📝 Add docstrings to main

Docstrings generation was requested by @ZhaoZuohong.

* https://github.com/QuantumNous/new-api/pull/2279#issuecomment-3568907431

The following files were modified:

* `relay/channel/openai/helper.go`
* `relay/channel/openai/reasoning_converter.go`
* `relay/channel/openai/relay-openai.go`

.env.example

@@ -9,14 +9,6 @@
 # ENABLE_PPROF=true
 # 启用调试模式
 # DEBUG=true
-# Pyroscope 配置
-# PYROSCOPE_URL=http://localhost:4040
-# PYROSCOPE_APP_NAME=new-api
-# PYROSCOPE_BASIC_AUTH_USER=your-user
-# PYROSCOPE_BASIC_AUTH_PASSWORD=your-password
-# PYROSCOPE_MUTEX_RATE=5
-# PYROSCOPE_BLOCK_RATE=5
-# HOSTNAME=your-hostname
 
 # 数据库相关配置
 # 数据库连接字符串

.gitignore

@@ -16,11 +16,8 @@ new-api
 tiktoken_cache
 .eslintcache
 .gocache
-.gomodcache/
 .cache
 web/bun.lock
 
 electron/node_modules
 electron/dist
-data/
-.gomodcache/

Dockerfile

@@ -14,7 +14,7 @@ ENV GO111MODULE=on CGO_ENABLED=0
 ARG TARGETOS
 ARG TARGETARCH
 ENV GOOS=${TARGETOS:-linux} GOARCH=${TARGETARCH:-amd64}
-ENV GOEXPERIMENT=greenteagc
+
 
 WORKDIR /build
 
@@ -25,11 +25,10 @@ COPY . .
 COPY --from=builder /build/dist ./web/dist
 RUN go build -ldflags "-s -w -X 'github.com/QuantumNous/new-api/common.Version=$(cat VERSION)'" -o new-api
 
-FROM debian:bookworm-slim
+FROM alpine
 
-RUN apt-get update \
-    && apt-get install -y --no-install-recommends ca-certificates tzdata libasan8 wget \
-    && rm -rf /var/lib/apt/lists/* \
+RUN apk upgrade --no-cache \
+    && apk add --no-cache ca-certificates tzdata \
     && update-ca-certificates
 
 COPY --from=builder2 /build/new-api /

README.en.md

@@ -146,7 +146,7 @@ docker run --name new-api -d --restart always \
 
 🎉 After deployment is complete, visit `http://localhost:3000` to start using!
 
-📖 For more deployment methods, please refer to [Deployment Guide](https://docs.newapi.pro/en/docs/installation)
+📖 For more deployment methods, please refer to [Deployment Guide](https://docs.newapi.pro/installation)
 
 ---
 
@@ -154,7 +154,7 @@ docker run --name new-api -d --restart always \
 
 <div align="center">
 
-### 📖 [Official Documentation](https://docs.newapi.pro/en/docs) | [![Ask DeepWiki](https://deepwiki.com/badge.svg)](https://deepwiki.com/QuantumNous/new-api)
+### 📖 [Official Documentation](https://docs.newapi.pro/) | [![Ask DeepWiki](https://deepwiki.com/badge.svg)](https://deepwiki.com/QuantumNous/new-api)
 
 </div>
 
@@ -162,17 +162,17 @@ docker run --name new-api -d --restart always \
 
 | Category | Link |
 |------|------|
-| 🚀 Deployment Guide | [Installation Documentation](https://docs.newapi.pro/en/docs/installation) |
-| ⚙️ Environment Configuration | [Environment Variables](https://docs.newapi.pro/en/docs/installation/config-maintenance/environment-variables) |
-| 📡 API Documentation | [API Documentation](https://docs.newapi.pro/en/docs/api) |
-| ❓ FAQ | [FAQ](https://docs.newapi.pro/en/docs/support/faq) |
-| 💬 Community Interaction | [Communication Channels](https://docs.newapi.pro/en/docs/support/community-interaction) |
+| 🚀 Deployment Guide | [Installation Documentation](https://docs.newapi.pro/installation) |
+| ⚙️ Environment Configuration | [Environment Variables](https://docs.newapi.pro/installation/environment-variables) |
+| 📡 API Documentation | [API Documentation](https://docs.newapi.pro/api) |
+| ❓ FAQ | [FAQ](https://docs.newapi.pro/support/faq) |
+| 💬 Community Interaction | [Communication Channels](https://docs.newapi.pro/support/community-interaction) |
 
 ---
 
 ## ✨ Key Features
 
-> For detailed features, please refer to [Features Introduction](https://docs.newapi.pro/en/docs/guide/wiki/basic-concepts/features-introduction)
+> For detailed features, please refer to [Features Introduction](https://docs.newapi.pro/wiki/features-introduction)
 
 ### 🎨 Core Functions
 
@@ -201,11 +201,11 @@ docker run --name new-api -d --restart always \
 ### 🚀 Advanced Features
 
 **API Format Support:**
-- ⚡ [OpenAI Responses](https://docs.newapi.pro/en/docs/api/ai-model/chat/openai/create-response)
-- ⚡ [OpenAI Realtime API](https://docs.newapi.pro/en/docs/api/ai-model/realtime/create-realtime-session) (including Azure)
-- ⚡ [Claude Messages](https://docs.newapi.pro/en/docs/api/ai-model/chat/create-message)
-- ⚡ [Google Gemini](https://doc.newapi.pro/en/api/google-gemini-chat)
-- 🔄 [Rerank Models](https://docs.newapi.pro/en/docs/api/ai-model/rerank/create-rerank) (Cohere, Jina)
+- ⚡ [OpenAI Responses](https://docs.newapi.pro/api/openai-responses)
+- ⚡ [OpenAI Realtime API](https://docs.newapi.pro/api/openai-realtime) (including Azure)
+- ⚡ [Claude Messages](https://docs.newapi.pro/api/anthropic-chat)
+- ⚡ [Google Gemini](https://docs.newapi.pro/api/google-gemini-chat/)
+- 🔄 [Rerank Models](https://docs.newapi.pro/api/jinaai-rerank) (Cohere, Jina)
 
 **Intelligent Routing:**
 - ⚖️ Channel weighted random
@@ -238,7 +238,6 @@ docker run --name new-api -d --restart always \
 - `gemini-2.5-flash-nothinking` - Disable thinking mode
 - `gemini-2.5-pro-thinking` - Enable thinking mode
 - `gemini-2.5-pro-thinking-128` - Enable thinking mode with thinking budget of 128 tokens
-- You can also append `-low`, `-medium`, or `-high` to any Gemini model name to request the corresponding reasoning effort (no extra thinking-budget suffix needed).
 
 </details>
 
@@ -246,16 +245,16 @@ docker run --name new-api -d --restart always \
 
 ## 🤖 Model Support
 
-> For details, please refer to [API Documentation - Relay Interface](https://docs.newapi.pro/en/docs/api)
+> For details, please refer to [API Documentation - Relay Interface](https://docs.newapi.pro/api)
 
 | Model Type | Description | Documentation |
 |---------|------|------|
 | 🤖 OpenAI GPTs | gpt-4-gizmo-* series | - |
-| 🎨 Midjourney-Proxy | [Midjourney-Proxy(Plus)](https://github.com/novicezk/midjourney-proxy) | [Documentation](https://doc.newapi.pro/en/api/midjourney-proxy-image) |
-| 🎵 Suno-API | [Suno API](https://github.com/Suno-API/Suno-API) | [Documentation](https://doc.newapi.pro/en/api/suno-music) |
-| 🔄 Rerank | Cohere, Jina | [Documentation](https://docs.newapi.pro/en/docs/api/ai-model/rerank/create-rerank) |
-| 💬 Claude | Messages format | [Documentation](https://docs.newapi.pro/en/docs/api/ai-model/chat/create-message) |
-| 🌐 Gemini | Google Gemini format | [Documentation](https://doc.newapi.pro/en/api/google-gemini-chat) |
+| 🎨 Midjourney-Proxy | [Midjourney-Proxy(Plus)](https://github.com/novicezk/midjourney-proxy) | [Documentation](https://docs.newapi.pro/api/midjourney-proxy-image) |
+| 🎵 Suno-API | [Suno API](https://github.com/Suno-API/Suno-API) | [Documentation](https://docs.newapi.pro/api/suno-music) |
+| 🔄 Rerank | Cohere, Jina | [Documentation](https://docs.newapi.pro/api/jinaai-rerank) |
+| 💬 Claude | Messages format | [Documentation](https://docs.newapi.pro/api/anthropic-chat) |
+| 🌐 Gemini | Google Gemini format | [Documentation](https://docs.newapi.pro/api/google-gemini-chat/) |
 | 🔧 Dify | ChatFlow mode | - |
 | 🎯 Custom | Supports complete call address | - |
 
@@ -264,16 +263,16 @@ docker run --name new-api -d --restart always \
 <details>
 <summary>View complete interface list</summary>
 
-- [Chat Interface (Chat Completions)](https://docs.newapi.pro/en/docs/api/ai-model/chat/openai/create-chat-completion)
-- [Response Interface (Responses)](https://docs.newapi.pro/en/docs/api/ai-model/chat/openai/create-response)
-- [Image Interface (Image)](https://docs.newapi.pro/en/docs/api/ai-model/images/openai/v1-images-generations--post)
-- [Audio Interface (Audio)](https://docs.newapi.pro/en/docs/api/ai-model/audio/openai/create-transcription)
-- [Video Interface (Video)](https://docs.newapi.pro/en/docs/api/ai-model/videos/create-video-generation)
-- [Embedding Interface (Embeddings)](https://docs.newapi.pro/en/docs/api/ai-model/embeddings/create-embedding)
-- [Rerank Interface (Rerank)](https://docs.newapi.pro/en/docs/api/ai-model/rerank/create-rerank)
-- [Realtime Conversation (Realtime)](https://docs.newapi.pro/en/docs/api/ai-model/realtime/create-realtime-session)
-- [Claude Chat](https://docs.newapi.pro/en/docs/api/ai-model/chat/create-message)
-- [Google Gemini Chat](https://doc.newapi.pro/en/api/google-gemini-chat)
+- [Chat Interface (Chat Completions)](https://docs.newapi.pro/api/openai-chat)
+- [Response Interface (Responses)](https://docs.newapi.pro/api/openai-responses)
+- [Image Interface (Image)](https://docs.newapi.pro/api/openai-image)
+- [Audio Interface (Audio)](https://docs.newapi.pro/api/openai-audio)
+- [Video Interface (Video)](https://docs.newapi.pro/api/openai-video)
+- [Embedding Interface (Embeddings)](https://docs.newapi.pro/api/openai-embeddings)
+- [Rerank Interface (Rerank)](https://docs.newapi.pro/api/jinaai-rerank)
+- [Realtime Conversation (Realtime)](https://docs.newapi.pro/api/openai-realtime)
+- [Claude Chat](https://docs.newapi.pro/api/anthropic-chat)
+- [Google Gemini Chat](https://docs.newapi.pro/api/google-gemini-chat/)
 
 </details>
 
@@ -304,19 +303,10 @@ docker run --name new-api -d --restart always \
 | `SQL_DSN` | Database connection string | - |
 | `REDIS_CONN_STRING` | Redis connection string | - |
 | `STREAMING_TIMEOUT` | Streaming timeout (seconds) | `300` |
-| `STREAM_SCANNER_MAX_BUFFER_MB` | Max per-line buffer (MB) for the stream scanner; increase when upstream sends huge image/base64 payloads | `64` |
-| `MAX_REQUEST_BODY_MB` | Max request body size (MB, counted **after decompression**; prevents huge requests/zip bombs from exhausting memory). Exceeding it returns `413` | `32` |
 | `AZURE_DEFAULT_API_VERSION` | Azure API version | `2025-04-01-preview` |
 | `ERROR_LOG_ENABLED` | Error log switch | `false` |
-| `PYROSCOPE_URL` | Pyroscope server address | - |
-| `PYROSCOPE_APP_NAME` | Pyroscope application name | `new-api` |
-| `PYROSCOPE_BASIC_AUTH_USER` | Pyroscope basic auth user | - |
-| `PYROSCOPE_BASIC_AUTH_PASSWORD` | Pyroscope basic auth password | - |
-| `PYROSCOPE_MUTEX_RATE` | Pyroscope mutex sampling rate | `5` |
-| `PYROSCOPE_BLOCK_RATE` | Pyroscope block sampling rate | `5` |
-| `HOSTNAME` | Hostname tag for Pyroscope | `new-api` |
 
-📖 **Complete configuration:** [Environment Variables Documentation](https://docs.newapi.pro/en/docs/installation/config-maintenance/environment-variables)
+📖 **Complete configuration:** [Environment Variables Documentation](https://docs.newapi.pro/installation/environment-variables)
 
 </details>
 
@@ -418,10 +408,10 @@ docker run --name new-api -d --restart always \
 
 | Resource | Link |
 |------|------|
-| 📘 FAQ | [FAQ](https://docs.newapi.pro/en/docs/support/faq) |
-| 💬 Community Interaction | [Communication Channels](https://docs.newapi.pro/en/docs/support/community-interaction) |
-| 🐛 Issue Feedback | [Issue Feedback](https://docs.newapi.pro/en/docs/support/feedback-issues) |
-| 📚 Complete Documentation | [Official Documentation](https://docs.newapi.pro/en/docs) |
+| 📘 FAQ | [FAQ](https://docs.newapi.pro/support/faq) |
+| 💬 Community Interaction | [Communication Channels](https://docs.newapi.pro/support/community-interaction) |
+| 🐛 Issue Feedback | [Issue Feedback](https://docs.newapi.pro/support/feedback-issues) |
+| 📚 Complete Documentation | [Official Documentation](https://docs.newapi.pro/support) |
 
 ### 🤝 Contribution Guide
 
@@ -450,7 +440,7 @@ Welcome all forms of contribution!
 
 If this project is helpful to you, welcome to give us a ⭐️ Star！
 
-**[Official Documentation](https://docs.newapi.pro/en/docs)** • **[Issue Feedback](https://github.com/Calcium-Ion/new-api/issues)** • **[Latest Release](https://github.com/Calcium-Ion/new-api/releases)**
+**[Official Documentation](https://docs.newapi.pro/)** • **[Issue Feedback](https://github.com/Calcium-Ion/new-api/issues)** • **[Latest Release](https://github.com/Calcium-Ion/new-api/releases)**
 
 <sub>Built with ❤️ by QuantumNous</sub>
 

README.fr.md

@@ -146,7 +146,7 @@ docker run --name new-api -d --restart always \
 
 🎉 Après le déploiement, visitez `http://localhost:3000` pour commencer à utiliser!
 
-📖 Pour plus de méthodes de déploiement, veuillez vous référer à [Guide de déploiement](https://docs.newapi.pro/en/docs/installation)
+📖 Pour plus de méthodes de déploiement, veuillez vous référer à [Guide de déploiement](https://docs.newapi.pro/installation)
 
 ---
 
@@ -154,7 +154,7 @@ docker run --name new-api -d --restart always \
 
 <div align="center">
 
-### 📖 [Documentation officielle](https://docs.newapi.pro/en/docs) | [![Demander à DeepWiki](https://deepwiki.com/badge.svg)](https://deepwiki.com/QuantumNous/new-api)
+### 📖 [Documentation officielle](https://docs.newapi.pro/) | [![Demander à DeepWiki](https://deepwiki.com/badge.svg)](https://deepwiki.com/QuantumNous/new-api)
 
 </div>
 
@@ -162,17 +162,17 @@ docker run --name new-api -d --restart always \
 
 | Catégorie | Lien |
 |------|------|
-| 🚀 Guide de déploiement | [Documentation d'installation](https://docs.newapi.pro/en/docs/installation) |
-| ⚙️ Configuration de l'environnement | [Variables d'environnement](https://docs.newapi.pro/en/docs/installation/config-maintenance/environment-variables) |
-| 📡 Documentation de l'API | [Documentation de l'API](https://docs.newapi.pro/en/docs/api) |
-| ❓ FAQ | [FAQ](https://docs.newapi.pro/en/docs/support/faq) |
-| 💬 Interaction avec la communauté | [Canaux de communication](https://docs.newapi.pro/en/docs/support/community-interaction) |
+| 🚀 Guide de déploiement | [Documentation d'installation](https://docs.newapi.pro/installation) |
+| ⚙️ Configuration de l'environnement | [Variables d'environnement](https://docs.newapi.pro/installation/environment-variables) |
+| 📡 Documentation de l'API | [Documentation de l'API](https://docs.newapi.pro/api) |
+| ❓ FAQ | [FAQ](https://docs.newapi.pro/support/faq) |
+| 💬 Interaction avec la communauté | [Canaux de communication](https://docs.newapi.pro/support/community-interaction) |
 
 ---
 
 ## ✨ Fonctionnalités clés
 
-> Pour les fonctionnalités détaillées, veuillez vous référer à [Présentation des fonctionnalités](https://docs.newapi.pro/en/docs/guide/wiki/basic-concepts/features-introduction) |
+> Pour les fonctionnalités détaillées, veuillez vous référer à [Présentation des fonctionnalités](https://docs.newapi.pro/wiki/features-introduction) |
 
 ### 🎨 Fonctions principales
 
@@ -200,11 +200,11 @@ docker run --name new-api -d --restart always \
 ### 🚀 Fonctionnalités avancées
 
 **Prise en charge des formats d'API:**
-- ⚡ [OpenAI Responses](https://docs.newapi.pro/en/docs/api/ai-model/chat/openai/create-response)
-- ⚡ [OpenAI Realtime API](https://docs.newapi.pro/en/docs/api/ai-model/realtime/create-realtime-session) (y compris Azure)
-- ⚡ [Claude Messages](https://docs.newapi.pro/en/docs/api/ai-model/chat/create-message)
-- ⚡ [Google Gemini](https://doc.newapi.pro/en/api/google-gemini-chat)
-- 🔄 [Modèles Rerank](https://docs.newapi.pro/en/docs/api/ai-model/rerank/create-rerank) (Cohere, Jina)
+- ⚡ [OpenAI Responses](https://docs.newapi.pro/api/openai-responses)
+- ⚡ [OpenAI Realtime API](https://docs.newapi.pro/api/openai-realtime) (y compris Azure)
+- ⚡ [Claude Messages](https://docs.newapi.pro/api/anthropic-chat)
+- ⚡ [Google Gemini](https://docs.newapi.pro/api/google-gemini-chat/)
+- 🔄 [Modèles Rerank](https://docs.newapi.pro/api/jinaai-rerank) (Cohere, Jina)
 
 **Routage intelligent:**
 - ⚖️ Sélection aléatoire pondérée des canaux
@@ -234,7 +234,6 @@ docker run --name new-api -d --restart always \
 - `gemini-2.5-flash-nothinking` - Désactiver le mode de pensée
 - `gemini-2.5-pro-thinking` - Activer le mode de pensée
 - `gemini-2.5-pro-thinking-128` - Activer le mode de pensée avec budget de pensée de 128 tokens
-- Vous pouvez également ajouter les suffixes `-low`, `-medium` ou `-high` aux modèles Gemini pour fixer le niveau d’effort de raisonnement (sans suffixe de budget supplémentaire).
 
 </details>
 
@@ -242,16 +241,16 @@ docker run --name new-api -d --restart always \
 
 ## 🤖 Prise en charge des modèles
 
-> Pour les détails, veuillez vous référer à [Documentation de l'API - Interface de relais](https://docs.newapi.pro/en/docs/api)
+> Pour les détails, veuillez vous référer à [Documentation de l'API - Interface de relais](https://docs.newapi.pro/api)
 
 | Type de modèle | Description | Documentation |
 |---------|------|------|
 | 🤖 OpenAI GPTs | série gpt-4-gizmo-* | - |
-| 🎨 Midjourney-Proxy | [Midjourney-Proxy(Plus)](https://github.com/novicezk/midjourney-proxy) | [Documentation](https://doc.newapi.pro/en/api/midjourney-proxy-image) |
-| 🎵 Suno-API | [Suno API](https://github.com/Suno-API/Suno-API) | [Documentation](https://doc.newapi.pro/en/api/suno-music) |
-| 🔄 Rerank | Cohere, Jina | [Documentation](https://docs.newapi.pro/en/docs/api/ai-model/rerank/create-rerank) |
-| 💬 Claude | Format Messages | [Documentation](https://docs.newapi.pro/en/docs/api/ai-model/chat/create-message) |
-| 🌐 Gemini | Format Google Gemini | [Documentation](https://doc.newapi.pro/en/api/google-gemini-chat) |
+| 🎨 Midjourney-Proxy | [Midjourney-Proxy(Plus)](https://github.com/novicezk/midjourney-proxy) | [Documentation](https://docs.newapi.pro/api/midjourney-proxy-image) |
+| 🎵 Suno-API | [Suno API](https://github.com/Suno-API/Suno-API) | [Documentation](https://docs.newapi.pro/api/suno-music) |
+| 🔄 Rerank | Cohere, Jina | [Documentation](https://docs.newapi.pro/api/jinaai-rerank) |
+| 💬 Claude | Format Messages | [Documentation](https://docs.newapi.pro/api/anthropic-chat) |
+| 🌐 Gemini | Format Google Gemini | [Documentation](https://docs.newapi.pro/api/google-gemini-chat/) |
 | 🔧 Dify | Mode ChatFlow | - |
 | 🎯 Personnalisé | Prise en charge de l'adresse d'appel complète | - |
 
@@ -260,16 +259,16 @@ docker run --name new-api -d --restart always \
 <details>
 <summary>Voir la liste complète des interfaces</summary>
 
-- [Interface de discussion (Chat Completions)](https://docs.newapi.pro/en/docs/api/ai-model/chat/openai/create-chat-completion)
-- [Interface de réponse (Responses)](https://docs.newapi.pro/en/docs/api/ai-model/chat/openai/create-response)
-- [Interface d'image (Image)](https://docs.newapi.pro/en/docs/api/ai-model/images/openai/v1-images-generations--post)
-- [Interface audio (Audio)](https://docs.newapi.pro/en/docs/api/ai-model/audio/openai/create-transcription)
-- [Interface vidéo (Video)](https://docs.newapi.pro/en/docs/api/ai-model/videos/create-video-generation)
-- [Interface d'incorporation (Embeddings)](https://docs.newapi.pro/en/docs/api/ai-model/embeddings/create-embedding)
-- [Interface de rerank (Rerank)](https://docs.newapi.pro/en/docs/api/ai-model/rerank/create-rerank)
-- [Conversation en temps réel (Realtime)](https://docs.newapi.pro/en/docs/api/ai-model/realtime/create-realtime-session)
-- [Discussion Claude](https://docs.newapi.pro/en/docs/api/ai-model/chat/create-message)
-- [Discussion Google Gemini](https://doc.newapi.pro/en/api/google-gemini-chat)
+- [Interface de discussion (Chat Completions)](https://docs.newapi.pro/api/openai-chat)
+- [Interface de réponse (Responses)](https://docs.newapi.pro/api/openai-responses)
+- [Interface d'image (Image)](https://docs.newapi.pro/api/openai-image)
+- [Interface audio (Audio)](https://docs.newapi.pro/api/openai-audio)
+- [Interface vidéo (Video)](https://docs.newapi.pro/api/openai-video)
+- [Interface d'incorporation (Embeddings)](https://docs.newapi.pro/api/openai-embeddings)
+- [Interface de rerank (Rerank)](https://docs.newapi.pro/api/jinaai-rerank)
+- [Conversation en temps réel (Realtime)](https://docs.newapi.pro/api/openai-realtime)
+- [Discussion Claude](https://docs.newapi.pro/api/anthropic-chat)
+- [Discussion Google Gemini](https://docs.newapi.pro/api/google-gemini-chat/)
 
 </details>
 
@@ -300,19 +299,10 @@ docker run --name new-api -d --restart always \
 | `SQL_DSN` | Chaine de connexion à la base de données | - |
 | `REDIS_CONN_STRING` | Chaine de connexion Redis | - |
 | `STREAMING_TIMEOUT` | Délai d'expiration du streaming (secondes) | `300` |
-| `STREAM_SCANNER_MAX_BUFFER_MB` | Taille max du buffer par ligne (Mo) pour le scanner SSE ; à augmenter quand les sorties image/base64 sont très volumineuses (ex. images 4K) | `64` |
-| `MAX_REQUEST_BODY_MB` | Taille maximale du corps de requête (Mo, comptée **après décompression** ; évite les requêtes énormes/zip bombs qui saturent la mémoire). Dépassement ⇒ `413` | `32` |
 | `AZURE_DEFAULT_API_VERSION` | Version de l'API Azure | `2025-04-01-preview` |
 | `ERROR_LOG_ENABLED` | Interrupteur du journal d'erreurs | `false` |
-| `PYROSCOPE_URL` | Adresse du serveur Pyroscope | - |
-| `PYROSCOPE_APP_NAME` | Nom de l'application Pyroscope | `new-api` |
-| `PYROSCOPE_BASIC_AUTH_USER` | Utilisateur Basic Auth Pyroscope | - |
-| `PYROSCOPE_BASIC_AUTH_PASSWORD` | Mot de passe Basic Auth Pyroscope | - |
-| `PYROSCOPE_MUTEX_RATE` | Taux d'échantillonnage mutex Pyroscope | `5` |
-| `PYROSCOPE_BLOCK_RATE` | Taux d'échantillonnage block Pyroscope | `5` |
-| `HOSTNAME` | Nom d'hôte tagué pour Pyroscope | `new-api` |
 
-📖 **Configuration complète:** [Documentation des variables d'environnement](https://docs.newapi.pro/en/docs/installation/config-maintenance/environment-variables)
+📖 **Configuration complète:** [Documentation des variables d'environnement](https://docs.newapi.pro/installation/environment-variables)
 
 </details>
 
@@ -412,10 +402,10 @@ docker run --name new-api -d --restart always \
 
 | Ressource | Lien |
 |------|------|
-| 📘 FAQ | [FAQ](https://docs.newapi.pro/en/docs/support/faq) |
-| 💬 Interaction avec la communauté | [Canaux de communication](https://docs.newapi.pro/en/docs/support/community-interaction) |
-| 🐛 Commentaires sur les problèmes | [Commentaires sur les problèmes](https://docs.newapi.pro/en/docs/support/feedback-issues) |
-| 📚 Documentation complète | [Documentation officielle](https://docs.newapi.pro/en/docs) |
+| 📘 FAQ | [FAQ](https://docs.newapi.pro/support/faq) |
+| 💬 Interaction avec la communauté | [Canaux de communication](https://docs.newapi.pro/support/community-interaction) |
+| 🐛 Commentaires sur les problèmes | [Commentaires sur les problèmes](https://docs.newapi.pro/support/feedback-issues) |
+| 📚 Documentation complète | [Documentation officielle](https://docs.newapi.pro/support) |
 
 ### 🤝 Guide de contribution
 
@@ -444,8 +434,8 @@ Bienvenue à toutes les formes de contribution!
 
 Si ce projet vous est utile, bienvenue à nous donner une ⭐️ Étoile！
 
-**[Documentation officielle](https://docs.newapi.pro/en/docs)** • **[Commentaires sur les problèmes](https://github.com/Calcium-Ion/new-api/issues)** • **[Dernière version](https://github.com/Calcium-Ion/new-api/releases)**
+**[Documentation officielle](https://docs.newapi.pro/)** • **[Commentaires sur les problèmes](https://github.com/Calcium-Ion/new-api/issues)** • **[Dernière version](https://github.com/Calcium-Ion/new-api/releases)**
 
 <sub>Construit avec ❤️ par QuantumNous</sub>
 
-</div>
+</div>

README.ja.md

@@ -146,7 +146,7 @@ docker run --name new-api -d --restart always \
 
 🎉 デプロイが完了したら、`http://localhost:3000` にアクセスして使用を開始してください！
 
-📖 その他のデプロイ方法については[デプロイガイド](https://docs.newapi.pro/ja/docs/installation)を参照してください。
+📖 その他のデプロイ方法については[デプロイガイド](https://docs.newapi.pro/installation)を参照してください。
 
 ---
 
@@ -154,7 +154,7 @@ docker run --name new-api -d --restart always \
 
 <div align="center">
 
-### 📖 [公式ドキュメント](https://docs.newapi.pro/ja/docs) | [![Ask DeepWiki](https://deepwiki.com/badge.svg)](https://deepwiki.com/QuantumNous/new-api)
+### 📖 [公式ドキュメント](https://docs.newapi.pro/) | [![Ask DeepWiki](https://deepwiki.com/badge.svg)](https://deepwiki.com/QuantumNous/new-api)
 
 </div>
 
@@ -162,17 +162,17 @@ docker run --name new-api -d --restart always \
 
 | カテゴリ | リンク |
 |------|------|
-| 🚀 デプロイガイド | [インストールドキュメント](https://docs.newapi.pro/ja/docs/installation) |
-| ⚙️ 環境設定 | [環境変数](https://docs.newapi.pro/ja/docs/installation/config-maintenance/environment-variables) |
-| 📡 APIドキュメント | [APIドキュメント](https://docs.newapi.pro/ja/docs/api) |
-| ❓ よくある質問 | [FAQ](https://docs.newapi.pro/ja/docs/support/faq) |
-| 💬 コミュニティ交流 | [交流チャネル](https://docs.newapi.pro/ja/docs/support/community-interaction) |
+| 🚀 デプロイガイド | [インストールドキュメント](https://docs.newapi.pro/installation) |
+| ⚙️ 環境設定 | [環境変数](https://docs.newapi.pro/installation/environment-variables) |
+| 📡 APIドキュメント | [APIドキュメント](https://docs.newapi.pro/api) |
+| ❓ よくある質問 | [FAQ](https://docs.newapi.pro/support/faq) |
+| 💬 コミュニティ交流 | [交流チャネル](https://docs.newapi.pro/support/community-interaction) |
 
 ---
 
 ## ✨ 主な機能
 
-> 詳細な機能については[機能説明](https://docs.newapi.pro/ja/docs/guide/wiki/basic-concepts/features-introduction)を参照してください。
+> 詳細な機能については[機能説明](https://docs.newapi.pro/wiki/features-introduction)を参照してください。
 
 ### 🎨 コア機能
 
@@ -202,15 +202,15 @@ docker run --name new-api -d --restart always \
 ### 🚀 高度な機能
 
 **APIフォーマットサポート:**
-- ⚡ [OpenAI Responses](https://docs.newapi.pro/ja/docs/api/ai-model/chat/openai/create-response)
-- ⚡ [OpenAI Realtime API](https://docs.newapi.pro/ja/docs/api/ai-model/realtime/create-realtime-session)（Azureを含む）
-- ⚡ [Claude Messages](https://docs.newapi.pro/ja/docs/api/ai-model/chat/create-message)
-- ⚡ [Google Gemini](https://doc.newapi.pro/ja/api/google-gemini-chat)
-- 🔄 [Rerankモデル](https://docs.newapi.pro/ja/docs/api/ai-model/rerank/create-rerank)
-- ⚡ [OpenAI Realtime API](https://docs.newapi.pro/ja/docs/api/ai-model/realtime/create-realtime-session)
-- ⚡ [Claude Messages](https://docs.newapi.pro/ja/docs/api/ai-model/chat/create-message)
-- ⚡ [Google Gemini](https://doc.newapi.pro/ja/api/google-gemini-chat)
-- 🔄 [Rerankモデル](https://docs.newapi.pro/ja/docs/api/ai-model/rerank/create-rerank)（Cohere、Jina）
+- ⚡ [OpenAI Responses](https://docs.newapi.pro/api/openai-responses)
+- ⚡ [OpenAI Realtime API](https://docs.newapi.pro/api/openai-realtime)（Azureを含む）
+- ⚡ [Claude Messages](https://docs.newapi.pro/api/anthropic-chat)
+- ⚡ [Google Gemini](https://docs.newapi.pro/api/google-gemini-chat/)
+- 🔄 [Rerankモデル](https://docs.newapi.pro/api/jinaai-rerank)
+- ⚡ [OpenAI Realtime API](https://docs.newapi.pro/api/openai-realtime)
+- ⚡ [Claude Messages](https://docs.newapi.pro/api/anthropic-chat)
+- ⚡ [Google Gemini](https://docs.newapi.pro/api/google-gemini-chat/)
+- 🔄 [Rerankモデル](https://docs.newapi.pro/api/jinaai-rerank)（Cohere、Jina）
 
 **インテリジェントルーティング:**
 - ⚖️ チャネル重み付けランダム
@@ -243,7 +243,6 @@ docker run --name new-api -d --restart always \
 - `gemini-2.5-flash-nothinking` - 思考モードを無効にする
 - `gemini-2.5-pro-thinking` - 思考モードを有効にする
 - `gemini-2.5-pro-thinking-128` - 思考モードを有効にし、思考予算を128トークンに設定する
-- Gemini モデル名の末尾に `-low` / `-medium` / `-high` を付けることで推論強度を直接指定できます（追加の思考予算サフィックスは不要です）。
 
