and enhance adaptive thinking logic
Co-authored-by: claude[bot] <41898282+claude[bot]@users.noreply.github.com> Co-authored-by: Claude Sonnet 4.5 <noreply@anthropic.com>
👷 chore: enable consistent-type-imports ESLint rule and fix violations
…IA NIM (#12333) * ✨ feat(nvidia): add interleaved thinking support with new reasoning models - Add MiniMax-M2.1, DeepSeek V3.2, GLM-4.7, GLM-5, Kimi K2.5 to NVIDIA model bank - Add reasoning conversion for interleaved thinking mode - Add tests for GLM-5 and DeepSeek V3.2 thinking * ♻️ refactor(nvidia): simplify payload handling logic - Remove redundant THINKING_MODELS and INTERLEAVED_THINKING_MODELS sets - Apply reasoning -> reasoning_content conversion for all NVIDIA models - Apply thinking -> chat_template_kwargs conversion based on user input only - Let API decide if model supports the parameters instead of client-side filtering * ♻️ refactor(nvidia): add preserved thinking support with model-specific params
…rovider (#12383) Co-authored-by: claude[bot] <41898282+claude[bot]@users.noreply.github.com> Co-authored-by: Claude Sonnet 4.6 <noreply@anthropic.com>
Only 4 checkouts truly need full git history (tag operations, branch sync). The remaining 18 occurrences were used in build/lint/test jobs that only need the current commit. Also removed redundant fetch-tags: true where fetch-depth: 0 already implies full tag fetch.
* improve total fix page size issue fix error message handler fix eval home page try to fix batch run agent step issue fix run list fix dataset loading fix abort issue improve jump and table column fix error streaming try to fix error output in vercel refactor qstash workflow client improve passK add evals to proxy refactor metrics try to fix build refactor tests improve detail page fix passK issue improve eval-rubric fix types support passK fix type update fix db insert issue improve dataset ui improve run config finish step limit now add step limited 100% coverage to models add failed tests todo support interruptOperation fix lint improve report detail improve pass rate improve sort order issue fix timeout issue Update db schema 完整 case 跑通 update database improve error handling refactor to improve database 优化 test case 的处理流程 优化部分细节体验和实现 基本完成 Benchmark 全流程功能 优化 run case 展示 优化 run case 序号问题 优化 eval test case 页面 新增 eval test 模式 新增 dataset 页面 update schema support finish create test run fix update improve import exp refactor data flow improve import workflow rubric Benchmark detail 页面 improve import ux update schema finish eval home page add eval workflow endpoint implement benchmark run model refactor RAG eval implement backend update db schema update db migration init benchmark * support rerun error test case * fix tests * fix tests
## Summary Merge latest changes from main into canary. ## Changes - Merge branch main into canary via codex/merge-main-into-canary-20260221 - Resolve one merge conflict in packages/model-bank/src/types/aiModel.ts by keeping both ModelParamsSchema and VideoModelParamsSchema imports ## Summary by Sourcery Update NVIDIA provider to support preserved thinking and reasoning_content for new reasoning-capable chat models and bump package version. New Features: - Add NVIDIA chat model entries for MiniMax-M2.1, DeepSeek V3.2, GLM-4.7, GLM-5, and Kimi K2.5 with reasoning support. Enhancements: - Extend NVIDIA runtime payload handling to map reasoning to reasoning_content and to translate thinking into either thinking or enable_thinking/clear_thinking depending on model capabilities. - Refine NVIDIA provider tests to cover GLM preserved thinking behavior and reasoning_content conversion across models. Build: - Bump package version from 2.1.31 to 2.1.32.
This release includes **82 commits** and **854 changed files**. Key updates are below. ### 🚀 New Features and Enhancements - Added **Agent Benchmark** support for more systematic agent performance evaluation. - Introduced the **video generation** feature end-to-end, including entry points, sidebar “new” badge support, and skeleton loading for topic switching. - Expanded memory capabilities: support for memory effort/tool permission configuration and improved timeout calculation for memory analysis tasks. - Added desktop editor support for image upload via file picker. ### 🤖 Models and Provider Expansion - Added a new provider: **Straico**. - Added/updated support for: - Claude Sonnet 4.6 - Gemini 3.1 Pro Preview - Qwen3.5 series - Grok Imagine (`grok-imagine-image`) - MiniMax 2.5 - Added related i18n copy and model parameter adaptations. ### 🖥️ Desktop Improvements - Integrated `electron-liquid-glass` (macOS Tahoe). - Improved DMG background assets and desktop release workflow. ### 🛠️ Stability, Security, and UX Fixes - Fixed multiple video generation pipeline issues: precharge refund handling, webhook token verification, pricing parameter usage, asset cleanup, and type safety. - Fixed `sanitizeFileName` path traversal risks and added unit tests. - Fixed MCP media URL generation with duplicated `APP_URL` prefix. - Fixed Qwen3 embedding failures caused by batch-size limits. - Fixed multiple UI/interaction issues, including mobile header agent selector/topic count, ChatInput scrolling behavior, and tooltip stacking context. - Fixed missing `@napi-rs/canvas` native bindings in Docker standalone builds. - Improved GitHub Copilot authentication retry behavior and response error handling in edge cases. ### 🙏 Thanks to Committers Huge thanks to these contributors (alphabetical): @AmAzing129 @Coooolfan @Innei @ONLY-yours @Zhouguanyang @arvinxx @eaten-cake @hezhijie0327 @nekomeowww @rdmclin2 @rivertwilight @sxjeru @tjx666
…nversation (#12410) Co-authored-by: claude[bot] <41898282+claude[bot]@users.noreply.github.com> Co-authored-by: Claude Sonnet 4.6 <noreply@anthropic.com>
This file contains hidden or bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
Sign up for free
to subscribe to this conversation on GitHub.
Already have an account?
Sign in.
19 participants
Add this suggestion to a batch that can be applied as a single commit.This suggestion is invalid because no changes were made to the code.Suggestions cannot be applied while the pull request is closed.Suggestions cannot be applied while viewing a subset of changes.Only one suggestion per line can be applied in a batch.Add this suggestion to a batch that can be applied as a single commit.Applying suggestions on deleted lines is not supported.You must change the existing code in this line in order to create a valid suggestion.Outdated suggestions cannot be applied.This suggestion has been applied or marked resolved.Suggestions cannot be applied from pending reviews.Suggestions cannot be applied on multi-line comments.Suggestions cannot be applied while the pull request is queued to merge.Suggestion cannot be applied right now. Please check back later.
See Commits and Changes for more details.
Created by
pull[bot] (v2.0.0-alpha.4)
Can you help keep this open source service alive? 💖 Please sponsor : )