github/new-api
1
0
Fork 0
mirror of https://github.com/QuantumNous/new-api.git synced 2026-03-30 04:40:59 +00:00
Code Issues Packages Projects Releases Wiki Activity
5,094 Commits 34 Branches 616 Tags
65b2ca41762ca5f8a9b38747eaf8df9a0e97dfc3
Commit Graph

5094 Commits

This Branch
This Branch
All Branches
Author SHA1 Message Date
Seefs
fdaa573c11 Revert "fix: video content api Priority use url field" 2026-01-21 23:38:47 +08:00
Seefs
46aae7358f fix: codex rm Temperature 2026-01-21 23:22:31 +08:00
Seefs
642aa092f6 Merge pull request #2688 from feitianbubu/pr/c579c7755c6b03e207853d06cc695ca7903388c9 2026-01-21 22:53:21 +08:00
Seefs
c24e68e0a6 Merge pull request #2691 from feitianbubu/pr/5f73324da8aebf6a98269c242dda05da3ea6d7bc 2026-01-21 22:52:36 +08:00
Seefs
bc2569b649 Merge pull request #2696 from Bliod-Cook/email-verification-fix 2026-01-21 22:51:06 +08:00
Seefs
5c01b77357 feat: optimized display 2026-01-21 00:17:20 +08:00
Seefs
3728fbdbf5 feat: optimized display 2026-01-21 00:12:41 +08:00
Seefs
6582020c80 feat: optimized display 2026-01-21 00:01:36 +08:00
Seefs
d4582ede98 feat: log shows request conversion 2026-01-20 23:43:29 +08:00
Seefs
9037d992be fix: Only models with the "qwen" designation can use the Claude-compatible interface; others require conversion. 2026-01-20 22:56:02 +08:00
Seefs
63921912dd fix: replace Alibaba's Claude-compatible interface with the new interface 2026-01-20 22:36:36 +08:00
Seefs
57ed2b3dae Merge pull request #2690 from feitianbubu/pr/0d926e8180210062b85a4ee06a0b324ba9ec91f6 2026-01-20 22:21:21 +08:00
Seefs
809a80815e fix: issue where consecutive calls to multiple tools in gemini all returned an index of 0 2026-01-20 22:03:19 +08:00
Bliod
c149c9cfcf fix: fix email send 2026-01-20 04:29:56 +00:00
daggeryu
f538336f7f fix request pass-through aws channels can't test 
common.GetRequestBody(c) read bod is null
 2026-01-20 10:08:56 +08:00
CaIon
d2df342f4e fix: update abortWithOpenAiMessage function to use types.ErrorCode 2026-01-19 17:35:28 +08:00
feitianbubu
fac4a5ffdd fix: video content api Priority use url field 2026-01-19 16:16:11 +08:00
feitianbubu
3b01cb3f41 fix: update warning threshold label from '5$' to '2$' 2026-01-19 12:58:10 +08:00
feitianbubu
575574f068 fix: jimeng i2v support multi image by metadata 2026-01-19 11:34:46 +08:00
Seefs
76164e951e fix: codex Unsupported parameter: max_output_tokens 2026-01-17 21:42:28 +08:00
Seefs
f96615110d fix: the login method cannot be displayed under the aff link. 2026-01-15 23:19:51 +08:00
Seefs
8ef99f4728 Merge pull request #2670 from seefs001/fix/chat2claude-log 2026-01-15 15:35:17 +08:00
Seefs
1d8a11b37a fix: for chat-based calls to the Claude model, tagging is required. Using Claude's rendering logs, the two approaches handle input rendering differently. 2026-01-15 15:28:02 +08:00
Seefs
af2d6ad8d2 feat: TLS_INSECURE_SKIP_VERIFY env 2026-01-15 14:43:53 +08:00
Seefs
ea802f2297 fix: openAI function to gemini function field adjusted to whitelist mode 2026-01-15 13:26:42 +08:00
Seefs
e5cb9ac03a feat: codex channel (#2652) 
* feat: codex channel

* feat: codex channel

* feat: codex oauth flow

* feat: codex refresh cred

* feat: codex usage

* fix: codex err message detail

* fix: codex setting ui

* feat: codex refresh cred task

* fix: import err

* fix: codex store must be false

* fix: chat -> responses tool call

* fix: chat -> responses tool call
v0.10.6-alpha.3 		2026-01-14 22:29:43 +08:00
Seefs
ca11fcbabd Merge pull request #2632 from feitianbubu/pr/add-doubao-video-1.5 2026-01-14 16:33:30 +08:00
Seefs
4bffc249d6 feat: customizable automatic retry status codes 2026-01-14 14:34:12 +08:00
Seefs
6169f46cc6 Merge pull request #2627 from seefs001/feature/channel-test-param-override 
feat: channel testing supports parameter overriding
v0.10.6-alpha.2 		2026-01-12 18:49:05 +08:00
Calcium-Ion
d73a0440b9 Merge pull request #2642 from seefs001/fix/gemini-propertyNames 
fix: clean propertyNames for gemini function
 2026-01-12 18:48:24 +08:00
Seefs
688280b3c3 fix: chat2response setting ui (#2643) 
* fix: setting ui

