feat: disk request body cache (#2780)

* feat: 引入通用 HTTP BodyStorage/DiskCache 缓存配置与管理

- 新增 common/body_storage.go 提供 HTTP 请求体存储抽象和文件缓存能力
- 增加 common/disk_cache_config.go 支持全局磁盘缓存配置
- main.go 挂载缓存初始化流程
- 新增和补充 controller/performance.go (及 unix/windows) 用于缓存性能监控接口
- middleware/body_cleanup.go 自动清理缓存文件
- router 挂载相关接口
- 前端 settings 页面新增性能监控设置 PerformanceSetting
- 优化缓存开关状态和模块热插拔能力
- 其他相关文件同步适配缓存扩展

* fix: 修复 BodyStorage 并发安全和错误处理问题

- 修复 diskStorage.Close() 竞态条件，先获取锁再执行 CAS
- 为 memoryStorage 添加互斥锁和 closed 状态检查
- 修复 CreateBodyStorageFromReader 在磁盘存储失败时的回退逻辑
- 添加缓存命中统计调用 (IncrementDiskCacheHits/IncrementMemoryCacheHits)
- 修复 gin.go 中 Seek 错误被忽略的问题
- 在 api-router 添加 BodyStorageCleanup 中间件
- 修复前端 formatBytes 对异常值的处理

Co-authored-by: Cursor <cursoragent@cursor.com>

---------

Co-authored-by: Cursor <cursoragent@cursor.com>

.dockerignore

@@ -6,4 +6,5 @@
 Makefile
 docs
 .eslintcache
-.gocache
+.gocache
+/web/node_modules

.env.example

@@ -9,6 +9,14 @@
 # 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
@@ -49,6 +57,9 @@
 # 流模式无响应超时时间，单位秒，如果出现空补全可以尝试改为更大值
 # STREAMING_TIMEOUT=300
 
+# TLS / HTTP 跳过验证设置
+# TLS_INSECURE_SKIP_VERIFY=false
+
 # Gemini 识别图片 最大图片数量
 # GEMINI_VISION_MAX_IMAGE_NUM=16
 
@@ -63,10 +74,13 @@
 # 是否统计图片token
 # GET_MEDIA_TOKEN=true
 # 是否在非流（stream=false）情况下统计图片token
-# GET_MEDIA_TOKEN_NOT_STREAM=true
+# GET_MEDIA_TOKEN_NOT_STREAM=false
 # 设置 Dify 渠道是否输出工作流和节点信息到客户端
 # DIFY_DEBUG=true
 
+# LinuxDo相关配置
+LINUX_DO_TOKEN_ENDPOINT=https://connect.linux.do/oauth2/token
+LINUX_DO_USER_ENDPOINT=https://connect.linux.do/api/user
 
 # 节点类型
 # 如果是主节点则为master

.github/CODE_OF_CONDUCT.md

@@ -0,0 +1,83 @@
+# Contributor Covenant Code of Conduct
+
+## Our Pledge
+
+We as members, contributors, and leaders pledge to make participation in our community a harassment-free experience for everyone, regardless of age, body size, visible or invisible disability, ethnicity, sex characteristics, gender identity and expression, level of experience, education, socio-economic status, nationality, personal appearance, race, religion, or sexual orientation.
+
+We pledge to act and interact in ways that contribute to an open, welcoming, diverse, inclusive, and healthy community.
+
+## Our Standards
+
+Examples of behavior that contributes to a positive environment for our community include:
+
+- Demonstrating empathy and kindness toward other people
+- Being respectful of differing opinions, viewpoints, and experiences
+- Giving and gracefully accepting constructive feedback
+- Accepting responsibility and apologizing to those affected by our mistakes, and learning from the experience
+- Focusing on what is best not just for us as individuals, but for the overall community
+
+Examples of unacceptable behavior include:
+
+- The use of sexualized language or imagery, and sexual attention or advances of any kind
+- Trolling, insulting or derogatory comments, and personal or political attacks
+- Public or private harassment
+- Publishing others' private information, such as a physical or email address, without their explicit permission
+- Other conduct which could reasonably be considered inappropriate in a professional setting
+
+## Enforcement Responsibilities
+
+Community leaders are responsible for clarifying and enforcing our standards of acceptable behavior and will take appropriate and fair corrective action in response to any behavior that they deem inappropriate, threatening, offensive, or harmful.
+
+Community leaders have the right and responsibility to remove, edit, or reject comments, commits, code, wiki edits, issues, and other contributions that are not aligned to this Code of Conduct, and will communicate reasons for moderation decisions when appropriate.
+
+## Scope
+
+This Code of Conduct applies within all community spaces, and also applies when an individual is officially representing the community in public spaces. Examples of representing our community include using an official e-mail address, posting via an official social media account, or acting as an appointed representative at an online or offline event.
+
+## Enforcement
+
+Instances of abusive, harassing, or otherwise unacceptable behavior may be reported to the community leaders responsible for enforcement at:
+
+**Email:** support@quantumnous.com
+
+All complaints will be reviewed and investigated promptly and fairly.
+
+All community leaders are obligated to respect the privacy and security of the reporter of any incident.
+
+## Enforcement Guidelines
+
+Community leaders will follow these Community Impact Guidelines in determining the consequences for any action they deem in violation of this Code of Conduct:
+
+### 1. Correction
+
+**Community Impact:** Use of inappropriate language or other behavior deemed unprofessional or unwelcome in the community.
+
+**Consequence:** A private, written warning from community leaders, providing clarity around the nature of the violation and an explanation of why the behavior was inappropriate. A public apology may be requested.
+
+### 2. Warning
+
+**Community Impact:** A violation through a single incident or series of actions.
+
+**Consequence:** A warning with consequences for continued behavior. No interaction with the people involved, including unsolicited interaction with those enforcing the Code of Conduct, for a specified period of time. This includes avoiding interactions in community spaces as well as external channels like social media. Violating these terms may lead to a temporary or permanent ban.
+
+### 3. Temporary Ban
+
+**Community Impact:** A serious violation of community standards, including sustained inappropriate behavior.
+
+**Consequence:** A temporary ban from any sort of interaction or public communication with the community for a specified period of time. No public or private interaction with the people involved, including unsolicited interaction with those enforcing the Code of Conduct, is allowed during this period. Violating these terms may lead to a permanent ban.
+
+### 4. Permanent Ban
+
+**Community Impact:** Demonstrating a pattern of violation of community standards, including sustained inappropriate behavior, harassment of an individual, or aggression toward or disparagement of classes of individuals.
+
+**Consequence:** A permanent ban from any sort of public interaction within the community.
+
+## Attribution
+
+This Code of Conduct is adapted from the [Contributor Covenant][homepage], version 2.0, available at https://www.contributor-covenant.org/version/2/0/code_of_conduct.html.
+
+Community Impact Guidelines were inspired by [Mozilla's code of conduct enforcement ladder](https://github.com/mozilla/diversity).
+
+For answers to common questions about this code of conduct, see the FAQ at https://www.contributor-covenant.org/faq. Translations are available at https://www.contributor-covenant.org/translations.
+
+[homepage]: https://www.contributor-covenant.org

.github/SECURITY.md

@@ -0,0 +1,86 @@
+# Security Policy
+
+## Supported Versions
+
+We provide security updates for the following versions:
+
+| Version | Supported          |
+| ------- | ------------------ |
+| Latest  | :white_check_mark: |
+| Older   | :x:                |
+
+We strongly recommend that users always use the latest version for the best security and features.
+
+## Reporting a Vulnerability
+
+We take security vulnerability reports very seriously. If you discover a security issue, please follow the steps below for responsible disclosure.
+
+### How to Report
+
+**Do NOT** report security vulnerabilities in public GitHub Issues.
+
+To report a security issue, please use the GitHub Security Advisories tab to "[Open a draft security advisory](https://github.com/QuantumNous/new-api/security/advisories/new)". This is the preferred method as it provides a built-in private communication channel.
+
+Alternatively, you can report via email:
+
+- **Email:** support@quantumnous.com
+- **Subject:** `[SECURITY] Security Vulnerability Report`
+
+### What to Include
+
+To help us understand and resolve the issue more quickly, please include the following information in your report:
+
+1. **Vulnerability Type** - Brief description of the vulnerability (e.g., SQL injection, XSS, authentication bypass, etc.)
+2. **Affected Component** - Affected file paths, endpoints, or functional modules
+3. **Reproduction Steps** - Detailed steps to reproduce
+4. **Impact Assessment** - Potential security impact and severity assessment
+5. **Proof of Concept** - If possible, provide proof of concept code or screenshots (do not test in production environments)
+6. **Suggested Fix** - If you have a fix suggestion, please provide it
+7. **Your Contact Information** - So we can communicate with you
+
+## Response Process
+
+1. **Acknowledgment:** We will acknowledge receipt of your report within **48 hours**.
+2. **Initial Assessment:** We will complete an initial assessment and communicate with you within **7 days**.
+3. **Fix Development:** Based on the severity of the vulnerability, we will prioritize developing a fix.
+4. **Security Advisory:** After the fix is released, we will publish a security advisory (if applicable).
+5. **Credit:** If you wish, we will credit your contribution in the security advisory.
+
+## Security Best Practices
+
+When deploying and using New API, we recommend following these security best practices:
+
+### Deployment Security
+
+- **Use HTTPS:** Always serve over HTTPS to ensure transport layer security
+- **Firewall Configuration:** Only open necessary ports and restrict access to management interfaces
+- **Regular Updates:** Update to the latest version promptly to receive security patches
+- **Environment Isolation:** Use separate database and Redis instances in production
+
+### API Key Security
+
+- **Key Protection:** Do not expose API keys in client-side code or public repositories
+- **Least Privilege:** Create different API keys for different purposes, following the principle of least privilege
+- **Regular Rotation:** Rotate API keys regularly
+- **Monitor Usage:** Monitor API key usage and detect anomalies promptly
+
+### Database Security
+
+- **Strong Passwords:** Use strong passwords to protect database access
+- **Network Isolation:** Database should not be directly exposed to the public internet
+- **Regular Backups:** Regularly backup the database and verify backup integrity
+- **Access Control:** Limit database user permissions, following the principle of least privilege
+
+## Security-Related Configuration
+
+Please ensure the following security-related environment variables and settings are properly configured:
+
+- `SESSION_SECRET` - Use a strong random string
+- `SQL_DSN` - Ensure database connection uses secure configuration
+- `REDIS_CONN_STRING` - If using Redis, ensure secure connection
+
+For detailed configuration instructions, please refer to the project documentation.
+
+## Disclaimer
+
+This project is provided "as is" without any express or implied warranty. Users should assess the security risks of using this software in their environment.

.github/workflows/release.yml

@@ -22,6 +22,10 @@ jobs:
         uses: actions/checkout@v3
         with:
           fetch-depth: 0
+      - name: Determine Version
+        run: |
+          VERSION=$(git describe --tags)
+          echo "VERSION=$VERSION" >> $GITHUB_ENV
       - uses: oven-sh/setup-bun@v2
         with:
           bun-version: latest
@@ -31,7 +35,7 @@ jobs:
         run: |
           cd web
           bun install
-          DISABLE_ESLINT_PLUGIN='true' VITE_REACT_APP_VERSION=$(git describe --tags) bun run build
+          DISABLE_ESLINT_PLUGIN='true' VITE_REACT_APP_VERSION=$VERSION bun run build
           cd ..
       - name: Set up Go
         uses: actions/setup-go@v3
@@ -40,13 +44,11 @@ jobs:
       - name: Build Backend (amd64)
         run: |
           go mod download
-          VERSION=$(git describe --tags)
           go build -ldflags "-s -w -X 'new-api/common.Version=$VERSION' -extldflags '-static'" -o new-api-$VERSION
       - name: Build Backend (arm64)
         run: |
           sudo apt-get update
           DEBIAN_FRONTEND=noninteractive sudo apt-get install -y gcc-aarch64-linux-gnu
-          VERSION=$(git describe --tags)
           CC=aarch64-linux-gnu-gcc CGO_ENABLED=1 GOOS=linux GOARCH=arm64 go build -ldflags "-s -w -X 'new-api/common.Version=$VERSION' -extldflags '-static'" -o new-api-arm64-$VERSION
       - name: Release
         uses: softprops/action-gh-release@v2
@@ -65,6 +67,10 @@ jobs:
         uses: actions/checkout@v3
         with:
           fetch-depth: 0
+      - name: Determine Version
+        run: |
+          VERSION=$(git describe --tags)
+          echo "VERSION=$VERSION" >> $GITHUB_ENV
       - uses: oven-sh/setup-bun@v2
         with:
           bun-version: latest
@@ -75,7 +81,7 @@ jobs:
         run: |
           cd web
           bun install
-          DISABLE_ESLINT_PLUGIN='true' VITE_REACT_APP_VERSION=$(git describe --tags) bun run build
+          DISABLE_ESLINT_PLUGIN='true' VITE_REACT_APP_VERSION=$VERSION bun run build
           cd ..
       - name: Set up Go
         uses: actions/setup-go@v3
@@ -84,7 +90,6 @@ jobs:
       - name: Build Backend
         run: |
           go mod download
-          VERSION=$(git describe --tags)
           go build -ldflags "-X 'new-api/common.Version=$VERSION'" -o new-api-macos-$VERSION
       - name: Release
         uses: softprops/action-gh-release@v2
@@ -105,6 +110,10 @@ jobs:
         uses: actions/checkout@v3
         with:
           fetch-depth: 0
+      - name: Determine Version
+        run: |
+          VERSION=$(git describe --tags)
+          echo "VERSION=$VERSION" >> $GITHUB_ENV
       - uses: oven-sh/setup-bun@v2
         with:
           bun-version: latest
@@ -114,7 +123,7 @@ jobs:
         run: |
           cd web
           bun install
-          DISABLE_ESLINT_PLUGIN='true' VITE_REACT_APP_VERSION=$(git describe --tags) bun run build
+          DISABLE_ESLINT_PLUGIN='true' VITE_REACT_APP_VERSION=$VERSION bun run build
           cd ..
       - name: Set up Go
         uses: actions/setup-go@v3
@@ -123,7 +132,6 @@ jobs:
       - name: Build Backend
         run: |
           go mod download
-          VERSION=$(git describe --tags)
           go build -ldflags "-s -w -X 'new-api/common.Version=$VERSION'" -o new-api-$VERSION.exe
       - name: Release
         uses: softprops/action-gh-release@v2
@@ -132,5 +140,3 @@ jobs:
           files: new-api-*.exe
         env:
           GITHUB_TOKEN: ${{ secrets.GITHUB_TOKEN }}
-
-

.gitignore

@@ -16,6 +16,14 @@ new-api
 tiktoken_cache
 .eslintcache
 .gocache
+.gomodcache/
+.cache
+web/bun.lock
+plans
 
 electron/node_modules
 electron/dist
+data/
+.gomodcache/
+.gocache-temp
+.gopath

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
 
@@ -25,10 +25,11 @@ 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 alpine
+FROM debian:bookworm-slim
 
-RUN apk upgrade --no-cache \
-    && apk add --no-cache ca-certificates tzdata \
+RUN apt-get update \
+    && apt-get install -y --no-install-recommends ca-certificates tzdata libasan8 wget \
+    && rm -rf /var/lib/apt/lists/* \
     && update-ca-certificates
 
 COPY --from=builder2 /build/new-api /

LICENSE

@@ -1,103 +1,661 @@
-# **New API 许可协议 (Licensing)**
+                    GNU AFFERO GENERAL PUBLIC LICENSE
+                       Version 3, 19 November 2007
 
-本项目采用**基于使用场景的双重许可 (Usage-Based Dual Licensing)** 模式。
+ Copyright (C) 2007 Free Software Foundation, Inc. <https://fsf.org/>
+ Everyone is permitted to copy and distribute verbatim copies
+ of this license document, but changing it is not allowed.
 
-**核心原则：**
+                            Preamble
 
-- **默认许可:** 本项目默认在 **GNU Affero 通用公共许可证 v3.0 (AGPLv3)** 下提供。任何用户在遵守 AGPLv3 条款和下述附加限制的前提下，均可免费使用。
-- **商业许可:** 在特定商业场景下，或当您希望获得 AGPLv3 之外的权利时，**必须**获取**商业许可证 (Commercial License)**。
+  The GNU Affero General Public License is a free, copyleft license for
+software and other kinds of works, specifically designed to ensure
+cooperation with the community in the case of network server software.
 
----
+  The licenses for most software and other practical works are designed
+to take away your freedom to share and change the works.  By contrast,
+our General Public Licenses are intended to guarantee your freedom to
+share and change all versions of a program--to make sure it remains free
+software for all its users.
 
-## **1. 开源许可证 (Open Source License): AGPLv3 - 适用于基础使用**
+  When we speak of free software, we are referring to freedom, not
+price.  Our General Public Licenses are designed to make sure that you
+have the freedom to distribute copies of free software (and charge for
+them if you wish), that you receive source code or can get it if you
+want it, that you can change the software or use pieces of it in new
+free programs, and that you know you can do these things.
 
-- 在遵守 **AGPLv3** 条款的前提下，您可以自由地使用、修改和分发 New API。AGPLv3 的完整文本可以访问 [https://www.gnu.org/licenses/agpl-3.0.html](https://www.gnu.org/licenses/agpl-3.0.html) 获取。
-- **核心义务:** AGPLv3 的一个关键要求是，如果您修改了 New API 并通过网络提供服务 (SaaS)，或者分发了修改后的版本，您必须以 AGPLv3 许可证向所有用户提供相应的**完整源代码**。
-- **附加限制 (重要):** 在仅使用 AGPLv3 开源许可证的情况下，您**必须**完整保留项目代码中原有的品牌标识、LOGO 及版权声明信息。**禁止以任何形式修改、移除或遮盖**这些信息。如需移除，必须获取商业许可证。
-- 使用前请务必仔细阅读并理解 AGPLv3 的所有条款及上述附加限制。
+  Developers that use our General Public Licenses protect your rights
+with two steps: (1) assert copyright on the software, and (2) offer
+you this License which gives you legal permission to copy, distribute
+and/or modify the software.
 
-## **2. 商业许可证 (Commercial License) - 适用于高级场景及闭源需求**
+  A secondary benefit of defending all users' freedom is that
+improvements made in alternate versions of the program, if they
+receive widespread use, become available for other developers to
+incorporate.  Many developers of free software are heartened and
+encouraged by the resulting cooperation.  However, in the case of
+software used on network servers, this result may fail to come about.
+The GNU General Public License permits making a modified version and
+letting the public access it on a server without ever releasing its
+source code to the public.
 
-在以下任一情况下，您**必须**联系我们获取并签署一份商业许可证，才能合法使用 New API：
+  The GNU Affero General Public License is designed specifically to
+ensure that, in such cases, the modified source code becomes available
+to the community.  It requires the operator of a network server to
+provide the source code of the modified version running there to the
+users of that server.  Therefore, public use of a modified version, on
+a publicly accessible server, gives the public access to the source
+code of the modified version.
 
-- **场景一：移除品牌和版权信息**  
-  您希望在您的产品或服务中移除 New API 的 LOGO、UI界面中的版权声明或其他品牌标识。
+  An older license, called the Affero General Public License and
+published by Affero, was designed to accomplish similar goals.  This is
+a different license, not a version of the Affero GPL, but Affero has
+released a new version of the Affero GPL which permits relicensing under
+this license.
 
-- **场景二：规避 AGPLv3 开源义务**  
-  您基于 New API 进行了修改，并希望：  
-    - 通过网络提供服务（SaaS），但**不希望**向您的服务用户公开您修改后的源代码。  
-    - 分发一个集成了 New API 的软件产品，但**不希望**以 AGPLv3 许可证发布您的产品或公开源代码。
+  The precise terms and conditions for copying, distribution and
+modification follow.
 
-- **场景三：企业政策与集成需求**  
-    - 您所在公司的政策、客户合同或项目要求不允许使用 AGPLv3 许可的软件。  
-    - 您需要进行 OEM 集成，将 New API 作为您闭源商业产品的一部分进行再分发。
+                       TERMS AND CONDITIONS
 
-- **场景四：需要商业支持与保障**  
-    您需要 AGPLv3 未提供的商业保障，如官方技术支持等。
+  0. Definitions.
 
-**获取商业许可：**  
-请通过电子邮件 **support@quantumnous.com** 联系 New API 团队洽谈商业授权事宜。
+  "This License" refers to version 3 of the GNU Affero General Public License.
 
-## **3. 贡献 (Contributions)**
+  "Copyright" also means copyright-like laws that apply to other kinds of
+works, such as semiconductor masks.
 
-- 我们欢迎社区对 New API 的贡献。所有向本项目提交的贡献（例如通过 Pull Request）都将被视为在 **AGPLv3** 许可证下提供。
-- 通过向本项目提交贡献，即表示您同意您的代码以 AGPLv3 许可证授权给本项目及所有后续使用者（无论这些使用者最终遵循 AGPLv3 还是商业许可）。
-- 您也理解并同意，您的贡献可能会被包含在根据商业许可证分发的 New API 版本中。
+  "The Program" refers to any copyrightable work licensed under this
+License.  Each licensee is addressed as "you".  "Licensees" and
+"recipients" may be individuals or organizations.
 
-## **4. 其他条款 (Other Terms)**
+  To "modify" a work means to copy from or adapt all or part of the work
+in a fashion requiring copyright permission, other than the making of an
+exact copy.  The resulting work is called a "modified version" of the
+earlier work or a work "based on" the earlier work.
 
-- 关于商业许可证的具体条款、条件和价格，以双方签署的正式商业许可协议为准。
-- 项目维护者保留根据需要更新本许可政策的权利。相关更新将通过项目官方渠道（如代码仓库、官方网站）进行通知。
+  A "covered work" means either the unmodified Program or a work based
+on the Program.
 
----
+  To "propagate" a work means to do anything with it that, without
+permission, would make you directly or secondarily liable for
+infringement under applicable copyright law, except executing it on a
+computer or modifying a private copy.  Propagation includes copying,
+distribution (with or without modification), making available to the
+public, and in some countries other activities as well.
 
-# **New API Licensing**
+  To "convey" a work means any kind of propagation that enables other
+parties to make or receive copies.  Mere interaction with a user through
+a computer network, with no transfer of a copy, is not conveying.
 
-This project uses a **Usage-Based Dual Licensing** model.
+  An interactive user interface displays "Appropriate Legal Notices"
+to the extent that it includes a convenient and prominently visible
+feature that (1) displays an appropriate copyright notice, and (2)
+tells the user that there is no warranty for the work (except to the
+extent that warranties are provided), that licensees may convey the
+work under this License, and how to view a copy of this License.  If
+the interface presents a list of user commands or options, such as a
+menu, a prominent item in the list meets this criterion.
 
-**Core Principles:**
+  1. Source Code.
 
-- **Default License:** This project is available by default under the **GNU Affero General Public License v3.0 (AGPLv3)**. Any user may use it free of charge, provided they comply with both the AGPLv3 terms and the additional restrictions listed below.
-- **Commercial License:** For specific commercial scenarios, or if you require rights beyond those granted by AGPLv3, you **must** obtain a **Commercial License**.
+  The "source code" for a work means the preferred form of the work
+for making modifications to it.  "Object code" means any non-source
+form of a work.
 
----
+  A "Standard Interface" means an interface that either is an official
+standard defined by a recognized standards body, or, in the case of
+interfaces specified for a particular programming language, one that
+is widely used among developers working in that language.
 
-## **1. Open Source License: AGPLv3 – For Basic Usage**
+  The "System Libraries" of an executable work include anything, other
+than the work as a whole, that (a) is included in the normal form of
+packaging a Major Component, but which is not part of that Major
+Component, and (b) serves only to enable use of the work with that
+Major Component, or to implement a Standard Interface for which an
+implementation is available to the public in source code form.  A
+"Major Component", in this context, means a major essential component
+(kernel, window system, and so on) of the specific operating system
+(if any) on which the executable work runs, or a compiler used to
+produce the work, or an object code interpreter used to run it.
 
-- Under the terms of the **AGPLv3**, you are free to use, modify, and distribute New API. The complete AGPLv3 license text can be viewed at [https://www.gnu.org/licenses/agpl-3.0.html](https://www.gnu.org/licenses/agpl-3.0.html).
-- **Core Obligation:** A key AGPLv3 requirement is that if you modify New API and provide it as a network service (SaaS), or distribute a modified version, you must make the **complete corresponding source code** available to all users under the AGPLv3 license.
-- **Additional Restriction (Important):** When using only the AGPLv3 open-source license, you **must** retain all original branding, logos, and copyright statements within the project’s code. **You are strictly prohibited from modifying, removing, or concealing** any such information. If you wish to remove this, you must obtain a Commercial License.
-- Please read and ensure that you fully understand all AGPLv3 terms and the above additional restriction before use.
+  The "Corresponding Source" for a work in object code form means all
+the source code needed to generate, install, and (for an executable
+work) run the object code and to modify the work, including scripts to
+control those activities.  However, it does not include the work's
+System Libraries, or general-purpose tools or generally available free
+programs which are used unmodified in performing those activities but
+which are not part of the work.  For example, Corresponding Source
+includes interface definition files associated with source files for
+the work, and the source code for shared libraries and dynamically
+linked subprograms that the work is specifically designed to require,
+such as by intimate data communication or control flow between those
+subprograms and other parts of the work.
 
-## **2. Commercial License – For Advanced Scenarios & Closed Source Needs**
+  The Corresponding Source need not include anything that users
+can regenerate automatically from other parts of the Corresponding
+Source.
 
-You **must** contact us to obtain and sign a Commercial License in any of the following scenarios in order to legally use New API:
+  The Corresponding Source for a work in source code form is that
+same work.
 
-- **Scenario 1: Removal of Branding and Copyright**  
-  You wish to remove the New API logo, copyright statement, or other branding elements from your product or service.
+  2. Basic Permissions.
 
-- **Scenario 2: Avoidance of AGPLv3 Open Source Obligations**  
-  You have modified New API and wish to:
-    - Offer it as a network service (SaaS) **without** disclosing your modifications' source code to your users.
-    - Distribute a software product integrated with New API **without** releasing your product under AGPLv3 or open-sourcing the code.
+  All rights granted under this License are granted for the term of
+copyright on the Program, and are irrevocable provided the stated
+conditions are met.  This License explicitly affirms your unlimited
+permission to run the unmodified Program.  The output from running a
+covered work is covered by this License only if the output, given its
+content, constitutes a covered work.  This License acknowledges your
+rights of fair use or other equivalent, as provided by copyright law.
 
-- **Scenario 3: Enterprise Policy & Integration Needs**  
-    - Your organization’s policies, client contracts, or project requirements prohibit the use of AGPLv3-licensed software.
-    - You require OEM integration and need to redistribute New API as part of your closed-source commercial product.
+  You may make, run and propagate covered works that you do not
+convey, without conditions so long as your license otherwise remains
+in force.  You may convey covered works to others for the sole purpose
+of having them make modifications exclusively for you, or provide you
+with facilities for running those works, provided that you comply with
+the terms of this License in conveying all material for which you do
+not control copyright.  Those thus making or running the covered works
+for you must do so exclusively on your behalf, under your direction
+and control, on terms that prohibit them from making any copies of
+your copyrighted material outside their relationship with you.
 
-- **Scenario 4: Commercial Support and Assurances**  
-    You require commercial assurances not provided by AGPLv3, such as official technical support.
+  Conveying under any other circumstances is permitted solely under
+the conditions stated below.  Sublicensing is not allowed; section 10
+makes it unnecessary.
 
-**Obtaining a Commercial License:**  
-Please contact the New API team via email at **support@quantumnous.com** to discuss commercial licensing.
+  3. Protecting Users' Legal Rights From Anti-Circumvention Law.
 
-## **3. Contributions**
+  No covered work shall be deemed part of an effective technological
+measure under any applicable law fulfilling obligations under article
+11 of the WIPO copyright treaty adopted on 20 December 1996, or
+similar laws prohibiting or restricting circumvention of such
+measures.
 
-- We welcome community contributions to New API. All contributions (e.g., via Pull Request) are deemed to be provided under the **AGPLv3** license.
-- By submitting a contribution, you agree that your code is licensed to this project and all downstream users under the AGPLv3 license (regardless of whether those users ultimately operate under AGPLv3 or a Commercial License).
-- You also acknowledge and agree that your contribution may be included in New API releases distributed under a Commercial License.
+  When you convey a covered work, you waive any legal power to forbid
+circumvention of technological measures to the extent such circumvention
+is effected by exercising rights under this License with respect to
+the covered work, and you disclaim any intention to limit operation or
+modification of the work as a means of enforcing, against the work's
+users, your or third parties' legal rights to forbid circumvention of
+technological measures.
 
-## **4. Other Terms**
+  4. Conveying Verbatim Copies.
 
-- The specific terms, conditions, and pricing of the Commercial License are governed by the formal commercial license agreement executed by both parties.
-- Project maintainers reserve the right to update this licensing policy as needed. Updates will be communicated via official project channels (e.g., repository, official website).
+  You may convey verbatim copies of the Program's source code as you
+receive it, in any medium, provided that you conspicuously and
+appropriately publish on each copy an appropriate copyright notice;
+keep intact all notices stating that this License and any
+non-permissive terms added in accord with section 7 apply to the code;
+keep intact all notices of the absence of any warranty; and give all
+recipients a copy of this License along with the Program.
+
+  You may charge any price or no price for each copy that you convey,
+and you may offer support or warranty protection for a fee.
+
+  5. Conveying Modified Source Versions.
+
+  You may convey a work based on the Program, or the modifications to
+produce it from the Program, in the form of source code under the
+terms of section 4, provided that you also meet all of these conditions:
+
+    a) The work must carry prominent notices stating that you modified
+    it, and giving a relevant date.
+
+    b) The work must carry prominent notices stating that it is
+    released under this License and any conditions added under section
+    7.  This requirement modifies the requirement in section 4 to
+    "keep intact all notices".
+
+    c) You must license the entire work, as a whole, under this
+    License to anyone who comes into possession of a copy.  This
+    License will therefore apply, along with any applicable section 7
+    additional terms, to the whole of the work, and all its parts,
+    regardless of how they are packaged.  This License gives no
+    permission to license the work in any other way, but it does not
+    invalidate such permission if you have separately received it.
+
+    d) If the work has interactive user interfaces, each must display
+    Appropriate Legal Notices; however, if the Program has interactive
+    interfaces that do not display Appropriate Legal Notices, your
+    work need not make them do so.
+
+  A compilation of a covered work with other separate and independent
+works, which are not by their nature extensions of the covered work,
+and which are not combined with it such as to form a larger program,
+in or on a volume of a storage or distribution medium, is called an
+"aggregate" if the compilation and its resulting copyright are not
+used to limit the access or legal rights of the compilation's users
+beyond what the individual works permit.  Inclusion of a covered work
+in an aggregate does not cause this License to apply to the other
+parts of the aggregate.
+
+  6. Conveying Non-Source Forms.
+
+  You may convey a covered work in object code form under the terms
+of sections 4 and 5, provided that you also convey the
+machine-readable Corresponding Source under the terms of this License,
+in one of these ways:
+
+    a) Convey the object code in, or embodied in, a physical product
+    (including a physical distribution medium), accompanied by the
+    Corresponding Source fixed on a durable physical medium
+    customarily used for software interchange.
+
+    b) Convey the object code in, or embodied in, a physical product
+    (including a physical distribution medium), accompanied by a
+    written offer, valid for at least three years and valid for as
+    long as you offer spare parts or customer support for that product
+    model, to give anyone who possesses the object code either (1) a
+    copy of the Corresponding Source for all the software in the
+    product that is covered by this License, on a durable physical
+    medium customarily used for software interchange, for a price no
+    more than your reasonable cost of physically performing this
+    conveying of source, or (2) access to copy the
+    Corresponding Source from a network server at no charge.
+
+    c) Convey individual copies of the object code with a copy of the
+    written offer to provide the Corresponding Source.  This
+    alternative is allowed only occasionally and noncommercially, and
+    only if you received the object code with such an offer, in accord
+    with subsection 6b.
+
+    d) Convey the object code by offering access from a designated
+    place (gratis or for a charge), and offer equivalent access to the
+    Corresponding Source in the same way through the same place at no
+    further charge.  You need not require recipients to copy the
+    Corresponding Source along with the object code.  If the place to
+    copy the object code is a network server, the Corresponding Source
+    may be on a different server (operated by you or a third party)
+    that supports equivalent copying facilities, provided you maintain
+    clear directions next to the object code saying where to find the
+    Corresponding Source.  Regardless of what server hosts the
+    Corresponding Source, you remain obligated to ensure that it is
+    available for as long as needed to satisfy these requirements.
+
+    e) Convey the object code using peer-to-peer transmission, provided
+    you inform other peers where the object code and Corresponding
+    Source of the work are being offered to the general public at no
+    charge under subsection 6d.
+
+  A separable portion of the object code, whose source code is excluded
+from the Corresponding Source as a System Library, need not be
+included in conveying the object code work.
+
+  A "User Product" is either (1) a "consumer product", which means any
+tangible personal property which is normally used for personal, family,
+or household purposes, or (2) anything designed or sold for incorporation
+into a dwelling.  In determining whether a product is a consumer product,
+doubtful cases shall be resolved in favor of coverage.  For a particular
+product received by a particular user, "normally used" refers to a
+typical or common use of that class of product, regardless of the status
+of the particular user or of the way in which the particular user
+actually uses, or expects or is expected to use, the product.  A product
+is a consumer product regardless of whether the product has substantial
+commercial, industrial or non-consumer uses, unless such uses represent
+the only significant mode of use of the product.
+
+  "Installation Information" for a User Product means any methods,
+procedures, authorization keys, or other information required to install
+and execute modified versions of a covered work in that User Product from
+a modified version of its Corresponding Source.  The information must
+suffice to ensure that the continued functioning of the modified object
+code is in no case prevented or interfered with solely because
+modification has been made.
+
+  If you convey an object code work under this section in, or with, or
+specifically for use in, a User Product, and the conveying occurs as
+part of a transaction in which the right of possession and use of the
+User Product is transferred to the recipient in perpetuity or for a
+fixed term (regardless of how the transaction is characterized), the
+Corresponding Source conveyed under this section must be accompanied
+by the Installation Information.  But this requirement does not apply
+if neither you nor any third party retains the ability to install
+modified object code on the User Product (for example, the work has
+been installed in ROM).
+
+  The requirement to provide Installation Information does not include a
+requirement to continue to provide support service, warranty, or updates
+for a work that has been modified or installed by the recipient, or for
+the User Product in which it has been modified or installed.  Access to a
+network may be denied when the modification itself materially and
+adversely affects the operation of the network or violates the rules and
+protocols for communication across the network.
+
+  Corresponding Source conveyed, and Installation Information provided,
+in accord with this section must be in a format that is publicly
+documented (and with an implementation available to the public in
+source code form), and must require no special password or key for
+unpacking, reading or copying.
+
+  7. Additional Terms.
+
+  "Additional permissions" are terms that supplement the terms of this
+License by making exceptions from one or more of its conditions.
+Additional permissions that are applicable to the entire Program shall
+be treated as though they were included in this License, to the extent
+that they are valid under applicable law.  If additional permissions
+apply only to part of the Program, that part may be used separately
+under those permissions, but the entire Program remains governed by
+this License without regard to the additional permissions.
+
+  When you convey a copy of a covered work, you may at your option
+remove any additional permissions from that copy, or from any part of
+it.  (Additional permissions may be written to require their own
+removal in certain cases when you modify the work.)  You may place
+additional permissions on material, added by you to a covered work,
+for which you have or can give appropriate copyright permission.
+
+  Notwithstanding any other provision of this License, for material you
+add to a covered work, you may (if authorized by the copyright holders of
+that material) supplement the terms of this License with terms:
+
+    a) Disclaiming warranty or limiting liability differently from the
+    terms of sections 15 and 16 of this License; or
+
+    b) Requiring preservation of specified reasonable legal notices or
+    author attributions in that material or in the Appropriate Legal
+    Notices displayed by works containing it; or
+
+    c) Prohibiting misrepresentation of the origin of that material, or
+    requiring that modified versions of such material be marked in
+    reasonable ways as different from the original version; or
+
+    d) Limiting the use for publicity purposes of names of licensors or
+    authors of the material; or
+
+    e) Declining to grant rights under trademark law for use of some
+    trade names, trademarks, or service marks; or
+
+    f) Requiring indemnification of licensors and authors of that
+    material by anyone who conveys the material (or modified versions of
+    it) with contractual assumptions of liability to the recipient, for
+    any liability that these contractual assumptions directly impose on
+    those licensors and authors.
+
+  All other non-permissive additional terms are considered "further
+restrictions" within the meaning of section 10.  If the Program as you
+received it, or any part of it, contains a notice stating that it is
+governed by this License along with a term that is a further
+restriction, you may remove that term.  If a license document contains
+a further restriction but permits relicensing or conveying under this
+License, you may add to a covered work material governed by the terms
+of that license document, provided that the further restriction does
+not survive such relicensing or conveying.
+
+  If you add terms to a covered work in accord with this section, you
+must place, in the relevant source files, a statement of the
+additional terms that apply to those files, or a notice indicating
+where to find the applicable terms.
+
+  Additional terms, permissive or non-permissive, may be stated in the
+form of a separately written license, or stated as exceptions;
+the above requirements apply either way.
+
+  8. Termination.
+
+  You may not propagate or modify a covered work except as expressly
+provided under this License.  Any attempt otherwise to propagate or
+modify it is void, and will automatically terminate your rights under
+this License (including any patent licenses granted under the third
+paragraph of section 11).
+
+  However, if you cease all violation of this License, then your
+license from a particular copyright holder is reinstated (a)
+provisionally, unless and until the copyright holder explicitly and
+finally terminates your license, and (b) permanently, if the copyright
+holder fails to notify you of the violation by some reasonable means
+prior to 60 days after the cessation.
+
+  Moreover, your license from a particular copyright holder is
+reinstated permanently if the copyright holder notifies you of the
+violation by some reasonable means, this is the first time you have
+received notice of violation of this License (for any work) from that
+copyright holder, and you cure the violation prior to 30 days after
+your receipt of the notice.
+
+  Termination of your rights under this section does not terminate the
+licenses of parties who have received copies or rights from you under
+this License.  If your rights have been terminated and not permanently
+reinstated, you do not qualify to receive new licenses for the same
+material under section 10.
+
+  9. Acceptance Not Required for Having Copies.
+
+  You are not required to accept this License in order to receive or
+run a copy of the Program.  Ancillary propagation of a covered work
+occurring solely as a consequence of using peer-to-peer transmission
+to receive a copy likewise does not require acceptance.  However,
+nothing other than this License grants you permission to propagate or
+modify any covered work.  These actions infringe copyright if you do
+not accept this License.  Therefore, by modifying or propagating a
+covered work, you indicate your acceptance of this License to do so.
+
+  10. Automatic Licensing of Downstream Recipients.
+
+  Each time you convey a covered work, the recipient automatically
+receives a license from the original licensors, to run, modify and
+propagate that work, subject to this License.  You are not responsible
+for enforcing compliance by third parties with this License.
+
+  An "entity transaction" is a transaction transferring control of an
+organization, or substantially all assets of one, or subdividing an
+organization, or merging organizations.  If propagation of a covered
+work results from an entity transaction, each party to that
+transaction who receives a copy of the work also receives whatever
+licenses to the work the party's predecessor in interest had or could
+give under the previous paragraph, plus a right to possession of the
+Corresponding Source of the work from the predecessor in interest, if
+the predecessor has it or can get it with reasonable efforts.
+
+  You may not impose any further restrictions on the exercise of the
+rights granted or affirmed under this License.  For example, you may
+not impose a license fee, royalty, or other charge for exercise of
+rights granted under this License, and you may not initiate litigation
+(including a cross-claim or counterclaim in a lawsuit) alleging that
+any patent claim is infringed by making, using, selling, offering for
+sale, or importing the Program or any portion of it.
+
+  11. Patents.
+
+  A "contributor" is a copyright holder who authorizes use under this
+License of the Program or a work on which the Program is based.  The
+work thus licensed is called the contributor's "contributor version".
+
+  A contributor's "essential patent claims" are all patent claims
+owned or controlled by the contributor, whether already acquired or
+hereafter acquired, that would be infringed by some manner, permitted
+by this License, of making, using, or selling its contributor version,
+but do not include claims that would be infringed only as a
+consequence of further modification of the contributor version.  For
+purposes of this definition, "control" includes the right to grant
+patent sublicenses in a manner consistent with the requirements of
+this License.
+
+  Each contributor grants you a non-exclusive, worldwide, royalty-free
+patent license under the contributor's essential patent claims, to
+make, use, sell, offer for sale, import and otherwise run, modify and
+propagate the contents of its contributor version.
+
+  In the following three paragraphs, a "patent license" is any express
+agreement or commitment, however denominated, not to enforce a patent
+(such as an express permission to practice a patent or covenant not to
+sue for patent infringement).  To "grant" such a patent license to a
+party means to make such an agreement or commitment not to enforce a
+patent against the party.
+
+  If you convey a covered work, knowingly relying on a patent license,
+and the Corresponding Source of the work is not available for anyone
+to copy, free of charge and under the terms of this License, through a
+publicly available network server or other readily accessible means,
+then you must either (1) cause the Corresponding Source to be so
+available, or (2) arrange to deprive yourself of the benefit of the
+patent license for this particular work, or (3) arrange, in a manner
+consistent with the requirements of this License, to extend the patent
+license to downstream recipients.  "Knowingly relying" means you have
+actual knowledge that, but for the patent license, your conveying the
+covered work in a country, or your recipient's use of the covered work
+in a country, would infringe one or more identifiable patents in that
+country that you have reason to believe are valid.
+
+  If, pursuant to or in connection with a single transaction or
+arrangement, you convey, or propagate by procuring conveyance of, a
+covered work, and grant a patent license to some of the parties
+receiving the covered work authorizing them to use, propagate, modify
+or convey a specific copy of the covered work, then the patent license
+you grant is automatically extended to all recipients of the covered
+work and works based on it.
+
+  A patent license is "discriminatory" if it does not include within
+the scope of its coverage, prohibits the exercise of, or is
+conditioned on the non-exercise of one or more of the rights that are
+specifically granted under this License.  You may not convey a covered
+work if you are a party to an arrangement with a third party that is
+in the business of distributing software, under which you make payment
+to the third party based on the extent of your activity of conveying
+the work, and under which the third party grants, to any of the
+parties who would receive the covered work from you, a discriminatory
+patent license (a) in connection with copies of the covered work
+conveyed by you (or copies made from those copies), or (b) primarily
+for and in connection with specific products or compilations that
+contain the covered work, unless you entered into that arrangement,
+or that patent license was granted, prior to 28 March 2007.
+
+  Nothing in this License shall be construed as excluding or limiting
+any implied license or other defenses to infringement that may
+otherwise be available to you under applicable patent law.
+
+  12. No Surrender of Others' Freedom.
+
+  If conditions are imposed on you (whether by court order, agreement or
+otherwise) that contradict the conditions of this License, they do not
+excuse you from the conditions of this License.  If you cannot convey a
+covered work so as to satisfy simultaneously your obligations under this
+License and any other pertinent obligations, then as a consequence you may
+not convey it at all.  For example, if you agree to terms that obligate you
+to collect a royalty for further conveying from those to whom you convey
+the Program, the only way you could satisfy both those terms and this
+License would be to refrain entirely from conveying the Program.
+
+  13. Remote Network Interaction; Use with the GNU General Public License.
+
+  Notwithstanding any other provision of this License, if you modify the
+Program, your modified version must prominently offer all users
+interacting with it remotely through a computer network (if your version
+supports such interaction) an opportunity to receive the Corresponding
+Source of your version by providing access to the Corresponding Source
+from a network server at no charge, through some standard or customary
+means of facilitating copying of software.  This Corresponding Source
+shall include the Corresponding Source for any work covered by version 3
+of the GNU General Public License that is incorporated pursuant to the
+following paragraph.
+
+  Notwithstanding any other provision of this License, you have
+permission to link or combine any covered work with a work licensed
+under version 3 of the GNU General Public License into a single
+combined work, and to convey the resulting work.  The terms of this
+License will continue to apply to the part which is the covered work,
+but the work with which it is combined will remain governed by version
+3 of the GNU General Public License.
+
+  14. Revised Versions of this License.
+
+  The Free Software Foundation may publish revised and/or new versions of
+the GNU Affero General Public License from time to time.  Such new versions
+will be similar in spirit to the present version, but may differ in detail to
+address new problems or concerns.
+
+  Each version is given a distinguishing version number.  If the
+Program specifies that a certain numbered version of the GNU Affero General
+Public License "or any later version" applies to it, you have the
+option of following the terms and conditions either of that numbered
+version or of any later version published by the Free Software
+Foundation.  If the Program does not specify a version number of the
+GNU Affero General Public License, you may choose any version ever published
+by the Free Software Foundation.
+
+  If the Program specifies that a proxy can decide which future
+versions of the GNU Affero General Public License can be used, that proxy's
+public statement of acceptance of a version permanently authorizes you
+to choose that version for the Program.
+
+  Later license versions may give you additional or different
+permissions.  However, no additional obligations are imposed on any
+author or copyright holder as a result of your choosing to follow a
+later version.
+
+  15. Disclaimer of Warranty.
+
+  THERE IS NO WARRANTY FOR THE PROGRAM, TO THE EXTENT PERMITTED BY
+APPLICABLE LAW.  EXCEPT WHEN OTHERWISE STATED IN WRITING THE COPYRIGHT
+HOLDERS AND/OR OTHER PARTIES PROVIDE THE PROGRAM "AS IS" WITHOUT WARRANTY
+OF ANY KIND, EITHER EXPRESSED OR IMPLIED, INCLUDING, BUT NOT LIMITED TO,
+THE IMPLIED WARRANTIES OF MERCHANTABILITY AND FITNESS FOR A PARTICULAR
+PURPOSE.  THE ENTIRE RISK AS TO THE QUALITY AND PERFORMANCE OF THE PROGRAM
+IS WITH YOU.  SHOULD THE PROGRAM PROVE DEFECTIVE, YOU ASSUME THE COST OF
+ALL NECESSARY SERVICING, REPAIR OR CORRECTION.
+
+  16. Limitation of Liability.
+
+  IN NO EVENT UNLESS REQUIRED BY APPLICABLE LAW OR AGREED TO IN WRITING
+WILL ANY COPYRIGHT HOLDER, OR ANY OTHER PARTY WHO MODIFIES AND/OR CONVEYS
+THE PROGRAM AS PERMITTED ABOVE, BE LIABLE TO YOU FOR DAMAGES, INCLUDING ANY
+GENERAL, SPECIAL, INCIDENTAL OR CONSEQUENTIAL DAMAGES ARISING OUT OF THE
+USE OR INABILITY TO USE THE PROGRAM (INCLUDING BUT NOT LIMITED TO LOSS OF
+DATA OR DATA BEING RENDERED INACCURATE OR LOSSES SUSTAINED BY YOU OR THIRD
+PARTIES OR A FAILURE OF THE PROGRAM TO OPERATE WITH ANY OTHER PROGRAMS),
+EVEN IF SUCH HOLDER OR OTHER PARTY HAS BEEN ADVISED OF THE POSSIBILITY OF
+SUCH DAMAGES.
+
+  17. Interpretation of Sections 15 and 16.
+
+  If the disclaimer of warranty and limitation of liability provided
+above cannot be given local legal effect according to their terms,
+reviewing courts shall apply local law that most closely approximates
+an absolute waiver of all civil liability in connection with the
+Program, unless a warranty or assumption of liability accompanies a
+copy of the Program in return for a fee.
+
+                     END OF TERMS AND CONDITIONS
+
+            How to Apply These Terms to Your New Programs
+
+  If you develop a new program, and you want it to be of the greatest
+possible use to the public, the best way to achieve this is to make it
+free software which everyone can redistribute and change under these terms.
+
+  To do so, attach the following notices to the program.  It is safest
+to attach them to the start of each source file to most effectively
+state the exclusion of warranty; and each file should have at least
+the "copyright" line and a pointer to where the full notice is found.
+
+    <one line to give the program's name and a brief idea of what it does.>
+    Copyright (C) <year>  <name of author>
+
+    This program is free software: you can redistribute it and/or modify
+    it under the terms of the GNU Affero General Public License as published
+    by the Free Software Foundation, either version 3 of the License, or
+    (at your option) any later version.
+
+    This program is distributed in the hope that it will be useful,
+    but WITHOUT ANY WARRANTY; without even the implied warranty of
+    MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE.  See the
+    GNU Affero General Public License for more details.
+
+    You should have received a copy of the GNU Affero General Public License
+    along with this program.  If not, see <https://www.gnu.org/licenses/>.
+
+Also add information on how to contact you by electronic and paper mail.
+
+  If your software can interact with users remotely through a computer
+network, you should also make sure that it provides a way for users to
+get its source.  For example, if your program is a web application, its
+interface could display a "Source" link that leads users to an archive
+of the code.  There are many ways you could offer source, and different
+solutions will be better for different programs; see section 13 for the
+specific requirements.
+
+  You should also get your employer (if you work as a programmer) or school,
+if any, to sign a "copyright disclaimer" for the program, if necessary.
+For more information on this, and how to apply and follow the GNU AGPL, see
+<https://www.gnu.org/licenses/>.