 </details>
 
@@ -251,16 +250,16 @@ docker run --name new-api -d --restart always \
 
 ## 🤖 モデルサポート
 
-> 詳細については[APIドキュメント - 中継インターフェース](https://docs.newapi.pro/ja/docs/api)
+> 詳細については[APIドキュメント - 中継インターフェース](https://docs.newapi.pro/api)
 
 | モデルタイプ | 説明 | ドキュメント |
 |---------|------|------|
 | 🤖 OpenAI GPTs | gpt-4-gizmo-* シリーズ | - |
-| 🎨 Midjourney-Proxy | [Midjourney-Proxy(Plus)](https://github.com/novicezk/midjourney-proxy) | [ドキュメント](https://doc.newapi.pro/ja/api/midjourney-proxy-image) |
-| 🎵 Suno-API | [Suno API](https://github.com/Suno-API/Suno-API) | [ドキュメント](https://doc.newapi.pro/ja/api/suno-music) |
-| 🔄 Rerank | Cohere、Jina | [ドキュメント](https://docs.newapi.pro/ja/docs/api/ai-model/rerank/create-rerank) |
-| 💬 Claude | Messagesフォーマット | [ドキュメント](https://docs.newapi.pro/ja/docs/api/ai-model/chat/create-message) |
-| 🌐 Gemini | Google Geminiフォーマット | [ドキュメント](https://doc.newapi.pro/ja/api/google-gemini-chat) |
+| 🎨 Midjourney-Proxy | [Midjourney-Proxy(Plus)](https://github.com/novicezk/midjourney-proxy) | [ドキュメント](https://docs.newapi.pro/api/midjourney-proxy-image) |
+| 🎵 Suno-API | [Suno API](https://github.com/Suno-API/Suno-API) | [ドキュメント](https://docs.newapi.pro/api/suno-music) |
+| 🔄 Rerank | Cohere、Jina | [ドキュメント](https://docs.newapi.pro/api/jinaai-rerank) |
+| 💬 Claude | Messagesフォーマット | [ドキュメント](https://docs.newapi.pro/api/suno-music) |
+| 🌐 Gemini | Google Geminiフォーマット | [ドキュメント](https://docs.newapi.pro/api/google-gemini-chat/) |
 | 🔧 Dify | ChatFlowモード | - |
 | 🎯 カスタム | 完全な呼び出しアドレスの入力をサポート | - |
 
@@ -269,16 +268,16 @@ docker run --name new-api -d --restart always \
 <details>
 <summary>完全なインターフェースリストを表示</summary>
 
-- [チャットインターフェース (Chat Completions)](https://docs.newapi.pro/ja/docs/api/ai-model/chat/openai/create-chat-completion)
-- [レスポンスインターフェース (Responses)](https://docs.newapi.pro/ja/docs/api/ai-model/chat/openai/create-response)
-- [イメージインターフェース (Image)](https://docs.newapi.pro/ja/docs/api/ai-model/images/openai/v1-images-generations--post)
-- [オーディオインターフェース (Audio)](https://docs.newapi.pro/ja/docs/api/ai-model/audio/openai/create-transcription)
-- [ビデオインターフェース (Video)](https://docs.newapi.pro/ja/docs/api/ai-model/videos/create-video-generation)
-- [エンベッドインターフェース (Embeddings)](https://docs.newapi.pro/ja/docs/api/ai-model/embeddings/create-embedding)
-- [再ランク付けインターフェース (Rerank)](https://docs.newapi.pro/ja/docs/api/ai-model/rerank/create-rerank)
-- [リアルタイム対話インターフェース (Realtime)](https://docs.newapi.pro/ja/docs/api/ai-model/realtime/create-realtime-session)
-- [Claudeチャット](https://docs.newapi.pro/ja/docs/api/ai-model/chat/create-message)
-- [Google Geminiチャット](https://doc.newapi.pro/ja/api/google-gemini-chat)
+- [チャットインターフェース (Chat Completions)](https://docs.newapi.pro/api/openai-chat)
+- [レスポンスインターフェース (Responses)](https://docs.newapi.pro/api/openai-responses)
+- [イメージインターフェース (Image)](https://docs.newapi.pro/api/openai-image)
+- [オーディオインターフェース (Audio)](https://docs.newapi.pro/api/openai-audio)
+- [ビデオインターフェース (Video)](https://docs.newapi.pro/api/openai-video)
+- [エンベッドインターフェース (Embeddings)](https://docs.newapi.pro/api/openai-embeddings)
+- [再ランク付けインターフェース (Rerank)](https://docs.newapi.pro/api/jinaai-rerank)
+- [リアルタイム対話インターフェース (Realtime)](https://docs.newapi.pro/api/openai-realtime)
+- [Claudeチャット](https://docs.newapi.pro/api/anthropic-chat)
+- [Google Geminiチャット](https://docs.newapi.pro/api/google-gemini-chat/)
 
 </details>
 
@@ -309,19 +308,10 @@ docker run --name new-api -d --restart always \
 | `SQL_DSN** | データベース接続文字列 | - |
 | `REDIS_CONN_STRING` | Redis接続文字列 | - |
 | `STREAMING_TIMEOUT` | ストリーミング応答のタイムアウト時間（秒） | `300` |
-| `STREAM_SCANNER_MAX_BUFFER_MB` | ストリームスキャナの1行あたりバッファ上限（MB）。4K画像など巨大なbase64 `data:` ペイロードを扱う場合は値を増加させてください | `64` |
-| `MAX_REQUEST_BODY_MB` | リクエストボディ最大サイズ（MB、**解凍後**に計測。巨大リクエスト/zip bomb によるメモリ枯渇を防止）。超過時は `413` | `32` |
 | `AZURE_DEFAULT_API_VERSION` | Azure APIバージョン | `2025-04-01-preview` |
 | `ERROR_LOG_ENABLED` | エラーログスイッチ | `false` |
-| `PYROSCOPE_URL` | Pyroscopeサーバーのアドレス | - |
-| `PYROSCOPE_APP_NAME` | Pyroscopeアプリ名 | `new-api` |
-| `PYROSCOPE_BASIC_AUTH_USER` | Pyroscope Basic Authユーザー | - |
-| `PYROSCOPE_BASIC_AUTH_PASSWORD` | Pyroscope Basic Authパスワード | - |
-| `PYROSCOPE_MUTEX_RATE` | Pyroscope mutexサンプリング率 | `5` |
-| `PYROSCOPE_BLOCK_RATE` | Pyroscope blockサンプリング率 | `5` |
-| `HOSTNAME` | Pyroscope用のホスト名タグ | `new-api` |
 
-📖 **完全な設定:** [環境変数ドキュメント](https://docs.newapi.pro/ja/docs/installation/config-maintenance/environment-variables)
+📖 **完全な設定:** [環境変数ドキュメント](https://docs.newapi.pro/installation/environment-variables)
 
 </details>
 
@@ -421,10 +411,10 @@ docker run --name new-api -d --restart always \
 
 | リソース | リンク |
 |------|------|
-| 📘 よくある質問 | [FAQ](https://docs.newapi.pro/ja/docs/support/faq) |
-| 💬 コミュニティ交流 | [交流チャネル](https://docs.newapi.pro/ja/docs/support/community-interaction) |
-| 🐛 問題のフィードバック | [問題フィードバック](https://docs.newapi.pro/ja/docs/support/feedback-issues) |
-| 📚 完全なドキュメント | [公式ドキュメント](https://docs.newapi.pro/ja/docs) |
+| 📘 よくある質問 | [FAQ](https://docs.newapi.pro/support/faq) |
+| 💬 コミュニティ交流 | [交流チャネル](https://docs.newapi.pro/support/community-interaction) |
+| 🐛 問題のフィードバック | [問題フィードバック](https://docs.newapi.pro/support/feedback-issues) |
+| 📚 完全なドキュメント | [公式ドキュメント](https://docs.newapi.pro/support) |
 
 ### 🤝 貢献ガイド
 
@@ -453,7 +443,7 @@ docker run --name new-api -d --restart always \
 
 このプロジェクトがあなたのお役に立てたなら、ぜひ ⭐️ スターをください！
 
-**[公式ドキュメント](https://docs.newapi.pro/ja/docs)** • **[問題フィードバック](https://github.com/Calcium-Ion/new-api/issues)** • **[最新リリース](https://github.com/Calcium-Ion/new-api/releases)**
+**[公式ドキュメント](https://docs.newapi.pro/)** • **[問題フィードバック](https://github.com/Calcium-Ion/new-api/issues)** • **[最新リリース](https://github.com/Calcium-Ion/new-api/releases)**
 
 <sub>❤️ で構築された QuantumNous</sub>
 

README.md

@@ -146,7 +146,7 @@ docker run --name new-api -d --restart always \
 
 🎉 部署完成后，访问 `http://localhost:3000` 即可使用！
 
-📖 更多部署方式请参考 [部署指南](https://docs.newapi.pro/zh/docs/installation)
+📖 更多部署方式请参考 [部署指南](https://docs.newapi.pro/installation)
 
 ---
 
@@ -154,7 +154,7 @@ docker run --name new-api -d --restart always \
 
 <div align="center">
 
-### 📖 [官方文档](https://docs.newapi.pro/zh/docs) | [![Ask DeepWiki](https://deepwiki.com/badge.svg)](https://deepwiki.com/QuantumNous/new-api)
+### 📖 [官方文档](https://docs.newapi.pro/) | [![Ask DeepWiki](https://deepwiki.com/badge.svg)](https://deepwiki.com/QuantumNous/new-api)
 
 </div>
 
@@ -162,17 +162,17 @@ docker run --name new-api -d --restart always \
 
 | 分类 | 链接 |
 |------|------|
-| 🚀 部署指南 | [安装文档](https://docs.newapi.pro/zh/docs/installation) |
-| ⚙️ 环境配置 | [环境变量](https://docs.newapi.pro/zh/docs/installation/config-maintenance/environment-variables) |
-| 📡 接口文档 | [API 文档](https://docs.newapi.pro/zh/docs/api) |
-| ❓ 常见问题 | [FAQ](https://docs.newapi.pro/zh/docs/support/faq) |
-| 💬 社区交流 | [交流渠道](https://docs.newapi.pro/zh/docs/support/community-interaction) |
+| 🚀 部署指南 | [安装文档](https://docs.newapi.pro/installation) |
+| ⚙️ 环境配置 | [环境变量](https://docs.newapi.pro/installation/environment-variables) |
+| 📡 接口文档 | [API 文档](https://docs.newapi.pro/api) |
+| ❓ 常见问题 | [FAQ](https://docs.newapi.pro/support/faq) |
+| 💬 社区交流 | [交流渠道](https://docs.newapi.pro/support/community-interaction) |
 
 ---
 
 ## ✨ 主要特性
 
-> 详细特性请参考 [特性说明](https://docs.newapi.pro/zh/docs/guide/wiki/basic-concepts/features-introduction)
+> 详细特性请参考 [特性说明](https://docs.newapi.pro/wiki/features-introduction)
 
 ### 🎨 核心功能
 
@@ -202,11 +202,11 @@ docker run --name new-api -d --restart always \
 ### 🚀 高级功能
 
 **API 格式支持：**
-- ⚡ [OpenAI Responses](https://docs.newapi.pro/zh/docs/api/ai-model/chat/openai/create-response)
-- ⚡ [OpenAI Realtime API](https://docs.newapi.pro/zh/docs/api/ai-model/realtime/create-realtime-session)（含 Azure）
-- ⚡ [Claude Messages](https://docs.newapi.pro/zh/docs/api/ai-model/chat/create-message)
-- ⚡ [Google Gemini](https://doc.newapi.pro/api/google-gemini-chat)
-- 🔄 [Rerank 模型](https://docs.newapi.pro/zh/docs/api/ai-model/rerank/create-rerank)（Cohere、Jina）
+- ⚡ [OpenAI Responses](https://docs.newapi.pro/api/openai-responses)
+- ⚡ [OpenAI Realtime API](https://docs.newapi.pro/api/openai-realtime)（含 Azure）
+- ⚡ [Claude Messages](https://docs.newapi.pro/api/anthropic-chat)
+- ⚡ [Google Gemini](https://docs.newapi.pro/api/google-gemini-chat/)
+- 🔄 [Rerank 模型](https://docs.newapi.pro/api/jinaai-rerank)（Cohere、Jina）
 
 **智能路由：**
 - ⚖️ 渠道加权随机
@@ -239,7 +239,6 @@ docker run --name new-api -d --restart always \
 - `gemini-2.5-flash-nothinking` - 禁用思考模式
 - `gemini-2.5-pro-thinking` - 启用思考模式
 - `gemini-2.5-pro-thinking-128` - 启用思考模式，并设置思考预算为128tokens
-- 也可以直接在 Gemini 模型名称后追加 `-low` / `-medium` / `-high` 来控制思考力度（无需再设置思考预算后缀）
 
 </details>
 
@@ -247,16 +246,16 @@ docker run --name new-api -d --restart always \
 
 ## 🤖 模型支持
 
-> 详情请参考 [接口文档 - 中继接口](https://docs.newapi.pro/zh/docs/api)
+> 详情请参考 [接口文档 - 中继接口](https://docs.newapi.pro/api)
 
 | 模型类型 | 说明 | 文档 |
 |---------|------|------|
 | 🤖 OpenAI GPTs | gpt-4-gizmo-* 系列 | - |
-| 🎨 Midjourney-Proxy | [Midjourney-Proxy(Plus)](https://github.com/novicezk/midjourney-proxy) | [文档](https://doc.newapi.pro/api/midjourney-proxy-image) |
-| 🎵 Suno-API | [Suno API](https://github.com/Suno-API/Suno-API) | [文档](https://doc.newapi.pro/api/suno-music) |
-| 🔄 Rerank | Cohere、Jina | [文档](https://docs.newapi.pro/zh/docs/api/ai-model/rerank/create-rerank) |
-| 💬 Claude | Messages 格式 | [文档](https://docs.newapi.pro/zh/docs/api/ai-model/chat/create-message) |
-| 🌐 Gemini | Google Gemini 格式 | [文档](https://doc.newapi.pro/api/google-gemini-chat) |
+| 🎨 Midjourney-Proxy | [Midjourney-Proxy(Plus)](https://github.com/novicezk/midjourney-proxy) | [文档](https://docs.newapi.pro/api/midjourney-proxy-image) |
+| 🎵 Suno-API | [Suno API](https://github.com/Suno-API/Suno-API) | [文档](https://docs.newapi.pro/api/suno-music) |
+| 🔄 Rerank | Cohere、Jina | [文档](https://docs.newapi.pro/api/jinaai-rerank) |
+| 💬 Claude | Messages 格式 | [文档](https://docs.newapi.pro/api/anthropic-chat) |
+| 🌐 Gemini | Google Gemini 格式 | [文档](https://docs.newapi.pro/api/google-gemini-chat/) |
 | 🔧 Dify | ChatFlow 模式 | - |
 | 🎯 自定义 | 支持完整调用地址 | - |
 
@@ -265,16 +264,16 @@ docker run --name new-api -d --restart always \
 <details>
 <summary>查看完整接口列表</summary>
 
-- [聊天接口 (Chat Completions)](https://docs.newapi.pro/zh/docs/api/ai-model/chat/openai/create-chat-completion)
-- [响应接口 (Responses)](https://docs.newapi.pro/zh/docs/api/ai-model/chat/openai/create-response)
-- [图像接口 (Image)](https://docs.newapi.pro/zh/docs/api/ai-model/images/openai/v1-images-generations--post)
-- [音频接口 (Audio)](https://docs.newapi.pro/zh/docs/api/ai-model/audio/openai/create-transcription)
-- [视频接口 (Video)](https://docs.newapi.pro/zh/docs/api/ai-model/videos/create-video-generation)
-- [嵌入接口 (Embeddings)](https://docs.newapi.pro/zh/docs/api/ai-model/embeddings/create-embedding)
-- [重排序接口 (Rerank)](https://docs.newapi.pro/zh/docs/api/ai-model/rerank/create-rerank)
-- [实时对话 (Realtime)](https://docs.newapi.pro/zh/docs/api/ai-model/realtime/create-realtime-session)
-- [Claude 聊天](https://docs.newapi.pro/zh/docs/api/ai-model/chat/create-message)
-- [Google Gemini 聊天](https://doc.newapi.pro/api/google-gemini-chat)
+- [聊天接口 (Chat Completions)](https://docs.newapi.pro/api/openai-chat)
+- [响应接口 (Responses)](https://docs.newapi.pro/api/openai-responses)
+- [图像接口 (Image)](https://docs.newapi.pro/api/openai-image)
+- [音频接口 (Audio)](https://docs.newapi.pro/api/openai-audio)
+- [视频接口 (Video)](https://docs.newapi.pro/api/openai-video)
+- [嵌入接口 (Embeddings)](https://docs.newapi.pro/api/openai-embeddings)
+- [重排序接口 (Rerank)](https://docs.newapi.pro/api/jinaai-rerank)
+- [实时对话 (Realtime)](https://docs.newapi.pro/api/openai-realtime)
+- [Claude 聊天](https://docs.newapi.pro/api/anthropic-chat)
+- [Google Gemini 聊天](https://docs.newapi.pro/api/google-gemini-chat)
 
 </details>
 
@@ -298,26 +297,17 @@ docker run --name new-api -d --restart always \
 <details>
 <summary>常用环境变量配置</summary>
 
-| 变量名 | 说明                                                           | 默认值 |
-|--------|--------------------------------------------------------------|--------|
-| `SESSION_SECRET` | 会话密钥（多机部署必须）                                                 | - |
-| `CRYPTO_SECRET` | 加密密钥（Redis 必须）                                               | - |
-| `SQL_DSN` | 数据库连接字符串                                                     | - |
-| `REDIS_CONN_STRING` | Redis 连接字符串                                                  | - |
-| `STREAMING_TIMEOUT` | 流式超时时间（秒）                                                    | `300` |
-| `STREAM_SCANNER_MAX_BUFFER_MB` | 流式扫描器单行最大缓冲（MB），图像生成等超大 `data:` 片段（如 4K 图片 base64）需适当调大 | `64` |
-| `MAX_REQUEST_BODY_MB` | 请求体最大大小（MB，**解压后**计；防止超大请求/zip bomb 导致内存暴涨），超过将返回 `413` | `32` |
-| `AZURE_DEFAULT_API_VERSION` | Azure API 版本                                                 | `2025-04-01-preview` |
-| `ERROR_LOG_ENABLED` | 错误日志开关                                                       | `false` |
-| `PYROSCOPE_URL` | Pyroscope 服务地址                                            | - |
-| `PYROSCOPE_APP_NAME` | Pyroscope 应用名                                        | `new-api` |
-| `PYROSCOPE_BASIC_AUTH_USER` | Pyroscope Basic Auth 用户名                        | - |
-| `PYROSCOPE_BASIC_AUTH_PASSWORD` | Pyroscope Basic Auth 密码                  | - |
-| `PYROSCOPE_MUTEX_RATE` | Pyroscope mutex 采样率                               | `5` |
-| `PYROSCOPE_BLOCK_RATE` | Pyroscope block 采样率                               | `5` |
-| `HOSTNAME` | Pyroscope 标签里的主机名                                          | `new-api` |
+| 变量名 | 说明 | 默认值 |
+|--------|------|--------|
+| `SESSION_SECRET` | 会话密钥（多机部署必须） | - |
+| `CRYPTO_SECRET` | 加密密钥（Redis 必须） | - |
+| `SQL_DSN` | 数据库连接字符串 | - |
+| `REDIS_CONN_STRING` | Redis 连接字符串 | - |
+| `STREAMING_TIMEOUT` | 流式超时时间（秒） | `300` |
+| `AZURE_DEFAULT_API_VERSION` | Azure API 版本 | `2025-04-01-preview` |
+| `ERROR_LOG_ENABLED` | 错误日志开关 | `false` |
 
-📖 **完整配置：** [环境变量文档](https://docs.newapi.pro/zh/docs/installation/config-maintenance/environment-variables)
+📖 **完整配置：** [环境变量文档](https://docs.newapi.pro/installation/environment-variables)
 
 </details>
 
@@ -419,10 +409,10 @@ docker run --name new-api -d --restart always \
 
 | 资源 | 链接 |
 |------|------|
-| 📘 常见问题 | [FAQ](https://docs.newapi.pro/zh/docs/support/faq) |
-| 💬 社区交流 | [交流渠道](https://docs.newapi.pro/zh/docs/support/community-interaction) |
-| 🐛 反馈问题 | [问题反馈](https://docs.newapi.pro/zh/docs/support/feedback-issues) |
-| 📚 完整文档 | [官方文档](https://docs.newapi.pro/zh/docs) |
+| 📘 常见问题 | [FAQ](https://docs.newapi.pro/support/faq) |
+| 💬 社区交流 | [交流渠道](https://docs.newapi.pro/support/community-interaction) |
+| 🐛 反馈问题 | [问题反馈](https://docs.newapi.pro/support/feedback-issues) |
+| 📚 完整文档 | [官方文档](https://docs.newapi.pro/support) |
 
 ### 🤝 贡献指南
 
@@ -451,7 +441,7 @@ docker run --name new-api -d --restart always \
 
 如果这个项目对你有帮助，欢迎给我们一个 ⭐️ Star！
 
-**[官方文档](https://docs.newapi.pro/zh/docs)** • **[问题反馈](https://github.com/Calcium-Ion/new-api/issues)** • **[最新发布](https://github.com/Calcium-Ion/new-api/releases)**
+**[官方文档](https://docs.newapi.pro/)** • **[问题反馈](https://github.com/Calcium-Ion/new-api/issues)** • **[最新发布](https://github.com/Calcium-Ion/new-api/releases)**
 
 <sub>Built with ❤️ by QuantumNous</sub>
 

common/audio.go

@@ -71,66 +71,15 @@ func getMP3Duration(r io.Reader) (float64, error) {
 
 // getWAVDuration 解析 WAV 文件头以获取时长。
 func getWAVDuration(r io.ReadSeeker) (float64, error) {
-	// 1. 强制复位指针
-	r.Seek(0, io.SeekStart)
-
 	dec := wav.NewDecoder(r)
-
-	// IsValidFile 会读取 fmt 块
 	if !dec.IsValidFile() {
 		return 0, errors.New("invalid wav file")
 	}
-
-	// 尝试寻找 data 块
-	if err := dec.FwdToPCM(); err != nil {
-		return 0, errors.Wrap(err, "failed to find PCM data chunk")
+	d, err := dec.Duration()
+	if err != nil {
+		return 0, errors.Wrap(err, "failed to get wav duration")
 	}
-
-	pcmSize := int64(dec.PCMSize)
-
-	// 如果读出来的 Size 是 0，尝试用文件大小反推
-	if pcmSize == 0 {
-		// 获取文件总大小
-		currentPos, _ := r.Seek(0, io.SeekCurrent) // 当前通常在 data chunk header 之后
-		endPos, _ := r.Seek(0, io.SeekEnd)
-		fileSize := endPos
-
-		// 恢复位置（虽然如果不继续读也没关系）
-		r.Seek(currentPos, io.SeekStart)
-
-		// 数据区大小 ≈ 文件总大小 - 当前指针位置(即Header大小)
-		// 注意：FwdToPCM 成功后，CurrentPos 应该刚好指向 Data 区数据的开始
-		// 或者是 Data Chunk ID + Size 之后。
-		// WAV Header 一般 44 字节。
-		if fileSize > 44 {
-			// 如果 FwdToPCM 成功，Reader 应该位于 data 块的数据起始处
-			// 所以剩余的所有字节理论上都是音频数据
-			pcmSize = fileSize - currentPos
-
-			// 简单的兜底：如果算出来还是负数或0，强制按文件大小-44计算
-			if pcmSize <= 0 {
-				pcmSize = fileSize - 44
-			}
-		}
-	}
-
-	numChans := int64(dec.NumChans)
-	bitDepth := int64(dec.BitDepth)
-	sampleRate := float64(dec.SampleRate)
-
-	if sampleRate == 0 || numChans == 0 || bitDepth == 0 {
-		return 0, errors.New("invalid wav header metadata")
-	}
-
-	bytesPerFrame := numChans * (bitDepth / 8)
-	if bytesPerFrame == 0 {
-		return 0, errors.New("invalid byte depth calculation")
-	}
-
-	totalFrames := pcmSize / bytesPerFrame
-
-	durationSeconds := float64(totalFrames) / sampleRate
-	return durationSeconds, nil
+	return d.Seconds(), nil
 }
 
 // getFLACDuration 解析 FLAC 文件的 STREAMINFO 块。

common/constants.go

@@ -121,9 +121,6 @@ var BatchUpdateInterval int
 
 var RelayTimeout int // unit is second
 
-var RelayMaxIdleConns int
-var RelayMaxIdleConnsPerHost int
-
 var GeminiSafetySetting string
 
 // https://docs.cohere.com/docs/safety-modes Type; NONE/CONTEXTUAL/STRICT

common/email.go

@@ -32,7 +32,7 @@ func SendEmail(subject string, receiver string, content string) error {
 	}
 	encodedSubject := fmt.Sprintf("=?UTF-8?B?%s?=", base64.StdEncoding.EncodeToString([]byte(subject)))
 	mail := []byte(fmt.Sprintf("To: %s\r\n"+
-		"From: %s <%s>\r\n"+
+		"From: %s<%s>\r\n"+
 		"Subject: %s\r\n"+
 		"Date: %s\r\n"+
 		"Message-ID: %s\r\n"+ // 添加 Message-ID 头

common/embed-file-system.go

@@ -4,7 +4,6 @@ import (
 	"embed"
 	"io/fs"
 	"net/http"
-	"os"
 
 	"github.com/gin-contrib/static"
 )
@@ -15,7 +14,7 @@ type embedFileSystem struct {
 	http.FileSystem
 }
 
-func (e *embedFileSystem) Exists(prefix string, path string) bool {
+func (e embedFileSystem) Exists(prefix string, path string) bool {
 	_, err := e.Open(path)
 	if err != nil {
 		return false
@@ -23,21 +22,12 @@ func (e *embedFileSystem) Exists(prefix string, path string) bool {
 	return true
 }
 
-func (e *embedFileSystem) Open(name string) (http.File, error) {
-	if name == "/" {
-		// This will make sure the index page goes to NoRouter handler,
-		// which will use the replaced index bytes with analytic codes.
-		return nil, os.ErrNotExist
-	}
-	return e.FileSystem.Open(name)
-}
-
 func EmbedFolder(fsEmbed embed.FS, targetPath string) static.ServeFileSystem {
 	efs, err := fs.Sub(fsEmbed, targetPath)
 	if err != nil {
 		panic(err)
 	}
-	return &embedFileSystem{
+	return embedFileSystem{
 		FileSystem: http.FS(efs),
 	}
 }

common/gin.go

@@ -2,7 +2,7 @@ package common
 
 import (
 	"bytes"
-	"fmt"
+	"errors"
 	"io"
 	"mime"
 	"mime/multipart"
@@ -12,61 +12,24 @@ import (
 	"time"
 
 	"github.com/QuantumNous/new-api/constant"
-	"github.com/pkg/errors"
 
 	"github.com/gin-gonic/gin"
 )
 
 const KeyRequestBody = "key_request_body"
 
-var ErrRequestBodyTooLarge = errors.New("request body too large")
-
-func IsRequestBodyTooLargeError(err error) bool {
-	if err == nil {
-		return false
-	}
-	if errors.Is(err, ErrRequestBodyTooLarge) {
-		return true
-	}
-	var mbe *http.MaxBytesError
-	return errors.As(err, &mbe)
-}
-
 func GetRequestBody(c *gin.Context) ([]byte, error) {
-	cached, exists := c.Get(KeyRequestBody)
-	if exists && cached != nil {
-		if b, ok := cached.([]byte); ok {
-			return b, nil
-		}
+	requestBody, _ := c.Get(KeyRequestBody)
+	if requestBody != nil {
+		return requestBody.([]byte), nil
 	}
-	maxMB := constant.MaxRequestBodyMB
-	if maxMB < 0 {
-		// no limit
-		body, err := io.ReadAll(c.Request.Body)
-		_ = c.Request.Body.Close()
-		if err != nil {
-			return nil, err
-		}
-		c.Set(KeyRequestBody, body)
-		return body, nil
-	}
-	maxBytes := int64(maxMB) << 20
-
-	limited := io.LimitReader(c.Request.Body, maxBytes+1)
-	body, err := io.ReadAll(limited)
+	requestBody, err := io.ReadAll(c.Request.Body)
 	if err != nil {
-		_ = c.Request.Body.Close()
-		if IsRequestBodyTooLargeError(err) {
-			return nil, errors.Wrap(ErrRequestBodyTooLarge, fmt.Sprintf("request body exceeds %d MB", maxMB))
-		}
 		return nil, err
 	}
 	_ = c.Request.Body.Close()
-	if int64(len(body)) > maxBytes {
-		return nil, errors.Wrap(ErrRequestBodyTooLarge, fmt.Sprintf("request body exceeds %d MB", maxMB))
-	}
-	c.Set(KeyRequestBody, body)
-	return body, nil
+	c.Set(KeyRequestBody, requestBody)
+	return requestBody.([]byte), nil
 }
 
 func UnmarshalBodyReusable(c *gin.Context, v any) error {

common/init.go

@@ -90,8 +90,6 @@ func InitEnv() {
 	SyncFrequency = GetEnvOrDefault("SYNC_FREQUENCY", 60)
 	BatchUpdateInterval = GetEnvOrDefault("BATCH_UPDATE_INTERVAL", 5)
 	RelayTimeout = GetEnvOrDefault("RELAY_TIMEOUT", 0)
-	RelayMaxIdleConns = GetEnvOrDefault("RELAY_MAX_IDLE_CONNS", 500)
-	RelayMaxIdleConnsPerHost = GetEnvOrDefault("RELAY_MAX_IDLE_CONNS_PER_HOST", 100)
 
 	// Initialize string variables with GetEnvOrDefaultString
 	GeminiSafetySetting = GetEnvOrDefaultString("GEMINI_SAFETY_SETTING", "BLOCK_NONE")
@@ -116,9 +114,6 @@ func initConstantEnv() {
 	constant.StreamingTimeout = GetEnvOrDefault("STREAMING_TIMEOUT", 300)
 	constant.DifyDebug = GetEnvOrDefaultBool("DIFY_DEBUG", true)
 	constant.MaxFileDownloadMB = GetEnvOrDefault("MAX_FILE_DOWNLOAD_MB", 20)
-	constant.StreamScannerMaxBufferMB = GetEnvOrDefault("STREAM_SCANNER_MAX_BUFFER_MB", 64)
-	// MaxRequestBodyMB 请求体最大大小（解压后），用于防止超大请求/zip bomb导致内存暴涨
-	constant.MaxRequestBodyMB = GetEnvOrDefault("MAX_REQUEST_BODY_MB", 64)
 	// ForceStreamOption 覆盖请求参数，强制返回usage信息
 	constant.ForceStreamOption = GetEnvOrDefaultBool("FORCE_STREAM_OPTION", true)
 	constant.CountToken = GetEnvOrDefaultBool("CountToken", true)
@@ -133,8 +128,6 @@ func initConstantEnv() {
 	constant.GenerateDefaultToken = GetEnvOrDefaultBool("GENERATE_DEFAULT_TOKEN", false)
 	// 是否启用错误日志
 	constant.ErrorLogEnabled = GetEnvOrDefaultBool("ERROR_LOG_ENABLED", false)
-	// 任务轮询时查询的最大数量
-	constant.TaskQueryLimit = GetEnvOrDefault("TASK_QUERY_LIMIT", 1000)
 
 	soraPatchStr := GetEnvOrDefaultString("TASK_PRICE_PATCH", "")
 	if soraPatchStr != "" {

common/ip.go

@@ -2,15 +2,6 @@ package common
 
 import "net"
 
