oadmin/new-api
1
0
Fork 0
Code Issues Pull Requests Actions Packages Projects Releases Wiki Activity
3,747 Commits 3 Branches 0 Tags
14a9a99e2d1b006f00a053c6310453d321196b67
Commit Graph

63 Commits

Author SHA1 Message Date
nekohy
14a9a99e2d fix: zhipu_v4 thinking 2025-08-11 21:37:10 +08:00
CaIon
72ffe61ad1 feat: add verbosity field to OpenAI request #1540 2025-08-09 20:12:27 +08:00
CaIon
2a804b6c02 feat: add system prompt override functionality in channel settings and request handling #1468 2025-08-09 12:53:06 +08:00
CaIon
d9c1fb5244 feat: update MaxTokens handling 2025-08-07 16:15:59 +08:00
CaIon
2469c439b1 fix: improve error messaging and JSON schema handling in distributor and relay components 2025-07-26 12:11:20 +08:00
CaIon
1297addfb1 feat: enhance request handling with pass-through options and system prompt support 2025-07-26 11:39:09 +08:00
CaIon
2402715492 fix: add Think field to OllamaRequest and support extra parameters in GeneralOpenAIRequest. (close #1125 
)
 2025-07-22 12:06:21 +08:00
Xyfacai
c674c3561a fix(response): tools 需要处理的参数很少 使用 map 2025-07-20 11:21:57 +08:00
t0ng7u
93b5638a9c Merge remote-tracking branch 'origin/multi_keys_channel' into alpha 
# Conflicts:
#	web/src/components/table/LogsTable.js
#	web/src/i18n/locales/en.json
#	web/src/pages/Channel/EditChannel.js
 2025-07-12 23:47:24 +08:00
RedwindA
22a0ed0ee2 feat: 支持 xAI 网络搜索 2025-07-12 02:22:40 +08:00
CaIon
98952198bb refactor: Introduce standardized API error 
This commit refactors the application's error handling mechanism by introducing a new standardized error type, `types.NewAPIError`. It also renames common JSON utility functions for better clarity.

Previously, internal error handling was tightly coupled to the `dto.OpenAIError` format. This change decouples the internal logic from the external API representation.

Key changes:
- A new `types.NewAPIError` struct is introduced to serve as a canonical internal representation for all API errors.
- All relay adapters (OpenAI, Claude, Gemini, etc.) are updated to return `*types.NewAPIError`.
- Controllers now convert the internal `NewAPIError` to the client-facing `OpenAIError` format at the API boundary, ensuring backward compatibility.
- Channel auto-disable/enable logic is updated to use the new standardized error type.
- JSON utility functions are renamed to align with Go's standard library conventions (e.g., `UnmarshalJson` -> `Unmarshal`, `EncodeJson` -> `Marshal`).
 2025-07-10 15:02:40 +08:00
CaIon
6b9237f868 🐛 fix: refactor JSON unmarshalling across multiple handlers to use UnmarshalJson and UnmarshalJsonStr for consistency 
This update replaces instances of DecodeJson and DecodeJsonStr with UnmarshalJson and UnmarshalJsonStr in various relay handlers, enhancing code consistency and clarity in JSON processing. The changes improve maintainability and align with recent refactoring efforts in the codebase.
 2025-06-28 00:02:07 +08:00
CaIon
1dad04ec09 ✨ feat: add Function and Container fields to ResponsesToolsCall struct #1305 2025-06-27 16:56:54 +08:00
Calcium-Ion
fd4447f60a Merge pull request #1120 from neotf/feat-04 
feat: enhance token usage details for upstream OpenRouter
 2025-06-22 01:10:49 +08:00
KamiPasi
d5a3eb7d04 透传thinking参数, 豆包模型用来控制是否思考 2025-06-19 12:06:42 +08:00
neotf
81bc096872 Merge branch 'main' into feat-04 2025-06-18 15:20:24 +08:00
CaIon
be7e09b14d ✨ feat(dto): add VlHighResolutionImages parameter to GeneralOpenAIRequest 2025-06-13 17:29:26 +08:00
neotf
d67d5d8006 format 2025-06-11 14:00:32 +08:00
neotf
c4f25a77d1 format 2025-06-11 13:56:44 +08:00
neotf
52763c09f2 Merge branch 'main' into feat-04 2025-06-11 13:55:47 +08:00
Calcium-Ion
dc0f303bb7 Merge pull request #1184 from QuantumNous/refactor/message 
fix: message 转 any 后，ImageUrl判断 panic
 2025-06-09 15:51:53 +08:00
Xyfacai
c95fb55c51 fix: message 转 any 后，ImageUrl判断 panic 2025-06-09 11:27:24 +08:00
CaIon
865377449e refactor(dto): change function and encoding fields to use json.RawMessage for improved flexibility 2025-06-08 16:28:47 +08:00
Xyfacai
b778cd2b23 refactor: message content 改成 any 
refactor: message content 改成 any
 2025-06-07 23:47:22 +08:00
neotf
e77555a04f Merge branch 'main' into feat-04 2025-06-05 20:35:47 +08:00
neotf
3665ad672e feat: support claude cache and thinking for upstream [OpenRouter] (#983) 
* feat: support claude cache for upstream [OpenRouter]