README.en.md

@@ -1,225 +0,0 @@
-<p align="right">
-   <a href="./README.md">中文</a> | <strong>English</strong> | <a href="./README.fr.md">Français</a> | <a href="./README.ja.md">日本語</a>
-</p>
-
-> [!NOTE]
-> **MT (Machine Translation)**: This document is machine translated. For the most accurate information, please refer to the [Chinese version](./README.md).
-
-<div align="center">
-
-![new-api](/web/public/logo.png)
-
-# New API
-
-🍥 Next-Generation Large Model Gateway and AI Asset Management System
-
-<a href="https://trendshift.io/repositories/8227" target="_blank"><img src="https://trendshift.io/api/badge/repositories/8227" alt="Calcium-Ion%2Fnew-api | Trendshift" style="width: 250px; height: 55px;" width="250" height="55"/></a>
-
-<p align="center">
-  <a href="https://raw.githubusercontent.com/Calcium-Ion/new-api/main/LICENSE">
-    <img src="https://img.shields.io/github/license/Calcium-Ion/new-api?color=brightgreen" alt="license">
-  </a>
-  <a href="https://github.com/Calcium-Ion/new-api/releases/latest">
-    <img src="https://img.shields.io/github/v/release/Calcium-Ion/new-api?color=brightgreen&include_prereleases" alt="release">
-  </a>
-  <a href="https://github.com/users/Calcium-Ion/packages/container/package/new-api">
-    <img src="https://img.shields.io/badge/docker-ghcr.io-blue" alt="docker">
-  </a>
-  <a href="https://hub.docker.com/r/CalciumIon/new-api">
-    <img src="https://img.shields.io/badge/docker-dockerHub-blue" alt="docker">
-  </a>
-  <a href="https://goreportcard.com/report/github.com/Calcium-Ion/new-api">
-    <img src="https://goreportcard.com/badge/github.com/Calcium-Ion/new-api" alt="GoReportCard">
-  </a>
-</p>
-</div>
-
-## 📝 Project Description
-
-> [!NOTE]  
-> This is an open-source project developed based on [One API](https://github.com/songquanpeng/one-api)
-
-> [!IMPORTANT]  
-> - This project is for personal learning purposes only, with no guarantee of stability or technical support.
-> - Users must comply with OpenAI's [Terms of Use](https://openai.com/policies/terms-of-use) and **applicable laws and regulations**, and must not use it for illegal purposes.
-> - According to the [《Interim Measures for the Management of Generative Artificial Intelligence Services》](http://www.cac.gov.cn/2023-07/13/c_1690898327029107.htm), please do not provide any unregistered generative AI services to the public in China.
-
-<h2>🤝 Trusted Partners</h2>
-<p id="premium-sponsors">&nbsp;</p>
-<p align="center"><strong>No particular order</strong></p>
-<p align="center">
-  <a href="https://www.cherry-ai.com/" target=_blank><img
-    src="./docs/images/cherry-studio.png" alt="Cherry Studio" height="120"
-  /></a>
-  <a href="https://bda.pku.edu.cn/" target=_blank><img
-    src="./docs/images/pku.png" alt="Peking University" height="120"
-  /></a>
-  <a href="https://www.compshare.cn/?ytag=GPU_yy_gh_newapi" target=_blank><img
-    src="./docs/images/ucloud.png" alt="UCloud" height="120"
-  /></a>
-  <a href="https://www.aliyun.com/" target=_blank><img
-    src="./docs/images/aliyun.png" alt="Alibaba Cloud" height="120"
-  /></a>
-  <a href="https://io.net/" target=_blank><img
-    src="./docs/images/io-net.png" alt="IO.NET" height="120"
-  /></a>
-</p>
-<p>&nbsp;</p>
-
-## 📚 Documentation
-
-For detailed documentation, please visit our official Wiki: [https://docs.newapi.pro/](https://docs.newapi.pro/)
-
-You can also access the AI-generated DeepWiki:
-[![Ask DeepWiki](https://deepwiki.com/badge.svg)](https://deepwiki.com/QuantumNous/new-api)
-
-## ✨ Key Features
-
-New API offers a wide range of features, please refer to [Features Introduction](https://docs.newapi.pro/wiki/features-introduction) for details:
-
-1. 🎨 Brand new UI interface
-2. 🌍 Multi-language support
-3. 💰 Online recharge functionality, currently supports EPay and Stripe
-4. 🔍 Support for querying usage quotas with keys (works with [neko-api-key-tool](https://github.com/Calcium-Ion/neko-api-key-tool))
-5. 🔄 Compatible with the original One API database
-6. 💵 Support for pay-per-use model pricing
-7. ⚖️ Support for weighted random channel selection
-8. 📈 Data dashboard (console)
-9. 🔒 Token grouping and model restrictions
-10. 🤖 Support for more authorization login methods (LinuxDO, Telegram, OIDC)
-11. 🔄 Support for Rerank models (Cohere and Jina), [API Documentation](https://docs.newapi.pro/api/jinaai-rerank)
-12. ⚡ Support for OpenAI Realtime API (including Azure channels), [API Documentation](https://docs.newapi.pro/api/openai-realtime)
-13. ⚡ Support for **OpenAI Responses** format, [API Documentation](https://docs.newapi.pro/api/openai-responses)
-14. ⚡ Support for **Claude Messages** format, [API Documentation](https://docs.newapi.pro/api/anthropic-chat)
-15. ⚡ Support for **Google Gemini** format, [API Documentation](https://docs.newapi.pro/api/google-gemini-chat/)
-16. 🧠 Support for setting reasoning effort through model name suffixes:
-    1. OpenAI o-series models
-        - Add `-high` suffix for high reasoning effort (e.g.: `o3-mini-high`)
-        - Add `-medium` suffix for medium reasoning effort (e.g.: `o3-mini-medium`)
-        - Add `-low` suffix for low reasoning effort (e.g.: `o3-mini-low`)
-    2. Claude thinking models
-        - Add `-thinking` suffix to enable thinking mode (e.g.: `claude-3-7-sonnet-20250219-thinking`)
-17. 🔄 Thinking-to-content functionality
-18. 🔄 Model rate limiting for users
-19. 🔄 Request format conversion functionality, supporting the following three format conversions:
-    1. OpenAI Chat Completions => Claude Messages
-    2. Claude Messages => OpenAI Chat Completions (can be used for Claude Code to call third-party models)
-    3. OpenAI Chat Completions => Gemini Chat
-20. 💰 Cache billing support, which allows billing at a set ratio when cache is hit:
-    1. Set the `Prompt Cache Ratio` option in `System Settings-Operation Settings`
-    2. Set `Prompt Cache Ratio` in the channel, range 0-1, e.g., setting to 0.5 means billing at 50% when cache is hit
-    3. Supported channels:
-        - [x] OpenAI
-        - [x] Azure
-        - [x] DeepSeek
-        - [x] Claude
-
-## Model Support
-
-This version supports multiple models, please refer to [API Documentation-Relay Interface](https://docs.newapi.pro/api) for details:
-
-1. Third-party models **gpts** (gpt-4-gizmo-*)
-2. Third-party channel [Midjourney-Proxy(Plus)](https://github.com/novicezk/midjourney-proxy) interface, [API Documentation](https://docs.newapi.pro/api/midjourney-proxy-image)
-3. Third-party channel [Suno API](https://github.com/Suno-API/Suno-API) interface, [API Documentation](https://docs.newapi.pro/api/suno-music)
-4. Custom channels, supporting full call address input
-5. Rerank models ([Cohere](https://cohere.ai/) and [Jina](https://jina.ai/)), [API Documentation](https://docs.newapi.pro/api/jinaai-rerank)
-6. Claude Messages format, [API Documentation](https://docs.newapi.pro/api/anthropic-chat)
-7. Google Gemini format, [API Documentation](https://docs.newapi.pro/api/google-gemini-chat/)
-8. Dify, currently only supports chatflow
-9. For more interfaces, please refer to [API Documentation](https://docs.newapi.pro/api)
-
-## Environment Variable Configuration
-
-For detailed configuration instructions, please refer to [Installation Guide-Environment Variables Configuration](https://docs.newapi.pro/installation/environment-variables):
-
-- `GENERATE_DEFAULT_TOKEN`: Whether to generate initial tokens for newly registered users, default is `false`
-- `STREAMING_TIMEOUT`: Streaming response timeout, default is 300 seconds
-- `DIFY_DEBUG`: Whether to output workflow and node information for Dify channels, default is `true`
-- `GET_MEDIA_TOKEN`: Whether to count image tokens, default is `true`
-- `GET_MEDIA_TOKEN_NOT_STREAM`: Whether to count image tokens in non-streaming cases, default is `true`
-- `UPDATE_TASK`: Whether to update asynchronous tasks (Midjourney, Suno), default is `true`
-- `GEMINI_VISION_MAX_IMAGE_NUM`: Maximum number of images for Gemini models, default is `16`
-- `MAX_FILE_DOWNLOAD_MB`: Maximum file download size in MB, default is `20`
-- `CRYPTO_SECRET`: Encryption key used for encrypting Redis database content
-- `AZURE_DEFAULT_API_VERSION`: Azure channel default API version, default is `2025-04-01-preview`
-- `NOTIFICATION_LIMIT_DURATION_MINUTE`: Notification limit duration, default is `10` minutes
-- `NOTIFY_LIMIT_COUNT`: Maximum number of user notifications within the specified duration, default is `2`
-- `ERROR_LOG_ENABLED=true`: Whether to record and display error logs, default is `false`
-
-## Deployment
-
-For detailed deployment guides, please refer to [Installation Guide-Deployment Methods](https://docs.newapi.pro/installation):
-
-> [!TIP]
-> Latest Docker image: `calciumion/new-api:latest`
-
-### Multi-machine Deployment Considerations
-- Environment variable `SESSION_SECRET` must be set, otherwise login status will be inconsistent across multiple machines
-- If sharing Redis, `CRYPTO_SECRET` must be set, otherwise Redis content cannot be accessed across multiple machines
-
-### Deployment Requirements
-- Local database (default): SQLite (Docker deployment must mount the `/data` directory)
-- Remote database: MySQL version >= 5.7.8, PgSQL version >= 9.6
-
-### Deployment Methods
-
-#### Using BaoTa Panel Docker Feature
-Install BaoTa Panel (version **9.2.0** or above), find **New-API** in the application store and install it.
-[Tutorial with images](./docs/BT.md)
-
-#### Using Docker Compose (Recommended)
-```shell
-# Download the project
-git clone https://github.com/Calcium-Ion/new-api.git
-cd new-api
-# Edit docker-compose.yml as needed
-# Start
-docker-compose up -d
-```
-
-#### Using Docker Image Directly
-```shell
-# Using SQLite
-docker run --name new-api -d --restart always -p 3000:3000 -e TZ=Asia/Shanghai -v /home/ubuntu/data/new-api:/data calciumion/new-api:latest
-
-# Using MySQL
-docker run --name new-api -d --restart always -p 3000:3000 -e SQL_DSN="root:123456@tcp(localhost:3306)/oneapi" -e TZ=Asia/Shanghai -v /home/ubuntu/data/new-api:/data calciumion/new-api:latest
-```
-
-## Channel Retry and Cache
-Channel retry functionality has been implemented, you can set the number of retries in `Settings->Operation Settings->General Settings->Failure Retry Count`, **recommended to enable caching** functionality.
-
-### Cache Configuration Method
-1. `REDIS_CONN_STRING`: Set Redis as cache
-2. `MEMORY_CACHE_ENABLED`: Enable memory cache (no need to set manually if Redis is set)
-
-## API Documentation
-
-For detailed API documentation, please refer to [API Documentation](https://docs.newapi.pro/api):
-
-- [Chat API (Chat Completions)](https://docs.newapi.pro/api/openai-chat)
-- [Response API (Responses)](https://docs.newapi.pro/api/openai-responses)
-- [Image API (Image)](https://docs.newapi.pro/api/openai-image)
-- [Rerank API (Rerank)](https://docs.newapi.pro/api/jinaai-rerank)
-- [Realtime Chat API (Realtime)](https://docs.newapi.pro/api/openai-realtime)
-- [Claude Chat API](https://docs.newapi.pro/api/anthropic-chat)
-- [Google Gemini Chat API](https://docs.newapi.pro/api/google-gemini-chat)
-
-## Related Projects
-- [One API](https://github.com/songquanpeng/one-api): Original project
-- [Midjourney-Proxy](https://github.com/novicezk/midjourney-proxy): Midjourney interface support
-- [neko-api-key-tool](https://github.com/Calcium-Ion/neko-api-key-tool): Query usage quota with key
-
-Other projects based on New API:
-- [new-api-horizon](https://github.com/Calcium-Ion/new-api-horizon): High-performance optimized version of New API
-
-## Help and Support
-
-If you have any questions, please refer to [Help and Support](https://docs.newapi.pro/support):
-- [Community Interaction](https://docs.newapi.pro/support/community-interaction)
-- [Issue Feedback](https://docs.newapi.pro/support/feedback-issues)
-- [FAQ](https://docs.newapi.pro/support/faq)
-
-## 🌟 Star History
-
-[![Star History Chart](https://api.star-history.com/svg?repos=Calcium-Ion/new-api&type=Date)](https://star-history.com/#Calcium-Ion/new-api&Date)

README.fr.md

@@ -1,19 +1,17 @@
-<p align="right">
-   <a href="./README.md">中文</a> | <a href="./README.en.md">English</a> | <strong>Français</strong> | <a href="./README.ja.md">日本語</a>
-</p>
-
-> [!NOTE]
-> **MT (Traduction Automatique)**: Ce document est traduit automatiquement. Pour les informations les plus précises, veuillez vous référer à la [version chinoise](./README.md).
-
 <div align="center">
 
 ![new-api](/web/public/logo.png)
 
 # New API
 
-🍥 Passerelle de modèles étendus de nouvelle génération et système de gestion d'actifs d'IA
+🍥 **Passerelle de modèles étendus de nouvelle génération et système de gestion d'actifs d'IA**
 
-<a href="https://trendshift.io/repositories/8227" target="_blank"><img src="https://trendshift.io/api/badge/repositories/8227" alt="Calcium-Ion%2Fnew-api | Trendshift" style="width: 250px; height: 55px;" width="250" height="55"/></a>
+<p align="center">
+  <a href="./README.zh.md">中文</a> | 
+  <a href="./README.md">English</a> | 
+  <strong>Français</strong> | 
+  <a href="./README.ja.md">日本語</a>
+</p>
 
 <p align="center">
   <a href="https://raw.githubusercontent.com/Calcium-Ion/new-api/main/LICENSE">
@@ -32,194 +30,439 @@
     <img src="https://goreportcard.com/badge/github.com/Calcium-Ion/new-api" alt="GoReportCard">
   </a>
 </p>
+
+<p align="center">
+  <a href="https://trendshift.io/repositories/8227" target="_blank">
+    <img src="https://trendshift.io/api/badge/repositories/8227" alt="Calcium-Ion%2Fnew-api | Trendshift" style="width: 250px; height: 55px;" width="250" height="55"/>
+  </a>
+  <br>
+  <a href="https://hellogithub.com/repository/QuantumNous/new-api" target="_blank">
+    <img src="https://api.hellogithub.com/v1/widgets/recommend.svg?rid=539ac4217e69431684ad4a0bab768811&claim_uid=tbFPfKIDHpc4TzR" alt="Featured｜HelloGitHub" style="width: 250px; height: 54px;" width="250" height="54" />
+  </a>
+  <a href="https://www.producthunt.com/products/new-api/launches/new-api?embed=true&utm_source=badge-featured&utm_medium=badge&utm_campaign=badge-new-api" target="_blank" rel="noopener noreferrer">
+    <img src="https://api.producthunt.com/widgets/embed-image/v1/featured.svg?post_id=1047693&theme=light&t=1769577875005" alt="New API - All-in-one AI asset management gateway. | Product Hunt" style="width: 250px; height: 54px;" width="250" height="54" />
+  </a>
+</p>
+
+<p align="center">
+  <a href="#-démarrage-rapide">Démarrage rapide</a> •
+  <a href="#-fonctionnalités-clés">Fonctionnalités clés</a> •
+  <a href="#-déploiement">Déploiement</a> •
+  <a href="#-documentation">Documentation</a> •
+  <a href="#-aide-support">Aide</a>
+</p>
+
 </div>
 
 ## 📝 Description du projet
 
-> [!NOTE]
+> [!NOTE]  
 > Il s'agit d'un projet open-source développé sur la base de [One API](https://github.com/songquanpeng/one-api)
 
-> [!IMPORTANT]
+> [!IMPORTANT]  
 > - Ce projet est uniquement destiné à des fins d'apprentissage personnel, sans garantie de stabilité ni de support technique.
 > - Les utilisateurs doivent se conformer aux [Conditions d'utilisation](https://openai.com/policies/terms-of-use) d'OpenAI et aux **lois et réglementations applicables**, et ne doivent pas l'utiliser à des fins illégales.
 > - Conformément aux [《Mesures provisoires pour la gestion des services d'intelligence artificielle générative》](http://www.cac.gov.cn/2023-07/13/c_1690898327029107.htm), veuillez ne fournir aucun service d'IA générative non enregistré au public en Chine.
 
-<h2>🤝 Partenaires de confiance</h2>
-<p id="premium-sponsors">&nbsp;</p>
-<p align="center"><strong>Sans ordre particulier</strong></p>
+---
+
+## 🤝 Partenaires de confiance
+
 <p align="center">
-  <a href="https://www.cherry-ai.com/" target=_blank><img
-    src="./docs/images/cherry-studio.png" alt="Cherry Studio" height="120"
-  /></a>
-  <a href="https://bda.pku.edu.cn/" target=_blank><img
-    src="./docs/images/pku.png" alt="Université de Pékin" height="120"
-  /></a>
-  <a href="https://www.compshare.cn/?ytag=GPU_yy_gh_newapi" target=_blank><img
-    src="./docs/images/ucloud.png" alt="UCloud" height="120"
-  /></a>
-  <a href="https://www.aliyun.com/" target=_blank><img
-    src="./docs/images/aliyun.png" alt="Alibaba Cloud" height="120"
-  /></a>
-  <a href="https://io.net/" target=_blank><img
-    src="./docs/images/io-net.png" alt="IO.NET" height="120"
-  /></a>
+  <em>Sans ordre particulier</em>
 </p>
-<p>&nbsp;</p>
 
-## 📚 Documentation
+<p align="center">
+  <a href="https://www.cherry-ai.com/" target="_blank">
+    <img src="./docs/images/cherry-studio.png" alt="Cherry Studio" height="80" />
+  </a>
+  <a href="https://bda.pku.edu.cn/" target="_blank">
+    <img src="./docs/images/pku.png" alt="Université de Pékin" height="80" />
+  </a>
+  <a href="https://www.compshare.cn/?ytag=GPU_yy_gh_newapi" target="_blank">
+    <img src="./docs/images/ucloud.png" alt="UCloud" height="80" />
+  </a>
+  <a href="https://www.aliyun.com/" target="_blank">
+    <img src="./docs/images/aliyun.png" alt="Alibaba Cloud" height="80" />
+  </a>
+  <a href="https://io.net/" target="_blank">
+    <img src="./docs/images/io-net.png" alt="IO.NET" height="80" />
+  </a>
+</p>
 
-Pour une documentation détaillée, veuillez consulter notre Wiki officiel : [https://docs.newapi.pro/](https://docs.newapi.pro/)
+---
 
-Vous pouvez également accéder au DeepWiki généré par l'IA :
-[![Demander à DeepWiki](https://deepwiki.com/badge.svg)](https://deepwiki.com/QuantumNous/new-api)
+## 🙏 Remerciements spéciaux
 
-## ✨ Fonctionnalités clés
+<p align="center">
+  <a href="https://www.jetbrains.com/?from=new-api" target="_blank">
+    <img src="https://resources.jetbrains.com/storage/products/company/brand/logos/jb_beam.png" alt="JetBrains Logo" width="120" />
+  </a>
+</p>
 
-New API offre un large éventail de fonctionnalités, veuillez vous référer à [Présentation des fonctionnalités](https://docs.newapi.pro/wiki/features-introduction) pour plus de détails :
+<p align="center">
+  <strong>Merci à <a href="https://www.jetbrains.com/?from=new-api">JetBrains</a> pour avoir fourni une licence de développement open-source gratuite pour ce projet</strong>
+</p>
 
-1. 🎨 Nouvelle interface utilisateur
-2. 🌍 Prise en charge multilingue
-3. 💰 Fonctionnalité de recharge en ligne, prend actuellement en charge EPay et Stripe
-4. 🔍 Prise en charge de la recherche de quotas d'utilisation avec des clés (fonctionne avec [neko-api-key-tool](https://github.com/Calcium-Ion/neko-api-key-tool))
-5. 🔄 Compatible avec la base de données originale de One API
-6. 💵 Prise en charge de la tarification des modèles de paiement à l'utilisation
-7. ⚖️ Prise en charge de la sélection aléatoire pondérée des canaux
-8. 📈 Tableau de bord des données (console)
-9. 🔒 Regroupement de jetons et restrictions de modèles
-10. 🤖 Prise en charge de plus de méthodes de connexion par autorisation (LinuxDO, Telegram, OIDC)
-11. 🔄 Prise en charge des modèles Rerank (Cohere et Jina), [Documentation de l'API](https://docs.newapi.pro/api/jinaai-rerank)
-12. ⚡ Prise en charge de l'API OpenAI Realtime (y compris les canaux Azure), [Documentation de l'API](https://docs.newapi.pro/api/openai-realtime)
-13. ⚡ Prise en charge du format **OpenAI Responses**, [Documentation de l'API](https://docs.newapi.pro/api/openai-responses)
-14. ⚡ Prise en charge du format **Claude Messages**, [Documentation de l'API](https://docs.newapi.pro/api/anthropic-chat)
-15. ⚡ Prise en charge du format **Google Gemini**, [Documentation de l'API](https://docs.newapi.pro/api/google-gemini-chat/)
-16. 🧠 Prise en charge de la définition de l'effort de raisonnement via les suffixes de nom de modèle :
-    1. Modèles de la série o d'OpenAI
-        - Ajouter le suffixe `-high` pour un effort de raisonnement élevé (par exemple : `o3-mini-high`)
-        - Ajouter le suffixe `-medium` pour un effort de raisonnement moyen (par exemple : `o3-mini-medium`)
-        - Ajouter le suffixe `-low` pour un effort de raisonnement faible (par exemple : `o3-mini-low`)
-    2. Modèles de pensée de Claude
-        - Ajouter le suffixe `-thinking` pour activer le mode de pensée (par exemple : `claude-3-7-sonnet-20250219-thinking`)
-17. 🔄 Fonctionnalité de la pensée au contenu
-18. 🔄 Limitation du débit du modèle pour les utilisateurs
-19. 🔄 Fonctionnalité de conversion de format de requête, prenant en charge les trois conversions de format suivantes :
-    1. OpenAI Chat Completions => Claude Messages
-    2. Claude Messages => OpenAI Chat Completions (peut être utilisé pour Claude Code pour appeler des modèles tiers)
-    3. OpenAI Chat Completions => Gemini Chat
-20. 💰 Prise en charge de la facturation du cache, qui permet de facturer à un ratio défini lorsque le cache est atteint :
-    1. Définir l'option `Ratio de cache d'invite` dans `Paramètres système->Paramètres de fonctionnement`
-    2. Définir le `Ratio de cache d'invite` dans le canal, plage de 0 à 1, par exemple, le définir sur 0,5 signifie facturer à 50 % lorsque le cache est atteint
-    3. Canaux pris en charge :
-        - [x] OpenAI
-        - [x] Azure
-        - [x] DeepSeek
-        - [x] Claude
+---
 
-## Prise en charge des modèles
+## 🚀 Démarrage rapide
 
-Cette version prend en charge plusieurs modèles, veuillez vous référer à [Documentation de l'API-Interface de relais](https://docs.newapi.pro/api) pour plus de détails :
+### Utilisation de Docker Compose (recommandé)
 
-1. Modèles tiers **gpts** (gpt-4-gizmo-*)
-2. Canal tiers [Midjourney-Proxy(Plus)](https://github.com/novicezk/midjourney-proxy), [Documentation de l'API](https://docs.newapi.pro/api/midjourney-proxy-image)
-3. Canal tiers [Suno API](https://github.com/Suno-API/Suno-API), [Documentation de l'API](https://docs.newapi.pro/api/suno-music)
-4. Canaux personnalisés, prenant en charge la saisie complète de l'adresse d'appel
-5. Modèles Rerank ([Cohere](https://cohere.ai/) et [Jina](https://jina.ai/)), [Documentation de l'API](https://docs.newapi.pro/api/jinaai-rerank)
-6. Format de messages Claude, [Documentation de l'API](https://docs.newapi.pro/api/anthropic-chat)
-7. Format Google Gemini, [Documentation de l'API](https://docs.newapi.pro/api/google-gemini-chat/)
-8. Dify, ne prend actuellement en charge que chatflow
-9. Pour plus d'interfaces, veuillez vous référer à la [Documentation de l'API](https://docs.newapi.pro/api)
-
-## Configuration des variables d'environnement
-
-Pour des instructions de configuration détaillées, veuillez vous référer à [Guide d'installation-Configuration des variables d'environnement](https://docs.newapi.pro/installation/environment-variables) :
-
-- `GENERATE_DEFAULT_TOKEN` : S'il faut générer des jetons initiaux pour les utilisateurs nouvellement enregistrés, la valeur par défaut est `false`
-- `STREAMING_TIMEOUT` : Délai d'expiration de la réponse en streaming, la valeur par défaut est de 300 secondes
-- `DIFY_DEBUG` : S'il faut afficher les informations sur le flux de travail et les nœuds pour les canaux Dify, la valeur par défaut est `true`
-- `GET_MEDIA_TOKEN` : S'il faut compter les jetons d'image, la valeur par défaut est `true`
-- `GET_MEDIA_TOKEN_NOT_STREAM` : S'il faut compter les jetons d'image dans les cas sans streaming, la valeur par défaut est `true`
-- `UPDATE_TASK` : S'il faut mettre à jour les tâches asynchrones (Midjourney, Suno), la valeur par défaut est `true`
-- `GEMINI_VISION_MAX_IMAGE_NUM` : Nombre maximum d'images pour les modèles Gemini, la valeur par défaut est `16`
-- `MAX_FILE_DOWNLOAD_MB` : Taille maximale de téléchargement de fichier en Mo, la valeur par défaut est `20`
-- `CRYPTO_SECRET` : Clé de chiffrement utilisée pour chiffrer le contenu de la base de données Redis
-- `AZURE_DEFAULT_API_VERSION` : Version de l'API par défaut du canal Azure, la valeur par défaut est `2025-04-01-preview`
-- `NOTIFICATION_LIMIT_DURATION_MINUTE` : Durée de la limite de notification, la valeur par défaut est de `10` minutes
-- `NOTIFY_LIMIT_COUNT` : Nombre maximal de notifications utilisateur dans la durée spécifiée, la valeur par défaut est `2`
-- `ERROR_LOG_ENABLED=true` : S'il faut enregistrer et afficher les journaux d'erreurs, la valeur par défaut est `false`
-
-## Déploiement
-
-Pour des guides de déploiement détaillés, veuillez vous référer à [Guide d'installation-Méthodes de déploiement](https://docs.newapi.pro/installation) :
-
-> [!TIP]
-> Dernière image Docker : `calciumion/new-api:latest`
-
-### Considérations sur le déploiement multi-machines
-- La variable d'environnement `SESSION_SECRET` doit être définie, sinon l'état de connexion sera incohérent sur plusieurs machines
-- Si vous partagez Redis, `CRYPTO_SECRET` doit être défini, sinon le contenu de Redis ne pourra pas être consulté sur plusieurs machines
-
-### Exigences de déploiement
-- Base de données locale (par défaut) : SQLite (le déploiement Docker doit monter le répertoire `/data`)
-- Base de données distante : MySQL version >= 5.7.8, PgSQL version >= 9.6
-
-### Méthodes de déploiement
-
-#### Utilisation de la fonctionnalité Docker du panneau BaoTa
-Installez le panneau BaoTa (version **9.2.0** ou supérieure), recherchez **New-API** dans le magasin d'applications et installez-le.
-[Tutoriel avec des images](./docs/BT.md)
-
-#### Utilisation de Docker Compose (recommandé)
-```shell
-# Télécharger le projet
-git clone https://github.com/Calcium-Ion/new-api.git
+```bash
+# Cloner le projet
+git clone https://github.com/QuantumNous/new-api.git
 cd new-api
-# Modifier docker-compose.yml si nécessaire
-# Démarrer
+
+# Modifier la configuration docker-compose.yml
+nano docker-compose.yml
+
+# Démarrer le service
 docker-compose up -d
 ```
 
-#### Utilisation directe de l'image Docker
-```shell
-# Utilisation de SQLite
-docker run --name new-api -d --restart always -p 3000:3000 -e TZ=Asia/Shanghai -v /home/ubuntu/data/new-api:/data calciumion/new-api:latest
+<details>
+<summary><strong>Utilisation des commandes Docker</strong></summary>
+
+```bash
+# Tirer la dernière image
+docker pull calciumion/new-api:latest
+
+# Utilisation de SQLite (par défaut)
+docker run --name new-api -d --restart always \
+  -p 3000:3000 \
+  -e TZ=Asia/Shanghai \
+  -v ./data:/data \
+  calciumion/new-api:latest
 
 # Utilisation de MySQL
-docker run --name new-api -d --restart always -p 3000:3000 -e SQL_DSN="root:123456@tcp(localhost:3306)/oneapi" -e TZ=Asia/Shanghai -v /home/ubuntu/data/new-api:/data calciumion/new-api:latest
+docker run --name new-api -d --restart always \
+  -p 3000:3000 \
+  -e SQL_DSN="root:123456@tcp(localhost:3306)/oneapi" \
+  -e TZ=Asia/Shanghai \
+  -v ./data:/data \
+  calciumion/new-api:latest
 ```
 
-## Nouvelle tentative de canal et cache
-La fonctionnalité de nouvelle tentative de canal a été implémentée, vous pouvez définir le nombre de tentatives dans `Paramètres->Paramètres de fonctionnement->Paramètres généraux->Nombre de tentatives en cas d'échec`, **recommandé d'activer la fonctionnalité de mise en cache**.
+> **💡 Astuce:** `-v ./data:/data` sauvegardera les données dans le dossier `data` du répertoire actuel, vous pouvez également le changer en chemin absolu comme `-v /your/custom/path:/data`
 
-### Méthode de configuration du cache
-1. `REDIS_CONN_STRING` : Définir Redis comme cache
-2. `MEMORY_CACHE_ENABLED` : Activer le cache mémoire (pas besoin de le définir manuellement si Redis est défini)
+</details>
 
-## Documentation de l'API
+---
 
-Pour une documentation détaillée de l'API, veuillez vous référer à [Documentation de l'API](https://docs.newapi.pro/api) :
+🎉 Après le déploiement, visitez `http://localhost:3000` pour commencer à utiliser!
 
-- [API de discussion (Chat Completions)](https://docs.newapi.pro/api/openai-chat)
-- [API de réponse (Responses)](https://docs.newapi.pro/api/openai-responses)
-- [API d'image (Image)](https://docs.newapi.pro/api/openai-image)
-- [API de rerank (Rerank)](https://docs.newapi.pro/api/jinaai-rerank)
-- [API de discussion en temps réel (Realtime)](https://docs.newapi.pro/api/openai-realtime)
-- [API de discussion Claude](https://docs.newapi.pro/api/anthropic-chat)
-- [API de discussion Google Gemini](https://docs.newapi.pro/api/google-gemini-chat)
+📖 Pour plus de méthodes de déploiement, veuillez vous référer à [Guide de déploiement](https://docs.newapi.pro/en/docs/installation)
 
-## Projets connexes
-- [One API](https://github.com/songquanpeng/one-api) : Projet original
-- [Midjourney-Proxy](https://github.com/novicezk/midjourney-proxy) : Prise en charge de l'interface Midjourney
-- [neko-api-key-tool](https://github.com/Calcium-Ion/neko-api-key-tool) : Interroger le quota d'utilisation avec une clé
+---
 
-Autres projets basés sur New API :
-- [new-api-horizon](https://github.com/Calcium-Ion/new-api-horizon) : Version optimisée hautes performances de New API
+## 📚 Documentation
 
-## Aide et support
+<div align="center">
 
-Si vous avez des questions, veuillez vous référer à [Aide et support](https://docs.newapi.pro/support) :
-- [Interaction avec la communauté](https://docs.newapi.pro/support/community-interaction)
-- [Commentaires sur les problèmes](https://docs.newapi.pro/support/feedback-issues)
-- [FAQ](https://docs.newapi.pro/support/faq)
+### 📖 [Documentation officielle](https://docs.newapi.pro/en/docs) | [![Demander à DeepWiki](https://deepwiki.com/badge.svg)](https://deepwiki.com/QuantumNous/new-api)
+
+</div>
+
+**Navigation rapide:**
+
+| 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) |
+
+---
+
+## ✨ 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) |
+
+### 🎨 Fonctions principales
+
+| Fonctionnalité | Description |
+|------|------|
+| 🎨 Nouvelle interface utilisateur | Conception d'interface utilisateur moderne |
+| 🌍 Multilingue | Prend en charge le chinois, l'anglais, le français, le japonais |
+| 🔄 Compatibilité des données | Complètement compatible avec la base de données originale de One API |
+| 📈 Tableau de bord des données | Console visuelle et analyse statistique |
+| 🔒 Gestion des permissions | Regroupement de jetons, restrictions de modèles, gestion des utilisateurs |
+
+### 💰 Paiement et facturation
+
+- ✅ Recharge en ligne (EPay, Stripe)
+- ✅ Tarification des modèles de paiement à l'utilisation
+- ✅ Prise en charge de la facturation du cache (OpenAI, Azure, DeepSeek, Claude, Qwen et tous les modèles pris en charge)
+- ✅ Configuration flexible des politiques de facturation
+
+### 🔐 Autorisation et sécurité
+
+- 😈 Connexion par autorisation Discord
+- 🤖 Connexion par autorisation LinuxDO
+- 📱 Connexion par autorisation Telegram
+- 🔑 Authentification unifiée OIDC
+- 🔍 Requête de quota d'utilisation de clé (avec [neko-api-key-tool](https://github.com/Calcium-Ion/neko-api-key-tool))
+
+### 🚀 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)
+
+**Routage intelligent:**
+- ⚖️ Sélection aléatoire pondérée des canaux
+- 🔄 Nouvelle tentative automatique en cas d'échec
+- 🚦 Limitation du débit du modèle pour les utilisateurs
+
+**Conversion de format:**
+- 🔄 **OpenAI Compatible ⇄ Claude Messages**
+- 🔄 **OpenAI Compatible → Google Gemini**
+- 🔄 **Google Gemini → OpenAI Compatible** - Texte uniquement, les appels de fonction ne sont pas encore pris en charge
+- 🚧 **OpenAI Compatible ⇄ OpenAI Responses** - En développement
+- 🔄 **Fonctionnalité de la pensée au contenu**
+
+**Prise en charge de l'effort de raisonnement:**
+
+<details>
+<summary>Voir la configuration détaillée</summary>
+
+**Modèles de la série OpenAI :**
+- `o3-mini-high` - Effort de raisonnement élevé
+- `o3-mini-medium` - Effort de raisonnement moyen
+- `o3-mini-low` - Effort de raisonnement faible
+- `gpt-5-high` - Effort de raisonnement élevé
+- `gpt-5-medium` - Effort de raisonnement moyen
+- `gpt-5-low` - Effort de raisonnement faible
+
+**Modèles de pensée de Claude:**
+- `claude-3-7-sonnet-20250219-thinking` - Activer le mode de pensée
+
+**Modèles de la série Google Gemini:**
+- `gemini-2.5-flash-thinking` - Activer le mode de pensée
+- `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>
+
+---
+
+## 🤖 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)
+
+| Type de modèle | Description | Documentation |
+|---------|------|------|
+| 🤖 OpenAI-Compatible | Modèles compatibles OpenAI | [Documentation](https://docs.newapi.pro/en/docs/api/ai-model/chat/openai/createchatcompletion) |
+| 🤖 OpenAI Responses | Format OpenAI Responses | [Documentation](https://docs.newapi.pro/en/docs/api/ai-model/chat/openai/createresponse) |
+| 🎨 Midjourney-Proxy | [Midjourney-Proxy(Plus)](https://github.com/novicezk/midjourney-proxy) | [Documentation](https://doc.newapi.pro/api/midjourney-proxy-image) |
+| 🎵 Suno-API | [Suno API](https://github.com/Suno-API/Suno-API) | [Documentation](https://doc.newapi.pro/api/suno-music) |
+| 🔄 Rerank | Cohere, Jina | [Documentation](https://docs.newapi.pro/en/docs/api/ai-model/rerank/creatererank) |
+| 💬 Claude | Format Messages | [Documentation](https://docs.newapi.pro/en/docs/api/ai-model/chat/createmessage) |
+| 🌐 Gemini | Format Google Gemini | [Documentation](https://docs.newapi.pro/en/docs/api/ai-model/chat/gemini/geminirelayv1beta) |
+| 🔧 Dify | Mode ChatFlow | - |
+| 🎯 Personnalisé | Prise en charge de l'adresse d'appel complète | - |
+
+### 📡 Interfaces prises en charge
+
+<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/createchatcompletion)
+- [Interface de réponse (Responses)](https://docs.newapi.pro/en/docs/api/ai-model/chat/openai/createresponse)
+- [Interface d'image (Image)](https://docs.newapi.pro/en/docs/api/ai-model/images/openai/post-v1-images-generations)
+- [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/audio/openai/createspeech)
+- [Interface d'incorporation (Embeddings)](https://docs.newapi.pro/en/docs/api/ai-model/embeddings/createembedding)
+- [Interface de rerank (Rerank)](https://docs.newapi.pro/en/docs/api/ai-model/rerank/creatererank)
+- [Conversation en temps réel (Realtime)](https://docs.newapi.pro/en/docs/api/ai-model/realtime/createrealtimesession)
+- [Discussion Claude](https://docs.newapi.pro/en/docs/api/ai-model/chat/createmessage)
+- [Discussion Google Gemini](https://docs.newapi.pro/en/docs/api/ai-model/chat/gemini/geminirelayv1beta)
+
+</details>
+
+---
+
+## 🚢 Déploiement
+
+> [!TIP]
+> **Dernière image Docker:** `calciumion/new-api:latest`
+
+### 📋 Exigences de déploiement
+
+| Composant | Exigence |
+|------|------|
+| **Base de données locale** | SQLite (Docker doit monter le répertoire `/data`)|
+| **Base de données distante | MySQL ≥ 5.7.8 ou PostgreSQL ≥ 9.6 |
+| **Moteur de conteneur** | Docker / Docker Compose |
+
+### ⚙️ Configuration des variables d'environnement
+
+<details>
+<summary>Configuration courante des variables d'environnement</summary>
+
+| Nom de variable | Description | Valeur par défaut |
+|--------|------|--------|
+| `SESSION_SECRET` | Secret de session (requis pour le déploiement multi-machines) |
+| `CRYPTO_SECRET` | Secret de chiffrement (requis pour Redis) | - |
+| `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)
+
+</details>
+
+### 🔧 Méthodes de déploiement
+
+<details>
+<summary><strong>Méthode 1: Docker Compose (recommandé)</strong></summary>
+
+```bash
+# Cloner le projet
+git clone https://github.com/QuantumNous/new-api.git
+cd new-api
+
+# Modifier la configuration
+nano docker-compose.yml
+
+# Démarrer le service
+docker-compose up -d
+```
+
+</details>
+
+<details>
+<summary><strong>Méthode 2: Commandes Docker</strong></summary>
+
+**Utilisation de SQLite:**
+```bash
+docker run --name new-api -d --restart always \
+  -p 3000:3000 \
+  -e TZ=Asia/Shanghai \
+  -v ./data:/data \
+  calciumion/new-api:latest
+```
+
+**Utilisation de MySQL:**
+```bash
+docker run --name new-api -d --restart always \
+  -p 3000:3000 \
+  -e SQL_DSN="root:123456@tcp(localhost:3306)/oneapi" \
+  -e TZ=Asia/Shanghai \
+  -v ./data:/data \
+  calciumion/new-api:latest
+```
+
+> **💡 Explication du chemin:** 
+> - `./data:/data` - Chemin relatif, données sauvegardées dans le dossier data du répertoire actuel
+> - Vous pouvez également utiliser un chemin absolu, par exemple : `/your/custom/path:/data`
+
+</details>
+
+<details>
+<summary><strong>Méthode 3: Panneau BaoTa</strong></summary>
+
+1. Installez le panneau BaoTa (version ≥ 9.2.0)
+2. Recherchez **New-API** dans le magasin d'applications
+3. Installation en un clic
+
+📖 [Tutoriel avec des images](./docs/BT.md)
+
+</details>
+
+### ⚠️ Considérations sur le déploiement multi-machines
+
+> [!WARNING]
+> - **Doit définir** `SESSION_SECRET` - Sinon l'état de connexion sera incohérent sur plusieurs machines
+> - **Redis partagé doit définir** `CRYPTO_SECRET` - Sinon les données ne pourront pas être déchiffrées
+
+### 🔄 Nouvelle tentative de canal et cache
+
+**Configuration de la nouvelle tentative:** `Paramètres → Paramètres de fonctionnement → Paramètres généraux → Nombre de tentatives en cas d'échec`
+
+**Configuration du cache:**
+- `REDIS_CONN_STRING`: Cache Redis (recommandé)
+- `MEMORY_CACHE_ENABLED`: Cache mémoire
+
+---
+
+## 🔗 Projets connexes
+
+### Projets en amont
+
+| Projet | Description |
+|------|------|
+| [One API](https://github.com/songquanpeng/one-api) | Base du projet original |
+| [Midjourney-Proxy](https://github.com/novicezk/midjourney-proxy) | Prise en charge de l'interface Midjourney |
+
+### Outils d'accompagnement
+
+| Projet | Description |
+|------|------|
+| [neko-api-key-tool](https://github.com/Calcium-Ion/neko-api-key-tool) | Outil de recherche de quota d'utilisation avec une clé |
+| [new-api-horizon](https://github.com/Calcium-Ion/new-api-horizon) | Version optimisée haute performance de New API |
+
+---
+
+## 💬 Aide et support
+
+### 📖 Ressources de documentation
+
+| 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) |
+
+### 🤝 Guide de contribution
+
+Bienvenue à toutes les formes de contribution!
+
+- 🐛 Signaler des bogues
+- 💡 Proposer de nouvelles fonctionnalités
+- 📝 Améliorer la documentation
+- 🔧 Soumettre du code
+
+---
 
 ## 🌟 Historique des étoiles
 
-[![Graphique de l'historique des étoiles](https://api.star-history.com/svg?repos=Calcium-Ion/new-api&type=Date)](https://star-history.com/#Calcium-Ion/new-api&Date)
+<div align="center">
+
+[![Graphique de l'historique des étoiles](https://api.star-history.com/svg?repos=Calcium-Ion/new-api&type=Date)](https://star-history.com/#Calcium-Ion/new-api&Date)
+
+</div>
+
+---
+
+<div align="center">
+
+### 💖 Merci d'utiliser New API
+
+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)**
+
+<sub>Construit avec ❤️ par QuantumNous</sub>
+
+</div>

README.ja.md

@@ -1,19 +1,17 @@
-<p align="right">
-   <a href="./README.md">中文</a> | <a href="./README.en.md">English</a> | <a href="./README.fr.md">Français</a> | <strong>日本語</strong>
-</p>
-
-> [!NOTE]
-> **MT（機械翻訳）**: この文書は機械翻訳されています。最も正確な情報については、[中国語版](./README.md)を参照してください。
-
 <div align="center">
 
 ![new-api](/web/public/logo.png)
 
 # New API
 
-🍥次世代大規模モデルゲートウェイとAI資産管理システム
+🍥 **次世代大規模モデルゲートウェイとAI資産管理システム**
 
-<a href="https://trendshift.io/repositories/8227" target="_blank"><img src="https://trendshift.io/api/badge/repositories/8227" alt="Calcium-Ion%2Fnew-api | Trendshift" style="width: 250px; height: 55px;" width="250" height="55"/></a>
+<p align="center">
+  <a href="./README.zh.md">中文</a> | 
+  <a href="./README.md">English</a> | 
+  <a href="./README.fr.md">Français</a> | 
+  <strong>日本語</strong>
+</p>
 