-func IsIP(s string) bool {
-	ip := net.ParseIP(s)
-	return ip != nil
-}
-
-func ParseIP(s string) net.IP {
-	return net.ParseIP(s)
-}
-
 func IsPrivateIP(ip net.IP) bool {
 	if ip.IsLoopback() || ip.IsLinkLocalUnicast() || ip.IsLinkLocalMulticast() {
 		return true
@@ -29,23 +20,3 @@ func IsPrivateIP(ip net.IP) bool {
 	}
 	return false
 }
-
-func IsIpInCIDRList(ip net.IP, cidrList []string) bool {
-	for _, cidr := range cidrList {
-		_, network, err := net.ParseCIDR(cidr)
-		if err != nil {
-			// 尝试作为单个IP处理
-			if whitelistIP := net.ParseIP(cidr); whitelistIP != nil {
-				if ip.Equal(whitelistIP) {
-					return true
-				}
-			}
-			continue
-		}
-
-		if network.Contains(ip) {
-			return true
-		}
-	}
-	return false
-}

common/json.go

@@ -23,11 +23,11 @@ func Marshal(v any) ([]byte, error) {
 }
 
 func GetJsonType(data json.RawMessage) string {
-	trimmed := bytes.TrimSpace(data)
-	if len(trimmed) == 0 {
+	data = bytes.TrimSpace(data)
+	if len(data) == 0 {
 		return "unknown"
 	}
-	firstChar := trimmed[0]
+	firstChar := bytes.TrimSpace(data)[0]
 	switch firstChar {
 	case '{':
 		return "object"

common/model.go

@@ -17,13 +17,6 @@ var (
 		"flux-",
 		"flux.1-",
 	}
-	OpenAITextModels = []string{
-		"gpt-",
-		"o1",
-		"o3",
-		"o4",
-		"chatgpt",
-	}
 )
 
 func IsOpenAIResponseOnlyModel(modelName string) bool {
@@ -47,13 +40,3 @@ func IsImageGenerationModel(modelName string) bool {
 	}
 	return false
 }
-
-func IsOpenAITextModel(modelName string) bool {
-	modelName = strings.ToLower(modelName)
-	for _, m := range OpenAITextModels {
-		if strings.Contains(modelName, m) {
-			return true
-		}
-	}
-	return false
-}

common/pyro.go

@@ -1,56 +0,0 @@
-package common
-
-import (
-	"runtime"
-
-	"github.com/grafana/pyroscope-go"
-)
-
-func StartPyroScope() error {
-
-	pyroscopeUrl := GetEnvOrDefaultString("PYROSCOPE_URL", "")
-	if pyroscopeUrl == "" {
-		return nil
-	}
-
-	pyroscopeAppName := GetEnvOrDefaultString("PYROSCOPE_APP_NAME", "new-api")
-	pyroscopeBasicAuthUser := GetEnvOrDefaultString("PYROSCOPE_BASIC_AUTH_USER", "")
-	pyroscopeBasicAuthPassword := GetEnvOrDefaultString("PYROSCOPE_BASIC_AUTH_PASSWORD", "")
-	pyroscopeHostname := GetEnvOrDefaultString("HOSTNAME", "new-api")
-
-	mutexRate := GetEnvOrDefault("PYROSCOPE_MUTEX_RATE", 5)
-	blockRate := GetEnvOrDefault("PYROSCOPE_BLOCK_RATE", 5)
-
-	runtime.SetMutexProfileFraction(mutexRate)
-	runtime.SetBlockProfileRate(blockRate)
-
-	_, err := pyroscope.Start(pyroscope.Config{
-		ApplicationName: pyroscopeAppName,
-
-		ServerAddress:     pyroscopeUrl,
-		BasicAuthUser:     pyroscopeBasicAuthUser,
-		BasicAuthPassword: pyroscopeBasicAuthPassword,
-
-		Logger: nil,
-
-		Tags: map[string]string{"hostname": pyroscopeHostname},
-
-		ProfileTypes: []pyroscope.ProfileType{
-			pyroscope.ProfileCPU,
-			pyroscope.ProfileAllocObjects,
-			pyroscope.ProfileAllocSpace,
-			pyroscope.ProfileInuseObjects,
-			pyroscope.ProfileInuseSpace,
-
-			pyroscope.ProfileGoroutines,
-			pyroscope.ProfileMutexCount,
-			pyroscope.ProfileMutexDuration,
-			pyroscope.ProfileBlockCount,
-			pyroscope.ProfileBlockDuration,
-		},
-	})
-	if err != nil {
-		return err
-	}
-	return nil
-}

common/ssrf_protection.go

@@ -186,7 +186,23 @@ func isIPListed(ip net.IP, list []string) bool {
 		return false
 	}
 
-	return IsIpInCIDRList(ip, list)
+	for _, whitelistCIDR := range list {
+		_, network, err := net.ParseCIDR(whitelistCIDR)
+		if err != nil {
+			// 尝试作为单个IP处理
+			if whitelistIP := net.ParseIP(whitelistCIDR); whitelistIP != nil {
+				if ip.Equal(whitelistIP) {
+					return true
+				}
+			}
+			continue
+		}
+
+		if network.Contains(ip) {
+			return true
+		}
+	}
+	return false
 }
 
 // IsIPAccessAllowed 检查IP是否允许访问

common/str.go

@@ -3,19 +3,12 @@ package common
 import (
 	"encoding/base64"
 	"encoding/json"
+	"math/rand"
 	"net/url"
 	"regexp"
 	"strconv"
 	"strings"
 	"unsafe"
-
-	"github.com/samber/lo"
-)
-
-var (
-	maskURLPattern    = regexp.MustCompile(`(http|https)://[^\s/$.?#].[^\s]*`)
-	maskDomainPattern = regexp.MustCompile(`\b(?:[a-zA-Z0-9](?:[a-zA-Z0-9-]{0,61}[a-zA-Z0-9])?\.)+[a-zA-Z]{2,}\b`)
-	maskIPPattern     = regexp.MustCompile(`\b(?:\d{1,3}\.){3}\d{1,3}\b`)
 )
 
 func GetStringIfEmpty(str string, defaultValue string) string {
@@ -26,10 +19,12 @@ func GetStringIfEmpty(str string, defaultValue string) string {
 }
 
 func GetRandomString(length int) string {
-	if length <= 0 {
-		return ""
+	//rand.Seed(time.Now().UnixNano())
+	key := make([]byte, length)
+	for i := 0; i < length; i++ {
+		key[i] = keyChars[rand.Intn(len(keyChars))]
 	}
-	return lo.RandomString(length, lo.AlphanumericCharset)
+	return string(key)
 }
 
 func MapToJsonStr(m map[string]interface{}) string {
@@ -175,7 +170,8 @@ func maskHostForPlainDomain(domain string) string {
 // api.openai.com -> ***.***.com
 func MaskSensitiveInfo(str string) string {
 	// Mask URLs
-	str = maskURLPattern.ReplaceAllStringFunc(str, func(urlStr string) string {
+	urlPattern := regexp.MustCompile(`(http|https)://[^\s/$.?#].[^\s]*`)
+	str = urlPattern.ReplaceAllStringFunc(str, func(urlStr string) string {
 		u, err := url.Parse(urlStr)
 		if err != nil {
 			return urlStr
@@ -228,12 +224,14 @@ func MaskSensitiveInfo(str string) string {
 	})
 
 	// Mask domain names without protocol (like openai.com, www.openai.com)
-	str = maskDomainPattern.ReplaceAllStringFunc(str, func(domain string) string {
+	domainPattern := regexp.MustCompile(`\b(?:[a-zA-Z0-9](?:[a-zA-Z0-9-]{0,61}[a-zA-Z0-9])?\.)+[a-zA-Z]{2,}\b`)
+	str = domainPattern.ReplaceAllStringFunc(str, func(domain string) string {
 		return maskHostForPlainDomain(domain)
 	})
 
 	// Mask IP addresses
-	str = maskIPPattern.ReplaceAllString(str, "***.***.***.***")
+	ipPattern := regexp.MustCompile(`\b(?:\d{1,3}\.){3}\d{1,3}\b`)
+	str = ipPattern.ReplaceAllString(str, "***.***.***.***")
 
 	return str
 }

common/utils.go

@@ -217,6 +217,11 @@ func IntMax(a int, b int) int {
 	}
 }
 
+func IsIP(s string) bool {
+	ip := net.ParseIP(s)
+	return ip != nil
+}
+
 func GetUUID() string {
 	code := uuid.New().String()
 	code = strings.Replace(code, "-", "", -1)

constant/channel.go

@@ -180,27 +180,3 @@ func GetChannelTypeName(channelType int) string {
 	}
 	return "Unknown"
 }
-
-type ChannelSpecialBase struct {
-	ClaudeBaseURL string
-	OpenAIBaseURL string
-}
-
-var ChannelSpecialBases = map[string]ChannelSpecialBase{
-	"glm-coding-plan": {
-		ClaudeBaseURL: "https://open.bigmodel.cn/api/anthropic",
-		OpenAIBaseURL: "https://open.bigmodel.cn/api/coding/paas/v4",
-	},
-	"glm-coding-plan-international": {
-		ClaudeBaseURL: "https://api.z.ai/api/anthropic",
-		OpenAIBaseURL: "https://api.z.ai/api/coding/paas/v4",
-	},
-	"kimi-coding-plan": {
-		ClaudeBaseURL: "https://api.kimi.com/coding",
-		OpenAIBaseURL: "https://api.kimi.com/coding/v1",
-	},
-	"doubao-coding-plan": {
-		ClaudeBaseURL: "https://ark.cn-beijing.volces.com/api/coding",
-		OpenAIBaseURL: "https://ark.cn-beijing.volces.com/api/coding/v3",
-	},
-}

constant/context_key.go

@@ -3,9 +3,8 @@ package constant
 type ContextKey string
 
 const (
-	ContextKeyTokenCountMeta  ContextKey = "token_count_meta"
-	ContextKeyPromptTokens    ContextKey = "prompt_tokens"
-	ContextKeyEstimatedTokens ContextKey = "estimated_tokens"
+	ContextKeyTokenCountMeta ContextKey = "token_count_meta"
+	ContextKeyPromptTokens   ContextKey = "prompt_tokens"
 
 	ContextKeyOriginalModel    ContextKey = "original_model"
 	ContextKeyRequestStartTime ContextKey = "request_start_time"
@@ -18,7 +17,6 @@ const (
 	ContextKeyTokenSpecificChannelId ContextKey = "specific_channel_id"
 	ContextKeyTokenModelLimitEnabled ContextKey = "token_model_limit_enabled"
 	ContextKeyTokenModelLimit        ContextKey = "token_model_limit"
-	ContextKeyTokenCrossGroupRetry   ContextKey = "token_cross_group_retry"
 
 	/* channel related keys */
 	ContextKeyChannelId                ContextKey = "channel_id"
@@ -38,10 +36,6 @@ const (
 	ContextKeyChannelMultiKeyIndex     ContextKey = "channel_multi_key_index"
 	ContextKeyChannelKey               ContextKey = "channel_key"
 
-	ContextKeyAutoGroup           ContextKey = "auto_group"
-	ContextKeyAutoGroupIndex      ContextKey = "auto_group_index"
-	ContextKeyAutoGroupRetryIndex ContextKey = "auto_group_retry_index"
-
 	/* user related keys */
 	ContextKeyUserId      ContextKey = "id"
 	ContextKeyUserSetting ContextKey = "user_setting"

constant/env.go

@@ -3,20 +3,17 @@ package constant
 var StreamingTimeout int
 var DifyDebug bool
 var MaxFileDownloadMB int
-var StreamScannerMaxBufferMB int
 var ForceStreamOption bool
 var CountToken bool
 var GetMediaToken bool
 var GetMediaTokenNotStream bool
 var UpdateTask bool
-var MaxRequestBodyMB int
 var AzureDefaultAPIVersion string
 var GeminiVisionMaxImageNum int
 var NotifyLimitCount int
 var NotificationLimitDurationMinute int
 var GenerateDefaultToken bool
 var ErrorLogEnabled bool
-var TaskQueryLimit int
 
 // temporary variable for sora patch, will be removed in future
 var TaskPricePatches []string

constant/task.go

@@ -15,7 +15,6 @@ const (
 	TaskActionTextGenerate      = "textGenerate"
 	TaskActionFirstTailGenerate = "firstTailGenerate"
 	TaskActionReferenceGenerate = "referenceGenerate"
-	TaskActionRemix             = "remixGenerate"
 )
 
 var SunoModel2Action = map[string]string{

controller/billing.go

@@ -2,9 +2,9 @@ package controller
 
 import (
 	"github.com/QuantumNous/new-api/common"
+	"github.com/QuantumNous/new-api/dto"
 	"github.com/QuantumNous/new-api/model"
 	"github.com/QuantumNous/new-api/setting/operation_setting"
-	"github.com/QuantumNous/new-api/types"
 	"github.com/gin-gonic/gin"
 )
 
@@ -29,7 +29,7 @@ func GetSubscription(c *gin.Context) {
 		expiredTime = 0
 	}
 	if err != nil {
-		openAIError := types.OpenAIError{
+		openAIError := dto.OpenAIError{
 			Message: err.Error(),
 			Type:    "upstream_error",
 		}
@@ -81,7 +81,7 @@ func GetUsage(c *gin.Context) {
 		quota, err = model.GetUserUsedQuota(userId)
 	}
 	if err != nil {
-		openAIError := types.OpenAIError{
+		openAIError := dto.OpenAIError{
 			Message: err.Error(),
 			Type:    "new_api_error",
 		}

controller/channel-test.go

@@ -97,11 +97,6 @@ func testChannel(channel *model.Channel, testModel string, endpointType string)
 		if channel.Type == constant.ChannelTypeVolcEngine && strings.Contains(testModel, "seedream") {
 			requestPath = "/v1/images/generations"
 		}
-
-		// responses-only models
-		if strings.Contains(strings.ToLower(testModel), "codex") {
-			requestPath = "/v1/responses"
-		}
 	}
 
 	c.Request = &http.Request{
@@ -181,7 +176,7 @@ func testChannel(channel *model.Channel, testModel string, endpointType string)
 		}
 	}
 
-	request := buildTestRequest(testModel, endpointType, channel)
+	request := buildTestRequest(testModel, endpointType)
 
 	info, err := relaycommon.GenRelayInfo(c, relayFormat, request, nil)
 
@@ -324,16 +319,6 @@ func testChannel(channel *model.Channel, testModel string, endpointType string)
 		httpResp = resp.(*http.Response)
 		if httpResp.StatusCode != http.StatusOK {
 			err := service.RelayErrorHandler(c.Request.Context(), httpResp, true)
-			common.SysError(fmt.Sprintf(
-				"channel test bad response: channel_id=%d name=%s type=%d model=%s endpoint_type=%s status=%d err=%v",
-				channel.Id,
-				channel.Name,
-				channel.Type,
-				testModel,
-				endpointType,
-				httpResp.StatusCode,
-				err,
-			))
 			return testResult{
 				context:     c,
 				localErr:    err,
@@ -366,7 +351,7 @@ func testChannel(channel *model.Channel, testModel string, endpointType string)
 			newAPIError: types.NewOpenAIError(err, types.ErrorCodeReadResponseBodyFailed, http.StatusInternalServerError),
 		}
 	}
-	info.SetEstimatePromptTokens(usage.PromptTokens)
+	info.PromptTokens = usage.PromptTokens
 
 	quota := 0
 	if !priceData.UsePrice {
@@ -404,7 +389,7 @@ func testChannel(channel *model.Channel, testModel string, endpointType string)
 	}
 }
 
-func buildTestRequest(model string, endpointType string, channel *model.Channel) dto.Request {
+func buildTestRequest(model string, endpointType string) dto.Request {
 	// 根据端点类型构建不同的测试请求
 	if endpointType != "" {
 		switch constant.EndpointType(endpointType) {
@@ -438,7 +423,7 @@ func buildTestRequest(model string, endpointType string, channel *model.Channel)
 			}
 		case constant.EndpointTypeAnthropic, constant.EndpointTypeGemini, constant.EndpointTypeOpenAI:
 			// 返回 GeneralOpenAIRequest
-			maxTokens := uint(16)
+			maxTokens := uint(10)
 			if constant.EndpointType(endpointType) == constant.EndpointTypeGemini {
 				maxTokens = 3000
 			}
@@ -468,14 +453,6 @@ func buildTestRequest(model string, endpointType string, channel *model.Channel)
 		}
 	}
 
-	// Responses-only models (e.g. codex series)
-	if strings.Contains(strings.ToLower(model), "codex") {
-		return &dto.OpenAIResponsesRequest{
-			Model: model,
-			Input: json.RawMessage("\"hi\""),
-		}
-	}
-
 	// Chat/Completion 请求 - 返回 GeneralOpenAIRequest
 	testRequest := &dto.GeneralOpenAIRequest{
 		Model:  model,
@@ -489,7 +466,7 @@ func buildTestRequest(model string, endpointType string, channel *model.Channel)
 	}
 
 	if strings.HasPrefix(model, "o") {
-		testRequest.MaxCompletionTokens = 16
+		testRequest.MaxCompletionTokens = 10
 	} else if strings.Contains(model, "thinking") {
 		if !strings.Contains(model, "claude") {
 			testRequest.MaxTokens = 50
@@ -497,7 +474,7 @@ func buildTestRequest(model string, endpointType string, channel *model.Channel)
 	} else if strings.Contains(model, "gemini") {
 		testRequest.MaxTokens = 3000
 	} else {
-		testRequest.MaxTokens = 16
+		testRequest.MaxTokens = 10
 	}
 
 	return testRequest

controller/channel.go

@@ -11,6 +11,7 @@ import (
 	"github.com/QuantumNous/new-api/constant"
 	"github.com/QuantumNous/new-api/dto"
 	"github.com/QuantumNous/new-api/model"
+	"github.com/QuantumNous/new-api/relay/channel/volcengine"
 	"github.com/QuantumNous/new-api/service"
 
 	"github.com/gin-gonic/gin"
@@ -165,30 +166,6 @@ func GetAllChannels(c *gin.Context) {
 	return
 }
 
-func buildFetchModelsHeaders(channel *model.Channel, key string) (http.Header, error) {
-	var headers http.Header
-	switch channel.Type {
-	case constant.ChannelTypeAnthropic:
-		headers = GetClaudeAuthHeader(key)
-	default:
-		headers = GetAuthHeader(key)
-	}
-
-	headerOverride := channel.GetHeaderOverride()
-	for k, v := range headerOverride {
-		str, ok := v.(string)
-		if !ok {
-			return nil, fmt.Errorf("invalid header override for key %s", k)
-		}
-		if strings.Contains(str, "{api_key}") {
-			str = strings.ReplaceAll(str, "{api_key}", key)
-		}
-		headers.Set(k, str)
-	}
-
-	return headers, nil
-}
-
 func FetchUpstreamModels(c *gin.Context) {
 	id, err := strconv.Atoi(c.Param("id"))
 	if err != nil {
@@ -215,20 +192,10 @@ func FetchUpstreamModels(c *gin.Context) {
 	case constant.ChannelTypeAli:
 		url = fmt.Sprintf("%s/compatible-mode/v1/models", baseURL)
 	case constant.ChannelTypeZhipu_v4:
-		if plan, ok := constant.ChannelSpecialBases[baseURL]; ok && plan.OpenAIBaseURL != "" {
-			url = fmt.Sprintf("%s/models", plan.OpenAIBaseURL)
-		} else {
-			url = fmt.Sprintf("%s/api/paas/v4/models", baseURL)
-		}
+		url = fmt.Sprintf("%s/api/paas/v4/models", baseURL)
 	case constant.ChannelTypeVolcEngine:
-		if plan, ok := constant.ChannelSpecialBases[baseURL]; ok && plan.OpenAIBaseURL != "" {
-			url = fmt.Sprintf("%s/v1/models", plan.OpenAIBaseURL)
-		} else {
-			url = fmt.Sprintf("%s/v1/models", baseURL)
-		}
-	case constant.ChannelTypeMoonshot:
-		if plan, ok := constant.ChannelSpecialBases[baseURL]; ok && plan.OpenAIBaseURL != "" {
-			url = fmt.Sprintf("%s/models", plan.OpenAIBaseURL)
+		if baseURL == volcengine.DoubaoCodingPlan {
+			url = fmt.Sprintf("%s/v1/models", volcengine.DoubaoCodingPlanOpenAIBaseURL)
 		} else {
 			url = fmt.Sprintf("%s/v1/models", baseURL)
 		}
@@ -247,13 +214,14 @@ func FetchUpstreamModels(c *gin.Context) {
 	}
 	key = strings.TrimSpace(key)
 
-	headers, err := buildFetchModelsHeaders(channel, key)
-	if err != nil {
-		common.ApiError(c, err)
-		return
+	// 获取响应体 - 根据渠道类型决定是否添加 AuthHeader
+	var body []byte
+	switch channel.Type {
+	case constant.ChannelTypeAnthropic:
+		body, err = GetResponseBody("GET", url, channel, GetClaudeAuthHeader(key))
+	default:
+		body, err = GetResponseBody("GET", url, channel, GetAuthHeader(key))
 	}
-
-	body, err := GetResponseBody("GET", url, channel, headers)
 	if err != nil {
 		common.ApiError(c, err)
 		return

controller/discord.go

@@ -114,7 +114,7 @@ func DiscordOAuth(c *gin.Context) {
 		DiscordBind(c)
 		return
 	}
-	if !system_setting.GetDiscordSettings().Enabled {
+		if !system_setting.GetDiscordSettings().Enabled {
 		c.JSON(http.StatusOK, gin.H{
 			"success": false,
 			"message": "管理员未开启通过 Discord 登录以及注册",

controller/model.go

@@ -18,7 +18,6 @@ import (
 	"github.com/QuantumNous/new-api/service"
 	"github.com/QuantumNous/new-api/setting/operation_setting"
 	"github.com/QuantumNous/new-api/setting/ratio_setting"
-	"github.com/QuantumNous/new-api/types"
 	"github.com/gin-gonic/gin"
 	"github.com/samber/lo"
 )
@@ -276,7 +275,7 @@ func RetrieveModel(c *gin.Context, modelType int) {
 			c.JSON(200, aiModel)
 		}
 	} else {
-		openAIError := types.OpenAIError{
+		openAIError := dto.OpenAIError{
 			Message: fmt.Sprintf("The model '%s' does not exist", modelId),
 			Type:    "invalid_request_error",
 			Param:   "model",

controller/model_sync.go

@@ -249,9 +249,7 @@ func ensureVendorID(vendorName string, vendorByName map[string]upstreamVendor, v
 	return 0
 }
 
-// SyncUpstreamModels 同步上游模型与供应商：
-// - 默认仅创建「未配置模型」
-// - 可通过 overwrite 选择性覆盖更新本地已有模型的字段（前提：sync_official <> 0）
+// SyncUpstreamModels 同步上游模型与供应商，仅对「未配置模型」生效
 func SyncUpstreamModels(c *gin.Context) {
 	var req syncRequest
 	// 允许空体
@@ -262,26 +260,12 @@ func SyncUpstreamModels(c *gin.Context) {
 		c.JSON(http.StatusOK, gin.H{"success": false, "message": err.Error()})
 		return
 	}
-
-	// 若既无缺失模型需要创建，也未指定覆盖更新字段，则无需请求上游数据，直接返回
-	if len(missing) == 0 && len(req.Overwrite) == 0 {
-		modelsURL, vendorsURL := getUpstreamURLs(req.Locale)
-		c.JSON(http.StatusOK, gin.H{
-			"success": true,
-			"data": gin.H{
-				"created_models":  0,
-				"created_vendors": 0,
-				"updated_models":  0,
-				"skipped_models":  []string{},
-				"created_list":    []string{},
-				"updated_list":    []string{},
-				"source": gin.H{
-					"locale":      req.Locale,
-					"models_url":  modelsURL,
-					"vendors_url": vendorsURL,
-				},
-			},
-		})
+	if len(missing) == 0 {
+		c.JSON(http.StatusOK, gin.H{"success": true, "data": gin.H{
+			"created_models":  0,
+			"created_vendors": 0,
+			"skipped_models":  []string{},
+		}})
 		return
 	}
 
@@ -331,9 +315,9 @@ func SyncUpstreamModels(c *gin.Context) {
 	createdModels := 0
 	createdVendors := 0
 	updatedModels := 0
-	skipped := make([]string, 0)
-	createdList := make([]string, 0)
-	updatedList := make([]string, 0)
+	var skipped []string
+	var createdList []string
+	var updatedList []string
 
 	// 本地缓存：vendorName -> id
 	vendorIDCache := make(map[string]int)

controller/playground.go

@@ -3,10 +3,12 @@ package controller
 import (
 	"errors"
 	"fmt"
+	"time"
 
+	"github.com/QuantumNous/new-api/common"
+	"github.com/QuantumNous/new-api/constant"
 	"github.com/QuantumNous/new-api/middleware"
 	"github.com/QuantumNous/new-api/model"
-	relaycommon "github.com/QuantumNous/new-api/relay/common"
 	"github.com/QuantumNous/new-api/types"
 
 	"github.com/gin-gonic/gin"
@@ -29,11 +31,8 @@ func Playground(c *gin.Context) {
 		return
 	}
 
-	relayInfo, err := relaycommon.GenRelayInfo(c, types.RelayFormatOpenAI, nil, nil)
-	if err != nil {
-		newAPIError = types.NewError(err, types.ErrorCodeInvalidRequest, types.ErrOptionWithSkipRetry())
-		return
-	}
+	group := common.GetContextKeyString(c, constant.ContextKeyUsingGroup)
+	modelName := c.GetString("original_model")
 
 	userId := c.GetInt("id")
 
@@ -47,10 +46,16 @@ func Playground(c *gin.Context) {
 
 	tempToken := &model.Token{
 		UserId: userId,
-		Name:   fmt.Sprintf("playground-%s", relayInfo.UsingGroup),
-		Group:  relayInfo.UsingGroup,
+		Name:   fmt.Sprintf("playground-%s", group),
+		Group:  group,
 	}
 	_ = middleware.SetupContextForToken(c, tempToken)
+	_, newAPIError = getChannel(c, group, modelName, 0)
+	if newAPIError != nil {
+		return
+	}
+	//middleware.SetupContextForSelectedChannel(c, channel, playgroundRequest.Model)
+	common.SetContextKey(c, constant.ContextKeyRequestStartTime, time.Now())
 
 	Relay(c, types.RelayFormatOpenAI)
 }

controller/relay.go

@@ -2,7 +2,6 @@ package controller
 
 import (
 	"bytes"
-	"errors"
 	"fmt"
 	"io"
 	"log"
@@ -65,8 +64,8 @@ func geminiRelayHandler(c *gin.Context, info *relaycommon.RelayInfo) *types.NewA
 func Relay(c *gin.Context, relayFormat types.RelayFormat) {
 
 	requestId := c.GetString(common.RequestIdKey)
-	//group := common.GetContextKeyString(c, constant.ContextKeyUsingGroup)
-	//originalModel := common.GetContextKeyString(c, constant.ContextKeyOriginalModel)
+	group := common.GetContextKeyString(c, constant.ContextKeyUsingGroup)
+	originalModel := common.GetContextKeyString(c, constant.ContextKeyOriginalModel)
 
 	var (
 		newAPIError *types.NewAPIError
@@ -105,12 +104,7 @@ func Relay(c *gin.Context, relayFormat types.RelayFormat) {
 
 	request, err := helper.GetAndValidateRequest(c, relayFormat)
 	if err != nil {
-		// Map "request body too large" to 413 so clients can handle it correctly
-		if common.IsRequestBodyTooLargeError(err) || errors.Is(err, common.ErrRequestBodyTooLarge) {
-			newAPIError = types.NewErrorWithStatusCode(err, types.ErrorCodeReadRequestBodyFailed, http.StatusRequestEntityTooLarge, types.ErrOptionWithSkipRetry())
-		} else {
-			newAPIError = types.NewError(err, types.ErrorCodeInvalidRequest)
-		}
+		newAPIError = types.NewError(err, types.ErrorCodeInvalidRequest)
 		return
 	}
 
@@ -120,17 +114,9 @@ func Relay(c *gin.Context, relayFormat types.RelayFormat) {
 		return
 	}
 
-	needSensitiveCheck := setting.ShouldCheckPromptSensitive()
-	needCountToken := constant.CountToken
-	// Avoid building huge CombineText (strings.Join) when token counting and sensitive check are both disabled.
-	var meta *types.TokenCountMeta
-	if needSensitiveCheck || needCountToken {
-		meta = request.GetTokenCountMeta()
-	} else {
-		meta = fastTokenCountMetaForPricing(request)
-	}
+	meta := request.GetTokenCountMeta()
 
-	if needSensitiveCheck && meta != nil {
+	if setting.ShouldCheckPromptSensitive() {
 		contains, words := service.CheckSensitiveText(meta.CombineText)
 		if contains {
 			logger.LogWarn(c, fmt.Sprintf("user sensitive words detected: %s", strings.Join(words, ", ")))
@@ -139,13 +125,13 @@ func Relay(c *gin.Context, relayFormat types.RelayFormat) {
 		}
 	}
 
-	tokens, err := service.EstimateRequestToken(c, meta, relayInfo)
+	tokens, err := service.CountRequestToken(c, meta, relayInfo)
 	if err != nil {
 		newAPIError = types.NewError(err, types.ErrorCodeCountTokenFailed)
 		return
 	}
 
-	relayInfo.SetEstimatePromptTokens(tokens)
+	relayInfo.SetPromptTokens(tokens)
 
 	priceData, err := helper.ModelPriceHelper(c, relayInfo, tokens, meta)
 	if err != nil {
@@ -171,32 +157,16 @@ func Relay(c *gin.Context, relayFormat types.RelayFormat) {
 		}
 	}()
 
-	retryParam := &service.RetryParam{
-		Ctx:        c,
-		TokenGroup: relayInfo.TokenGroup,
-		ModelName:  relayInfo.OriginModelName,
-		Retry:      common.GetPointer(0),
-	}
-
-	for ; retryParam.GetRetry() <= common.RetryTimes; retryParam.IncreaseRetry() {
-		channel, channelErr := getChannel(c, relayInfo, retryParam)
-		if channelErr != nil {
-			logger.LogError(c, channelErr.Error())
-			newAPIError = channelErr
+	for i := 0; i <= common.RetryTimes; i++ {
+		channel, err := getChannel(c, group, originalModel, i)
+		if err != nil {
+			logger.LogError(c, err.Error())
+			newAPIError = err
 			break
 		}
 
 		addUsedChannel(c, channel.Id)
-		requestBody, bodyErr := common.GetRequestBody(c)
-		if bodyErr != nil {
-			// Ensure consistent 413 for oversized bodies even when error occurs later (e.g., retry path)
-			if common.IsRequestBodyTooLargeError(bodyErr) || errors.Is(bodyErr, common.ErrRequestBodyTooLarge) {
-				newAPIError = types.NewErrorWithStatusCode(bodyErr, types.ErrorCodeReadRequestBodyFailed, http.StatusRequestEntityTooLarge, types.ErrOptionWithSkipRetry())
-			} else {
-				newAPIError = types.NewErrorWithStatusCode(bodyErr, types.ErrorCodeReadRequestBodyFailed, http.StatusBadRequest, types.ErrOptionWithSkipRetry())
-			}
-			break
-		}
+		requestBody, _ := common.GetRequestBody(c)
 		c.Request.Body = io.NopCloser(bytes.NewBuffer(requestBody))
 
 		switch relayFormat {
@@ -216,7 +186,7 @@ func Relay(c *gin.Context, relayFormat types.RelayFormat) {
 
 		processChannelError(c, *types.NewChannelError(channel.Id, channel.Type, channel.Name, channel.ChannelInfo.IsMultiKey, common.GetContextKeyString(c, constant.ContextKeyChannelKey), channel.GetAutoBan()), newAPIError)
 
-		if !shouldRetry(c, newAPIError, common.RetryTimes-retryParam.GetRetry()) {
+		if !shouldRetry(c, newAPIError, common.RetryTimes-i) {
 			break
 		}
 	}
@@ -241,35 +211,8 @@ func addUsedChannel(c *gin.Context, channelId int) {
 	c.Set("use_channel", useChannel)
 }
 
