Cherry Studio Files

v1.5.4

Summary

1. New service provider: AWS Bedrock
2. Rich text editor support: Improved prompt editing experience with enhanced formatting options
3. Drag-and-drop input optimization: Supports dragging text directly from other software into the input box, simplifying content input
4. Parameter adjustment enhancements: Added Top-P and Temperature toggle settings for more flexible model control
5. Background translation tasks: Translation tasks now support background execution, improving multitasking efficiency
6. New model support: Added Qwen-MT, Qwen3235BA22Bthinking, and sonar-deep-research models to expand reasoning capabilities
7. Improved inference stability: Fixed issues where some models failed to output reasoning content, ensuring complete results
8. Mistral model fix: Resolved issues preventing the Mistral model from functioning, restoring its inference capability
9. Backup directory optimization: Supports relative path input, improving backup configuration flexibility
10. Data export adjustments: Added a toggle for exporting referenced content, providing finer export control
11. Text stream integrity: Fixed text loss at the end of streams to ensure complete output
12. Memory leak fixes: Optimized code logic to resolve memory leaks and improve runtime stability
13. Simplified embedding models: Reduced configuration complexity for embedding models, improving usability
14. MCP Tool long-running tasks: Enhanced stability for the MCP tool, supporting prolonged task execution
15. Settings page optimization: Improved layout for a better user experience