 <p align="center">
   <a href="https://raw.githubusercontent.com/Calcium-Ion/new-api/main/LICENSE">
@@ -32,6 +30,28 @@
     <img src="https://goreportcard.com/badge/github.com/Calcium-Ion/new-api" alt="GoReportCard">
   </a>
 </p>
+
+<p align="center">
+  <a href="https://trendshift.io/repositories/8227" target="_blank">
+    <img src="https://trendshift.io/api/badge/repositories/8227" alt="Calcium-Ion%2Fnew-api | Trendshift" style="width: 250px; height: 55px;" width="250" height="55"/>
+  </a>
+  <br>
+  <a href="https://hellogithub.com/repository/QuantumNous/new-api" target="_blank">
+    <img src="https://api.hellogithub.com/v1/widgets/recommend.svg?rid=539ac4217e69431684ad4a0bab768811&claim_uid=tbFPfKIDHpc4TzR" alt="Featured｜HelloGitHub" style="width: 250px; height: 54px;" width="250" height="54" />
+  </a>
+  <a href="https://www.producthunt.com/products/new-api/launches/new-api?embed=true&utm_source=badge-featured&utm_medium=badge&utm_campaign=badge-new-api" target="_blank" rel="noopener noreferrer">
+    <img src="https://api.producthunt.com/widgets/embed-image/v1/featured.svg?post_id=1047693&theme=light&t=1769577875005" alt="New API - All-in-one AI asset management gateway. | Product Hunt" style="width: 250px; height: 54px;" width="250" height="54" />
+  </a>
+</p>
+
+<p align="center">
+  <a href="#-クイックスタート">クイックスタート</a> •
+  <a href="#-主な機能">主な機能</a> •
+  <a href="#-デプロイ">デプロイ</a> •
+  <a href="#-ドキュメント">ドキュメント</a> •
+  <a href="#-ヘルプサポート">ヘルプ</a>
+</p>
+
 </div>
 
 ## 📝 プロジェクト説明
@@ -44,183 +64,405 @@
 > - ユーザーは、OpenAIの[利用規約](https://openai.com/policies/terms-of-use)および**法律法規**を遵守する必要があり、違法な目的で使用してはいけません。
 > - [《生成式人工智能服务管理暂行办法》](http://www.cac.gov.cn/2023-07/13/c_1690898327029107.htm)の要求に従い、中国地域の公衆に未登録の生成式AI サービスを提供しないでください。
 
-<h2>🤝 信頼できるパートナー</h2>
-<p id="premium-sponsors">&nbsp;</p>
-<p align="center"><strong>順不同</strong></p>
+---
+
+## 🤝 信頼できるパートナー
+
 <p align="center">
-  <a href="https://www.cherry-ai.com/" target=_blank><img
-    src="./docs/images/cherry-studio.png" alt="Cherry Studio" height="120"
-  /></a>
-  <a href="https://bda.pku.edu.cn/" target=_blank><img
-    src="./docs/images/pku.png" alt="北京大学" height="120"
-  /></a>
-  <a href="https://www.compshare.cn/?ytag=GPU_yy_gh_newapi" target=_blank><img
-    src="./docs/images/ucloud.png" alt="UCloud 優刻得" height="120"
-  /></a>
-  <a href="https://www.aliyun.com/" target=_blank><img
-    src="./docs/images/aliyun.png" alt="Alibaba Cloud" height="120"
-  /></a>
-  <a href="https://io.net/" target=_blank><img
-    src="./docs/images/io-net.png" alt="IO.NET" height="120"
-  /></a>
+  <em>順不同</em>
 </p>
-<p>&nbsp;</p>
 
-## 📚 ドキュメント
+<p align="center">
+  <a href="https://www.cherry-ai.com/" target="_blank">
+    <img src="./docs/images/cherry-studio.png" alt="Cherry Studio" height="80" />
+  </a>
+  <a href="https://bda.pku.edu.cn/" target="_blank">
+    <img src="./docs/images/pku.png" alt="北京大学" height="80" />
+  </a>
+  <a href="https://www.compshare.cn/?ytag=GPU_yy_gh_newapi" target="_blank">
+    <img src="./docs/images/ucloud.png" alt="UCloud 優刻得" height="80" />
+  </a>
+  <a href="https://www.aliyun.com/" target="_blank">
+    <img src="./docs/images/aliyun.png" alt="Alibaba Cloud" height="80" />
+  </a>
+  <a href="https://io.net/" target="_blank">
+    <img src="./docs/images/io-net.png" alt="IO.NET" height="80" />
+  </a>
+</p>
 
-詳細なドキュメントは公式Wikiをご覧ください：[https://docs.newapi.pro/](https://docs.newapi.pro/)
+---
 
-AIが生成したDeepWikiにもアクセスできます：
-[![Ask DeepWiki](https://deepwiki.com/badge.svg)](https://deepwiki.com/QuantumNous/new-api)
+## 🙏 特別な感謝
 
-## ✨ 主な機能
+<p align="center">
+  <a href="https://www.jetbrains.com/?from=new-api" target="_blank">
+    <img src="https://resources.jetbrains.com/storage/products/company/brand/logos/jb_beam.png" alt="JetBrains Logo" width="120" />
+  </a>
+</p>
 
-New APIは豊富な機能を提供しています。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：
+<p align="center">
+  <strong>感謝 <a href="https://www.jetbrains.com/?from=new-api">JetBrains</a> が本プロジェクトに無料のオープンソース開発ライセンスを提供してくれたことに感謝します</strong>
+</p>
 
-1. 🎨 全く新しいUIインターフェース
-2. 🌍 多言語サポート
-3. 💰 オンラインチャージ機能をサポート、現在EPayとStripeをサポート
-4. 🔍 キーによる使用量クォータの照会をサポート（[neko-api-key-tool](https://github.com/Calcium-Ion/neko-api-key-tool)と連携）
-5. 🔄 オリジナルのOne APIデータベースと互換性あり
-6. 💵 モデルの従量課金をサポート
-7. ⚖️ チャネルの重み付けランダムをサポート
-8. 📈 データダッシュボード（コンソール）
-9. 🔒 トークングループ化、モデル制限
-10. 🤖 より多くの認証ログイン方法をサポート（LinuxDO、Telegram、OIDC）
-11. 🔄 Rerankモデルをサポート（CohereとJina）、[API ドキュメント](https://docs.newapi.pro/api/jinaai-rerank)
-12. ⚡ OpenAI Realtime APIをサポート（Azureチャネルを含む）、[APIドキュメント](https://docs.newapi.pro/api/openai-realtime)
-13. ⚡ **OpenAI Responses**形式をサポート、[APIドキュメント](https://docs.newapi.pro/api/openai-responses)
-14. ⚡ **Claude Messages**形式をサポート、[APIドキュメント](https://docs.newapi.pro/api/anthropic-chat)
-15. ⚡ **Google Gemini**形式をサポート、[APIドキュメント](https://docs.newapi.pro/api/google-gemini-chat/)
-16. 🧠 モデル名のサフィックスを通じてreasoning effortを設定することをサポート：
-    1. OpenAI oシリーズモデル
-        - `-high`サフィックスを追加してhigh reasoning effortに設定（例：`o3-mini-high`）
-        - `-medium`サフィックスを追加してmedium reasoning effortに設定（例：`o3-mini-medium`）
-        - `-low`サフィックスを追加してlow reasoning effortに設定（例：`o3-mini-low`）
-    2. Claude思考モデル
-        - `-thinking`サフィックスを追加して思考モードを有効にする（例：`claude-3-7-sonnet-20250219-thinking`）
-17. 🔄 思考からコンテンツへの機能
-18. 🔄 ユーザーに対するモデルレート制限機能
-19. 🔄 リクエストフォーマット変換機能、以下の3つのフォーマット変換をサポート：
-    1. OpenAI Chat Completions => Claude Messages
-    2. Claude Messages => OpenAI Chat Completions（Claude Codeがサードパーティモデルを呼び出す際に使用可能）
-    3. OpenAI Chat Completions => Gemini Chat
-20. 💰 キャッシュ課金サポート、有効にするとキャッシュがヒットした際に設定された比率で課金できます：
-    1. `システム設定-運営設定`で`プロンプトキャッシュ倍率`オプションを設定
-    2. チャネルで`プロンプトキャッシュ倍率`を設定、範囲は0-1、例えば0.5に設定するとキャッシュがヒットした際に50%で課金
-    3. サポートされているチャネル：
-        - [x] OpenAI
-        - [x] Azure
-        - [x] DeepSeek
-        - [x] Claude
+---
 
-## モデルサポート
+## 🚀 クイックスタート
 
-このバージョンは複数のモデルをサポートしています。詳細は[APIドキュメント-中継インターフェース](https://docs.newapi.pro/api)を参照してください：
+### Docker Composeを使用（推奨）
 
-1. サードパーティモデル **gpts**（gpt-4-gizmo-*）
-2. サードパーティチャネル[Midjourney-Proxy(Plus)](https://github.com/novicezk/midjourney-proxy)インターフェース、[APIドキュメント](https://docs.newapi.pro/api/midjourney-proxy-image)
-3. サードパーティチャネル[Suno API](https://github.com/Suno-API/Suno-API)インターフェース、[APIドキュメント](https://docs.newapi.pro/api/suno-music)
-4. カスタムチャネル、完全な呼び出しアドレスの入力をサポート
-5. Rerankモデル（[Cohere](https://cohere.ai/)と[Jina](https://jina.ai/)）、[APIドキュメント](https://docs.newapi.pro/api/jinaai-rerank)
-6. Claude Messages形式、[APIドキュメント](https://docs.newapi.pro/api/anthropic-chat)
-7. Google Gemini形式、[APIドキュメント](https://docs.newapi.pro/api/google-gemini-chat/)
-8. Dify、現在はchatflowのみをサポート
-9. その他のインターフェースについては[APIドキュメント](https://docs.newapi.pro/api)を参照してください
-
-## 環境変数設定
-
-詳細な設定説明については[インストールガイド-環境変数設定](https://docs.newapi.pro/installation/environment-variables)を参照してください：
-
-- `GENERATE_DEFAULT_TOKEN`：新規登録ユーザーに初期トークンを生成するかどうか、デフォルトは`false`
-- `STREAMING_TIMEOUT`：ストリーミング応答のタイムアウト時間、デフォルトは300秒
-- `DIFY_DEBUG`：Difyチャネルがワークフローとノード情報を出力するかどうか、デフォルトは`true`
-- `GET_MEDIA_TOKEN`：画像トークンを統計するかどうか、デフォルトは`true`
-- `GET_MEDIA_TOKEN_NOT_STREAM`：非ストリーミングの場合に画像トークンを統計するかどうか、デフォルトは`true`
-- `UPDATE_TASK`：非同期タスク（Midjourney、Suno）を更新するかどうか、デフォルトは`true`
-- `GEMINI_VISION_MAX_IMAGE_NUM`：Geminiモデルの最大画像数、デフォルトは`16`
-- `MAX_FILE_DOWNLOAD_MB`: 最大ファイルダウンロードサイズ、単位MB、デフォルトは`20`
-- `CRYPTO_SECRET`：暗号化キー、Redisデータベースの内容を暗号化するために使用
-- `AZURE_DEFAULT_API_VERSION`：Azureチャネルのデフォルトのバージョン、デフォルトは`2025-04-01-preview`
-- `NOTIFICATION_LIMIT_DURATION_MINUTE`：メールなどの通知制限の継続時間、デフォルトは`10`分
-- `NOTIFY_LIMIT_COUNT`：指定された継続時間内のユーザー通知の最大数、デフォルトは`2`
-- `ERROR_LOG_ENABLED=true`: エラーログを記録して表示するかどうか、デフォルトは`false`
-
-## デプロイ
-
-詳細なデプロイガイドについては[インストールガイド-デプロイ方法](https://docs.newapi.pro/installation)を参照してください：
-
-> [!TIP]
-> 最新のDockerイメージ：`calciumion/new-api:latest`  
-
-### マルチマシンデプロイの注意事項
-- 環境変数`SESSION_SECRET`を設定する必要があります。そうしないとマルチマシンデプロイ時にログイン状態が不一致になります
-- Redisを共有する場合、`CRYPTO_SECRET`を設定する必要があります。そうしないとマルチマシンデプロイ時にRedisの内容を取得できません
-
-### デプロイ要件
-- ローカルデータベース（デフォルト）：SQLite（Dockerデプロイの場合は`/data`ディレクトリをマウントする必要があります）
-- リモートデータベース：MySQLバージョン >= 5.7.8、PgSQLバージョン >= 9.6
-
-### デプロイ方法
-
-#### 宝塔パネルのDocker機能を使用してデプロイ
-宝塔パネル（**9.2.0バージョン**以上）をインストールし、アプリケーションストアで**New-API**を見つけてインストールします。
-[画像付きチュートリアル](./docs/BT.md)
-
-#### Docker Composeを使用してデプロイ（推奨）
-```shell
-# プロジェクトをダウンロード
-git clone https://github.com/Calcium-Ion/new-api.git
+```bash
+# プロジェクトをクローン
+git clone https://github.com/QuantumNous/new-api.git
 cd new-api
-# 必要に応じてdocker-compose.ymlを編集
-# 起動
+
+# docker-compose.yml 設定を編集
+nano docker-compose.yml
+
+# サービスを起動
 docker-compose up -d
 ```
 
-#### Dockerイメージを直接使用
-```shell
-# SQLiteを使用
-docker run --name new-api -d --restart always -p 3000:3000 -e TZ=Asia/Shanghai -v /home/ubuntu/data/new-api:/data calciumion/new-api:latest
+<details>
+<summary><strong>Dockerコマンドを使用</strong></summary>
+
+```bash
+# 最新のイメージをプル
+docker pull calciumion/new-api:latest
+
+# SQLiteを使用（デフォルト）
+docker run --name new-api -d --restart always \
+  -p 3000:3000 \
+  -e TZ=Asia/Shanghai \
+  -v ./data:/data \
+  calciumion/new-api:latest
 
 # MySQLを使用
-docker run --name new-api -d --restart always -p 3000:3000 -e SQL_DSN="root:123456@tcp(localhost:3306)/oneapi" -e TZ=Asia/Shanghai -v /home/ubuntu/data/new-api:/data calciumion/new-api:latest
+docker run --name new-api -d --restart always \
+  -p 3000:3000 \
+  -e SQL_DSN="root:123456@tcp(localhost:3306)/oneapi" \
+  -e TZ=Asia/Shanghai \
+  -v ./data:/data \
+  calciumion/new-api:latest
 ```
 
-## チャネルリトライとキャッシュ
-チャネルリトライ機能はすでに実装されており、`設定->運営設定->一般設定->失敗リトライ回数`でリトライ回数を設定できます。**キャッシュ機能を有効にすることを推奨します**。
+> **💡 ヒント:** `-v ./data:/data` は現在のディレクトリの `data` フォルダにデータを保存します。絶対パスに変更することもできます：`-v /your/custom/path:/data`
 
-### キャッシュ設定方法
-1. `REDIS_CONN_STRING`：Redisをキャッシュとして設定
-2. `MEMORY_CACHE_ENABLED`：メモリキャッシュを有効にする（Redisを設定した場合は手動設定不要）
+</details>
 
-## APIドキュメント
+---
 
-詳細なAPIドキュメントについては[APIドキュメント](https://docs.newapi.pro/api)を参照してください：
+🎉 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！
 
-- [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)
-- [画像インターフェース（Image）](https://docs.newapi.pro/api/openai-image)
-- [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チャットインターフェース](https://docs.newapi.pro/api/anthropic-chat)
-- [Google Geminiチャットインターフェース](https://docs.newapi.pro/api/google-gemini-chat)
+📖 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。
 
-## 関連プロジェクト
-- [One API](https://github.com/songquanpeng/one-api)：オリジナルプロジェクト
-- [Midjourney-Proxy](https://github.com/novicezk/midjourney-proxy)：Midjourneyインターフェースサポート
-- [neko-api-key-tool](https://github.com/Calcium-Ion/neko-api-key-tool)：キーを使用して使用量クォータを照会
+---
 
-New APIベースのその他のプロジェクト：
-- [new-api-horizon](https://github.com/Calcium-Ion/new-api-horizon)：New API高性能最適化版
+## 📚 ドキュメント
 
-## ヘルプサポート
+<div align="center">
 
-問題がある場合は、[ヘルプサポート](https://docs.newapi.pro/support)を参照してください：
-- [コミュニティ交流](https://docs.newapi.pro/support/community-interaction)
-- [問題のフィードバック](https://docs.newapi.pro/support/feedback-issues)
-- [よくある質問](https://docs.newapi.pro/support/faq)
+### 📖 [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)
 
-## 🌟 Star History
+</div>
 
-[![Star History Chart](https://api.star-history.com/svg?repos=Calcium-Ion/new-api&type=Date)](https://star-history.com/#Calcium-Ion/new-api&Date)
+**クイックナビゲーション:**
 
+| 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) |
+
+---
+
+## ✨ 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。
+
+### 🎨 コア機能
+
+| 機能 | 説明 |
+|------|------|
+| 🎨 新しいUI | モダンなユーザーインターフェースデザイン |
+| 🌍 多言語 | 中国語、英語、フランス語、日本語をサポート |
+| 🔄 データ互換性 | オリジナルのOne APIデータベースと完全に互換性あり |
+| 📈 データダッシュボード | ビジュアルコンソールと統計分析 |
+| 🔒 権限管理 | トークングループ化、モデル制限、ユーザー管理 |
+
+### 💰 支払いと課金
+
+- ✅ オンライン充電（EPay、Stripe）
+- ✅ モデルの従量課金
+- ✅ キャッシュ課金サポート（OpenAI、Azure、DeepSeek、Claude、Qwenなどすべてのサポートされているモデル）
+- ✅ 柔軟な課金ポリシー設定
+
+### 🔐 認証とセキュリティ
+
+- 😈 Discord認証ログイン
+- 🤖 LinuxDO認証ログイン
+- 📱 Telegram認証ログイン
+- 🔑 OIDC統一認証
+- 🔍 Key使用量クォータ照会（[neko-api-key-tool](https://github.com/Calcium-Ion/neko-api-key-tool)と併用）
+
+
+
+### 🚀 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)（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
+- 🔄 失敗自動リトライ
+- 🚦 ユーザーレベルモデルレート制限
+
+**フォーマット変換:**
+- 🔄 **OpenAI Compatible ⇄ Claude Messages**
+- 🔄 **OpenAI Compatible → Google Gemini**
+- 🔄 **Google Gemini → OpenAI Compatible** - テキストのみ、関数呼び出しはまだサポートされていません
+- 🚧 **OpenAI Compatible ⇄ OpenAI Responses** - 開発中
+- 🔄 **思考からコンテンツへの機能**
+
+**Reasoning Effort サポート:**
+
+<details>
+<summary>詳細設定を表示</summary>
+
+**OpenAIシリーズモデル:**
+- `o3-mini-high` - 高思考努力
+- `o3-mini-medium` - 中思考努力
+- `o3-mini-low` - 低思考努力
+- `gpt-5-high` - 高思考努力
+- `gpt-5-medium` - 中思考努力
+- `gpt-5-low` - 低思考努力
+
+**Claude思考モデル:**
+- `claude-3-7-sonnet-20250219-thinking` - 思考モードを有効にする
+
+**Google Geminiシリーズモデル:**
+- `gemini-2.5-flash-thinking` - 思考モードを有効にする
+- `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>
+
+---
+
+## 🤖 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)
+
+| モデルタイプ | 説明 | ドキュメント |
+|---------|------|------|
+| 🤖 OpenAI-Compatible | OpenAI互換モデル | [ドキュメント](https://docs.newapi.pro/ja/docs/api/ai-model/chat/openai/createchatcompletion) |
+| 🤖 OpenAI Responses | OpenAI Responsesフォーマット | [ドキュメント](https://docs.newapi.pro/ja/docs/api/ai-model/chat/openai/createresponse) |
+| 🎨 Midjourney-Proxy | [Midjourney-Proxy(Plus)](https://github.com/novicezk/midjourney-proxy) | [ドキュメント](https://doc.newapi.pro/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/api/suno-music) |
+| 🔄 Rerank | Cohere、Jina | [ドキュメント](https://docs.newapi.pro/ja/docs/api/ai-model/rerank/creatererank) |
+| 💬 Claude | Messagesフォーマット | [ドキュメント](https://docs.newapi.pro/ja/docs/api/ai-model/chat/createmessage) |
+| 🌐 Gemini | Google Geminiフォーマット | [ドキュメント](https://docs.newapi.pro/ja/docs/api/ai-model/chat/gemini/geminirelayv1beta) |
+| 🔧 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 | - |
+
+### 📡 サポートされているインターフェース
+
+<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/createchatcompletion)
+- [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/createresponse)
+- [イメージインターフェース (Image)](https://docs.newapi.pro/ja/docs/api/ai-model/images/openai/post-v1-images-generations)
+- [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/audio/openai/createspeech)
+- [エンベッドインターフェース (Embeddings)](https://docs.newapi.pro/ja/docs/api/ai-model/embeddings/createembedding)
+- [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/creatererank)
+- [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/createrealtimesession)
+- [Claudeチャット](https://docs.newapi.pro/ja/docs/api/ai-model/chat/createmessage)
+- [Google Geminiチャット](https://docs.newapi.pro/ja/docs/api/ai-model/chat/gemini/geminirelayv1beta)
+
+</details>
+
+---
+
+## 🚢 デプロイ
+
+> [!TIP]
+> **最新のDockerイメージ:** `calciumion/new-api:latest`
+
+### 📋 デプロイ要件
+
+| コンポーネント | 要件 |
+|------|------|
+| **ローカルデータベース** | SQLite（Dockerは `/data` ディレクトリをマウントする必要があります）|
+| **リモートデータベース** | MySQL ≥ 5.7.8 または PostgreSQL ≥ 9.6 |
+| **コンテナエンジン** | Docker / Docker Compose |
+
+### ⚙️ 環境変数設定
+
+<details>
+<summary>一般的な環境変数設定</summary>
+
+| 変数名 | 説明 | デフォルト値 |
+|--------|------|--------|
+| `SESSION_SECRET` | セッションシークレット（マルチマシンデプロイに必須） | - |
+| `CRYPTO_SECRET` | 暗号化シークレット（Redisに必須） | - |
+| `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)
+
+</details>
+
+### 🔧 デプロイ方法
+
+<details>
+<summary><strong>方法 1: Docker Compose（推奨）</strong></summary>
+
+```bash
+# プロジェクトをクローン
+git clone https://github.com/QuantumNous/new-api.git
+cd new-api
+
+# 設定を編集
+nano docker-compose.yml
+
+# サービスを起動
+docker-compose up -d
+```
+
+</details>
+
+<details>
+<summary><strong>方法 2: Dockerコマンド</strong></summary>
+
+**SQLiteを使用:**
+```bash
+docker run --name new-api -d --restart always \
+  -p 3000:3000 \
+  -e TZ=Asia/Shanghai \
+  -v ./data:/data \
+  calciumion/new-api:latest
+```
+
+**MySQLを使用:**
+```bash
+docker run --name new-api -d --restart always \
+  -p 3000:3000 \
+  -e SQL_DSN="root:123456@tcp(localhost:3306)/oneapi" \
+  -e TZ=Asia/Shanghai \
+  -v ./data:/data \
+  calciumion/new-api:latest
+```
+
+> **💡 パス説明:** 
+> - `./data:/data` - 相対パス、データは現在のディレクトリのdataフォルダに保存されます
+> - 絶対パスを使用することもできます：`/your/custom/path:/data`
+
+</details>
+
+<details>
+<summary><strong>方法 3: 宝塔パネル</strong></summary>
+
+1. 宝塔パネル（**9.2.0バージョン**以上）をインストールし、アプリケーションストアで**New-API**を検索してインストールします。
+
+📖 [画像付きチュートリアル](./docs/BT.md)
+
+</details>
+
+### ⚠️ マルチマシンデプロイの注意事項
+
+> [!WARNING]
+> - **必ず設定する必要があります** `SESSION_SECRET` - そうしないとマルチマシンデプロイ時にログイン状態が不一致になります
+> - **共有Redisは必ず設定する必要があります** `CRYPTO_SECRET` - そうしないとデータを復号化できません
+
+### 🔄 チャネルリトライとキャッシュ
+
+**リトライ設定:** `設定 → 運営設定 → 一般設定 → 失敗リトライ回数`
+
+**キャッシュ設定:**
+- `REDIS_CONN_STRING`：Redisキャッシュ（推奨）
+- `MEMORY_CACHE_ENABLED`：メモリキャッシュ
+
+---
+
+## 🔗 関連プロジェクト
+
+### 上流プロジェクト
+
+| プロジェクト | 説明 |
+|------|------|
+| [One API](https://github.com/songquanpeng/one-api) | オリジナルプロジェクトベース |
+| [Midjourney-Proxy](https://github.com/novicezk/midjourney-proxy) | Midjourneyインターフェースサポート |
+
+### 補助ツール
+
+| プロジェクト | 説明 |
+|------|------|
+| [neko-api-key-tool](https://github.com/Calcium-Ion/neko-api-key-tool) | キー使用量クォータ照会ツール |
+| [new-api-horizon](https://github.com/Calcium-Ion/new-api-horizon) | New API高性能最適化版 |
+
+---
+
+## 💬 ヘルプサポート
+
+### 📖 ドキュメントリソース
+
+| 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) |
+
+### 🤝 貢献ガイド
+
+あらゆる形の貢献を歓迎します！
+
+- 🐛 バグを報告する
+- 💡 新しい機能を提案する
+- 📝 ドキュメントを改善する
+- 🔧 コードを提出する
+
+---
+
+## 🌟 スター履歴
+
+<div align="center">
+
+[![スター履歴チャート](https://api.star-history.com/svg?repos=Calcium-Ion/new-api&type=Date)](https://star-history.com/#Calcium-Ion/new-api&Date)
+
+</div>
+
+---
+
+<div align="center">
+
+### 💖 New APIをご利用いただきありがとうございます
+
+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)**
+
+<sub>❤️ で構築された QuantumNous</sub>
+
+</div>

README.md

@@ -1,15 +1,17 @@
-<p align="right">
-   <strong>中文</strong> | <a href="./README.en.md">English</a> | <a href="./README.fr.md">Français</a> | <a href="./README.ja.md">日本語</a>
-</p>
 <div align="center">
 
 ![new-api](/web/public/logo.png)
 
 # New API
 
-🍥新一代大模型网关与AI资产管理系统
+🍥 **Next-Generation LLM Gateway and AI Asset Management System**
 
-<a href="https://trendshift.io/repositories/8227" target="_blank"><img src="https://trendshift.io/api/badge/repositories/8227" alt="Calcium-Ion%2Fnew-api | Trendshift" style="width: 250px; height: 55px;" width="250" height="55"/></a>
+<p align="center">
+  <a href="./README.zh.md">中文</a> | 
+  <strong>English</strong> | 
+  <a href="./README.fr.md">Français</a> | 
+  <a href="./README.ja.md">日本語</a>
+</p>
 
 <p align="center">
   <a href="https://raw.githubusercontent.com/Calcium-Ion/new-api/main/LICENSE">
@@ -28,200 +30,439 @@
     <img src="https://goreportcard.com/badge/github.com/Calcium-Ion/new-api" alt="GoReportCard">
   </a>
 </p>
+
+<p align="center">
+  <a href="https://trendshift.io/repositories/8227" target="_blank">
+    <img src="https://trendshift.io/api/badge/repositories/8227" alt="Calcium-Ion%2Fnew-api | Trendshift" style="width: 250px; height: 55px;" width="250" height="55"/>
+  </a>
+  <br>
+  <a href="https://hellogithub.com/repository/QuantumNous/new-api" target="_blank">
+    <img src="https://api.hellogithub.com/v1/widgets/recommend.svg?rid=539ac4217e69431684ad4a0bab768811&claim_uid=tbFPfKIDHpc4TzR" alt="Featured｜HelloGitHub" style="width: 250px; height: 54px;" width="250" height="54" />
+  </a>
+  <a href="https://www.producthunt.com/products/new-api/launches/new-api?embed=true&utm_source=badge-featured&utm_medium=badge&utm_campaign=badge-new-api" target="_blank" rel="noopener noreferrer">
+    <img src="https://api.producthunt.com/widgets/embed-image/v1/featured.svg?post_id=1047693&theme=light&t=1769577875005" alt="New API - All-in-one AI asset management gateway. | Product Hunt" style="width: 250px; height: 54px;" width="250" height="54" />
+  </a>
+</p>
+
+<p align="center">
+  <a href="#-quick-start">Quick Start</a> •
+  <a href="#-key-features">Key Features</a> •
+  <a href="#-deployment">Deployment</a> •
+  <a href="#-documentation">Documentation</a> •
+  <a href="#-help-support">Help</a>
+</p>
+
 </div>
 
-## 📝 项目说明
+## 📝 Project Description
 
 > [!NOTE]  
-> 本项目为开源项目，在[One API](https://github.com/songquanpeng/one-api)的基础上进行二次开发
+> This is an open-source project developed based on [One API](https://github.com/songquanpeng/one-api)
 
 > [!IMPORTANT]  
-> - 本项目仅供个人学习使用，不保证稳定性，且不提供任何技术支持。
-> - 使用者必须在遵循 OpenAI 的[使用条款](https://openai.com/policies/terms-of-use)以及**法律法规**的情况下使用，不得用于非法用途。
-> - 根据[《生成式人工智能服务管理暂行办法》](http://www.cac.gov.cn/2023-07/13/c_1690898327029107.htm)的要求，请勿对中国地区公众提供一切未经备案的生成式人工智能服务。
+> - This project is for personal learning purposes only, with no guarantee of stability or technical support
+> - Users must comply with OpenAI's [Terms of Use](https://openai.com/policies/terms-of-use) and **applicable laws and regulations**, and must not use it for illegal purposes
+> - According to the [《Interim Measures for the Management of Generative Artificial Intelligence Services》](http://www.cac.gov.cn/2023-07/13/c_1690898327029107.htm), please do not provide any unregistered generative AI services to the public in China.
+
+---
+
+## 🤝 Trusted Partners
 
-<h2>🤝 我们信任的合作伙伴</h2>
-<p id="premium-sponsors">&nbsp;</p>
-<p align="center"><strong>排名不分先后</strong></p>
 <p align="center">
-  <a href="https://www.cherry-ai.com/" target=_blank><img
-    src="./docs/images/cherry-studio.png" alt="Cherry Studio" height="120"
-  /></a>
-  <a href="https://bda.pku.edu.cn/" target=_blank><img
-    src="./docs/images/pku.png" alt="北京大学" height="120"
-  /></a>
-  <a href="https://www.compshare.cn/?ytag=GPU_yy_gh_newapi" target=_blank><img
-    src="./docs/images/ucloud.png" alt="UCloud 优刻得" height="120"
-  /></a>
-  <a href="https://www.aliyun.com/" target=_blank><img
-    src="./docs/images/aliyun.png" alt="阿里云" height="120"
-  /></a>
-  <a href="https://io.net/" target=_blank><img
-    src="./docs/images/io-net.png" alt="IO.NET" height="120"
-  /></a>
+  <em>No particular order</em>
 </p>
-<p>&nbsp;</p>
 
-## 📚 文档
+<p align="center">
+  <a href="https://www.cherry-ai.com/" target="_blank">
+    <img src="./docs/images/cherry-studio.png" alt="Cherry Studio" height="80" />
+  </a>
+  <a href="https://bda.pku.edu.cn/" target="_blank">
+    <img src="./docs/images/pku.png" alt="Peking University" height="80" />
+  </a>
+  <a href="https://www.compshare.cn/?ytag=GPU_yy_gh_newapi" target="_blank">
+    <img src="./docs/images/ucloud.png" alt="UCloud" height="80" />
+  </a>
+  <a href="https://www.aliyun.com/" target="_blank">
+    <img src="./docs/images/aliyun.png" alt="Alibaba Cloud" height="80" />
+  </a>
+  <a href="https://io.net/" target="_blank">
+    <img src="./docs/images/io-net.png" alt="IO.NET" height="80" />
+  </a>
+</p>
 
-详细文档请访问我们的官方Wiki：[https://docs.newapi.pro/](https://docs.newapi.pro/)
+---
 
-也可访问AI生成的DeepWiki:
-[![Ask DeepWiki](https://deepwiki.com/badge.svg)](https://deepwiki.com/QuantumNous/new-api)
+## 🙏 Special Thanks
 
-## ✨ 主要特性
+<p align="center">
+  <a href="https://www.jetbrains.com/?from=new-api" target="_blank">
+    <img src="https://resources.jetbrains.com/storage/products/company/brand/logos/jb_beam.png" alt="JetBrains Logo" width="120" />
+  </a>
+</p>
 
-New API提供了丰富的功能，详细特性请参考[特性说明](https://docs.newapi.pro/wiki/features-introduction)：
+<p align="center">
+  <strong>Thanks to <a href="https://www.jetbrains.com/?from=new-api">JetBrains</a> for providing free open-source development license for this project</strong>
+</p>
 
-1. 🎨 全新的UI界面
-2. 🌍 多语言支持
-3. 💰 支持在线充值功能，当前支持易支付和Stripe
-4. 🔍 支持用key查询使用额度（配合[neko-api-key-tool](https://github.com/Calcium-Ion/neko-api-key-tool)）
-5. 🔄 兼容原版One API的数据库
-6. 💵 支持模型按次数收费
-7. ⚖️ 支持渠道加权随机
-8. 📈 数据看板（控制台）
-9. 🔒 令牌分组、模型限制
-10. 🤖 支持更多授权登陆方式（LinuxDO,Telegram、OIDC）
-11. 🔄 支持Rerank模型（Cohere和Jina），[接口文档](https://docs.newapi.pro/api/jinaai-rerank)
-12. ⚡ 支持OpenAI Realtime API（包括Azure渠道），[接口文档](https://docs.newapi.pro/api/openai-realtime)
-13. ⚡ 支持 **OpenAI Responses** 格式，[接口文档](https://docs.newapi.pro/api/openai-responses)
-14. ⚡ 支持 **Claude Messages** 格式，[接口文档](https://docs.newapi.pro/api/anthropic-chat)
-15. ⚡ 支持 **Google Gemini** 格式，[接口文档](https://docs.newapi.pro/api/google-gemini-chat/)
-16. 🧠 支持通过模型名称后缀设置 reasoning effort：
-    1. OpenAI o系列模型
-        - 添加后缀 `-high` 设置为 high reasoning effort (例如: `o3-mini-high`)
-        - 添加后缀 `-medium` 设置为 medium reasoning effort (例如: `o3-mini-medium`)
-        - 添加后缀 `-low` 设置为 low reasoning effort (例如: `o3-mini-low`)
-    2. Claude 思考模型
-        - 添加后缀 `-thinking` 启用思考模式 (例如: `claude-3-7-sonnet-20250219-thinking`)
-17. 🔄 思考转内容功能
-18. 🔄 针对用户的模型限流功能
-19. 🔄 请求格式转换功能，支持以下三种格式转换：
-    1. OpenAI Chat Completions => Claude Messages （OpenAI格式调用Claude模型）
-    2. Clade Messages => OpenAI Chat Completions (可用于Claude Code调用第三方模型)
-    3. OpenAI Chat Completions => Gemini Chat （OpenAI格式调用Gemini模型）
-20. 💰 缓存计费支持，开启后可以在缓存命中时按照设定的比例计费：
-    1. 在 `系统设置-运营设置` 中设置 `提示缓存倍率` 选项
-    2. 在渠道中设置 `提示缓存倍率`，范围 0-1，例如设置为 0.5 表示缓存命中时按照 50% 计费
-    3. 支持的渠道：
-        - [x] OpenAI
-        - [x] Azure
-        - [x] DeepSeek
-        - [x] Claude
+---
 
-## 模型支持
+## 🚀 Quick Start
 
-此版本支持多种模型，详情请参考[接口文档-中继接口](https://docs.newapi.pro/api)：
+### Using Docker Compose (Recommended)
 
-1. 第三方模型 **gpts** （gpt-4-gizmo-*）
-2. 第三方渠道[Midjourney-Proxy(Plus)](https://github.com/novicezk/midjourney-proxy)接口，[接口文档](https://docs.newapi.pro/api/midjourney-proxy-image)
-3. 第三方渠道[Suno API](https://github.com/Suno-API/Suno-API)接口，[接口文档](https://docs.newapi.pro/api/suno-music)
-4. 自定义渠道，支持填入完整调用地址
-5. Rerank模型（[Cohere](https://cohere.ai/)和[Jina](https://jina.ai/)），[接口文档](https://docs.newapi.pro/api/jinaai-rerank)
-6. Claude Messages 格式，[接口文档](https://docs.newapi.pro/api/anthropic-chat)
-7. Google Gemini格式，[接口文档](https://docs.newapi.pro/api/google-gemini-chat/)
-8. Dify，当前仅支持chatflow
-9. 更多接口请参考[接口文档](https://docs.newapi.pro/api)
-
-## 环境变量配置
-
-详细配置说明请参考[安装指南-环境变量配置](https://docs.newapi.pro/installation/environment-variables)：
-
-- `GENERATE_DEFAULT_TOKEN`：是否为新注册用户生成初始令牌，默认为 `false`
-- `STREAMING_TIMEOUT`：流式回复超时时间，默认300秒
-- `DIFY_DEBUG`：Dify渠道是否输出工作流和节点信息，默认 `true`
-- `GET_MEDIA_TOKEN`：是否统计图片token，默认 `true`
-- `GET_MEDIA_TOKEN_NOT_STREAM`：非流情况下是否统计图片token，默认 `true`
-- `UPDATE_TASK`：是否更新异步任务（Midjourney、Suno），默认 `true`
-- `GEMINI_VISION_MAX_IMAGE_NUM`：Gemini模型最大图片数量，默认 `16`
-- `MAX_FILE_DOWNLOAD_MB`: 最大文件下载大小，单位MB，默认 `20`
-- `CRYPTO_SECRET`：加密密钥，用于加密Redis数据库内容
-- `AZURE_DEFAULT_API_VERSION`：Azure渠道默认API版本，默认 `2025-04-01-preview`
-- `NOTIFICATION_LIMIT_DURATION_MINUTE`：邮件等通知限制持续时间，默认 `10`分钟
-- `NOTIFY_LIMIT_COUNT`：用户通知在指定持续时间内的最大数量，默认 `2`
-- `ERROR_LOG_ENABLED=true`: 是否记录并显示错误日志，默认`false`
-
-## 部署
-
-详细部署指南请参考[安装指南-部署方式](https://docs.newapi.pro/installation)：
-
-> [!TIP]
-> 最新版Docker镜像：`calciumion/new-api:latest`  
-
-### 多机部署注意事项
-- 必须设置环境变量 `SESSION_SECRET`，否则会导致多机部署时登录状态不一致
-- 如果公用Redis，必须设置 `CRYPTO_SECRET`，否则会导致多机部署时Redis内容无法获取
-
-### 部署要求
-- 本地数据库（默认）：SQLite（Docker部署必须挂载`/data`目录）
-- 远程数据库：MySQL版本 >= 5.7.8，PgSQL版本 >= 9.6
-
-### 部署方式
-
-#### 使用宝塔面板Docker功能部署
-安装宝塔面板（**9.2.0版本**及以上），在应用商店中找到**New-API**安装即可。
-[图文教程](./docs/BT.md)
-
-#### 使用Docker Compose部署（推荐）
-```shell
-# 下载项目源码
+```bash
+# Clone the project
 git clone https://github.com/QuantumNous/new-api.git
-
-# 进入项目目录
 cd new-api
 
-# 根据需要编辑 docker-compose.yml 文件
-# 使用nano编辑器
+# Edit docker-compose.yml configuration
 nano docker-compose.yml
-# 或使用vim编辑器
-# vim docker-compose.yml
 
+# Start the service
+docker-compose up -d
 ```
 
-#### 直接使用Docker镜像
-```shell
-# 使用SQLite
-docker run --name new-api -d --restart always -p 3000:3000 -e TZ=Asia/Shanghai -v /home/ubuntu/data/new-api:/data calciumion/new-api:latest
+<details>
+<summary><strong>Using Docker Commands</strong></summary>
 
-# 使用MySQL
-docker run --name new-api -d --restart always -p 3000:3000 -e SQL_DSN="root:123456@tcp(localhost:3306)/oneapi" -e TZ=Asia/Shanghai -v /home/ubuntu/data/new-api:/data calciumion/new-api:latest
+```bash
+# Pull the latest image
+docker pull calciumion/new-api:latest
+
+# Using SQLite (default)
+docker run --name new-api -d --restart always \
+  -p 3000:3000 \
+  -e TZ=Asia/Shanghai \
+  -v ./data:/data \
+  calciumion/new-api:latest
+
+# Using MySQL
+docker run --name new-api -d --restart always \
+  -p 3000:3000 \
+  -e SQL_DSN="root:123456@tcp(localhost:3306)/oneapi" \
+  -e TZ=Asia/Shanghai \
+  -v ./data:/data \
+  calciumion/new-api:latest
 ```
 
-## 渠道重试与缓存
-渠道重试功能已经实现，可以在`设置->运营设置->通用设置->失败重试次数`设置重试次数，**建议开启缓存**功能。
+> **💡 Tip:** `-v ./data:/data` will save data in the `data` folder of the current directory, you can also change it to an absolute path like `-v /your/custom/path:/data`
 
-### 缓存设置方法
-1. `REDIS_CONN_STRING`：设置Redis作为缓存
-2. `MEMORY_CACHE_ENABLED`：启用内存缓存（设置了Redis则无需手动设置）
+</details>
 
-## 接口文档
+---
 
-详细接口文档请参考[接口文档](https://docs.newapi.pro/api)：
+🎉 After deployment is complete, visit `http://localhost:3000` to start using!
 