-func fastTokenCountMetaForPricing(request dto.Request) *types.TokenCountMeta {
-	if request == nil {
-		return &types.TokenCountMeta{}
-	}
-	meta := &types.TokenCountMeta{
-		TokenType: types.TokenTypeTokenizer,
-	}
-	switch r := request.(type) {
-	case *dto.GeneralOpenAIRequest:
-		if r.MaxCompletionTokens > r.MaxTokens {
-			meta.MaxTokens = int(r.MaxCompletionTokens)
-		} else {
-			meta.MaxTokens = int(r.MaxTokens)
-		}
-	case *dto.OpenAIResponsesRequest:
-		meta.MaxTokens = int(r.MaxOutputTokens)
-	case *dto.ClaudeRequest:
-		meta.MaxTokens = int(r.MaxTokens)
-	case *dto.ImageRequest:
-		// Pricing for image requests depends on ImagePriceRatio; safe to compute even when CountToken is disabled.
-		return r.GetTokenCountMeta()
-	default:
-		// Best-effort: leave CombineText empty to avoid large allocations.
-	}
-	return meta
-}
-
-func getChannel(c *gin.Context, info *relaycommon.RelayInfo, retryParam *service.RetryParam) (*model.Channel, *types.NewAPIError) {
-	if info.ChannelMeta == nil {
+func getChannel(c *gin.Context, group, originalModel string, retryCount int) (*model.Channel, *types.NewAPIError) {
+	if retryCount == 0 {
 		autoBan := c.GetBool("auto_ban")
 		autoBanInt := 1
 		if !autoBan {
@@ -282,18 +225,14 @@ func getChannel(c *gin.Context, info *relaycommon.RelayInfo, retryParam *service
 			AutoBan: &autoBanInt,
 		}, nil
 	}
-	channel, selectGroup, err := service.CacheGetRandomSatisfiedChannel(retryParam)
-
-	info.PriceData.GroupRatioInfo = helper.HandleGroupRatio(c, info)
-
+	channel, selectGroup, err := service.CacheGetRandomSatisfiedChannel(c, group, originalModel, retryCount)
 	if err != nil {
-		return nil, types.NewError(fmt.Errorf("获取分组 %s 下模型 %s 的可用渠道失败（retry）: %s", selectGroup, info.OriginModelName, err.Error()), types.ErrorCodeGetChannelFailed, types.ErrOptionWithSkipRetry())
+		return nil, types.NewError(fmt.Errorf("获取分组 %s 下模型 %s 的可用渠道失败（retry）: %s", selectGroup, originalModel, err.Error()), types.ErrorCodeGetChannelFailed, types.ErrOptionWithSkipRetry())
 	}
 	if channel == nil {
-		return nil, types.NewError(fmt.Errorf("分组 %s 下模型 %s 的可用渠道不存在（retry）", selectGroup, info.OriginModelName), types.ErrorCodeGetChannelFailed, types.ErrOptionWithSkipRetry())
+		return nil, types.NewError(fmt.Errorf("分组 %s 下模型 %s 的可用渠道不存在（retry）", selectGroup, originalModel), types.ErrorCodeGetChannelFailed, types.ErrOptionWithSkipRetry())
 	}
-
-	newAPIError := middleware.SetupContextForSelectedChannel(c, channel, info.OriginModelName)
+	newAPIError := middleware.SetupContextForSelectedChannel(c, channel, originalModel)
 	if newAPIError != nil {
 		return nil, newAPIError
 	}
@@ -346,7 +285,7 @@ func processChannelError(c *gin.Context, channelError types.ChannelError, err *t
 	logger.LogError(c, fmt.Sprintf("channel error (channel #%d, status code: %d): %s", channelError.ChannelId, err.StatusCode, err.Error()))
 	// 不要使用context获取渠道信息，异步处理时可能会出现渠道信息不一致的情况
 	// do not use context to get channel info, there may be inconsistent channel info when processing asynchronously
-	if service.ShouldDisableChannel(channelError.ChannelType, err) && channelError.AutoBan {
+	if service.ShouldDisableChannel(channelError.ChannelId, err) && channelError.AutoBan {
 		gopool.Go(func() {
 			service.DisableChannel(channelError, err.Error())
 		})
@@ -427,7 +366,7 @@ func RelayMidjourney(c *gin.Context) {
 }
 
 func RelayNotImplemented(c *gin.Context) {
-	err := types.OpenAIError{
+	err := dto.OpenAIError{
 		Message: "API not implemented",
 		Type:    "new_api_error",
 		Param:   "",
@@ -439,7 +378,7 @@ func RelayNotImplemented(c *gin.Context) {
 }
 
 func RelayNotFound(c *gin.Context) {
-	err := types.OpenAIError{
+	err := dto.OpenAIError{
 		Message: fmt.Sprintf("Invalid URL (%s %s)", c.Request.Method, c.Request.URL.Path),
 		Type:    "invalid_request_error",
 		Param:   "",
@@ -453,6 +392,8 @@ func RelayNotFound(c *gin.Context) {
 func RelayTask(c *gin.Context) {
 	retryTimes := common.RetryTimes
 	channelId := c.GetInt("channel_id")
+	group := c.GetString("group")
+	originalModel := c.GetString("original_model")
 	c.Set("use_channel", []string{fmt.Sprintf("%d", channelId)})
 	relayInfo, err := relaycommon.GenRelayInfo(c, types.RelayFormatTask, nil, nil)
 	if err != nil {
@@ -462,14 +403,8 @@ func RelayTask(c *gin.Context) {
 	if taskErr == nil {
 		retryTimes = 0
 	}
-	retryParam := &service.RetryParam{
-		Ctx:        c,
-		TokenGroup: relayInfo.TokenGroup,
-		ModelName:  relayInfo.OriginModelName,
-		Retry:      common.GetPointer(0),
-	}
-	for ; shouldRetryTaskRelay(c, channelId, taskErr, retryTimes) && retryParam.GetRetry() < retryTimes; retryParam.IncreaseRetry() {
-		channel, newAPIError := getChannel(c, relayInfo, retryParam)
+	for i := 0; shouldRetryTaskRelay(c, channelId, taskErr, retryTimes) && i < retryTimes; i++ {
+		channel, newAPIError := getChannel(c, group, originalModel, i)
 		if newAPIError != nil {
 			logger.LogError(c, fmt.Sprintf("CacheGetRandomSatisfiedChannel failed: %s", newAPIError.Error()))
 			taskErr = service.TaskErrorWrapperLocal(newAPIError.Err, "get_channel_failed", http.StatusInternalServerError)
@@ -479,18 +414,10 @@ func RelayTask(c *gin.Context) {
 		useChannel := c.GetStringSlice("use_channel")
 		useChannel = append(useChannel, fmt.Sprintf("%d", channelId))
 		c.Set("use_channel", useChannel)
-		logger.LogInfo(c, fmt.Sprintf("using channel #%d to retry (remain times %d)", channel.Id, retryParam.GetRetry()))
+		logger.LogInfo(c, fmt.Sprintf("using channel #%d to retry (remain times %d)", channel.Id, i))
 		//middleware.SetupContextForSelectedChannel(c, channel, originalModel)
 
-		requestBody, err := common.GetRequestBody(c)
-		if err != nil {
-			if common.IsRequestBodyTooLargeError(err) || errors.Is(err, common.ErrRequestBodyTooLarge) {
-				taskErr = service.TaskErrorWrapperLocal(err, "read_request_body_failed", http.StatusRequestEntityTooLarge)
-			} else {
-				taskErr = service.TaskErrorWrapperLocal(err, "read_request_body_failed", http.StatusBadRequest)
-			}
-			break
-		}
+		requestBody, _ := common.GetRequestBody(c)
 		c.Request.Body = io.NopCloser(bytes.NewBuffer(requestBody))
 		taskErr = taskRelayHandler(c, relayInfo)
 	}

controller/task.go

@@ -29,7 +29,7 @@ func UpdateTaskBulk() {
 		time.Sleep(time.Duration(15) * time.Second)
 		common.SysLog("任务进度轮询开始")
 		ctx := context.TODO()
-		allTasks := model.GetAllUnFinishSyncTasks(constant.TaskQueryLimit)
+		allTasks := model.GetAllUnFinishSyncTasks(500)
 		platformTask := make(map[constant.TaskPlatform][]*model.Task)
 		for _, t := range allTasks {
 			platformTask[t.Platform] = append(platformTask[t.Platform], t)
@@ -88,7 +88,7 @@ func UpdateSunoTaskAll(ctx context.Context, taskChannelM map[int][]string, taskM
 	for channelId, taskIds := range taskChannelM {
 		err := updateSunoTaskAll(ctx, channelId, taskIds, taskM)
 		if err != nil {
-			logger.LogError(ctx, fmt.Sprintf("渠道 #%d 更新异步任务失败: %s", channelId, err.Error()))
+			logger.LogError(ctx, fmt.Sprintf("渠道 #%d 更新异步任务失败: %d", channelId, err.Error()))
 		}
 	}
 	return nil
@@ -116,10 +116,9 @@ func updateSunoTaskAll(ctx context.Context, channelId int, taskIds []string, tas
 	if adaptor == nil {
 		return errors.New("adaptor not found")
 	}
-	proxy := channel.GetSetting().Proxy
 	resp, err := adaptor.FetchTask(*channel.BaseURL, channel.Key, map[string]any{
 		"ids": taskIds,
-	}, proxy)
+	})
 	if err != nil {
 		common.SysLog(fmt.Sprintf("Get Task Do req error: %v", err))
 		return err
@@ -141,7 +140,7 @@ func updateSunoTaskAll(ctx context.Context, channelId int, taskIds []string, tas
 		return err
 	}
 	if !responseItems.IsSuccess() {
-		common.SysLog(fmt.Sprintf("渠道 #%d 未完成的任务有: %d, 成功获取到任务数: %s", channelId, len(taskIds), string(responseBody)))
+		common.SysLog(fmt.Sprintf("渠道 #%d 未完成的任务有: %d, 成功获取到任务数: %d", channelId, len(taskIds), string(responseBody)))
 		return err
 	}
 

controller/task_video.go

@@ -67,7 +67,6 @@ func updateVideoSingleTask(ctx context.Context, adaptor channel.TaskAdaptor, cha
 	if channel.GetBaseURL() != "" {
 		baseURL = channel.GetBaseURL()
 	}
-	proxy := channel.GetSetting().Proxy
 
 	task := taskM[taskId]
 	if task == nil {
@@ -77,7 +76,7 @@ func updateVideoSingleTask(ctx context.Context, adaptor channel.TaskAdaptor, cha
 	resp, err := adaptor.FetchTask(baseURL, channel.Key, map[string]any{
 		"task_id": taskId,
 		"action":  task.Action,
-	}, proxy)
+	})
 	if err != nil {
 		return fmt.Errorf("fetchTask failed for task %s: %w", taskId, err)
 	}

controller/token.go

@@ -142,7 +142,7 @@ func AddToken(c *gin.Context) {
 		common.ApiError(c, err)
 		return
 	}
-	if len(token.Name) > 50 {
+	if len(token.Name) > 30 {
 		c.JSON(http.StatusOK, gin.H{
 			"success": false,
 			"message": "令牌名称过长",
@@ -171,7 +171,6 @@ func AddToken(c *gin.Context) {
 		ModelLimits:        token.ModelLimits,
 		AllowIps:           token.AllowIps,
 		Group:              token.Group,
-		CrossGroupRetry:    token.CrossGroupRetry,
 	}
 	err = cleanToken.Insert()
 	if err != nil {
@@ -209,7 +208,7 @@ func UpdateToken(c *gin.Context) {
 		common.ApiError(c, err)
 		return
 	}
-	if len(token.Name) > 50 {
+	if len(token.Name) > 30 {
 		c.JSON(http.StatusOK, gin.H{
 			"success": false,
 			"message": "令牌名称过长",
@@ -249,7 +248,6 @@ func UpdateToken(c *gin.Context) {
 		cleanToken.ModelLimits = token.ModelLimits
 		cleanToken.AllowIps = token.AllowIps
 		cleanToken.Group = token.Group
-		cleanToken.CrossGroupRetry = token.CrossGroupRetry
 	}
 	err = cleanToken.Update()
 	if err != nil {

controller/topup_creem.go

@@ -7,12 +7,12 @@ import (
 	"encoding/hex"
 	"encoding/json"
 	"fmt"
-	"github.com/QuantumNous/new-api/common"
-	"github.com/QuantumNous/new-api/model"
-	"github.com/QuantumNous/new-api/setting"
 	"io"
 	"log"
 	"net/http"
+	"github.com/QuantumNous/new-api/common"
+	"github.com/QuantumNous/new-api/model"
+	"github.com/QuantumNous/new-api/setting"
 	"time"
 
 	"github.com/gin-gonic/gin"

controller/user.go

@@ -110,17 +110,18 @@ func setupLogin(user *model.User, c *gin.Context) {
 		})
 		return
 	}
+	cleanUser := model.User{
+		Id:          user.Id,
+		Username:    user.Username,
+		DisplayName: user.DisplayName,
+		Role:        user.Role,
+		Status:      user.Status,
+		Group:       user.Group,
+	}
 	c.JSON(http.StatusOK, gin.H{
 		"message": "",
 		"success": true,
-		"data": map[string]any{
-			"id":           user.Id,
-			"username":     user.Username,
-			"display_name": user.DisplayName,
-			"role":         user.Role,
-			"status":       user.Status,
-			"group":        user.Group,
-		},
+		"data":    cleanUser,
 	})
 }
 
@@ -763,10 +764,7 @@ func checkUpdatePassword(originalPassword string, newPassword string, userId int
 	if err != nil {
 		return
 	}
-
-	// 密码不为空,需要验证原密码
-	// 支持第一次账号绑定时原密码为空的情况
-	if !common.ValidatePasswordAndHash(originalPassword, currentUser.Password) && currentUser.Password != "" {
+	if !common.ValidatePasswordAndHash(originalPassword, currentUser.Password) {
 		err = fmt.Errorf("原密码错误")
 		return
 	}

controller/video_proxy.go

@@ -1,7 +1,6 @@
 package controller
 
 import (
-	"context"
 	"fmt"
 	"io"
 	"net/http"
@@ -11,7 +10,6 @@ import (
 	"github.com/QuantumNous/new-api/constant"
 	"github.com/QuantumNous/new-api/logger"
 	"github.com/QuantumNous/new-api/model"
-	"github.com/QuantumNous/new-api/service"
 
 	"github.com/gin-gonic/gin"
 )
@@ -77,22 +75,11 @@ func VideoProxy(c *gin.Context) {
 	}
 
 	var videoURL string
-	proxy := channel.GetSetting().Proxy
-	client, err := service.GetHttpClientWithProxy(proxy)
-	if err != nil {
-		logger.LogError(c.Request.Context(), fmt.Sprintf("Failed to create proxy client for task %s: %s", taskID, err.Error()))
-		c.JSON(http.StatusInternalServerError, gin.H{
-			"error": gin.H{
-				"message": "Failed to create proxy client",
-				"type":    "server_error",
-			},
-		})
-		return
+	client := &http.Client{
+		Timeout: 60 * time.Second,
 	}
 
-	ctx, cancel := context.WithTimeout(c.Request.Context(), 60*time.Second)
-	defer cancel()
-	req, err := http.NewRequestWithContext(ctx, http.MethodGet, "", nil)
+	req, err := http.NewRequestWithContext(c.Request.Context(), http.MethodGet, "", nil)
 	if err != nil {
 		logger.LogError(c.Request.Context(), fmt.Sprintf("Failed to create request: %s", err.Error()))
 		c.JSON(http.StatusInternalServerError, gin.H{
@@ -130,12 +117,13 @@ func VideoProxy(c *gin.Context) {
 			return
 		}
 		req.Header.Set("x-goog-api-key", apiKey)
-	case constant.ChannelTypeOpenAI, constant.ChannelTypeSora:
-		videoURL = fmt.Sprintf("%s/v1/videos/%s/content", baseURL, task.TaskID)
-		req.Header.Set("Authorization", "Bearer "+channel.Key)
-	default:
+	case constant.ChannelTypeAli:
 		// Video URL is directly in task.FailReason
 		videoURL = task.FailReason
+	default:
+		// Default (Sora, etc.): Use original logic
+		videoURL = fmt.Sprintf("%s/v1/videos/%s/content", baseURL, task.TaskID)
+		req.Header.Set("Authorization", "Bearer "+channel.Key)
 	}
 
 	req.URL, err = url.Parse(videoURL)

controller/video_proxy_gemini.go

@@ -35,11 +35,10 @@ func getGeminiVideoURL(channel *model.Channel, task *model.Task, apiKey string)
 		return "", fmt.Errorf("api key not available for task")
 	}
 
-	proxy := channel.GetSetting().Proxy
 	resp, err := adaptor.FetchTask(baseURL, apiKey, map[string]any{
 		"task_id": task.TaskID,
 		"action":  task.Action,
-	}, proxy)
+	})
 	if err != nil {
 		return "", fmt.Errorf("fetch task failed: %w", err)
 	}

docs/api/api_auth.md

@@ -0,0 +1,53 @@
+# API 鉴权文档
+
+## 认证方式
+
+### Access Token
+
+对于需要鉴权的 API 接口，必须同时提供以下两个请求头来进行 Access Token 认证：
+
+1. **请求头中的 `Authorization` 字段**
+
+    将 Access Token 放置于 HTTP 请求头部的 `Authorization` 字段中，格式如下：
+
+    ```
+    Authorization: <your_access_token>
+    ```
+
+    其中 `<your_access_token>` 需要替换为实际的 Access Token 值。
+
+2. **请求头中的 `New-Api-User` 字段**
+
+    将用户 ID 放置于 HTTP 请求头部的 `New-Api-User` 字段中，格式如下：
+
+    ```
+    New-Api-User: <your_user_id>
+    ```
+
+    其中 `<your_user_id>` 需要替换为实际的用户 ID。
+
+**注意：**
+
+*   **必须同时提供 `Authorization` 和 `New-Api-User` 两个请求头才能通过鉴权。**
+*   如果只提供其中一个请求头，或者两个请求头都未提供，则会返回 `401 Unauthorized` 错误。
+*   如果 `Authorization` 中的 Access Token 无效，则会返回 `401 Unauthorized` 错误，并提示“无权进行此操作，access token 无效”。
+*   如果 `New-Api-User` 中的用户 ID 与 Access Token 不匹配，则会返回 `401 Unauthorized` 错误，并提示“无权进行此操作，与登录用户不匹配，请重新登录”。
+*   如果没有提供 `New-Api-User` 请求头，则会返回 `401 Unauthorized` 错误，并提示“无权进行此操作，未提供 New-Api-User”。
+*   如果 `New-Api-User` 请求头格式错误，则会返回 `401 Unauthorized` 错误，并提示“无权进行此操作，New-Api-User 格式错误”。
+*   如果用户已被禁用，则会返回 `403 Forbidden` 错误，并提示“用户已被封禁”。
+*   如果用户权限不足，则会返回 `403 Forbidden` 错误，并提示“无权进行此操作，权限不足”。
+*   如果用户信息无效，则会返回 `403 Forbidden` 错误，并提示“无权进行此操作，用户信息无效”。
+
+## Curl 示例
+
+假设您的 Access Token 为 `access_token`，用户 ID 为 `123`，要访问的 API 接口为 `/api/user/self`，则可以使用以下 curl 命令：
+
+```bash
+curl -X GET \
+  -H "Authorization: access_token" \
+  -H "New-Api-User: 123" \
+  https://your-domain.com/api/user/self
+```
+
+请将 `access_token`、`123` 和 `https://your-domain.com` 替换为实际的值。
+

docs/api/web_api.md

@@ -0,0 +1,198 @@
+# New API – Web 界面后端接口文档
+
+> 本文档汇总了 **New API** 后端提供给前端 Web 界面的全部 REST 接口（不含 *Relay* 相关接口）。
+>
+> 接口前缀统一为 `https://<your-domain>`，以下仅列出 **路径**、**HTTP 方法**、**鉴权要求** 与 **功能简介**。
+>
+> 鉴权级别说明：
+> * **公开** – 不需要登录即可调用
+> * **用户** – 需携带用户 Token（`middleware.UserAuth`）
+> * **管理员** – 需管理员 Token（`middleware.AdminAuth`）
+> * **Root** – 仅限最高权限 Root 用户（`middleware.RootAuth`）
+
+---
+
+## 1. 初始化 / 系统状态
+| 方法 | 路径 | 鉴权 | 说明 |
+|------|------|------|------|
+| GET  | /api/setup | 公开 | 获取系统初始化状态 |
+| POST | /api/setup | 公开 | 完成首次安装向导 |
+| GET  | /api/status | 公开 | 获取运行状态摘要 |
+| GET  | /api/uptime/status | 公开 | Uptime-Kuma 兼容状态探针 |
+| GET  | /api/status/test | 管理员 | 测试后端与依赖组件是否正常 |
+
+## 2. 公共信息
+| 方法 | 路径 | 鉴权 | 说明 |
+|------|------|------|------|
+| GET | /api/models | 用户 | 获取前端可用模型列表 |
+| GET | /api/notice | 公开 | 获取公告栏内容 |
+| GET | /api/about | 公开 | 关于页面信息 |
+| GET | /api/home_page_content | 公开 | 首页自定义内容 |
+| GET | /api/pricing | 可匿名/用户 | 价格与套餐信息 |
+| GET | /api/ratio_config | 公开 | 模型倍率配置（仅公开字段） |
+
+## 3. 邮件 / 身份验证
+| 方法 | 路径 | 鉴权 | 说明 |
+|------|------|------|------|
+| GET | /api/verification | 公开 (限流) | 发送邮箱验证邮件 |
+| GET | /api/reset_password | 公开 (限流) | 发送重置密码邮件 |
+| POST | /api/user/reset | 公开 | 提交重置密码请求 |
+
+## 4. OAuth / 第三方登录
+| 方法 | 路径 | 鉴权 | 说明 |
+|------|------|------|------|
+| GET | /api/oauth/github | 公开 | GitHub OAuth 跳转 |
+| GET | /api/oauth/discord | 公开 | Discord 通用 OAuth 跳转 |
+| GET | /api/oauth/oidc | 公开 | OIDC 通用 OAuth 跳转 |
+| GET | /api/oauth/linuxdo | 公开 | LinuxDo OAuth 跳转 |
+| GET | /api/oauth/wechat | 公开 | 微信扫码登录跳转 |
+| GET | /api/oauth/wechat/bind | 公开 | 微信账户绑定 |
+| GET | /api/oauth/email/bind | 公开 | 邮箱绑定 |
+| GET | /api/oauth/telegram/login | 公开 | Telegram 登录 |
+| GET | /api/oauth/telegram/bind | 公开 | Telegram 账户绑定 |
+| GET | /api/oauth/state | 公开 | 获取随机 state（防 CSRF） |
+
+## 5. 用户模块
+### 5.1 账号注册/登录
+| 方法 | 路径 | 鉴权 | 说明 |
+|------|------|------|------|
+| POST | /api/user/register | 公开 | 注册新账号 |
+| POST | /api/user/login | 公开 | 用户登录 |
+| GET  | /api/user/logout | 用户 | 退出登录 |
+| GET  | /api/user/epay/notify | 公开 | Epay 支付回调 |
+| GET  | /api/user/groups | 公开 | 列出所有分组（无鉴权版） |
+
+### 5.2 用户自身操作 (需登录)
+| 方法 | 路径 | 鉴权 | 说明 |
+|------|------|------|------|
+| GET | /api/user/self/groups | 用户 | 获取自己所在分组 |
+| GET | /api/user/self | 用户 | 获取个人资料 |
+| GET | /api/user/models | 用户 | 获取模型可见性 |
+| PUT | /api/user/self | 用户 | 修改个人资料 |
+| DELETE | /api/user/self | 用户 | 注销账号 |
+| GET | /api/user/token | 用户 | 生成用户级别 Access Token |
+| GET | /api/user/aff | 用户 | 获取推广码信息 |
+| POST | /api/user/topup | 用户 | 余额直充 |
+| POST | /api/user/pay | 用户 | 提交支付订单 |
+| POST | /api/user/amount | 用户 | 余额支付 |
+| POST | /api/user/aff_transfer | 用户 | 推广额度转账 |
+| PUT | /api/user/setting | 用户 | 更新用户设置 |
+
+### 5.3 管理员用户管理
+| 方法 | 路径 | 鉴权 | 说明 |
+|------|------|------|------|
+| GET | /api/user/ | 管理员 | 获取全部用户列表 |
+| GET | /api/user/search | 管理员 | 搜索用户 |
+| GET | /api/user/:id | 管理员 | 获取单个用户信息 |
+| POST | /api/user/ | 管理员 | 创建用户 |
+| POST | /api/user/manage | 管理员 | 冻结/重置等管理操作 |
+| PUT | /api/user/ | 管理员 | 更新用户 |
+| DELETE | /api/user/:id | 管理员 | 删除用户 |
+
+## 6. 站点选项 (Root)
+| 方法 | 路径 | 鉴权 | 说明 |
+|------|------|------|------|
+| GET | /api/option/ | Root | 获取全局配置 |
+| PUT | /api/option/ | Root | 更新全局配置 |
+| POST | /api/option/rest_model_ratio | Root | 重置模型倍率 |
+| POST | /api/option/migrate_console_setting | Root | 迁移旧版控制台配置 |
+
+## 7. 模型倍率同步 (Root)
+| 方法 | 路径 | 鉴权 | 说明 |
+|------|------|------|------|
+| GET | /api/ratio_sync/channels | Root | 获取可同步渠道列表 |
+| POST | /api/ratio_sync/fetch | Root | 从上游拉取倍率 |
+
+## 8. 渠道管理 (管理员)
+| 方法 | 路径 | 说明 |
+|------|------|------|
+| GET | /api/channel/ | 获取渠道列表 |
+| GET | /api/channel/search | 搜索渠道 |
+| GET | /api/channel/models | 查询渠道模型能力 |
+| GET | /api/channel/models_enabled | 查询启用模型能力 |
+| GET | /api/channel/:id | 获取单个渠道 |
+| GET | /api/channel/test | 批量测试渠道连通性 |
+| GET | /api/channel/test/:id | 单个渠道测试 |
+| GET | /api/channel/update_balance | 批量刷新余额 |
+| GET | /api/channel/update_balance/:id | 单个刷新余额 |
+| POST | /api/channel/ | 新增渠道 |
+| PUT | /api/channel/ | 更新渠道 |
+| DELETE | /api/channel/disabled | 删除已禁用渠道 |
+| POST | /api/channel/tag/disabled | 批量禁用标签渠道 |
+| POST | /api/channel/tag/enabled | 批量启用标签渠道 |
+| PUT | /api/channel/tag | 编辑渠道标签 |
+| DELETE | /api/channel/:id | 删除渠道 |
+| POST | /api/channel/batch | 批量删除渠道 |
+| POST | /api/channel/fix | 修复渠道能力表 |
+| GET | /api/channel/fetch_models/:id | 拉取单渠道模型 |
+| POST | /api/channel/fetch_models | 拉取全部渠道模型 |
+| POST | /api/channel/batch/tag | 批量设置渠道标签 |
+| GET | /api/channel/tag/models | 根据标签获取模型 |
+| POST | /api/channel/copy/:id | 复制渠道 |
+
+## 9. Token 管理
+| 方法 | 路径 | 鉴权 | 说明 |
+|------|------|------|------|
+| GET | /api/token/ | 用户 | 获取全部 Token |
+| GET | /api/token/search | 用户 | 搜索 Token |
+| GET | /api/token/:id | 用户 | 获取单个 Token |
+| POST | /api/token/ | 用户 | 创建 Token |
+| PUT | /api/token/ | 用户 | 更新 Token |
+| DELETE | /api/token/:id | 用户 | 删除 Token |
+| POST | /api/token/batch | 用户 | 批量删除 Token |
+
+## 10. 兑换码管理 (管理员)
+| 方法 | 路径 | 说明 |
+|------|------|------|
+| GET | /api/redemption/ | 获取兑换码列表 |
+| GET | /api/redemption/search | 搜索兑换码 |
+| GET | /api/redemption/:id | 获取单个兑换码 |
+| POST | /api/redemption/ | 创建兑换码 |
+| PUT | /api/redemption/ | 更新兑换码 |
+| DELETE | /api/redemption/invalid | 删除无效兑换码 |
+| DELETE | /api/redemption/:id | 删除兑换码 |
+
+## 11. 日志
+| 方法 | 路径 | 鉴权 | 说明 |
+|------|------|------|------|
+| GET | /api/log/ | 管理员 | 获取全部日志 |
+| DELETE | /api/log/ | 管理员 | 删除历史日志 |
+| GET | /api/log/stat | 管理员 | 日志统计 |
+| GET | /api/log/self/stat | 用户 | 我的日志统计 |
+| GET | /api/log/search | 管理员 | 搜索全部日志 |
+| GET | /api/log/self | 用户 | 获取我的日志 |
+| GET | /api/log/self/search | 用户 | 搜索我的日志 |
+| GET | /api/log/token | 公开 | 根据 Token 查询日志（支持 CORS） |
+
+## 12. 数据统计
+| 方法 | 路径 | 鉴权 | 说明 |
+|------|------|------|------|
+| GET | /api/data/ | 管理员 | 全站用量按日期统计 |
+| GET | /api/data/self | 用户 | 我的用量按日期统计 |
+
+## 13. 分组
+| GET | /api/group/ | 管理员 | 获取全部分组列表 |
+
+## 14. Midjourney 任务
+| 方法 | 路径 | 鉴权 | 说明 |
+|------|------|------|------|
+| GET | /api/mj/self | 用户 | 获取自己的 MJ 任务 |
+| GET | /api/mj/ | 管理员 | 获取全部 MJ 任务 |
+
+## 15. 任务中心
+| 方法 | 路径 | 鉴权 | 说明 |
+|------|------|------|------|
+| GET | /api/task/self | 用户 | 获取我的任务 |
+| GET | /api/task/ | 管理员 | 获取全部任务 |
+
+## 16. 账户计费面板 (Dashboard)
+| 方法 | 路径 | 鉴权 | 说明 |
+|------|------|------|------|
+| GET | /dashboard/billing/subscription | 用户 Token | 获取订阅额度信息 |
+| GET | /v1/dashboard/billing/subscription | 同上 | 兼容 OpenAI SDK 路径 |
+| GET | /dashboard/billing/usage | 用户 Token | 获取使用量信息 |
+| GET | /v1/dashboard/billing/usage | 同上 | 兼容 OpenAI SDK 路径 |
+
+---
+
+> **更新日期**：2025.07.17

docs/models/Midjourney.md

@@ -0,0 +1,82 @@
+# Midjourney Proxy API文档
+
+**简介**:Midjourney Proxy API文档
+
+## 接口列表
+支持的接口如下：
++ [x] /mj/submit/imagine
++ [x] /mj/submit/change
++ [x] /mj/submit/blend
++ [x] /mj/submit/describe
++ [x] /mj/image/{id} （通过此接口获取图片，**请必须在系统设置中填写服务器地址！！**）
++ [x] /mj/task/{id}/fetch （此接口返回的图片地址为经过One API转发的地址）
++ [x] /task/list-by-condition
++ [x] /mj/submit/action （仅midjourney-proxy-plus支持，下同）
++ [x] /mj/submit/modal
++ [x] /mj/submit/shorten
++ [x] /mj/task/{id}/image-seed
++ [x] /mj/insight-face/swap （InsightFace）
+
+## 模型列表
+
+### midjourney-proxy支持
+
+- mj_imagine (绘图)
+- mj_variation (变换)
+- mj_reroll (重绘)
+- mj_blend (混合)
+- mj_upscale (放大)
+- mj_describe (图生文)
+
+### 仅midjourney-proxy-plus支持
+
+- mj_zoom (比例变焦)
+- mj_shorten (提示词缩短)
+- mj_modal (窗口提交，局部重绘和自定义比例变焦必须和mj_modal一同添加)
+- mj_inpaint (局部重绘提交，必须和mj_modal一同添加)
+- mj_custom_zoom (自定义比例变焦，必须和mj_modal一同添加)
+- mj_high_variation (强变换)
+- mj_low_variation (弱变换)
+- mj_pan (平移)
+- swap_face (换脸)
+
+## 模型价格设置（在设置-运营设置-模型固定价格设置中设置）
+```json
+{
+  "mj_imagine": 0.1,
+  "mj_variation": 0.1,
+  "mj_reroll": 0.1,
+  "mj_blend": 0.1,
+  "mj_modal": 0.1,
+  "mj_zoom": 0.1,
+  "mj_shorten": 0.1,
+  "mj_high_variation": 0.1,
+  "mj_low_variation": 0.1,
+  "mj_pan": 0.1,
+  "mj_inpaint": 0,
+  "mj_custom_zoom": 0,
+  "mj_describe": 0.05,
+  "mj_upscale": 0.05,
+  "swap_face": 0.05
+}
+```
+其中mj_inpaint和mj_custom_zoom的价格设置为0，是因为这两个模型需要搭配mj_modal使用，所以价格由mj_modal决定。
+
+## 渠道设置
+
+### 对接 midjourney-proxy(plus)
+
+1.
+
+部署Midjourney-Proxy，并配置好midjourney账号等（强烈建议设置密钥），[项目地址](https://github.com/novicezk/midjourney-proxy)
+
+2. 在渠道管理中添加渠道，渠道类型选择**Midjourney Proxy**，如果是plus版本选择**Midjourney Proxy Plus**
+   ，模型请参考上方模型列表
+3. **代理**填写midjourney-proxy部署的地址，例如：http://localhost:8080
+4. 密钥填写midjourney-proxy的密钥，如果没有设置密钥，可以随便填
+
+### 对接上游new api
+
+1. 在渠道管理中添加渠道，渠道类型选择**Midjourney Proxy Plus**，模型请参考上方模型列表
+2. **代理**填写上游new api的地址，例如：http://localhost:3000
+3. 密钥填写上游new api的密钥

docs/models/Rerank.md

@@ -0,0 +1,62 @@
+# Rerank API文档
+
+**简介**:Rerank API文档
+
+## 接入Dify
+模型供应商选择Jina，按要求填写模型信息即可接入Dify。
+
+## 请求方式
+
+Post: /v1/rerank
+
+Request:
+
+```json
+{
+  "model": "jina-reranker-v2-base-multilingual",
+  "query": "What is the capital of the United States?",
+  "top_n": 3,
+  "documents": [
+    "Carson City is the capital city of the American state of Nevada.",
+    "The Commonwealth of the Northern Mariana Islands is a group of islands in the Pacific Ocean. Its capital is Saipan.",
+    "Washington, D.C. (also known as simply Washington or D.C., and officially as the District of Columbia) is the capital of the United States. It is a federal district.",
+    "Capitalization or capitalisation in English grammar is the use of a capital letter at the start of a word. English usage varies from capitalization in other languages.",
+    "Capital punishment (the death penalty) has existed in the United States since beforethe United States was a country. As of 2017, capital punishment is legal in 30 of the 50 states."
+  ]
+}
+```
+
+Response:
+
+```json
+{
+  "results": [
+    {
+      "document": {
+        "text": "Washington, D.C. (also known as simply Washington or D.C., and officially as the District of Columbia) is the capital of the United States. It is a federal district."
+      },
+      "index": 2,
+      "relevance_score": 0.9999702
+    },
+    {
+      "document": {
+        "text": "Carson City is the capital city of the American state of Nevada."
+      },
+      "index": 0,
+      "relevance_score": 0.67800725
+    },
+    {
+      "document": {
+        "text": "Capitalization or capitalisation in English grammar is the use of a capital letter at the start of a word. English usage varies from capitalization in other languages."
+      },
+      "index": 3,
+      "relevance_score": 0.02800752
+    }
+  ],
+  "usage": {
+    "prompt_tokens": 158,
+    "completion_tokens": 0,
+    "total_tokens": 158
+  }
+}
+```

docs/models/Suno.md

@@ -0,0 +1,44 @@
+# Suno API文档
+
+**简介**:Suno API文档
+
+## 接口列表
+支持的接口如下：
++ [x] /suno/submit/music
++ [x] /suno/submit/lyrics
++ [x] /suno/fetch
++ [x] /suno/fetch/:id
+
+## 模型列表
+
+### Suno API支持
+
+- suno_music (自定义模式、灵感模式、续写)
+- suno_lyrics (生成歌词)
+
+
+## 模型价格设置（在设置-运营设置-模型固定价格设置中设置）
+```json
+{
+  "suno_music": 0.3,
+  "suno_lyrics": 0.01
+}
+```
+
+## 渠道设置
+
+### 对接 Suno API
+
+1.
+部署 Suno API，并配置好suno账号等（强烈建议设置密钥），[项目地址](https://github.com/Suno-API/Suno-API)
+
+2. 在渠道管理中添加渠道，渠道类型选择**Suno API**
+   ，模型请参考上方模型列表
+3. **代理**填写 Suno API 部署的地址，例如：http://localhost:8080
+4. 密钥填写 Suno API 的密钥，如果没有设置密钥，可以随便填
+
+### 对接上游new api
+
+1. 在渠道管理中添加渠道，渠道类型选择**Suno API**，或任意类型，只需模型包含上方模型列表的模型
+2. **代理**填写上游new api的地址，例如：http://localhost:3000
+3. 密钥填写上游new api的密钥

dto/audio.go

@@ -2,7 +2,6 @@ package dto
 
 import (
 	"encoding/json"
-	"strings"
 