What's Changed

• fix(AiProvider): remove unnecessary middleware removal logic for… by @DeJeune in https://github.com/CherryHQ/cherry-studio/pull/8437
• Feat/vertex-claude-support by @DeJeune in https://github.com/CherryHQ/cherry-studio/pull/7564
• fix(mcp-tools): enhance tool lookup logic to support partial matches by @DeJeune in https://github.com/CherryHQ/cherry-studio/pull/8473
• chore(deps): update vite to rolldown-vite by @beyondkmp in https://github.com/CherryHQ/cherry-studio/pull/8460
• refactor(ThinkChunkMiddleware): remove reasoning check for improved logic clarity by @DeJeune in https://github.com/CherryHQ/cherry-studio/pull/8505
• chore: ignore qwen-code settings by @alephpiece in https://github.com/CherryHQ/cherry-studio/pull/8509
• chore: Update channel improve by @beyondkmp in https://github.com/CherryHQ/cherry-studio/pull/8501
• fix: aihubmix provider generate image logic by @DDU1222 in https://github.com/CherryHQ/cherry-studio/pull/8478
• refactor(MessageEditor): lower minrows to 1, add padding by @alephpiece in https://github.com/CherryHQ/cherry-studio/pull/8434
• feat: use code editor in prompt settings by @alephpiece in https://github.com/CherryHQ/cherry-studio/pull/8456
• fix/mcp-bug by @DeJeune in https://github.com/CherryHQ/cherry-studio/pull/8518
• feat: support Relative Path Input for Backup Directory by @beyondkmp in https://github.com/CherryHQ/cherry-studio/pull/8471
• feat(MCPSettings): enhance JSON loading to inherit all MCPServer fields by @vaayne in https://github.com/CherryHQ/cherry-studio/pull/8498
• chore(i18n): forced nested structure to support i18n ally by @EurFelux in https://github.com/CherryHQ/cherry-studio/pull/8457
• refactor(useSmoothStream): optimize chunk handling and state management by @MyPrototypeWhat in https://github.com/CherryHQ/cherry-studio/pull/8514
• fix: call tool bug by @DeJeune in https://github.com/CherryHQ/cherry-studio/pull/8526
• fix(i18n): standardize i18n usage by @EurFelux in https://github.com/CherryHQ/cherry-studio/pull/8525
• fix: set consolelog eslint to error when in prci lint check by @0xfullex in https://github.com/CherryHQ/cherry-studio/pull/8532
• refactor(Knowledge): simplify dimension settings, support base migration by @alephpiece in https://github.com/CherryHQ/cherry-studio/pull/8315
• Feat/long run mcp by @DeJeune in https://github.com/CherryHQ/cherry-studio/pull/8499
• fix: [#8531] by @Pleasurecruise in https://github.com/CherryHQ/cherry-studio/pull/8535
• feat(translate): add Ukrainian by @EurFelux in https://github.com/CherryHQ/cherry-studio/pull/8528
• feat(models): add support for new Qwen model and update effort ratio by @DeJeune in https://github.com/CherryHQ/cherry-studio/pull/8537
• fix(i18n): add i18n for data restore by @EurFelux in https://github.com/CherryHQ/cherry-studio/pull/8533
• feat(export): citation export control by @GeorgeDong32 in https://github.com/CherryHQ/cherry-studio/pull/8519
• Fix/qwen-mt by @DeJeune in https://github.com/CherryHQ/cherry-studio/pull/8527
• feat(mcp): add shouldConfig flag and i18n support for builtin MCPServer description by @EurFelux in https://github.com/CherryHQ/cherry-studio/pull/8440
• refactor(OpenAIApiClient, models, ThinkingButton): streamline reasoning model checks and enhance support for Perplexity models by @DeJeune in https://github.com/CherryHQ/cherry-studio/pull/8487
• feat(models): add Grok 4 model and update reasoning regex by @GeorgeDong32 in https://github.com/CherryHQ/cherry-studio/pull/8545
• feat(assistants): place copied assistant after the original one by @EurFelux in https://github.com/CherryHQ/cherry-studio/pull/8557
• perf(i18n): improve performance when getting i18n text by @EurFelux in https://github.com/CherryHQ/cherry-studio/pull/8548
• fix: pangu-pro-moe not reasoning by @Pleasurecruise in https://github.com/CherryHQ/cherry-studio/pull/8572
• fix(ModelEditContent): preserve model price settings by @EurFelux in https://github.com/CherryHQ/cherry-studio/pull/8560
• feat(contentsearch): optimize searchbar UI by @GeorgeDong32 in https://github.com/CherryHQ/cherry-studio/pull/8556
• feat(inputbar): drop text into inputbar by @EurFelux in https://github.com/CherryHQ/cherry-studio/pull/8579
• fix: add isPathInside functionality to check path relationships by @beyondkmp in https://github.com/CherryHQ/cherry-studio/pull/8590
• feat: add Top-P parameter toggle with default enabled state and improved UI styling by @lihqi in https://github.com/CherryHQ/cherry-studio/pull/8137
• feat(installer): add architecture compatibility check to NSIS installer by @beyondkmp in https://github.com/CherryHQ/cherry-studio/pull/8587
• fix(LocalBackup): streamline local backup relative directory handling by @beyondkmp in https://github.com/CherryHQ/cherry-studio/pull/8595
• feat(models): add support for Zhipu model and enhance reasoning checks by @DeJeune in https://github.com/CherryHQ/cherry-studio/pull/8609
