Version 0.2.3

🚀 主要新功能

📝 Notion MCP服务器支持

• 新增Notion MCP服务器集成，支持与Notion工作区的无缝连接
• 提供完整的Notion文档操作能力

🐙 GitHub MCP集成

• 集成GitHub MCP服务，支持代码仓库管理
• 提供GitHub API的完整访问能力

🔧 MCP工具系统优化

• 新增多个MCP服务支持，扩展工具生态
• 支持公共MCP测试和工具缓存机制
• MCP搜索支持托管和本地两种部署类型
• MCP SSE消息传输无需密钥验证
• 新增MCP工具列表功能

💰 计费系统更新

🎯 豆包模型定价支持

• 新增豆包1-6模型的条件定价支持
• 优化计费策略，提供更灵活的定价方案

🛠️ 技术改进

📊 Redis缓存优化

• 新增Redis键前缀支持

🐛 问题修复

• 修复Gemini function call name空指针异常

Version 0.2.2

v0.2.2

chore: remove unused sql (#264)

Version 0.2.1

Feat:

• mcp proxy pannel
• channel sets support
• model sets

Fix:

• log show detail

Version 0.2.0

Feat:

• Support built-in mcp server
• Support sora video generation model
• Web management panel
• Model plugin support (cache, web search...)

Version 0.1.8

Release Notes

Features

• Image Support:
  • Image edit mode implementation (#159, #161)
  • Image usage tracking support (#153)
  • Batch patch image URL to base64 conversion (#152)
• Audio & Speech:
  • Fixed audio opus duration handling (#144)
  • Resolved audio multi-time issues (#145)
• MCP (Model Control Protocol) Enhancements:
  • Streamable HTTP MCP support (#142)
  • Group custom MCP support (#141)
  • OpenAPI MCP server and SSE MCP proxy (#137)
• Embedding & Models:
  • Jina embed support (#146)
• API Improvements:
  • Added retry delay when using same channel (#155)
  • Channel type constant implementation (#156)
  • Create token API with ignore exist parameter (#133)
  • Get log with code functionality (#157)

Fixes

• Image Processing:
  • Fixed image edit mode check (#161)
  • Fixed summary image input tokens field name (#160)
• Model Integrations:
  • Fixed Claude raw endpoint SSE (#138)
  • Ignored Claude unused responses (#139)
  • Fixed Gemini tool functionality (#132)
• Data Handling:
  • Fixed multi splitter heads (#143)
  • Fixed Ali STT usage tracking (#149)

Other Changes

• Usage Tracking:
  • STT (Speech-to-Text) usage tracking (#148)
  • Reused usage field implementation (#150)
• Documentation:
  • Fixed typo in README CN (#158)
• Deprecations:
  • Deprecated front log query functionality (#147)
• Dependency Updates:
  • Bumped Go MCP SDK (#151)

Version 0.1.8-beta.3 (Prerelease)

v0.1.8-beta.3

fix: summary image input tokens filed name (#160)

Version 0.1.8-beta.1 (Prerelease)

v0.1.8-beta.1

feat: retry delay when suing same channel (#155)

Version 0.1.7

Features

• Error Monitoring: Panic detection and notification system (#129)
• Database Optimization:
  • Added unique index with non-null constraint (#125)
• Search Integrations:
  • Ali web search support (#118)
  • Doubao bot usage tracking (#116)

Fixes

• API Handling:
  • Fixed unsupported error status codes for OpenAI tools (#127)
  • Adjusted VertexAI token expiration time to 30 minutes (#126)
• Third-Party Services:
  • Resolved nil pointer dereference in Doubao (#128)
  • Fixed GitHub token permission configuration (#119)
• Search & Tools:
  • Corrected summary web search functionality (#120)
• Token Management:
  • Fixed token amount calculation logic (#122)

Chores

• Dependency Updates:
  • Bumped AWS Bedrockruntime (#113, #109)
  • Updated gin-contrib/cors to v1.7.5 (#112)
  • Upgraded gin-contrib/gzip to v1.2.3 (#114)
  • Updated AWS credentials library (#115)
  • Bumped golang.org/x/sync to v0.13.0 (#117)
  • Upgraded cloud.google.com/go/iam to v1.5.0 (#110)
  • Bumped Go module dependencies (#123)

Version 0.1.6

Features

• Notification System:
  • Request ID notification support (#108)
  • Detailed 429 rate limit alerts (#107)
  • Group balance alerts with timezone support (#104)
• Dashboard Enhancements:
  • Timezone localization for chart data (#104)
  • Token usage summary tables (#95, #101)
  • Sortable usage metrics (#105)
• API Improvements:
  • Channel type naming support (#98)
  • Relay mode validation (#99)
• Billing System:
  • Timezone-aware token usage calculations (#111)

Fixes

• Data Handling:
  • Fix empty time value handling (#102)
  • Corrected usage amount sorting (#106)
  • PostgreSQL string aggregation fix (#94)
• API Handling:
  • Improved 401 error handling (#97)
  • SealOS balance synchronization fix (#100)
• Billing:
  • Timezone adjustments for billing data (#111)

Chores

• Dependencies:
  • Bump AWS BedrockRuntime SDK (#109)
  • Update Google IAM to v1.5.0 (#110)
  • Upgrade AWS credentials package (#96)
  • Update Google API client (#78)
• Code Quality:
  • Added request ID tracing (#108)
  • Improved rate limit diagnostics (#107)

Infrastructure

• Local timezone default configuration (#111)
• Enhanced billing cache stability (#100)

Version 0.1.5

Features

• Log Management: Batch log cleaning with optimized performance (#90, #89, #76)
• Database Optimization: Asynchronous log index creation & vacuum logs (#85, #84)
• Dashboard Enhancements: Timestamp query support & token usage statistics (#83, #82, #69)
• Security: IP group detection and blocking (#79)
• Model Configurations: Group model configuration support (#70)
• API Improvements:
  • VertexAI Claude cache usage tracking (#68)
  • Claude extended tool type support (#63)
  • Basic AIProxy HTTP handler (#64)
  • Channel parameter support (#77)
• Monitoring:
  • TTFB (Time to First Byte) recording (#73)
  • RPM/TPM metric optimizations (#81)

Fixes

• Data Cleanup:
  • Concurrent cleanup fix (#93)
  • SQL query optimizations (#92, #86)
  • Decimal summation for used amounts (#88)
• API Handling:
  • VertexAI Claude stream mode input usage (#65)
  • Gemini image detection (#52)
  • Azure API version defaults (#42)
• Logging:
  • RequestID exclusion from log indexes (#91)
  • Time truncation adjustments (#87)
• Billing:
  • PDF price parsing (#37)
  • Token expression fixes (#27)

Performance

• Log index optimizations (#91, #74)
• Database query optimizations (#71)
• Cleanup process performance improvements (#89, #86)

Chores

• Documentation:
  • Updated usage documentation (#80)
  • Swagger API docs implementation (#50, #75)
  • Listen address customization (#48)
• Dependencies:
  • JWT library bump to v5.2.2 (#66)
  • AWS credentials dependency update (#72)
• Code Quality:
  • Removed unused packages (#36)
  • SQL query optimizations (#71)
  • Error handling improvements (#23, #28)

Infrastructure

• Memory limits and header constraints (#43)
• Token billing cache support (#33)
• Embed tokenization optimization (#34)