 	"github.com/QuantumNous/new-api/types"
 
@@ -25,14 +24,11 @@ func (r *AudioRequest) GetTokenCountMeta() *types.TokenCountMeta {
 		CombineText: r.Input,
 		TokenType:   types.TokenTypeTextNumber,
 	}
-	if strings.Contains(r.Model, "gpt") {
-		meta.TokenType = types.TokenTypeTokenizer
-	}
 	return meta
 }
 
 func (r *AudioRequest) IsStream(c *gin.Context) bool {
-	return r.StreamFormat == "sse"
+	return false
 }
 
 func (r *AudioRequest) SetModelName(modelName string) {

dto/claude.go

@@ -203,9 +203,6 @@ type ClaudeRequest struct {
 	Stream            bool            `json:"stream,omitempty"`
 	Tools             any             `json:"tools,omitempty"`
 	ContextManagement json.RawMessage `json:"context_management,omitempty"`
-	OutputConfig      json.RawMessage `json:"output_config,omitempty"`
-	OutputFormat      json.RawMessage `json:"output_format,omitempty"`
-	Container         json.RawMessage `json:"container,omitempty"`
 	ToolChoice        any             `json:"tool_choice,omitempty"`
 	Thinking          *Thinking       `json:"thinking,omitempty"`
 	McpServers        json.RawMessage `json:"mcp_servers,omitempty"`

dto/error.go

@@ -1,32 +1,26 @@
 package dto
 
-import (
-	"encoding/json"
+import "github.com/QuantumNous/new-api/types"
 
-	"github.com/QuantumNous/new-api/common"
-	"github.com/QuantumNous/new-api/types"
-)
-
-//type OpenAIError struct {
-//	Message string `json:"message"`
-//	Type    string `json:"type"`
-//	Param   string `json:"param"`
-//	Code    any    `json:"code"`
-//}
+type OpenAIError struct {
+	Message string `json:"message"`
+	Type    string `json:"type"`
+	Param   string `json:"param"`
+	Code    any    `json:"code"`
+}
 
 type OpenAIErrorWithStatusCode struct {
-	Error      types.OpenAIError `json:"error"`
-	StatusCode int               `json:"status_code"`
+	Error      OpenAIError `json:"error"`
+	StatusCode int         `json:"status_code"`
 	LocalError bool
 }
 
 type GeneralErrorResponse struct {
-	Error    json.RawMessage `json:"error"`
-	Message  string          `json:"message"`
-	Msg      string          `json:"msg"`
-	Err      string          `json:"err"`
-	ErrorMsg string          `json:"error_msg"`
-	Metadata json.RawMessage   `json:"metadata,omitempty"`
+	Error    types.OpenAIError `json:"error"`
+	Message  string            `json:"message"`
+	Msg      string            `json:"msg"`
+	Err      string            `json:"err"`
+	ErrorMsg string            `json:"error_msg"`
 	Header   struct {
 		Message string `json:"message"`
 	} `json:"header"`
@@ -37,35 +31,9 @@ type GeneralErrorResponse struct {
 	} `json:"response"`
 }
 
-func (e GeneralErrorResponse) TryToOpenAIError() *types.OpenAIError {
-	var openAIError types.OpenAIError
-	if len(e.Error) > 0 {
-		err := common.Unmarshal(e.Error, &openAIError)
-		if err == nil && openAIError.Message != "" {
-			return &openAIError
-		}
-	}
-	return nil
-}
-
 func (e GeneralErrorResponse) ToMessage() string {
-	if len(e.Error) > 0 {
-		switch common.GetJsonType(e.Error) {
-		case "object":
-			var openAIError types.OpenAIError
-			err := common.Unmarshal(e.Error, &openAIError)
-			if err == nil && openAIError.Message != "" {
-				return openAIError.Message
-			}
-		case "string":
-			var msg string
-			err := common.Unmarshal(e.Error, &msg)
-			if err == nil && msg != "" {
-				return msg
-			}
-		default:
-			return string(e.Error)
-		}
+	if e.Error.Message != "" {
+		return e.Error.Message
 	}
 	if e.Message != "" {
 		return e.Message

dto/gemini.go

@@ -22,27 +22,6 @@ type GeminiChatRequest struct {
 	CachedContent      string                     `json:"cachedContent,omitempty"`
 }
 
-// UnmarshalJSON allows GeminiChatRequest to accept both snake_case and camelCase fields.
-func (r *GeminiChatRequest) UnmarshalJSON(data []byte) error {
-	type Alias GeminiChatRequest
-	var aux struct {
-		Alias
-		SystemInstructionSnake *GeminiChatContent `json:"system_instruction,omitempty"`
-	}
-
-	if err := common.Unmarshal(data, &aux); err != nil {
-		return err
-	}
-
-	*r = GeminiChatRequest(aux.Alias)
-
-	if aux.SystemInstructionSnake != nil {
-		r.SystemInstructions = aux.SystemInstructionSnake
-	}
-
-	return nil
-}
-
 type ToolConfig struct {
 	FunctionCallingConfig *FunctionCallingConfig `json:"functionCallingConfig,omitempty"`
 	RetrievalConfig       *RetrievalConfig       `json:"retrievalConfig,omitempty"`
@@ -163,7 +142,7 @@ type GeminiThinkingConfig struct {
 	IncludeThoughts bool `json:"includeThoughts,omitempty"`
 	ThinkingBudget  *int `json:"thinkingBudget,omitempty"`
 	// TODO Conflict with thinkingbudget.
-	ThinkingLevel string `json:"thinkingLevel,omitempty"`
+	ThinkingLevel json.RawMessage `json:"thinkingLevel,omitempty"`
 }
 
 // UnmarshalJSON allows GeminiThinkingConfig to accept both snake_case and camelCase fields.
@@ -171,9 +150,9 @@ func (c *GeminiThinkingConfig) UnmarshalJSON(data []byte) error {
 	type Alias GeminiThinkingConfig
 	var aux struct {
 		Alias
-		IncludeThoughtsSnake *bool  `json:"include_thoughts,omitempty"`
-		ThinkingBudgetSnake  *int   `json:"thinking_budget,omitempty"`
-		ThinkingLevelSnake   string `json:"thinking_level,omitempty"`
+		IncludeThoughtsSnake *bool           `json:"include_thoughts,omitempty"`
+		ThinkingBudgetSnake  *int            `json:"thinking_budget,omitempty"`
+		ThinkingLevelSnake   json.RawMessage `json:"thinking_level,omitempty"`
 	}
 
 	if err := common.Unmarshal(data, &aux); err != nil {
@@ -190,7 +169,7 @@ func (c *GeminiThinkingConfig) UnmarshalJSON(data []byte) error {
 		c.ThinkingBudget = aux.ThinkingBudgetSnake
 	}
 
-	if aux.ThinkingLevelSnake != "" {
+	if len(aux.ThinkingLevelSnake) > 0 {
 		c.ThinkingLevel = aux.ThinkingLevelSnake
 	}
 

dto/openai_image.go

@@ -27,11 +27,8 @@ type ImageRequest struct {
 	OutputCompression json.RawMessage `json:"output_compression,omitempty"`
 	PartialImages     json.RawMessage `json:"partial_images,omitempty"`
 	// Stream            bool            `json:"stream,omitempty"`
-	Watermark *bool `json:"watermark,omitempty"`
-	// zhipu 4v
-	WatermarkEnabled json.RawMessage `json:"watermark_enabled,omitempty"`
-	UserId           json.RawMessage `json:"user_id,omitempty"`
-	Image            json.RawMessage `json:"image,omitempty"`
+	Watermark *bool           `json:"watermark,omitempty"`
+	Image     json.RawMessage `json:"image,omitempty"`
 	// 用匿名参数接收额外参数
 	Extra map[string]json.RawMessage `json:"-"`
 }

dto/openai_request.go

@@ -83,7 +83,6 @@ type GeneralOpenAIRequest struct {
 	// Ali Qwen Params
 	VlHighResolutionImages json.RawMessage `json:"vl_high_resolution_images,omitempty"`
 	EnableThinking         any             `json:"enable_thinking,omitempty"`
-	ChatTemplateKwargs     json.RawMessage `json:"chat_template_kwargs,omitempty"`
 	// ollama Params
 	Think json.RawMessage `json:"think,omitempty"`
 	// baidu v2

go.mod

@@ -27,14 +27,13 @@ require (
 	github.com/golang-jwt/jwt/v5 v5.3.0
 	github.com/google/uuid v1.6.0
 	github.com/gorilla/websocket v1.5.0
-	github.com/grafana/pyroscope-go v1.2.7
 	github.com/jfreymuth/oggvorbis v1.0.5
 	github.com/jinzhu/copier v0.4.0
 	github.com/joho/godotenv v1.5.1
 	github.com/mewkiz/flac v1.0.13
 	github.com/pkg/errors v0.9.1
 	github.com/pquerna/otp v1.5.0
-	github.com/samber/lo v1.52.0
+	github.com/samber/lo v1.39.0
 	github.com/shirou/gopsutil v3.21.11+incompatible
 	github.com/shopspring/decimal v1.4.0
 	github.com/stripe/stripe-go/v81 v81.4.0
@@ -78,11 +77,11 @@ require (
 	github.com/go-sql-driver/mysql v1.7.0 // indirect
 	github.com/go-webauthn/x v0.1.25 // indirect
 	github.com/goccy/go-json v0.10.2 // indirect
+	github.com/google/go-cmp v0.6.0 // indirect
 	github.com/google/go-tpm v0.9.5 // indirect
 	github.com/gorilla/context v1.1.1 // indirect
 	github.com/gorilla/securecookie v1.1.1 // indirect
 	github.com/gorilla/sessions v1.2.1 // indirect
-	github.com/grafana/pyroscope-go/godeltaprof v0.1.9 // indirect
 	github.com/icza/bitio v1.1.0 // indirect
 	github.com/jackc/pgpassfile v1.0.0 // indirect
 	github.com/jackc/pgservicefile v0.0.0-20240606120523-5a60cdf6a761 // indirect
@@ -92,7 +91,6 @@ require (
 	github.com/jinzhu/inflection v1.0.0 // indirect
 	github.com/jinzhu/now v1.1.5 // indirect
 	github.com/json-iterator/go v1.1.12 // indirect
-	github.com/klauspost/compress v1.17.8 // indirect
 	github.com/klauspost/cpuid/v2 v2.3.0 // indirect
 	github.com/leodido/go-urn v1.4.0 // indirect
 	github.com/mattn/go-isatty v0.0.20 // indirect
@@ -101,7 +99,6 @@ require (
 	github.com/mitchellh/mapstructure v1.5.0 // indirect
 	github.com/modern-go/concurrent v0.0.0-20180306012644-bacd9c7ef1dd // indirect
 	github.com/modern-go/reflect2 v1.0.2 // indirect
-	github.com/ncruces/go-strftime v0.1.9 // indirect
 	github.com/pelletier/go-toml/v2 v2.2.1 // indirect
 	github.com/remyoudompheng/bigfft v0.0.0-20230129092748-24d4a6f8daec // indirect
 	github.com/tidwall/match v1.1.1 // indirect
@@ -113,13 +110,13 @@ require (
 	github.com/x448/float16 v0.8.4 // indirect
 	github.com/yusufpapurcu/wmi v1.2.3 // indirect
 	golang.org/x/arch v0.21.0 // indirect
-	golang.org/x/exp v0.0.0-20250620022241-b7579e27df2b // indirect
+	golang.org/x/exp v0.0.0-20240404231335-c0f41cb1a7a0 // indirect
 	golang.org/x/sys v0.38.0 // indirect
 	golang.org/x/text v0.31.0 // indirect
 	google.golang.org/protobuf v1.34.2 // indirect
 	gopkg.in/yaml.v3 v3.0.1 // indirect
-	modernc.org/libc v1.66.10 // indirect
-	modernc.org/mathutil v1.7.1 // indirect
-	modernc.org/memory v1.11.0 // indirect
-	modernc.org/sqlite v1.40.1 // indirect
+	modernc.org/libc v1.22.5 // indirect
+	modernc.org/mathutil v1.5.0 // indirect
+	modernc.org/memory v1.5.0 // indirect
+	modernc.org/sqlite v1.23.1 // indirect
 )

go.sum

@@ -118,8 +118,8 @@ github.com/google/go-cmp v0.6.0/go.mod h1:17dUlkBOakJ0+DkrSSNjCkIjxS6bF9zb3elmeN
 github.com/google/go-tpm v0.9.5 h1:ocUmnDebX54dnW+MQWGQRbdaAcJELsa6PqZhJ48KwVU=
 github.com/google/go-tpm v0.9.5/go.mod h1:h9jEsEECg7gtLis0upRBQU+GhYVH6jMjrFxI8u6bVUY=
 github.com/google/gofuzz v1.0.0/go.mod h1:dBl0BpW6vV/+mYPU4Po3pmUjxk6FQPldtuIdl/M65Eg=
-github.com/google/pprof v0.0.0-20250317173921-a4b03ec1a45e h1:ijClszYn+mADRFY17kjQEVQ1XRhq2/JR1M3sGqeJoxs=
-github.com/google/pprof v0.0.0-20250317173921-a4b03ec1a45e/go.mod h1:boTsfXsheKC2y+lKOCMpSfarhxDeIzfZG1jqGcPl3cA=
+github.com/google/pprof v0.0.0-20221118152302-e6195bd50e26 h1:Xim43kblpZXfIBQsbuBVKCudVG457BR2GZFIz3uw3hQ=
+github.com/google/pprof v0.0.0-20221118152302-e6195bd50e26/go.mod h1:dDKJzRmX4S37WGHujM7tX//fmj1uioxKzKxz3lo4HJo=
 github.com/google/uuid v1.1.2/go.mod h1:TIyPZe4MgqvfeYDBFedMoGGpEw/LqOeaOT+nhxU+yHo=
 github.com/google/uuid v1.6.0 h1:NIvaJDMOsjHA8n1jAhLSgzrAzy1Hgr+hNrb57e+94F0=
 github.com/google/uuid v1.6.0/go.mod h1:TIyPZe4MgqvfeYDBFedMoGGpEw/LqOeaOT+nhxU+yHo=
@@ -131,10 +131,6 @@ github.com/gorilla/sessions v1.2.1 h1:DHd3rPN5lE3Ts3D8rKkQ8x/0kqfeNmBAaiSi+o7Fsg
 github.com/gorilla/sessions v1.2.1/go.mod h1:dk2InVEVJ0sfLlnXv9EAgkf6ecYs/i80K/zI+bUmuGM=
 github.com/gorilla/websocket v1.5.0 h1:PPwGk2jz7EePpoHN/+ClbZu8SPxiqlu12wZP/3sWmnc=
 github.com/gorilla/websocket v1.5.0/go.mod h1:YR8l580nyteQvAITg2hZ9XVh4b55+EU/adAjf1fMHhE=
-github.com/grafana/pyroscope-go v1.2.7 h1:VWBBlqxjyR0Cwk2W6UrE8CdcdD80GOFNutj0Kb1T8ac=
-github.com/grafana/pyroscope-go v1.2.7/go.mod h1:o/bpSLiJYYP6HQtvcoVKiE9s5RiNgjYTj1DhiddP2Pc=
-github.com/grafana/pyroscope-go/godeltaprof v0.1.9 h1:c1Us8i6eSmkW+Ez05d3co8kasnuOY813tbMN8i/a3Og=
-github.com/grafana/pyroscope-go/godeltaprof v0.1.9/go.mod h1:2+l7K7twW49Ct4wFluZD3tZ6e0SjanjcUUBPVD/UuGU=
 github.com/icza/bitio v1.1.0 h1:ysX4vtldjdi3Ygai5m1cWy4oLkhWTAi+SyO6HC8L9T0=
 github.com/icza/bitio v1.1.0/go.mod h1:0jGnlLAx8MKMr9VGnn/4YrvZiprkvBelsVIbA9Jjr9A=
 github.com/icza/mighty v0.0.0-20180919140131-cfd07d671de6 h1:8UsGZ2rr2ksmEru6lToqnXgA8Mz1DP11X4zSJ159C3k=
@@ -163,15 +159,12 @@ github.com/joho/godotenv v1.5.1/go.mod h1:f4LDr5Voq0i2e/R5DDNOoa2zzDfwtkZa6DnEwA
 github.com/json-iterator/go v1.1.9/go.mod h1:KdQUCv79m/52Kvf8AW2vK1V8akMuk1QjK/uOdHXbAo4=
 github.com/json-iterator/go v1.1.12 h1:PV8peI4a0ysnczrg+LtxykD8LfKY9ML6u2jnxaEnrnM=
 github.com/json-iterator/go v1.1.12/go.mod h1:e30LSqwooZae/UwlEbR2852Gd8hjQvJoHmT4TnhNGBo=
-github.com/klauspost/compress v1.17.8 h1:YcnTYrq7MikUT7k0Yb5eceMmALQPYBW/Xltxn0NAMnU=
-github.com/klauspost/compress v1.17.8/go.mod h1:Di0epgTjJY877eYKx5yC51cX2A2Vl2ibi7bDH9ttBbw=
 github.com/klauspost/cpuid/v2 v2.3.0 h1:S4CRMLnYUhGeDFDqkGriYKdfoFlDnMtqTiI/sFzhA9Y=
 github.com/klauspost/cpuid/v2 v2.3.0/go.mod h1:hqwkgyIinND0mEev00jJYCxPNVRVXFQeu1XKlok6oO0=
 github.com/kr/pretty v0.1.0/go.mod h1:dAy3ld7l9f0ibDNOQOHHMYYIIbhfbHSm3C4ZsoJORNo=
 github.com/kr/pretty v0.2.1/go.mod h1:ipq/a2n7PKx3OHsz4KJII5eveXtPO4qwEXGdVfWzfnI=
+github.com/kr/pretty v0.3.0 h1:WgNl7dwNpEZ6jJ9k1snq4pZsg7DOEN8hP9Xw0Tsjwk0=
 github.com/kr/pretty v0.3.0/go.mod h1:640gp4NfQd8pI5XOwp5fnNeVWj67G7CFk/SaSQn7NBk=
-github.com/kr/pretty v0.3.1 h1:flRD4NNwYAUpkphVc1HcthR4KEIFJ65n8Mw5qdRn3LE=
-github.com/kr/pretty v0.3.1/go.mod h1:hoEshYVHaxMs3cyo3Yncou5ZscifuDolrwPKZanG3xk=
 github.com/kr/pty v1.1.1/go.mod h1:pFQYn66WHrOpPYNljwOMqo10TkYh1fy3cYio2l3bCsQ=
 github.com/kr/pty v1.1.8/go.mod h1:O1sed60cT9XZ5uDucP5qwvh+TE3NnUj51EiZO/lmSfw=
 github.com/kr/text v0.1.0/go.mod h1:4Jbv+DJW3UT/LiOwJeYQe1efqtUx/iVham/4vfdArNI=
@@ -200,8 +193,6 @@ github.com/modern-go/concurrent v0.0.0-20180306012644-bacd9c7ef1dd/go.mod h1:6dJ
 github.com/modern-go/reflect2 v0.0.0-20180701023420-4b7aa43c6742/go.mod h1:bx2lNnkwVCuqBIxFjflWJWanXIb3RllmbCylyMrvgv0=
 github.com/modern-go/reflect2 v1.0.2 h1:xBagoLtFs94CBntxluKeaWgTMpvLxC4ur3nMaC9Gz0M=
 github.com/modern-go/reflect2 v1.0.2/go.mod h1:yWuevngMOJpCy52FWWMvUC8ws7m/LJsjYzDa0/r8luk=
-github.com/ncruces/go-strftime v0.1.9 h1:bY0MQC28UADQmHmaF5dgpLmImcShSi2kHU9XLdhx/f4=
-github.com/ncruces/go-strftime v0.1.9/go.mod h1:Fwc5htZGVVkseilnfgOVb9mKy6w1naJmn9CehxcKcls=
 github.com/nxadm/tail v1.4.8 h1:nPr65rt6Y5JFSKQO7qToXr7pePgD6Gwiw05lkbyAQTE=
 github.com/nxadm/tail v1.4.8/go.mod h1:+ncqLTQzXmGhMZNUePPaPqPvBxHAIsmXswZKocGu+AU=
 github.com/onsi/ginkgo v1.16.5 h1:8xi0RTUf59SOSfEtZMvwTvXYMzG4gV23XVHOZiXNtnE=
@@ -220,13 +211,14 @@ github.com/pmezard/go-difflib v1.0.0 h1:4DBwDE0NGyQoBHbLQYPwSUPoCMWR5BEzIk/f1lZb
 github.com/pmezard/go-difflib v1.0.0/go.mod h1:iKH77koFhYxTK1pcRnkKkqfTogsbg7gZNVY4sRDYZ/4=
 github.com/pquerna/otp v1.5.0 h1:NMMR+WrmaqXU4EzdGJEE1aUUI0AMRzsp96fFFWNPwxs=
 github.com/pquerna/otp v1.5.0/go.mod h1:dkJfzwRKNiegxyNb54X/3fLwhCynbMspSyWKnvi1AEg=
+github.com/remyoudompheng/bigfft v0.0.0-20200410134404-eec4a21b6bb0/go.mod h1:qqbHyh8v60DhA7CoWK5oRCqLrMHRGoxYCSS9EjAz6Eo=
 github.com/remyoudompheng/bigfft v0.0.0-20230129092748-24d4a6f8daec h1:W09IVJc94icq4NjY3clb7Lk8O1qJ8BdBEF8z0ibU0rE=
 github.com/remyoudompheng/bigfft v0.0.0-20230129092748-24d4a6f8daec/go.mod h1:qqbHyh8v60DhA7CoWK5oRCqLrMHRGoxYCSS9EjAz6Eo=
 github.com/rogpeppe/go-internal v1.6.1/go.mod h1:xXDCJY+GAPziupqXw64V24skbSoqbTEfhy4qGm1nDQc=
 github.com/rogpeppe/go-internal v1.8.0 h1:FCbCCtXNOY3UtUuHUYaghJg4y7Fd14rXifAYUAtL9R8=
 github.com/rogpeppe/go-internal v1.8.0/go.mod h1:WmiCO8CzOY8rg0OYDC4/i/2WRWAB6poM+XZ2dLUbcbE=
-github.com/samber/lo v1.52.0 h1:Rvi+3BFHES3A8meP33VPAxiBZX/Aws5RxrschYGjomw=
-github.com/samber/lo v1.52.0/go.mod h1:4+MXEGsJzbKGaUEQFKBq2xtfuznW9oz/WrgyzMzRoM0=
+github.com/samber/lo v1.39.0 h1:4gTz1wUhNYLhFSKl6O+8peW0v2F4BCY034GRpU9WnuA=
+github.com/samber/lo v1.39.0/go.mod h1:+m/ZKRl6ClXCE2Lgf3MsQlWfh4bn1bz6CXEOxnEXnEA=
 github.com/shirou/gopsutil v3.21.11+incompatible h1:+1+c1VGhc88SSonWP6foOcLhvnKlUeu/erjjvaPEYiI=
 github.com/shirou/gopsutil v3.21.11+incompatible/go.mod h1:5b4v6he4MtMOwMlS0TUMTu2PcXUg8+E1lC7eC3UO/RA=
 github.com/shopspring/decimal v1.4.0 h1:bxl37RwXBklmTi0C79JfXCEBD1cqqHt0bbgBAGFp81k=
@@ -234,7 +226,6 @@ github.com/shopspring/decimal v1.4.0/go.mod h1:gawqmDU56v4yIKSwfBSFip1HdCCXN8/+D
 github.com/stretchr/objx v0.1.0/go.mod h1:HFkY916IF+rwdDfMAkV7OtwuqBVzrE8GR6GFx+wExME=
 github.com/stretchr/objx v0.4.0/go.mod h1:YvHI0jy2hoMjB+UWwv71VJQ9isScKT/TqJzVSSt89Yw=
 github.com/stretchr/objx v0.5.0/go.mod h1:Yh+to48EsGEfYuaHDzXPcE3xhTkx73EhmCGUpEOglKo=
-github.com/stretchr/objx v0.5.2 h1:xuMeJ0Sdp5ZMRXx/aWO6RZxdr3beISkG5/G/aIRr3pY=
 github.com/stretchr/objx v0.5.2/go.mod h1:FRsXN1f5AsAjCGJKqEizvkpNtU+EGNCLh3NxZ/8L+MA=
 github.com/stretchr/testify v1.3.0/go.mod h1:M5WIy9Dh21IEIfnGCwXGc5bZfKNJtfHm1UVUgZn+9EI=
 github.com/stretchr/testify v1.4.0/go.mod h1:j7eGeouHqKxXV5pUuKE4zz7dFj8WfuZ+81PSLYec5m4=
@@ -292,12 +283,10 @@ golang.org/x/arch v0.21.0/go.mod h1:dNHoOeKiyja7GTvF9NJS1l3Z2yntpQNzgrjh1cU103A=
 golang.org/x/crypto v0.0.0-20210711020723-a769d52b0f97/go.mod h1:GvvjBRRGRdwPK5ydBHafDWAxML/pGHZbMvKqRZ5+Abc=
 golang.org/x/crypto v0.45.0 h1:jMBrvKuj23MTlT0bQEOBcAE0mjg8mK9RXFhRH6nyF3Q=
 golang.org/x/crypto v0.45.0/go.mod h1:XTGrrkGJve7CYK7J8PEww4aY7gM3qMCElcJQ8n8JdX4=
-golang.org/x/exp v0.0.0-20250620022241-b7579e27df2b h1:M2rDM6z3Fhozi9O7NWsxAkg/yqS/lQJ6PmkyIV3YP+o=
-golang.org/x/exp v0.0.0-20250620022241-b7579e27df2b/go.mod h1:3//PLf8L/X+8b4vuAfHzxeRUl04Adcb341+IGKfnqS8=
+golang.org/x/exp v0.0.0-20240404231335-c0f41cb1a7a0 h1:985EYyeCOxTpcgOTJpflJUwOeEz0CQOdPt73OzpE9F8=
+golang.org/x/exp v0.0.0-20240404231335-c0f41cb1a7a0/go.mod h1:/lliqkxwWAhPjf5oSOIJup2XcqJaw8RGS6k3TGEc7GI=
 golang.org/x/image v0.23.0 h1:HseQ7c2OpPKTPVzNjG5fwJsOTCiiwS4QdsYi5XU6H68=
 golang.org/x/image v0.23.0/go.mod h1:wJJBTdLfCCf3tiHa1fNxpZmUI4mmoZvwMCPP0ddoNKY=
-golang.org/x/mod v0.29.0 h1:HV8lRxZC4l2cr3Zq1LvtOsi/ThTgWnUk/y64QSs8GwA=
-golang.org/x/mod v0.29.0/go.mod h1:NyhrlYXJ2H4eJiRy/WDBO6HMqZQ6q9nk4JzS3NuCK+w=
 golang.org/x/net v0.0.0-20210226172049-e18ecbb05110/go.mod h1:m0MpNAwzfU5UDzcl9v0D8zg8gWTRqZa9RBIspLL5mdg=
 golang.org/x/net v0.0.0-20210520170846-37e1c6afe023/go.mod h1:9nx3DQGgdP8bBQD5qxJ1jj9UTztislL4KSBs9R2vV5Y=
 golang.org/x/net v0.47.0 h1:Mx+4dIFzqraBXUugkia1OOvlD6LemFo1ALMHjrXDOhY=
@@ -325,8 +314,6 @@ golang.org/x/text v0.3.6/go.mod h1:5Zoc/QRtKVWzQhOtBMvqHzDpF6irO9z98xDceosuGiQ=
 golang.org/x/text v0.31.0 h1:aC8ghyu4JhP8VojJ2lEHBnochRno1sgL6nEi9WGFGMM=
 golang.org/x/text v0.31.0/go.mod h1:tKRAlv61yKIjGGHX/4tP1LTbc13YSec1pxVEWXzfoeM=
 golang.org/x/tools v0.0.0-20180917221912-90fa682c2a6e/go.mod h1:n7NCudcB/nEzxVGmLbDWY5pfWTLqBcC2KZ6jyYvM4mQ=
-golang.org/x/tools v0.38.0 h1:Hx2Xv8hISq8Lm16jvBZ2VQf+RLmbd7wVUsALibYI/IQ=
-golang.org/x/tools v0.38.0/go.mod h1:yEsQ/d/YK8cjh0L6rZlY8tgtlKiBNTL14pGDJPJpYQs=
 golang.org/x/xerrors v0.0.0-20191204190536-9bdfabe68543/go.mod h1:I/5z698sn9Ka8TeJc9MKroUUfqBBauWjQqLJ2OPfmY0=
 google.golang.org/protobuf v1.26.0-rc.1/go.mod h1:jlhhOSvTdKEhbULTjvd4ARK9grFBp09yW+WbY/TyQbw=
 google.golang.org/protobuf v1.28.0/go.mod h1:HV8QOd/L58Z+nl8r43ehVNZIU/HEI6OcFqwMG9pJV4I=
@@ -356,29 +343,11 @@ gorm.io/driver/postgres v1.5.2/go.mod h1:fmpX0m2I1PKuR7mKZiEluwrP3hbs+ps7JIGMUBp
 gorm.io/gorm v1.23.8/go.mod h1:l2lP/RyAtc1ynaTjFksBde/O8v9oOGIApu2/xRitmZk=
 gorm.io/gorm v1.25.2 h1:gs1o6Vsa+oVKG/a9ElL3XgyGfghFfkKA2SInQaCyMho=
 gorm.io/gorm v1.25.2/go.mod h1:L4uxeKpfBml98NYqVqwAdmV1a2nBtAec/cf3fpucW/k=
-modernc.org/cc/v4 v4.26.5 h1:xM3bX7Mve6G8K8b+T11ReenJOT+BmVqQj0FY5T4+5Y4=
-modernc.org/cc/v4 v4.26.5/go.mod h1:uVtb5OGqUKpoLWhqwNQo/8LwvoiEBLvZXIQ/SmO6mL0=
-modernc.org/ccgo/v4 v4.28.1 h1:wPKYn5EC/mYTqBO373jKjvX2n+3+aK7+sICCv4Fjy1A=
-modernc.org/ccgo/v4 v4.28.1/go.mod h1:uD+4RnfrVgE6ec9NGguUNdhqzNIeeomeXf6CL0GTE5Q=
-modernc.org/fileutil v1.3.40 h1:ZGMswMNc9JOCrcrakF1HrvmergNLAmxOPjizirpfqBA=
-modernc.org/fileutil v1.3.40/go.mod h1:HxmghZSZVAz/LXcMNwZPA/DRrQZEVP9VX0V4LQGQFOc=
-modernc.org/gc/v2 v2.6.5 h1:nyqdV8q46KvTpZlsw66kWqwXRHdjIlJOhG6kxiV/9xI=
-modernc.org/gc/v2 v2.6.5/go.mod h1:YgIahr1ypgfe7chRuJi2gD7DBQiKSLMPgBQe9oIiito=
-modernc.org/goabi0 v0.2.0 h1:HvEowk7LxcPd0eq6mVOAEMai46V+i7Jrj13t4AzuNks=
-modernc.org/goabi0 v0.2.0/go.mod h1:CEFRnnJhKvWT1c1JTI3Avm+tgOWbkOu5oPA8eH8LnMI=
-modernc.org/libc v1.66.10 h1:yZkb3YeLx4oynyR+iUsXsybsX4Ubx7MQlSYEw4yj59A=
-modernc.org/libc v1.66.10/go.mod h1:8vGSEwvoUoltr4dlywvHqjtAqHBaw0j1jI7iFBTAr2I=
-modernc.org/mathutil v1.7.1 h1:GCZVGXdaN8gTqB1Mf/usp1Y/hSqgI2vAGGP4jZMCxOU=
-modernc.org/mathutil v1.7.1/go.mod h1:4p5IwJITfppl0G4sUEDtCr4DthTaT47/N3aT6MhfgJg=
-modernc.org/memory v1.11.0 h1:o4QC8aMQzmcwCK3t3Ux/ZHmwFPzE6hf2Y5LbkRs+hbI=
-modernc.org/memory v1.11.0/go.mod h1:/JP4VbVC+K5sU2wZi9bHoq2MAkCnrt2r98UGeSK7Mjw=
-modernc.org/opt v0.1.4 h1:2kNGMRiUjrp4LcaPuLY2PzUfqM/w9N23quVwhKt5Qm8=
-modernc.org/opt v0.1.4/go.mod h1:03fq9lsNfvkYSfxrfUhZCWPk1lm4cq4N+Bh//bEtgns=
-modernc.org/sortutil v1.2.1 h1:+xyoGf15mM3NMlPDnFqrteY07klSFxLElE2PVuWIJ7w=
-modernc.org/sortutil v1.2.1/go.mod h1:7ZI3a3REbai7gzCLcotuw9AC4VZVpYMjDzETGsSMqJE=
-modernc.org/sqlite v1.40.1 h1:VfuXcxcUWWKRBuP8+BR9L7VnmusMgBNNnBYGEe9w/iY=
-modernc.org/sqlite v1.40.1/go.mod h1:9fjQZ0mB1LLP0GYrp39oOJXx/I2sxEnZtzCmEQIKvGE=
-modernc.org/strutil v1.2.1 h1:UneZBkQA+DX2Rp35KcM69cSsNES9ly8mQWD71HKlOA0=
-modernc.org/strutil v1.2.1/go.mod h1:EHkiggD70koQxjVdSBM3JKM7k6L0FbGE5eymy9i3B9A=
-modernc.org/token v1.1.0 h1:Xl7Ap9dKaEs5kLoOQeQmPWevfnk/DM5qcLcYlA8ys6Y=
-modernc.org/token v1.1.0/go.mod h1:UGzOrNV1mAFSEB63lOFHIpNRUVMvYTc6yu1SMY/XTDM=
+modernc.org/libc v1.22.5 h1:91BNch/e5B0uPbJFgqbxXuOnxBQjlS//icfQEGmvyjE=
+modernc.org/libc v1.22.5/go.mod h1:jj+Z7dTNX8fBScMVNRAYZ/jF91K8fdT2hYMThc3YjBY=
+modernc.org/mathutil v1.5.0 h1:rV0Ko/6SfM+8G+yKiyI830l3Wuz1zRutdslNoQ0kfiQ=
+modernc.org/mathutil v1.5.0/go.mod h1:mZW8CKdRPY1v87qxC/wUdX5O1qDzXMP5TH3wjfpga6E=
+modernc.org/memory v1.5.0 h1:N+/8c5rE6EqugZwHii4IFsaJ7MUhoWX07J5tC/iI5Ds=
+modernc.org/memory v1.5.0/go.mod h1:PkUhL0Mugw21sHPeskwZW4D6VscE/GQJOnIpCnW6pSU=
+modernc.org/sqlite v1.23.1 h1:nrSBg4aRQQwq59JpvGEQ15tNxoO5pX/kUjcRNwSAGQM=
+modernc.org/sqlite v1.23.1/go.mod h1:OrDj17Mggn6MhE+iPbBNf7RGKODDE9NFT0f3EwDzJqk=

main.go

@@ -124,11 +124,6 @@ func main() {
 		common.SysLog("pprof enabled")
 	}
 
-	err = common.StartPyroScope()
-	if err != nil {
-		common.SysError(fmt.Sprintf("start pyroscope error : %v", err))
-	}
-
 	// Initialize HTTP server
 	server := gin.New()
 	server.Use(gin.CustomRecovery(func(c *gin.Context, err any) {

middleware/auth.go

@@ -2,14 +2,12 @@ package middleware
 
 import (
 	"fmt"
-	"net"
 	"net/http"
 	"strconv"
 	"strings"
 