-- [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)
-- [重排序接口（Rerank）](https://docs.newapi.pro/api/jinaai-rerank)
-- [实时对话接口（Realtime）](https://docs.newapi.pro/api/openai-realtime)
-- [Claude聊天接口](https://docs.newapi.pro/api/anthropic-chat)
-- [Google Gemini聊天接口](https://docs.newapi.pro/api/google-gemini-chat)
+📖 For more deployment methods, please refer to [Deployment Guide](https://docs.newapi.pro/en/docs/installation)
 
-## 相关项目
-- [One API](https://github.com/songquanpeng/one-api)：原版项目
-- [Midjourney-Proxy](https://github.com/novicezk/midjourney-proxy)：Midjourney接口支持
-- [neko-api-key-tool](https://github.com/Calcium-Ion/neko-api-key-tool)：用key查询使用额度
+---
 
-其他基于New API的项目：
-- [new-api-horizon](https://github.com/Calcium-Ion/new-api-horizon)：New API高性能优化版
+## 📚 Documentation
 
-## 帮助支持
+<div align="center">
 
-如有问题，请参考[帮助支持](https://docs.newapi.pro/support)：
-- [社区交流](https://docs.newapi.pro/support/community-interaction)
-- [反馈问题](https://docs.newapi.pro/support/feedback-issues)
-- [常见问题](https://docs.newapi.pro/support/faq)
+### 📖 [Official Documentation](https://docs.newapi.pro/en/docs) | [![Ask DeepWiki](https://deepwiki.com/badge.svg)](https://deepwiki.com/QuantumNous/new-api)
+
+</div>
+
+**Quick Navigation:**
+
+| 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) |
+
+---
+
+## ✨ Key Features
+
+> For detailed features, please refer to [Features Introduction](https://docs.newapi.pro/en/docs/guide/wiki/basic-concepts/features-introduction)
+
+### 🎨 Core Functions
+
+| Feature | Description |
+|------|------|
+| 🎨 New UI | Modern user interface design |
+| 🌍 Multi-language | Supports Chinese, English, French, Japanese |
+| 🔄 Data Compatibility | Fully compatible with the original One API database |
+| 📈 Data Dashboard | Visual console and statistical analysis |
+| 🔒 Permission Management | Token grouping, model restrictions, user management |
+
+### 💰 Payment and Billing
+
+- ✅ Online recharge (EPay, Stripe)
+- ✅ Pay-per-use model pricing
+- ✅ Cache billing support (OpenAI, Azure, DeepSeek, Claude, Qwen and all supported models)
+- ✅ Flexible billing policy configuration
+
+### 🔐 Authorization and Security
+
+- 😈 Discord authorization login
+- 🤖 LinuxDO authorization login
+- 📱 Telegram authorization login
+- 🔑 OIDC unified authentication
+- 🔍 Key quota query usage (with [neko-api-key-tool](https://github.com/Calcium-Ion/neko-api-key-tool))
+
+### 🚀 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)
+
+**Intelligent Routing:**
+- ⚖️ Channel weighted random
+- 🔄 Automatic retry on failure
+- 🚦 User-level model rate limiting
+
+**Format Conversion:**
+- 🔄 **OpenAI Compatible ⇄ Claude Messages**
+- 🔄 **OpenAI Compatible → Google Gemini**
+- 🔄 **Google Gemini → OpenAI Compatible** - Text only, function calling not supported yet
+- 🚧 **OpenAI Compatible ⇄ OpenAI Responses** - In development
+- 🔄 **Thinking-to-content functionality**
+
+**Reasoning Effort Support:**
+
+<details>
+<summary>View detailed configuration</summary>
+
+**OpenAI series models:**
+- `o3-mini-high` - High reasoning effort
+- `o3-mini-medium` - Medium reasoning effort
+- `o3-mini-low` - Low reasoning effort
+- `gpt-5-high` - High reasoning effort
+- `gpt-5-medium` - Medium reasoning effort
+- `gpt-5-low` - Low reasoning effort
+
+**Claude thinking models:**
+- `claude-3-7-sonnet-20250219-thinking` - Enable thinking mode
+
+**Google Gemini series models:**
+- `gemini-2.5-flash-thinking` - Enable thinking mode
+- `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>
+
+---
+
+## 🤖 Model Support
+
+> For details, please refer to [API Documentation - Relay Interface](https://docs.newapi.pro/en/docs/api)
+
+| Model Type | Description | Documentation |
+|---------|------|------|
+| 🤖 OpenAI-Compatible | OpenAI compatible models | [Documentation](https://docs.newapi.pro/en/docs/api/ai-model/chat/openai/createchatcompletion) |
+| 🤖 OpenAI Responses | OpenAI Responses format | [Documentation](https://docs.newapi.pro/en/docs/api/ai-model/chat/openai/createresponse) |
+| 🎨 Midjourney-Proxy | [Midjourney-Proxy(Plus)](https://github.com/novicezk/midjourney-proxy) | [Documentation](https://doc.newapi.pro/api/midjourney-proxy-image) |
+| 🎵 Suno-API | [Suno API](https://github.com/Suno-API/Suno-API) | [Documentation](https://doc.newapi.pro/api/suno-music) |
+| 🔄 Rerank | Cohere, Jina | [Documentation](https://docs.newapi.pro/en/docs/api/ai-model/rerank/creatererank) |
+| 💬 Claude | Messages format | [Documentation](https://docs.newapi.pro/en/docs/api/ai-model/chat/createmessage) |
+| 🌐 Gemini | Google Gemini format | [Documentation](https://docs.newapi.pro/en/docs/api/ai-model/chat/gemini/geminirelayv1beta) |
+| 🔧 Dify | ChatFlow mode | - |
+| 🎯 Custom | Supports complete call address | - |
+
+### 📡 Supported Interfaces
+
+<details>
+<summary>View complete interface list</summary>
+
+- [Chat Interface (Chat Completions)](https://docs.newapi.pro/en/docs/api/ai-model/chat/openai/createchatcompletion)
+- [Response Interface (Responses)](https://docs.newapi.pro/en/docs/api/ai-model/chat/openai/createresponse)
+- [Image Interface (Image)](https://docs.newapi.pro/en/docs/api/ai-model/images/openai/post-v1-images-generations)
+- [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/audio/openai/createspeech)
+- [Embedding Interface (Embeddings)](https://docs.newapi.pro/en/docs/api/ai-model/embeddings/createembedding)
+- [Rerank Interface (Rerank)](https://docs.newapi.pro/en/docs/api/ai-model/rerank/creatererank)
+- [Realtime Conversation (Realtime)](https://docs.newapi.pro/en/docs/api/ai-model/realtime/createrealtimesession)
+- [Claude Chat](https://docs.newapi.pro/en/docs/api/ai-model/chat/createmessage)
+- [Google Gemini Chat](https://docs.newapi.pro/en/docs/api/ai-model/chat/gemini/geminirelayv1beta)
+
+</details>
+
+---
+
+## 🚢 Deployment
+
+> [!TIP]
+> **Latest Docker image:** `calciumion/new-api:latest`
+
+### 📋 Deployment Requirements
+
+| Component | Requirement |
+|------|------|
+| **Local database** | SQLite (Docker must mount `/data` directory)|
+| **Remote database** | MySQL ≥ 5.7.8 or PostgreSQL ≥ 9.6 |
+| **Container engine** | Docker / Docker Compose |
+
+### ⚙️ Environment Variable Configuration
+
+<details>
+<summary>Common environment variable configuration</summary>
+
+| Variable Name | Description | Default Value |
+|--------|------|--------|
+| `SESSION_SECRET` | Session secret (required for multi-machine deployment) | - |
+| `CRYPTO_SECRET` | Encryption secret (required for Redis) | - |
+| `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)
+
+</details>
+
+### 🔧 Deployment Methods
+
+<details>
+<summary><strong>Method 1: Docker Compose (Recommended)</strong></summary>
+
+```bash
+# Clone the project
+git clone https://github.com/QuantumNous/new-api.git
+cd new-api
+
+# Edit configuration
+nano docker-compose.yml
+
+# Start service
+docker-compose up -d
+```
+
+</details>
+
+<details>
+<summary><strong>Method 2: Docker Commands</strong></summary>
+
+**Using SQLite:**
+```bash
+docker run --name new-api -d --restart always \
+  -p 3000:3000 \
+  -e TZ=Asia/Shanghai \
+  -v ./data:/data \
+  calciumion/new-api:latest
+```
+
+**Using MySQL:**
+```bash
+docker run --name new-api -d --restart always \
+  -p 3000:3000 \
+  -e SQL_DSN="root:123456@tcp(localhost:3306)/oneapi" \
+  -e TZ=Asia/Shanghai \
+  -v ./data:/data \
+  calciumion/new-api:latest
+```
+
+> **💡 Path explanation:** 
+> - `./data:/data` - Relative path, data saved in the data folder of the current directory
+> - You can also use absolute path, e.g.: `/your/custom/path:/data`
+
+</details>
+
+<details>
+<summary><strong>Method 3: BaoTa Panel</strong></summary>
+
+1. Install BaoTa Panel (≥ 9.2.0 version)
+2. Search for **New-API** in the application store
+3. One-click installation
+
+📖 [Tutorial with images](./docs/BT.md)
+
+</details>
+
+### ⚠️ Multi-machine Deployment Considerations
+
+> [!WARNING]
+> - **Must set** `SESSION_SECRET` - Otherwise login status inconsistent
+> - **Shared Redis must set** `CRYPTO_SECRET` - Otherwise data cannot be decrypted
+
+### 🔄 Channel Retry and Cache
+
+**Retry configuration:** `Settings → Operation Settings → General Settings → Failure Retry Count`
+
+**Cache configuration:**
+- `REDIS_CONN_STRING`: Redis cache (recommended)
+- `MEMORY_CACHE_ENABLED`: Memory cache
+
+---
+
+## 🔗 Related Projects
+
+### Upstream Projects
+
+| Project | Description |
+|------|------|
+| [One API](https://github.com/songquanpeng/one-api) | Original project base |
+| [Midjourney-Proxy](https://github.com/novicezk/midjourney-proxy) | Midjourney interface support |
+
+### Supporting Tools
+
+| Project | Description |
+|------|------|
+| [neko-api-key-tool](https://github.com/Calcium-Ion/neko-api-key-tool) | Key quota query tool |
+| [new-api-horizon](https://github.com/Calcium-Ion/new-api-horizon) | New API high-performance optimized version |
+
+---
+
+## 💬 Help Support
+
+### 📖 Documentation Resources
+
+| 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) |
+
+### 🤝 Contribution Guide
+
+Welcome all forms of contribution!
+
+- 🐛 Report Bugs
+- 💡 Propose New Features
+- 📝 Improve Documentation
+- 🔧 Submit Code
+
+---
 
 ## 🌟 Star History
 
+<div align="center">
+
 [![Star History Chart](https://api.star-history.com/svg?repos=Calcium-Ion/new-api&type=Date)](https://star-history.com/#Calcium-Ion/new-api&Date)
+
+</div>
+
+---
+
+<div align="center">
+
+### 💖 Thank you for using New API
+
+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)**
+
+<sub>Built with ❤️ by QuantumNous</sub>
+
+</div>

README.zh.md

@@ -0,0 +1,468 @@
+<div align="center">
+
+![new-api](/web/public/logo.png)
+
+# New API
+
+🍥 **新一代大模型网关与AI资产管理系统**
+
+<p align="center">
+  <strong>中文</strong> | 
+  <a href="./README.md">English</a> | 
+  <a href="./README.fr.md">Français</a> | 
+  <a href="./README.ja.md">日本語</a>
+</p>
+
+<p align="center">
+  <a href="https://raw.githubusercontent.com/Calcium-Ion/new-api/main/LICENSE">
+    <img src="https://img.shields.io/github/license/Calcium-Ion/new-api?color=brightgreen" alt="license">
+  </a>
+  <a href="https://github.com/Calcium-Ion/new-api/releases/latest">
+    <img src="https://img.shields.io/github/v/release/Calcium-Ion/new-api?color=brightgreen&include_prereleases" alt="release">
+  </a>
+  <a href="https://github.com/users/Calcium-Ion/packages/container/package/new-api">
+    <img src="https://img.shields.io/badge/docker-ghcr.io-blue" alt="docker">
+  </a>
+  <a href="https://hub.docker.com/r/CalciumIon/new-api">
+    <img src="https://img.shields.io/badge/docker-dockerHub-blue" alt="docker">
+  </a>
+  <a href="https://goreportcard.com/report/github.com/Calcium-Ion/new-api">
+    <img src="https://goreportcard.com/badge/github.com/Calcium-Ion/new-api" alt="GoReportCard">
+  </a>
+</p>
+
+<p align="center">
+  <a href="https://trendshift.io/repositories/8227" target="_blank">
+    <img src="https://trendshift.io/api/badge/repositories/8227" alt="Calcium-Ion%2Fnew-api | Trendshift" style="width: 250px; height: 55px;" width="250" height="55"/>
+  </a>
+  <br>
+  <a href="https://hellogithub.com/repository/QuantumNous/new-api" target="_blank">
+    <img src="https://api.hellogithub.com/v1/widgets/recommend.svg?rid=539ac4217e69431684ad4a0bab768811&claim_uid=tbFPfKIDHpc4TzR" alt="Featured｜HelloGitHub" style="width: 250px; height: 54px;" width="250" height="54" />
+  </a>
+  <a href="https://www.producthunt.com/products/new-api/launches/new-api?embed=true&utm_source=badge-featured&utm_medium=badge&utm_campaign=badge-new-api" target="_blank" rel="noopener noreferrer">
+    <img src="https://api.producthunt.com/widgets/embed-image/v1/featured.svg?post_id=1047693&theme=light&t=1769577875005" alt="New API - All-in-one AI asset management gateway. | Product Hunt" style="width: 250px; height: 54px;" width="250" height="54" />
+  </a>
+</p>
+
+<p align="center">
+  <a href="#-快速开始">快速开始</a> •
+  <a href="#-主要特性">主要特性</a> •
+  <a href="#-部署">部署</a> •
+  <a href="#-文档">文档</a> •
+  <a href="#-帮助支持">帮助</a>
+</p>
+
+</div>
+
+## 📝 项目说明
+
+> [!NOTE]  
+> 本项目为开源项目，在 [One API](https://github.com/songquanpeng/one-api) 的基础上进行二次开发
+
+> [!IMPORTANT]  
+> - 本项目仅供个人学习使用，不保证稳定性，且不提供任何技术支持
+> - 使用者必须在遵循 OpenAI 的 [使用条款](https://openai.com/policies/terms-of-use) 以及**法律法规**的情况下使用，不得用于非法用途
+> - 根据 [《生成式人工智能服务管理暂行办法》](http://www.cac.gov.cn/2023-07/13/c_1690898327029107.htm) 的要求，请勿对中国地区公众提供一切未经备案的生成式人工智能服务
+
+---
+
+## 🤝 我们信任的合作伙伴
+
+<p align="center">
+  <em>排名不分先后</em>
+</p>
+
+<p align="center">
+  <a href="https://www.cherry-ai.com/" target="_blank">
+    <img src="./docs/images/cherry-studio.png" alt="Cherry Studio" height="80" />
+  </a>
+  <a href="https://bda.pku.edu.cn/" target="_blank">
+    <img src="./docs/images/pku.png" alt="北京大学" height="80" />
+  </a>
+  <a href="https://www.compshare.cn/?ytag=GPU_yy_gh_newapi" target="_blank">
+    <img src="./docs/images/ucloud.png" alt="UCloud 优刻得" height="80" />
+  </a>
+  <a href="https://www.aliyun.com/" target="_blank">
+    <img src="./docs/images/aliyun.png" alt="阿里云" height="80" />
+  </a>
+  <a href="https://io.net/" target="_blank">
+    <img src="./docs/images/io-net.png" alt="IO.NET" height="80" />
+  </a>
+</p>
+
+---
+
+## 🙏 特别鸣谢
+
+<p align="center">
+  <a href="https://www.jetbrains.com/?from=new-api" target="_blank">
+    <img src="https://resources.jetbrains.com/storage/products/company/brand/logos/jb_beam.png" alt="JetBrains Logo" width="120" />
+  </a>
+</p>
+
+<p align="center">
+  <strong>感谢 <a href="https://www.jetbrains.com/?from=new-api">JetBrains</a> 为本项目提供免费的开源开发许可证</strong>
+</p>
+
+---
+
+## 🚀 快速开始
+
+### 使用 Docker Compose（推荐）
+
+```bash
+# 克隆项目
+git clone https://github.com/QuantumNous/new-api.git
+cd new-api
+
+# 编辑 docker-compose.yml 配置
+nano docker-compose.yml
+
+# 启动服务
+docker-compose up -d
+```
+
+<details>
+<summary><strong>使用 Docker 命令</strong></summary>
+
+```bash
+# 拉取最新镜像
+docker pull calciumion/new-api:latest
+
+# 使用 SQLite（默认）
+docker run --name new-api -d --restart always \
+  -p 3000:3000 \
+  -e TZ=Asia/Shanghai \
+  -v ./data:/data \
+  calciumion/new-api:latest
+
+# 使用 MySQL
+docker run --name new-api -d --restart always \
+  -p 3000:3000 \
+  -e SQL_DSN="root:123456@tcp(localhost:3306)/oneapi" \
+  -e TZ=Asia/Shanghai \
+  -v ./data:/data \
+  calciumion/new-api:latest
+```
+
+> **💡 提示：** `-v ./data:/data` 会将数据保存在当前目录的 `data` 文件夹中，你也可以改为绝对路径如 `-v /your/custom/path:/data`
+
+</details>
+
+---
+
+🎉 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)
+
+---
+
+## 📚 文档
+
+<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)
+
+</div>
+
+**快速导航：**
+
+| 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) |
+
+---
+
+## ✨ 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)
+
+### 🎨 核心功能
+
+| 特性 | 说明 |
+|------|------|
+| 🎨 全新 UI | 现代化的用户界面设计 |
+| 🌍 多语言 | 支持中文、英文、法语、日语 |
+| 🔄 数据兼容 | 完全兼容原版 One API 数据库 |
+| 📈 数据看板 | 可视化控制台与统计分析 |
+| 🔒 权限管理 | 令牌分组、模型限制、用户管理 |
+
+### 💰 支付与计费
+
+- ✅ 在线充值（易支付、Stripe）
+- ✅ 模型按次数收费
+- ✅ 缓存计费支持（OpenAI、Azure、DeepSeek、Claude、Qwen等所有支持的模型）
+- ✅ 灵活的计费策略配置
+
+### 🔐 授权与安全
+
+- 😈 Discord 授权登录
+- 🤖 LinuxDO 授权登录
+- 📱 Telegram 授权登录
+- 🔑 OIDC 统一认证
+- 🔍 Key 查询使用额度（配合 [neko-api-key-tool](https://github.com/Calcium-Ion/neko-api-key-tool)）
+
+### 🚀 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）
+
+**智能路由：**
+- ⚖️ 渠道加权随机
+- 🔄 失败自动重试
+- 🚦 用户级别模型限流
+
+**格式转换：**
+- 🔄 **OpenAI Compatible ⇄ Claude Messages**
+- 🔄 **OpenAI Compatible → Google Gemini**
+- 🔄 **Google Gemini → OpenAI Compatible** - 仅支持文本，暂不支持函数调用
+- 🚧 **OpenAI Compatible ⇄ OpenAI Responses** - 开发中
+- 🔄 **思考转内容功能**
+
+**Reasoning Effort 支持：**
+
+<details>
+<summary>查看详细配置</summary>
+
+**OpenAI 系列模型：**
+- `o3-mini-high` - High reasoning effort
+- `o3-mini-medium` - Medium reasoning effort
+- `o3-mini-low` - Low reasoning effort
+- `gpt-5-high` - High reasoning effort
+- `gpt-5-medium` - Medium reasoning effort
+- `gpt-5-low` - Low reasoning effort
+
+**Claude 思考模型：**
+- `claude-3-7-sonnet-20250219-thinking` - 启用思考模式
+
+**Google Gemini 系列模型：**
+- `gemini-2.5-flash-thinking` - 启用思考模式
+- `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>
+
+---
+
+## 🤖 模型支持
+
+> 详情请参考 [接口文档 - 中继接口](https://docs.newapi.pro/zh/docs/api)
+
+| 模型类型 | 说明 | 文档 |
+|---------|------|------|
+| 🤖 OpenAI-Compatible | OpenAI 兼容模型 | [文档](https://docs.newapi.pro/zh/docs/api/ai-model/chat/openai/createchatcompletion) |
+| 🤖 OpenAI Responses | OpenAI Responses 格式 | [文档](https://docs.newapi.pro/zh/docs/api/ai-model/chat/openai/createresponse) |
+| 🎨 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/createmessage) |
+| 🌐 Gemini | Google Gemini 格式 | [文档](https://docs.newapi.pro/zh/docs/api/ai-model/chat/gemini/geminirelayv1beta) |
+| 🔧 Dify | ChatFlow 模式 | - |
+| 🎯 自定义 | 支持完整调用地址 | - |
+
+### 📡 支持的接口
+
+<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/createchatcompletion)
+- [响应接口 (Responses)](https://docs.newapi.pro/zh/docs/api/ai-model/chat/openai/createresponse)
+- [图像接口 (Image)](https://docs.newapi.pro/zh/docs/api/ai-model/images/openai/post-v1-images-generations)
+- [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/audio/openai/createspeech)
+- [嵌入接口 (Embeddings)](https://docs.newapi.pro/zh/docs/api/ai-model/embeddings/createembedding)
+- [重排序接口 (Rerank)](https://docs.newapi.pro/zh/docs/api/ai-model/rerank/creatererank)
+- [实时对话 (Realtime)](https://docs.newapi.pro/zh/docs/api/ai-model/realtime/createrealtimesession)
+- [Claude 聊天](https://docs.newapi.pro/zh/docs/api/ai-model/chat/createmessage)
+- [Google Gemini 聊天](https://docs.newapi.pro/zh/docs/api/ai-model/chat/gemini/geminirelayv1beta)
+
+</details>
+
+---
+
+## 🚢 部署
+
+> [!TIP]
+> **最新版 Docker 镜像：** `calciumion/new-api:latest`
+
+### 📋 部署要求
+
+| 组件 | 要求 |
+|------|------|
+| **本地数据库** | SQLite（Docker 需挂载 `/data` 目录）|
+| **远程数据库** | MySQL ≥ 5.7.8 或 PostgreSQL ≥ 9.6 |
+| **容器引擎** | Docker / Docker Compose |
+
+### ⚙️ 环境变量配置
+
+<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` |
+
+📖 **完整配置：** [环境变量文档](https://docs.newapi.pro/zh/docs/installation/config-maintenance/environment-variables)
+
+</details>
+
+### 🔧 部署方式
+
+<details>
+<summary><strong>方式 1：Docker Compose（推荐）</strong></summary>
+
+```bash
+# 克隆项目
+git clone https://github.com/QuantumNous/new-api.git
+cd new-api
+
+# 编辑配置
+nano docker-compose.yml
+
+# 启动服务
+docker-compose up -d
+```
+
+</details>
+
+<details>
+<summary><strong>方式 2：Docker 命令</strong></summary>
+
+**使用 SQLite：**
+```bash
+docker run --name new-api -d --restart always \
+  -p 3000:3000 \
+  -e TZ=Asia/Shanghai \
+  -v ./data:/data \
+  calciumion/new-api:latest
+```
+
+**使用 MySQL：**
+```bash
+docker run --name new-api -d --restart always \
+  -p 3000:3000 \
+  -e SQL_DSN="root:123456@tcp(localhost:3306)/oneapi" \
+  -e TZ=Asia/Shanghai \
+  -v ./data:/data \
+  calciumion/new-api:latest
+```
+
+> **💡 路径说明：** 
+> - `./data:/data` - 相对路径，数据保存在当前目录的 data 文件夹
+> - 也可使用绝对路径，如：`/your/custom/path:/data`
+
+</details>
+
+<details>
+<summary><strong>方式 3：宝塔面板</strong></summary>
+
+1. 安装宝塔面板（≥ 9.2.0 版本）
+2. 在应用商店搜索 **New-API**
+3. 一键安装
+
+📖 [图文教程](./docs/BT.md)
+
+</details>
+
+### ⚠️ 多机部署注意事项
+
+> [!WARNING]
+> - **必须设置** `SESSION_SECRET` - 否则登录状态不一致
+> - **公用 Redis 必须设置** `CRYPTO_SECRET` - 否则数据无法解密
+
+### 🔄 渠道重试与缓存
+
+**重试配置：** `设置 → 运营设置 → 通用设置 → 失败重试次数`
+
+**缓存配置：**
+- `REDIS_CONN_STRING`：Redis 缓存（推荐）
+- `MEMORY_CACHE_ENABLED`：内存缓存
+
+---
+
+## 🔗 相关项目
+
+### 上游项目
+
+| 项目 | 说明 |
+|------|------|
+| [One API](https://github.com/songquanpeng/one-api) | 原版项目基础 |
+| [Midjourney-Proxy](https://github.com/novicezk/midjourney-proxy) | Midjourney 接口支持 |
+
+### 配套工具
+
+| 项目 | 说明 |
+|------|------|
+| [neko-api-key-tool](https://github.com/Calcium-Ion/neko-api-key-tool) | Key 额度查询工具 |
+| [new-api-horizon](https://github.com/Calcium-Ion/new-api-horizon) | New API 高性能优化版 |
+
+---
+
+## 💬 帮助支持
+
+### 📖 文档资源
+
+| 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) |
+
+### 🤝 贡献指南
+
+欢迎各种形式的贡献！
+
+- 🐛 报告 Bug
+- 💡 提出新功能
+- 📝 改进文档
+- 🔧 提交代码
+
+---
+
+## 🌟 Star History
+
+<div align="center">
+
+[![Star History Chart](https://api.star-history.com/svg?repos=Calcium-Ion/new-api&type=Date)](https://star-history.com/#Calcium-Ion/new-api&Date)
+
+</div>
+
+---
+
+<div align="center">
+
+### 💖 感谢使用 New API
+
+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)**
+
+<sub>Built with ❤️ by QuantumNous</sub>
+
+</div>

common/api_type.go

@@ -71,6 +71,10 @@ func ChannelType2APIType(channelType int) (int, bool) {
 		apiType = constant.APITypeSubmodel
 	case constant.ChannelTypeMiniMax:
 		apiType = constant.APITypeMiniMax
+	case constant.ChannelTypeReplicate:
+		apiType = constant.APITypeReplicate
+	case constant.ChannelTypeCodex:
+		apiType = constant.APITypeCodex
 	}
 	if apiType == -1 {
 		return constant.APITypeOpenAI, false

common/audio.go

@@ -71,15 +71,66 @@ 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")
 	}
-	d, err := dec.Duration()
-	if err != nil {
-		return 0, errors.Wrap(err, "failed to get wav duration")
+
+	// 尝试寻找 data 块
+	if err := dec.FwdToPCM(); err != nil {
+		return 0, errors.Wrap(err, "failed to find PCM data chunk")
 	}
-	return d.Seconds(), nil
+
+	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
 }
 
 // getFLACDuration 解析 FLAC 文件的 STREAMINFO 块。

common/body_storage.go

@@ -0,0 +1,365 @@
+package common
+
+import (
+	"bytes"
+	"fmt"
+	"io"
+	"os"
+	"path/filepath"
+	"sync"
+	"sync/atomic"
+	"time"
+
+	"github.com/google/uuid"
+)
+
+// BodyStorage 请求体存储接口
+type BodyStorage interface {
+	io.ReadSeeker
+	io.Closer
+	// Bytes 获取全部内容
+	Bytes() ([]byte, error)
+	// Size 获取数据大小
+	Size() int64
+	// IsDisk 是否是磁盘存储
+	IsDisk() bool
+}
+
+// ErrStorageClosed 存储已关闭错误
+var ErrStorageClosed = fmt.Errorf("body storage is closed")
+
+// memoryStorage 内存存储实现
+type memoryStorage struct {
+	data   []byte
+	reader *bytes.Reader
+	size   int64
+	closed int32
+	mu     sync.Mutex
+}
+
+func newMemoryStorage(data []byte) *memoryStorage {
+	size := int64(len(data))
+	IncrementMemoryBuffers(size)
+	return &memoryStorage{
+		data:   data,
+		reader: bytes.NewReader(data),
+		size:   size,
+	}
+}
+
+func (m *memoryStorage) Read(p []byte) (n int, err error) {
+	m.mu.Lock()
+	defer m.mu.Unlock()
+	if atomic.LoadInt32(&m.closed) == 1 {
+		return 0, ErrStorageClosed
+	}
+	return m.reader.Read(p)
+}
+
+func (m *memoryStorage) Seek(offset int64, whence int) (int64, error) {
+	m.mu.Lock()
+	defer m.mu.Unlock()
+	if atomic.LoadInt32(&m.closed) == 1 {
+		return 0, ErrStorageClosed
+	}
+	return m.reader.Seek(offset, whence)
+}
+
+func (m *memoryStorage) Close() error {
+	m.mu.Lock()
+	defer m.mu.Unlock()
+	if atomic.CompareAndSwapInt32(&m.closed, 0, 1) {
+		DecrementMemoryBuffers(m.size)
+	}
+	return nil
+}
+
+func (m *memoryStorage) Bytes() ([]byte, error) {
+	m.mu.Lock()
+	defer m.mu.Unlock()
+	if atomic.LoadInt32(&m.closed) == 1 {
+		return nil, ErrStorageClosed
+	}
+	return m.data, nil
+}
+
+func (m *memoryStorage) Size() int64 {
+	return m.size
+}
+
+func (m *memoryStorage) IsDisk() bool {
+	return false
+}
+
+// diskStorage 磁盘存储实现
+type diskStorage struct {
+	file     *os.File
+	filePath string
+	size     int64
+	closed   int32
+	mu       sync.Mutex
+}
+
+func newDiskStorage(data []byte, cachePath string) (*diskStorage, error) {
+	// 确定缓存目录
+	dir := cachePath
+	if dir == "" {
+		dir = os.TempDir()
+	}
+	dir = filepath.Join(dir, "new-api-body-cache")
+
+	// 确保目录存在
+	if err := os.MkdirAll(dir, 0755); err != nil {
+		return nil, fmt.Errorf("failed to create cache directory: %w", err)
+	}
+
+	// 创建临时文件
+	filename := fmt.Sprintf("body-%s-%d.tmp", uuid.New().String()[:8], time.Now().UnixNano())
+	filePath := filepath.Join(dir, filename)
+
+	file, err := os.OpenFile(filePath, os.O_CREATE|os.O_RDWR|os.O_EXCL, 0600)
+	if err != nil {
+		return nil, fmt.Errorf("failed to create temp file: %w", err)
+	}
+
+	// 写入数据
+	n, err := file.Write(data)
+	if err != nil {
+		file.Close()
+		os.Remove(filePath)
+		return nil, fmt.Errorf("failed to write to temp file: %w", err)
+	}
+
+	// 重置文件指针
+	if _, err := file.Seek(0, io.SeekStart); err != nil {
+		file.Close()
+		os.Remove(filePath)
+		return nil, fmt.Errorf("failed to seek temp file: %w", err)
+	}
+
+	size := int64(n)
+	IncrementDiskFiles(size)
+
+	return &diskStorage{
+		file:     file,
+		filePath: filePath,
+		size:     size,
+	}, nil
+}
+
+func newDiskStorageFromReader(reader io.Reader, maxBytes int64, cachePath string) (*diskStorage, error) {
+	// 确定缓存目录
+	dir := cachePath
+	if dir == "" {
+		dir = os.TempDir()
+	}
+	dir = filepath.Join(dir, "new-api-body-cache")
+
+	// 确保目录存在
+	if err := os.MkdirAll(dir, 0755); err != nil {
+		return nil, fmt.Errorf("failed to create cache directory: %w", err)
+	}
+
+	// 创建临时文件
+	filename := fmt.Sprintf("body-%s-%d.tmp", uuid.New().String()[:8], time.Now().UnixNano())
+	filePath := filepath.Join(dir, filename)
+
+	file, err := os.OpenFile(filePath, os.O_CREATE|os.O_RDWR|os.O_EXCL, 0600)
+	if err != nil {
+		return nil, fmt.Errorf("failed to create temp file: %w", err)
+	}
+
+	// 从 reader 读取并写入文件
+	written, err := io.Copy(file, io.LimitReader(reader, maxBytes+1))
+	if err != nil {
+		file.Close()
+		os.Remove(filePath)
+		return nil, fmt.Errorf("failed to write to temp file: %w", err)
+	}
+
+	if written > maxBytes {
+		file.Close()
+		os.Remove(filePath)
+		return nil, ErrRequestBodyTooLarge
+	}
+
+	// 重置文件指针
+	if _, err := file.Seek(0, io.SeekStart); err != nil {
+		file.Close()
+		os.Remove(filePath)
+		return nil, fmt.Errorf("failed to seek temp file: %w", err)
+	}
+
+	IncrementDiskFiles(written)
+
+	return &diskStorage{
+		file:     file,
+		filePath: filePath,
+		size:     written,
+	}, nil
+}
+
+func (d *diskStorage) Read(p []byte) (n int, err error) {
+	d.mu.Lock()
+	defer d.mu.Unlock()
+	if atomic.LoadInt32(&d.closed) == 1 {
+		return 0, ErrStorageClosed
+	}
+	return d.file.Read(p)
+}
+
+func (d *diskStorage) Seek(offset int64, whence int) (int64, error) {
+	d.mu.Lock()
+	defer d.mu.Unlock()
+	if atomic.LoadInt32(&d.closed) == 1 {
+		return 0, ErrStorageClosed
+	}
+	return d.file.Seek(offset, whence)
+}
+
+func (d *diskStorage) Close() error {
+	d.mu.Lock()
+	defer d.mu.Unlock()
+	if atomic.CompareAndSwapInt32(&d.closed, 0, 1) {
+		d.file.Close()
+		os.Remove(d.filePath)
+		DecrementDiskFiles(d.size)
+	}
+	return nil
+}
+
+func (d *diskStorage) Bytes() ([]byte, error) {
+	d.mu.Lock()
+	defer d.mu.Unlock()
+
+	if atomic.LoadInt32(&d.closed) == 1 {
+		return nil, ErrStorageClosed
+	}
+
+	// 保存当前位置
+	currentPos, err := d.file.Seek(0, io.SeekCurrent)
+	if err != nil {
+		return nil, err
+	}
+
+	// 移动到开头
+	if _, err := d.file.Seek(0, io.SeekStart); err != nil {
+		return nil, err
+	}
+
+	// 读取全部内容
+	data := make([]byte, d.size)
+	_, err = io.ReadFull(d.file, data)
+	if err != nil {
+		return nil, err
+	}
+
+	// 恢复位置
+	if _, err := d.file.Seek(currentPos, io.SeekStart); err != nil {
+		return nil, err
+	}
+
+	return data, nil
+}
+
+func (d *diskStorage) Size() int64 {
+	return d.size
+}
+
+func (d *diskStorage) IsDisk() bool {
+	return true
+}
+
+// CreateBodyStorage 根据数据大小创建合适的存储
+func CreateBodyStorage(data []byte) (BodyStorage, error) {
+	size := int64(len(data))
+	threshold := GetDiskCacheThresholdBytes()
+
+	// 检查是否应该使用磁盘缓存
+	if IsDiskCacheEnabled() &&
+		size >= threshold &&
+		IsDiskCacheAvailable(size) {
+		storage, err := newDiskStorage(data, GetDiskCachePath())
+		if err != nil {
+			// 如果磁盘存储失败，回退到内存存储
+			SysError(fmt.Sprintf("failed to create disk storage, falling back to memory: %v", err))
+			return newMemoryStorage(data), nil
+		}
+		return storage, nil
+	}
+
+	return newMemoryStorage(data), nil
+}
+
+// CreateBodyStorageFromReader 从 Reader 创建存储（用于大请求的流式处理）
+func CreateBodyStorageFromReader(reader io.Reader, contentLength int64, maxBytes int64) (BodyStorage, error) {
+	threshold := GetDiskCacheThresholdBytes()
+
+	// 如果启用了磁盘缓存且内容长度超过阈值，直接使用磁盘存储
+	if IsDiskCacheEnabled() &&
+		contentLength > 0 &&
+		contentLength >= threshold &&
+		IsDiskCacheAvailable(contentLength) {
+		storage, err := newDiskStorageFromReader(reader, maxBytes, GetDiskCachePath())
+		if err != nil {
+			if IsRequestBodyTooLargeError(err) {
+				return nil, err
+			}
+			// 磁盘存储失败，reader 已被消费，无法安全回退
+			// 直接返回错误而非尝试回退（因为 reader 数据已丢失）
+			return nil, fmt.Errorf("disk storage creation failed: %w", err)
+		}
+		IncrementDiskCacheHits()
+		return storage, nil
+	}
+
+	// 使用内存读取
+	data, err := io.ReadAll(io.LimitReader(reader, maxBytes+1))
+	if err != nil {
+		return nil, err
+	}
+	if int64(len(data)) > maxBytes {
+		return nil, ErrRequestBodyTooLarge
+	}
+
+	storage, err := CreateBodyStorage(data)
+	if err != nil {
+		return nil, err
+	}
+	// 如果最终使用内存存储，记录内存缓存命中
+	if !storage.IsDisk() {
+		IncrementMemoryCacheHits()
+	} else {
+		IncrementDiskCacheHits()
+	}
+	return storage, nil
+}
+
+// CleanupOldCacheFiles 清理旧的缓存文件（用于启动时清理残留）
+func CleanupOldCacheFiles() {
+	cachePath := GetDiskCachePath()
+	if cachePath == "" {
+		cachePath = os.TempDir()
+	}
+	dir := filepath.Join(cachePath, "new-api-body-cache")
+
+	entries, err := os.ReadDir(dir)
+	if err != nil {
+		return // 目录不存在或无法读取
+	}
+
+	now := time.Now()
+	for _, entry := range entries {
+		if entry.IsDir() {
+			continue
+		}
+		info, err := entry.Info()
+		if err != nil {
+			continue
+		}
+		// 删除超过 5 分钟的旧文件
+		if now.Sub(info.ModTime()) > 5*time.Minute {
+			os.Remove(filepath.Join(dir, entry.Name()))
+		}
+	}
+}

common/constants.go

@@ -1,6 +1,7 @@
 package common
 
 import (
+	"crypto/tls"
 	//"os"
 	//"strconv"
 	"sync"
@@ -73,6 +74,9 @@ var MemoryCacheEnabled bool
 
 var LogConsumeEnabled = true
 
+var TLSInsecureSkipVerify bool
+var InsecureTLSConfig = &tls.Config{InsecureSkipVerify: true}
+
 var SMTPServer = ""
 var SMTPPort = 587
 var SMTPSSLEnabled = false
@@ -121,6 +125,9 @@ 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
@@ -159,14 +166,15 @@ var (
 	GlobalWebRateLimitNum      int
 	GlobalWebRateLimitDuration int64
 
+	CriticalRateLimitEnable   bool
+	CriticalRateLimitNum            = 20
+	CriticalRateLimitDuration int64 = 20 * 60
+
 	UploadRateLimitNum            = 10
 	UploadRateLimitDuration int64 = 60
 
 	DownloadRateLimitNum            = 10
 	DownloadRateLimitDuration int64 = 60
-
-	CriticalRateLimitNum            = 20
-	CriticalRateLimitDuration int64 = 20 * 60
 )
 
 var RateLimitKeyExpirationDuration = 20 * time.Minute

common/disk_cache_config.go

@@ -0,0 +1,156 @@
+package common
+
+import (
+	"sync"
+	"sync/atomic"
+)
+
+// DiskCacheConfig 磁盘缓存配置（由 performance_setting 包更新）
+type DiskCacheConfig struct {
+	// Enabled 是否启用磁盘缓存
+	Enabled bool
+	// ThresholdMB 触发磁盘缓存的请求体大小阈值（MB）
+	ThresholdMB int
+	// MaxSizeMB 磁盘缓存最大总大小（MB）
+	MaxSizeMB int
+	// Path 磁盘缓存目录
+	Path string
+}
+
+// 全局磁盘缓存配置
+var diskCacheConfig = DiskCacheConfig{
+	Enabled:     false,
+	ThresholdMB: 10,
+	MaxSizeMB:   1024,
+	Path:        "",
+}
+var diskCacheConfigMu sync.RWMutex
+
+// GetDiskCacheConfig 获取磁盘缓存配置
+func GetDiskCacheConfig() DiskCacheConfig {
+	diskCacheConfigMu.RLock()
+	defer diskCacheConfigMu.RUnlock()
+	return diskCacheConfig
+}
+
+// SetDiskCacheConfig 设置磁盘缓存配置
+func SetDiskCacheConfig(config DiskCacheConfig) {
+	diskCacheConfigMu.Lock()
+	defer diskCacheConfigMu.Unlock()
+	diskCacheConfig = config
+}
+
+// IsDiskCacheEnabled 是否启用磁盘缓存
+func IsDiskCacheEnabled() bool {
+	diskCacheConfigMu.RLock()
+	defer diskCacheConfigMu.RUnlock()
+	return diskCacheConfig.Enabled
+}
+
+// GetDiskCacheThresholdBytes 获取磁盘缓存阈值（字节）
+func GetDiskCacheThresholdBytes() int64 {
+	diskCacheConfigMu.RLock()
+	defer diskCacheConfigMu.RUnlock()
+	return int64(diskCacheConfig.ThresholdMB) << 20
+}
+
+// GetDiskCacheMaxSizeBytes 获取磁盘缓存最大大小（字节）
+func GetDiskCacheMaxSizeBytes() int64 {
+	diskCacheConfigMu.RLock()
+	defer diskCacheConfigMu.RUnlock()
+	return int64(diskCacheConfig.MaxSizeMB) << 20
+}
+
+// GetDiskCachePath 获取磁盘缓存目录
+func GetDiskCachePath() string {
+	diskCacheConfigMu.RLock()
+	defer diskCacheConfigMu.RUnlock()
+	return diskCacheConfig.Path
+}
+
+// DiskCacheStats 磁盘缓存统计信息
+type DiskCacheStats struct {
+	// 当前活跃的磁盘缓存文件数
+	ActiveDiskFiles int64 `json:"active_disk_files"`
+	// 当前磁盘缓存总大小（字节）
+	CurrentDiskUsageBytes int64 `json:"current_disk_usage_bytes"`
+	// 当前内存缓存数量
+	ActiveMemoryBuffers int64 `json:"active_memory_buffers"`
+	// 当前内存缓存总大小（字节）
+	CurrentMemoryUsageBytes int64 `json:"current_memory_usage_bytes"`
+	// 磁盘缓存命中次数
+	DiskCacheHits int64 `json:"disk_cache_hits"`
+	// 内存缓存命中次数
+	MemoryCacheHits int64 `json:"memory_cache_hits"`
+	// 磁盘缓存最大限制（字节）
+	DiskCacheMaxBytes int64 `json:"disk_cache_max_bytes"`
+	// 磁盘缓存阈值（字节）
+	DiskCacheThresholdBytes int64 `json:"disk_cache_threshold_bytes"`
+}
+
+var diskCacheStats DiskCacheStats
+
+// GetDiskCacheStats 获取缓存统计信息
+func GetDiskCacheStats() DiskCacheStats {
+	stats := DiskCacheStats{
+		ActiveDiskFiles:         atomic.LoadInt64(&diskCacheStats.ActiveDiskFiles),
+		CurrentDiskUsageBytes:   atomic.LoadInt64(&diskCacheStats.CurrentDiskUsageBytes),
+		ActiveMemoryBuffers:     atomic.LoadInt64(&diskCacheStats.ActiveMemoryBuffers),
+		CurrentMemoryUsageBytes: atomic.LoadInt64(&diskCacheStats.CurrentMemoryUsageBytes),
+		DiskCacheHits:           atomic.LoadInt64(&diskCacheStats.DiskCacheHits),
+		MemoryCacheHits:         atomic.LoadInt64(&diskCacheStats.MemoryCacheHits),
+		DiskCacheMaxBytes:       GetDiskCacheMaxSizeBytes(),
+		DiskCacheThresholdBytes: GetDiskCacheThresholdBytes(),
+	}
+	return stats
+}
+
+// IncrementDiskFiles 增加磁盘文件计数
+func IncrementDiskFiles(size int64) {
+	atomic.AddInt64(&diskCacheStats.ActiveDiskFiles, 1)
+	atomic.AddInt64(&diskCacheStats.CurrentDiskUsageBytes, size)
+}
+
+// DecrementDiskFiles 减少磁盘文件计数
+func DecrementDiskFiles(size int64) {
+	atomic.AddInt64(&diskCacheStats.ActiveDiskFiles, -1)
+	atomic.AddInt64(&diskCacheStats.CurrentDiskUsageBytes, -size)
+}
+
+// IncrementMemoryBuffers 增加内存缓存计数
+func IncrementMemoryBuffers(size int64) {
+	atomic.AddInt64(&diskCacheStats.ActiveMemoryBuffers, 1)
+	atomic.AddInt64(&diskCacheStats.CurrentMemoryUsageBytes, size)
+}
+
+// DecrementMemoryBuffers 减少内存缓存计数
+func DecrementMemoryBuffers(size int64) {
+	atomic.AddInt64(&diskCacheStats.ActiveMemoryBuffers, -1)
+	atomic.AddInt64(&diskCacheStats.CurrentMemoryUsageBytes, -size)
+}
+
+// IncrementDiskCacheHits 增加磁盘缓存命中次数
+func IncrementDiskCacheHits() {
+	atomic.AddInt64(&diskCacheStats.DiskCacheHits, 1)
+}
+
+// IncrementMemoryCacheHits 增加内存缓存命中次数
+func IncrementMemoryCacheHits() {
+	atomic.AddInt64(&diskCacheStats.MemoryCacheHits, 1)
+}
+
+// ResetDiskCacheStats 重置统计信息（不重置当前使用量）
+func ResetDiskCacheStats() {
+	atomic.StoreInt64(&diskCacheStats.DiskCacheHits, 0)
+	atomic.StoreInt64(&diskCacheStats.MemoryCacheHits, 0)
+}
+
+// IsDiskCacheAvailable 检查是否可以创建新的磁盘缓存
+func IsDiskCacheAvailable(requestSize int64) bool {
+	if !IsDiskCacheEnabled() {
+		return false
+	}
+	maxBytes := GetDiskCacheMaxSizeBytes()
+	currentUsage := atomic.LoadInt64(&diskCacheStats.CurrentDiskUsageBytes)
+	return currentUsage+requestSize <= maxBytes
+}

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

@@ -4,6 +4,7 @@ import (
 	"embed"
 	"io/fs"
 	"net/http"
+	"os"
 
 	"github.com/gin-contrib/static"
 )
@@ -14,7 +15,7 @@ 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
@@ -22,12 +23,21 @@ 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/endpoint_defaults.go

@@ -17,13 +17,14 @@ type EndpointInfo struct {
 
 // defaultEndpointInfoMap 保存内置端点的默认 Path 与 Method
 var defaultEndpointInfoMap = map[constant.EndpointType]EndpointInfo{
-	constant.EndpointTypeOpenAI:          {Path: "/v1/chat/completions", Method: "POST"},
-	constant.EndpointTypeOpenAIResponse:  {Path: "/v1/responses", Method: "POST"},
-	constant.EndpointTypeAnthropic:       {Path: "/v1/messages", Method: "POST"},
-	constant.EndpointTypeGemini:          {Path: "/v1beta/models/{model}:generateContent", Method: "POST"},
-	constant.EndpointTypeJinaRerank:      {Path: "/rerank", Method: "POST"},
-	constant.EndpointTypeImageGeneration: {Path: "/v1/images/generations", Method: "POST"},
-	constant.EndpointTypeEmbeddings:      {Path: "/v1/embeddings", Method: "POST"},
+	constant.EndpointTypeOpenAI:                {Path: "/v1/chat/completions", Method: "POST"},
+	constant.EndpointTypeOpenAIResponse:        {Path: "/v1/responses", Method: "POST"},
+	constant.EndpointTypeOpenAIResponseCompact: {Path: "/v1/responses/compact", Method: "POST"},
+	constant.EndpointTypeAnthropic:             {Path: "/v1/messages", Method: "POST"},
+	constant.EndpointTypeGemini:                {Path: "/v1beta/models/{model}:generateContent", Method: "POST"},
+	constant.EndpointTypeJinaRerank:            {Path: "/v1/rerank", Method: "POST"},
+	constant.EndpointTypeImageGeneration:       {Path: "/v1/images/generations", Method: "POST"},
+	constant.EndpointTypeEmbeddings:            {Path: "/v1/embeddings", Method: "POST"},
 }
 
 // GetDefaultEndpointInfo 返回指定端点类型的默认信息以及是否存在

common/gin.go

@@ -2,7 +2,9 @@ package common
 
 import (
 	"bytes"
+	"fmt"
 	"io"
+	"mime"
 	"mime/multipart"
 	"net/http"
 	"net/url"
@@ -10,24 +12,119 @@ import (
 	"time"
 
 	"github.com/QuantumNous/new-api/constant"
+	"github.com/pkg/errors"
 
