admin777/new-api
1
0
Fork 0
Code Issues Pull Requests Actions Packages Projects Releases Wiki Activity
5,725 Commits 3 Branches 660 Tags
Commit Graph

270 Commits

Author SHA1 Message Date
Seefs
38a3314b9b
fix: preserve OpenAI image edit reference fields (#4646) 
* fix: preserve OpenAI image edit reference fields

* feat: support json image edit requests
 2026-05-06 21:27:47 +08:00
heimoshuiyu
8ca103342d fix: Message.ReasoningContent/Reasoning 改为 *string，修复空思考内容在请求转发时被静默丢弃的问题 
问题：
在非 passThrough 模式下，客户端发送的 reasoning_content: "" 经过
Go struct 反序列化再序列化后，因 string + omitempty 无法区分空串和
字段缺失，导致空的思考内容被静默丢弃。

根因：
dto.Message.ReasoningContent 和 Message.Reasoning 使用 string（非指针）
加 omitempty，违反 AGENTS.md Rule 6（可选标量字段必须用指针类型）。

修复：
1. Message.ReasoningContent/Reasoning 类型从 string 改为 *string
   - nil = 字段缺失 → JSON 省略
   - &"" = 显式空串 → JSON 保留 reasoning_content: ""
2. 新增 Message.GetReasoningContent() 辅助方法
3. 更新所有读写处：relay-openai, relay-claude, relay-gemini, ollama
4. 新增测试覆盖空串保留、字段省略、getter 回退逻辑
 2026-04-29 13:43:26 +08:00
Seefs
db89b57e1c
fix: support raw JSON response tool arguments 2026-04-26 13:47:37 +08:00
HynoR
435d7ae0dd
feat: support DeepSeek V4 reasoning suffix handling 2026-04-24 16:50:35 +08:00
woan1136
3ab65a8221
fix: add Azure channel support for /v1/responses/compact URL routing (#4149)
Some checks failed
Publish Docker image (Multi Registries, native amd64+arm64) / Build & push (amd64) [native] (push) Has been cancelled
Details
Publish Docker image (Multi Registries, native amd64+arm64) / Build & push (arm64) [native] (push) Has been cancelled
Details
Publish Docker image (Multi Registries, native amd64+arm64) / Create multi-arch manifests (Docker Hub) (push) Has been cancelled
Details
Build Electron App / build (windows-latest) (push) Has been cancelled
Details
Build Electron App / release (push) Has been cancelled
Details
Release (Linux, macOS, Windows) / Linux Release (push) Has been cancelled
Details
Release (Linux, macOS, Windows) / macOS Release (push) Has been cancelled
Details
Release (Linux, macOS, Windows) / Windows Release (push) Has been cancelled
Details 
The Azure channel's GetRequestURL method only handled RelayModeResponses
but missed RelayModeResponsesCompact. This caused compact requests to
fall through to the generic deployments URL pattern, producing an
incorrect path that Azure returns 404 for.

This fix extends the existing responses API special handling to also
cover the compact mode, appending /compact to the subUrl when the relay
mode is ResponsesCompact.

Affected URLs (before → after):
- Normal Azure: /openai/deployments/{model}/responses/compact → /openai/v1/responses/compact
- cognitiveservices: same pattern → /openai/responses/compact
- Custom AzureResponsesVersion: properly respected for compact too