* fix: rm global.chat_completions_to_responses_policy

* fix: rm global.chat_completions_to_responses_policy
 2026-01-12 18:48:05 +08:00
Seefs
41da848c56 Merge pull request #2647 from seefs001/feature/status-code-auto-disable 
feat: status code auto-disable configuration
 2026-01-12 18:47:45 +08:00
Seefs
22b9438588 Merge pull request #2646 from deanxv/fix/gemini-unmarshal 2026-01-12 12:33:01 +08:00
dean
4ed4a7659a fix: support snake_case fields in GeminiChatGenerationConfig 2026-01-12 12:23:24 +08:00
Seefs
138fcd2327 fix: clean propertyNames for gemini function 2026-01-11 23:34:18 +08:00
Seefs
62b796fa6a feat: /v1/chat/completion -> /v1/response (#2629) 
* feat: /v1/chat/completion -> /v1/response
v0.10.6-alpha.1 		2026-01-11 21:38:07 +08:00
feitianbubu
a4f28f0b79 feat: add doubao video 1.5 2026-01-10 22:23:31 +08:00
Seefs
1a5c8f3c35 Merge pull request #2615 from RedwindA/feat/GeminiNativeFetchModels 
fix(gemini): fetch model list via native v1beta/models endpoint
 2026-01-09 23:54:36 +08:00
Seefs
e1d43a820f Merge pull request #2619 from RedwindA/fix/disableMinimaxFetchModels 
fix: remove Minimax from FETCHABLE channels
 2026-01-09 21:42:25 +08:00
RedwindA
c975b4cfa8 fix(minimax): 添加 MiniMax-M2 系列模型到 ModelList 2026-01-09 20:46:47 +08:00
RedwindA
b51d1e2f78 fix: remove Minimax from FETCHABLE channels 2026-01-09 20:37:12 +08:00
RedwindA
07e77b3c6f refactor(gemini): 更新 GeminiModelsResponse 以使用 dto.GeminiModel 类型 2026-01-09 18:08:11 +08:00
RedwindA
c2464fc877 fix(gemini): fetch model list via native v1beta/models endpoint 
Use the native Gemini Models API (/v1beta/models) instead of the OpenAI-compatible
path when listing models for Gemini channels, improving compatibility with
third-party Gemini-format providers that don't implement OpenAI routes.

- Add paginated model listing with timeout and optional proxy support
- Select an enabled key for multi-key Gemini channels
 2026-01-09 18:00:40 +08:00
Bliod-Cook
b6313a1354 Merge branch 'QuantumNous:main' into main 2026-01-08 23:30:45 +08:00
Bliod
d4edec6ac2 feat: select model in visualized modl mapping 2026-01-08 15:26:59 +00:00
CaIon
93012631d1 docs: update readme 2026-01-07 20:52:27 +08:00
Xyfacai
1ab0c35540 Merge pull request #2590 from xyfacai/fix/max-body-limit 
fix: 设置默认max req body 为128MB
 2026-01-06 21:47:12 +08:00
Xyfacai
022fbcee04 Merge pull request #2588 from PowerfulBart/fix/auto-group-task-logging 
fix(task): 修复使用 auto 分组时 Task Relay 不记录日志和不扣费的问题
 2026-01-06 11:14:49 +08:00
郑伯涛
aed1900364 fix(task): 修复使用 auto 分组时 Task Relay 不记录日志和不扣费的问题 
问题描述：
- 使用 auto 分组的令牌调用 /v1/videos 等 Task 接口时，虽然任务能成功创建，
  但使用日志不显示记录，且不会扣费

根本原因：
- Distribute 中间件在选择渠道后，会将实际选中的分组存储在 ContextKeyAutoGroup 中
- 但 RelayTaskSubmit 函数没有从 context 中读取这个值来更新 info.UsingGroup
- 导致 info.UsingGroup 始终是 "auto" 而不是实际选中的分组（如 "sora2逆"）
- 当 auto 分组的倍率配置为 0 时，quota 计算结果为 0
- 日志记录条件 "if quota != 0" 不满足，导致日志不记录、不扣费

修复方案：
- 在 RelayTaskSubmit 函数中计算分组倍率之前，添加从 ContextKeyAutoGroup
  获取实际分组的逻辑
- 使用安全的类型断言，避免潜在的 panic 风险

影响范围：
- 仅影响 Task Relay 流程（/v1/videos, /suno, /kling 等接口）
- 不影响使用具体分组令牌的调用
- 不影响其他 Relay 类型（chat/completions 等已有类似处理逻辑）
 2026-01-06 00:16:50 +08:00
Seefs
f8938a8f78 Merge pull request #2587 from xiangsx/main 2026-01-05 23:36:16 +08:00