• fix(WebSearchSettings): responsive table layout by @EurFelux in https://github.com/CherryHQ/cherry-studio/pull/8606
• fix(think-tool): update prompt handling logic and improve comments by @DeJeune in https://github.com/CherryHQ/cherry-studio/pull/8538
• fix: show something reasonable when missing embedding model by @EurFelux in https://github.com/CherryHQ/cherry-studio/pull/8600
• feat: improve builtin mcp sever display style by @kovsu in https://github.com/CherryHQ/cherry-studio/pull/8470
• feat(translate): support background execution of translation tasks by @EurFelux in https://github.com/CherryHQ/cherry-studio/pull/7892
• fix: no /no_think for qwen3 anymore if provider is dashscope by @EurFelux in https://github.com/CherryHQ/cherry-studio/pull/8616
• refactor(ModelEditContent): enhance model capabilities management and… by @DeJeune in https://github.com/CherryHQ/cherry-studio/pull/8562
• fix: reset pyodide globals between runs by @alephpiece in https://github.com/CherryHQ/cherry-studio/pull/8620
• fix/export-roletext-level by @GeorgeDong32 in https://github.com/CherryHQ/cherry-studio/pull/8634
• fix: change jschardet to chardet by @Pleasurecruise in https://github.com/CherryHQ/cherry-studio/pull/8577
• perf: part of memory leak by @EurFelux in https://github.com/CherryHQ/cherry-studio/pull/8619
• integrate AWS Bedrock API by @silenceboychen in https://github.com/CherryHQ/cherry-studio/pull/8383
• fix: resolve issue of top navigation bar being obscured by miniapp by @YinsenHo in https://github.com/CherryHQ/cherry-studio/pull/8517
• fix: remove compareVersions utility and update version check logic in AboutSettings by @beyondkmp in https://github.com/CherryHQ/cherry-studio/pull/8640
• refactor(aiCore): extract MixedBaseAPIClient as abstract class by @EurFelux in https://github.com/CherryHQ/cherry-studio/pull/8618
• feat: add support for Qwen 3-235B-A22B thinking model detection by @DeJeune in https://github.com/CherryHQ/cherry-studio/pull/8641
• fix(vite-rolldown): cannot parse pdf file by @beyondkmp in https://github.com/CherryHQ/cherry-studio/pull/8652
• fix(AppUpdater): simplify error logging and update version check logic by @beyondkmp in https://github.com/CherryHQ/cherry-studio/pull/8656
• feat: Support Cherry Studio as a Service (CSaaS) by @vaayne in https://github.com/CherryHQ/cherry-studio/pull/8098
• fix: apiserver display by @Pleasurecruise in https://github.com/CherryHQ/cherry-studio/pull/8669
• test: add tests for aiCore/middleware/utils by @farion1231 in https://github.com/CherryHQ/cherry-studio/pull/8645
• fix: update express dependency in package.json by @beyondkmp in https://github.com/CherryHQ/cherry-studio/pull/8677
• perf(ModelList): provider settings and model list responsiveness by @alephpiece in https://github.com/CherryHQ/cherry-studio/pull/8667
• fix(ModelList): stop propagation by @alephpiece in https://github.com/CherryHQ/cherry-studio/pull/8685
• refactor(ApiService): optimize memory search handling and improve error logging by @DeJeune in https://github.com/CherryHQ/cherry-studio/pull/8671
• feat: make API server default to closed/disabled by @vaayne in https://github.com/CherryHQ/cherry-studio/pull/8691
• fix: do not exit on emoji picker by @alephpiece in https://github.com/CherryHQ/cherry-studio/pull/8702
• refactor: update new zhipu ai dev docs website link by @tomsun28 in https://github.com/CherryHQ/cherry-studio/pull/8713
• feat(models): refine Qwen model support and token limits by @GeorgeDong32 in https://github.com/CherryHQ/cherry-studio/pull/8716
• fix(prompt): resolve variable replacement in function mode and add UI features by @KumaKorin in https://github.com/CherryHQ/cherry-studio/pull/6581
• feat: add multi-select mode wrapper for message component by @kovsu in https://github.com/CherryHQ/cherry-studio/pull/8653
• refactor: add feedback on saving assistant prompt by @alephpiece in https://github.com/CherryHQ/cherry-studio/pull/8726
• docs: update CLAUDE.md with current project requirements by @farion1231 in https://github.com/CherryHQ/cherry-studio/pull/8729
• feat(database): enable strict transaction durability for CherryStudio database by @beyondkmp in https://github.com/CherryHQ/cherry-studio/pull/8737
• fix(prompt): remove think tool by @EurFelux in https://github.com/CherryHQ/cherry-studio/pull/8733
• refactor: add a custom dynamic virtual list component by @alephpiece in https://github.com/CherryHQ/cherry-studio/pull/8711
• refactor(ApiService): comment out built-in tools import and usage by @DeJeune in https://github.com/CherryHQ/cherry-studio/pull/8744
• feat: add smooth transition animation to narrow mode toggle by @kovsu in https://github.com/CherryHQ/cherry-studio/pull/8740
• fix: flush redux persist data when app quit and update by @beyondkmp in https://github.com/CherryHQ/cherry-studio/pull/8741
• perf: improve model list loading by @alephpiece in https://github.com/CherryHQ/cherry-studio/pull/8751
• fix: conditional auto-focus based on last focused component by @kovsu in https://github.com/CherryHQ/cherry-studio/pull/8739
