oadmin/new-api
1
0
Fork 0
Code Issues Pull Requests Actions Packages Projects Releases Wiki Activity
3,474 Commits 3 Branches 0 Tags
2fe3706ef05dee8dfd06bdd35571a220d3046e52
Commit Graph

739 Commits

Author SHA1 Message Date
CaIon
77e3502028 fix(adaptor): enhance response handling and error logging for Claude format 2025-07-23 20:59:56 +08:00
CaIon
ae0461692c feat: support ollama claude format 2025-07-23 20:01:03 +08:00
CaIon
13bdb80958 fix(adaptor): update relay mode handling #1419 2025-07-23 19:28:58 +08:00
CaIon
6f74e7b738 fix(adaptor): implement request conversion methods for Claude and Image. (close #1419) 2025-07-23 19:09:20 +08:00
feitianbubu
7bc9192f3f chore: opt video channel and platform 2025-07-22 20:14:24 +08:00
CaIon
6c4ada5098 Merge remote-tracking branch 'origin/alpha' into alpha 2025-07-22 12:06:28 +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
t0ng7u
90011aa0c9 ✨ feat(kling): send both model_name and model fields for upstream compatibility 
Some upstream Kling deployments still expect the legacy `model` key
instead of `model_name`.
This change adds the `model` field to `requestPayload` and populates it
with the same value as `model_name`, ensuring the generated JSON works
with both old and new versions.

Changes:
• Added `Model string "json:\"model,omitempty\""` to `requestPayload`
• Set `Model` alongside `ModelName` in `convertToRequestPayload`
• Updated comments to clarify compatibility purpose

Result:
Kling task requests now contain both `model_name` and `model`, removing
integration issues with upstreams that only recognize one of the keys.
 2025-07-22 01:21:56 +08:00
feitianbubu
fcc006ecd3 feat: channel kling support New API 2025-07-21 21:38:53 +08:00
feitianbubu
5b869376ab fix: ali embedding support base64 2025-07-20 12:05:20 +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
Xyfacai
7aa2972c3f fix(price): 未设置价格，错误返回模型价格匹配的名字 2025-07-20 10:12:36 +08:00
CaIon
a3059597fb fix: replace NewError with NewOpenAIError for improved error handling in multiple handlers 2025-07-19 11:29:31 +08:00
CaIon
d19a6914f9 fix: create NewOpenAIError function for improved error handling in Relay 2025-07-19 11:28:18 +08:00
Calcium-Ion
1e3450fdcb Merge pull request #1381 from feitianbubu/pr/task-origin-name 
feat: video priority use origin model name
 2025-07-18 20:49:53 +08:00
Calcium-Ion
514fea65c4 Merge pull request #1363 from feitianbubu/pr/add-jimeng-image 
feat: 增加即梦生图功能
 2025-07-18 20:45:49 +08:00
feitianbubu
0862a9bfa7 feat: add jimeng image -- fix alpha 2025-07-18 11:47:27 +08:00
Xyfacai
b485f2e42e fix(image): 只有 dalle模型才受 size、quality 影响价格 2025-07-18 00:30:49 +08:00
Calcium-Ion
6b3f1ab0e4 Merge pull request #1384 from QuantumNous/RequestOpenAI2ClaudeMessage 
feat: 改进 RequestOpenAI2ClaudeMessage 和添加 claude web search 计费
 2025-07-17 19:15:54 +08:00
feitianbubu
4369b18fbf feat: priority use origin model name 2025-07-16 15:38:51 +08:00
creamlike1024
961bc874d2 feat: claude web search tool 计费 2025-07-15 18:57:22 +08:00
creamlike1024
77da33de4f feat: RequestOpenAI2ClaudeMessage add more parms map 2025-07-15 12:38:05 +08:00
RedwindA
b7c3ad0867 🐛 fix: Add nil check for xaiResponse.Usage before calculating CompletionTokens 2025-07-14 21:40:15 +08:00
RedwindA
ea3545cc7e 🐛 fix: Use correct dto for non-stream xai 2025-07-14 21:32:31 +08:00
CaIon
75b486b467 feat: comment out model validation in ConvertClaudeRequest method 2025-07-13 15:17:15 +08:00
feitianbubu
aa8d112c58 feat: add jimeng image 2025-07-13 13:36:33 +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
CaIon
52a5e58f0c ✨ feat(adaptor): refactor response handlers to return usage first and improve error handling 2025-07-12 21:12:46 +08:00
RedwindA
22a0ed0ee2 feat: 支持 xAI 网络搜索 2025-07-12 02:22:40 +08:00
CaIon
cd8c23c0ab ✨ feat(channel): enhance channel status management 2025-07-10 17:49:53 +08:00
CaIon
cb16bf552e Merge branch 'alpha' into refactor_error 
# Conflicts:
#	controller/channel.go
#	middleware/distributor.go
#	model/channel.go
#	model/user.go
#	model/user_cache.go
#	relay/common/relay_info.go
 2025-07-10 15:11:55 +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
Calcium-Ion
f8d67a62a2 Merge pull request #1334 from duyazhe/fix-baidu-bug 
修复了百度请求时候需要传appid的bug
 2025-07-07 14:51:23 +08:00
Xiangyuan-liu
7b29f429ee refactor: log params and channel params 
refactor: log params and channel params
 2025-07-07 14:26:37 +08:00
CaIon
265c7d93a2 🔧 refactor(adaptor): update HTTP referer to new API domain 2025-07-07 12:36:04 +08:00
duyazhe
ce57ad3570 Update adaptor.go 2025-07-07 09:57:20 +08:00
duyazhe
9282f1d893 修复了百度请求时候需要传appid的bug 2025-07-06 23:09:49 +08:00
CaIon
f0f277dc2a 🔧 refactor(auth, channel, context): improve context setup and validation for multi-key channels 2025-07-06 12:37:56 +08:00
Calcium-Ion
5ec421d8e6 Merge pull request #1321 from iszcz/main 
支持Midjourney视频任务和图片编辑
 2025-07-05 15:28:33 +08:00
CaIon
22e8b46159 ✨ feat: make TopN field in RerankRequest optional in JSON serialization 2025-07-03 15:45:32 +08:00
Calcium-Ion
fce07325b9 Merge pull request #1325 from feitianbubu/pr/fix-ali-embedding-lost-prompt-token 
fix: ali embedding lose prompt_tokens
 2025-07-03 13:26:51 +08:00
CaIon
7e298f8ad1 ✨ feat: refactor environment variable initialization and introduce new constant types for API and context keys 2025-07-03 13:10:25 +08:00
IcedTangerine
34aca14858 Merge pull request #1309 from feitianbubu/pr/alpha/video-action-constant2 
feat: video action to constant
 2025-07-02 15:50:23 +08:00
skynono
6b1f94348a fix: ali embedding lose prompt_tokens 2025-07-02 15:12:02 +08:00
CaIon
efb691e6c2 Merge remote-tracking branch 'origin/alpha' into alpha 2025-07-01 13:14:40 +08:00
CaIon
53e3b35437 ✨ feat: enhance JWT exchange process with proxy support. (close #1087) 2025-07-01 13:14:24 +08:00
CaIon
eb265a55e1 ✨ feat: enhance environment configuration and resource initialization 2025-07-01 13:13:30 +08:00
skynono
6bd2316d9c feat: jimeng apiKey format to use | delimiter 2025-07-01 10:35:29 +08:00
iszcz
660180ea1b 支持Midjourney视频任务和图片编辑 2025-06-30 22:31:12 +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