 	"github.com/gin-gonic/gin"
 )
 
 const KeyRequestBody = "key_request_body"
+const KeyBodyStorage = "key_body_storage"
+
+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) {
-	requestBody, _ := c.Get(KeyRequestBody)
-	if requestBody != nil {
-		return requestBody.([]byte), nil
+	// 首先检查是否有 BodyStorage 缓存
+	if storage, exists := c.Get(KeyBodyStorage); exists && storage != nil {
+		if bs, ok := storage.(BodyStorage); ok {
+			if _, err := bs.Seek(0, io.SeekStart); err != nil {
+				return nil, fmt.Errorf("failed to seek body storage: %w", err)
+			}
+			return bs.Bytes()
+		}
 	}
-	requestBody, err := io.ReadAll(c.Request.Body)
+
+	// 检查旧的缓存方式
+	cached, exists := c.Get(KeyRequestBody)
+	if exists && cached != nil {
+		if b, ok := cached.([]byte); ok {
+			return b, nil
+		}
+	}
+
+	maxMB := constant.MaxRequestBodyMB
+	if maxMB <= 0 {
+		maxMB = 128 // 默认 128MB
+	}
+	maxBytes := int64(maxMB) << 20
+
+	contentLength := c.Request.ContentLength
+
+	// 使用新的存储系统
+	storage, err := CreateBodyStorageFromReader(c.Request.Body, contentLength, maxBytes)
+	_ = c.Request.Body.Close()
+
+	if err != nil {
+		if IsRequestBodyTooLargeError(err) {
+			return nil, errors.Wrap(ErrRequestBodyTooLarge, fmt.Sprintf("request body exceeds %d MB", maxMB))
+		}
+		return nil, err
+	}
+
+	// 缓存存储对象
+	c.Set(KeyBodyStorage, storage)
+
+	// 获取字节数据
+	body, err := storage.Bytes()
 	if err != nil {
 		return nil, err
 	}
-	_ = c.Request.Body.Close()
-	c.Set(KeyRequestBody, requestBody)
-	return requestBody.([]byte), nil
+
+	// 同时设置旧的缓存键以保持兼容性
+	c.Set(KeyRequestBody, body)
+
+	return body, nil
+}
+
+// GetBodyStorage 获取请求体存储对象（用于需要多次读取的场景）
+func GetBodyStorage(c *gin.Context) (BodyStorage, error) {
+	// 检查是否已有存储
+	if storage, exists := c.Get(KeyBodyStorage); exists && storage != nil {
+		if bs, ok := storage.(BodyStorage); ok {
+			if _, err := bs.Seek(0, io.SeekStart); err != nil {
+				return nil, fmt.Errorf("failed to seek body storage: %w", err)
+			}
+			return bs, nil
+		}
+	}
+
+	// 如果没有，调用 GetRequestBody 创建存储
+	_, err := GetRequestBody(c)
+	if err != nil {
+		return nil, err
+	}
+
+	// 再次获取存储
+	if storage, exists := c.Get(KeyBodyStorage); exists && storage != nil {
+		if bs, ok := storage.(BodyStorage); ok {
+			if _, err := bs.Seek(0, io.SeekStart); err != nil {
+				return nil, fmt.Errorf("failed to seek body storage: %w", err)
+			}
+			return bs, nil
+		}
+	}
+
+	return nil, errors.New("failed to get body storage")
+}
+
+// CleanupBodyStorage 清理请求体存储（应在请求结束时调用）
+func CleanupBodyStorage(c *gin.Context) {
+	if storage, exists := c.Get(KeyBodyStorage); exists && storage != nil {
+		if bs, ok := storage.(BodyStorage); ok {
+			bs.Close()
+		}
+		c.Set(KeyBodyStorage, nil)
+	}
 }
 
 func UnmarshalBodyReusable(c *gin.Context, v any) error {
@@ -128,13 +225,13 @@ func ParseMultipartFormReusable(c *gin.Context) (*multipart.Form, error) {
 	}
 
 	contentType := c.Request.Header.Get("Content-Type")
-	boundary := ""
-	if idx := strings.Index(contentType, "boundary="); idx != -1 {
-		boundary = contentType[idx+9:]
+	boundary, err := parseBoundary(contentType)
+	if err != nil {
+		return nil, err
 	}
 
 	reader := multipart.NewReader(bytes.NewReader(requestBody), boundary)
-	form, err := reader.ReadForm(32 << 20) // 32 MB max memory
+	form, err := reader.ReadForm(multipartMemoryLimit())
 	if err != nil {
 		return nil, err
 	}
@@ -177,17 +274,16 @@ func parseFormData(data []byte, v any) error {
 
 func parseMultipartFormData(c *gin.Context, data []byte, v any) error {
 	contentType := c.Request.Header.Get("Content-Type")
-	boundary := ""
-	if idx := strings.Index(contentType, "boundary="); idx != -1 {
-		boundary = contentType[idx+9:]
-	}
-
-	if boundary == "" {
-		return Unmarshal(data, v) // Fallback to JSON
+	boundary, err := parseBoundary(contentType)
+	if err != nil {
+		if errors.Is(err, errBoundaryNotFound) {
+			return Unmarshal(data, v) // Fallback to JSON
+		}
+		return err
 	}
 
 	reader := multipart.NewReader(bytes.NewReader(data), boundary)
-	form, err := reader.ReadForm(32 << 20) // 32 MB max memory
+	form, err := reader.ReadForm(multipartMemoryLimit())
 	if err != nil {
 		return err
 	}
@@ -203,3 +299,31 @@ func parseMultipartFormData(c *gin.Context, data []byte, v any) error {
 
 	return processFormMap(formMap, v)
 }
+
+var errBoundaryNotFound = errors.New("multipart boundary not found")
+
+// parseBoundary extracts the multipart boundary from the Content-Type header using mime.ParseMediaType
+func parseBoundary(contentType string) (string, error) {
+	if contentType == "" {
+		return "", errBoundaryNotFound
+	}
+	// Boundary-UUID / boundary-------xxxxxx
+	_, params, err := mime.ParseMediaType(contentType)
+	if err != nil {
+		return "", err
+	}
+	boundary, ok := params["boundary"]
+	if !ok || boundary == "" {
+		return "", errBoundaryNotFound
+	}
+	return boundary, nil
+}
+
+// multipartMemoryLimit returns the configured multipart memory limit in bytes
+func multipartMemoryLimit() int64 {
+	limitMB := constant.MaxFileDownloadMB
+	if limitMB <= 0 {
+		limitMB = 32
+	}
+	return int64(limitMB) << 20
+}

common/init.go

@@ -4,6 +4,7 @@ import (
 	"flag"
 	"fmt"
 	"log"
+	"net/http"
 	"os"
 	"path/filepath"
 	"strconv"
@@ -30,6 +31,11 @@ func printHelp() {
 func InitEnv() {
 	flag.Parse()
 
+	envVersion := os.Getenv("VERSION")
+	if envVersion != "" {
+		Version = envVersion
+	}
+
 	if *PrintVersion {
 		fmt.Println(Version)
 		os.Exit(0)
@@ -76,6 +82,16 @@ func InitEnv() {
 	DebugEnabled = os.Getenv("DEBUG") == "true"
 	MemoryCacheEnabled = os.Getenv("MEMORY_CACHE_ENABLED") == "true"
 	IsMasterNode = os.Getenv("NODE_TYPE") != "slave"
+	TLSInsecureSkipVerify = GetEnvOrDefaultBool("TLS_INSECURE_SKIP_VERIFY", false)
+	if TLSInsecureSkipVerify {
+		if tr, ok := http.DefaultTransport.(*http.Transport); ok && tr != nil {
+			if tr.TLSClientConfig != nil {
+				tr.TLSClientConfig.InsecureSkipVerify = true
+			} else {
+				tr.TLSClientConfig = InsecureTLSConfig
+			}
+		}
+	}
 
 	// Parse requestInterval and set RequestInterval
 	requestInterval, _ = strconv.Atoi(os.Getenv("POLLING_INTERVAL"))
@@ -85,6 +101,8 @@ 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")
@@ -99,17 +117,24 @@ func InitEnv() {
 	GlobalWebRateLimitNum = GetEnvOrDefault("GLOBAL_WEB_RATE_LIMIT", 60)
 	GlobalWebRateLimitDuration = int64(GetEnvOrDefault("GLOBAL_WEB_RATE_LIMIT_DURATION", 180))
 
+	CriticalRateLimitEnable = GetEnvOrDefaultBool("CRITICAL_RATE_LIMIT_ENABLE", true)
+	CriticalRateLimitNum = GetEnvOrDefault("CRITICAL_RATE_LIMIT", 20)
+	CriticalRateLimitDuration = int64(GetEnvOrDefault("CRITICAL_RATE_LIMIT_DURATION", 20*60))
 	initConstantEnv()
 }
 
 func initConstantEnv() {
 	constant.StreamingTimeout = GetEnvOrDefault("STREAMING_TIMEOUT", 300)
 	constant.DifyDebug = GetEnvOrDefaultBool("DIFY_DEBUG", true)
-	constant.MaxFileDownloadMB = GetEnvOrDefault("MAX_FILE_DOWNLOAD_MB", 20)
+	constant.MaxFileDownloadMB = GetEnvOrDefault("MAX_FILE_DOWNLOAD_MB", 64)
+	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", 128)
 	// 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)
 	constant.GetMediaToken = GetEnvOrDefaultBool("GET_MEDIA_TOKEN", true)
-	constant.GetMediaTokenNotStream = GetEnvOrDefaultBool("GET_MEDIA_TOKEN_NOT_STREAM", true)
+	constant.GetMediaTokenNotStream = GetEnvOrDefaultBool("GET_MEDIA_TOKEN_NOT_STREAM", false)
 	constant.UpdateTask = GetEnvOrDefaultBool("UPDATE_TASK", true)
 	constant.AzureDefaultAPIVersion = GetEnvOrDefaultString("AZURE_DEFAULT_API_VERSION", "2025-04-01-preview")
 	constant.GeminiVisionMaxImageNum = GetEnvOrDefault("GEMINI_VISION_MAX_IMAGE_NUM", 16)
@@ -119,6 +144,8 @@ 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

@@ -2,6 +2,15 @@ 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
@@ -20,3 +29,23 @@ 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 {
-	data = bytes.TrimSpace(data)
-	if len(data) == 0 {
+	trimmed := bytes.TrimSpace(data)
+	if len(trimmed) == 0 {
 		return "unknown"
 	}
-	firstChar := bytes.TrimSpace(data)[0]
+	firstChar := trimmed[0]
 	switch firstChar {
 	case '{':
 		return "object"

common/model.go

@@ -17,6 +17,13 @@ var (
 		"flux-",
 		"flux.1-",
 	}
+	OpenAITextModels = []string{
+		"gpt-",
+		"o1",
+		"o3",
+		"o4",
+		"chatgpt",
+	}
 )
 
 func IsOpenAIResponseOnlyModel(modelName string) bool {
@@ -40,3 +47,13 @@ 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

@@ -0,0 +1,56 @@
+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

@@ -186,23 +186,7 @@ func isIPListed(ip net.IP, list []string) bool {
 		return false
 	}
 
-	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
+	return IsIpInCIDRList(ip, list)
 }
 
 // IsIPAccessAllowed 检查IP是否允许访问

common/str.go

@@ -3,12 +3,21 @@ 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`)
+	// maskApiKeyPattern matches patterns like 'api_key:xxx' or "api_key:xxx" to mask the API key value
+	maskApiKeyPattern = regexp.MustCompile(`(['"]?)api_key:([^\s'"]+)(['"]?)`)
 )
 
 func GetStringIfEmpty(str string, defaultValue string) string {
@@ -19,12 +28,10 @@ func GetStringIfEmpty(str string, defaultValue string) string {
 }
 
 func GetRandomString(length int) string {
-	//rand.Seed(time.Now().UnixNano())
-	key := make([]byte, length)
-	for i := 0; i < length; i++ {
-		key[i] = keyChars[rand.Intn(len(keyChars))]
+	if length <= 0 {
+		return ""
 	}
-	return string(key)
+	return lo.RandomString(length, lo.AlphanumericCharset)
 }
 
 func MapToJsonStr(m map[string]interface{}) string {
@@ -170,8 +177,7 @@ func maskHostForPlainDomain(domain string) string {
 // api.openai.com -> ***.***.com
 func MaskSensitiveInfo(str string) string {
 	// Mask URLs
-	urlPattern := regexp.MustCompile(`(http|https)://[^\s/$.?#].[^\s]*`)
-	str = urlPattern.ReplaceAllStringFunc(str, func(urlStr string) string {
+	str = maskURLPattern.ReplaceAllStringFunc(str, func(urlStr string) string {
 		u, err := url.Parse(urlStr)
 		if err != nil {
 			return urlStr
@@ -224,14 +230,15 @@ func MaskSensitiveInfo(str string) string {
 	})
 
 	// Mask domain names without protocol (like openai.com, www.openai.com)
-	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 {
+	str = maskDomainPattern.ReplaceAllStringFunc(str, func(domain string) string {
 		return maskHostForPlainDomain(domain)
 	})
 
 	// Mask IP addresses
-	ipPattern := regexp.MustCompile(`\b(?:\d{1,3}\.){3}\d{1,3}\b`)
-	str = ipPattern.ReplaceAllString(str, "***.***.***.***")
+	str = maskIPPattern.ReplaceAllString(str, "***.***.***.***")
+
+	// Mask API keys (e.g., "api_key:AIzaSyAAAaUooTUni8AdaOkSRMda30n_Q4vrV70" -> "api_key:***")
+	str = maskApiKeyPattern.ReplaceAllString(str, "${1}api_key:***${3}")
 
 	return str
 }

common/utils.go

@@ -217,11 +217,6 @@ 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)
@@ -268,7 +263,7 @@ func GetTimestamp() int64 {
 }
 
 func GetTimeString() string {
-	now := time.Now()
+	now := time.Now().UTC()
 	return fmt.Sprintf("%s%d", now.Format("20060102150405"), now.UnixNano()%1e9)
 }
 

constant/api_type.go

@@ -34,5 +34,7 @@ const (
 	APITypeMoonshot
 	APITypeSubmodel
 	APITypeMiniMax
+	APITypeReplicate
+	APITypeCodex
 	APITypeDummy // this one is only for count, do not add any channel after this
 )

constant/channel.go

@@ -53,6 +53,8 @@ const (
 	ChannelTypeSubmodel       = 53
 	ChannelTypeDoubaoVideo    = 54
 	ChannelTypeSora           = 55
+	ChannelTypeReplicate      = 56
+	ChannelTypeCodex          = 57
 	ChannelTypeDummy          // this one is only for count, do not add any channel after this
 
 )
@@ -114,6 +116,8 @@ var ChannelBaseURLs = []string{
 	"https://llm.submodel.ai",                   //53
 	"https://ark.cn-beijing.volces.com",         //54
 	"https://api.openai.com",                    //55
+	"https://api.replicate.com",                 //56
+	"https://chatgpt.com",                       //57
 }
 
 var ChannelTypeNames = map[int]string{
@@ -169,6 +173,8 @@ var ChannelTypeNames = map[int]string{
 	ChannelTypeSubmodel:       "Submodel",
 	ChannelTypeDoubaoVideo:    "DoubaoVideo",
 	ChannelTypeSora:           "Sora",
+	ChannelTypeReplicate:      "Replicate",
+	ChannelTypeCodex:          "Codex",
 }
 
 func GetChannelTypeName(channelType int) string {
@@ -177,3 +183,27 @@ 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

@@ -3,8 +3,9 @@ package constant
 type ContextKey string
 
 const (
-	ContextKeyTokenCountMeta ContextKey = "token_count_meta"
-	ContextKeyPromptTokens   ContextKey = "prompt_tokens"
+	ContextKeyTokenCountMeta  ContextKey = "token_count_meta"
+	ContextKeyPromptTokens    ContextKey = "prompt_tokens"
+	ContextKeyEstimatedTokens ContextKey = "estimated_tokens"
 
 	ContextKeyOriginalModel    ContextKey = "original_model"
 	ContextKeyRequestStartTime ContextKey = "request_start_time"
@@ -17,6 +18,7 @@ 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"
@@ -36,6 +38,10 @@ 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"
@@ -46,5 +52,11 @@ const (
 	ContextKeyUsingGroup  ContextKey = "group"
 	ContextKeyUserName    ContextKey = "username"
 
+	ContextKeyLocalCountTokens ContextKey = "local_count_tokens"
+
 	ContextKeySystemPromptOverride ContextKey = "system_prompt_override"
+
+	// ContextKeyAdminRejectReason stores an admin-only reject/block reason extracted from upstream responses.
+	// It is not returned to end users, but can be persisted into consume/error logs for debugging.
+	ContextKeyAdminRejectReason ContextKey = "admin_reject_reason"
 )

constant/endpoint_type.go

@@ -3,14 +3,15 @@ package constant
 type EndpointType string
 
 const (
-	EndpointTypeOpenAI          EndpointType = "openai"
-	EndpointTypeOpenAIResponse  EndpointType = "openai-response"
-	EndpointTypeAnthropic       EndpointType = "anthropic"
-	EndpointTypeGemini          EndpointType = "gemini"
-	EndpointTypeJinaRerank      EndpointType = "jina-rerank"
-	EndpointTypeImageGeneration EndpointType = "image-generation"
-	EndpointTypeEmbeddings      EndpointType = "embeddings"
-	EndpointTypeOpenAIVideo     EndpointType = "openai-video"
+	EndpointTypeOpenAI                EndpointType = "openai"
+	EndpointTypeOpenAIResponse        EndpointType = "openai-response"
+	EndpointTypeOpenAIResponseCompact EndpointType = "openai-response-compact"
+	EndpointTypeAnthropic             EndpointType = "anthropic"
+	EndpointTypeGemini                EndpointType = "gemini"
+	EndpointTypeJinaRerank            EndpointType = "jina-rerank"
+	EndpointTypeImageGeneration       EndpointType = "image-generation"
+	EndpointTypeEmbeddings            EndpointType = "embeddings"
+	EndpointTypeOpenAIVideo           EndpointType = "openai-video"
 	//EndpointTypeMidjourney     EndpointType = "midjourney-proxy"
 	//EndpointTypeSuno           EndpointType = "suno-proxy"
 	//EndpointTypeKling          EndpointType = "kling"

constant/env.go

@@ -3,16 +3,20 @@ 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

@@ -15,6 +15,7 @@ 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 := dto.OpenAIError{
+		openAIError := types.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 := dto.OpenAIError{
+		openAIError := types.OpenAIError{
 			Message: err.Error(),
 			Type:    "new_api_error",
 		}

controller/channel-test.go

@@ -26,6 +26,7 @@ import (
 	"github.com/QuantumNous/new-api/relay/helper"
 	"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/bytedance/gopkg/util/gopool"
@@ -84,6 +85,11 @@ func testChannel(channel *model.Channel, testModel string, endpointType string)
 		}
 	} else {
 		// 如果没有指定端点类型，使用原有的自动检测逻辑
+
+		if strings.Contains(strings.ToLower(testModel), "rerank") {
+			requestPath = "/v1/rerank"
+		}
+
 		// 先判断是否为 Embedding 模型
 		if strings.Contains(strings.ToLower(testModel), "embedding") ||
 			strings.HasPrefix(testModel, "m3e") || // m3e 系列模型
@@ -97,6 +103,19 @@ 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"
+		}
+
+		// responses compaction models (must use /v1/responses/compact)
+		if strings.HasSuffix(testModel, ratio_setting.CompactModelSuffix) {
+			requestPath = "/v1/responses/compact"
+		}
+	}
+	if strings.HasPrefix(requestPath, "/v1/responses/compact") {
+		testModel = ratio_setting.WithCompactModelSuffix(testModel)
 	}
 
 	c.Request = &http.Request{
@@ -140,6 +159,8 @@ func testChannel(channel *model.Channel, testModel string, endpointType string)
 			relayFormat = types.RelayFormatOpenAI
 		case constant.EndpointTypeOpenAIResponse:
 			relayFormat = types.RelayFormatOpenAIResponses
+		case constant.EndpointTypeOpenAIResponseCompact:
+			relayFormat = types.RelayFormatOpenAIResponsesCompaction
 		case constant.EndpointTypeAnthropic:
 			relayFormat = types.RelayFormatClaude
 		case constant.EndpointTypeGemini:
@@ -174,9 +195,12 @@ func testChannel(channel *model.Channel, testModel string, endpointType string)
 		if c.Request.URL.Path == "/v1/responses" {
 			relayFormat = types.RelayFormatOpenAIResponses
 		}
+		if strings.HasPrefix(c.Request.URL.Path, "/v1/responses/compact") {
+			relayFormat = types.RelayFormatOpenAIResponsesCompaction
+		}
 	}
 
-	request := buildTestRequest(testModel, endpointType)
+	request := buildTestRequest(testModel, endpointType, channel)
 
 	info, err := relaycommon.GenRelayInfo(c, relayFormat, request, nil)
 
@@ -188,6 +212,7 @@ func testChannel(channel *model.Channel, testModel string, endpointType string)
 		}
 	}
 
+	info.IsChannelTest = true
 	info.InitChannelMeta(c)
 
 	err = helper.ModelMappedHelper(c, info, request)
@@ -204,6 +229,15 @@ func testChannel(channel *model.Channel, testModel string, endpointType string)
 	request.SetModelName(testModel)
 
 	apiType, _ := common.ChannelType2APIType(channel.Type)
+	if info.RelayMode == relayconstant.RelayModeResponsesCompact &&
+		apiType != constant.APITypeOpenAI &&
+		apiType != constant.APITypeCodex {
+		return testResult{
+			context:     c,
+			localErr:    fmt.Errorf("responses compaction test only supports openai/codex channels, got api type %d", apiType),
+			newAPIError: types.NewError(fmt.Errorf("unsupported api type: %d", apiType), types.ErrorCodeInvalidApiType),
+		}
+	}
 	adaptor := relay.GetAdaptor(apiType)
 	if adaptor == nil {
 		return testResult{
@@ -276,6 +310,25 @@ func testChannel(channel *model.Channel, testModel string, endpointType string)
 				newAPIError: types.NewError(errors.New("invalid response request type"), types.ErrorCodeConvertRequestFailed),
 			}
 		}
+	case relayconstant.RelayModeResponsesCompact:
+		// Response compaction request - convert to OpenAIResponsesRequest before adapting
+		switch req := request.(type) {
+		case *dto.OpenAIResponsesCompactionRequest:
+			convertedRequest, err = adaptor.ConvertOpenAIResponsesRequest(c, info, dto.OpenAIResponsesRequest{
+				Model:              req.Model,
+				Input:              req.Input,
+				Instructions:       req.Instructions,
+				PreviousResponseID: req.PreviousResponseID,
+			})
+		case *dto.OpenAIResponsesRequest:
+			convertedRequest, err = adaptor.ConvertOpenAIResponsesRequest(c, info, *req)
+		default:
+			return testResult{
+				context:     c,
+				localErr:    errors.New("invalid response compaction request type"),
+				newAPIError: types.NewError(errors.New("invalid response compaction request type"), types.ErrorCodeConvertRequestFailed),
+			}
+		}
 	default:
 		// Chat/Completion 等其他请求类型
 		if generalReq, ok := request.(*dto.GeneralOpenAIRequest); ok {
@@ -304,8 +357,29 @@ func testChannel(channel *model.Channel, testModel string, endpointType string)
 			newAPIError: types.NewError(err, types.ErrorCodeJsonMarshalFailed),
 		}
 	}
+
+	//jsonData, err = relaycommon.RemoveDisabledFields(jsonData, info.ChannelOtherSettings)
+	//if err != nil {
+	//	return testResult{
+	//		context:     c,
+	//		localErr:    err,
+	//		newAPIError: types.NewError(err, types.ErrorCodeConvertRequestFailed),
+	//	}
+	//}
+
+	if len(info.ParamOverride) > 0 {
+		jsonData, err = relaycommon.ApplyParamOverride(jsonData, info.ParamOverride, relaycommon.BuildParamOverrideContext(info))
+		if err != nil {
+			return testResult{
+				context:     c,
+				localErr:    err,
+				newAPIError: types.NewError(err, types.ErrorCodeChannelParamOverrideInvalid),
+			}
+		}
+	}
+
 	requestBody := bytes.NewBuffer(jsonData)
-	c.Request.Body = io.NopCloser(requestBody)
+	c.Request.Body = io.NopCloser(bytes.NewBuffer(jsonData))
 	resp, err := adaptor.DoRequest(c, info, requestBody)
 	if err != nil {
 		return testResult{
@@ -319,6 +393,16 @@ 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,
@@ -351,7 +435,7 @@ func testChannel(channel *model.Channel, testModel string, endpointType string)
 			newAPIError: types.NewOpenAIError(err, types.ErrorCodeReadResponseBodyFailed, http.StatusInternalServerError),
 		}
 	}
-	info.PromptTokens = usage.PromptTokens
+	info.SetEstimatePromptTokens(usage.PromptTokens)
 
 	quota := 0
 	if !priceData.UsePrice {
@@ -389,7 +473,9 @@ func testChannel(channel *model.Channel, testModel string, endpointType string)
 	}
 }
 
-func buildTestRequest(model string, endpointType string) dto.Request {
+func buildTestRequest(model string, endpointType string, channel *model.Channel) dto.Request {
+	testResponsesInput := json.RawMessage(`[{"role":"user","content":"hi"}]`)
+
 	// 根据端点类型构建不同的测试请求
 	if endpointType != "" {
 		switch constant.EndpointType(endpointType) {
@@ -419,11 +505,17 @@ func buildTestRequest(model string, endpointType string) dto.Request {
 			// 返回 OpenAIResponsesRequest
 			return &dto.OpenAIResponsesRequest{
 				Model: model,
-				Input: json.RawMessage("\"hi\""),
+				Input: json.RawMessage(`[{"role":"user","content":"hi"}]`),
+			}
+		case constant.EndpointTypeOpenAIResponseCompact:
+			// 返回 OpenAIResponsesCompactionRequest
+			return &dto.OpenAIResponsesCompactionRequest{
+				Model: model,
+				Input: testResponsesInput,
 			}
 		case constant.EndpointTypeAnthropic, constant.EndpointTypeGemini, constant.EndpointTypeOpenAI:
 			// 返回 GeneralOpenAIRequest
-			maxTokens := uint(10)
+			maxTokens := uint(16)
 			if constant.EndpointType(endpointType) == constant.EndpointTypeGemini {
 				maxTokens = 3000
 			}
@@ -442,6 +534,15 @@ func buildTestRequest(model string, endpointType string) dto.Request {
 	}
 
 	// 自动检测逻辑（保持原有行为）
+	if strings.Contains(strings.ToLower(model), "rerank") {
+		return &dto.RerankRequest{
+			Model:     model,
+			Query:     "What is Deep Learning?",
+			Documents: []any{"Deep Learning is a subset of machine learning.", "Machine learning is a field of artificial intelligence."},
+			TopN:      2,
+		}
+	}
+
 	// 先判断是否为 Embedding 模型
 	if strings.Contains(strings.ToLower(model), "embedding") ||
 		strings.HasPrefix(model, "m3e") ||
@@ -453,6 +554,22 @@ func buildTestRequest(model string, endpointType string) dto.Request {
 		}
 	}
 
+	// Responses compaction models (must use /v1/responses/compact)
+	if strings.HasSuffix(model, ratio_setting.CompactModelSuffix) {
+		return &dto.OpenAIResponsesCompactionRequest{
+			Model: model,
+			Input: testResponsesInput,
+		}
+	}
+
+	// Responses-only models (e.g. codex series)
+	if strings.Contains(strings.ToLower(model), "codex") {
+		return &dto.OpenAIResponsesRequest{
+			Model: model,
+			Input: json.RawMessage(`[{"role":"user","content":"hi"}]`),
+		}
+	}
+
 	// Chat/Completion 请求 - 返回 GeneralOpenAIRequest
 	testRequest := &dto.GeneralOpenAIRequest{
 		Model:  model,
@@ -466,7 +583,7 @@ func buildTestRequest(model string, endpointType string) dto.Request {
 	}
 
 	if strings.HasPrefix(model, "o") {
-		testRequest.MaxCompletionTokens = 10
+		testRequest.MaxCompletionTokens = 16
 	} else if strings.Contains(model, "thinking") {
 		if !strings.Contains(model, "claude") {
 			testRequest.MaxTokens = 50
@@ -474,7 +591,7 @@ func buildTestRequest(model string, endpointType string) dto.Request {
 	} else if strings.Contains(model, "gemini") {
 		testRequest.MaxTokens = 3000
 	} else {
-		testRequest.MaxTokens = 10
+		testRequest.MaxTokens = 16
 	}
 
 	return testRequest
@@ -617,6 +734,10 @@ func TestAllChannels(c *gin.Context) {
 var autoTestChannelsOnce sync.Once
 
 func AutomaticallyTestChannels() {
+	// 只在Master节点定时测试渠道
+	if !common.IsMasterNode {
+		return
+	}
 	autoTestChannelsOnce.Do(func() {
 		for {
 			if !operation_setting.GetMonitorSetting().AutoTestChannelEnabled {

controller/channel.go

@@ -1,26 +1,31 @@
 package controller
 
 import (
+	"context"
 	"encoding/json"
 	"fmt"
 	"net/http"
 	"strconv"
 	"strings"
+	"time"
 
 	"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/gemini"
+	"github.com/QuantumNous/new-api/relay/channel/ollama"
 	"github.com/QuantumNous/new-api/service"
 
 	"github.com/gin-gonic/gin"
 )
 
 type OpenAIModel struct {
-	ID         string `json:"id"`
-	Object     string `json:"object"`
-	Created    int64  `json:"created"`
-	OwnedBy    string `json:"owned_by"`
+	ID         string         `json:"id"`
+	Object     string         `json:"object"`
+	Created    int64          `json:"created"`
+	OwnedBy    string         `json:"owned_by"`
+	Metadata   map[string]any `json:"metadata,omitempty"`
 	Permission []struct {
 		ID                 string `json:"id"`
 		Object             string `json:"object"`
@@ -91,7 +96,7 @@ func GetAllChannels(c *gin.Context) {
 			if tag == nil || *tag == "" {
 				continue
 			}
-			tagChannels, err := model.GetChannelsByTag(*tag, idSort)
+			tagChannels, err := model.GetChannelsByTag(*tag, idSort, false)
 			if err != nil {
 				continue
 			}
@@ -165,6 +170,30 @@ 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 {
@@ -183,28 +212,130 @@ func FetchUpstreamModels(c *gin.Context) {
 		baseURL = channel.GetBaseURL()
 	}
 
+	// 对于 Ollama 渠道，使用特殊处理
+	if channel.Type == constant.ChannelTypeOllama {
+		key := strings.Split(channel.Key, "\n")[0]
+		models, err := ollama.FetchOllamaModels(baseURL, key)
+		if err != nil {
+			c.JSON(http.StatusOK, gin.H{
+				"success": false,
+				"message": fmt.Sprintf("获取Ollama模型失败: %s", err.Error()),
+			})
+			return
+		}
+
+		result := OpenAIModelsResponse{
+			Data: make([]OpenAIModel, 0, len(models)),
+		}
+
+		for _, modelInfo := range models {
+			metadata := map[string]any{}
+			if modelInfo.Size > 0 {
+				metadata["size"] = modelInfo.Size
+			}
+			if modelInfo.Digest != "" {
+				metadata["digest"] = modelInfo.Digest
+			}
+			if modelInfo.ModifiedAt != "" {
+				metadata["modified_at"] = modelInfo.ModifiedAt
+			}
+			details := modelInfo.Details
+			if details.ParentModel != "" || details.Format != "" || details.Family != "" || len(details.Families) > 0 || details.ParameterSize != "" || details.QuantizationLevel != "" {
+				metadata["details"] = modelInfo.Details
+			}
+			if len(metadata) == 0 {
+				metadata = nil
+			}
+
+			result.Data = append(result.Data, OpenAIModel{
+				ID:       modelInfo.Name,
+				Object:   "model",
+				Created:  0,
+				OwnedBy:  "ollama",
+				Metadata: metadata,
+			})
+		}
+
+		c.JSON(http.StatusOK, gin.H{
+			"success": true,
+			"data":    result.Data,
+		})
+		return
+	}
+
+	// 对于 Gemini 渠道，使用特殊处理
+	if channel.Type == constant.ChannelTypeGemini {
+		// 获取用于请求的可用密钥（多密钥渠道优先使用启用状态的密钥）
+		key, _, apiErr := channel.GetNextEnabledKey()
+		if apiErr != nil {
+			c.JSON(http.StatusOK, gin.H{
+				"success": false,
+				"message": fmt.Sprintf("获取渠道密钥失败: %s", apiErr.Error()),
+			})
+			return
+		}
+		key = strings.TrimSpace(key)
+		models, err := gemini.FetchGeminiModels(baseURL, key, channel.GetSetting().Proxy)
+		if err != nil {
+			c.JSON(http.StatusOK, gin.H{
+				"success": false,
+				"message": fmt.Sprintf("获取Gemini模型失败: %s", err.Error()),
+			})
+			return
+		}
+
+		c.JSON(http.StatusOK, gin.H{
+			"success": true,
+			"message": "",
+			"data":    models,
+		})
+		return
+	}
+
 	var url string
 	switch channel.Type {
-	case constant.ChannelTypeGemini:
-		// curl https://example.com/v1beta/models?key=$GEMINI_API_KEY
-		url = fmt.Sprintf("%s/v1beta/openai/models", baseURL) // Remove key in url since we need to use AuthHeader
 	case constant.ChannelTypeAli:
 		url = fmt.Sprintf("%s/compatible-mode/v1/models", baseURL)
 	case constant.ChannelTypeZhipu_v4:
-		url = fmt.Sprintf("%s/api/paas/v4/models", baseURL)
+		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)
+		}
+	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)
+		} else {
+			url = fmt.Sprintf("%s/v1/models", baseURL)
+		}
 	default:
 		url = fmt.Sprintf("%s/v1/models", baseURL)
 	}
 
-	// 获取响应体 - 根据渠道类型决定是否添加 AuthHeader
-	var body []byte
-	key := strings.Split(channel.Key, "\n")[0]
-	switch channel.Type {
-	case constant.ChannelTypeAnthropic:
-		body, err = GetResponseBody("GET", url, channel, GetClaudeAuthHeader(key))
-	default:
-		body, err = GetResponseBody("GET", url, channel, GetAuthHeader(key))
+	// 获取用于请求的可用密钥（多密钥渠道优先使用启用状态的密钥）
+	key, _, apiErr := channel.GetNextEnabledKey()
+	if apiErr != nil {
+		c.JSON(http.StatusOK, gin.H{
+			"success": false,
+			"message": fmt.Sprintf("获取渠道密钥失败: %s", apiErr.Error()),
+		})
+		return
 	}
+	key = strings.TrimSpace(key)
+
+	headers, err := buildFetchModelsHeaders(channel, key)
+	if err != nil {
+		common.ApiError(c, err)
+		return
+	}
+
+	body, err := GetResponseBody("GET", url, channel, headers)
 	if err != nil {
 		common.ApiError(c, err)
 		return
@@ -271,7 +402,7 @@ func SearchChannels(c *gin.Context) {
 		}
 		for _, tag := range tags {
 			if tag != nil && *tag != "" {
-				tagChannel, err := model.GetChannelsByTag(*tag, idSort)
+				tagChannel, err := model.GetChannelsByTag(*tag, idSort, false)
 				if err == nil {
 					channelData = append(channelData, tagChannel...)
 				}
@@ -475,9 +606,60 @@ func validateChannel(channel *model.Channel, isAdd bool) error {
 		}
 	}
 
+	// Codex OAuth key validation (optional, only when JSON object is provided)
+	if channel.Type == constant.ChannelTypeCodex {
+		trimmedKey := strings.TrimSpace(channel.Key)
+		if isAdd || trimmedKey != "" {
+			if !strings.HasPrefix(trimmedKey, "{") {
+				return fmt.Errorf("Codex key must be a valid JSON object")
+			}
+			var keyMap map[string]any
+			if err := common.Unmarshal([]byte(trimmedKey), &keyMap); err != nil {
+				return fmt.Errorf("Codex key must be a valid JSON object")
+			}
+			if v, ok := keyMap["access_token"]; !ok || v == nil || strings.TrimSpace(fmt.Sprintf("%v", v)) == "" {
+				return fmt.Errorf("Codex key JSON must include access_token")
+			}
+			if v, ok := keyMap["account_id"]; !ok || v == nil || strings.TrimSpace(fmt.Sprintf("%v", v)) == "" {
+				return fmt.Errorf("Codex key JSON must include account_id")
+			}
+		}
+	}
+
 	return nil
 }
 
+func RefreshCodexChannelCredential(c *gin.Context) {
+	channelId, err := strconv.Atoi(c.Param("id"))
+	if err != nil {
+		common.ApiError(c, fmt.Errorf("invalid channel id: %w", err))
+		return
+	}
+
+	ctx, cancel := context.WithTimeout(c.Request.Context(), 10*time.Second)
+	defer cancel()
+
+	oauthKey, ch, err := service.RefreshCodexChannelCredential(ctx, channelId, service.CodexCredentialRefreshOptions{ResetCaches: true})
+	if err != nil {
+		c.JSON(http.StatusOK, gin.H{"success": false, "message": err.Error()})
+		return
+	}
+
+	c.JSON(http.StatusOK, gin.H{
+		"success": true,
+		"message": "refreshed",
+		"data": gin.H{
+			"expires_at":   oauthKey.Expired,
+			"last_refresh": oauthKey.LastRefresh,
+			"account_id":   oauthKey.AccountID,
+			"email":        oauthKey.Email,
+			"channel_id":   ch.Id,
+			"channel_type": ch.Type,
+			"channel_name": ch.Name,
+		},
+	})
+}
+
 type AddChannelRequest struct {
 	Mode                      string                `json:"mode"`
 	MultiKeyMode              constant.MultiKeyMode `json:"multi_key_mode"`
@@ -649,13 +831,15 @@ func DeleteDisabledChannel(c *gin.Context) {
 }
 
 type ChannelTag struct {
-	Tag          string  `json:"tag"`
-	NewTag       *string `json:"new_tag"`
-	Priority     *int64  `json:"priority"`
-	Weight       *uint   `json:"weight"`
-	ModelMapping *string `json:"model_mapping"`
-	Models       *string `json:"models"`
-	Groups       *string `json:"groups"`
+	Tag            string  `json:"tag"`
+	NewTag         *string `json:"new_tag"`
+	Priority       *int64  `json:"priority"`
+	Weight         *uint   `json:"weight"`
+	ModelMapping   *string `json:"model_mapping"`
+	Models         *string `json:"models"`
+	Groups         *string `json:"groups"`
+	ParamOverride  *string `json:"param_override"`
+	HeaderOverride *string `json:"header_override"`
 }
 
 func DisableTagChannels(c *gin.Context) {
@@ -721,7 +905,29 @@ func EditTagChannels(c *gin.Context) {
 		})
 		return
 	}
-	err = model.EditChannelByTag(channelTag.Tag, channelTag.NewTag, channelTag.ModelMapping, channelTag.Models, channelTag.Groups, channelTag.Priority, channelTag.Weight)
+	if channelTag.ParamOverride != nil {
+		trimmed := strings.TrimSpace(*channelTag.ParamOverride)
+		if trimmed != "" && !json.Valid([]byte(trimmed)) {
+			c.JSON(http.StatusOK, gin.H{
+				"success": false,
+				"message": "参数覆盖必须是合法的 JSON 格式",
+			})
+			return
+		}
+		channelTag.ParamOverride = common.GetPointer[string](trimmed)
+	}
+	if channelTag.HeaderOverride != nil {
+		trimmed := strings.TrimSpace(*channelTag.HeaderOverride)
+		if trimmed != "" && !json.Valid([]byte(trimmed)) {
+			c.JSON(http.StatusOK, gin.H{
+				"success": false,
+				"message": "请求头覆盖必须是合法的 JSON 格式",
+			})
+			return
+		}
+		channelTag.HeaderOverride = common.GetPointer[string](trimmed)
+	}
+	err = model.EditChannelByTag(channelTag.Tag, channelTag.NewTag, channelTag.ModelMapping, channelTag.Models, channelTag.Groups, channelTag.Priority, channelTag.Weight, channelTag.ParamOverride, channelTag.HeaderOverride)
 	if err != nil {
 		common.ApiError(c, err)
 		return
@@ -844,9 +1050,6 @@ func UpdateChannel(c *gin.Context) {
 						// 单个JSON密钥
 						newKeys = []string{channel.Key}
 					}
-					// 合并密钥
-					allKeys := append(existingKeys, newKeys...)
-					channel.Key = strings.Join(allKeys, "\n")
 				} else {
 					// 普通渠道的处理
 					inputKeys := strings.Split(channel.Key, "\n")
@@ -856,10 +1059,31 @@ func UpdateChannel(c *gin.Context) {
 							newKeys = append(newKeys, key)
 						}
 					}
-					// 合并密钥
-					allKeys := append(existingKeys, newKeys...)
-					channel.Key = strings.Join(allKeys, "\n")
 				}
+
+				seen := make(map[string]struct{}, len(existingKeys)+len(newKeys))
+				for _, key := range existingKeys {
+					normalized := strings.TrimSpace(key)
+					if normalized == "" {
+						continue
+					}
+					seen[normalized] = struct{}{}
+				}
+				dedupedNewKeys := make([]string, 0, len(newKeys))
+				for _, key := range newKeys {
+					normalized := strings.TrimSpace(key)
+					if normalized == "" {
+						continue
+					}
+					if _, ok := seen[normalized]; ok {
+						continue
+					}
+					seen[normalized] = struct{}{}
+					dedupedNewKeys = append(dedupedNewKeys, normalized)
+				}
+
+				allKeys := append(existingKeys, dedupedNewKeys...)
+				channel.Key = strings.Join(allKeys, "\n")
 			}
 		case "replace":
 			// 覆盖模式：直接使用新密钥（默认行为，不需要特殊处理）
@@ -902,6 +1126,49 @@ func FetchModels(c *gin.Context) {
 		baseURL = constant.ChannelBaseURLs[req.Type]
 	}
 
+	// remove line breaks and extra spaces.
+	key := strings.TrimSpace(req.Key)
+	key = strings.Split(key, "\n")[0]
+
+	if req.Type == constant.ChannelTypeOllama {
+		models, err := ollama.FetchOllamaModels(baseURL, key)
+		if err != nil {
+			c.JSON(http.StatusOK, gin.H{
+				"success": false,
+				"message": fmt.Sprintf("获取Ollama模型失败: %s", err.Error()),
+			})
+			return
+		}
+
+		names := make([]string, 0, len(models))
+		for _, modelInfo := range models {
+			names = append(names, modelInfo.Name)
+		}
+
+		c.JSON(http.StatusOK, gin.H{
+			"success": true,
+			"data":    names,
+		})
+		return
+	}
+
+	if req.Type == constant.ChannelTypeGemini {
+		models, err := gemini.FetchGeminiModels(baseURL, key, "")
+		if err != nil {
+			c.JSON(http.StatusOK, gin.H{
+				"success": false,
+				"message": fmt.Sprintf("获取Gemini模型失败: %s", err.Error()),
+			})
+			return
+		}
+
+		c.JSON(http.StatusOK, gin.H{
+			"success": true,
+			"data":    models,
+		})
+		return
+	}
+
 	client := &http.Client{}
 	url := fmt.Sprintf("%s/v1/models", baseURL)
 
@@ -914,10 +1181,6 @@ func FetchModels(c *gin.Context) {
 		return
 	}
 
-	// remove line breaks and extra spaces.
-	key := strings.TrimSpace(req.Key)
-	// If the key contains a line break, only take the first part.
-	key = strings.Split(key, "\n")[0]
 	request.Header.Set("Authorization", "Bearer "+key)
 
 	response, err := client.Do(request)
@@ -997,7 +1260,7 @@ func GetTagModels(c *gin.Context) {
 		return
 	}
 
