"fix_deep_stream_interrupted_and_timeout"

"fix_retry_timeout_for_cloudflare_524"

"fix_backend_retry_logic"

feat: 实现反检测速率限制器，模拟人类行为模式避免被 Google 封禁

feat: 实现智能速率限制器，支持自适应超时、队列管理和监控指标

fix: 修复速率限制器死锁风险、临时文件清理兼容性和图片目录初始化问题

fix(P0/P1/P2): 添加 Cookie 持久化、临时文件清理、速率限制和移除 API 密钥暴露

update: 同步最新代码与配置

update: 更新聊天服务、客户端连接池和辅助工具

update: 更新前端样式、模型、聊天服务和客户端代码

修复流式输出错乱问题

:bug: Update function call format to avoid potential leak issues (#96)

:sparkles: Enable real-time streaming responses and completely solve the issue with reusable sessions. (#95)

refactor: Optimize performance by reducing token usage and speed up model response time. (#89)

feat: Add support for custom Gemini models and model loading strategies (#86)

:sparkles: Update the /v1/responses endpoint (#75)

:sparkles: Optimize Response API, Link Handling, and Add File Upload Support (#73)

:sparkles: Add proxy support and fix bugs (#56)

:sparkles: Fix bugs and add an option to schedule database cleanup. (#49)

:sparkles: Add tool call support and fix image input and output (#47)

:sparkles: Add retrying to fix ModelInvalid error (#23)

:bug: Fix tagging when using XML (#18)

:sparkles: Multi-segment text merging, ultra-long message splitting, xml prompt, tag, session, and token calculation optimization. (#16)

:recycle: Refactor history sanitizing (#12)

:bug: Fix session persistence, when request contains <think> (#10)

:sparkles: Implement Gemini client pool (#7)

:bug: Fix LMDB history mismatch (#4)

:pencil2: Fix typo in method name (#3)

:bug: Fix lmdb health check

:sparkles: Add hash for model name and fix bugs

:bug: Fix broken multiple line streaming

:pencil: Fix docs

:sparkles: Add support for multi-round conversation

:bug: Fix bugs and optimize file uploading

:construction: Refactored and fix bugs

:construction: Refactored with new structure