 	"github.com/QuantumNous/new-api/common"
 	"github.com/QuantumNous/new-api/constant"
-	"github.com/QuantumNous/new-api/logger"
 	"github.com/QuantumNous/new-api/model"
 	"github.com/QuantumNous/new-api/service"
 	"github.com/QuantumNous/new-api/setting/ratio_setting"
@@ -218,14 +216,10 @@ func TokenAuth() func(c *gin.Context) {
 		}
 		key := c.Request.Header.Get("Authorization")
 		parts := make([]string, 0)
-		if strings.HasPrefix(key, "Bearer ") || strings.HasPrefix(key, "bearer ") {
-			key = strings.TrimSpace(key[7:])
-		}
+		key = strings.TrimPrefix(key, "Bearer ")
 		if key == "" || key == "midjourney-proxy" {
 			key = c.Request.Header.Get("mj-api-secret")
-			if strings.HasPrefix(key, "Bearer ") || strings.HasPrefix(key, "bearer ") {
-				key = strings.TrimSpace(key[7:])
-			}
+			key = strings.TrimPrefix(key, "Bearer ")
 			key = strings.TrimPrefix(key, "sk-")
 			parts = strings.Split(key, "-")
 			key = parts[0]
@@ -246,20 +240,13 @@ func TokenAuth() func(c *gin.Context) {
 			return
 		}
 
-		allowIps := token.GetIpLimits()
-		if len(allowIps) > 0 {
+		allowIpsMap := token.GetIpLimitsMap()
+		if len(allowIpsMap) != 0 {
 			clientIp := c.ClientIP()
-			logger.LogDebug(c, "Token has IP restrictions, checking client IP %s", clientIp)
-			ip := net.ParseIP(clientIp)
-			if ip == nil {
-				abortWithOpenAiMessage(c, http.StatusForbidden, "无法解析客户端 IP 地址")
-				return
-			}
-			if common.IsIpInCIDRList(ip, allowIps) == false {
+			if _, ok := allowIpsMap[clientIp]; !ok {
 				abortWithOpenAiMessage(c, http.StatusForbidden, "您的 IP 不在令牌允许访问的列表中")
 				return
 			}
-			logger.LogDebug(c, "Client IP %s passed the token IP restrictions check", clientIp)
 		}
 
 		userCache, err := model.GetUserCache(token.UserId)
@@ -320,8 +307,7 @@ func SetupContextForToken(c *gin.Context, token *model.Token, parts ...string) e
 	} else {
 		c.Set("token_model_limit_enabled", false)
 	}
-	common.SetContextKey(c, constant.ContextKeyTokenGroup, token.Group)
-	common.SetContextKey(c, constant.ContextKeyTokenCrossGroupRetry, token.CrossGroupRetry)
+	c.Set("token_group", token.Group)
 	if len(parts) > 1 {
 		if model.IsAdmin(token.UserId) {
 			c.Set("specific_channel_id", parts[1])

middleware/distributor.go

@@ -97,12 +97,7 @@ func Distribute() func(c *gin.Context) {
 						common.SetContextKey(c, constant.ContextKeyUsingGroup, usingGroup)
 					}
 				}
-				channel, selectGroup, err = service.CacheGetRandomSatisfiedChannel(&service.RetryParam{
-					Ctx:        c,
-					ModelName:  modelRequest.Model,
-					TokenGroup: usingGroup,
-					Retry:      common.GetPointer(0),
-				})
+				channel, selectGroup, err = service.CacheGetRandomSatisfiedChannel(c, usingGroup, modelRequest.Model, 0)
 				if err != nil {
 					showGroup := usingGroup
 					if usingGroup == "auto" {
@@ -162,7 +157,7 @@ func getModelRequest(c *gin.Context) (*ModelRequest, bool, error) {
 			}
 			midjourneyModel, mjErr, success := service.GetMjRequestModel(relayMode, &midjourneyRequest)
 			if mjErr != nil {
-				return nil, false, fmt.Errorf("%s", mjErr.Description)
+				return nil, false, fmt.Errorf(mjErr.Description)
 			}
 			if midjourneyModel == "" {
 				if !success {
@@ -186,10 +181,6 @@ func getModelRequest(c *gin.Context) (*ModelRequest, bool, error) {
 		}
 		c.Set("platform", string(constant.TaskPlatformSuno))
 		c.Set("relay_mode", relayMode)
-	} else if strings.Contains(c.Request.URL.Path, "/v1/videos/") && strings.HasSuffix(c.Request.URL.Path, "/remix") {
-		relayMode := relayconstant.RelayModeVideoSubmit
-		c.Set("relay_mode", relayMode)
-		shouldSelectChannel = false
 	} else if strings.Contains(c.Request.URL.Path, "/v1/videos") {
 		//curl https://api.openai.com/v1/videos \
 		//  -H "Authorization: Bearer $OPENAI_API_KEY" \

middleware/gzip.go

@@ -5,69 +5,32 @@ import (
 	"io"
 	"net/http"
 
-	"github.com/QuantumNous/new-api/constant"
 	"github.com/andybalholm/brotli"
 	"github.com/gin-gonic/gin"
 )
 
-type readCloser struct {
-	io.Reader
-	closeFn func() error
-}
-
-func (rc *readCloser) Close() error {
-	if rc.closeFn != nil {
-		return rc.closeFn()
-	}
-	return nil
-}
-
 func DecompressRequestMiddleware() gin.HandlerFunc {
 	return func(c *gin.Context) {
 		if c.Request.Body == nil || c.Request.Method == http.MethodGet {
 			c.Next()
 			return
 		}
-		maxMB := constant.MaxRequestBodyMB
-		if maxMB <= 0 {
-			maxMB = 32
-		}
-		maxBytes := int64(maxMB) << 20
-
-		origBody := c.Request.Body
-		wrapMaxBytes := func(body io.ReadCloser) io.ReadCloser {
-			return http.MaxBytesReader(c.Writer, body, maxBytes)
-		}
-
 		switch c.GetHeader("Content-Encoding") {
 		case "gzip":
-			gzipReader, err := gzip.NewReader(origBody)
+			gzipReader, err := gzip.NewReader(c.Request.Body)
 			if err != nil {
-				_ = origBody.Close()
 				c.AbortWithStatus(http.StatusBadRequest)
 				return
 			}
-			// Replace the request body with the decompressed data, and enforce a max size (post-decompression).
-			c.Request.Body = wrapMaxBytes(&readCloser{
-				Reader: gzipReader,
-				closeFn: func() error {
-					_ = gzipReader.Close()
-					return origBody.Close()
-				},
-			})
+			defer gzipReader.Close()
+
+			// Replace the request body with the decompressed data
+			c.Request.Body = io.NopCloser(gzipReader)
 			c.Request.Header.Del("Content-Encoding")
 		case "br":
-			reader := brotli.NewReader(origBody)
-			c.Request.Body = wrapMaxBytes(&readCloser{
-				Reader: reader,
-				closeFn: func() error {
-					return origBody.Close()
-				},
-			})
+			reader := brotli.NewReader(c.Request.Body)
+			c.Request.Body = io.NopCloser(reader)
 			c.Request.Header.Del("Content-Encoding")
-		default:
-			// Even for uncompressed bodies, enforce a max size to avoid huge request allocations.
-			c.Request.Body = wrapMaxBytes(origBody)
 		}
 
 		// Continue processing the request

model/channel.go

@@ -254,9 +254,6 @@ func (channel *Channel) Save() error {
 }
 
 func (channel *Channel) SaveWithoutKey() error {
-	if channel.Id == 0 {
-		return errors.New("channel ID is 0")
-	}
 	return DB.Omit("key").Save(channel).Error
 }
 

model/token.go

@@ -6,6 +6,7 @@ import (
 	"strings"
 
 	"github.com/QuantumNous/new-api/common"
+
 	"github.com/bytedance/gopkg/util/gopool"
 	"gorm.io/gorm"
 )
@@ -26,7 +27,6 @@ type Token struct {
 	AllowIps           *string        `json:"allow_ips" gorm:"default:''"`
 	UsedQuota          int            `json:"used_quota" gorm:"default:0"` // used quota
 	Group              string         `json:"group" gorm:"default:''"`
-	CrossGroupRetry    bool           `json:"cross_group_retry" gorm:"default:false"` // 跨分组重试，仅auto分组有效
 	DeletedAt          gorm.DeletedAt `gorm:"index"`
 }
 
@@ -34,26 +34,26 @@ func (token *Token) Clean() {
 	token.Key = ""
 }
 
-func (token *Token) GetIpLimits() []string {
+func (token *Token) GetIpLimitsMap() map[string]any {
 	// delete empty spaces
 	//split with \n
-	ipLimits := make([]string, 0)
+	ipLimitsMap := make(map[string]any)
 	if token.AllowIps == nil {
-		return ipLimits
+		return ipLimitsMap
 	}
 	cleanIps := strings.ReplaceAll(*token.AllowIps, " ", "")
 	if cleanIps == "" {
-		return ipLimits
+		return ipLimitsMap
 	}
 	ips := strings.Split(cleanIps, "\n")
 	for _, ip := range ips {
 		ip = strings.TrimSpace(ip)
 		ip = strings.ReplaceAll(ip, ",", "")
-		if ip != "" {
-			ipLimits = append(ipLimits, ip)
+		if common.IsIP(ip) {
+			ipLimitsMap[ip] = true
 		}
 	}
-	return ipLimits
+	return ipLimitsMap
 }
 
 func GetAllUserTokens(userId int, startIdx int, num int) ([]*Token, error) {
@@ -112,12 +112,7 @@ func ValidateUserToken(key string) (token *Token, err error) {
 		}
 		return token, nil
 	}
-	common.SysLog("ValidateUserToken: failed to get token: " + err.Error())
-	if errors.Is(err, gorm.ErrRecordNotFound) {
-		return nil, errors.New("无效的令牌")
-	} else {
-		return nil, errors.New("无效的令牌，数据库查询出错，请联系管理员")
-	}
+	return nil, errors.New("无效的令牌")
 }
 
 func GetTokenByIds(id int, userId int) (*Token, error) {
@@ -190,7 +185,7 @@ func (token *Token) Update() (err error) {
 		}
 	}()
 	err = DB.Model(token).Select("name", "status", "expired_time", "remain_quota", "unlimited_quota",
-		"model_limits_enabled", "model_limits", "allow_ips", "group", "cross_group_retry").Updates(token).Error
+		"model_limits_enabled", "model_limits", "allow_ips", "group").Updates(token).Error
 	return err
 }
 

relay/audio_handler.go

@@ -67,11 +67,8 @@ func AudioHelper(c *gin.Context, info *relaycommon.RelayInfo) (newAPIError *type
 		service.ResetStatusCode(newAPIError, statusCodeMappingStr)
 		return newAPIError
 	}
-	if usage.(*dto.Usage).CompletionTokenDetails.AudioTokens > 0 || usage.(*dto.Usage).PromptTokensDetails.AudioTokens > 0 {
-		service.PostAudioConsumeQuota(c, info, usage.(*dto.Usage), "")
-	} else {
-		postConsumeQuota(c, info, usage.(*dto.Usage), "")
-	}
+
+	postConsumeQuota(c, info, usage.(*dto.Usage), "")
 
 	return nil
 }

relay/channel/adapter.go

@@ -47,7 +47,7 @@ type TaskAdaptor interface {
 	GetChannelName() string
 
 	// FetchTask
-	FetchTask(baseUrl, key string, body map[string]any, proxy string) (*http.Response, error)
+	FetchTask(baseUrl, key string, body map[string]any) (*http.Response, error)
 
 	ParseTaskResult(respBody []byte) (*relaycommon.TaskInfo, error)
 }

relay/channel/aws/constants.go

@@ -18,7 +18,6 @@ var awsModelIDMap = map[string]string{
 	"claude-opus-4-1-20250805":   "anthropic.claude-opus-4-1-20250805-v1:0",
 	"claude-sonnet-4-5-20250929": "anthropic.claude-sonnet-4-5-20250929-v1:0",
 	"claude-haiku-4-5-20251001":  "anthropic.claude-haiku-4-5-20251001-v1:0",
-	"claude-opus-4-5-20251101":   "anthropic.claude-opus-4-5-20251101-v1:0",
 	// Nova models
 	"nova-micro-v1:0":   "amazon.nova-micro-v1:0",
 	"nova-lite-v1:0":    "amazon.nova-lite-v1:0",
@@ -77,11 +76,6 @@ var awsModelCanCrossRegionMap = map[string]map[string]bool{
 		"ap": true,
 		"eu": true,
 	},
-	"anthropic.claude-opus-4-5-20251101-v1:0": {
-		"us": true,
-		"ap": true,
-		"eu": true,
-	},
 	"anthropic.claude-haiku-4-5-20251001-v1:0": {
 		"us": true,
 		"ap": true,

relay/channel/aws/relay-aws.go

@@ -18,7 +18,6 @@ import (
 	"github.com/gin-gonic/gin"
 	"github.com/pkg/errors"
 
-	"github.com/QuantumNous/new-api/setting/model_setting"
 	"github.com/aws/aws-sdk-go-v2/aws"
 	"github.com/aws/aws-sdk-go-v2/credentials"
 	"github.com/aws/aws-sdk-go-v2/service/bedrockruntime"
@@ -26,17 +25,6 @@ import (
 	"github.com/aws/smithy-go/auth/bearer"
 )
 
-// getAwsErrorStatusCode extracts HTTP status code from AWS SDK error
-func getAwsErrorStatusCode(err error) int {
-	// Check for HTTP response error which contains status code
-	var httpErr interface{ HTTPStatusCode() int }
-	if errors.As(err, &httpErr) {
-		return httpErr.HTTPStatusCode()
-	}
-	// Default to 500 if we can't determine the status code
-	return http.StatusInternalServerError
-}
-
 func newAwsClient(c *gin.Context, info *relaycommon.RelayInfo) (*bedrockruntime.Client, error) {
 	var (
 		httpClient *http.Client
@@ -130,7 +118,7 @@ func doAwsClientRequest(c *gin.Context, info *relaycommon.RelayInfo, a *Adaptor,
 				Accept:      aws.String("application/json"),
 				ContentType: aws.String("application/json"),
 			}
-			awsReq.Body, err = buildAwsRequestBody(c, info, awsClaudeReq)
+			awsReq.Body, err = common.Marshal(awsClaudeReq)
 			if err != nil {
 				return nil, types.NewError(errors.Wrap(err, "marshal aws request fail"), types.ErrorCodeBadRequestBody)
 			}
@@ -142,7 +130,7 @@ func doAwsClientRequest(c *gin.Context, info *relaycommon.RelayInfo, a *Adaptor,
 				Accept:      aws.String("application/json"),
 				ContentType: aws.String("application/json"),
 			}
-			awsReq.Body, err = buildAwsRequestBody(c, info, awsClaudeReq)
+			awsReq.Body, err = common.Marshal(awsClaudeReq)
 			if err != nil {
 				return nil, types.NewError(errors.Wrap(err, "marshal aws request fail"), types.ErrorCodeBadRequestBody)
 			}
@@ -152,24 +140,6 @@ func doAwsClientRequest(c *gin.Context, info *relaycommon.RelayInfo, a *Adaptor,
 	}
 }
 
-// buildAwsRequestBody prepares the payload for AWS requests, applying passthrough rules when enabled.
-func buildAwsRequestBody(c *gin.Context, info *relaycommon.RelayInfo, awsClaudeReq any) ([]byte, error) {
-	if model_setting.GetGlobalSettings().PassThroughRequestEnabled || info.ChannelSetting.PassThroughBodyEnabled {
-		body, err := common.GetRequestBody(c)
-		if err != nil {
-			return nil, errors.Wrap(err, "get request body for pass-through fail")
-		}
-		var data map[string]interface{}
-		if err := common.Unmarshal(body, &data); err != nil {
-			return nil, errors.Wrap(err, "pass-through unmarshal request body fail")
-		}
-		delete(data, "model")
-		delete(data, "stream")
-		return common.Marshal(data)
-	}
-	return common.Marshal(awsClaudeReq)
-}
-
 func getAwsRegionPrefix(awsRegionId string) string {
 	parts := strings.Split(awsRegionId, "-")
 	regionPrefix := ""
@@ -203,8 +173,7 @@ func awsHandler(c *gin.Context, info *relaycommon.RelayInfo, a *Adaptor) (*types
 
 	awsResp, err := a.AwsClient.InvokeModel(c.Request.Context(), a.AwsReq.(*bedrockruntime.InvokeModelInput))
 	if err != nil {
-		statusCode := getAwsErrorStatusCode(err)
-		return types.NewOpenAIError(errors.Wrap(err, "InvokeModel"), types.ErrorCodeAwsInvokeError, statusCode), nil
+		return types.NewOpenAIError(errors.Wrap(err, "InvokeModel"), types.ErrorCodeAwsInvokeError, http.StatusInternalServerError), nil
 	}
 
 	claudeInfo := &claude.ClaudeResponseInfo{
@@ -230,8 +199,7 @@ func awsHandler(c *gin.Context, info *relaycommon.RelayInfo, a *Adaptor) (*types
 func awsStreamHandler(c *gin.Context, info *relaycommon.RelayInfo, a *Adaptor) (*types.NewAPIError, *dto.Usage) {
 	awsResp, err := a.AwsClient.InvokeModelWithResponseStream(c.Request.Context(), a.AwsReq.(*bedrockruntime.InvokeModelWithResponseStreamInput))
 	if err != nil {
-		statusCode := getAwsErrorStatusCode(err)
-		return types.NewOpenAIError(errors.Wrap(err, "InvokeModelWithResponseStream"), types.ErrorCodeAwsInvokeError, statusCode), nil
+		return types.NewOpenAIError(errors.Wrap(err, "InvokeModelWithResponseStream"), types.ErrorCodeAwsInvokeError, http.StatusInternalServerError), nil
 	}
 	stream := awsResp.GetStream()
 	defer stream.Close()
@@ -270,8 +238,7 @@ func handleNovaRequest(c *gin.Context, info *relaycommon.RelayInfo, a *Adaptor)
 
 	awsResp, err := a.AwsClient.InvokeModel(c.Request.Context(), a.AwsReq.(*bedrockruntime.InvokeModelInput))
 	if err != nil {
-		statusCode := getAwsErrorStatusCode(err)
-		return types.NewOpenAIError(errors.Wrap(err, "InvokeModel"), types.ErrorCodeAwsInvokeError, statusCode), nil
+		return types.NewError(errors.Wrap(err, "InvokeModel"), types.ErrorCodeChannelAwsClientError), nil
 	}
 
 	// 解析Nova响应

relay/channel/baidu/relay-baidu.go

@@ -150,7 +150,7 @@ func baiduHandler(c *gin.Context, info *relaycommon.RelayInfo, resp *http.Respon
 		return types.NewError(err, types.ErrorCodeBadResponseBody), nil
 	}
 	if baiduResponse.ErrorMsg != "" {
-		return types.NewError(fmt.Errorf("%s", baiduResponse.ErrorMsg), types.ErrorCodeBadResponseBody), nil
+		return types.NewError(fmt.Errorf(baiduResponse.ErrorMsg), types.ErrorCodeBadResponseBody), nil
 	}
 	fullTextResponse := responseBaidu2OpenAI(&baiduResponse)
 	jsonResponse, err := json.Marshal(fullTextResponse)
@@ -175,7 +175,7 @@ func baiduEmbeddingHandler(c *gin.Context, info *relaycommon.RelayInfo, resp *ht
 		return types.NewError(err, types.ErrorCodeBadResponseBody), nil
 	}
 	if baiduResponse.ErrorMsg != "" {
-		return types.NewError(fmt.Errorf("%s", baiduResponse.ErrorMsg), types.ErrorCodeBadResponseBody), nil
+		return types.NewError(fmt.Errorf(baiduResponse.ErrorMsg), types.ErrorCodeBadResponseBody), nil
 	}
 	fullTextResponse := embeddingResponseBaidu2OpenAI(&baiduResponse)
 	jsonResponse, err := json.Marshal(fullTextResponse)

relay/channel/claude/constants.go

@@ -9,7 +9,6 @@ var ModelList = []string{
 	"claude-3-opus-20240229",
 	"claude-3-haiku-20240307",
 	"claude-3-5-haiku-20241022",
-	"claude-haiku-4-5-20251001",
 	"claude-3-5-sonnet-20240620",
 	"claude-3-5-sonnet-20241022",
 	"claude-3-7-sonnet-20250219",
@@ -22,8 +21,6 @@ var ModelList = []string{
 	"claude-opus-4-1-20250805-thinking",
 	"claude-sonnet-4-5-20250929",
 	"claude-sonnet-4-5-20250929-thinking",
-	"claude-opus-4-5-20251101",
-	"claude-opus-4-5-20251101-thinking",
 }
 
 var ChannelName = "claude"

relay/channel/claude/relay-claude.go

@@ -483,11 +483,9 @@ func StreamResponseClaude2OpenAI(reqMode int, claudeResponse *dto.ClaudeResponse
 				}
 			}
 		} else if claudeResponse.Type == "message_delta" {
-			if claudeResponse.Delta != nil && claudeResponse.Delta.StopReason != nil {
-				finishReason := stopReasonClaude2OpenAI(*claudeResponse.Delta.StopReason)
-				if finishReason != "null" {
-					choice.FinishReason = &finishReason
-				}
+			finishReason := stopReasonClaude2OpenAI(*claudeResponse.Delta.StopReason)
+			if finishReason != "null" {
+				choice.FinishReason = &finishReason
 			}
 			//claudeUsage = &claudeResponse.Usage
 		} else if claudeResponse.Type == "message_stop" {
@@ -675,7 +673,7 @@ func HandleStreamResponseData(c *gin.Context, info *relaycommon.RelayInfo, claud
 func HandleStreamFinalResponse(c *gin.Context, info *relaycommon.RelayInfo, claudeInfo *ClaudeResponseInfo, requestMode int) {
 
 	if requestMode == RequestModeCompletion {
-		claudeInfo.Usage = service.ResponseText2Usage(c, claudeInfo.ResponseText.String(), info.UpstreamModelName, info.GetEstimatePromptTokens())
+		claudeInfo.Usage = service.ResponseText2Usage(c, claudeInfo.ResponseText.String(), info.UpstreamModelName, info.PromptTokens)
 	} else {
 		if claudeInfo.Usage.PromptTokens == 0 {
 			//上游出错
@@ -736,7 +734,10 @@ func HandleClaudeResponseData(c *gin.Context, info *relaycommon.RelayInfo, claud
 		return types.WithClaudeError(*claudeError, http.StatusInternalServerError)
 	}
 	if requestMode == RequestModeCompletion {
-		claudeInfo.Usage = service.ResponseText2Usage(c, claudeResponse.Completion, info.UpstreamModelName, info.GetEstimatePromptTokens())
+		completionTokens := service.CountTextToken(claudeResponse.Completion, info.OriginModelName)
+		claudeInfo.Usage.PromptTokens = info.PromptTokens
+		claudeInfo.Usage.CompletionTokens = completionTokens
+		claudeInfo.Usage.TotalTokens = info.PromptTokens + completionTokens
 	} else {
 		claudeInfo.Usage.PromptTokens = claudeResponse.Usage.InputTokens
 		claudeInfo.Usage.CompletionTokens = claudeResponse.Usage.OutputTokens

relay/channel/cloudflare/relay_cloudflare.go

@@ -74,7 +74,7 @@ func cfStreamHandler(c *gin.Context, info *relaycommon.RelayInfo, resp *http.Res
 	if err := scanner.Err(); err != nil {
 		logger.LogError(c, "error_scanning_stream_response: "+err.Error())
 	}
-	usage := service.ResponseText2Usage(c, responseText, info.UpstreamModelName, info.GetEstimatePromptTokens())
+	usage := service.ResponseText2Usage(c, responseText, info.UpstreamModelName, info.PromptTokens)
 	if info.ShouldIncludeUsage {
 		response := helper.GenerateFinalUsageResponse(id, info.StartTime.Unix(), info.UpstreamModelName, *usage)
 		err := helper.ObjectData(c, response)
@@ -105,7 +105,7 @@ func cfHandler(c *gin.Context, info *relaycommon.RelayInfo, resp *http.Response)
 	for _, choice := range response.Choices {
 		responseText += choice.Message.StringContent()
 	}
-	usage := service.ResponseText2Usage(c, responseText, info.UpstreamModelName, info.GetEstimatePromptTokens())
+	usage := service.ResponseText2Usage(c, responseText, info.UpstreamModelName, info.PromptTokens)
 	response.Usage = *usage
 	response.Id = helper.GetResponseID(c)
 	jsonResponse, err := json.Marshal(response)
@@ -142,6 +142,10 @@ func cfSTTHandler(c *gin.Context, info *relaycommon.RelayInfo, resp *http.Respon
 	c.Writer.WriteHeader(resp.StatusCode)
 	_, _ = c.Writer.Write(jsonResponse)
 
-	usage := service.ResponseText2Usage(c, cfResp.Result.Text, info.UpstreamModelName, info.GetEstimatePromptTokens())
+	usage := &dto.Usage{}
+	usage.PromptTokens = info.PromptTokens
+	usage.CompletionTokens = service.CountTextToken(cfResp.Result.Text, info.UpstreamModelName)
+	usage.TotalTokens = usage.PromptTokens + usage.CompletionTokens
+
 	return nil, usage
 }

relay/channel/cohere/relay-cohere.go

@@ -165,7 +165,7 @@ func cohereStreamHandler(c *gin.Context, info *relaycommon.RelayInfo, resp *http
 		}
 	})
 	if usage.PromptTokens == 0 {
-		usage = service.ResponseText2Usage(c, responseText, info.UpstreamModelName, info.GetEstimatePromptTokens())
+		usage = service.ResponseText2Usage(c, responseText, info.UpstreamModelName, info.PromptTokens)
 	}
 	return usage, nil
 }
@@ -225,9 +225,9 @@ func cohereRerankHandler(c *gin.Context, resp *http.Response, info *relaycommon.
 	}
 	usage := dto.Usage{}
 	if cohereResp.Meta.BilledUnits.InputTokens == 0 {
-		usage.PromptTokens = info.GetEstimatePromptTokens()
+		usage.PromptTokens = info.PromptTokens
 		usage.CompletionTokens = 0
-		usage.TotalTokens = info.GetEstimatePromptTokens()
+		usage.TotalTokens = info.PromptTokens
 	} else {
 		usage.PromptTokens = cohereResp.Meta.BilledUnits.InputTokens
 		usage.CompletionTokens = cohereResp.Meta.BilledUnits.OutputTokens

relay/channel/coze/relay-coze.go

@@ -208,7 +208,7 @@ func handleCozeEvent(c *gin.Context, event string, data string, responseText *st
 			return
 		}
 
-		common.SysLog(fmt.Sprintf("stream event error: %v %v", errorData.Code, errorData.Message))
+		common.SysLog(fmt.Sprintf("stream event error: ", errorData.Code, errorData.Message))
 	}
 }
 

relay/channel/dify/relay-dify.go

@@ -246,7 +246,7 @@ func difyStreamHandler(c *gin.Context, info *relaycommon.RelayInfo, resp *http.R
 	})
 	helper.Done(c)
 	if usage.TotalTokens == 0 {
-		usage = service.ResponseText2Usage(c, responseText, info.UpstreamModelName, info.GetEstimatePromptTokens())
+		usage = service.ResponseText2Usage(c, responseText, info.UpstreamModelName, info.PromptTokens)
 	}
 	usage.CompletionTokens += nodeToken
 	return usage, nil

relay/channel/gemini/adaptor.go

@@ -13,7 +13,6 @@ import (
 	relaycommon "github.com/QuantumNous/new-api/relay/common"
 	"github.com/QuantumNous/new-api/relay/constant"
 	"github.com/QuantumNous/new-api/setting/model_setting"
-	"github.com/QuantumNous/new-api/setting/reasoning"
 	"github.com/QuantumNous/new-api/types"
 
 	"github.com/gin-gonic/gin"
@@ -138,8 +137,6 @@ func (a *Adaptor) GetRequestURL(info *relaycommon.RelayInfo) (string, error) {
 			info.UpstreamModelName = strings.TrimSuffix(info.UpstreamModelName, "-thinking")
 		} else if strings.HasSuffix(info.UpstreamModelName, "-nothinking") {
 			info.UpstreamModelName = strings.TrimSuffix(info.UpstreamModelName, "-nothinking")
-		} else if baseModel, level, ok := reasoning.TrimEffortSuffix(info.UpstreamModelName); ok && level != "" {
-			info.UpstreamModelName = baseModel
 		}
 	}
 

relay/channel/gemini/relay-gemini-native.go

@@ -5,6 +5,7 @@ import (
 	"net/http"
 
 	"github.com/QuantumNous/new-api/common"
+	"github.com/QuantumNous/new-api/constant"
 	"github.com/QuantumNous/new-api/dto"
 	"github.com/QuantumNous/new-api/logger"
 	relaycommon "github.com/QuantumNous/new-api/relay/common"
@@ -69,7 +70,12 @@ func NativeGeminiEmbeddingHandler(c *gin.Context, resp *http.Response, info *rel
 		println(string(responseBody))
 	}
 
-	usage := service.ResponseText2Usage(c, "", info.UpstreamModelName, info.GetEstimatePromptTokens())
+	usage := &dto.Usage{
+		PromptTokens: info.PromptTokens,
+		TotalTokens:  info.PromptTokens,
+	}
+
+	common.SetContextKey(c, constant.ContextKeyLocalCountTokens, true)
 
 	if info.IsGeminiBatchEmbedding {
 		var geminiResponse dto.GeminiBatchEmbeddingResponse
@@ -94,10 +100,10 @@ func GeminiTextGenerationStreamHandler(c *gin.Context, info *relaycommon.RelayIn
 	helper.SetEventStreamHeaders(c)
 
 	return geminiStreamHandler(c, info, resp, func(data string, geminiResponse *dto.GeminiChatResponse) bool {
+		// 直接发送 GeminiChatResponse 响应
 		err := helper.StringData(c, data)
 		if err != nil {
-			logger.LogError(c, "failed to write stream data: "+err.Error())
-			return false
+			logger.LogError(c, err.Error())
 		}
 		info.SendResponseCount++
 		return true

relay/channel/gemini/relay-gemini.go

@@ -19,8 +19,8 @@ import (
 	"github.com/QuantumNous/new-api/relay/helper"
 	"github.com/QuantumNous/new-api/service"
 	"github.com/QuantumNous/new-api/setting/model_setting"
-	"github.com/QuantumNous/new-api/setting/reasoning"
 	"github.com/QuantumNous/new-api/types"
+
 	"github.com/gin-gonic/gin"
 )
 