Co-authored-by: 彭俊杰 <pengjunjie@onero.com>
 2026-04-13 15:23:38 +08:00
Seefs
a19a63b98c
feat: fill in some custom fields for vllm-omini. 2026-04-09 12:41:51 +08:00
CaIon
5238f279db feat: record stream interruption reasons via StreamStatus
Some checks failed
Publish Docker image (Multi Registries, native amd64+arm64) / Build & push (amd64) [native] (push) Has been cancelled
Details
Publish Docker image (Multi Registries, native amd64+arm64) / Build & push (arm64) [native] (push) Has been cancelled
Details
Publish Docker image (Multi Registries, native amd64+arm64) / Create multi-arch manifests (Docker Hub) (push) Has been cancelled
Details
Build Electron App / build (windows-latest) (push) Has been cancelled
Details
Build Electron App / release (push) Has been cancelled
Details
Release (Linux, macOS, Windows) / Linux Release (push) Has been cancelled
Details
Release (Linux, macOS, Windows) / macOS Release (push) Has been cancelled
Details
Release (Linux, macOS, Windows) / Windows Release (push) Has been cancelled
Details 
- Add StreamStatus type (relay/common) to track stream end reason
  (done/timeout/client_gone/scanner_error/eof/panic/ping_fail) and
  accumulate soft errors during streaming via sync.Once + sync.Mutex.
- Add StreamResult (relay/helper) as the callback interface: adapters
  call sr.Error() for soft errors, sr.Stop() for fatal, sr.Done() for
  normal completion. No early-return problem — multiple errors per chunk
  are naturally supported.
- Refactor StreamScannerHandler callback from func(string) bool to
  func(string, *StreamResult). All 9 channel adapters updated.
- Write stream_status into log other JSON field (admin-only) with
  status ok/error, end_reason, error_count, and error messages.
- Frontend: display stream status in log detail expansion for admins.
 2026-03-31 16:54:39 +08:00
wenyifan
2c3ae32c8e fix map 2026-03-20 16:48:04 +08:00
wenyifan
498199b37d fix code quality 2026-03-20 16:38:48 +08:00
wenyifan
ff29900f30 feat: Add support for counting cache-hit tokens in llama.cpp OpenAI-Compatible API 2026-03-20 16:10:18 +08:00
CaIon
da8a52f50a feat: add conditional setting for HTTP headers in OpenRouter channel type 2026-03-12 19:05:30 +08:00
Seefs
24ec27f844 Merge pull request #3221 from RedwindA/chore/updateModelList
Some checks failed
Publish Docker image (Multi Registries, native amd64+arm64) / Build & push (amd64) [native] (push) Has been cancelled
Details
Publish Docker image (Multi Registries, native amd64+arm64) / Build & push (arm64) [native] (push) Has been cancelled
Details
Publish Docker image (Multi Registries, native amd64+arm64) / Create multi-arch manifests (Docker Hub) (push) Has been cancelled
Details
Build Electron App / build (windows-latest) (push) Has been cancelled
Details
Build Electron App / release (push) Has been cancelled
Details
Release (Linux, macOS, Windows) / Linux Release (push) Has been cancelled
Details
Release (Linux, macOS, Windows) / macOS Release (push) Has been cancelled
Details
Release (Linux, macOS, Windows) / Windows Release (push) Has been cancelled
Details 
chore: update model lists for frequently used channels
 2026-03-12 15:13:03 +08:00
CaIon
5e9cc681f5 feat: update header title for OpenRouter channel type 2026-03-12 15:05:58 +08:00
RedwindA
7e68e1b36a chore: update model lists for frequently used channels 2026-03-11 23:39:18 +08:00
Nekohy
a4629f2630 feats: repair the thinking of claude to openrouter convert 2026-03-05 06:12:48 +08:00
Seefs
2cf3c1836c fix: preserve explicit zero values in native relay requests 2026-03-01 15:47:03 +08:00
Seefs
3d0c75f42c Merge branch 'feature/messages2responses' into upstream-main 
# Conflicts:
#	service/openaicompat/chat_to_responses.go
 2026-02-08 00:16:35 +08:00
Seefs
8f52072f53 feat: /v1/messages -> /v1/responses 2026-02-06 15:22:32 +08:00
Seefs
d5f0ab01df fix: add paragraph breaks between reasoning summary chunks in chat2responses stream 2026-02-06 14:46:29 +08:00
Seefs
a0574ae516 fix reasoning_effort log 2026-02-05 00:31:52 +08:00
Seefs
25f88050d3 fix: map Responses reasoning stream to chat completion deltas 
fix: default summary = detailed

fix ReasoningContent

fix ReasoningContent

fix ReasoningContent

fix ReasoningContent

Revert "fix ReasoningContent"

This reverts commit 45a88f78b91ce2376bca68745d19374bb9e95e88.

fix ReasoningContent

fix ReasoningContent
 2026-02-05 00:12:16 +08:00
Seefs
cf114ca7d6 feat: openai response /v1/response/compact (#2644) 
* feat: openai response /v1/response/compact

