 t0ng7u
|
8e3f9b1faa
🛡️ fix: prevent OOM on large/decompressed requests; skip heavy prompt meta when token count is disabled
|
hai 3 meses |
 Seefs
|
e1c7a4f41f
format: package name -> github.com/QuantumNous/new-api (#2017)
|
hai 5 meses |
 CaIon
|
6748b006b7
refactor: centralize logging and update resource initialization
|
hai 7 meses |
|
CaIon
|
e2037ad756
refactor: Introduce pre-consume quota and unify relay handlers
|
hai 7 meses |
|
CaIon
|
d9c1fb5244
feat: update MaxTokens handling
|
hai 8 meses |
|
CaIon
|
98952198bb
refactor: Introduce standardized API error
|
hai 9 meses |
 CaIon
|
eb265a55e1
✨ feat: enhance environment configuration and resource initialization
|
hai 9 meses |
|
CaIon
|
281054ff4c
🐛 fix: replace direct response body closure with common.CloseResponseBodyGracefully for improved error handling
|
hai 9 meses |
|
CaIon
|
3002659f47
✨ feat: add CloseResponseBodyGracefully function to handle HTTP response body closure
|
hai 9 meses |
 Xyfacai
|
b778cd2b23
refactor: message content 改成 any
|
hai 10 meses |
|
1808837298@qq.com
|
37a83ecc33
refactor: Centralize stream handling and helper functions in relay package
|
hai 1 ano |
|
1808837298@qq.com
|
f5e3063f33
feat: Improve embedding request handling and support across channels
|
hai 1 ano |
|
CalciumIon
|
195ab1fdd5
feat: add gemini tool_calls finish reason
|
hai 1 ano |
|
CalciumIon
|
90abe7f27d
fix: baidu max_output_tokens (#353)
|
hai 1 ano |
|
CalciumIon
|
02545e4856
fix: baidu max_output_tokens (close #353)
|
hai 1 ano |
|
CalciumIon
|
eb382d28ab
feat: update baidu
|
hai 1 ano |
|
CaIon
|
d1c8947851
fix: 规范claude返回格式
|
hai 1 ano |
|
1808837298@qq.com
|
626217fbd4
fix: 修复流模式错误扣费的问题 (close #95)
|
%!s(int64=2) %!d(string=hai) anos |
|
1808837298@qq.com
|
3ab4f145db
feat: 支持部分渠道的system角色 (close #89)
|
%!s(int64=2) %!d(string=hai) anos |
|
1808837298@qq.com
|
5b18cd6b0a
feat: 初步重构
|
%!s(int64=2) %!d(string=hai) anos |