@@ -98,7 +98,6 @@ func clampThinkingBudget(modelName string, budget int) int {
 // "effort": "high" - Allocates a large portion of tokens for reasoning (approximately 80% of max_tokens)
 // "effort": "medium" - Allocates a moderate portion of tokens (approximately 50% of max_tokens)
 // "effort": "low" - Allocates a smaller portion of tokens (approximately 20% of max_tokens)
-// "effort": "minimal" - Allocates a minimal portion of tokens (approximately 5% of max_tokens)
 func clampThinkingBudgetByEffort(modelName string, effort string) int {
 	isNew25Pro := isNew25ProModel(modelName)
 	is25FlashLite := is25FlashLiteModel(modelName)
@@ -119,8 +118,6 @@ func clampThinkingBudgetByEffort(modelName string, effort string) int {
 		maxBudget = maxBudget * 50 / 100
 	case "low":
 		maxBudget = maxBudget * 20 / 100
-	case "minimal":
-		maxBudget = maxBudget * 5 / 100
 	}
 	return clampThinkingBudget(modelName, maxBudget)
 }
@@ -181,12 +178,6 @@ func ThinkingAdaptor(geminiRequest *dto.GeminiChatRequest, info *relaycommon.Rel
 					ThinkingBudget: common.GetPointer(0),
 				}
 			}
-		} else if _, level, ok := reasoning.TrimEffortSuffix(info.UpstreamModelName); ok && level != "" {
-			geminiRequest.GenerationConfig.ThinkingConfig = &dto.GeminiThinkingConfig{
-				IncludeThoughts: true,
-				ThinkingLevel:   level,
-			}
-			info.ReasoningEffort = level
 		}
 	}
 }
@@ -217,7 +208,6 @@ func CovertOpenAI2Gemini(c *gin.Context, textRequest dto.GeneralOpenAIRequest, i
 
 	adaptorWithExtraBody := false
 
-	// patch extra_body
 	if len(textRequest.ExtraBody) > 0 {
 		if !strings.HasSuffix(info.UpstreamModelName, "-nothinking") {
 			var extraBody map[string]interface{}
@@ -249,39 +239,6 @@ func CovertOpenAI2Gemini(c *gin.Context, textRequest dto.GeneralOpenAIRequest, i
 						}
 					}
 				}
-
-				// check error param name like imageConfig, should be image_config
-				if _, hasErrorParam := googleBody["imageConfig"]; hasErrorParam {
-					return nil, errors.New("extra_body.google.imageConfig is not supported, use extra_body.google.image_config instead")
-				}
-
-				if imageConfig, ok := googleBody["image_config"].(map[string]interface{}); ok {
-					// check error param name like aspectRatio, should be aspect_ratio
-					if _, hasErrorParam := imageConfig["aspectRatio"]; hasErrorParam {
-						return nil, errors.New("extra_body.google.image_config.aspectRatio is not supported, use extra_body.google.image_config.aspect_ratio instead")
-					}
-					// check error param name like imageSize, should be image_size
-					if _, hasErrorParam := imageConfig["imageSize"]; hasErrorParam {
-						return nil, errors.New("extra_body.google.image_config.imageSize is not supported, use extra_body.google.image_config.image_size instead")
-					}
-
-					// convert snake_case to camelCase for Gemini API
-					geminiImageConfig := make(map[string]interface{})
-					if aspectRatio, ok := imageConfig["aspect_ratio"]; ok {
-						geminiImageConfig["aspectRatio"] = aspectRatio
-					}
-					if imageSize, ok := imageConfig["image_size"]; ok {
-						geminiImageConfig["imageSize"] = imageSize
-					}
-
-					if len(geminiImageConfig) > 0 {
-						imageConfigBytes, err := common.Marshal(geminiImageConfig)
-						if err != nil {
-							return nil, fmt.Errorf("failed to marshal image_config: %w", err)
-						}
-						geminiRequest.GenerationConfig.ImageConfig = imageConfigBytes
-					}
-				}
 			}
 		}
 	}
@@ -455,68 +412,9 @@ func CovertOpenAI2Gemini(c *gin.Context, textRequest dto.GeneralOpenAIRequest, i
 				if part.Text == "" {
 					continue
 				}
-				// check markdown image ![image](data:image/jpeg;base64,xxxxxxxxxxxx)
-				// 使用字符串查找而非正则，避免大文本性能问题
-				text := part.Text
-				hasMarkdownImage := false
-				for {
-					// 快速检查是否包含 markdown 图片标记
-					startIdx := strings.Index(text, "![")
-					if startIdx == -1 {
-						break
-					}
-					// 找到 ](
-					bracketIdx := strings.Index(text[startIdx:], "](data:")
-					if bracketIdx == -1 {
-						break
-					}
-					bracketIdx += startIdx
-					// 找到闭合的 )
-					closeIdx := strings.Index(text[bracketIdx+2:], ")")
-					if closeIdx == -1 {
-						break
-					}
-					closeIdx += bracketIdx + 2
-
-					hasMarkdownImage = true
-					// 添加图片前的文本
-					if startIdx > 0 {
-						textBefore := text[:startIdx]
-						if textBefore != "" {
-							parts = append(parts, dto.GeminiPart{
-								Text: textBefore,
-							})
-						}
-					}
-					// 提取 data URL (从 "](" 后面开始，到 ")" 之前)
-					dataUrl := text[bracketIdx+2 : closeIdx]
-					imageNum += 1
-					if constant.GeminiVisionMaxImageNum != -1 && imageNum > constant.GeminiVisionMaxImageNum {
-						return nil, fmt.Errorf("too many images in the message, max allowed is %d", constant.GeminiVisionMaxImageNum)
-					}
-					format, base64String, err := service.DecodeBase64FileData(dataUrl)
-					if err != nil {
-						return nil, fmt.Errorf("decode markdown base64 image data failed: %s", err.Error())
-					}
-					imgPart := dto.GeminiPart{
-						InlineData: &dto.GeminiInlineData{
-							MimeType: format,
-							Data:     base64String,
-						},
-					}
-					if shouldAttachThoughtSignature {
-						imgPart.ThoughtSignature = json.RawMessage(strconv.Quote(thoughtSignatureBypassValue))
-					}
-					parts = append(parts, imgPart)
-					// 继续处理剩余文本
-					text = text[closeIdx+1:]
-				}
-				// 添加剩余文本或原始文本（如果没有找到 markdown 图片）
-				if !hasMarkdownImage {
-					parts = append(parts, dto.GeminiPart{
-						Text: part.Text,
-					})
-				}
+				parts = append(parts, dto.GeminiPart{
+					Text: part.Text,
+				})
 			} else if part.Type == dto.ContentTypeImageURL {
 				imageNum += 1
 
@@ -586,17 +484,6 @@ func CovertOpenAI2Gemini(c *gin.Context, textRequest dto.GeneralOpenAIRequest, i
 			}
 		}
 
-		// 如果需要附加签名但还没有附加（没有 tool_calls 或 tool_calls 为空），
-		// 则在第一个文本 part 上附加 thoughtSignature
-		if shouldAttachThoughtSignature && !signatureAttached && len(parts) > 0 {
-			for i := range parts {
-				if parts[i].Text != "" {
-					parts[i].ThoughtSignature = json.RawMessage(strconv.Quote(thoughtSignatureBypassValue))
-					break
-				}
-			}
-		}
-
 		content.Parts = parts
 
 		// there's no assistant role in gemini and API shall vomit if Role is not user or model
@@ -1124,7 +1011,7 @@ func geminiStreamHandler(c *gin.Context, info *relaycommon.RelayInfo, resp *http
 	if usage.CompletionTokens <= 0 {
 		str := responseText.String()
 		if len(str) > 0 {
-			usage = service.ResponseText2Usage(c, responseText.String(), info.UpstreamModelName, info.GetEstimatePromptTokens())
+			usage = service.ResponseText2Usage(c, responseText.String(), info.UpstreamModelName, info.PromptTokens)
 		} else {
 			usage = &dto.Usage{}
 		}
@@ -1297,7 +1184,11 @@ func GeminiEmbeddingHandler(c *gin.Context, info *relaycommon.RelayInfo, resp *h
 	// Google has not yet clarified how embedding models will be billed
 	// refer to openai billing method to use input tokens billing
 	// https://platform.openai.com/docs/guides/embeddings#what-are-embeddings
-	usage := service.ResponseText2Usage(c, "", info.UpstreamModelName, info.GetEstimatePromptTokens())
+	usage := &dto.Usage{
+		PromptTokens:     info.PromptTokens,
+		CompletionTokens: 0,
+		TotalTokens:      info.PromptTokens,
+	}
 	openAIResponse.Usage = *usage
 
 	jsonResponse, jsonErr := common.Marshal(openAIResponse)

relay/channel/minimax/tts.go

@@ -163,7 +163,7 @@ func handleTTSResponse(c *gin.Context, resp *http.Response, info *relaycommon.Re
 	}
 
 	usage = &dto.Usage{
-		PromptTokens:     info.GetEstimatePromptTokens(),
+		PromptTokens:     info.PromptTokens,
 		CompletionTokens: 0,
 		TotalTokens:      int(minimaxResp.ExtraInfo.UsageCharacters),
 	}

relay/channel/moonshot/adaptor.go

@@ -6,7 +6,6 @@ import (
 	"io"
 	"net/http"
 
-	channelconstant "github.com/QuantumNous/new-api/constant"
 	"github.com/QuantumNous/new-api/dto"
 	"github.com/QuantumNous/new-api/relay/channel"
 	"github.com/QuantumNous/new-api/relay/channel/claude"
@@ -45,16 +44,6 @@ func (a *Adaptor) Init(info *relaycommon.RelayInfo) {
 }
 
 func (a *Adaptor) GetRequestURL(info *relaycommon.RelayInfo) (string, error) {
-	baseURL := info.ChannelBaseUrl
-	if specialPlan, ok := channelconstant.ChannelSpecialBases[baseURL]; ok {
-		if info.RelayFormat == types.RelayFormatClaude {
-			return fmt.Sprintf("%s/v1/messages", specialPlan.ClaudeBaseURL), nil
-		}
-		if info.RelayFormat == types.RelayFormatOpenAI {
-			return fmt.Sprintf("%s/chat/completions", specialPlan.OpenAIBaseURL), nil
-		}
-	}
-
 	switch info.RelayFormat {
 	case types.RelayFormatClaude:
 		return fmt.Sprintf("%s/anthropic/v1/messages", info.ChannelBaseUrl), nil

relay/channel/openai/adaptor.go

@@ -42,7 +42,7 @@ type Adaptor struct {
 // support OAI models: o1-mini/o3-mini/o4-mini/o1/o3 etc...
 // minimal effort only available in gpt-5
 func parseReasoningEffortFromModelSuffix(model string) (string, string) {
-	effortSuffixes := []string{"-high", "-minimal", "-low", "-medium", "-none", "-xhigh"}
+	effortSuffixes := []string{"-high", "-minimal", "-low", "-medium", "-none"}
 	for _, suffix := range effortSuffixes {
 		if strings.HasSuffix(model, suffix) {
 			effort := strings.TrimPrefix(suffix, "-")
@@ -306,11 +306,10 @@ func (a *Adaptor) ConvertOpenAIRequest(c *gin.Context, info *relaycommon.RelayIn
 			request.Temperature = nil
 		}
 
-		// gpt-5系列模型适配 归零不再支持的参数
 		if strings.HasPrefix(info.UpstreamModelName, "gpt-5") {
-			request.Temperature = nil
-			request.TopP = 0 // oai 的 top_p 默认值是 1.0，但是为了 omitempty 属性直接不传，这里显式设置为 0
-			request.LogProbs = false
+			if info.UpstreamModelName != "gpt-5-chat-latest" {
+				request.Temperature = nil
+			}
 		}
 
 		// 转换模型推理力度后缀

relay/channel/openai/audio.go

@@ -1,145 +0,0 @@
-package openai
-
-import (
-	"bytes"
-	"fmt"
-	"io"
-	"math"
-	"net/http"
-
-	"github.com/QuantumNous/new-api/common"
-	"github.com/QuantumNous/new-api/constant"
-	"github.com/QuantumNous/new-api/dto"
-	"github.com/QuantumNous/new-api/logger"
-	relaycommon "github.com/QuantumNous/new-api/relay/common"
-	"github.com/QuantumNous/new-api/relay/helper"
-	"github.com/QuantumNous/new-api/service"
-	"github.com/QuantumNous/new-api/types"
-	"github.com/gin-gonic/gin"
-)
-
-func OpenaiTTSHandler(c *gin.Context, resp *http.Response, info *relaycommon.RelayInfo) *dto.Usage {
-	// the status code has been judged before, if there is a body reading failure,
-	// it should be regarded as a non-recoverable error, so it should not return err for external retry.
-	// Analogous to nginx's load balancing, it will only retry if it can't be requested or
-	// if the upstream returns a specific status code, once the upstream has already written the header,
-	// the subsequent failure of the response body should be regarded as a non-recoverable error,
-	// and can be terminated directly.
-	defer service.CloseResponseBodyGracefully(resp)
-	usage := &dto.Usage{}
-	usage.PromptTokens = info.GetEstimatePromptTokens()
-	usage.TotalTokens = info.GetEstimatePromptTokens()
-	for k, v := range resp.Header {
-		c.Writer.Header().Set(k, v[0])
-	}
-	c.Writer.WriteHeader(resp.StatusCode)
-
-	if info.IsStream {
-		helper.StreamScannerHandler(c, resp, info, func(data string) bool {
-			if service.SundaySearch(data, "usage") {
-				var simpleResponse dto.SimpleResponse
-				err := common.Unmarshal([]byte(data), &simpleResponse)
-				if err != nil {
-					logger.LogError(c, err.Error())
-				}
-				if simpleResponse.Usage.TotalTokens != 0 {
-					usage.PromptTokens = simpleResponse.Usage.InputTokens
-					usage.CompletionTokens = simpleResponse.OutputTokens
-					usage.TotalTokens = simpleResponse.TotalTokens
-				}
-			}
-			_ = helper.StringData(c, data)
-			return true
-		})
-	} else {
-		common.SetContextKey(c, constant.ContextKeyLocalCountTokens, true)
-		// 读取响应体到缓冲区
-		bodyBytes, err := io.ReadAll(resp.Body)
-		if err != nil {
-			logger.LogError(c, fmt.Sprintf("failed to read TTS response body: %v", err))
-			c.Writer.WriteHeaderNow()
-			return usage
-		}
-
-		// 写入响应到客户端
-		c.Writer.WriteHeaderNow()
-		_, err = c.Writer.Write(bodyBytes)
-		if err != nil {
-			logger.LogError(c, fmt.Sprintf("failed to write TTS response: %v", err))
-		}
-
-		// 计算音频时长并更新 usage
-		audioFormat := "mp3" // 默认格式
-		if audioReq, ok := info.Request.(*dto.AudioRequest); ok && audioReq.ResponseFormat != "" {
-			audioFormat = audioReq.ResponseFormat
-		}
-
-		var duration float64
-		var durationErr error
-
-		if audioFormat == "pcm" {
-			// PCM 格式没有文件头，根据 OpenAI TTS 的 PCM 参数计算时长
-			// 采样率: 24000 Hz, 位深度: 16-bit (2 bytes), 声道数: 1
-			const sampleRate = 24000
-			const bytesPerSample = 2
-			const channels = 1
-			duration = float64(len(bodyBytes)) / float64(sampleRate*bytesPerSample*channels)
-		} else {
-			ext := "." + audioFormat
-			reader := bytes.NewReader(bodyBytes)
-			duration, durationErr = common.GetAudioDuration(c.Request.Context(), reader, ext)
-		}
-
-		usage.PromptTokensDetails.TextTokens = usage.PromptTokens
-
-		if durationErr != nil {
-			logger.LogWarn(c, fmt.Sprintf("failed to get audio duration: %v", durationErr))
-			// 如果无法获取时长，则设置保底的 CompletionTokens，根据body大小计算
-			sizeInKB := float64(len(bodyBytes)) / 1000.0
-			estimatedTokens := int(math.Ceil(sizeInKB)) // 粗略估算每KB约等于1 token
-			usage.CompletionTokens = estimatedTokens
-			usage.CompletionTokenDetails.AudioTokens = estimatedTokens
-		} else if duration > 0 {
-			// 计算 token: ceil(duration) / 60.0 * 1000，即每分钟 1000 tokens
-			completionTokens := int(math.Round(math.Ceil(duration) / 60.0 * 1000))
-			usage.CompletionTokens = completionTokens
-			usage.CompletionTokenDetails.AudioTokens = completionTokens
-		}
-		usage.TotalTokens = usage.PromptTokens + usage.CompletionTokens
-	}
-
-	return usage
-}
-
-func OpenaiSTTHandler(c *gin.Context, resp *http.Response, info *relaycommon.RelayInfo, responseFormat string) (*types.NewAPIError, *dto.Usage) {
-	defer service.CloseResponseBodyGracefully(resp)
-
-	responseBody, err := io.ReadAll(resp.Body)
-	if err != nil {
-		return types.NewOpenAIError(err, types.ErrorCodeReadResponseBodyFailed, http.StatusInternalServerError), nil
-	}
-	// 写入新的 response body
-	service.IOCopyBytesGracefully(c, resp, responseBody)
-
-	var responseData struct {
-		Usage *dto.Usage `json:"usage"`
-	}
-	if err := common.Unmarshal(responseBody, &responseData); err == nil && responseData.Usage != nil {
-		if responseData.Usage.TotalTokens > 0 {
-			usage := responseData.Usage
-			if usage.PromptTokens == 0 {
-				usage.PromptTokens = usage.InputTokens
-			}
-			if usage.CompletionTokens == 0 {
-				usage.CompletionTokens = usage.OutputTokens
-			}
-			return nil, usage
-		}
-	}
-
-	usage := &dto.Usage{}
-	usage.PromptTokens = info.GetEstimatePromptTokens()
-	usage.CompletionTokens = 0
-	usage.TotalTokens = usage.PromptTokens + usage.CompletionTokens
-	return nil, usage
-}

relay/channel/openai/helper.go

@@ -5,6 +5,7 @@ import (
 	"strings"
 
 	"github.com/QuantumNous/new-api/common"
+	"github.com/QuantumNous/new-api/constant"
 	"github.com/QuantumNous/new-api/dto"
 	"github.com/QuantumNous/new-api/logger"
 	relaycommon "github.com/QuantumNous/new-api/relay/common"
@@ -18,10 +19,26 @@ import (
 	"github.com/gin-gonic/gin"
 )
 
-// 辅助函数
+// HandleStreamFormat processes a streaming response payload according to the provided RelayInfo and forwards it to the appropriate format-specific handler.
+//
+// It increments info.SendResponseCount, optionally converts OpenRouter "reasoning" fields to "reasoning_content" when the channel is OpenRouter and OpenRouterConvertToOpenAI is enabled, and then dispatches the (possibly modified) JSON string to the handler for the configured RelayFormat (OpenAI, Claude, or Gemini). It returns any error produced by the selected handler or nil if no handler is invoked.
 func HandleStreamFormat(c *gin.Context, info *relaycommon.RelayInfo, data string, forceFormat bool, thinkToContent bool) error {
 	info.SendResponseCount++
 
+	// OpenRouter reasoning 字段转换：reasoning -> reasoning_content
+	// 仅当启用转换为OpenAI兼容格式时执行
+	if info.ChannelType == constant.ChannelTypeOpenRouter && info.ChannelOtherSettings.OpenRouterConvertToOpenAI {
+		var streamResponse dto.ChatCompletionsStreamResponse
+		if err := common.Unmarshal(common.StringToByteSlice(data), &streamResponse); err == nil {
+			convertOpenRouterReasoningFieldsStream(&streamResponse)
+			// 重新序列化为JSON
+			newData, err := common.Marshal(streamResponse)
+			if err == nil {
+				data = string(newData)
+			}
+		}
+	}
+
 	switch info.RelayFormat {
 	case types.RelayFormatOpenAI:
 		return sendStreamData(c, info, data, forceFormat, thinkToContent)
@@ -172,7 +189,7 @@ func handleLastResponse(lastStreamData string, responseId *string, createAt *int
 	shouldSendLastResp *bool) error {
 
 	var lastStreamResponse dto.ChatCompletionsStreamResponse
-	if err := common.Unmarshal(common.StringToByteSlice(lastStreamData), &lastStreamResponse); err != nil {
+	if err := json.Unmarshal(common.StringToByteSlice(lastStreamData), &lastStreamResponse); err != nil {
 		return err
 	}
 
@@ -253,9 +270,26 @@ func HandleFinalResponse(c *gin.Context, info *relaycommon.RelayInfo, lastStream
 	}
 }
 
+// sendResponsesStreamData sends a non-empty data chunk for the given stream response to the client.
+// If data is empty, it returns without sending anything.
 func sendResponsesStreamData(c *gin.Context, streamResponse dto.ResponsesStreamResponse, data string) {
 	if data == "" {
 		return
 	}
 	helper.ResponseChunkData(c, streamResponse, data)
 }
+
+// convertOpenRouterReasoningFieldsStream converts each choice's `Delta` in a streaming ChatCompletions response
+// by normalizing any `reasoning` fields into `reasoning_content`.
+// It applies ConvertReasoningField to every choice's Delta and is a no-op if `response` is nil or has no choices.
+func convertOpenRouterReasoningFieldsStream(response *dto.ChatCompletionsStreamResponse) {
+	if response == nil || len(response.Choices) == 0 {
+		return
+	}
+
+	// 遍历所有choices，对每个Delta使用统一的泛型函数进行转换
+	for i := range response.Choices {
+		choice := &response.Choices[i]
+		ConvertReasoningField(&choice.Delta)
+	}
+}

relay/channel/openai/reasoning_converter.go

@@ -0,0 +1,35 @@
+package openai
+
+// ReasoningHolder 定义一个通用的接口，用于操作包含reasoning字段的结构体
+type ReasoningHolder interface {
+	// 获取reasoning字段的值
+	GetReasoning() string
+	// 设置reasoning字段的值
+	SetReasoning(reasoning string)
+	// 获取reasoning_content字段的值
+	GetReasoningContent() string
+	// 设置reasoning_content字段的值
+	SetReasoningContent(reasoningContent string)
+}
+
+// ConvertReasoningField 通用的reasoning字段转换函数
+// 将reasoning字段的内容移动到reasoning_content字段
+// ConvertReasoningField moves the holder's reasoning into its reasoning content and clears the original reasoning field.
+// If GetReasoning returns an empty string, the holder is unchanged. When clearing, types that implement SetReasoningToNil()
+// will have that method invoked; otherwise SetReasoning("") is used.
+func ConvertReasoningField[T ReasoningHolder](holder T) {
+	reasoning := holder.GetReasoning()
+	if reasoning != "" {
+		holder.SetReasoningContent(reasoning)
+	}
+	
+	// 使用类型断言来智能清理reasoning字段
+	switch h := any(holder).(type) {
+	case interface{ SetReasoningToNil() }:
+		// 流式响应：指针类型，设为nil
+		h.SetReasoningToNil()
+	default:
+		// 非流式响应：值类型，设为空字符串
+		holder.SetReasoning("")
+	}
+}

relay/channel/openai/relay-openai.go

@@ -1,6 +1,7 @@
 package openai
 
 import (
+	"encoding/json"
 	"fmt"
 	"io"
 	"net/http"
@@ -150,7 +151,7 @@ func OaiStreamHandler(c *gin.Context, info *relaycommon.RelayInfo, resp *http.Re
 		var streamResp struct {
 			Usage *dto.Usage `json:"usage"`
 		}
-		err := common.Unmarshal([]byte(secondLastStreamData), &streamResp)
+		err := json.Unmarshal([]byte(secondLastStreamData), &streamResp)
 		if err == nil && streamResp.Usage != nil && service.ValidUsage(streamResp.Usage) {
 			usage = streamResp.Usage
 			containStreamUsage = true
@@ -182,7 +183,7 @@ func OaiStreamHandler(c *gin.Context, info *relaycommon.RelayInfo, resp *http.Re
 	}
 
 	if !containStreamUsage {
-		usage = service.ResponseText2Usage(c, responseTextBuilder.String(), info.UpstreamModelName, info.GetEstimatePromptTokens())
+		usage = service.ResponseText2Usage(c, responseTextBuilder.String(), info.UpstreamModelName, info.PromptTokens)
 		usage.CompletionTokens += toolCount * 7
 	}
 
@@ -193,6 +194,25 @@ func OaiStreamHandler(c *gin.Context, info *relaycommon.RelayInfo, resp *http.Re
 	return usage, nil
 }
 
+// OpenaiHandler processes an upstream OpenAI-like HTTP response, normalizes or infers token usage,
+// optionally converts OpenRouter reasoning fields to OpenAI-compatible `reasoning_content`, adapts
+// the response to the configured relay format (OpenAI, Claude, or Gemini), writes the final body
+// to the client, and returns the computed usage.
+//
+// It will:
+// - Handle OpenRouter enterprise wrapper responses when the channel is OpenRouter Enterprise.
+// - Unmarshal the upstream body into an internal simple response and, when configured,
+//   convert OpenRouter `reasoning` fields into `reasoning_content`.
+// - If usage prompt tokens are missing, infer completion tokens by counting tokens in choices
+//   (falling back to per-choice text token counting) and set Prompt/Completion/Total tokens.
+// - Apply channel-specific post-processing to usage (cached token adjustments).
+// - Depending on RelayFormat and channel settings, inject updated usage into the body,
+//   reserialize the converted simple response when ForceFormat is enabled or when OpenRouter
+//   conversion was applied, or convert the response to Claude/Gemini formats.
+// - Write the final response body to the client via a graceful copy helper.
+//
+// Returns the final usage (possibly inferred or modified) or a NewAPIError describing any failure
+// encountered while reading, parsing, or transforming the upstream response.
 func OpenaiHandler(c *gin.Context, info *relaycommon.RelayInfo, resp *http.Response) (*dto.Usage, *types.NewAPIError) {
 	defer service.CloseResponseBodyGracefully(resp)
 
@@ -225,6 +245,12 @@ func OpenaiHandler(c *gin.Context, info *relaycommon.RelayInfo, resp *http.Respo
 		return nil, types.NewOpenAIError(err, types.ErrorCodeBadResponseBody, http.StatusInternalServerError)
 	}
 
+	// OpenRouter reasoning 字段转换：reasoning -> reasoning_content
+	// 仅当启用转换为OpenAI兼容格式时执行（修改现有无条件转换）
+	if info.ChannelType == constant.ChannelTypeOpenRouter && info.ChannelOtherSettings.OpenRouterConvertToOpenAI {
+		convertOpenRouterReasoningFields(&simpleResponse)
+	}
+
 	if oaiError := simpleResponse.GetOpenAIError(); oaiError != nil && oaiError.Type != "" {
 		return nil, types.WithOpenAIError(*oaiError, resp.StatusCode)
 	}
@@ -244,9 +270,9 @@ func OpenaiHandler(c *gin.Context, info *relaycommon.RelayInfo, resp *http.Respo
 			}
 		}
 		simpleResponse.Usage = dto.Usage{
-			PromptTokens:     info.GetEstimatePromptTokens(),
+			PromptTokens:     info.PromptTokens,
 			CompletionTokens: completionTokens,
-			TotalTokens:      info.GetEstimatePromptTokens() + completionTokens,
+			TotalTokens:      info.PromptTokens + completionTokens,
 		}
 		usageModified = true
 	}
@@ -270,6 +296,13 @@ func OpenaiHandler(c *gin.Context, info *relaycommon.RelayInfo, resp *http.Respo
 				return nil, types.NewError(err, types.ErrorCodeBadResponseBody)
 			}
 		} else {
+			// 对于 OpenRouter，仅在执行转换后重新序列化
+			if info.ChannelType == constant.ChannelTypeOpenRouter && info.ChannelOtherSettings.OpenRouterConvertToOpenAI {
+				responseBody, err = common.Marshal(simpleResponse)
+				if err != nil {
+					return nil, types.NewError(err, types.ErrorCodeBadResponseBody)
+				}
+			}
 			break
 		}
 	case types.RelayFormatClaude:
@@ -326,6 +359,68 @@ func streamTTSResponse(c *gin.Context, resp *http.Response) {
 	}
 }
 
+func OpenaiTTSHandler(c *gin.Context, resp *http.Response, info *relaycommon.RelayInfo) *dto.Usage {
+	// the status code has been judged before, if there is a body reading failure,
+	// it should be regarded as a non-recoverable error, so it should not return err for external retry.
+	// Analogous to nginx's load balancing, it will only retry if it can't be requested or
+	// if the upstream returns a specific status code, once the upstream has already written the header,
+	// the subsequent failure of the response body should be regarded as a non-recoverable error,
+	// and can be terminated directly.
+	defer service.CloseResponseBodyGracefully(resp)
+	usage := &dto.Usage{}
+	usage.PromptTokens = info.PromptTokens
+	usage.TotalTokens = info.PromptTokens
+	for k, v := range resp.Header {
+		c.Writer.Header().Set(k, v[0])
+	}
+	c.Writer.WriteHeader(resp.StatusCode)
+
+	isStreaming := resp.ContentLength == -1 || resp.Header.Get("Content-Length") == ""
+	if isStreaming {
+		streamTTSResponse(c, resp)
+	} else {
+		c.Writer.WriteHeaderNow()
+		_, err := io.Copy(c.Writer, resp.Body)
+		if err != nil {
+			logger.LogError(c, err.Error())
+		}
+	}
+	return usage
+}
+
+func OpenaiSTTHandler(c *gin.Context, resp *http.Response, info *relaycommon.RelayInfo, responseFormat string) (*types.NewAPIError, *dto.Usage) {
+	defer service.CloseResponseBodyGracefully(resp)
+
+	responseBody, err := io.ReadAll(resp.Body)
+	if err != nil {
+		return types.NewOpenAIError(err, types.ErrorCodeReadResponseBodyFailed, http.StatusInternalServerError), nil
+	}
+	// 写入新的 response body
+	service.IOCopyBytesGracefully(c, resp, responseBody)
+
+	var responseData struct {
+		Usage *dto.Usage `json:"usage"`
+	}
+	if err := json.Unmarshal(responseBody, &responseData); err == nil && responseData.Usage != nil {
+		if responseData.Usage.TotalTokens > 0 {
+			usage := responseData.Usage
+			if usage.PromptTokens == 0 {
+				usage.PromptTokens = usage.InputTokens
+			}
+			if usage.CompletionTokens == 0 {
+				usage.CompletionTokens = usage.OutputTokens
+			}
+			return nil, usage
+		}
+	}
+
+	usage := &dto.Usage{}
+	usage.PromptTokens = info.PromptTokens
+	usage.CompletionTokens = 0
+	usage.TotalTokens = usage.PromptTokens + usage.CompletionTokens
+	return nil, usage
+}
+
 func OpenaiRealtimeHandler(c *gin.Context, info *relaycommon.RelayInfo) (*types.NewAPIError, *dto.RealtimeUsage) {
 	if info == nil || info.ClientWs == nil || info.TargetWs == nil {
 		return types.NewError(fmt.Errorf("invalid websocket connection"), types.ErrorCodeBadResponse), nil
@@ -596,7 +691,7 @@ func applyUsagePostProcessing(info *relaycommon.RelayInfo, usage *dto.Usage, res
 		if usage.PromptTokensDetails.CachedTokens == 0 && usage.PromptCacheHitTokens != 0 {
 			usage.PromptTokensDetails.CachedTokens = usage.PromptCacheHitTokens
 		}
-	case constant.ChannelTypeZhipu_v4, constant.ChannelTypeMoonshot:
+	case constant.ChannelTypeZhipu_v4:
 		if usage.PromptTokensDetails.CachedTokens == 0 {
 			if usage.InputTokensDetails != nil && usage.InputTokensDetails.CachedTokens > 0 {
 				usage.PromptTokensDetails.CachedTokens = usage.InputTokensDetails.CachedTokens
@@ -609,6 +704,10 @@ func applyUsagePostProcessing(info *relaycommon.RelayInfo, usage *dto.Usage, res
 	}
 }
 
+// extractCachedTokensFromBody extracts a cached token count from a JSON response body.
+// It looks for cached token values in the following fields (in order): `usage.prompt_tokens_details.cached_tokens`,
+// `usage.cached_tokens`, and `usage.prompt_cache_hit_tokens`. It returns the first found value and `true`;
+// if none are present or the body cannot be parsed, it returns 0 and `false`.
 func extractCachedTokensFromBody(body []byte) (int, bool) {
 	if len(body) == 0 {
 		return 0, false
@@ -624,7 +723,7 @@ func extractCachedTokensFromBody(body []byte) (int, bool) {
 		} `json:"usage"`
 	}
 
