admin777/new-api
1
0
Fork 0
Code Issues Pull Requests Actions Packages Projects Releases Wiki Activity
2,269 Commits 3 Branches 660 Tags
Commit Graph

118 Commits

Author SHA1 Message Date
1808837298@qq.com
a36d6de8d1 feat: Add prompt cache hit tokens support for DeepSeek channel #406 2025-03-08 16:50:53 +08:00
Sh1n3zZ
c1ed9d552e fix: possible incomplete return of the think field and incorrect occurrences of the reasoning field 2025-03-06 19:20:29 +08:00
Sh1n3zZ
aa6c894f56 fix: adapting return format for openrouter think content (#793) 2025-03-06 19:16:26 +08:00
1808837298@qq.com
c4ca4af8ce fix: Prevent resource leaks by adding body close in stream handlers 2025-03-05 19:51:22 +08:00
1808837298@qq.com
d647214555 refactor: Centralize stream handling and helper functions in relay package 2025-03-05 19:47:41 +08:00
1808837298@qq.com
efc7c4d7f9 feat: Add context-aware goroutine pool for safer concurrent operations 2025-03-04 18:42:34 +08:00
1808837298@qq.com
67e17dcdbd fix: Ignore EOF errors in OpenAI stream scanner 2025-03-04 17:35:41 +08:00
1808837298@qq.com
b0ee0f1501 fix: Handle scanner errors in OpenAI relay stream handler 2025-03-04 17:10:56 +08:00
1808837298@qq.com
0aa30ed3f6 feat: Add new model management features
Some checks failed
Publish Docker image (amd64) / Push Docker image to multiple registries (push) Has been cancelled
Details
Publish Docker image (arm64) / Push Docker image to multiple registries (push) Has been cancelled
Details
Linux Release / release (push) Has been cancelled
Details
macOS Release / release (push) Has been cancelled
Details
Windows Release / release (push) Has been cancelled
Details 
- Implement `/api/channel/models_enabled` endpoint to retrieve enabled models
- Add `EnabledListModels` handler in controller
- Create new `ModelRatioNotSetEditor` component for managing unset model ratios
- Update router to include new models_enabled route
- Add internationalization support for new model management UI
- Include GPT-4.5 preview model in OpenAI model list
 2025-02-28 21:13:30 +08:00
1808837298@qq.com
c3b0e57ea4 feat: Add Jina reranking support for OpenAI adaptor 2025-02-26 21:46:06 +08:00
1808837298@qq.com
4597816a14 feat: Add thinking-to-content conversion for stream responses 2025-02-23 17:05:57 +08:00
1808837298@qq.com
991b6f8bb0 fix: mistral 2025-02-22 16:29:48 +08:00
1808837298@qq.com
8101cd3ce3 feat: Add reasoning content support in OpenAI response handling
Some checks failed
Publish Docker image (amd64) / Push Docker image to multiple registries (push) Has been cancelled
Details
Publish Docker image (arm64) / Push Docker image to multiple registries (push) Has been cancelled
Details
Linux Release / release (push) Has been cancelled
Details
macOS Release / release (push) Has been cancelled
Details
Windows Release / release (push) Has been cancelled
Details
2025-02-21 18:52:51 +08:00
1808837298@qq.com
af9d03140c fix: Extend temperature handling for OpenAI-like models 
- Add support for suppressing temperature for o1 models
- Expand model prefix check to include 'o1' alongside 'o3' models
 2025-02-18 16:00:56 +08:00
1808837298@qq.com
2869dbf60a feat: Enhance VolcEngine channel support with bot model routing (fix #757)
Some checks failed
Publish Docker image (amd64) / Push Docker image to multiple registries (push) Has been cancelled
Details
Publish Docker image (arm64) / Push Docker image to multiple registries (push) Has been cancelled
Details
Linux Release / release (push) Has been cancelled
Details
macOS Release / release (push) Has been cancelled
Details
Windows Release / release (push) Has been cancelled
Details
2025-02-15 00:10:58 +08:00
1808837298@qq.com
9e2433e2a6 fix: Improve OpenAI stream data parsing and handling 2025-02-14 23:52:25 +08:00
1808837298@qq.com
61ad1adbda feat: Improve embedding request handling and support across channels
Some checks failed
Publish Docker image (amd64) / Push Docker image to multiple registries (push) Has been cancelled
Details
Publish Docker image (arm64) / Push Docker image to multiple registries (push) Has been cancelled
Details