-	channels, err := model.GetChannelsByTag(tag, false) // Assuming false for idSort is fine here
+	channels, err := model.GetChannelsByTag(tag, false, false) // idSort=false, selectAll=false
 	if err != nil {
 		c.JSON(http.StatusInternalServerError, gin.H{
 			"success": false,
@@ -1567,3 +1830,262 @@ func ManageMultiKeys(c *gin.Context) {
 		return
 	}
 }
+
+// OllamaPullModel 拉取 Ollama 模型
+func OllamaPullModel(c *gin.Context) {
+	var req struct {
+		ChannelID int    `json:"channel_id"`
+		ModelName string `json:"model_name"`
+	}
+
+	if err := c.ShouldBindJSON(&req); err != nil {
+		c.JSON(http.StatusBadRequest, gin.H{
+			"success": false,
+			"message": "Invalid request parameters",
+		})
+		return
+	}
+
+	if req.ChannelID == 0 || req.ModelName == "" {
+		c.JSON(http.StatusBadRequest, gin.H{
+			"success": false,
+			"message": "Channel ID and model name are required",
+		})
+		return
+	}
+
+	// 获取渠道信息
+	channel, err := model.GetChannelById(req.ChannelID, true)
+	if err != nil {
+		c.JSON(http.StatusNotFound, gin.H{
+			"success": false,
+			"message": "Channel not found",
+		})
+		return
+	}
+
+	// 检查是否是 Ollama 渠道
+	if channel.Type != constant.ChannelTypeOllama {
+		c.JSON(http.StatusBadRequest, gin.H{
+			"success": false,
+			"message": "This operation is only supported for Ollama channels",
+		})
+		return
+	}
+
+	baseURL := constant.ChannelBaseURLs[channel.Type]
+	if channel.GetBaseURL() != "" {
+		baseURL = channel.GetBaseURL()
+	}
+
+	key := strings.Split(channel.Key, "\n")[0]
+	err = ollama.PullOllamaModel(baseURL, key, req.ModelName)
+	if err != nil {
+		c.JSON(http.StatusInternalServerError, gin.H{
+			"success": false,
+			"message": fmt.Sprintf("Failed to pull model: %s", err.Error()),
+		})
+		return
+	}
+
+	c.JSON(http.StatusOK, gin.H{
+		"success": true,
+		"message": fmt.Sprintf("Model %s pulled successfully", req.ModelName),
+	})
+}
+
+// OllamaPullModelStream 流式拉取 Ollama 模型
+func OllamaPullModelStream(c *gin.Context) {
+	var req struct {
+		ChannelID int    `json:"channel_id"`
+		ModelName string `json:"model_name"`
+	}
+
+	if err := c.ShouldBindJSON(&req); err != nil {
+		c.JSON(http.StatusBadRequest, gin.H{
+			"success": false,
+			"message": "Invalid request parameters",
+		})
+		return
+	}
+
+	if req.ChannelID == 0 || req.ModelName == "" {
+		c.JSON(http.StatusBadRequest, gin.H{
+			"success": false,
+			"message": "Channel ID and model name are required",
+		})
+		return
+	}
+
+	// 获取渠道信息
+	channel, err := model.GetChannelById(req.ChannelID, true)
+	if err != nil {
+		c.JSON(http.StatusNotFound, gin.H{
+			"success": false,
+			"message": "Channel not found",
+		})
+		return
+	}
+
+	// 检查是否是 Ollama 渠道
+	if channel.Type != constant.ChannelTypeOllama {
+		c.JSON(http.StatusBadRequest, gin.H{
+			"success": false,
+			"message": "This operation is only supported for Ollama channels",
+		})
+		return
+	}
+
+	baseURL := constant.ChannelBaseURLs[channel.Type]
+	if channel.GetBaseURL() != "" {
+		baseURL = channel.GetBaseURL()
+	}
+
+	// 设置 SSE 头部
+	c.Header("Content-Type", "text/event-stream")
+	c.Header("Cache-Control", "no-cache")
+	c.Header("Connection", "keep-alive")
+	c.Header("Access-Control-Allow-Origin", "*")
+
+	key := strings.Split(channel.Key, "\n")[0]
+
+	// 创建进度回调函数
+	progressCallback := func(progress ollama.OllamaPullResponse) {
+		data, _ := json.Marshal(progress)
+		fmt.Fprintf(c.Writer, "data: %s\n\n", string(data))
+		c.Writer.Flush()
+	}
+
+	// 执行拉取
+	err = ollama.PullOllamaModelStream(baseURL, key, req.ModelName, progressCallback)
+
+	if err != nil {
+		errorData, _ := json.Marshal(gin.H{
+			"error": err.Error(),
+		})
+		fmt.Fprintf(c.Writer, "data: %s\n\n", string(errorData))
+	} else {
+		successData, _ := json.Marshal(gin.H{
+			"message": fmt.Sprintf("Model %s pulled successfully", req.ModelName),
+		})
+		fmt.Fprintf(c.Writer, "data: %s\n\n", string(successData))
+	}
+
+	// 发送结束标志
+	fmt.Fprintf(c.Writer, "data: [DONE]\n\n")
+	c.Writer.Flush()
+}
+
+// OllamaDeleteModel 删除 Ollama 模型
+func OllamaDeleteModel(c *gin.Context) {
+	var req struct {
+		ChannelID int    `json:"channel_id"`
+		ModelName string `json:"model_name"`
+	}
+
+	if err := c.ShouldBindJSON(&req); err != nil {
+		c.JSON(http.StatusBadRequest, gin.H{
+			"success": false,
+			"message": "Invalid request parameters",
+		})
+		return
+	}
+
+	if req.ChannelID == 0 || req.ModelName == "" {
+		c.JSON(http.StatusBadRequest, gin.H{
+			"success": false,
+			"message": "Channel ID and model name are required",
+		})
+		return
+	}
+
+	// 获取渠道信息
+	channel, err := model.GetChannelById(req.ChannelID, true)
+	if err != nil {
+		c.JSON(http.StatusNotFound, gin.H{
+			"success": false,
+			"message": "Channel not found",
+		})
+		return
+	}
+
+	// 检查是否是 Ollama 渠道
+	if channel.Type != constant.ChannelTypeOllama {
+		c.JSON(http.StatusBadRequest, gin.H{
+			"success": false,
+			"message": "This operation is only supported for Ollama channels",
+		})
+		return
+	}
+
+	baseURL := constant.ChannelBaseURLs[channel.Type]
+	if channel.GetBaseURL() != "" {
+		baseURL = channel.GetBaseURL()
+	}
+
+	key := strings.Split(channel.Key, "\n")[0]
+	err = ollama.DeleteOllamaModel(baseURL, key, req.ModelName)
+	if err != nil {
+		c.JSON(http.StatusInternalServerError, gin.H{
+			"success": false,
+			"message": fmt.Sprintf("Failed to delete model: %s", err.Error()),
+		})
+		return
+	}
+
+	c.JSON(http.StatusOK, gin.H{
+		"success": true,
+		"message": fmt.Sprintf("Model %s deleted successfully", req.ModelName),
+	})
+}
+
+// OllamaVersion 获取 Ollama 服务版本信息
+func OllamaVersion(c *gin.Context) {
+	id, err := strconv.Atoi(c.Param("id"))
+	if err != nil {
+		c.JSON(http.StatusBadRequest, gin.H{
+			"success": false,
+			"message": "Invalid channel id",
+		})
+		return
+	}
+
+	channel, err := model.GetChannelById(id, true)
+	if err != nil {
+		c.JSON(http.StatusNotFound, gin.H{
+			"success": false,
+			"message": "Channel not found",
+		})
+		return
+	}
+
+	if channel.Type != constant.ChannelTypeOllama {
+		c.JSON(http.StatusBadRequest, gin.H{
+			"success": false,
+			"message": "This operation is only supported for Ollama channels",
+		})
+		return
+	}
+
+	baseURL := constant.ChannelBaseURLs[channel.Type]
+	if channel.GetBaseURL() != "" {
+		baseURL = channel.GetBaseURL()
+	}
+
+	key := strings.Split(channel.Key, "\n")[0]
+	version, err := ollama.FetchOllamaVersion(baseURL, key)
+	if err != nil {
+		c.JSON(http.StatusOK, gin.H{
+			"success": false,
+			"message": fmt.Sprintf("获取Ollama版本失败: %s", err.Error()),
+		})
+		return
+	}
+
+	c.JSON(http.StatusOK, gin.H{
+		"success": true,
+		"data": gin.H{
+			"version": version,
+		},
+	})
+}

controller/channel_affinity_cache.go

@@ -0,0 +1,60 @@
+package controller
+
+import (
+	"net/http"
+	"strings"
+
+	"github.com/QuantumNous/new-api/service"
+	"github.com/gin-gonic/gin"
+)
+
+func GetChannelAffinityCacheStats(c *gin.Context) {
+	stats := service.GetChannelAffinityCacheStats()
+	c.JSON(http.StatusOK, gin.H{
+		"success": true,
+		"message": "",
+		"data":    stats,
+	})
+}
+
+func ClearChannelAffinityCache(c *gin.Context) {
+	all := strings.TrimSpace(c.Query("all"))
+	ruleName := strings.TrimSpace(c.Query("rule_name"))
+
+	if all == "true" {
+		deleted := service.ClearChannelAffinityCacheAll()
+		c.JSON(http.StatusOK, gin.H{
+			"success": true,
+			"message": "",
+			"data": gin.H{
+				"deleted": deleted,
+			},
+		})
+		return
+	}
+
+	if ruleName == "" {
+		c.JSON(http.StatusBadRequest, gin.H{
+			"success": false,
+			"message": "缺少参数：rule_name，或使用 all=true 清空全部",
+		})
+		return
+	}
+
+	deleted, err := service.ClearChannelAffinityCacheByRuleName(ruleName)
+	if err != nil {
+		c.JSON(http.StatusBadRequest, gin.H{
+			"success": false,
+			"message": err.Error(),
+		})
+		return
+	}
+
+	c.JSON(http.StatusOK, gin.H{
+		"success": true,
+		"message": "",
+		"data": gin.H{
+			"deleted": deleted,
+		},
+	})
+}

controller/checkin.go

@@ -0,0 +1,72 @@
+package controller
+
+import (
+	"fmt"
+	"net/http"
+	"time"
+
+	"github.com/QuantumNous/new-api/common"
+	"github.com/QuantumNous/new-api/logger"
+	"github.com/QuantumNous/new-api/model"
+	"github.com/QuantumNous/new-api/setting/operation_setting"
+	"github.com/gin-gonic/gin"
+)
+
+// GetCheckinStatus 获取用户签到状态和历史记录
+func GetCheckinStatus(c *gin.Context) {
+	setting := operation_setting.GetCheckinSetting()
+	if !setting.Enabled {
+		common.ApiErrorMsg(c, "签到功能未启用")
+		return
+	}
+	userId := c.GetInt("id")
+	// 获取月份参数，默认为当前月份
+	month := c.DefaultQuery("month", time.Now().Format("2006-01"))
+
+	stats, err := model.GetUserCheckinStats(userId, month)
+	if err != nil {
+		c.JSON(http.StatusOK, gin.H{
+			"success": false,
+			"message": err.Error(),
+		})
+		return
+	}
+
+	c.JSON(http.StatusOK, gin.H{
+		"success": true,
+		"data": gin.H{
+			"enabled":   setting.Enabled,
+			"min_quota": setting.MinQuota,
+			"max_quota": setting.MaxQuota,
+			"stats":     stats,
+		},
+	})
+}
+
+// DoCheckin 执行用户签到
+func DoCheckin(c *gin.Context) {
+	setting := operation_setting.GetCheckinSetting()
+	if !setting.Enabled {
+		common.ApiErrorMsg(c, "签到功能未启用")
+		return
+	}
+
+	userId := c.GetInt("id")
+
+	checkin, err := model.UserCheckin(userId)
+	if err != nil {
+		c.JSON(http.StatusOK, gin.H{
+			"success": false,
+			"message": err.Error(),
+		})
+		return
+	}
+	model.RecordLog(userId, model.LogTypeSystem, fmt.Sprintf("用户签到，获得额度 %s", logger.LogQuota(checkin.QuotaAwarded)))
+	c.JSON(http.StatusOK, gin.H{
+		"success": true,
+		"message": "签到成功",
+		"data": gin.H{
+			"quota_awarded": checkin.QuotaAwarded,
+			"checkin_date":  checkin.CheckinDate},
+	})
+}

controller/codex_oauth.go

@@ -0,0 +1,243 @@
+package controller
+
+import (
+	"context"
+	"errors"
+	"fmt"
+	"net/http"
+	"net/url"
+	"strconv"
+	"strings"
+	"time"
+
+	"github.com/QuantumNous/new-api/common"
+	"github.com/QuantumNous/new-api/constant"
+	"github.com/QuantumNous/new-api/model"
+	"github.com/QuantumNous/new-api/relay/channel/codex"
+	"github.com/QuantumNous/new-api/service"
+
+	"github.com/gin-contrib/sessions"
+	"github.com/gin-gonic/gin"
+)
+
+type codexOAuthCompleteRequest struct {
+	Input string `json:"input"`
+}
+
+func codexOAuthSessionKey(channelID int, field string) string {
+	return fmt.Sprintf("codex_oauth_%s_%d", field, channelID)
+}
+
+func parseCodexAuthorizationInput(input string) (code string, state string, err error) {
+	v := strings.TrimSpace(input)
+	if v == "" {
+		return "", "", errors.New("empty input")
+	}
+	if strings.Contains(v, "#") {
+		parts := strings.SplitN(v, "#", 2)
+		code = strings.TrimSpace(parts[0])
+		state = strings.TrimSpace(parts[1])
+		return code, state, nil
+	}
+	if strings.Contains(v, "code=") {
+		u, parseErr := url.Parse(v)
+		if parseErr == nil {
+			q := u.Query()
+			code = strings.TrimSpace(q.Get("code"))
+			state = strings.TrimSpace(q.Get("state"))
+			return code, state, nil
+		}
+		q, parseErr := url.ParseQuery(v)
+		if parseErr == nil {
+			code = strings.TrimSpace(q.Get("code"))
+			state = strings.TrimSpace(q.Get("state"))
+			return code, state, nil
+		}
+	}
+
+	code = v
+	return code, "", nil
+}
+
+func StartCodexOAuth(c *gin.Context) {
+	startCodexOAuthWithChannelID(c, 0)
+}
+
+func StartCodexOAuthForChannel(c *gin.Context) {
+	channelID, err := strconv.Atoi(c.Param("id"))
+	if err != nil {
+		common.ApiError(c, fmt.Errorf("invalid channel id: %w", err))
+		return
+	}
+	startCodexOAuthWithChannelID(c, channelID)
+}
+
+func startCodexOAuthWithChannelID(c *gin.Context, channelID int) {
+	if channelID > 0 {
+		ch, err := model.GetChannelById(channelID, false)
+		if err != nil {
+			common.ApiError(c, err)
+			return
+		}
+		if ch == nil {
+			c.JSON(http.StatusOK, gin.H{"success": false, "message": "channel not found"})
+			return
+		}
+		if ch.Type != constant.ChannelTypeCodex {
+			c.JSON(http.StatusOK, gin.H{"success": false, "message": "channel type is not Codex"})
+			return
+		}
+	}
+
+	flow, err := service.CreateCodexOAuthAuthorizationFlow()
+	if err != nil {
+		common.ApiError(c, err)
+		return
+	}
+
+	session := sessions.Default(c)
+	session.Set(codexOAuthSessionKey(channelID, "state"), flow.State)
+	session.Set(codexOAuthSessionKey(channelID, "verifier"), flow.Verifier)
+	session.Set(codexOAuthSessionKey(channelID, "created_at"), time.Now().Unix())
+	_ = session.Save()
+
+	c.JSON(http.StatusOK, gin.H{
+		"success": true,
+		"message": "",
+		"data": gin.H{
+			"authorize_url": flow.AuthorizeURL,
+		},
+	})
+}
+
+func CompleteCodexOAuth(c *gin.Context) {
+	completeCodexOAuthWithChannelID(c, 0)
+}
+
+func CompleteCodexOAuthForChannel(c *gin.Context) {
+	channelID, err := strconv.Atoi(c.Param("id"))
+	if err != nil {
+		common.ApiError(c, fmt.Errorf("invalid channel id: %w", err))
+		return
+	}
+	completeCodexOAuthWithChannelID(c, channelID)
+}
+
+func completeCodexOAuthWithChannelID(c *gin.Context, channelID int) {
+	req := codexOAuthCompleteRequest{}
+	if err := c.ShouldBindJSON(&req); err != nil {
+		common.ApiError(c, err)
+		return
+	}
+
+	code, state, err := parseCodexAuthorizationInput(req.Input)
+	if err != nil {
+		c.JSON(http.StatusOK, gin.H{"success": false, "message": err.Error()})
+		return
+	}
+	if strings.TrimSpace(code) == "" {
+		c.JSON(http.StatusOK, gin.H{"success": false, "message": "missing authorization code"})
+		return
+	}
+	if strings.TrimSpace(state) == "" {
+		c.JSON(http.StatusOK, gin.H{"success": false, "message": "missing state in input"})
+		return
+	}
+
+	if channelID > 0 {
+		ch, err := model.GetChannelById(channelID, false)
+		if err != nil {
+			common.ApiError(c, err)
+			return
+		}
+		if ch == nil {
+			c.JSON(http.StatusOK, gin.H{"success": false, "message": "channel not found"})
+			return
+		}
+		if ch.Type != constant.ChannelTypeCodex {
+			c.JSON(http.StatusOK, gin.H{"success": false, "message": "channel type is not Codex"})
+			return
+		}
+	}
+
+	session := sessions.Default(c)
+	expectedState, _ := session.Get(codexOAuthSessionKey(channelID, "state")).(string)
+	verifier, _ := session.Get(codexOAuthSessionKey(channelID, "verifier")).(string)
+	if strings.TrimSpace(expectedState) == "" || strings.TrimSpace(verifier) == "" {
+		c.JSON(http.StatusOK, gin.H{"success": false, "message": "oauth flow not started or session expired"})
+		return
+	}
+	if state != expectedState {
+		c.JSON(http.StatusOK, gin.H{"success": false, "message": "state mismatch"})
+		return
+	}
+
+	ctx, cancel := context.WithTimeout(c.Request.Context(), 15*time.Second)
+	defer cancel()
+
+	tokenRes, err := service.ExchangeCodexAuthorizationCode(ctx, code, verifier)
+	if err != nil {
+		c.JSON(http.StatusOK, gin.H{"success": false, "message": err.Error()})
+		return
+	}
+
+	accountID, ok := service.ExtractCodexAccountIDFromJWT(tokenRes.AccessToken)
+	if !ok {
+		c.JSON(http.StatusOK, gin.H{"success": false, "message": "failed to extract account_id from access_token"})
+		return
+	}
+	email, _ := service.ExtractEmailFromJWT(tokenRes.AccessToken)
+
+	key := codex.OAuthKey{
+		AccessToken:  tokenRes.AccessToken,
+		RefreshToken: tokenRes.RefreshToken,
+		AccountID:    accountID,
+		LastRefresh:  time.Now().Format(time.RFC3339),
+		Expired:      tokenRes.ExpiresAt.Format(time.RFC3339),
+		Email:        email,
+		Type:         "codex",
+	}
+	encoded, err := common.Marshal(key)
+	if err != nil {
+		common.ApiError(c, err)
+		return
+	}
+
+	session.Delete(codexOAuthSessionKey(channelID, "state"))
+	session.Delete(codexOAuthSessionKey(channelID, "verifier"))
+	session.Delete(codexOAuthSessionKey(channelID, "created_at"))
+	_ = session.Save()
+
+	if channelID > 0 {
+		if err := model.DB.Model(&model.Channel{}).Where("id = ?", channelID).Update("key", string(encoded)).Error; err != nil {
+			common.ApiError(c, err)
+			return
+		}
+		model.InitChannelCache()
+		service.ResetProxyClientCache()
+		c.JSON(http.StatusOK, gin.H{
+			"success": true,
+			"message": "saved",
+			"data": gin.H{
+				"channel_id":   channelID,
+				"account_id":   accountID,
+				"email":        email,
+				"expires_at":   key.Expired,
+				"last_refresh": key.LastRefresh,
+			},
+		})
+		return
+	}
+
+	c.JSON(http.StatusOK, gin.H{
+		"success": true,
+		"message": "generated",
+		"data": gin.H{
+			"key":          string(encoded),
+			"account_id":   accountID,
+			"email":        email,
+			"expires_at":   key.Expired,
+			"last_refresh": key.LastRefresh,
+		},
+	})
+}

controller/codex_usage.go

@@ -0,0 +1,124 @@
+package controller
+
+import (
+	"context"
+	"encoding/json"
+	"fmt"
+	"net/http"
+	"strconv"
+	"strings"
+	"time"
+
+	"github.com/QuantumNous/new-api/common"
+	"github.com/QuantumNous/new-api/constant"
+	"github.com/QuantumNous/new-api/model"
+	"github.com/QuantumNous/new-api/relay/channel/codex"
+	"github.com/QuantumNous/new-api/service"
+
+	"github.com/gin-gonic/gin"
+)
+
+func GetCodexChannelUsage(c *gin.Context) {
+	channelId, err := strconv.Atoi(c.Param("id"))
+	if err != nil {
+		common.ApiError(c, fmt.Errorf("invalid channel id: %w", err))
+		return
+	}
+
+	ch, err := model.GetChannelById(channelId, true)
+	if err != nil {
+		common.ApiError(c, err)
+		return
+	}
+	if ch == nil {
+		c.JSON(http.StatusOK, gin.H{"success": false, "message": "channel not found"})
+		return
+	}
+	if ch.Type != constant.ChannelTypeCodex {
+		c.JSON(http.StatusOK, gin.H{"success": false, "message": "channel type is not Codex"})
+		return
+	}
+	if ch.ChannelInfo.IsMultiKey {
+		c.JSON(http.StatusOK, gin.H{"success": false, "message": "multi-key channel is not supported"})
+		return
+	}
+
+	oauthKey, err := codex.ParseOAuthKey(strings.TrimSpace(ch.Key))
+	if err != nil {
+		c.JSON(http.StatusOK, gin.H{"success": false, "message": err.Error()})
+		return
+	}
+	accessToken := strings.TrimSpace(oauthKey.AccessToken)
+	accountID := strings.TrimSpace(oauthKey.AccountID)
+	if accessToken == "" {
+		c.JSON(http.StatusOK, gin.H{"success": false, "message": "codex channel: access_token is required"})
+		return
+	}
+	if accountID == "" {
+		c.JSON(http.StatusOK, gin.H{"success": false, "message": "codex channel: account_id is required"})
+		return
+	}
+
+	client, err := service.NewProxyHttpClient(ch.GetSetting().Proxy)
+	if err != nil {
+		common.ApiError(c, err)
+		return
+	}
+
+	ctx, cancel := context.WithTimeout(c.Request.Context(), 15*time.Second)
+	defer cancel()
+
+	statusCode, body, err := service.FetchCodexWhamUsage(ctx, client, ch.GetBaseURL(), accessToken, accountID)
+	if err != nil {
+		c.JSON(http.StatusOK, gin.H{"success": false, "message": err.Error()})
+		return
+	}
+
+	if (statusCode == http.StatusUnauthorized || statusCode == http.StatusForbidden) && strings.TrimSpace(oauthKey.RefreshToken) != "" {
+		refreshCtx, refreshCancel := context.WithTimeout(c.Request.Context(), 10*time.Second)
+		defer refreshCancel()
+
+		res, refreshErr := service.RefreshCodexOAuthToken(refreshCtx, oauthKey.RefreshToken)
+		if refreshErr == nil {
+			oauthKey.AccessToken = res.AccessToken
+			oauthKey.RefreshToken = res.RefreshToken
+			oauthKey.LastRefresh = time.Now().Format(time.RFC3339)
+			oauthKey.Expired = res.ExpiresAt.Format(time.RFC3339)
+			if strings.TrimSpace(oauthKey.Type) == "" {
+				oauthKey.Type = "codex"
+			}
+
+			encoded, encErr := common.Marshal(oauthKey)
+			if encErr == nil {
+				_ = model.DB.Model(&model.Channel{}).Where("id = ?", ch.Id).Update("key", string(encoded)).Error
+				model.InitChannelCache()
+				service.ResetProxyClientCache()
+			}
+
+			ctx2, cancel2 := context.WithTimeout(c.Request.Context(), 15*time.Second)
+			defer cancel2()
+			statusCode, body, err = service.FetchCodexWhamUsage(ctx2, client, ch.GetBaseURL(), oauthKey.AccessToken, accountID)
+			if err != nil {
+				c.JSON(http.StatusOK, gin.H{"success": false, "message": err.Error()})
+				return
+			}
+		}
+	}
+
+	var payload any
+	if json.Unmarshal(body, &payload) != nil {
+		payload = string(body)
+	}
+
+	ok := statusCode >= 200 && statusCode < 300
+	resp := gin.H{
+		"success":         ok,
+		"message":         "",
+		"upstream_status": statusCode,
+		"data":            payload,
+	}
+	if !ok {
+		resp["message"] = fmt.Sprintf("upstream status: %d", statusCode)
+	}
+	c.JSON(http.StatusOK, resp)
+}

controller/deployment.go

@@ -0,0 +1,810 @@
+package controller
+
+import (
+	"bytes"
+	"encoding/json"
+	"fmt"
+	"strconv"
+	"strings"
+	"time"
+
+	"github.com/QuantumNous/new-api/common"
+	"github.com/QuantumNous/new-api/pkg/ionet"
+	"github.com/gin-gonic/gin"
+)
+
+func getIoAPIKey(c *gin.Context) (string, bool) {
+	common.OptionMapRWMutex.RLock()
+	enabled := common.OptionMap["model_deployment.ionet.enabled"] == "true"
+	apiKey := common.OptionMap["model_deployment.ionet.api_key"]
+	common.OptionMapRWMutex.RUnlock()
+	if !enabled || strings.TrimSpace(apiKey) == "" {
+		common.ApiErrorMsg(c, "io.net model deployment is not enabled or api key missing")
+		return "", false
+	}
+	return apiKey, true
+}
+
+func GetModelDeploymentSettings(c *gin.Context) {
+	common.OptionMapRWMutex.RLock()
+	enabled := common.OptionMap["model_deployment.ionet.enabled"] == "true"
+	hasAPIKey := strings.TrimSpace(common.OptionMap["model_deployment.ionet.api_key"]) != ""
+	common.OptionMapRWMutex.RUnlock()
+
+	common.ApiSuccess(c, gin.H{
+		"provider":    "io.net",
+		"enabled":     enabled,
+		"configured":  hasAPIKey,
+		"can_connect": enabled && hasAPIKey,
+	})
+}
+
+func getIoClient(c *gin.Context) (*ionet.Client, bool) {
+	apiKey, ok := getIoAPIKey(c)
+	if !ok {
+		return nil, false
+	}
+	return ionet.NewClient(apiKey), true
+}
+
+func getIoEnterpriseClient(c *gin.Context) (*ionet.Client, bool) {
+	apiKey, ok := getIoAPIKey(c)
+	if !ok {
+		return nil, false
+	}
+	return ionet.NewEnterpriseClient(apiKey), true
+}
+
+func TestIoNetConnection(c *gin.Context) {
+	var req struct {
+		APIKey string `json:"api_key"`
+	}
+
+	rawBody, err := c.GetRawData()
+	if err != nil {
+		common.ApiError(c, err)
+		return
+	}
+	if len(bytes.TrimSpace(rawBody)) > 0 {
+		if err := json.Unmarshal(rawBody, &req); err != nil {
+			common.ApiErrorMsg(c, "invalid request payload")
+			return
+		}
+	}
+
+	apiKey := strings.TrimSpace(req.APIKey)
+	if apiKey == "" {
+		common.OptionMapRWMutex.RLock()
+		storedKey := strings.TrimSpace(common.OptionMap["model_deployment.ionet.api_key"])
+		common.OptionMapRWMutex.RUnlock()
+		if storedKey == "" {
+			common.ApiErrorMsg(c, "api_key is required")
+			return
+		}
+		apiKey = storedKey
+	}
+
+	client := ionet.NewEnterpriseClient(apiKey)
+	result, err := client.GetMaxGPUsPerContainer()
+	if err != nil {
+		if apiErr, ok := err.(*ionet.APIError); ok {
+			message := strings.TrimSpace(apiErr.Message)
+			if message == "" {
+				message = "failed to validate api key"
+			}
+			common.ApiErrorMsg(c, message)
+			return
+		}
+		common.ApiError(c, err)
+		return
+	}
+
+	totalHardware := 0
+	totalAvailable := 0
+	if result != nil {
+		totalHardware = len(result.Hardware)
+		totalAvailable = result.Total
+		if totalAvailable == 0 {
+			for _, hw := range result.Hardware {
+				totalAvailable += hw.Available
+			}
+		}
+	}
+
+	common.ApiSuccess(c, gin.H{
+		"hardware_count":  totalHardware,
+		"total_available": totalAvailable,
+	})
+}
+
+func requireDeploymentID(c *gin.Context) (string, bool) {
+	deploymentID := strings.TrimSpace(c.Param("id"))
+	if deploymentID == "" {
+		common.ApiErrorMsg(c, "deployment ID is required")
+		return "", false
+	}
+	return deploymentID, true
+}
+
+func requireContainerID(c *gin.Context) (string, bool) {
+	containerID := strings.TrimSpace(c.Param("container_id"))
+	if containerID == "" {
+		common.ApiErrorMsg(c, "container ID is required")
+		return "", false
+	}
+	return containerID, true
+}
+
+func mapIoNetDeployment(d ionet.Deployment) map[string]interface{} {
+	var created int64
+	if d.CreatedAt.IsZero() {
+		created = time.Now().Unix()
+	} else {
+		created = d.CreatedAt.Unix()
+	}
+
+	timeRemainingHours := d.ComputeMinutesRemaining / 60
+	timeRemainingMins := d.ComputeMinutesRemaining % 60
+	var timeRemaining string
+	if timeRemainingHours > 0 {
+		timeRemaining = fmt.Sprintf("%d hour %d minutes", timeRemainingHours, timeRemainingMins)
+	} else if timeRemainingMins > 0 {
+		timeRemaining = fmt.Sprintf("%d minutes", timeRemainingMins)
+	} else {
+		timeRemaining = "completed"
+	}
+
+	hardwareInfo := fmt.Sprintf("%s %s x%d", d.BrandName, d.HardwareName, d.HardwareQuantity)
+
+	return map[string]interface{}{
+		"id":                        d.ID,
+		"deployment_name":           d.Name,
+		"container_name":            d.Name,
+		"status":                    strings.ToLower(d.Status),
+		"type":                      "Container",
+		"time_remaining":            timeRemaining,
+		"time_remaining_minutes":    d.ComputeMinutesRemaining,
+		"hardware_info":             hardwareInfo,
+		"hardware_name":             d.HardwareName,
+		"brand_name":                d.BrandName,
+		"hardware_quantity":         d.HardwareQuantity,
+		"completed_percent":         d.CompletedPercent,
+		"compute_minutes_served":    d.ComputeMinutesServed,
+		"compute_minutes_remaining": d.ComputeMinutesRemaining,
+		"created_at":                created,
+		"updated_at":                created,
+		"model_name":                "",
+		"model_version":             "",
+		"instance_count":            d.HardwareQuantity,
+		"resource_config": map[string]interface{}{
+			"cpu":    "",
+			"memory": "",
+			"gpu":    strconv.Itoa(d.HardwareQuantity),
+		},
+		"description": "",
+		"provider":    "io.net",
+	}
+}
+
+func computeStatusCounts(total int, deployments []ionet.Deployment) map[string]int64 {
+	counts := map[string]int64{
+		"all": int64(total),
+	}
+
+	for _, status := range []string{"running", "completed", "failed", "deployment requested", "termination requested", "destroyed"} {
+		counts[status] = 0
+	}
+
+	for _, d := range deployments {
+		status := strings.ToLower(strings.TrimSpace(d.Status))
+		counts[status] = counts[status] + 1
+	}
+
+	return counts
+}
+
+func GetAllDeployments(c *gin.Context) {
+	pageInfo := common.GetPageQuery(c)
+	client, ok := getIoEnterpriseClient(c)
+	if !ok {
+		return
+	}
+
+	status := c.Query("status")
+	opts := &ionet.ListDeploymentsOptions{
+		Status:    strings.ToLower(strings.TrimSpace(status)),
+		Page:      pageInfo.GetPage(),
+		PageSize:  pageInfo.GetPageSize(),
+		SortBy:    "created_at",
+		SortOrder: "desc",
+	}
+
+	dl, err := client.ListDeployments(opts)
+	if err != nil {
+		common.ApiError(c, err)
+		return
+	}
+
+	items := make([]map[string]interface{}, 0, len(dl.Deployments))
+	for _, d := range dl.Deployments {
+		items = append(items, mapIoNetDeployment(d))
+	}
+
+	data := gin.H{
+		"page":          pageInfo.GetPage(),
+		"page_size":     pageInfo.GetPageSize(),
+		"total":         dl.Total,
+		"items":         items,
+		"status_counts": computeStatusCounts(dl.Total, dl.Deployments),
+	}
+	common.ApiSuccess(c, data)
+}
+
+func SearchDeployments(c *gin.Context) {
+	pageInfo := common.GetPageQuery(c)
+	client, ok := getIoEnterpriseClient(c)
+	if !ok {
+		return
+	}
+
+	status := strings.ToLower(strings.TrimSpace(c.Query("status")))
+	keyword := strings.TrimSpace(c.Query("keyword"))
+
+	dl, err := client.ListDeployments(&ionet.ListDeploymentsOptions{
+		Status:    status,
+		Page:      pageInfo.GetPage(),
+		PageSize:  pageInfo.GetPageSize(),
+		SortBy:    "created_at",
+		SortOrder: "desc",
+	})
+	if err != nil {
+		common.ApiError(c, err)
+		return
+	}
+
+	filtered := make([]ionet.Deployment, 0, len(dl.Deployments))
+	if keyword == "" {
+		filtered = dl.Deployments
+	} else {
+		kw := strings.ToLower(keyword)
+		for _, d := range dl.Deployments {
+			if strings.Contains(strings.ToLower(d.Name), kw) {
+				filtered = append(filtered, d)
+			}
+		}
+	}
+
+	items := make([]map[string]interface{}, 0, len(filtered))
+	for _, d := range filtered {
+		items = append(items, mapIoNetDeployment(d))
+	}
+
+	total := dl.Total
+	if keyword != "" {
+		total = len(filtered)
+	}
+
+	data := gin.H{
+		"page":      pageInfo.GetPage(),
+		"page_size": pageInfo.GetPageSize(),
+		"total":     total,
+		"items":     items,
+	}
+	common.ApiSuccess(c, data)
+}
+
+func GetDeployment(c *gin.Context) {
+	client, ok := getIoEnterpriseClient(c)
+	if !ok {
+		return
+	}
+
+	deploymentID, ok := requireDeploymentID(c)
+	if !ok {
+		return
+	}
+
+	details, err := client.GetDeployment(deploymentID)
+	if err != nil {
+		common.ApiError(c, err)
+		return
+	}
+
+	data := map[string]interface{}{
+		"id":              details.ID,
+		"deployment_name": details.ID,
+		"model_name":      "",
+		"model_version":   "",
+		"status":          strings.ToLower(details.Status),
+		"instance_count":  details.TotalContainers,
+		"hardware_id":     details.HardwareID,
+		"resource_config": map[string]interface{}{
+			"cpu":    "",
+			"memory": "",
+			"gpu":    strconv.Itoa(details.TotalGPUs),
+		},
+		"created_at":                details.CreatedAt.Unix(),
+		"updated_at":                details.CreatedAt.Unix(),
+		"description":               "",
+		"amount_paid":               details.AmountPaid,
+		"completed_percent":         details.CompletedPercent,
+		"gpus_per_container":        details.GPUsPerContainer,
+		"total_gpus":                details.TotalGPUs,
+		"total_containers":          details.TotalContainers,
+		"hardware_name":             details.HardwareName,
+		"brand_name":                details.BrandName,
+		"compute_minutes_served":    details.ComputeMinutesServed,
+		"compute_minutes_remaining": details.ComputeMinutesRemaining,
+		"locations":                 details.Locations,
+		"container_config":          details.ContainerConfig,
+	}
+
+	common.ApiSuccess(c, data)
+}
+
+func UpdateDeploymentName(c *gin.Context) {
+	client, ok := getIoEnterpriseClient(c)
+	if !ok {
+		return
+	}
+
+	deploymentID, ok := requireDeploymentID(c)
+	if !ok {
+		return
+	}
+
+	var req struct {
+		Name string `json:"name" binding:"required"`
+	}
+
+	if err := c.ShouldBindJSON(&req); err != nil {
+		common.ApiError(c, err)
+		return
+	}
+
+	updateReq := &ionet.UpdateClusterNameRequest{
+		Name: strings.TrimSpace(req.Name),
+	}
+
+	if updateReq.Name == "" {
+		common.ApiErrorMsg(c, "deployment name cannot be empty")
+		return
+	}
+
+	available, err := client.CheckClusterNameAvailability(updateReq.Name)
+	if err != nil {
+		common.ApiError(c, fmt.Errorf("failed to check name availability: %w", err))
+		return
+	}
+
+	if !available {
+		common.ApiErrorMsg(c, "deployment name is not available, please choose a different name")
+		return
+	}
+
+	resp, err := client.UpdateClusterName(deploymentID, updateReq)
+	if err != nil {
+		common.ApiError(c, err)
+		return
+	}
+
+	data := gin.H{
+		"status":  resp.Status,
+		"message": resp.Message,
+		"id":      deploymentID,
+		"name":    updateReq.Name,
+	}
+	common.ApiSuccess(c, data)
+}
+
+func UpdateDeployment(c *gin.Context) {
+	client, ok := getIoEnterpriseClient(c)
+	if !ok {
+		return
+	}
+
+	deploymentID, ok := requireDeploymentID(c)
+	if !ok {
+		return
+	}
+
+	var req ionet.UpdateDeploymentRequest
+	if err := c.ShouldBindJSON(&req); err != nil {
+		common.ApiError(c, err)
+		return
+	}
+
+	resp, err := client.UpdateDeployment(deploymentID, &req)
+	if err != nil {
+		common.ApiError(c, err)
+		return
+	}
+
+	data := gin.H{
+		"status":        resp.Status,
+		"deployment_id": resp.DeploymentID,
+	}
+	common.ApiSuccess(c, data)
+}
+
+func ExtendDeployment(c *gin.Context) {
+	client, ok := getIoEnterpriseClient(c)
+	if !ok {
+		return
+	}
+
+	deploymentID, ok := requireDeploymentID(c)
+	if !ok {
+		return
+	}
+
+	var req ionet.ExtendDurationRequest
+	if err := c.ShouldBindJSON(&req); err != nil {
+		common.ApiError(c, err)
+		return
+	}
+
+	details, err := client.ExtendDeployment(deploymentID, &req)
+	if err != nil {
+		common.ApiError(c, err)
+		return
+	}
+
+	data := mapIoNetDeployment(ionet.Deployment{
+		ID:                      details.ID,
+		Status:                  details.Status,
+		Name:                    deploymentID,
+		CompletedPercent:        float64(details.CompletedPercent),
+		HardwareQuantity:        details.TotalGPUs,
+		BrandName:               details.BrandName,
+		HardwareName:            details.HardwareName,
+		ComputeMinutesServed:    details.ComputeMinutesServed,
+		ComputeMinutesRemaining: details.ComputeMinutesRemaining,
+		CreatedAt:               details.CreatedAt,
+	})
+
+	common.ApiSuccess(c, data)
+}
+
+func DeleteDeployment(c *gin.Context) {
+	client, ok := getIoEnterpriseClient(c)
+	if !ok {
+		return
+	}
+
+	deploymentID, ok := requireDeploymentID(c)
+	if !ok {
+		return
+	}
+
+	resp, err := client.DeleteDeployment(deploymentID)
+	if err != nil {
+		common.ApiError(c, err)
+		return
+	}
+
+	data := gin.H{
+		"status":        resp.Status,
+		"deployment_id": resp.DeploymentID,
+		"message":       "Deployment termination requested successfully",
+	}
+	common.ApiSuccess(c, data)
+}
+
+func CreateDeployment(c *gin.Context) {
+	client, ok := getIoEnterpriseClient(c)
+	if !ok {
+		return
+	}
+
+	var req ionet.DeploymentRequest
+	if err := c.ShouldBindJSON(&req); err != nil {
+		common.ApiError(c, err)
+		return
+	}
+
+	resp, err := client.DeployContainer(&req)
+	if err != nil {
+		common.ApiError(c, err)
+		return
+	}
+
+	data := gin.H{
+		"deployment_id": resp.DeploymentID,
+		"status":        resp.Status,
+		"message":       "Deployment created successfully",
+	}
+	common.ApiSuccess(c, data)
+}
+
+func GetHardwareTypes(c *gin.Context) {
+	client, ok := getIoEnterpriseClient(c)
+	if !ok {
+		return
+	}
+
+	hardwareTypes, totalAvailable, err := client.ListHardwareTypes()
+	if err != nil {
+		common.ApiError(c, err)
+		return
+	}
+
+	data := gin.H{
+		"hardware_types":  hardwareTypes,
+		"total":           len(hardwareTypes),
+		"total_available": totalAvailable,
+	}
+	common.ApiSuccess(c, data)
+}
+
+func GetLocations(c *gin.Context) {
+	client, ok := getIoClient(c)
+	if !ok {
+		return
+	}
+
+	locationsResp, err := client.ListLocations()
+	if err != nil {
+		common.ApiError(c, err)
+		return
+	}
+
+	total := locationsResp.Total
+	if total == 0 {
+		total = len(locationsResp.Locations)
+	}
+
+	data := gin.H{
+		"locations": locationsResp.Locations,
+		"total":     total,
+	}
+	common.ApiSuccess(c, data)
+}
+
+func GetAvailableReplicas(c *gin.Context) {
+	client, ok := getIoEnterpriseClient(c)
+	if !ok {
+		return
+	}
+
+	hardwareIDStr := c.Query("hardware_id")
+	gpuCountStr := c.Query("gpu_count")
+
+	if hardwareIDStr == "" {
+		common.ApiErrorMsg(c, "hardware_id parameter is required")
+		return
+	}
+
+	hardwareID, err := strconv.Atoi(hardwareIDStr)
+	if err != nil || hardwareID <= 0 {
+		common.ApiErrorMsg(c, "invalid hardware_id parameter")
+		return
+	}
+
+	gpuCount := 1
+	if gpuCountStr != "" {
+		if parsed, err := strconv.Atoi(gpuCountStr); err == nil && parsed > 0 {
+			gpuCount = parsed
+		}
+	}
+
+	replicas, err := client.GetAvailableReplicas(hardwareID, gpuCount)
+	if err != nil {
+		common.ApiError(c, err)
+		return
+	}
+
+	common.ApiSuccess(c, replicas)
+}
+
+func GetPriceEstimation(c *gin.Context) {
+	client, ok := getIoEnterpriseClient(c)
+	if !ok {
+		return
+	}
+
+	var req ionet.PriceEstimationRequest
+	if err := c.ShouldBindJSON(&req); err != nil {
+		common.ApiError(c, err)
+		return
+	}
+
+	priceResp, err := client.GetPriceEstimation(&req)
+	if err != nil {
+		common.ApiError(c, err)
+		return
+	}
+
+	common.ApiSuccess(c, priceResp)
+}
+
+func CheckClusterNameAvailability(c *gin.Context) {
+	client, ok := getIoEnterpriseClient(c)
+	if !ok {
+		return
+	}
+
+	clusterName := strings.TrimSpace(c.Query("name"))
+	if clusterName == "" {
+		common.ApiErrorMsg(c, "name parameter is required")
+		return
+	}
+
+	available, err := client.CheckClusterNameAvailability(clusterName)
+	if err != nil {
+		common.ApiError(c, err)
+		return
+	}
+
+	data := gin.H{
+		"available": available,
+		"name":      clusterName,
+	}
+	common.ApiSuccess(c, data)
+}
+
+func GetDeploymentLogs(c *gin.Context) {
+	client, ok := getIoClient(c)
+	if !ok {
+		return
+	}
+
+	deploymentID, ok := requireDeploymentID(c)
+	if !ok {
+		return
+	}
+
+	containerID := c.Query("container_id")
+	if containerID == "" {
+		common.ApiErrorMsg(c, "container_id parameter is required")
+		return
+	}
+	level := c.Query("level")
+	stream := c.Query("stream")
+	cursor := c.Query("cursor")
+	limitStr := c.Query("limit")
+	follow := c.Query("follow") == "true"
+
+	var limit int = 100
+	if limitStr != "" {
+		if parsedLimit, err := strconv.Atoi(limitStr); err == nil && parsedLimit > 0 {
+			limit = parsedLimit
+			if limit > 1000 {
+				limit = 1000
+			}
+		}
+	}
+
+	opts := &ionet.GetLogsOptions{
+		Level:  level,
+		Stream: stream,
+		Limit:  limit,
+		Cursor: cursor,
+		Follow: follow,
+	}
+
+	if startTime := c.Query("start_time"); startTime != "" {
+		if t, err := time.Parse(time.RFC3339, startTime); err == nil {
+			opts.StartTime = &t
+		}
+	}
+	if endTime := c.Query("end_time"); endTime != "" {
+		if t, err := time.Parse(time.RFC3339, endTime); err == nil {
+			opts.EndTime = &t
+		}
+	}
+
+	rawLogs, err := client.GetContainerLogsRaw(deploymentID, containerID, opts)
+	if err != nil {
+		common.ApiError(c, err)
+		return
+	}
+
+	common.ApiSuccess(c, rawLogs)
+}
+
+func ListDeploymentContainers(c *gin.Context) {
+	client, ok := getIoEnterpriseClient(c)
+	if !ok {
+		return
+	}
+
+	deploymentID, ok := requireDeploymentID(c)
+	if !ok {
+		return
+	}
+
+	containers, err := client.ListContainers(deploymentID)
+	if err != nil {
+		common.ApiError(c, err)
+		return
+	}
+
+	items := make([]map[string]interface{}, 0)
+	if containers != nil {
+		items = make([]map[string]interface{}, 0, len(containers.Workers))
+		for _, ctr := range containers.Workers {
+			events := make([]map[string]interface{}, 0, len(ctr.ContainerEvents))
+			for _, event := range ctr.ContainerEvents {
+				events = append(events, map[string]interface{}{
+					"time":    event.Time.Unix(),
+					"message": event.Message,
+				})
+			}
+
+			items = append(items, map[string]interface{}{
+				"container_id":       ctr.ContainerID,
+				"device_id":          ctr.DeviceID,
+				"status":             strings.ToLower(strings.TrimSpace(ctr.Status)),
+				"hardware":           ctr.Hardware,
+				"brand_name":         ctr.BrandName,
+				"created_at":         ctr.CreatedAt.Unix(),
+				"uptime_percent":     ctr.UptimePercent,
+				"gpus_per_container": ctr.GPUsPerContainer,
+				"public_url":         ctr.PublicURL,
+				"events":             events,
+			})
+		}
+	}
+
+	response := gin.H{
+		"total":      0,
+		"containers": items,
+	}
+	if containers != nil {
+		response["total"] = containers.Total
+	}
+
+	common.ApiSuccess(c, response)
+}
+
+func GetContainerDetails(c *gin.Context) {
+	client, ok := getIoEnterpriseClient(c)
+	if !ok {
+		return
+	}
+
+	deploymentID, ok := requireDeploymentID(c)
+	if !ok {
+		return
+	}
+
+	containerID, ok := requireContainerID(c)
+	if !ok {
+		return
+	}
+
+	details, err := client.GetContainerDetails(deploymentID, containerID)
+	if err != nil {
+		common.ApiError(c, err)
+		return
+	}
+	if details == nil {
+		common.ApiErrorMsg(c, "container details not found")
+		return
+	}
+
+	events := make([]map[string]interface{}, 0, len(details.ContainerEvents))
+	for _, event := range details.ContainerEvents {
+		events = append(events, map[string]interface{}{
+			"time":    event.Time.Unix(),
+			"message": event.Message,
+		})
+	}
+
+	data := gin.H{
+		"deployment_id":      deploymentID,
+		"container_id":       details.ContainerID,
+		"device_id":          details.DeviceID,
+		"status":             strings.ToLower(strings.TrimSpace(details.Status)),
+		"hardware":           details.Hardware,
+		"brand_name":         details.BrandName,
+		"created_at":         details.CreatedAt.Unix(),
+		"uptime_percent":     details.UptimePercent,
+		"gpus_per_container": details.GPUsPerContainer,
+		"public_url":         details.PublicURL,
+		"events":             events,
+	}
+
+	common.ApiSuccess(c, data)
+}

controller/discord.go

@@ -0,0 +1,223 @@
+package controller
+
+import (
+	"encoding/json"
+	"errors"
+	"fmt"
+	"net/http"
+	"net/url"
+	"strconv"
+	"strings"
+	"time"
+
+	"github.com/QuantumNous/new-api/common"
+	"github.com/QuantumNous/new-api/model"
+	"github.com/QuantumNous/new-api/setting/system_setting"
+
+	"github.com/gin-contrib/sessions"
+	"github.com/gin-gonic/gin"
+)
+
+type DiscordResponse struct {
+	AccessToken  string `json:"access_token"`
+	IDToken      string `json:"id_token"`
+	RefreshToken string `json:"refresh_token"`
+	TokenType    string `json:"token_type"`
+	ExpiresIn    int    `json:"expires_in"`
+	Scope        string `json:"scope"`
+}
+
+type DiscordUser struct {
+	UID  string `json:"id"`
+	ID   string `json:"username"`
+	Name string `json:"global_name"`
+}
+
+func getDiscordUserInfoByCode(code string) (*DiscordUser, error) {
+	if code == "" {
+		return nil, errors.New("无效的参数")
+	}
+
+	values := url.Values{}
+	values.Set("client_id", system_setting.GetDiscordSettings().ClientId)
+	values.Set("client_secret", system_setting.GetDiscordSettings().ClientSecret)
+	values.Set("code", code)
+	values.Set("grant_type", "authorization_code")
+	values.Set("redirect_uri", fmt.Sprintf("%s/oauth/discord", system_setting.ServerAddress))
+	formData := values.Encode()
+	req, err := http.NewRequest("POST", "https://discord.com/api/v10/oauth2/token", strings.NewReader(formData))
+	if err != nil {
+		return nil, err
+	}
+	req.Header.Set("Content-Type", "application/x-www-form-urlencoded")
+	req.Header.Set("Accept", "application/json")
+	client := http.Client{
+		Timeout: 5 * time.Second,
+	}
+	res, err := client.Do(req)
+	if err != nil {
+		common.SysLog(err.Error())
+		return nil, errors.New("无法连接至 Discord 服务器，请稍后重试！")
+	}
+	defer res.Body.Close()
+	var discordResponse DiscordResponse
+	err = json.NewDecoder(res.Body).Decode(&discordResponse)
+	if err != nil {
+		return nil, err
+	}
+
+	if discordResponse.AccessToken == "" {
+		common.SysError("Discord 获取 Token 失败，请检查设置！")
+		return nil, errors.New("Discord 获取 Token 失败，请检查设置！")
+	}
+
+	req, err = http.NewRequest("GET", "https://discord.com/api/v10/users/@me", nil)
+	if err != nil {
+		return nil, err
+	}
+	req.Header.Set("Authorization", "Bearer "+discordResponse.AccessToken)
+	res2, err := client.Do(req)
+	if err != nil {
+		common.SysLog(err.Error())
+		return nil, errors.New("无法连接至 Discord 服务器，请稍后重试！")
+	}
+	defer res2.Body.Close()
+	if res2.StatusCode != http.StatusOK {
+		common.SysError("Discord 获取用户信息失败！请检查设置！")
+		return nil, errors.New("Discord 获取用户信息失败！请检查设置！")
+	}
+
+	var discordUser DiscordUser
+	err = json.NewDecoder(res2.Body).Decode(&discordUser)
+	if err != nil {
+		return nil, err
+	}
+	if discordUser.UID == "" || discordUser.ID == "" {
+		common.SysError("Discord 获取用户信息为空！请检查设置！")
+		return nil, errors.New("Discord 获取用户信息为空！请检查设置！")
+	}
+	return &discordUser, nil
+}
+
+func DiscordOAuth(c *gin.Context) {
+	session := sessions.Default(c)
+	state := c.Query("state")
+	if state == "" || session.Get("oauth_state") == nil || state != session.Get("oauth_state").(string) {
+		c.JSON(http.StatusForbidden, gin.H{
+			"success": false,
+			"message": "state is empty or not same",
+		})
+		return
+	}
+	username := session.Get("username")
+	if username != nil {
+		DiscordBind(c)
+		return
+	}
+	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",
+		})
+		return
+	}
+	code := c.Query("code")
+	discordUser, err := getDiscordUserInfoByCode(code)
+	if err != nil {
+		common.ApiError(c, err)
+		return
+	}
+	user := model.User{
+		DiscordId: discordUser.UID,
+	}
+	if model.IsDiscordIdAlreadyTaken(user.DiscordId) {
+		err := user.FillUserByDiscordId()
+		if err != nil {
+			c.JSON(http.StatusOK, gin.H{
+				"success": false,
+				"message": err.Error(),
+			})
+			return
+		}
+	} else {
+		if common.RegisterEnabled {
+			if discordUser.ID != "" {
+				user.Username = discordUser.ID
+			} else {
+				user.Username = "discord_" + strconv.Itoa(model.GetMaxUserId()+1)
+			}
+			if discordUser.Name != "" {
+				user.DisplayName = discordUser.Name
+			} else {
+				user.DisplayName = "Discord User"
+			}
+			err := user.Insert(0)
+			if err != nil {
+				c.JSON(http.StatusOK, gin.H{
+					"success": false,
+					"message": err.Error(),
+				})
+				return
+			}
+		} else {
+			c.JSON(http.StatusOK, gin.H{
+				"success": false,
+				"message": "管理员关闭了新用户注册",
+			})
+			return
+		}
+	}
+
+	if user.Status != common.UserStatusEnabled {
+		c.JSON(http.StatusOK, gin.H{
+			"message": "用户已被封禁",
+			"success": false,
+		})
+		return
+	}
+	setupLogin(&user, c)
+}
+
+func DiscordBind(c *gin.Context) {
+	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",
+		})
+		return
+	}
+	code := c.Query("code")
+	discordUser, err := getDiscordUserInfoByCode(code)
+	if err != nil {
+		common.ApiError(c, err)
+		return
+	}
+	user := model.User{
+		DiscordId: discordUser.UID,
+	}
+	if model.IsDiscordIdAlreadyTaken(user.DiscordId) {
+		c.JSON(http.StatusOK, gin.H{
+			"success": false,
+			"message": "该 Discord 账户已被绑定",
+		})
+		return
+	}
+	session := sessions.Default(c)
+	id := session.Get("id")
+	user.Id = id.(int)
+	err = user.FillUserById()
+	if err != nil {
+		common.ApiError(c, err)
+		return
+	}
+	user.DiscordId = discordUser.UID
+	err = user.Update(false)
+	if err != nil {
+		common.ApiError(c, err)
+		return
+	}
+	c.JSON(http.StatusOK, gin.H{
+		"success": true,
+		"message": "bind",
+	})
+}

controller/github.go

@@ -44,7 +44,7 @@ func getGitHubUserInfoByCode(code string) (*GitHubUser, error) {
 	req.Header.Set("Content-Type", "application/json")
 	req.Header.Set("Accept", "application/json")
 	client := http.Client{
-		Timeout: 5 * time.Second,
+		Timeout: 20 * time.Second,
 	}
 	res, err := client.Do(req)
 	if err != nil {

controller/linuxdo.go

@@ -84,7 +84,7 @@ func getLinuxdoUserInfoByCode(code string, c *gin.Context) (*LinuxdoUser, error)
 	}
 