* feat: /v1/response/compact bill

* feat: /v1/response/compact

* feat: /v1/responses/compact -> codex channel

* feat: /v1/responses/compact -> codex channel

* feat: /v1/responses/compact -> codex channel

* feat: codex channel default models

* feat: compact model price

* feat: /v1/responses/comapct test
 2026-01-26 20:20:16 +08:00
Calcium-Ion
57c65c2782 Merge pull request #2742 from seefs001/fix/pr-2540 
feat(gemini): 支持 tool_choice 参数转换，优化多个渠道错误处理
 2026-01-26 15:12:09 +08:00
Seefs
7eaa80583b Revert "feat: xai refusal reason" 
This reverts commit 2548eaf8d38108862cf6a7e05f4f2418abb07c10.
 2026-01-25 16:38:58 +08:00
Seefs
2548eaf8d3 feat: xai refusal reason 2026-01-25 16:07:37 +08:00
Seefs
68e1e635e9 feat: logs show reject reason 2026-01-25 14:52:18 +08:00
Li-Xingyu
36b0f4b0ae feat: enhance Authorization header handling with Header Override support 2026-01-25 14:36:37 +08:00
Li-Xingyu
0dfa607147 feat: enhance Authorization header handling with Header Override support 2026-01-25 04:28:11 +08:00
Seefs
2a15e3b152 feat: codex channel (#2652)
Some checks failed
Publish Docker image (Multi Registries, native amd64+arm64) / Build & push (amd64) [native] (push) Has been cancelled
Details
Publish Docker image (Multi Registries, native amd64+arm64) / Build & push (arm64) [native] (push) Has been cancelled
Details
Publish Docker image (Multi Registries, native amd64+arm64) / Create multi-arch manifests (Docker Hub) (push) Has been cancelled
Details 
* 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
 2026-01-14 22:29:43 +08:00
Seefs
71460cba15 feat: /v1/chat/completion -> /v1/response (#2629)
Some checks failed
Publish Docker image (Multi Registries, native amd64+arm64) / Build & push (amd64) [native] (push) Has been cancelled
Details
Publish Docker image (Multi Registries, native amd64+arm64) / Build & push (arm64) [native] (push) Has been cancelled
Details
Publish Docker image (Multi Registries, native amd64+arm64) / Create multi-arch manifests (Docker Hub) (push) Has been cancelled
Details 
* feat: /v1/chat/completion -> /v1/response
 2026-01-11 21:38:07 +08:00
John Chen
6a2da31946 fix: 修复智普、Moonshot渠道在stream=true时无法拿到cachePrompt的统计数据。 
根本原因：
1. 在OaiStreamHandler流式处理函数中，调用applyUsagePostProcessing(info, usage, nil)时传入的responseBody为nil，导致无法从响应体中提取缓存tokens。
2. 两个渠道的cached_tokens位置不同：
  - 智普：标准位置 usage.prompt_tokens_details.cached_tokens
  - Moonshot：非标准位置 choices[].usage.cached_tokens