Linux Release / release (push) Has been cancelled
Details
macOS Release / release (push) Has been cancelled
Details
Windows Release / release (push) Has been cancelled
Details 
- Update EmbeddingRequest DTO to support more flexible input types
- Add input parsing method to handle various input formats
- Implement ConvertEmbeddingRequest for multiple channel adaptors
- Remove relayMode parameter from EmbeddingHelper
- Add input validation for embedding requests
- Simplify embedding request conversion for different channels
 2025-02-12 14:39:36 +08:00
kuwork
fdebb6e6e8 Merge branch 'main' into main 2025-02-04 22:52:37 +08:00
1808837298@qq.com
80f60109cf feat: add Azure default API version configuration 
- Introduce `AZURE_DEFAULT_API_VERSION` environment variable
- Set default Azure API version to `2024-12-01-preview`
- Update README documentation for new environment configuration
- Modify Azure channel relay to use default API version when not specified
 2025-02-03 22:38:23 +08:00
1808837298@qq.com
c2702a7125 feat: enhance model name handling and logging
Some checks failed
Publish Docker image (amd64) / Push Docker image to multiple registries (push) Has been cancelled
Details
Publish Docker image (arm64) / Push Docker image to multiple registries (push) Has been cancelled
Details
Linux Release / release (push) Has been cancelled
Details
macOS Release / release (push) Has been cancelled
Details
Windows Release / release (push) Has been cancelled
Details 
- Add `RecodeModelName` to `RelayInfo` struct for more flexible model name tracking
- Update text relay and quota consumption to use `RecodeModelName`
- Move reasoning effort from admin info to other info in log generation
- Ensure consistent model name handling across relay components
 2025-02-03 15:06:46 +08:00
1808837298@qq.com
e641fb346e feat: add reasoning effort logging and display 
- Add `ReasoningEffort` field to `RelayInfo` struct
- Update log generation to include reasoning effort in admin info
- Modify logs table component to display reasoning effort when available
- Preserve reasoning effort information during request processing
 2025-02-03 14:44:40 +08:00
1808837298@qq.com
587ed2afae fix: improve reasoning effort model suffix handling 
- Remove model name suffixes after extracting reasoning effort
- Update upstream model name to reflect the base model
- Ensure clean model name is passed to the upstream service
 2025-02-03 14:34:00 +08:00
1808837298@qq.com
b010700391 fix: update reasoning effort model suffix parsing 
- Modify model suffix parsing to use hyphen-separated suffixes
- Ensure consistent parsing of `-high`, `-medium`, and `-low` reasoning effort indicators
 2025-02-03 14:23:26 +08:00
1808837298@qq.com
0b2585ed52 feat: add reasoning effort configuration for models 
- Support setting reasoning effort via model name suffix
- Add `-high`, `-medium`, and `-low` suffixes to control reasoning effort
- Update README with new model configuration option
- Modify OpenAI adaptor to handle reasoning effort settings
 2025-02-03 14:22:34 +08:00
1808837298@qq.com
c81e23b0e4 f*** o3-mini
Some checks failed
Publish Docker image (amd64) / Push Docker image to multiple registries (push) Has been cancelled
Details
Publish Docker image (arm64) / Push Docker image to multiple registries (push) Has been cancelled
Details
Linux Release / release (push) Has been cancelled
Details
macOS Release / release (push) Has been cancelled
Details
Windows Release / release (push) Has been cancelled
Details
2025-02-01 14:11:34 +08:00
1808837298@qq.com
4131304c1f feat: add support for o3-mini models in model ratio and request handling 2025-02-01 13:41:25 +08:00
Jerry
fcc32ffbc9 Fix M3E not working 2025-01-23 05:54:39 +08:00
沈浩
dab21d5263 fix: incorrect whisper audio usage 2025-01-17 18:12:05 +08:00
1808837298@qq.com
a3fe6c03b8 Adjust streaming timeout for OpenAI models in OaiStreamHandler 
- Implemented conditional logic to double the streaming timeout for models starting with "o1" or "o3".
- Improved handling of streaming timeout configuration to enhance performance based on model type.
