DeepChat V0.3.4

[zerob13]

🚀 DeepChat 0.3.4 正式发布 | 重新定义你的 AI 对话体验！

—— 不再是简单的 ChatBot，而是你的自然语言 Agent 工具🌟

新功能

• 支持 TokenFlux.ai、更新豆包模型
• 全新启动画面 + 主题
• 悬浮按钮 JS 重写，支持多屏边界检测

优化

• Gemini 推理解析、模型配置、关闭内存占用
• 减少 IPC 调用、并行退出、原子化 provider 操作
• Markdown 转义、导入器修复

New

• TokenFlux.ai provider + updated Doubao models
• New splash screen with themes
• Floating button re-written in JS, multi-monitor aware

Improved

• Gemini reasoning & model fixes, memory leak on close
• Fewer IPC calls, faster shutdown, atomic provider ops
• Markdown escape fixes, importer tweaks

What's Changed

• fix: Correctly parse Gemini reasoning for both new thought field an… by @neoragex2002 in fix: Correctly parse Gemini reasoning for both new thought field an… #801
• fix: correct Gemini 2.5 Flash Image Preview model capabilities and token limits by @yyhhyyyyyy in fix: correct Gemini 2.5 Flash Image Preview model capabilities and token limits #802
• feat: add TokenFlux.ai provider support by @zerob13 in feat: add TokenFlux.ai provider support #804
• fix: optimize polling logic to prevent unnecessary IPC calls by @yyhhyyyyyy in fix: optimize polling logic to prevent unnecessary IPC calls #806
• fix: escape brackets in Markdown content to prevent parsing issues & refactor MessageBlockContent if branch by @Simon-He95 in fix: escape brackets in Markdown content to prevent parsing issues & refactor MessageBlockContent if branch #808
• fix memory when close window by @hllshiro in fix memory when close window #809
• Reorganize gemini model configs; Refine Gemini reasoning content parsing; Markdown rendering of fixed by @neoragex2002 in Reorganize gemini model configs; Refine Gemini reasoning content parsing; Markdown rendering of <a> fixed #807
• feat: refactor floating button with JavaScript-based drag and fix interaction issues by @yyhhyyyyyy in feat: refactor floating button with JavaScript-based drag and fix interaction issues #810
• Refactor/app lifecycle management by @hllshiro in Refactor/app lifecycle management #803
• perf: parallelize lifecycle hooks execution for faster app shutdown by @yyhhyyyyyy in perf: parallelize lifecycle hooks execution for faster app shutdown #811
• fix: resolve race condition in floating button drag-and-drop detection by @neoragex2002 in fix: resolve race condition in floating button drag-and-drop detection #813
• fix: resolve floating button multi-display boundary detection issue by @yyhhyyyyyy in fix: resolve floating button multi-display boundary detection issue #814
• Optimize/lifecycle actuator optimization by @hllshiro in Optimize/lifecycle actuator optimization #812
• perf: implement atomic provider operations to optimize performance by @yyhhyyyyyy in perf: implement atomic provider operations to optimize performance #815
• feat: update Doubao provider with new models by @yyhhyyyyyy in feat: update Doubao provider with new models #816
• fix: resolve application hang when quitting during startup by @yyhhyyyyyy in fix: resolve application hang when quitting during startup #817
• chore: fix DataImporter bug and some ux optimises by @zerob13 in chore: fix DataImporter bug and some ux optimises #818

Full Changelog: v0.3.3...v0.3.4

🔥 为什么选择 DeepChat？

✅ 商业友好：基于原版 Apache License 2.0 开源，无任何协议外的额外约束，面向开源。
✅ 开箱即用：极简配置，即刻开启你的智能对话之旅。
✅ 极致灵活：自由切换模型，自定义模型源，满足你多样化的对话和探索需求。
✅ 体验绝佳：LaTeX 公式渲染、代码高亮、Markdown 支持，模型对话从未如此顺畅。
✅ 持续进化：我们倾听用户反馈，不断迭代更新，为你带来更卓越的 AI 对话体验。

📥 立即体验未来

💬 反馈有礼：欢迎提交你的宝贵建议，加入 VIP 用户社群，与我们一同塑造 DeepChat 的未来！

---

This discussion was created from the release DeepChat V0.3.4.