-	if err := common.Unmarshal(body, &payload); err != nil {
+	if err := json.Unmarshal(body, &payload); err != nil {
 		return 0, false
 	}
 
@@ -639,3 +738,18 @@ func extractCachedTokensFromBody(body []byte) (int, bool) {
 	}
 	return 0, false
 }
+
+// convertOpenRouterReasoningFields 转换OpenRouter响应中的reasoning字段为reasoning_content
+// convertOpenRouterReasoningFields converts OpenRouter-style `reasoning` fields into `reasoning_content` for every choice's message in the provided OpenAITextResponse.
+// It modifies the response in place and is a no-op if `response` is nil or contains no choices.
+func convertOpenRouterReasoningFields(response *dto.OpenAITextResponse) {
+	if response == nil || len(response.Choices) == 0 {
+		return
+	}
+
+	// 遍历所有choices，对每个Message使用统一的泛型函数进行转换
+	for i := range response.Choices {
+		choice := &response.Choices[i]
+		ConvertReasoningField(&choice.Message)
+	}
+}

relay/channel/openai/relay_responses.go

@@ -141,7 +141,7 @@ func OaiResponsesStreamHandler(c *gin.Context, info *relaycommon.RelayInfo, resp
 	}
 
 	if usage.PromptTokens == 0 && usage.CompletionTokens != 0 {
-		usage.PromptTokens = info.GetEstimatePromptTokens()
+		usage.PromptTokens = info.PromptTokens
 	}
 
 	usage.TotalTokens = usage.PromptTokens + usage.CompletionTokens

relay/channel/palm/adaptor.go

@@ -81,7 +81,7 @@ func (a *Adaptor) DoResponse(c *gin.Context, resp *http.Response, info *relaycom
 	if info.IsStream {
 		var responseText string
 		err, responseText = palmStreamHandler(c, resp)
-		usage = service.ResponseText2Usage(c, responseText, info.UpstreamModelName, info.GetEstimatePromptTokens())
+		usage = service.ResponseText2Usage(c, responseText, info.UpstreamModelName, info.PromptTokens)
 	} else {
 		usage, err = palmHandler(c, info, resp)
 	}

relay/channel/palm/relay-palm.go

@@ -121,8 +121,13 @@ func palmHandler(c *gin.Context, info *relaycommon.RelayInfo, resp *http.Respons
 		}, resp.StatusCode)
 	}
 	fullTextResponse := responsePaLM2OpenAI(&palmResponse)
-	usage := service.ResponseText2Usage(c, palmResponse.Candidates[0].Content, info.UpstreamModelName, info.GetEstimatePromptTokens())
-	fullTextResponse.Usage = *usage
+	completionTokens := service.CountTextToken(palmResponse.Candidates[0].Content, info.UpstreamModelName)
+	usage := dto.Usage{
+		PromptTokens:     info.PromptTokens,
+		CompletionTokens: completionTokens,
+		TotalTokens:      info.PromptTokens + completionTokens,
+	}
+	fullTextResponse.Usage = usage
 	jsonResponse, err := common.Marshal(fullTextResponse)
 	if err != nil {
 		return nil, types.NewError(err, types.ErrorCodeBadResponseBody)
@@ -130,5 +135,5 @@ func palmHandler(c *gin.Context, info *relaycommon.RelayInfo, resp *http.Respons
 	c.Writer.Header().Set("Content-Type", "application/json")
 	c.Writer.WriteHeader(resp.StatusCode)
 	service.IOCopyBytesGracefully(c, resp, jsonResponse)
-	return usage, nil
+	return &usage, nil
 }

relay/channel/task/ali/adaptor.go

@@ -393,7 +393,7 @@ func (a *TaskAdaptor) DoResponse(c *gin.Context, resp *http.Response, info *rela
 }
 
 // FetchTask 查询任务状态
-func (a *TaskAdaptor) FetchTask(baseUrl, key string, body map[string]any, proxy string) (*http.Response, error) {
+func (a *TaskAdaptor) FetchTask(baseUrl, key string, body map[string]any) (*http.Response, error) {
 	taskID, ok := body["task_id"].(string)
 	if !ok {
 		return nil, fmt.Errorf("invalid task_id")
@@ -408,11 +408,7 @@ func (a *TaskAdaptor) FetchTask(baseUrl, key string, body map[string]any, proxy
 
 	req.Header.Set("Authorization", "Bearer "+key)
 
-	client, err := service.GetHttpClientWithProxy(proxy)
-	if err != nil {
-		return nil, fmt.Errorf("new proxy http client failed: %w", err)
-	}
-	return client.Do(req)
+	return service.GetHttpClient().Do(req)
 }
 
 func (a *TaskAdaptor) GetModelList() []string {

relay/channel/task/doubao/adaptor.go

@@ -146,7 +146,7 @@ func (a *TaskAdaptor) DoResponse(c *gin.Context, resp *http.Response, info *rela
 }
 
 // FetchTask fetch task status
-func (a *TaskAdaptor) FetchTask(baseUrl, key string, body map[string]any, proxy string) (*http.Response, error) {
+func (a *TaskAdaptor) FetchTask(baseUrl, key string, body map[string]any) (*http.Response, error) {
 	taskID, ok := body["task_id"].(string)
 	if !ok {
 		return nil, fmt.Errorf("invalid task_id")
@@ -163,11 +163,7 @@ func (a *TaskAdaptor) FetchTask(baseUrl, key string, body map[string]any, proxy
 	req.Header.Set("Content-Type", "application/json")
 	req.Header.Set("Authorization", "Bearer "+key)
 
-	client, err := service.GetHttpClientWithProxy(proxy)
-	if err != nil {
-		return nil, fmt.Errorf("new proxy http client failed: %w", err)
-	}
-	return client.Do(req)
+	return service.GetHttpClient().Do(req)
 }
 
 func (a *TaskAdaptor) GetModelList() []string {

relay/channel/task/gemini/adaptor.go

@@ -200,7 +200,7 @@ func (a *TaskAdaptor) GetChannelName() string {
 }
 
 // FetchTask fetch task status
-func (a *TaskAdaptor) FetchTask(baseUrl, key string, body map[string]any, proxy string) (*http.Response, error) {
+func (a *TaskAdaptor) FetchTask(baseUrl, key string, body map[string]any) (*http.Response, error) {
 	taskID, ok := body["task_id"].(string)
 	if !ok {
 		return nil, fmt.Errorf("invalid task_id")
@@ -223,11 +223,7 @@ func (a *TaskAdaptor) FetchTask(baseUrl, key string, body map[string]any, proxy
 	req.Header.Set("Accept", "application/json")
 	req.Header.Set("x-goog-api-key", key)
 
-	client, err := service.GetHttpClientWithProxy(proxy)
-	if err != nil {
-		return nil, fmt.Errorf("new proxy http client failed: %w", err)
-	}
-	return client.Do(req)
+	return service.GetHttpClient().Do(req)
 }
 
 func (a *TaskAdaptor) ParseTaskResult(respBody []byte) (*relaycommon.TaskInfo, error) {

relay/channel/task/hailuo/adaptor.go

@@ -110,7 +110,7 @@ func (a *TaskAdaptor) DoResponse(c *gin.Context, resp *http.Response, info *rela
 	return hResp.TaskID, responseBody, nil
 }
 
-func (a *TaskAdaptor) FetchTask(baseUrl, key string, body map[string]any, proxy string) (*http.Response, error) {
+func (a *TaskAdaptor) FetchTask(baseUrl, key string, body map[string]any) (*http.Response, error) {
 	taskID, ok := body["task_id"].(string)
 	if !ok {
 		return nil, fmt.Errorf("invalid task_id")
@@ -126,11 +126,7 @@ func (a *TaskAdaptor) FetchTask(baseUrl, key string, body map[string]any, proxy
 	req.Header.Set("Accept", "application/json")
 	req.Header.Set("Authorization", "Bearer "+key)
 
-	client, err := service.GetHttpClientWithProxy(proxy)
-	if err != nil {
-		return nil, fmt.Errorf("new proxy http client failed: %w", err)
-	}
-	return client.Do(req)
+	return service.GetHttpClient().Do(req)
 }
 
 func (a *TaskAdaptor) GetModelList() []string {

relay/channel/task/jimeng/adaptor.go

@@ -196,7 +196,7 @@ func (a *TaskAdaptor) DoResponse(c *gin.Context, resp *http.Response, info *rela
 	}
 
 	if jResp.Code != 10000 {
-		taskErr = service.TaskErrorWrapper(fmt.Errorf("%s", jResp.Message), fmt.Sprintf("%d", jResp.Code), http.StatusInternalServerError)
+		taskErr = service.TaskErrorWrapper(fmt.Errorf(jResp.Message), fmt.Sprintf("%d", jResp.Code), http.StatusInternalServerError)
 		return
 	}
 
@@ -210,7 +210,7 @@ func (a *TaskAdaptor) DoResponse(c *gin.Context, resp *http.Response, info *rela
 }
 
 // FetchTask fetch task status
-func (a *TaskAdaptor) FetchTask(baseUrl, key string, body map[string]any, proxy string) (*http.Response, error) {
+func (a *TaskAdaptor) FetchTask(baseUrl, key string, body map[string]any) (*http.Response, error) {
 	taskID, ok := body["task_id"].(string)
 	if !ok {
 		return nil, fmt.Errorf("invalid task_id")
@@ -251,11 +251,7 @@ func (a *TaskAdaptor) FetchTask(baseUrl, key string, body map[string]any, proxy
 			return nil, errors.Wrap(err, "sign request failed")
 		}
 	}
-	client, err := service.GetHttpClientWithProxy(proxy)
-	if err != nil {
-		return nil, fmt.Errorf("new proxy http client failed: %w", err)
-	}
-	return client.Do(req)
+	return service.GetHttpClient().Do(req)
 }
 
 func (a *TaskAdaptor) GetModelList() []string {

relay/channel/task/kling/adaptor.go

@@ -186,7 +186,7 @@ func (a *TaskAdaptor) DoResponse(c *gin.Context, resp *http.Response, info *rela
 		return
 	}
 	if kResp.Code != 0 {
-		taskErr = service.TaskErrorWrapperLocal(fmt.Errorf("%s", kResp.Message), "task_failed", http.StatusBadRequest)
+		taskErr = service.TaskErrorWrapperLocal(fmt.Errorf(kResp.Message), "task_failed", http.StatusBadRequest)
 		return
 	}
 	ov := dto.NewOpenAIVideo()
@@ -199,7 +199,7 @@ func (a *TaskAdaptor) DoResponse(c *gin.Context, resp *http.Response, info *rela
 }
 
 // FetchTask fetch task status
-func (a *TaskAdaptor) FetchTask(baseUrl, key string, body map[string]any, proxy string) (*http.Response, error) {
+func (a *TaskAdaptor) FetchTask(baseUrl, key string, body map[string]any) (*http.Response, error) {
 	taskID, ok := body["task_id"].(string)
 	if !ok {
 		return nil, fmt.Errorf("invalid task_id")
@@ -228,11 +228,7 @@ func (a *TaskAdaptor) FetchTask(baseUrl, key string, body map[string]any, proxy
 	req.Header.Set("Authorization", "Bearer "+token)
 	req.Header.Set("User-Agent", "kling-sdk/1.0")
 
-	client, err := service.GetHttpClientWithProxy(proxy)
-	if err != nil {
-		return nil, fmt.Errorf("new proxy http client failed: %w", err)
-	}
-	return client.Do(req)
+	return service.GetHttpClient().Do(req)
 }
 
 func (a *TaskAdaptor) GetModelList() []string {

relay/channel/task/sora/adaptor.go

@@ -5,10 +5,8 @@ import (
 	"fmt"
 	"io"
 	"net/http"
-	"strings"
 
 	"github.com/QuantumNous/new-api/common"
-	"github.com/QuantumNous/new-api/constant"
 	"github.com/QuantumNous/new-api/dto"
 	"github.com/QuantumNous/new-api/model"
 	"github.com/QuantumNous/new-api/relay/channel"
@@ -69,30 +67,11 @@ func (a *TaskAdaptor) Init(info *relaycommon.RelayInfo) {
 	a.apiKey = info.ApiKey
 }
 
-func validateRemixRequest(c *gin.Context) *dto.TaskError {
-	var req struct {
-		Prompt string `json:"prompt"`
-	}
-	if err := common.UnmarshalBodyReusable(c, &req); err != nil {
-		return service.TaskErrorWrapperLocal(err, "invalid_request", http.StatusBadRequest)
-	}
-	if strings.TrimSpace(req.Prompt) == "" {
-		return service.TaskErrorWrapperLocal(fmt.Errorf("field prompt is required"), "invalid_request", http.StatusBadRequest)
-	}
-	return nil
-}
-
 func (a *TaskAdaptor) ValidateRequestAndSetAction(c *gin.Context, info *relaycommon.RelayInfo) (taskErr *dto.TaskError) {
-	if info.Action == constant.TaskActionRemix {
-		return validateRemixRequest(c)
-	}
 	return relaycommon.ValidateMultipartDirect(c, info)
 }
 
 func (a *TaskAdaptor) BuildRequestURL(info *relaycommon.RelayInfo) (string, error) {
-	if info.Action == constant.TaskActionRemix {
-		return fmt.Sprintf("%s/v1/videos/%s/remix", a.baseURL, info.OriginTaskID), nil
-	}
 	return fmt.Sprintf("%s/v1/videos", a.baseURL), nil
 }
 
@@ -146,7 +125,7 @@ func (a *TaskAdaptor) DoResponse(c *gin.Context, resp *http.Response, _ *relayco
 }
 
 // FetchTask fetch task status
-func (a *TaskAdaptor) FetchTask(baseUrl, key string, body map[string]any, proxy string) (*http.Response, error) {
+func (a *TaskAdaptor) FetchTask(baseUrl, key string, body map[string]any) (*http.Response, error) {
 	taskID, ok := body["task_id"].(string)
 	if !ok {
 		return nil, fmt.Errorf("invalid task_id")
@@ -161,11 +140,7 @@ func (a *TaskAdaptor) FetchTask(baseUrl, key string, body map[string]any, proxy
 
 	req.Header.Set("Authorization", "Bearer "+key)
 
-	client, err := service.GetHttpClientWithProxy(proxy)
-	if err != nil {
-		return nil, fmt.Errorf("new proxy http client failed: %w", err)
-	}
-	return client.Do(req)
+	return service.GetHttpClient().Do(req)
 }
 
 func (a *TaskAdaptor) GetModelList() []string {

relay/channel/task/suno/adaptor.go

@@ -105,7 +105,7 @@ func (a *TaskAdaptor) DoResponse(c *gin.Context, resp *http.Response, info *rela
 		return
 	}
 	if !sunoResponse.IsSuccess() {
-		taskErr = service.TaskErrorWrapper(fmt.Errorf("%s", sunoResponse.Message), sunoResponse.Code, http.StatusInternalServerError)
+		taskErr = service.TaskErrorWrapper(fmt.Errorf(sunoResponse.Message), sunoResponse.Code, http.StatusInternalServerError)
 		return
 	}
 
@@ -132,7 +132,7 @@ func (a *TaskAdaptor) GetChannelName() string {
 	return ChannelName
 }
 
-func (a *TaskAdaptor) FetchTask(baseUrl, key string, body map[string]any, proxy string) (*http.Response, error) {
+func (a *TaskAdaptor) FetchTask(baseUrl, key string, body map[string]any) (*http.Response, error) {
 	requestUrl := fmt.Sprintf("%s/suno/fetch", baseUrl)
 	byteBody, err := json.Marshal(body)
 	if err != nil {
@@ -153,11 +153,11 @@ func (a *TaskAdaptor) FetchTask(baseUrl, key string, body map[string]any, proxy
 	req = req.WithContext(ctx)
 	req.Header.Set("Content-Type", "application/json")
 	req.Header.Set("Authorization", "Bearer "+key)
-	client, err := service.GetHttpClientWithProxy(proxy)
+	resp, err := service.GetHttpClient().Do(req)
 	if err != nil {
-		return nil, fmt.Errorf("new proxy http client failed: %w", err)
+		return nil, err
 	}
-	return client.Do(req)
+	return resp, nil
 }
 
 func actionValidate(c *gin.Context, sunoRequest *dto.SunoSubmitReq, action string) (err error) {

relay/channel/task/vertex/adaptor.go

@@ -12,6 +12,7 @@ import (
 
 	"github.com/QuantumNous/new-api/common"
 	"github.com/QuantumNous/new-api/model"
+
 	"github.com/gin-gonic/gin"
 
 	"github.com/QuantumNous/new-api/constant"
@@ -120,11 +121,7 @@ func (a *TaskAdaptor) BuildRequestHeader(c *gin.Context, req *http.Request, info
 		return fmt.Errorf("failed to decode credentials: %w", err)
 	}
 
-	proxy := ""
-	if info != nil {
-		proxy = info.ChannelSetting.Proxy
-	}
-	token, err := vertexcore.AcquireAccessToken(*adc, proxy)
+	token, err := vertexcore.AcquireAccessToken(*adc, "")
 	if err != nil {
 		return fmt.Errorf("failed to acquire access token: %w", err)
 	}
@@ -150,40 +147,13 @@ func (a *TaskAdaptor) BuildRequestBody(c *gin.Context, info *relaycommon.RelayIn
 			body.Parameters["storageUri"] = v
 		}
 		if v, ok := req.Metadata["sampleCount"]; ok {
-			if i, ok := v.(int); ok {
-				body.Parameters["sampleCount"] = i
-			}
-			if f, ok := v.(float64); ok {
-				body.Parameters["sampleCount"] = int(f)
-			}
+			body.Parameters["sampleCount"] = v
 		}
 	}
 	if _, ok := body.Parameters["sampleCount"]; !ok {
 		body.Parameters["sampleCount"] = 1
 	}
 
-	if body.Parameters["sampleCount"].(int) <= 0 {
-		return nil, fmt.Errorf("sampleCount must be greater than 0")
-	}
-
-	// if req.Duration > 0 {
-	// 	body.Parameters["durationSeconds"] = req.Duration
-	// } else if req.Seconds != "" {
-	// 	seconds, err := strconv.Atoi(req.Seconds)
-	// 	if err != nil {
-	// 		return nil, errors.Wrap(err, "convert seconds to int failed")
-	// 	}
-	// 	body.Parameters["durationSeconds"] = seconds
-	// }
-
-	info.PriceData.OtherRatios = map[string]float64{
-		"sampleCount": float64(body.Parameters["sampleCount"].(int)),
-	}
-
-	// if v, ok := body.Parameters["durationSeconds"]; ok {
-	// 	info.PriceData.OtherRatios["durationSeconds"] = float64(v.(int))
-	// }
-
 	data, err := json.Marshal(body)
 	if err != nil {
 		return nil, err
@@ -220,7 +190,7 @@ func (a *TaskAdaptor) GetModelList() []string { return []string{"veo-3.0-generat
 func (a *TaskAdaptor) GetChannelName() string { return "vertex" }
 
 // FetchTask fetch task status
-func (a *TaskAdaptor) FetchTask(baseUrl, key string, body map[string]any, proxy string) (*http.Response, error) {
+func (a *TaskAdaptor) FetchTask(baseUrl, key string, body map[string]any) (*http.Response, error) {
 	taskID, ok := body["task_id"].(string)
 	if !ok {
 		return nil, fmt.Errorf("invalid task_id")
@@ -253,7 +223,7 @@ func (a *TaskAdaptor) FetchTask(baseUrl, key string, body map[string]any, proxy
 	if err := json.Unmarshal([]byte(key), adc); err != nil {
 		return nil, fmt.Errorf("failed to decode credentials: %w", err)
 	}
-	token, err := vertexcore.AcquireAccessToken(*adc, proxy)
+	token, err := vertexcore.AcquireAccessToken(*adc, "")
 	if err != nil {
 		return nil, fmt.Errorf("failed to acquire access token: %w", err)
 	}
@@ -265,11 +235,7 @@ func (a *TaskAdaptor) FetchTask(baseUrl, key string, body map[string]any, proxy
 	req.Header.Set("Accept", "application/json")
 	req.Header.Set("Authorization", "Bearer "+token)
 	req.Header.Set("x-goog-user-project", adc.ProjectID)
-	client, err := service.GetHttpClientWithProxy(proxy)
-	if err != nil {
-		return nil, fmt.Errorf("new proxy http client failed: %w", err)
-	}
-	return client.Do(req)
+	return service.GetHttpClient().Do(req)
 }
 
 func (a *TaskAdaptor) ParseTaskResult(respBody []byte) (*relaycommon.TaskInfo, error) {

relay/channel/task/vidu/adaptor.go

@@ -188,7 +188,7 @@ func (a *TaskAdaptor) DoResponse(c *gin.Context, resp *http.Response, info *rela
 	return vResp.TaskId, responseBody, nil
 }
 
-func (a *TaskAdaptor) FetchTask(baseUrl, key string, body map[string]any, proxy string) (*http.Response, error) {
+func (a *TaskAdaptor) FetchTask(baseUrl, key string, body map[string]any) (*http.Response, error) {
 	taskID, ok := body["task_id"].(string)
 	if !ok {
 		return nil, fmt.Errorf("invalid task_id")
@@ -204,11 +204,7 @@ func (a *TaskAdaptor) FetchTask(baseUrl, key string, body map[string]any, proxy
 	req.Header.Set("Accept", "application/json")
 	req.Header.Set("Authorization", "Token "+key)
 
-	client, err := service.GetHttpClientWithProxy(proxy)
-	if err != nil {
-		return nil, fmt.Errorf("new proxy http client failed: %w", err)
-	}
-	return client.Do(req)
+	return service.GetHttpClient().Do(req)
 }
 
 func (a *TaskAdaptor) GetModelList() []string {

relay/channel/tencent/relay-tencent.go

@@ -105,7 +105,7 @@ func tencentStreamHandler(c *gin.Context, info *relaycommon.RelayInfo, resp *htt
 		data = strings.TrimPrefix(data, "data:")
 
 		var tencentResponse TencentChatResponse
-		err := common.Unmarshal([]byte(data), &tencentResponse)
+		err := json.Unmarshal([]byte(data), &tencentResponse)
 		if err != nil {
 			common.SysLog("error unmarshalling stream response: " + err.Error())
 			continue
@@ -130,7 +130,7 @@ func tencentStreamHandler(c *gin.Context, info *relaycommon.RelayInfo, resp *htt
 
 	service.CloseResponseBodyGracefully(resp)
 
-	return service.ResponseText2Usage(c, responseText, info.UpstreamModelName, info.GetEstimatePromptTokens()), nil
+	return service.ResponseText2Usage(c, responseText, info.UpstreamModelName, info.PromptTokens), nil
 }
 
 func tencentHandler(c *gin.Context, info *relaycommon.RelayInfo, resp *http.Response) (*dto.Usage, *types.NewAPIError) {

relay/channel/vertex/adaptor.go

@@ -17,7 +17,6 @@ import (
 	relaycommon "github.com/QuantumNous/new-api/relay/common"
 	"github.com/QuantumNous/new-api/relay/constant"
 	"github.com/QuantumNous/new-api/setting/model_setting"
-	"github.com/QuantumNous/new-api/setting/reasoning"
 	"github.com/QuantumNous/new-api/types"
 
 	"github.com/gin-gonic/gin"
@@ -40,7 +39,6 @@ var claudeModelMap = map[string]string{
 	"claude-opus-4-20250514":     "claude-opus-4@20250514",
 	"claude-opus-4-1-20250805":   "claude-opus-4-1@20250805",
 	"claude-sonnet-4-5-20250929": "claude-sonnet-4-5@20250929",
-	"claude-opus-4-5-20251101":   "claude-opus-4-5@20251101",
 }
 
 const anthropicVersion = "vertex-2023-10-16"
@@ -51,43 +49,10 @@ type Adaptor struct {
 }
 
 func (a *Adaptor) ConvertGeminiRequest(c *gin.Context, info *relaycommon.RelayInfo, request *dto.GeminiChatRequest) (any, error) {
-	// Vertex AI does not support functionResponse.id; keep it stripped here for consistency.
-	if model_setting.GetGeminiSettings().RemoveFunctionResponseIdEnabled {
-		removeFunctionResponseID(request)
-	}
 	geminiAdaptor := gemini.Adaptor{}
 	return geminiAdaptor.ConvertGeminiRequest(c, info, request)
 }
 
-func removeFunctionResponseID(request *dto.GeminiChatRequest) {
-	if request == nil {
-		return
-	}
-
-	if len(request.Contents) > 0 {
-		for i := range request.Contents {
-			if len(request.Contents[i].Parts) == 0 {
-				continue
-			}
-			for j := range request.Contents[i].Parts {
-				part := &request.Contents[i].Parts[j]
-				if part.FunctionResponse == nil {
-					continue
-				}
-				if len(part.FunctionResponse.ID) > 0 {
-					part.FunctionResponse.ID = nil
-				}
-			}
-		}
-	}
-
-	if len(request.Requests) > 0 {
-		for i := range request.Requests {
-			removeFunctionResponseID(&request.Requests[i])
-		}
-	}
-}
-
 func (a *Adaptor) ConvertClaudeRequest(c *gin.Context, info *relaycommon.RelayInfo, request *dto.ClaudeRequest) (any, error) {
 	if v, ok := claudeModelMap[info.UpstreamModelName]; ok {
 		c.Set("request_model", v)
@@ -215,8 +180,6 @@ func (a *Adaptor) GetRequestURL(info *relaycommon.RelayInfo) (string, error) {
 				info.UpstreamModelName = strings.TrimSuffix(info.UpstreamModelName, "-thinking")
 			} else if strings.HasSuffix(info.UpstreamModelName, "-nothinking") {
 				info.UpstreamModelName = strings.TrimSuffix(info.UpstreamModelName, "-nothinking")
-			} else if baseModel, level, ok := reasoning.TrimEffortSuffix(info.UpstreamModelName); ok && level != "" {
-				info.UpstreamModelName = baseModel
 			}
 		}
 

relay/channel/volcengine/adaptor.go

@@ -13,7 +13,6 @@ import (
 	channelconstant "github.com/QuantumNous/new-api/constant"
 	"github.com/QuantumNous/new-api/dto"
 	"github.com/QuantumNous/new-api/relay/channel"
-	"github.com/QuantumNous/new-api/relay/channel/claude"
 	"github.com/QuantumNous/new-api/relay/channel/openai"
 	relaycommon "github.com/QuantumNous/new-api/relay/common"
 	"github.com/QuantumNous/new-api/relay/constant"
@@ -24,8 +23,11 @@ import (
 )
 
 const (
-	contextKeyTTSRequest     = "volcengine_tts_request"
-	contextKeyResponseFormat = "response_format"
+	contextKeyTTSRequest          = "volcengine_tts_request"
+	contextKeyResponseFormat      = "response_format"
+	DoubaoCodingPlan              = "doubao-coding-plan"
+	DoubaoCodingPlanClaudeBaseURL = "https://ark.cn-beijing.volces.com/api/coding"
+	DoubaoCodingPlanOpenAIBaseURL = "https://ark.cn-beijing.volces.com/api/coding/v3"
 )
 
 type Adaptor struct {
@@ -37,10 +39,6 @@ func (a *Adaptor) ConvertGeminiRequest(*gin.Context, *relaycommon.RelayInfo, *dt
 }
 
 func (a *Adaptor) ConvertClaudeRequest(c *gin.Context, info *relaycommon.RelayInfo, req *dto.ClaudeRequest) (any, error) {
-	if _, ok := channelconstant.ChannelSpecialBases[info.ChannelBaseUrl]; ok {
-		adaptor := claude.Adaptor{}
-		return adaptor.ConvertClaudeRequest(c, info, req)
-	}
 	adaptor := openai.Adaptor{}
 	return adaptor.ConvertClaudeRequest(c, info, req)
 }
@@ -240,12 +238,11 @@ func (a *Adaptor) GetRequestURL(info *relaycommon.RelayInfo) (string, error) {
 	if baseUrl == "" {
 		baseUrl = channelconstant.ChannelBaseURLs[channelconstant.ChannelTypeVolcEngine]
 	}
-	specialPlan, hasSpecialPlan := channelconstant.ChannelSpecialBases[baseUrl]
 
 	switch info.RelayFormat {
 	case types.RelayFormatClaude:
-		if hasSpecialPlan && specialPlan.ClaudeBaseURL != "" {
-			return fmt.Sprintf("%s/v1/messages", specialPlan.ClaudeBaseURL), nil
+		if baseUrl == DoubaoCodingPlan {
+			return fmt.Sprintf("%s/v1/messages", DoubaoCodingPlanClaudeBaseURL), nil
 		}
 		if strings.HasPrefix(info.UpstreamModelName, "bot") {
 			return fmt.Sprintf("%s/api/v3/bots/chat/completions", baseUrl), nil
@@ -254,8 +251,8 @@ func (a *Adaptor) GetRequestURL(info *relaycommon.RelayInfo) (string, error) {
 	default:
 		switch info.RelayMode {
 		case constant.RelayModeChatCompletions:
-			if hasSpecialPlan && specialPlan.OpenAIBaseURL != "" {
-				return fmt.Sprintf("%s/chat/completions", specialPlan.OpenAIBaseURL), nil
+			if baseUrl == DoubaoCodingPlan {
+				return fmt.Sprintf("%s/chat/completions", DoubaoCodingPlanOpenAIBaseURL), nil
 			}
 			if strings.HasPrefix(info.UpstreamModelName, "bot") {
 				return fmt.Sprintf("%s/api/v3/bots/chat/completions", baseUrl), nil
@@ -343,15 +340,6 @@ func (a *Adaptor) DoRequest(c *gin.Context, info *relaycommon.RelayInfo, request
 }
 
 func (a *Adaptor) DoResponse(c *gin.Context, resp *http.Response, info *relaycommon.RelayInfo) (usage any, err *types.NewAPIError) {
-	if info.RelayFormat == types.RelayFormatClaude {
-		if _, ok := channelconstant.ChannelSpecialBases[info.ChannelBaseUrl]; ok {
-			if info.IsStream {
-				return claude.ClaudeStreamHandler(c, resp, info, claude.RequestModeMessage)
-			}
-			return claude.ClaudeHandler(c, resp, info, claude.RequestModeMessage)
-		}
-	}
-
 	if info.RelayMode == constant.RelayModeAudioSpeech {
 		encoding := mapEncoding(c.GetString(contextKeyResponseFormat))
 		if info.IsStream {

relay/channel/volcengine/protocols.go

@@ -385,7 +385,7 @@ func (m *Message) writeSessionID(buf *bytes.Buffer) error {
 	}
 
 	size := len(m.SessionID)
-	if int64(size) > math.MaxUint32 {
+	if size > math.MaxUint32 {
 		return fmt.Errorf("session ID size (%d) exceeds max(uint32)", size)
 	}
 
@@ -407,7 +407,7 @@ func (m *Message) writeErrorCode(buf *bytes.Buffer) error {
 
 func (m *Message) writePayload(buf *bytes.Buffer) error {
 	size := len(m.Payload)
-	if int64(size) > math.MaxUint32 {
+	if size > math.MaxUint32 {
 		return fmt.Errorf("payload size (%d) exceeds max(uint32)", size)
 	}
 

relay/channel/volcengine/tts.go

@@ -184,9 +184,9 @@ func handleTTSResponse(c *gin.Context, resp *http.Response, info *relaycommon.Re
 	c.Data(http.StatusOK, contentType, audioData)
 
 	usage = &dto.Usage{
-		PromptTokens:     info.GetEstimatePromptTokens(),
+		PromptTokens:     info.PromptTokens,
 		CompletionTokens: 0,
-		TotalTokens:      info.GetEstimatePromptTokens(),
+		TotalTokens:      info.PromptTokens,
 	}
 
 	return usage, nil
@@ -284,9 +284,9 @@ func handleTTSWebSocketResponse(c *gin.Context, requestURL string, volcRequest V
 			if msg.Sequence < 0 {
 				c.Status(http.StatusOK)
 				usage = &dto.Usage{
-					PromptTokens:     info.GetEstimatePromptTokens(),
+					PromptTokens:     info.PromptTokens,
 					CompletionTokens: 0,
-					TotalTokens:      info.GetEstimatePromptTokens(),
+					TotalTokens:      info.PromptTokens,
 				}
 				return usage, nil
 			}
@@ -297,9 +297,9 @@ func handleTTSWebSocketResponse(c *gin.Context, requestURL string, volcRequest V
 
 	c.Status(http.StatusOK)
 	usage = &dto.Usage{
-		PromptTokens:     info.GetEstimatePromptTokens(),
+		PromptTokens:     info.PromptTokens,
 		CompletionTokens: 0,
-		TotalTokens:      info.GetEstimatePromptTokens(),
+		TotalTokens:      info.PromptTokens,
 	}
 	return usage, nil
 }

relay/channel/xai/text.go

@@ -70,7 +70,7 @@ func xAIStreamHandler(c *gin.Context, info *relaycommon.RelayInfo, resp *http.Re
 	})
 
 	if !containStreamUsage {
-		usage = service.ResponseText2Usage(c, responseTextBuilder.String(), info.UpstreamModelName, info.GetEstimatePromptTokens())
+		usage = service.ResponseText2Usage(c, responseTextBuilder.String(), info.UpstreamModelName, info.PromptTokens)
 		usage.CompletionTokens += toolCount * 7
 	}