 	// Get access token using Basic auth
-	tokenEndpoint := "https://connect.linux.do/oauth2/token"
+	tokenEndpoint := common.GetEnvOrDefaultString("LINUX_DO_TOKEN_ENDPOINT", "https://connect.linux.do/oauth2/token")
 	credentials := common.LinuxDOClientId + ":" + common.LinuxDOClientSecret
 	basicAuth := "Basic " + base64.StdEncoding.EncodeToString([]byte(credentials))
 
@@ -129,7 +129,7 @@ func getLinuxdoUserInfoByCode(code string, c *gin.Context) (*LinuxdoUser, error)
 	}
 
 	// Get user info
-	userEndpoint := "https://connect.linux.do/api/user"
+	userEndpoint := common.GetEnvOrDefaultString("LINUX_DO_USER_ENDPOINT", "https://connect.linux.do/api/user")
 	req, err = http.NewRequest("GET", userEndpoint, nil)
 	if err != nil {
 		return nil, err

controller/misc.go

@@ -52,6 +52,8 @@ func GetStatus(c *gin.Context) {
 		"email_verification":          common.EmailVerificationEnabled,
 		"github_oauth":                common.GitHubOAuthEnabled,
 		"github_client_id":            common.GitHubClientId,
+		"discord_oauth":               system_setting.GetDiscordSettings().Enabled,
+		"discord_client_id":           system_setting.GetDiscordSettings().ClientId,
 		"linuxdo_oauth":               common.LinuxDOOAuthEnabled,
 		"linuxdo_client_id":           common.LinuxDOClientId,
 		"linuxdo_minimum_trust_level": common.LinuxDOMinimumTrustLevel,
@@ -112,6 +114,8 @@ func GetStatus(c *gin.Context) {
 		"setup":                       constant.Setup,
 		"user_agreement_enabled":      legalSetting.UserAgreement != "",
 		"privacy_policy_enabled":      legalSetting.PrivacyPolicy != "",
+		"checkin_enabled":             operation_setting.GetCheckinSetting().Enabled,
+		"_qn":                          "new-api",
 	}
 
 	// 根据启用状态注入可选内容

controller/model.go

@@ -16,6 +16,9 @@ import (
 	"github.com/QuantumNous/new-api/relay/channel/moonshot"
 	relaycommon "github.com/QuantumNous/new-api/relay/common"
 	"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"
 )
@@ -109,6 +112,17 @@ func init() {
 func ListModels(c *gin.Context, modelType int) {
 	userOpenAiModels := make([]dto.OpenAIModels, 0)
 
+	acceptUnsetRatioModel := operation_setting.SelfUseModeEnabled
+	if !acceptUnsetRatioModel {
+		userId := c.GetInt("id")
+		if userId > 0 {
+			userSettings, _ := model.GetUserSetting(userId, false)
+			if userSettings.AcceptUnsetRatioModel {
+				acceptUnsetRatioModel = true
+			}
+		}
+	}
+
 	modelLimitEnable := common.GetContextKeyBool(c, constant.ContextKeyTokenModelLimitEnabled)
 	if modelLimitEnable {
 		s, ok := common.GetContextKey(c, constant.ContextKeyTokenModelLimit)
@@ -119,6 +133,12 @@ func ListModels(c *gin.Context, modelType int) {
 			tokenModelLimit = map[string]bool{}
 		}
 		for allowModel, _ := range tokenModelLimit {
+			if !acceptUnsetRatioModel {
+				_, _, exist := ratio_setting.GetModelRatioOrPrice(allowModel)
+				if !exist {
+					continue
+				}
+			}
 			if oaiModel, ok := openAIModelsMap[allowModel]; ok {
 				oaiModel.SupportedEndpointTypes = model.GetModelSupportEndpointTypes(allowModel)
 				userOpenAiModels = append(userOpenAiModels, oaiModel)
@@ -161,6 +181,12 @@ func ListModels(c *gin.Context, modelType int) {
 			models = model.GetGroupEnabledModels(group)
 		}
 		for _, modelName := range models {
+			if !acceptUnsetRatioModel {
+				_, _, exist := ratio_setting.GetModelRatioOrPrice(modelName)
+				if !exist {
+					continue
+				}
+			}
 			if oaiModel, ok := openAIModelsMap[modelName]; ok {
 				oaiModel.SupportedEndpointTypes = model.GetModelSupportEndpointTypes(modelName)
 				userOpenAiModels = append(userOpenAiModels, oaiModel)
@@ -175,6 +201,7 @@ func ListModels(c *gin.Context, modelType int) {
 			}
 		}
 	}
+
 	switch modelType {
 	case constant.ChannelTypeAnthropic:
 		useranthropicModels := make([]dto.AnthropicModel, len(userOpenAiModels))
@@ -249,7 +276,7 @@ func RetrieveModel(c *gin.Context, modelType int) {
 			c.JSON(200, aiModel)
 		}
 	} else {
-		openAIError := dto.OpenAIError{
+		openAIError := types.OpenAIError{
 			Message: fmt.Sprintf("The model '%s' does not exist", modelId),
 			Type:    "invalid_request_error",
 			Param:   "model",

controller/model_sync.go

@@ -99,6 +99,9 @@ func newHTTPClient() *http.Client {
 		ExpectContinueTimeout: 1 * time.Second,
 		ResponseHeaderTimeout: time.Duration(timeoutSec) * time.Second,
 	}
+	if common.TLSInsecureSkipVerify {
+		transport.TLSClientConfig = common.InsecureTLSConfig
+	}
 	transport.DialContext = func(ctx context.Context, network, addr string) (net.Conn, error) {
 		host, _, err := net.SplitHostPort(addr)
 		if err != nil {
@@ -115,7 +118,17 @@ func newHTTPClient() *http.Client {
 	return &http.Client{Transport: transport}
 }
 
-var httpClient = newHTTPClient()
+var (
+	httpClientOnce sync.Once
+	httpClient     *http.Client
+)
+
+func getHTTPClient() *http.Client {
+	httpClientOnce.Do(func() {
+		httpClient = newHTTPClient()
+	})
+	return httpClient
+}
 
 func fetchJSON[T any](ctx context.Context, url string, out *upstreamEnvelope[T]) error {
 	var lastErr error
@@ -138,7 +151,7 @@ func fetchJSON[T any](ctx context.Context, url string, out *upstreamEnvelope[T])
 		}
 		cacheMutex.RUnlock()
 
-		resp, err := httpClient.Do(req)
+		resp, err := getHTTPClient().Do(req)
 		if err != nil {
 			lastErr = err
 			// backoff with jitter
@@ -249,7 +262,9 @@ func ensureVendorID(vendorName string, vendorByName map[string]upstreamVendor, v
 	return 0
 }
 
-// SyncUpstreamModels 同步上游模型与供应商，仅对「未配置模型」生效
+// 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）
 func SyncUpstreamModels(c *gin.Context) {
 	var req syncRequest
 	// 允许空体
@@ -260,12 +275,26 @@ func SyncUpstreamModels(c *gin.Context) {
 		c.JSON(http.StatusOK, gin.H{"success": false, "message": err.Error()})
 		return
 	}
-	if len(missing) == 0 {
-		c.JSON(http.StatusOK, gin.H{"success": true, "data": gin.H{
-			"created_models":  0,
-			"created_vendors": 0,
-			"skipped_models":  []string{},
-		}})
+
+	// 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,
+				},
+			},
+		})
 		return
 	}
 
@@ -315,9 +344,9 @@ func SyncUpstreamModels(c *gin.Context) {
 	createdModels := 0
 	createdVendors := 0
 	updatedModels := 0
-	var skipped []string
-	var createdList []string
-	var updatedList []string
+	skipped := make([]string, 0)
+	createdList := make([]string, 0)
+	updatedList := make([]string, 0)
 
 	// 本地缓存：vendorName -> id
 	vendorIDCache := make(map[string]int)

controller/option.go

@@ -10,6 +10,7 @@ import (
 	"github.com/QuantumNous/new-api/model"
 	"github.com/QuantumNous/new-api/setting"
 	"github.com/QuantumNous/new-api/setting/console_setting"
+	"github.com/QuantumNous/new-api/setting/operation_setting"
 	"github.com/QuantumNous/new-api/setting/ratio_setting"
 	"github.com/QuantumNous/new-api/setting/system_setting"
 
@@ -20,7 +21,11 @@ func GetOptions(c *gin.Context) {
 	var options []*model.Option
 	common.OptionMapRWMutex.Lock()
 	for k, v := range common.OptionMap {
-		if strings.HasSuffix(k, "Token") || strings.HasSuffix(k, "Secret") || strings.HasSuffix(k, "Key") {
+		if strings.HasSuffix(k, "Token") ||
+			strings.HasSuffix(k, "Secret") ||
+			strings.HasSuffix(k, "Key") ||
+			strings.HasSuffix(k, "secret") ||
+			strings.HasSuffix(k, "api_key") {
 			continue
 		}
 		options = append(options, &model.Option{
@@ -71,6 +76,14 @@ func UpdateOption(c *gin.Context) {
 			})
 			return
 		}
+	case "discord.enabled":
+		if option.Value == "true" && system_setting.GetDiscordSettings().ClientId == "" {
+			c.JSON(http.StatusOK, gin.H{
+				"success": false,
+				"message": "无法启用 Discord OAuth，请先填入 Discord Client Id 以及 Discord Client Secret！",
+			})
+			return
+		}
 	case "oidc.enabled":
 		if option.Value == "true" && system_setting.GetOIDCSettings().ClientId == "" {
 			c.JSON(http.StatusOK, gin.H{
@@ -165,6 +178,24 @@ func UpdateOption(c *gin.Context) {
 			})
 			return
 		}
+	case "AutomaticDisableStatusCodes":
+		_, err = operation_setting.ParseHTTPStatusCodeRanges(option.Value.(string))
+		if err != nil {
+			c.JSON(http.StatusOK, gin.H{
+				"success": false,
+				"message": err.Error(),
+			})
+			return
+		}
+	case "AutomaticRetryStatusCodes":
+		_, err = operation_setting.ParseHTTPStatusCodeRanges(option.Value.(string))
+		if err != nil {
+			c.JSON(http.StatusOK, gin.H{
+				"success": false,
+				"message": err.Error(),
+			})
+			return
+		}
 	case "console_setting.api_info":
 		err = console_setting.ValidateConsoleSettings(option.Value.(string), "ApiInfo")
 		if err != nil {

controller/performance.go

@@ -0,0 +1,202 @@
+package controller
+
+import (
+	"net/http"
+	"os"
+	"path/filepath"
+	"runtime"
+
+	"github.com/QuantumNous/new-api/common"
+	"github.com/gin-gonic/gin"
+)
+
+// PerformanceStats 性能统计信息
+type PerformanceStats struct {
+	// 缓存统计
+	CacheStats common.DiskCacheStats `json:"cache_stats"`
+	// 系统内存统计
+	MemoryStats MemoryStats `json:"memory_stats"`
+	// 磁盘缓存目录信息
+	DiskCacheInfo DiskCacheInfo `json:"disk_cache_info"`
+	// 磁盘空间信息
+	DiskSpaceInfo DiskSpaceInfo `json:"disk_space_info"`
+	// 配置信息
+	Config PerformanceConfig `json:"config"`
+}
+
+// MemoryStats 内存统计
+type MemoryStats struct {
+	// 已分配内存（字节）
+	Alloc uint64 `json:"alloc"`
+	// 总分配内存（字节）
+	TotalAlloc uint64 `json:"total_alloc"`
+	// 系统内存（字节）
+	Sys uint64 `json:"sys"`
+	// GC 次数
+	NumGC uint32 `json:"num_gc"`
+	// Goroutine 数量
+	NumGoroutine int `json:"num_goroutine"`
+}
+
+// DiskCacheInfo 磁盘缓存目录信息
+type DiskCacheInfo struct {
+	// 缓存目录路径
+	Path string `json:"path"`
+	// 目录是否存在
+	Exists bool `json:"exists"`
+	// 文件数量
+	FileCount int `json:"file_count"`
+	// 总大小（字节）
+	TotalSize int64 `json:"total_size"`
+}
+
+// DiskSpaceInfo 磁盘空间信息
+type DiskSpaceInfo struct {
+	// 总空间（字节）
+	Total uint64 `json:"total"`
+	// 可用空间（字节）
+	Free uint64 `json:"free"`
+	// 已用空间（字节）
+	Used uint64 `json:"used"`
+	// 使用百分比
+	UsedPercent float64 `json:"used_percent"`
+}
+
+// PerformanceConfig 性能配置
+type PerformanceConfig struct {
+	// 是否启用磁盘缓存
+	DiskCacheEnabled bool `json:"disk_cache_enabled"`
+	// 磁盘缓存阈值（MB）
+	DiskCacheThresholdMB int `json:"disk_cache_threshold_mb"`
+	// 磁盘缓存最大大小（MB）
+	DiskCacheMaxSizeMB int `json:"disk_cache_max_size_mb"`
+	// 磁盘缓存路径
+	DiskCachePath string `json:"disk_cache_path"`
+	// 是否在容器中运行
+	IsRunningInContainer bool `json:"is_running_in_container"`
+}
+
+// GetPerformanceStats 获取性能统计信息
+func GetPerformanceStats(c *gin.Context) {
+	// 获取缓存统计
+	cacheStats := common.GetDiskCacheStats()
+
+	// 获取内存统计
+	var memStats runtime.MemStats
+	runtime.ReadMemStats(&memStats)
+
+	// 获取磁盘缓存目录信息
+	diskCacheInfo := getDiskCacheInfo()
+
+	// 获取配置信息
+	diskConfig := common.GetDiskCacheConfig()
+	config := PerformanceConfig{
+		DiskCacheEnabled:      diskConfig.Enabled,
+		DiskCacheThresholdMB:  diskConfig.ThresholdMB,
+		DiskCacheMaxSizeMB:    diskConfig.MaxSizeMB,
+		DiskCachePath:         diskConfig.Path,
+		IsRunningInContainer:  common.IsRunningInContainer(),
+	}
+
+	// 获取磁盘空间信息
+	diskSpaceInfo := getDiskSpaceInfo()
+
+	stats := PerformanceStats{
+		CacheStats: cacheStats,
+		MemoryStats: MemoryStats{
+			Alloc:        memStats.Alloc,
+			TotalAlloc:   memStats.TotalAlloc,
+			Sys:          memStats.Sys,
+			NumGC:        memStats.NumGC,
+			NumGoroutine: runtime.NumGoroutine(),
+		},
+		DiskCacheInfo: diskCacheInfo,
+		DiskSpaceInfo: diskSpaceInfo,
+		Config:        config,
+	}
+
+	c.JSON(http.StatusOK, gin.H{
+		"success": true,
+		"data":    stats,
+	})
+}
+
+// ClearDiskCache 清理磁盘缓存
+func ClearDiskCache(c *gin.Context) {
+	cachePath := common.GetDiskCachePath()
+	if cachePath == "" {
+		cachePath = os.TempDir()
+	}
+	dir := filepath.Join(cachePath, "new-api-body-cache")
+
+	// 删除缓存目录
+	err := os.RemoveAll(dir)
+	if err != nil && !os.IsNotExist(err) {
+		common.ApiError(c, err)
+		return
+	}
+
+	// 重置统计
+	common.ResetDiskCacheStats()
+
+	c.JSON(http.StatusOK, gin.H{
+		"success": true,
+		"message": "磁盘缓存已清理",
+	})
+}
+
+// ResetPerformanceStats 重置性能统计
+func ResetPerformanceStats(c *gin.Context) {
+	common.ResetDiskCacheStats()
+
+	c.JSON(http.StatusOK, gin.H{
+		"success": true,
+		"message": "统计信息已重置",
+	})
+}
+
+// ForceGC 强制执行 GC
+func ForceGC(c *gin.Context) {
+	runtime.GC()
+
+	c.JSON(http.StatusOK, gin.H{
+		"success": true,
+		"message": "GC 已执行",
+	})
+}
+
+// getDiskCacheInfo 获取磁盘缓存目录信息
+func getDiskCacheInfo() DiskCacheInfo {
+	cachePath := common.GetDiskCachePath()
+	if cachePath == "" {
+		cachePath = os.TempDir()
+	}
+	dir := filepath.Join(cachePath, "new-api-body-cache")
+
+	info := DiskCacheInfo{
+		Path:   dir,
+		Exists: false,
+	}
+
+	entries, err := os.ReadDir(dir)
+	if err != nil {
+		return info
+	}
+
+	info.Exists = true
+	info.FileCount = 0
+	info.TotalSize = 0
+
+	for _, entry := range entries {
+		if entry.IsDir() {
+			continue
+		}
+		info.FileCount++
+		if fileInfo, err := entry.Info(); err == nil {
+			info.TotalSize += fileInfo.Size()
+		}
+	}
+
+	return info
+}
+

controller/performance_unix.go

@@ -0,0 +1,37 @@
+//go:build !windows
+
+package controller
+
+import (
+	"os"
+
+	"github.com/QuantumNous/new-api/common"
+	"golang.org/x/sys/unix"
+)
+
+// getDiskSpaceInfo 获取缓存目录所在磁盘的空间信息 (Unix/Linux/macOS)
+func getDiskSpaceInfo() DiskSpaceInfo {
+	cachePath := common.GetDiskCachePath()
+	if cachePath == "" {
+		cachePath = os.TempDir()
+	}
+
+	info := DiskSpaceInfo{}
+
+	var stat unix.Statfs_t
+	err := unix.Statfs(cachePath, &stat)
+	if err != nil {
+		return info
+	}
+
+	// 计算磁盘空间
+	info.Total = stat.Blocks * uint64(stat.Bsize)
+	info.Free = stat.Bavail * uint64(stat.Bsize)
+	info.Used = info.Total - stat.Bfree*uint64(stat.Bsize)
+
+	if info.Total > 0 {
+		info.UsedPercent = float64(info.Used) / float64(info.Total) * 100
+	}
+
+	return info
+}

controller/performance_windows.go

@@ -0,0 +1,52 @@
+//go:build windows
+
+package controller
+
+import (
+	"os"
+	"syscall"
+	"unsafe"
+
+	"github.com/QuantumNous/new-api/common"
+)
+
+// getDiskSpaceInfo 获取缓存目录所在磁盘的空间信息 (Windows)
+func getDiskSpaceInfo() DiskSpaceInfo {
+	cachePath := common.GetDiskCachePath()
+	if cachePath == "" {
+		cachePath = os.TempDir()
+	}
+
+	info := DiskSpaceInfo{}
+
+	kernel32 := syscall.NewLazyDLL("kernel32.dll")
+	getDiskFreeSpaceEx := kernel32.NewProc("GetDiskFreeSpaceExW")
+
+	var freeBytesAvailable, totalBytes, totalFreeBytes uint64
+
+	pathPtr, err := syscall.UTF16PtrFromString(cachePath)
+	if err != nil {
+		return info
+	}
+
+	ret, _, _ := getDiskFreeSpaceEx.Call(
+		uintptr(unsafe.Pointer(pathPtr)),
+		uintptr(unsafe.Pointer(&freeBytesAvailable)),
+		uintptr(unsafe.Pointer(&totalBytes)),
+		uintptr(unsafe.Pointer(&totalFreeBytes)),
+	)
+
+	if ret == 0 {
+		return info
+	}
+
+	info.Total = totalBytes
+	info.Free = freeBytesAvailable
+	info.Used = totalBytes - totalFreeBytes
+
+	if info.Total > 0 {
+		info.UsedPercent = float64(info.Used) / float64(info.Total) * 100
+	}
+
+	return info
+}

controller/playground.go

@@ -3,12 +3,10 @@ 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"
@@ -31,8 +29,11 @@ func Playground(c *gin.Context) {
 		return
 	}
 
-	group := common.GetContextKeyString(c, constant.ContextKeyUsingGroup)
-	modelName := c.GetString("original_model")
+	relayInfo, err := relaycommon.GenRelayInfo(c, types.RelayFormatOpenAI, nil, nil)
+	if err != nil {
+		newAPIError = types.NewError(err, types.ErrorCodeInvalidRequest, types.ErrOptionWithSkipRetry())
+		return
+	}
 
 	userId := c.GetInt("id")
 
@@ -46,16 +47,10 @@ func Playground(c *gin.Context) {
 
 	tempToken := &model.Token{
 		UserId: userId,
-		Name:   fmt.Sprintf("playground-%s", group),
-		Group:  group,
+		Name:   fmt.Sprintf("playground-%s", relayInfo.UsingGroup),
+		Group:  relayInfo.UsingGroup,
 	}
 	_ = 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/ratio_sync.go

@@ -11,6 +11,7 @@ import (
 	"sync"
 	"time"
 
+	"github.com/QuantumNous/new-api/common"
 	"github.com/QuantumNous/new-api/logger"
 
 	"github.com/QuantumNous/new-api/dto"
@@ -110,6 +111,9 @@ func FetchUpstreamRatios(c *gin.Context) {
 
 	dialer := &net.Dialer{Timeout: 10 * time.Second}
 	transport := &http.Transport{MaxIdleConns: 100, IdleConnTimeout: 90 * time.Second, TLSHandshakeTimeout: 10 * time.Second, ExpectContinueTimeout: 1 * time.Second, ResponseHeaderTimeout: 10 * time.Second}
+	if common.TLSInsecureSkipVerify {
+		transport.TLSClientConfig = common.InsecureTLSConfig
+	}
 	transport.DialContext = func(ctx context.Context, network, addr string) (net.Conn, error) {
 		host, _, err := net.SplitHostPort(addr)
 		if err != nil {

controller/relay.go

@@ -2,6 +2,7 @@ package controller
 
 import (
 	"bytes"
+	"errors"
 	"fmt"
 	"io"
 	"log"
@@ -20,6 +21,7 @@ import (
 	"github.com/QuantumNous/new-api/relay/helper"
 	"github.com/QuantumNous/new-api/service"
 	"github.com/QuantumNous/new-api/setting"
+	"github.com/QuantumNous/new-api/setting/operation_setting"
 	"github.com/QuantumNous/new-api/types"
 
 	"github.com/bytedance/gopkg/util/gopool"
@@ -43,7 +45,7 @@ func relayHandler(c *gin.Context, info *relaycommon.RelayInfo) *types.NewAPIErro
 		err = relay.RerankHelper(c, info)
 	case relayconstant.RelayModeEmbeddings:
 		err = relay.EmbeddingHelper(c, info)
-	case relayconstant.RelayModeResponses:
+	case relayconstant.RelayModeResponses, relayconstant.RelayModeResponsesCompact:
 		err = relay.ResponsesHelper(c, info)
 	default:
 		err = relay.TextHelper(c, info)
@@ -64,8 +66,8 @@ 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
@@ -104,7 +106,12 @@ func Relay(c *gin.Context, relayFormat types.RelayFormat) {
 
 	request, err := helper.GetAndValidateRequest(c, relayFormat)
 	if err != nil {
-		newAPIError = types.NewError(err, types.ErrorCodeInvalidRequest)
+		// 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)
+		}
 		return
 	}
 
@@ -114,9 +121,17 @@ func Relay(c *gin.Context, relayFormat types.RelayFormat) {
 		return
 	}
 
-	meta := request.GetTokenCountMeta()
+	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)
+	}
 
-	if setting.ShouldCheckPromptSensitive() {
+	if needSensitiveCheck && meta != nil {
 		contains, words := service.CheckSensitiveText(meta.CombineText)
 		if contains {
 			logger.LogWarn(c, fmt.Sprintf("user sensitive words detected: %s", strings.Join(words, ", ")))
@@ -125,13 +140,13 @@ func Relay(c *gin.Context, relayFormat types.RelayFormat) {
 		}
 	}
 
-	tokens, err := service.CountRequestToken(c, meta, relayInfo)
+	tokens, err := service.EstimateRequestToken(c, meta, relayInfo)
 	if err != nil {
 		newAPIError = types.NewError(err, types.ErrorCodeCountTokenFailed)
 		return
 	}
 
-	relayInfo.SetPromptTokens(tokens)
+	relayInfo.SetEstimatePromptTokens(tokens)
 
 	priceData, err := helper.ModelPriceHelper(c, relayInfo, tokens, meta)
 	if err != nil {
@@ -152,21 +167,41 @@ func Relay(c *gin.Context, relayFormat types.RelayFormat) {
 
 	defer func() {
 		// Only return quota if downstream failed and quota was actually pre-consumed
-		if newAPIError != nil && relayInfo.FinalPreConsumedQuota != 0 {
-			service.ReturnPreConsumedQuota(c, relayInfo)
+		if newAPIError != nil {
+			newAPIError = service.NormalizeViolationFeeError(newAPIError)
+			if relayInfo.FinalPreConsumedQuota != 0 {
+				service.ReturnPreConsumedQuota(c, relayInfo)
+			}
+			service.ChargeViolationFeeIfNeeded(c, relayInfo, newAPIError)
 		}
 	}()
 
-	for i := 0; i <= common.RetryTimes; i++ {
-		channel, err := getChannel(c, group, originalModel, i)
-		if err != nil {
-			logger.LogError(c, err.Error())
-			newAPIError = err
+	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
 			break
 		}
 
 		addUsedChannel(c, channel.Id)
-		requestBody, _ := common.GetRequestBody(c)
+		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
+		}
 		c.Request.Body = io.NopCloser(bytes.NewBuffer(requestBody))
 
 		switch relayFormat {
@@ -184,9 +219,11 @@ func Relay(c *gin.Context, relayFormat types.RelayFormat) {
 			return
 		}
 
+		newAPIError = service.NormalizeViolationFeeError(newAPIError)
+
 		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-i) {
+		if !shouldRetry(c, newAPIError, common.RetryTimes-retryParam.GetRetry()) {
 			break
 		}
 	}
@@ -211,8 +248,35 @@ func addUsedChannel(c *gin.Context, channelId int) {
 	c.Set("use_channel", useChannel)
 }
 
-func getChannel(c *gin.Context, group, originalModel string, retryCount int) (*model.Channel, *types.NewAPIError) {
-	if retryCount == 0 {
+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 {
 		autoBan := c.GetBool("auto_ban")
 		autoBanInt := 1
 		if !autoBan {
@@ -225,14 +289,18 @@ func getChannel(c *gin.Context, group, originalModel string, retryCount int) (*m
 			AutoBan: &autoBanInt,
 		}, nil
 	}
-	channel, selectGroup, err := service.CacheGetRandomSatisfiedChannel(c, group, originalModel, retryCount)
+	channel, selectGroup, err := service.CacheGetRandomSatisfiedChannel(retryParam)
+
+	info.PriceData.GroupRatioInfo = helper.HandleGroupRatio(c, info)
+
 	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, originalModel, 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, info.OriginModelName, 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, originalModel), 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, info.OriginModelName), types.ErrorCodeGetChannelFailed, types.ErrOptionWithSkipRetry())
 	}
-	newAPIError := middleware.SetupContextForSelectedChannel(c, channel, originalModel)
+
+	newAPIError := middleware.SetupContextForSelectedChannel(c, channel, info.OriginModelName)
 	if newAPIError != nil {
 		return nil, newAPIError
 	}
@@ -255,39 +323,23 @@ func shouldRetry(c *gin.Context, openaiErr *types.NewAPIError, retryTimes int) b
 	if _, ok := c.Get("specific_channel_id"); ok {
 		return false
 	}
-	if openaiErr.StatusCode == http.StatusTooManyRequests {
-		return true
-	}
-	if openaiErr.StatusCode == 307 {
-		return true
-	}
-	if openaiErr.StatusCode/100 == 5 {
-		// 超时不重试
-		if openaiErr.StatusCode == 504 || openaiErr.StatusCode == 524 {
-			return false
-		}
-		return true
-	}
-	if openaiErr.StatusCode == http.StatusBadRequest {
+	code := openaiErr.StatusCode
+	if code >= 200 && code < 300 {
 		return false
 	}
-	if openaiErr.StatusCode == 408 {
-		// azure处理超时不重试
-		return false
+	if code < 100 || code > 599 {
+		return true
 	}
-	if openaiErr.StatusCode/100 == 2 {
-		return false
-	}
-	return true
+	return operation_setting.ShouldRetryByStatusCode(code)
 }
 
 func processChannelError(c *gin.Context, channelError types.ChannelError, err *types.NewAPIError) {
 	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.ChannelId, err) && channelError.AutoBan {
+	if service.ShouldDisableChannel(channelError.ChannelType, err) && channelError.AutoBan {
 		gopool.Go(func() {
-			service.DisableChannel(channelError, err.Error())
+			service.DisableChannel(channelError, err.ErrorWithStatusCode())
 		})
 	}
 
@@ -316,8 +368,9 @@ func processChannelError(c *gin.Context, channelError types.ChannelError, err *t
 			adminInfo["is_multi_key"] = true
 			adminInfo["multi_key_index"] = common.GetContextKeyInt(c, constant.ContextKeyChannelMultiKeyIndex)
 		}
+		service.AppendChannelAffinityAdminInfo(c, adminInfo)
 		other["admin_info"] = adminInfo
-		model.RecordErrorLog(c, userId, channelId, modelName, tokenName, err.MaskSensitiveError(), tokenId, 0, false, userGroup, other)
+		model.RecordErrorLog(c, userId, channelId, modelName, tokenName, err.MaskSensitiveErrorWithStatusCode(), tokenId, 0, false, userGroup, other)
 	}
 
 }
@@ -366,7 +419,7 @@ func RelayMidjourney(c *gin.Context) {
 }
 
 func RelayNotImplemented(c *gin.Context) {
-	err := dto.OpenAIError{
+	err := types.OpenAIError{
 		Message: "API not implemented",
 		Type:    "new_api_error",
 		Param:   "",
@@ -378,7 +431,7 @@ func RelayNotImplemented(c *gin.Context) {
 }
 
 func RelayNotFound(c *gin.Context) {
-	err := dto.OpenAIError{
+	err := types.OpenAIError{
 		Message: fmt.Sprintf("Invalid URL (%s %s)", c.Request.Method, c.Request.URL.Path),
 		Type:    "invalid_request_error",
 		Param:   "",
@@ -392,8 +445,6 @@ 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 {
@@ -403,8 +454,14 @@ func RelayTask(c *gin.Context) {
 	if taskErr == nil {
 		retryTimes = 0
 	}
-	for i := 0; shouldRetryTaskRelay(c, channelId, taskErr, retryTimes) && i < retryTimes; i++ {
-		channel, newAPIError := getChannel(c, group, originalModel, i)
+	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)
 		if newAPIError != nil {
 			logger.LogError(c, fmt.Sprintf("CacheGetRandomSatisfiedChannel failed: %s", newAPIError.Error()))
 			taskErr = service.TaskErrorWrapperLocal(newAPIError.Err, "get_channel_failed", http.StatusInternalServerError)
@@ -414,10 +471,18 @@ 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, i))
+		logger.LogInfo(c, fmt.Sprintf("using channel #%d to retry (remain times %d)", channel.Id, retryParam.GetRetry()))
 		//middleware.SetupContextForSelectedChannel(c, channel, originalModel)
 
-		requestBody, _ := common.GetRequestBody(c)
+		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
+		}
 		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(500)
+		allTasks := model.GetAllUnFinishSyncTasks(constant.TaskQueryLimit)
 		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: %d", channelId, err.Error()))
+			logger.LogError(ctx, fmt.Sprintf("渠道 #%d 更新异步任务失败: %s", channelId, err.Error()))
 		}
 	}
 	return nil
@@ -116,9 +116,10 @@ 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
@@ -140,7 +141,7 @@ 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: %d", 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: %s", channelId, len(taskIds), string(responseBody)))
 		return err
 	}
 

controller/task_video.go

@@ -52,6 +52,7 @@ func updateVideoTaskAll(ctx context.Context, platform constant.TaskPlatform, cha
 	info.ChannelMeta = &relaycommon.ChannelMeta{
 		ChannelBaseUrl: cacheGetChannel.GetBaseURL(),
 	}
+	info.ApiKey = cacheGetChannel.Key
 	adaptor.Init(info)
 	for _, taskId := range taskIds {
 		if err := updateVideoSingleTask(ctx, adaptor, cacheGetChannel, taskId, taskM); err != nil {
@@ -66,16 +67,23 @@ 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 {
 		logger.LogError(ctx, fmt.Sprintf("Task %s not found in taskM", taskId))
 		return fmt.Errorf("task %s not found", taskId)
 	}
-	resp, err := adaptor.FetchTask(baseURL, channel.Key, map[string]any{
+	key := channel.Key
+
+	privateData := task.PrivateData
+	if privateData.Key != "" {
+		key = privateData.Key
+	}
+	resp, err := adaptor.FetchTask(baseURL, 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

@@ -1,6 +1,7 @@
 package controller
 
 import (
+	"fmt"
 	"net/http"
 	"strconv"
 	"strings"
@@ -142,13 +143,31 @@ func AddToken(c *gin.Context) {
 		common.ApiError(c, err)
 		return
 	}
-	if len(token.Name) > 30 {
+	if len(token.Name) > 50 {
 		c.JSON(http.StatusOK, gin.H{
 			"success": false,
 			"message": "令牌名称过长",
 		})
 		return
 	}
+	// 非无限额度时，检查额度值是否超出有效范围
+	if !token.UnlimitedQuota {
+		if token.RemainQuota < 0 {
+			c.JSON(http.StatusOK, gin.H{
+				"success": false,
+				"message": "额度值不能为负数",
+			})
+			return
+		}
+		maxQuotaValue := int((1000000000 * common.QuotaPerUnit))
+		if token.RemainQuota > maxQuotaValue {
+			c.JSON(http.StatusOK, gin.H{
+				"success": false,
+				"message": fmt.Sprintf("额度值超出有效范围，最大值为 %d", maxQuotaValue),
+			})
+			return
+		}
+	}
 	key, err := common.GenerateKey()
 	if err != nil {
 		c.JSON(http.StatusOK, gin.H{
@@ -171,6 +190,7 @@ func AddToken(c *gin.Context) {
 		ModelLimits:        token.ModelLimits,
 		AllowIps:           token.AllowIps,
 		Group:              token.Group,
+		CrossGroupRetry:    token.CrossGroupRetry,
 	}
 	err = cleanToken.Insert()
 	if err != nil {
@@ -208,13 +228,30 @@ func UpdateToken(c *gin.Context) {
 		common.ApiError(c, err)
 		return
 	}
-	if len(token.Name) > 30 {
+	if len(token.Name) > 50 {
 		c.JSON(http.StatusOK, gin.H{
 			"success": false,
 			"message": "令牌名称过长",
 		})
 		return
 	}
+	if !token.UnlimitedQuota {
+		if token.RemainQuota < 0 {
+			c.JSON(http.StatusOK, gin.H{
+				"success": false,
+				"message": "额度值不能为负数",
+			})
+			return
+		}
+		maxQuotaValue := int((1000000000 * common.QuotaPerUnit))
+		if token.RemainQuota > maxQuotaValue {
+			c.JSON(http.StatusOK, gin.H{
+				"success": false,
+				"message": fmt.Sprintf("额度值超出有效范围，最大值为 %d", maxQuotaValue),
+			})
+			return
+		}
+	}
 	cleanToken, err := model.GetTokenByIds(token.Id, userId)
 	if err != nil {
 		common.ApiError(c, err)
@@ -248,6 +285,7 @@ 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 {
@@ -259,7 +297,6 @@ func UpdateToken(c *gin.Context) {
 		"message": "",
 		"data":    cleanToken,
 	})
-	return
 }
 
 type TokenBatch struct {

controller/topup_creem.go

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

controller/user.go

@@ -110,18 +110,17 @@ 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":    cleanUser,
+		"data": map[string]any{
+			"id":           user.Id,
+			"username":     user.Username,
+			"display_name": user.DisplayName,
+			"role":         user.Role,
+			"status":       user.Status,
+			"group":        user.Group,
+		},
 	})
 }
 
@@ -453,6 +452,7 @@ func GetSelf(c *gin.Context) {
 		"status":            user.Status,
 		"email":             user.Email,
 		"github_id":         user.GitHubId,
+		"discord_id":        user.DiscordId,
 		"oidc_id":           user.OidcId,
 		"wechat_id":         user.WeChatId,
 		"telegram_id":       user.TelegramId,
@@ -763,7 +763,10 @@ func checkUpdatePassword(originalPassword string, newPassword string, userId int
 	if err != nil {
 		return
 	}
-	if !common.ValidatePasswordAndHash(originalPassword, currentUser.Password) {
+
+	// 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 != "" {
 		err = fmt.Errorf("原密码错误")
 		return
 	}

controller/video_proxy.go

@@ -1,6 +1,7 @@
 package controller
 
 import (
+	"context"
 	"fmt"
 	"io"
 	"net/http"
@@ -10,6 +11,7 @@ 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"
 )
@@ -75,11 +77,22 @@ func VideoProxy(c *gin.Context) {
 	}
 
 	var videoURL string
-	client := &http.Client{
-		Timeout: 60 * time.Second,
+	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
 	}
 
-	req, err := http.NewRequestWithContext(c.Request.Context(), http.MethodGet, "", nil)
+	ctx, cancel := context.WithTimeout(c.Request.Context(), 60*time.Second)
+	defer cancel()
+	req, err := http.NewRequestWithContext(ctx, 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{
@@ -117,13 +130,12 @@ func VideoProxy(c *gin.Context) {
 			return
 		}
 		req.Header.Set("x-goog-api-key", apiKey)
-	case constant.ChannelTypeAli:
-		// Video URL is directly in task.FailReason
-		videoURL = task.FailReason
-	default:
-		// Default (Sora, etc.): Use original logic
+	case constant.ChannelTypeOpenAI, constant.ChannelTypeSora:
 		videoURL = fmt.Sprintf("%s/v1/videos/%s/content", baseURL, task.TaskID)
 		req.Header.Set("Authorization", "Bearer "+channel.Key)
+	default:
+		// Video URL is directly in task.FailReason
+		videoURL = task.FailReason
 	}
 
 	req.URL, err = url.Parse(videoURL)

controller/video_proxy_gemini.go

@@ -35,10 +35,11 @@ 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

@@ -1,53 +0,0 @@
-# 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

@@ -1,197 +0,0 @@
-# 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/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/ionet-client.md

@@ -0,0 +1,7 @@
+Request URL
+https://api.io.solutions/v1/io-cloud/clusters/654fc0a9-0d4a-4db4-9b95-3f56189348a2/update-name
+Request Method
+PUT
+
+{"status":"succeeded","message":"Cluster name updated successfully"}
+

docs/models/Midjourney.md

@@ -1,82 +0,0 @@
-# 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

@@ -1,62 +0,0 @@
-# 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

@@ -1,44 +0,0 @@
-# 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

@@ -2,6 +2,7 @@ package dto
 
 import (
 	"encoding/json"
+	"strings"
 
 	"github.com/QuantumNous/new-api/types"
 
@@ -24,11 +25,14 @@ 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 false
+	return r.StreamFormat == "sse"
 }
 
 func (r *AudioRequest) SetModelName(modelName string) {

dto/claude.go

@@ -203,6 +203,9 @@ 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

@@ -1,26 +1,33 @@
 package dto
 
-import "github.com/QuantumNous/new-api/types"
+import (
+	"encoding/json"
 
-type OpenAIError struct {
-	Message string `json:"message"`
-	Type    string `json:"type"`
-	Param   string `json:"param"`
-	Code    any    `json:"code"`
-}
+	"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 OpenAIErrorWithStatusCode struct {
-	Error      OpenAIError `json:"error"`
-	StatusCode int         `json:"status_code"`
+	Error      types.OpenAIError `json:"error"`
+	StatusCode int               `json:"status_code"`
 	LocalError bool
 }
 
 type GeneralErrorResponse struct {
-	Error    types.OpenAIError `json:"error"`
-	Message  string            `json:"message"`
-	Msg      string            `json:"msg"`
-	Err      string            `json:"err"`
-	ErrorMsg string            `json:"error_msg"`
+	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"`
+	Detail   string          `json:"detail,omitempty"`
 	Header   struct {
 		Message string `json:"message"`
 	} `json:"header"`
@@ -31,9 +38,35 @@ 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 e.Error.Message != "" {
-		return e.Error.Message
+	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.Message != "" {
 		return e.Message
@@ -47,6 +80,9 @@ func (e GeneralErrorResponse) ToMessage() string {
 	if e.ErrorMsg != "" {
 		return e.ErrorMsg
 	}
+	if e.Detail != "" {
+		return e.Detail
+	}
 	if e.Header.Message != "" {
 		return e.Header.Message
 	}

dto/gemini.go

@@ -22,6 +22,27 @@ 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"`
@@ -105,7 +126,7 @@ func (r *GeminiChatRequest) SetModelName(modelName string) {
 
 func (r *GeminiChatRequest) GetTools() []GeminiChatTool {
 	var tools []GeminiChatTool
-	if strings.HasSuffix(string(r.Tools), "[") {
+	if strings.HasPrefix(string(r.Tools), "[") {
 		// is array
 		if err := common.Unmarshal(r.Tools, &tools); err != nil {
 			logger.LogError(nil, "error_unmarshalling_tools: "+err.Error())
@@ -141,6 +162,39 @@ func (r *GeminiChatRequest) SetTools(tools []GeminiChatTool) {
 type GeminiThinkingConfig struct {
 	IncludeThoughts bool `json:"includeThoughts,omitempty"`
 	ThinkingBudget  *int `json:"thinkingBudget,omitempty"`
+	// TODO Conflict with thinkingbudget.
+	ThinkingLevel string `json:"thinkingLevel,omitempty"`
+}
+
+// UnmarshalJSON allows GeminiThinkingConfig to accept both snake_case and camelCase fields.
+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"`
+	}
+
+	if err := common.Unmarshal(data, &aux); err != nil {
+		return err
+	}
+
+	*c = GeminiThinkingConfig(aux.Alias)
+
+	if aux.IncludeThoughtsSnake != nil {
+		c.IncludeThoughts = *aux.IncludeThoughtsSnake
+	}
+
+	if aux.ThinkingBudgetSnake != nil {
+		c.ThinkingBudget = aux.ThinkingBudgetSnake
+	}
+
+	if aux.ThinkingLevelSnake != "" {
+		c.ThinkingLevel = aux.ThinkingLevelSnake
+	}
+
+	return nil
 }
 
 func (c *GeminiThinkingConfig) SetThinkingBudget(budget int) {
@@ -182,8 +236,12 @@ type FunctionCall struct {
 }
 
 type GeminiFunctionResponse struct {
-	Name     string                 `json:"name"`
-	Response map[string]interface{} `json:"response"`
+	Name         string                 `json:"name"`
+	Response     map[string]interface{} `json:"response"`
+	WillContinue json.RawMessage        `json:"willContinue,omitempty"`
+	Scheduling   json.RawMessage        `json:"scheduling,omitempty"`
+	Parts        json.RawMessage        `json:"parts,omitempty"`
+	ID           json.RawMessage        `json:"id,omitempty"`
 }
 
 type GeminiPartExecutableCode struct {
@@ -202,11 +260,15 @@ type GeminiFileData struct {
 }
 
 type GeminiPart struct {
-	Text                string                         `json:"text,omitempty"`
-	Thought             bool                           `json:"thought,omitempty"`
-	InlineData          *GeminiInlineData              `json:"inlineData,omitempty"`
-	FunctionCall        *FunctionCall                  `json:"functionCall,omitempty"`
-	FunctionResponse    *GeminiFunctionResponse        `json:"functionResponse,omitempty"`
+	Text             string                  `json:"text,omitempty"`
+	Thought          bool                    `json:"thought,omitempty"`
+	InlineData       *GeminiInlineData       `json:"inlineData,omitempty"`
+	FunctionCall     *FunctionCall           `json:"functionCall,omitempty"`
+	ThoughtSignature json.RawMessage         `json:"thoughtSignature,omitempty"`
+	FunctionResponse *GeminiFunctionResponse `json:"functionResponse,omitempty"`
+	// Optional. Media resolution for the input media.
+	MediaResolution     json.RawMessage                `json:"mediaResolution,omitempty"`
+	VideoMetadata       json.RawMessage                `json:"videoMetadata,omitempty"`
 	FileData            *GeminiFileData                `json:"fileData,omitempty"`
 	ExecutableCode      *GeminiPartExecutableCode      `json:"executableCode,omitempty"`
 	CodeExecutionResult *GeminiPartCodeExecutionResult `json:"codeExecutionResult,omitempty"`
@@ -279,6 +341,88 @@ type GeminiChatGenerationConfig struct {
 	ImageConfig        json.RawMessage       `json:"imageConfig,omitempty"`  // RawMessage to allow flexible image config
 }
 