处理方案：
1. 传递body信息到applyUsagePostProcessing中
2. 拆分智普和Moonshot的解析，并为Moonshot单独写一个解析方法。
 2025-12-30 17:38:32 +08:00
Seefs
6526976453 fix: glm 4.7 finish reason (#2545) 2025-12-29 19:41:15 +08:00
John Chen
6dbe89f1cf 为Moonshot添加缓存tokens读取逻辑 
为Moonshot添加缓存tokens读取逻辑。其与智普V4的逻辑相同，所以共用逻辑
 2025-12-22 17:05:16 +08:00
CaIon
3822f4577c fix(audio): correct TotalTokens calculation for accurate usage reporting 2025-12-13 17:49:57 +08:00
CaIon
be2a863b9b feat(audio): enhance audio request handling with token type detection and streaming support 2025-12-13 17:24:23 +08:00
Calcium-Ion
2a01d1c996 Merge pull request #2429 from QuantumNous/feat/xhigh 
feat(adaptor): add '-xhigh' suffix to reasoning effort options
 2025-12-12 22:06:19 +08:00
CaIon
27dd42718b feat(adaptor): add '-xhigh' suffix to reasoning effort options for model parsing 2025-12-12 20:53:48 +08:00
Calcium-Ion
3c5edc54b7 Merge pull request #2426 from QuantumNous/feat/auto-cross-group-retry
Some checks failed
Publish Docker image (Multi Registries, native amd64+arm64) / Build & push (amd64) [native] (push) Has been cancelled
Details
Publish Docker image (Multi Registries, native amd64+arm64) / Build & push (arm64) [native] (push) Has been cancelled
Details
Publish Docker image (Multi Registries, native amd64+arm64) / Create multi-arch manifests (Docker Hub) (push) Has been cancelled
Details 
feat(token): add cross-group retry option for token processing
 2025-12-12 20:45:54 +08:00
CaIon
c87deaa7d9 feat(token): add cross-group retry option for token processing 2025-12-12 17:59:21 +08:00
Seefs
cf243588fa Merge pull request #2229 from HynoR/chore/v1 
fix: Set default to unsupported value for gpt-5 model series requests
 2025-12-08 20:59:30 +08:00
CaIon
1fededceb3 feat: refactor token estimation logic 
- Introduced new OpenAI text models in `common/model.go`.
- Added `IsOpenAITextModel` function to check for OpenAI text models.
- Refactored token estimation methods across various channels to use estimated prompt tokens instead of direct prompt token counts.
- Updated related functions and structures to accommodate the new token estimation approach, enhancing overall token management.
 2025-12-02 21:34:39 +08:00
CaIon
c8bbf7bed8 feat: Add ContextKeyLocalCountTokens and update ResponseText2Usage to use context in multiple channels 2025-11-21 18:17:01 +08:00
HynoR
601d257b80 fix: Set default to unsupported value for gpt-5 model series requests 2025-11-15 13:28:38 +08:00
CaIon
7827828abf fix(adaptor): Add '-none' suffix to effortSuffixes for model parsing 2025-11-14 14:04:34 +08:00
Seefs
fd55ba7f2c feat: ShouldPreserveThinkingSuffix (#2189)
Some checks failed
Publish Docker image (Multi Registries, native amd64+arm64) / Build & push (amd64) [native] (push) Has been cancelled
Details
Publish Docker image (Multi Registries, native amd64+arm64) / Build & push (arm64) [native] (push) Has been cancelled
Details
Publish Docker image (Multi Registries, native amd64+arm64) / Create multi-arch manifests (Docker Hub) (push) Has been cancelled
Details
Build Electron App / build (windows-latest) (push) Has been cancelled
Details
Build Electron App / release (push) Has been cancelled
Details
Release (Linux, macOS, Windows) / Linux Release (push) Has been cancelled
Details
Release (Linux, macOS, Windows) / macOS Release (push) Has been cancelled
Details
Release (Linux, macOS, Windows) / Windows Release (push) Has been cancelled
Details
2025-11-07 17:43:33 +08:00
IcedTangerine
961af95ec4 fix: openai 音频模型流模式未正确计费 (#2160)
Some checks failed
Publish Docker image (Multi Registries, native amd64+arm64) / Build & push (amd64) [native] (push) Has been cancelled
Details
Publish Docker image (Multi Registries, native amd64+arm64) / Build & push (arm64) [native] (push) Has been cancelled
Details
Publish Docker image (Multi Registries, native amd64+arm64) / Create multi-arch manifests (Docker Hub) (push) Has been cancelled
Details
Build Electron App / build (windows-latest) (push) Has been cancelled
Details
Build Electron App / release (push) Has been cancelled
Details
Release (Linux, macOS, Windows) / Linux Release (push) Has been cancelled
Details
Release (Linux, macOS, Windows) / macOS Release (push) Has been cancelled
Details
Release (Linux, macOS, Windows) / Windows Release (push) Has been cancelled
Details
2025-11-04 01:43:04 +08:00
CaIon
5d12755798 refactor(relay): enhance error logging and improve multipart form handling in audio requests #2127
Some checks failed
Publish Docker image (Multi Registries, native amd64+arm64) / Build & push (amd64) [native] (push) Has been cancelled
Details
Publish Docker image (Multi Registries, native amd64+arm64) / Build & push (arm64) [native] (push) Has been cancelled
Details
Publish Docker image (Multi Registries, native amd64+arm64) / Create multi-arch manifests (Docker Hub) (push) Has been cancelled
Details
Build Electron App / build (windows-latest) (push) Has been cancelled
Details
Build Electron App / release (push) Has been cancelled
Details
Release (Linux, macOS, Windows) / Linux Release (push) Has been cancelled
Details
Release (Linux, macOS, Windows) / macOS Release (push) Has been cancelled
Details
Release (Linux, macOS, Windows) / Windows Release (push) Has been cancelled
Details
2025-10-29 23:33:55 +08:00
CaIon
a00c6393c5 feat: implement audio duration retrieval without ffmpeg dependencies
Some checks failed
Publish Docker image (Multi Registries, native amd64+arm64) / Build & push (amd64) [native] (push) Has been cancelled
Details
Publish Docker image (Multi Registries, native amd64+arm64) / Build & push (arm64) [native] (push) Has been cancelled
Details
Publish Docker image (Multi Registries, native amd64+arm64) / Create multi-arch manifests (Docker Hub) (push) Has been cancelled
Details
Build Electron App / build (windows-latest) (push) Has been cancelled
Details
Build Electron App / release (push) Has been cancelled
Details
Release (Linux, macOS, Windows) / Linux Release (push) Has been cancelled
Details
Release (Linux, macOS, Windows) / macOS Release (push) Has been cancelled
Details
Release (Linux, macOS, Windows) / Windows Release (push) Has been cancelled
Details
2025-10-28 15:50:45 +08:00
feitianbubu
f617ff8741 feat: openai tts support streaming realtime audio 2025-10-22 13:33:01 +08:00
feitianbubu
a2d34b9e47 feat: add minimax api adaptor 2025-10-20 16:26:50 +08:00