• perf: shiki code block by @alephpiece in https://github.com/CherryHQ/cherry-studio/pull/8763
• fix(WindowService): comment out dock icon hiding for macOS when closing to tray due to cmd+h behavior issue by @beyondkmp in https://github.com/CherryHQ/cherry-studio/pull/8658
• feature/dmxapi_painting_custom_size by @jin-wang-c in https://github.com/CherryHQ/cherry-studio/pull/8689
• fix/release-sync-git_tag by @brucewang5638 in https://github.com/CherryHQ/cherry-studio/pull/8755
• chore(tsconfig): adjust the path order by @EurFelux in https://github.com/CherryHQ/cherry-studio/pull/8769
• feat(llm): add provider Poe by @EurFelux in https://github.com/CherryHQ/cherry-studio/pull/8758
• fix(MCP): add missing /mcp suffix to TokenFlux sync URLs by @vaayne in https://github.com/CherryHQ/cherry-studio/pull/8777
• perf: model select popup by @alephpiece in https://github.com/CherryHQ/cherry-studio/pull/8766
• fix(Inputbar): input bar auto focus by @EurFelux in https://github.com/CherryHQ/cherry-studio/pull/8756
• refactor(ModelList): improve group style by @EurFelux in https://github.com/CherryHQ/cherry-studio/pull/8761
• Chore/issue template by @EurFelux in https://github.com/CherryHQ/cherry-studio/pull/8789
• refactor(ManageModelsPopup): better animation and feedback by @alephpiece in https://github.com/CherryHQ/cherry-studio/pull/8797
• feat(ProviderSettings): add more api options for non-system providers by @EurFelux in https://github.com/CherryHQ/cherry-studio/pull/7794
• fix(models): add 'qwen-plus-latest' entry and update regex patterns for model token limits by @DeJeune in https://github.com/CherryHQ/cherry-studio/pull/8804
• refactor: align model list buttons, use lucide icons by @alephpiece in https://github.com/CherryHQ/cherry-studio/pull/8803
• fix(OpenAIApiClient): fix multiple reasoning content handling by @EurFelux in https://github.com/CherryHQ/cherry-studio/pull/8767
• feat(miniapp): add banner attribute to google login tip by @kovsu in https://github.com/CherryHQ/cherry-studio/pull/8813
• refactor: update theme handling in TabContainer and Sidebar components by @beyondkmp in https://github.com/CherryHQ/cherry-studio/pull/8816
• fix(s3): add volces.com to virtual host suffix whitelist by @GeorgeDong32 in https://github.com/CherryHQ/cherry-studio/pull/8824
• feat: enable additional GPU channel features and improve crash reportdetails in renderer by @beyondkmp in https://github.com/CherryHQ/cherry-studio/pull/8819
• refactor: align lucide icons in antd button, use more lucide icons by @alephpiece in https://github.com/CherryHQ/cherry-studio/pull/8805
• feat: support bypass proxy by @beyondkmp in https://github.com/CherryHQ/cherry-studio/pull/8791
• fix the query for agents with the same name is not fully displayed by @wfy-belief in https://github.com/CherryHQ/cherry-studio/pull/8826
• fix: better mcp tool match and feedback by @EurFelux in https://github.com/CherryHQ/cherry-studio/pull/8825
• feat: add OpenAI o3 model support with enhanced tool calling by @lukegalea in https://github.com/CherryHQ/cherry-studio/pull/8253
• refactor: animate auto get dimension by @alephpiece in https://github.com/CherryHQ/cherry-studio/pull/8831
• perf(ApiService): speed up api check by @EurFelux in https://github.com/CherryHQ/cherry-studio/pull/8830
• feat: disable mask closing for various popups across the application by @DeJeune in https://github.com/CherryHQ/cherry-studio/pull/8832
• refactor: health check timeout by @alephpiece in https://github.com/CherryHQ/cherry-studio/pull/8837
• feat(Markdown): enable github markdown alert by @alephpiece in https://github.com/CherryHQ/cherry-studio/pull/8842
• feat: mini window state management by @kovsu in https://github.com/CherryHQ/cherry-studio/pull/8834
• refactor: improve style for antd select virtual list scrollbar by @alephpiece in https://github.com/CherryHQ/cherry-studio/pull/8841
• fix(models): some qwen3 models cannot disable thinking by @EurFelux in https://github.com/CherryHQ/cherry-studio/pull/8854
• refactor(providers): support more provider to remove /no_think command for qwen3 by @EurFelux in https://github.com/CherryHQ/cherry-studio/pull/8855
• feat(model): support step models by @EurFelux in https://github.com/CherryHQ/cherry-studio/pull/8853
• fix(ProxyManager): handle optional currentProxy in system proxy check and log changes by @beyondkmp in https://github.com/CherryHQ/cherry-studio/pull/8865

New Contributors

• @lihqi made their first contribution in https://github.com/CherryHQ/cherry-studio/pull/8137
• @tomsun28 made their first contribution in https://github.com/CherryHQ/cherry-studio/pull/8713
• @brucewang5638 made their first contribution in https://github.com/CherryHQ/cherry-studio/pull/8755
• @lukegalea made their first contribution in https://github.com/CherryHQ/cherry-studio/pull/8253

Full Changelog: https://github.com/CherryHQ/cherry-studio/compare/v1.5.3...v1.5.4