 2025-01-06 17:52:33 +08:00
1808837298@qq.com
d953b98417 feat: support gpt-4o-mini-realtime-preview 2025-01-03 18:51:09 +08:00
CalciumIon
62469a5226 feat: support azure stream_options
Some checks failed
Publish Docker image (amd64) / Push Docker image to multiple registries (push) Has been cancelled
Details
Publish Docker image (arm64) / Push Docker image to multiple registries (push) Has been cancelled
Details
Linux Release / release (push) Has been cancelled
Details
macOS Release / release (push) Has been cancelled
Details
Windows Release / release (push) Has been cancelled
Details
2024-12-26 22:51:06 +08:00
HynoR
616f41d4c9 feat: 适配o1模型 2024-12-20 23:14:10 +08:00
HynoR
11408d011d feat: 适配o1模型 2024-12-20 22:07:53 +08:00
CalciumIon
0ad03de153 feat: implement channel settings configuration 
fix #620
 2024-12-15 15:52:41 +08:00
iszcz
8a1d16955a 1 2024-12-04 16:20:42 +08:00
Calcium-Ion
20483652e7 Merge pull request #574 from Calcium-Ion/channel-tag
Some checks failed
Publish Docker image (amd64) / Push Docker image to multiple registries (push) Has been cancelled
Details
Publish Docker image (arm64) / Push Docker image to multiple registries (push) Has been cancelled
Details
Linux Release / release (push) Has been cancelled
Details
macOS Release / release (push) Has been cancelled
Details
Windows Release / release (push) Has been cancelled
Details 
feat: 初步集成渠道标签分组功能
 2024-11-30 17:45:16 +08:00
CalciumIon
96e3eeceb1 fix: xAI missing finish_reason #572 2024-11-30 16:57:57 +08:00
CalciumIon
ba6c908fbc fix: stt模型计费
Some checks failed
Publish Docker image (amd64) / Push Docker image to multiple registries (push) Has been cancelled
Details
Publish Docker image (arm64) / Push Docker image to multiple registries (push) Has been cancelled
Details
Linux Release / release (push) Has been cancelled
Details
macOS Release / release (push) Has been cancelled
Details
Windows Release / release (push) Has been cancelled
Details
2024-11-25 19:31:59 +08:00
CalciumIon
2ae6060a31 feat: support audio response_format #580
Some checks failed
Publish Docker image (amd64) / Push Docker image to multiple registries (push) Has been cancelled
Details
Publish Docker image (arm64) / Push Docker image to multiple registries (push) Has been cancelled
Details
Linux Release / release (push) Has been cancelled
Details
macOS Release / release (push) Has been cancelled
Details
Windows Release / release (push) Has been cancelled
Details
2024-11-24 16:44:27 +08:00
HynoR
1a2e5da179 Chore: support gpt-4o-2024-11-20 2024-11-21 09:14:23 +08:00
CalciumIon
faf4ddc247 feat: 暂时禁用透传功能
Some checks failed
Publish Docker image (amd64) / Push Docker image to multiple registries (push) Has been cancelled
Details
Publish Docker image (arm64) / Push Docker image to multiple registries (push) Has been cancelled
Details
Linux Release / release (push) Has been cancelled
Details
macOS Release / release (push) Has been cancelled
Details
Windows Release / release (push) Has been cancelled
Details
2024-11-19 15:06:54 +08:00
CalciumIon
710c88cb26 feat: 暂时禁用透传功能 2024-11-19 15:04:19 +08:00
CalciumIon
75b480d821 chore: 删除无用日志 2024-11-05 19:41:38 +08:00
1808837298@qq.com
bacfdbc725 fix: realtime计费 
(cherry picked from commit fdfea8726c6d86d3844af1ac18d7b3df908f26a7)
 2024-11-05 19:29:06 +08:00
Xyfacai
67bdfea903 fix(realtime): 修复ws 握手失败、计费问题 
(cherry picked from commit 618dffc43fd5a5f4065944db87761f9ee18e44d3)
 2024-11-05 19:28:46 +08:00
Xyfacai
16f6bdc81e refactor: realtime log 
(cherry picked from commit fd24dc467bfc360008b313220e607f0176ee7aa3)
 2024-11-05 19:28:09 +08:00
Xyfacai
14f4320923 fix: 部分情况缺少返回预扣 
(cherry picked from commit 96373455521a38095706bd81c57f9a18557d9c2e)
 2024-11-05 19:28:08 +08:00
1808837298@qq.com
d9c7e98115 feat: realtime pre consume 
(cherry picked from commit 273d154e1640bae26b7caedddf1685e9ff21ab74)
 2024-11-05 19:28:06 +08:00
1808837298@qq.com
e052d7d02b feat: realtime pre consume 
(cherry picked from commit d87917f8f6eb9d2e144a9f840d6d91767ea2eb69)
 2024-11-05 19:28:03 +08:00
1808837298@qq.com
efd7ea075e feat: azure realtime 
(cherry picked from commit 75ff3d98f06103dc2df1f8817bd3fcbf433e0f20)
 2024-11-05 19:27:55 +08:00