* feat: support claude thinking for upstream [OpenRouter]

* feat: reasoning is common params for OpenRouter
 2025-06-05 17:35:48 +08:00
CaIon
611d77e1a9 feat: add ToMap method and enhance OpenAI request handling 2025-06-01 01:10:10 +08:00
neotf
66778efcc5 feat: enhance token usage details for upstream OpenRouter 2025-05-29 00:55:57 +08:00
CaIon
e01b517843 fix: Change ParallelTooCalls from bool to *bool in GeneralOpenAIRequest for optional handling 2025-05-28 21:12:55 +08:00
IcedTangerine
e3d7b31a49 Update openai_request.go 2025-05-28 14:25:24 +08:00
wang.rong
76824a0337 chat/completion透传parallel_tool_calls参数 2025-05-27 09:32:20 +08:00
creamlike1024
30d5a11f46 fix: search-preview model web search billing 2025-05-26 18:53:41 +08:00
Calcium-Ion
48af027903 Merge pull request #1020 from QuantumNous/v1responses 
feat: support /v1/responses API
 2025-05-04 17:13:39 +08:00
CaIon
e097d5a538 feat: add video URL support in MediaContent and update token counting logic 2025-05-03 21:12:07 +08:00
creamlike1024
425feb88d8 feat: support /v1/responses API 2025-05-02 13:59:46 +08:00
CaIon
b64480b750 fix: gemini thinking tokens count #1014 2025-04-29 16:21:54 +08:00
CaIon
1eebdc4773 refactor: remove reasoning field from GeneralOpenAIRequest struct 2025-04-17 17:11:42 +08:00
CaIon
9b6c898675 feat: add reasoning field to GeneralOpenAIReques 2025-04-17 17:09:46 +08:00
CaIon
4b3e30e669 feat: 完善openai转claude支持 2025-04-11 18:28:50 +08:00
CaIon
cca9c0479f feat: enhance file handling and logging in the application 2025-04-11 16:23:54 +08:00
1808837298@qq.com
dd393cd0d9 feat: support dify upload image file 2025-03-15 19:10:12 +08:00
Sh1n3zZ
b95142bbac fix: adapting return format for openrouter think content (#793) 2025-03-06 19:16:26 +08:00
1808837298@qq.com
13ab0f8e4f fix: gemini&claude tool call format #795 #766 2025-02-26 23:56:10 +08:00
Calcium-Ion
dc36fdedc2 Merge pull request #781 from zeyugao/main 
feat: Pass extra_body in OpenAI request to the backend
 2025-02-24 16:29:48 +08:00
1808837298@qq.com
7ff4cebdbe feat: Enhance token counting and content parsing for messages 2025-02-24 14:18:15 +08:00
Elsa
af00f7b311 Pass extra_body to the backend 2025-02-24 10:52:55 +08:00
1808837298@qq.com
88a2fec190 fix: mistral 2025-02-22 16:29:48 +08:00
1808837298@qq.com
cc5066c510 refactor: Improve message content parsing with robust type handling 2025-02-21 18:27:43 +08:00
1808837298@qq.com
b9b69b01e5 refactor: Improve message content handling and quota error responses 2025-02-21 18:18:21 +08:00
1808837298@qq.com
971aea09ee feat: Improve image handling for Ollama channels 2025-02-19 20:45:42 +08:00