+// UnmarshalJSON allows GeminiChatGenerationConfig to accept both snake_case and camelCase fields.
+func (c *GeminiChatGenerationConfig) UnmarshalJSON(data []byte) error {
+	type Alias GeminiChatGenerationConfig
+	var aux struct {
+		Alias
+		TopPSnake               float64               `json:"top_p,omitempty"`
+		TopKSnake               float64               `json:"top_k,omitempty"`
+		MaxOutputTokensSnake    uint                  `json:"max_output_tokens,omitempty"`
+		CandidateCountSnake     int                   `json:"candidate_count,omitempty"`
+		StopSequencesSnake      []string              `json:"stop_sequences,omitempty"`
+		ResponseMimeTypeSnake   string                `json:"response_mime_type,omitempty"`
+		ResponseSchemaSnake     any                   `json:"response_schema,omitempty"`
+		ResponseJsonSchemaSnake json.RawMessage       `json:"response_json_schema,omitempty"`
+		PresencePenaltySnake    *float32              `json:"presence_penalty,omitempty"`
+		FrequencyPenaltySnake   *float32              `json:"frequency_penalty,omitempty"`
+		ResponseLogprobsSnake   bool                  `json:"response_logprobs,omitempty"`
+		MediaResolutionSnake    MediaResolution       `json:"media_resolution,omitempty"`
+		ResponseModalitiesSnake []string              `json:"response_modalities,omitempty"`
+		ThinkingConfigSnake     *GeminiThinkingConfig `json:"thinking_config,omitempty"`
+		SpeechConfigSnake       json.RawMessage       `json:"speech_config,omitempty"`
+		ImageConfigSnake        json.RawMessage       `json:"image_config,omitempty"`
+	}
+
+	if err := common.Unmarshal(data, &aux); err != nil {
+		return err
+	}
+
+	*c = GeminiChatGenerationConfig(aux.Alias)
+
+	// Prioritize snake_case if present
+	if aux.TopPSnake != 0 {
+		c.TopP = aux.TopPSnake
+	}
+	if aux.TopKSnake != 0 {
+		c.TopK = aux.TopKSnake
+	}
+	if aux.MaxOutputTokensSnake != 0 {
+		c.MaxOutputTokens = aux.MaxOutputTokensSnake
+	}
+	if aux.CandidateCountSnake != 0 {
+		c.CandidateCount = aux.CandidateCountSnake
+	}
+	if len(aux.StopSequencesSnake) > 0 {
+		c.StopSequences = aux.StopSequencesSnake
+	}
+	if aux.ResponseMimeTypeSnake != "" {
+		c.ResponseMimeType = aux.ResponseMimeTypeSnake
+	}
+	if aux.ResponseSchemaSnake != nil {
+		c.ResponseSchema = aux.ResponseSchemaSnake
+	}
+	if len(aux.ResponseJsonSchemaSnake) > 0 {
+		c.ResponseJsonSchema = aux.ResponseJsonSchemaSnake
+	}
+	if aux.PresencePenaltySnake != nil {
+		c.PresencePenalty = aux.PresencePenaltySnake
+	}
+	if aux.FrequencyPenaltySnake != nil {
+		c.FrequencyPenalty = aux.FrequencyPenaltySnake
+	}
+	if aux.ResponseLogprobsSnake {
+		c.ResponseLogprobs = aux.ResponseLogprobsSnake
+	}
+	if aux.MediaResolutionSnake != "" {
+		c.MediaResolution = aux.MediaResolutionSnake
+	}
+	if len(aux.ResponseModalitiesSnake) > 0 {
+		c.ResponseModalities = aux.ResponseModalitiesSnake
+	}
+	if aux.ThinkingConfigSnake != nil {
+		c.ThinkingConfig = aux.ThinkingConfigSnake
+	}
+	if len(aux.SpeechConfigSnake) > 0 {
+		c.SpeechConfig = aux.SpeechConfigSnake
+	}
+	if len(aux.ImageConfigSnake) > 0 {
+		c.ImageConfig = aux.ImageConfigSnake
+	}
+
+	return nil
+}
+
 type MediaResolution string
 
 type GeminiChatCandidate struct {

dto/openai_compaction.go

@@ -0,0 +1,20 @@
+package dto
+
+import (
+	"encoding/json"
+
+	"github.com/QuantumNous/new-api/types"
+)
+
+type OpenAIResponsesCompactionResponse struct {
+	ID        string          `json:"id"`
+	Object    string          `json:"object"`
+	CreatedAt int             `json:"created_at"`
+	Output    json.RawMessage `json:"output"`
+	Usage     *Usage          `json:"usage"`
+	Error     any             `json:"error,omitempty"`
+}
+
+func (o *OpenAIResponsesCompactionResponse) GetOpenAIError() *types.OpenAIError {
+	return GetOpenAIError(o.Error)
+}

dto/openai_image.go

@@ -27,8 +27,11 @@ 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"`
-	Image     json.RawMessage `json:"image,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"`
 	// 用匿名参数接收额外参数
 	Extra map[string]json.RawMessage `json:"-"`
 }
@@ -164,9 +167,9 @@ func (i *ImageRequest) SetModelName(modelName string) {
 }
 
 type ImageResponse struct {
-	Data    []ImageData `json:"data"`
-	Created int64       `json:"created"`
-	Extra   any         `json:"extra,omitempty"`
+	Data     []ImageData     `json:"data"`
+	Created  int64           `json:"created"`
+	Metadata json.RawMessage `json:"metadata,omitempty"`
 }
 type ImageData struct {
 	Url           string `json:"url"`

dto/openai_request.go

@@ -23,6 +23,8 @@ type FormatJsonSchema struct {
 	Strict      json.RawMessage `json:"strict,omitempty"`
 }
 
+// GeneralOpenAIRequest represents a general request structure for OpenAI-compatible APIs.
+// 参数增加规范：无引用的参数必须使用json.RawMessage类型，并添加omitempty标签
 type GeneralOpenAIRequest struct {
 	Model               string            `json:"model,omitempty"`
 	Messages            []Message         `json:"messages,omitempty"`
@@ -66,10 +68,11 @@ type GeneralOpenAIRequest struct {
 	// 注意：默认过滤此字段以保护用户隐私，但过滤后可能导致 Codex 无法正常使用
 	Store json.RawMessage `json:"store,omitempty"`
 	// Used by OpenAI to cache responses for similar requests to optimize your cache hit rates. Replaces the user field
-	PromptCacheKey string          `json:"prompt_cache_key,omitempty"`
-	LogitBias      json.RawMessage `json:"logit_bias,omitempty"`
-	Metadata       json.RawMessage `json:"metadata,omitempty"`
-	Prediction     json.RawMessage `json:"prediction,omitempty"`
+	PromptCacheKey       string          `json:"prompt_cache_key,omitempty"`
+	PromptCacheRetention json.RawMessage `json:"prompt_cache_retention,omitempty"`
+	LogitBias            json.RawMessage `json:"logit_bias,omitempty"`
+	Metadata             json.RawMessage `json:"metadata,omitempty"`
+	Prediction           json.RawMessage `json:"prediction,omitempty"`
 	// gemini
 	ExtraBody json.RawMessage `json:"extra_body,omitempty"`
 	//xai
@@ -81,7 +84,9 @@ type GeneralOpenAIRequest struct {
 	Reasoning json.RawMessage `json:"reasoning,omitempty"`
 	// Ali Qwen Params
 	VlHighResolutionImages json.RawMessage `json:"vl_high_resolution_images,omitempty"`
-	EnableThinking         any             `json:"enable_thinking,omitempty"`
+	EnableThinking         json.RawMessage `json:"enable_thinking,omitempty"`
+	ChatTemplateKwargs     json.RawMessage `json:"chat_template_kwargs,omitempty"`
+	EnableSearch           json.RawMessage `json:"enable_search,omitempty"`
 	// ollama Params
 	Think json.RawMessage `json:"think,omitempty"`
 	// baidu v2
@@ -232,10 +237,13 @@ func (r *GeneralOpenAIRequest) GetSystemRoleName() string {
 	return "system"
 }
 
+const CustomType = "custom"
+
 type ToolCallRequest struct {
 	ID       string          `json:"id,omitempty"`
 	Type     string          `json:"type"`
-	Function FunctionRequest `json:"function"`
+	Function FunctionRequest `json:"function,omitempty"`
+	Custom   json.RawMessage `json:"custom,omitempty"`
 }
 
 type FunctionRequest struct {
@@ -795,19 +803,20 @@ type OpenAIResponsesRequest struct {
 	PreviousResponseID string          `json:"previous_response_id,omitempty"`
 	Reasoning          *Reasoning      `json:"reasoning,omitempty"`
 	// 服务层级字段，用于指定 API 服务等级。允许透传可能导致实际计费高于预期，默认应过滤
-	ServiceTier    string          `json:"service_tier,omitempty"`
-	Store          json.RawMessage `json:"store,omitempty"`
-	PromptCacheKey json.RawMessage `json:"prompt_cache_key,omitempty"`
-	Stream         bool            `json:"stream,omitempty"`
-	Temperature    float64         `json:"temperature,omitempty"`
-	Text           json.RawMessage `json:"text,omitempty"`
-	ToolChoice     json.RawMessage `json:"tool_choice,omitempty"`
-	Tools          json.RawMessage `json:"tools,omitempty"` // 需要处理的参数很少，MCP 参数太多不确定，所以用 map
-	TopP           float64         `json:"top_p,omitempty"`
-	Truncation     string          `json:"truncation,omitempty"`
-	User           string          `json:"user,omitempty"`
-	MaxToolCalls   uint            `json:"max_tool_calls,omitempty"`
-	Prompt         json.RawMessage `json:"prompt,omitempty"`
+	ServiceTier          string          `json:"service_tier,omitempty"`
+	Store                json.RawMessage `json:"store,omitempty"`
+	PromptCacheKey       json.RawMessage `json:"prompt_cache_key,omitempty"`
+	PromptCacheRetention json.RawMessage `json:"prompt_cache_retention,omitempty"`
+	Stream               bool            `json:"stream,omitempty"`
+	Temperature          *float64        `json:"temperature,omitempty"`
+	Text                 json.RawMessage `json:"text,omitempty"`
+	ToolChoice           json.RawMessage `json:"tool_choice,omitempty"`
+	Tools                json.RawMessage `json:"tools,omitempty"` // 需要处理的参数很少，MCP 参数太多不确定，所以用 map
+	TopP                 *float64        `json:"top_p,omitempty"`
+	Truncation           string          `json:"truncation,omitempty"`
+	User                 string          `json:"user,omitempty"`
+	MaxToolCalls         uint            `json:"max_tool_calls,omitempty"`
+	Prompt               json.RawMessage `json:"prompt,omitempty"`
 }
 
 func (r *OpenAIResponsesRequest) GetTokenCountMeta() *types.TokenCountMeta {
@@ -892,6 +901,12 @@ type Reasoning struct {
 	Summary string `json:"summary,omitempty"`
 }
 
+type Input struct {
+	Type    string          `json:"type,omitempty"`
+	Role    string          `json:"role,omitempty"`
+	Content json.RawMessage `json:"content,omitempty"`
+}
+
 type MediaInput struct {
 	Type     string `json:"type"`
 	Text     string `json:"text,omitempty"`
@@ -910,7 +925,7 @@ func (r *OpenAIResponsesRequest) ParseInput() []MediaInput {
 		return nil
 	}
 
-	var inputs []MediaInput
+	var mediaInputs []MediaInput
 
 	// Try string first
 	// if str, ok := common.GetJsonType(r.Input); ok {
@@ -920,60 +935,74 @@ func (r *OpenAIResponsesRequest) ParseInput() []MediaInput {
 	if common.GetJsonType(r.Input) == "string" {
 		var str string
 		_ = common.Unmarshal(r.Input, &str)
-		inputs = append(inputs, MediaInput{Type: "input_text", Text: str})
-		return inputs
+		mediaInputs = append(mediaInputs, MediaInput{Type: "input_text", Text: str})
+		return mediaInputs
 	}
 
 	// Try array of parts
 	if common.GetJsonType(r.Input) == "array" {
-		var array []any
-		_ = common.Unmarshal(r.Input, &array)
-		for _, itemAny := range array {
-			// Already parsed MediaInput
-			if media, ok := itemAny.(MediaInput); ok {
-				inputs = append(inputs, media)
-				continue
+		var inputs []Input
+		_ = common.Unmarshal(r.Input, &inputs)
+		for _, input := range inputs {
+			if common.GetJsonType(input.Content) == "string" {
+				var str string
+				_ = common.Unmarshal(input.Content, &str)
+				mediaInputs = append(mediaInputs, MediaInput{Type: "input_text", Text: str})
 			}
-			// Generic map
-			item, ok := itemAny.(map[string]any)
-			if !ok {
-				continue
-			}
-			typeVal, ok := item["type"].(string)
-			if !ok {
-				continue
-			}
-			switch typeVal {
-			case "input_text":
-				text, _ := item["text"].(string)
-				inputs = append(inputs, MediaInput{Type: "input_text", Text: text})
-			case "input_image":
-				// image_url may be string or object with url field
-				var imageUrl string
-				switch v := item["image_url"].(type) {
-				case string:
-					imageUrl = v
-				case map[string]any:
-					if url, ok := v["url"].(string); ok {
-						imageUrl = url
+
+			if common.GetJsonType(input.Content) == "array" {
+				var array []any
+				_ = common.Unmarshal(input.Content, &array)
+				for _, itemAny := range array {
+					// Already parsed MediaContent
+					if media, ok := itemAny.(MediaInput); ok {
+						mediaInputs = append(mediaInputs, media)
+						continue
+					}
+
+					// Generic map
+					item, ok := itemAny.(map[string]any)
+					if !ok {
+						continue
+					}
+
+					typeVal, ok := item["type"].(string)
+					if !ok {
+						continue
+					}
+					switch typeVal {
+					case "input_text":
+						text, _ := item["text"].(string)
+						mediaInputs = append(mediaInputs, MediaInput{Type: "input_text", Text: text})
+					case "input_image":
+						// image_url may be string or object with url field
+						var imageUrl string
+						switch v := item["image_url"].(type) {
+						case string:
+							imageUrl = v
+						case map[string]any:
+							if url, ok := v["url"].(string); ok {
+								imageUrl = url
+							}
+						}
+						mediaInputs = append(mediaInputs, MediaInput{Type: "input_image", ImageUrl: imageUrl})
+					case "input_file":
+						// file_url may be string or object with url field
+						var fileUrl string
+						switch v := item["file_url"].(type) {
+						case string:
+							fileUrl = v
+						case map[string]any:
+							if url, ok := v["url"].(string); ok {
+								fileUrl = url
+							}
+						}
+						mediaInputs = append(mediaInputs, MediaInput{Type: "input_file", FileUrl: fileUrl})
 					}
 				}
-				inputs = append(inputs, MediaInput{Type: "input_image", ImageUrl: imageUrl})
-			case "input_file":
-				// file_url may be string or object with url field
-				var fileUrl string
-				switch v := item["file_url"].(type) {
-				case string:
-					fileUrl = v
-				case map[string]any:
-					if url, ok := v["url"].(string); ok {
-						fileUrl = url
-					}
-				}
-				inputs = append(inputs, MediaInput{Type: "input_file", FileUrl: fileUrl})
 			}
 		}
 	}
 
-	return inputs
+	return mediaInputs
 }

dto/openai_response.go

@@ -334,13 +334,16 @@ type IncompleteDetails struct {
 }
 
 type ResponsesOutput struct {
-	Type    string                   `json:"type"`
-	ID      string                   `json:"id"`
-	Status  string                   `json:"status"`
-	Role    string                   `json:"role"`
-	Content []ResponsesOutputContent `json:"content"`
-	Quality string                   `json:"quality"`
-	Size    string                   `json:"size"`
+	Type      string                   `json:"type"`
+	ID        string                   `json:"id"`
+	Status    string                   `json:"status"`
+	Role      string                   `json:"role"`
+	Content   []ResponsesOutputContent `json:"content"`
+	Quality   string                   `json:"quality"`
+	Size      string                   `json:"size"`
+	CallId    string                   `json:"call_id,omitempty"`
+	Name      string                   `json:"name,omitempty"`
+	Arguments string                   `json:"arguments,omitempty"`
 }
 
 type ResponsesOutputContent struct {
@@ -369,6 +372,10 @@ type ResponsesStreamResponse struct {
 	Response *OpenAIResponsesResponse `json:"response,omitempty"`
 	Delta    string                   `json:"delta,omitempty"`
 	Item     *ResponsesOutput         `json:"item,omitempty"`
+	// - response.function_call_arguments.delta
+	// - response.function_call_arguments.done
+	OutputIndex *int   `json:"output_index,omitempty"`
+	ItemID      string `json:"item_id,omitempty"`
 }
 
 // GetOpenAIError 从动态错误类型中提取OpenAIError结构

dto/openai_responses_compaction_request.go

@@ -0,0 +1,40 @@
+package dto
+
+import (
+	"encoding/json"
+	"strings"
+
+	"github.com/QuantumNous/new-api/types"
+
+	"github.com/gin-gonic/gin"
+)
+
+type OpenAIResponsesCompactionRequest struct {
+	Model              string          `json:"model"`
+	Input              json.RawMessage `json:"input,omitempty"`
+	Instructions       json.RawMessage `json:"instructions,omitempty"`
+	PreviousResponseID string          `json:"previous_response_id,omitempty"`
+}
+
+func (r *OpenAIResponsesCompactionRequest) GetTokenCountMeta() *types.TokenCountMeta {
+	var parts []string
+	if len(r.Instructions) > 0 {
+		parts = append(parts, string(r.Instructions))
+	}
+	if len(r.Input) > 0 {
+		parts = append(parts, string(r.Input))
+	}
+	return &types.TokenCountMeta{
+		CombineText: strings.Join(parts, "\n"),
+	}
+}
+
+func (r *OpenAIResponsesCompactionRequest) IsStream(c *gin.Context) bool {
+	return false
+}
+
+func (r *OpenAIResponsesCompactionRequest) SetModelName(modelName string) {
+	if modelName != "" {
+		r.Model = modelName
+	}
+}

dto/values.go

@@ -0,0 +1,55 @@
+package dto
+
+import (
+	"encoding/json"
+	"strconv"
+)
+
+type IntValue int
+
+func (i *IntValue) UnmarshalJSON(b []byte) error {
+	var n int
+	if err := json.Unmarshal(b, &n); err == nil {
+		*i = IntValue(n)
+		return nil
+	}
+	var s string
+	if err := json.Unmarshal(b, &s); err != nil {
+		return err
+	}
+	v, err := strconv.Atoi(s)
+	if err != nil {
+		return err
+	}
+	*i = IntValue(v)
+	return nil
+}
+
+func (i IntValue) MarshalJSON() ([]byte, error) {
+	return json.Marshal(int(i))
+}
+
+type BoolValue bool
+
+func (b *BoolValue) UnmarshalJSON(data []byte) error {
+	var boolean bool
+	if err := json.Unmarshal(data, &boolean); err == nil {
+		*b = BoolValue(boolean)
+		return nil
+	}
+	var str string
+	if err := json.Unmarshal(data, &str); err != nil {
+		return err
+	}
+	if str == "true" {
+		*b = BoolValue(true)
+	} else if str == "false" {
+		*b = BoolValue(false)
+	} else {
+		return json.Unmarshal(data, &boolean)
+	}
+	return nil
+}
+func (b BoolValue) MarshalJSON() ([]byte, error) {
+	return json.Marshal(bool(b))
+}

electron/package-lock.json

@@ -2784,9 +2784,9 @@
       }
     },
     "node_modules/js-yaml": {
-      "version": "4.1.0",
-      "resolved": "https://registry.npmjs.org/js-yaml/-/js-yaml-4.1.0.tgz",
-      "integrity": "sha512-wpxZs9NoxZaJESJGIZTyDEaYpl0FKSA+FB9aJiyemKhMwkxQg63h4T1KJgUGHpTqPDNRcmmYLugrRjJlBtWvRA==",
+      "version": "4.1.1",
+      "resolved": "https://registry.npmjs.org/js-yaml/-/js-yaml-4.1.1.tgz",
+      "integrity": "sha512-qQKT4zQxXl8lLwBtHMWwaTcGfFOZviOJet3Oy/xmGk2gZH677CJM9EvtfdSkgWcATZhj/55JZ0rmy3myCT5lsA==",
       "dev": true,
       "license": "MIT",
       "dependencies": {

go.mod

@@ -27,15 +27,17 @@ 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 v1.39.0
+	github.com/samber/lo v1.52.0
 	github.com/shirou/gopsutil v3.21.11+incompatible
 	github.com/shopspring/decimal v1.4.0
+	github.com/stretchr/testify v1.11.1
 	github.com/stripe/stripe-go/v81 v81.4.0
 	github.com/tcolgate/mp3 v0.0.0-20170426193717-e79c5a46d300
 	github.com/thanhpk/randstr v1.0.6
@@ -43,25 +45,28 @@ require (
 	github.com/tidwall/sjson v1.2.5
 	github.com/tiktoken-go/tokenizer v0.6.2
 	github.com/yapingcat/gomedia v0.0.0-20240906162731-17feea57090c
-	golang.org/x/crypto v0.42.0
+	golang.org/x/crypto v0.45.0
 	golang.org/x/image v0.23.0
-	golang.org/x/net v0.43.0
-	golang.org/x/sync v0.17.0
+	golang.org/x/net v0.47.0
+	golang.org/x/sync v0.18.0
 	gorm.io/driver/mysql v1.4.3
 	gorm.io/driver/postgres v1.5.2
 	gorm.io/gorm v1.25.2
 )
 
 require (
+	github.com/DmitriyVTitov/size v1.5.0 // indirect
 	github.com/anknown/darts v0.0.0-20151216065714-83ff685239e6 // indirect
 	github.com/aws/aws-sdk-go-v2/aws/protocol/eventstream v1.7.0 // indirect
 	github.com/aws/aws-sdk-go-v2/internal/configsources v1.4.2 // indirect
 	github.com/aws/aws-sdk-go-v2/internal/endpoints/v2 v2.7.2 // indirect
+	github.com/beorn7/perks v1.0.1 // indirect
 	github.com/boombuler/barcode v1.1.0 // indirect
 	github.com/bytedance/sonic v1.14.1 // indirect
 	github.com/bytedance/sonic/loader v0.3.0 // indirect
 	github.com/cespare/xxhash/v2 v2.3.0 // indirect
 	github.com/cloudwego/base64x v0.1.6 // indirect
+	github.com/davecgh/go-spew v1.1.2-0.20180830191138-d8f796af33cc // indirect
 	github.com/dgryski/go-rendezvous v0.0.0-20200823014737-9f7001d12a5f // indirect
 	github.com/dlclark/regexp2 v1.11.5 // indirect
 	github.com/dustin/go-humanize v1.0.1 // indirect
@@ -77,11 +82,11 @@ 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
@@ -91,6 +96,7 @@ 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 v1.18.0 // 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
@@ -99,8 +105,18 @@ 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/munnerz/goautoneg v0.0.0-20191010083416-a7dc8b61c822 // indirect
+	github.com/ncruces/go-strftime v0.1.9 // indirect
 	github.com/pelletier/go-toml/v2 v2.2.1 // indirect
+	github.com/pmezard/go-difflib v1.0.1-0.20181226105442-5d4384ee4fb2 // indirect
+	github.com/prometheus/client_golang v1.22.0 // indirect
+	github.com/prometheus/client_model v0.6.1 // indirect
+	github.com/prometheus/common v0.62.0 // indirect
+	github.com/prometheus/procfs v0.15.1 // indirect
 	github.com/remyoudompheng/bigfft v0.0.0-20230129092748-24d4a6f8daec // indirect
+	github.com/samber/go-singleflightx v0.3.2 // indirect
+	github.com/samber/hot v0.11.0 // indirect
+	github.com/stretchr/objx v0.5.2 // indirect
 	github.com/tidwall/match v1.1.1 // indirect
 	github.com/tidwall/pretty v1.2.0 // indirect
 	github.com/tklauser/go-sysconf v0.3.12 // indirect
@@ -110,13 +126,13 @@ 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 v0.0.0-20240404231335-c0f41cb1a7a0 // indirect
-	golang.org/x/sys v0.36.0 // indirect
-	golang.org/x/text v0.29.0 // indirect
-	google.golang.org/protobuf v1.34.2 // indirect
+	golang.org/x/exp v0.0.0-20250620022241-b7579e27df2b // indirect
+	golang.org/x/sys v0.38.0 // indirect
+	golang.org/x/text v0.31.0 // indirect
+	google.golang.org/protobuf v1.36.5 // indirect
 	gopkg.in/yaml.v3 v3.0.1 // 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
+	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
 )

go.sum

@@ -1,5 +1,7 @@
 github.com/Calcium-Ion/go-epay v0.0.4 h1:C96M7WfRLadcIVscWzwLiYs8etI1wrDmtFMuK2zP22A=
 github.com/Calcium-Ion/go-epay v0.0.4/go.mod h1:cxo/ZOg8ClvE3VAnCmEzbuyAZINSq7kFEN9oHj5WQ2U=
+github.com/DmitriyVTitov/size v1.5.0 h1:/PzqxYrOyOUX1BXj6J9OuVRVGe+66VL4D9FlUaW515g=
+github.com/DmitriyVTitov/size v1.5.0/go.mod h1:le6rNI4CoLQV1b9gzp1+3d7hMAD/uu2QcJ+aYbNgiU0=
 github.com/abema/go-mp4 v1.4.1 h1:YoS4VRqd+pAmddRPLFf8vMk74kuGl6ULSjzhsIqwr6M=
 github.com/abema/go-mp4 v1.4.1/go.mod h1:vPl9t5ZK7K0x68jh12/+ECWBCXoWuIDtNgPtU2f04ws=
 github.com/andybalholm/brotli v1.1.1 h1:PR2pgnyFznKEugtsUo0xLdDop5SKXd5Qf5ysW+7XdTA=
@@ -22,6 +24,8 @@ github.com/aws/aws-sdk-go-v2/service/bedrockruntime v1.33.0 h1:JzidOz4Hcn2RbP5fv
 github.com/aws/aws-sdk-go-v2/service/bedrockruntime v1.33.0/go.mod h1:9A4/PJYlWjvjEzzoOLGQjkLt4bYK9fRWi7uz1GSsAcA=
 github.com/aws/smithy-go v1.22.5 h1:P9ATCXPMb2mPjYBgueqJNCA5S9UfktsW0tTxi+a7eqw=
 github.com/aws/smithy-go v1.22.5/go.mod h1:t1ufH5HMublsJYulve2RKmHDC15xu1f26kHCp/HgceI=
+github.com/beorn7/perks v1.0.1 h1:VlbKKnNfV8bJzeqoa4cOKqO6bYr3WgKZxO8Z16+hsOM=
+github.com/beorn7/perks v1.0.1/go.mod h1:G2ZrVWU2WbWT9wwq4/hrbKbnv/1ERSJQ0ibhJ6rlkpw=
 github.com/boombuler/barcode v1.0.1-0.20190219062509-6c824513bacc/go.mod h1:paBWMcWSl3LHKBqUq+rly7CNSldXjb2rDl3JlRe0mD8=
 github.com/boombuler/barcode v1.1.0 h1:ChaYjBR63fr4LFyGn8E8nt7dBSt3MiU3zMOZqFvVkHo=
 github.com/boombuler/barcode v1.1.0/go.mod h1:paBWMcWSl3LHKBqUq+rly7CNSldXjb2rDl3JlRe0mD8=
@@ -40,6 +44,8 @@ github.com/creack/pty v1.1.9/go.mod h1:oKZEueFk5CKHvIhNR5MUki03XCEU+Q6VDXinZuGJ3
 github.com/davecgh/go-spew v1.1.0/go.mod h1:J7Y8YcW2NihsgmVo/mv3lAwl/skON4iLHjSsI+c5H38=
 github.com/davecgh/go-spew v1.1.1 h1:vj9j/u1bqnvCEfJOwUhtlOARqs3+rkHYY13jYWTU97c=
 github.com/davecgh/go-spew v1.1.1/go.mod h1:J7Y8YcW2NihsgmVo/mv3lAwl/skON4iLHjSsI+c5H38=
+github.com/davecgh/go-spew v1.1.2-0.20180830191138-d8f796af33cc h1:U9qPSI2PIWSS1VwoXQT9A3Wy9MM3WgvqSxFWenqJduM=
+github.com/davecgh/go-spew v1.1.2-0.20180830191138-d8f796af33cc/go.mod h1:J7Y8YcW2NihsgmVo/mv3lAwl/skON4iLHjSsI+c5H38=
 github.com/dgryski/go-rendezvous v0.0.0-20200823014737-9f7001d12a5f h1:lO4WD4F/rVNCu3HqELle0jiPLLBs70cWOduZpkS1E78=
 github.com/dgryski/go-rendezvous v0.0.0-20200823014737-9f7001d12a5f/go.mod h1:cuUVRXasLTGF7a8hSLbxyZXjz+1KgoB3wDUb6vlszIc=
 github.com/dlclark/regexp2 v1.11.5 h1:Q/sSnsKerHeCkc/jSTNq1oCm7KiVgUMZRDUoRu0JQZQ=
@@ -110,6 +116,7 @@ github.com/goccy/go-json v0.10.2 h1:CrxCmQqYDkv1z7lO7Wbh2HN93uovUHgrECaO5ZrCXAU=
 github.com/goccy/go-json v0.10.2/go.mod h1:6MelG93GURQebXPDq3khkgXZkazVtN9CRI+MGFi0w8I=
 github.com/golang-jwt/jwt/v5 v5.3.0 h1:pv4AsKCKKZuqlgs5sUmn4x8UlGa0kEVt/puTpKx9vvo=
 github.com/golang-jwt/jwt/v5 v5.3.0/go.mod h1:fxCRLWMO43lRc8nhHWY6LGqRcf+1gQWArsqaEUEa5bE=
+github.com/golang/groupcache v0.0.0-20210331224755-41bb18bfe9da/go.mod h1:cIg4eruTrX1D+g88fzRXU5OdNfaM+9IcxsU14FzY7Hc=
 github.com/golang/protobuf v1.3.3/go.mod h1:vzj43D7+SQXF/4pzW/hwtAqwc6iTitCiVSaWz5lYuqw=
 github.com/golang/protobuf v1.5.0/go.mod h1:FsONVRAS9T7sI+LIUmWTfcYkHO4aIWwzhcaSAoJOfIk=
 github.com/google/go-cmp v0.5.5/go.mod h1:v8dTdLbMG2kIc/vJvl+f65V22dbkXbowE6jgT/gNBxE=
@@ -118,8 +125,8 @@ 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 v0.0.0-20221118152302-e6195bd50e26 h1:Xim43kblpZXfIBQsbuBVKCudVG457BR2GZFIz3uw3hQ=
-github.com/google/pprof v0.0.0-20221118152302-e6195bd50e26/go.mod h1:dDKJzRmX4S37WGHujM7tX//fmj1uioxKzKxz3lo4HJo=
+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/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=
@@ -131,6 +138,10 @@ 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=
@@ -159,12 +170,17 @@ 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/compress v1.18.0 h1:c/Cqfb0r+Yi+JtIEq73FWXVkRonBlf0CRNYc8Zttxdo=
+github.com/klauspost/compress v1.18.0/go.mod h1:2Pp+KzxcywXVXMr50+X0Q/Lsb43OQHYWRCY2AiWywWQ=
 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=
@@ -193,6 +209,10 @@ 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/munnerz/goautoneg v0.0.0-20191010083416-a7dc8b61c822 h1:C3w9PqII01/Oq1c1nUAm88MOHcQC9l5mIlSMApZMrHA=
+github.com/munnerz/goautoneg v0.0.0-20191010083416-a7dc8b61c822/go.mod h1:+n7T8mK8HuQTcFwEeznm/DIxMOiR9yIdICNftLE1DvQ=
+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=
@@ -209,16 +229,29 @@ github.com/pkg/errors v0.9.1 h1:FEBLx1zS214owpjy7qsBeixbURkuhQAwrK5UwLGTwt4=
 github.com/pkg/errors v0.9.1/go.mod h1:bwawxfHBFNV+L2hUp1rHADufV3IMtnDRdf1r5NINEl0=
 github.com/pmezard/go-difflib v1.0.0 h1:4DBwDE0NGyQoBHbLQYPwSUPoCMWR5BEzIk/f1lZbAQM=
 github.com/pmezard/go-difflib v1.0.0/go.mod h1:iKH77koFhYxTK1pcRnkKkqfTogsbg7gZNVY4sRDYZ/4=
+github.com/pmezard/go-difflib v1.0.1-0.20181226105442-5d4384ee4fb2 h1:Jamvg5psRIccs7FGNTlIRMkT8wgtp5eCXdBlqhYGL6U=
+github.com/pmezard/go-difflib v1.0.1-0.20181226105442-5d4384ee4fb2/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/prometheus/client_golang v1.22.0 h1:rb93p9lokFEsctTys46VnV1kLCDpVZ0a/Y92Vm0Zc6Q=
+github.com/prometheus/client_golang v1.22.0/go.mod h1:R7ljNsLXhuQXYZYtw6GAE9AZg8Y7vEW5scdCXrWRXC0=
+github.com/prometheus/client_model v0.6.1 h1:ZKSh/rekM+n3CeS952MLRAdFwIKqeY8b62p8ais2e9E=
+github.com/prometheus/client_model v0.6.1/go.mod h1:OrxVMOVHjw3lKMa8+x6HeMGkHMQyHDk9E3jmP2AmGiY=
+github.com/prometheus/common v0.62.0 h1:xasJaQlnWAeyHdUBeGjXmutelfJHWMRr+Fg4QszZ2Io=
+github.com/prometheus/common v0.62.0/go.mod h1:vyBcEuLSvWos9B1+CyL7JZ2up+uFzXhkqml0W5zIY1I=
+github.com/prometheus/procfs v0.15.1 h1:YagwOFzUgYfKKHX6Dr+sHT7km/hxC76UB0learggepc=
+github.com/prometheus/procfs v0.15.1/go.mod h1:fB45yRUv8NstnjriLhBQLuOUt+WW4BsoGhij/e3PBqk=
 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 v1.39.0 h1:4gTz1wUhNYLhFSKl6O+8peW0v2F4BCY034GRpU9WnuA=
-github.com/samber/lo v1.39.0/go.mod h1:+m/ZKRl6ClXCE2Lgf3MsQlWfh4bn1bz6CXEOxnEXnEA=
+github.com/samber/go-singleflightx v0.3.2 h1:jXbUU0fvis8Fdv4HGONboX5WdEZcYLoBEcKiE+ITCyQ=
+github.com/samber/go-singleflightx v0.3.2/go.mod h1:X2BR+oheHIYc73PvxRMlcASg6KYYTQyUYpdVU7t/ux4=
+github.com/samber/hot v0.11.0 h1:JhV9hk8SmZIqB0To8OyCzPubvszkuoSXWx/7FCEGO+Q=
+github.com/samber/hot v0.11.0/go.mod h1:NB9v5U4NfDx7jmlrP+zHuqCuLUsywgAtCH7XOAkOxAg=
+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/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=
@@ -226,6 +259,7 @@ 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=
@@ -281,18 +315,20 @@ go.uber.org/mock v0.6.0/go.mod h1:KiVJ4BqZJaMj4svdfmHM0AUx4NJYO8ZNpPnZn1Z+BBU=
 golang.org/x/arch v0.21.0 h1:iTC9o7+wP6cPWpDWkivCvQFGAHDQ59SrSxsLPcnkArw=
 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 v0.42.0 h1:chiH31gIWm57EkTXpwnqf8qeuMUi0yekh6mT2AvFlqI=
-golang.org/x/crypto v0.42.0/go.mod h1:4+rDnOTJhQCx2q7/j6rAN5XDw8kPjeaXEUR2eL94ix8=
-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/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/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 v0.43.0 h1:lat02VYK2j4aLzMzecihNvTlJNQUq316m2Mr9rnM6YE=
-golang.org/x/net v0.43.0/go.mod h1:vhO1fvI4dGsIjh73sWfUVjj3N7CA9WkKJNQm2svM6Jg=
-golang.org/x/sync v0.17.0 h1:l60nONMj9l5drqw6jlhIELNv9I0A4OFgRsG9k2oT9Ug=
-golang.org/x/sync v0.17.0/go.mod h1:9KTHXmSnoGruLpwFjVSX0lNNA75CykiMECbovNTZqGI=
+golang.org/x/net v0.47.0 h1:Mx+4dIFzqraBXUugkia1OOvlD6LemFo1ALMHjrXDOhY=
+golang.org/x/net v0.47.0/go.mod h1:/jNxtkgq5yWUGYkaZGqo27cfGZ1c5Nen03aYrrKpVRU=
+golang.org/x/sync v0.18.0 h1:kr88TuHDroi+UVf+0hZnirlk8o8T+4MrK6mr60WkH/I=
+golang.org/x/sync v0.18.0/go.mod h1:9KTHXmSnoGruLpwFjVSX0lNNA75CykiMECbovNTZqGI=
 golang.org/x/sys v0.0.0-20190726091711-fc99dfbffb4e/go.mod h1:h1NjWce9XRLGQEsW7wpKNCjG9DtNlClVuFLEZdDNbEs=
 golang.org/x/sys v0.0.0-20190916202348-b4ddaad3f8a3/go.mod h1:h1NjWce9XRLGQEsW7wpKNCjG9DtNlClVuFLEZdDNbEs=
 golang.org/x/sys v0.0.0-20200116001909-b77594299b42/go.mod h1:h1NjWce9XRLGQEsW7wpKNCjG9DtNlClVuFLEZdDNbEs=
@@ -304,21 +340,25 @@ golang.org/x/sys v0.0.0-20210806184541-e5e7981a1069/go.mod h1:oPkhp1MJrh7nUepCBc
 golang.org/x/sys v0.6.0/go.mod h1:oPkhp1MJrh7nUepCBck5+mAzfO9JrbApNNgaTdGDITg=
 golang.org/x/sys v0.8.0/go.mod h1:oPkhp1MJrh7nUepCBck5+mAzfO9JrbApNNgaTdGDITg=
 golang.org/x/sys v0.11.0/go.mod h1:oPkhp1MJrh7nUepCBck5+mAzfO9JrbApNNgaTdGDITg=
-golang.org/x/sys v0.36.0 h1:KVRy2GtZBrk1cBYA7MKu5bEZFxQk4NIDV6RLVcC8o0k=
-golang.org/x/sys v0.36.0/go.mod h1:OgkHotnGiDImocRcuBABYBEXf8A9a87e/uXjp9XT3ks=
+golang.org/x/sys v0.38.0 h1:3yZWxaJjBmCWXqhN1qh02AkOnCQ1poK6oF+a7xWL6Gc=
+golang.org/x/sys v0.38.0/go.mod h1:OgkHotnGiDImocRcuBABYBEXf8A9a87e/uXjp9XT3ks=
 golang.org/x/term v0.0.0-20201126162022-7de9c90e9dd1/go.mod h1:bj7SfCRtBDWHUb9snDiAeCFNEtKQo2Wmx5Cou7ajbmo=
 golang.org/x/term v0.0.0-20210927222741-03fcf44c2211/go.mod h1:jbD1KX2456YbFQfuXm/mYQcufACuNUgVhRMnK/tPxf8=
 golang.org/x/text v0.3.2/go.mod h1:bEr9sfX3Q8Zfm5fL9x+3itogRgK3+ptLWKqgva+5dAk=
 golang.org/x/text v0.3.3/go.mod h1:5Zoc/QRtKVWzQhOtBMvqHzDpF6irO9z98xDceosuGiQ=
 golang.org/x/text v0.3.6/go.mod h1:5Zoc/QRtKVWzQhOtBMvqHzDpF6irO9z98xDceosuGiQ=
-golang.org/x/text v0.29.0 h1:1neNs90w9YzJ9BocxfsQNHKuAT4pkghyXc4nhZ6sJvk=
-golang.org/x/text v0.29.0/go.mod h1:7MhJOA9CD2qZyOKYazxdYMF85OwPdEr9jTtBpO7ydH4=
+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=
 google.golang.org/protobuf v1.34.2 h1:6xV6lTsCfpGD21XK49h7MhtcApnLqkfYgPcdHftf6hg=
 google.golang.org/protobuf v1.34.2/go.mod h1:qYOHts0dSfpeUzUFpOMr/WGzszTmLH+DiWniOlNbLDw=
+google.golang.org/protobuf v1.36.5 h1:tPhr+woSbjfYvY6/GPufUoYizxw1cF/yFoxJ2fmpwlM=
+google.golang.org/protobuf v1.36.5/go.mod h1:9fA7Ob0pmnwhb644+1+CVWFRbNajQ6iRojtC/QF5bRE=
 gopkg.in/check.v1 v0.0.0-20161208181325-20d25e280405/go.mod h1:Co6ibVJAznAaIkqp8huTwlJQCZ016jof/cbN4VW5Yz0=
 gopkg.in/check.v1 v1.0.0-20180628173108-788fd7840127/go.mod h1:Co6ibVJAznAaIkqp8huTwlJQCZ016jof/cbN4VW5Yz0=
 gopkg.in/check.v1 v1.0.0-20201130134442-10cb98267c6c h1:Hei/4ADfdWqJk1ZMxUNpqntNwaWcugrBjAiHlqqRiVk=
@@ -343,11 +383,29 @@ 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/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=
+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=

logger/logger.go

@@ -67,8 +67,10 @@ func LogError(ctx context.Context, msg string) {
 }
 
 func LogDebug(ctx context.Context, msg string, args ...any) {
-	msg = fmt.Sprintf(msg, args...)
 	if common.DebugEnabled {
+		if len(args) > 0 {
+			msg = fmt.Sprintf(msg, args...)
+		}
 		logHelper(ctx, loggerDebug, msg)
 	}
 }

main.go

@@ -20,6 +20,7 @@ import (
 	"github.com/QuantumNous/new-api/router"
 	"github.com/QuantumNous/new-api/service"
 	"github.com/QuantumNous/new-api/setting/ratio_setting"
+	_ "github.com/QuantumNous/new-api/setting/performance_setting" // 注册性能设置
 
 	"github.com/bytedance/gopkg/util/gopool"
 	"github.com/gin-contrib/sessions"
@@ -102,6 +103,9 @@ func main() {
 
 	go controller.AutomaticallyTestChannels()
 
+	// Codex credential auto-refresh check every 10 minutes, refresh when expires within 1 day
+	service.StartCodexCredentialAutoRefreshTask()
+
 	if common.IsMasterNode && constant.UpdateTask {
 		gopool.Go(func() {
 			controller.UpdateMidjourneyTaskBulk()
@@ -124,6 +128,11 @@ 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) {
@@ -138,6 +147,7 @@ func main() {
 	// This will cause SSE not to work!!!
 	//server.Use(gzip.Gzip(gzip.DefaultCompression))
 	server.Use(middleware.RequestId())
+	server.Use(middleware.PoweredBy())
 	middleware.SetUpLogger(server)
 	// Initialize session store
 	store := cookie.NewStore([]byte(common.SessionSecret))
@@ -183,6 +193,7 @@ func InjectUmamiAnalytics() {
 		analyticsInjectBuilder.WriteString(umamiSiteID)
 		analyticsInjectBuilder.WriteString("\"></script>")
 	}
+	analyticsInjectBuilder.WriteString("<!--Umami QuantumNous-->\n")
 	analyticsInject := analyticsInjectBuilder.String()
 	indexPage = bytes.ReplaceAll(indexPage, []byte("<!--umami-->\n"), []byte(analyticsInject))
 }
@@ -204,6 +215,7 @@ func InjectGoogleAnalytics() {
 		analyticsInjectBuilder.WriteString("');")
 		analyticsInjectBuilder.WriteString("</script>")
 	}
+	analyticsInjectBuilder.WriteString("<!--Google Analytics QuantumNous-->\n")
 	analyticsInject := analyticsInjectBuilder.String()
 	indexPage = bytes.ReplaceAll(indexPage, []byte("<!--Google Analytics-->\n"), []byte(analyticsInject))
 }
@@ -242,6 +254,9 @@ func InitResources() error {
 	// Initialize options, should after model.InitDB()
 	model.InitOptionMap()
 
+	// 清理旧的磁盘缓存文件
+	common.CleanupOldCacheFiles()
+
 	// 初始化模型
 	model.GetPricing()
 

middleware/auth.go

@@ -2,15 +2,18 @@ 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"
+	"github.com/QuantumNous/new-api/types"
 
 	"github.com/gin-contrib/sessions"
 	"github.com/gin-gonic/gin"
@@ -193,8 +196,8 @@ func TokenAuth() func(c *gin.Context) {
 			}
 			c.Request.Header.Set("Authorization", "Bearer "+key)
 		}
-		// 检查path包含/v1/messages
-		if strings.Contains(c.Request.URL.Path, "/v1/messages") {
+		// 检查path包含/v1/messages 或 /v1/models
+		if strings.Contains(c.Request.URL.Path, "/v1/messages") || strings.Contains(c.Request.URL.Path, "/v1/models") {
 			anthropicKey := c.Request.Header.Get("x-api-key")
 			if anthropicKey != "" {
 				c.Request.Header.Set("Authorization", "Bearer "+anthropicKey)
@@ -216,10 +219,14 @@ func TokenAuth() func(c *gin.Context) {
 		}
 		key := c.Request.Header.Get("Authorization")
 		parts := make([]string, 0)
-		key = strings.TrimPrefix(key, "Bearer ")
+		if strings.HasPrefix(key, "Bearer ") || strings.HasPrefix(key, "bearer ") {
+			key = strings.TrimSpace(key[7:])
+		}
 		if key == "" || key == "midjourney-proxy" {
 			key = c.Request.Header.Get("mj-api-secret")
-			key = strings.TrimPrefix(key, "Bearer ")
+			if strings.HasPrefix(key, "Bearer ") || strings.HasPrefix(key, "bearer ") {
+				key = strings.TrimSpace(key[7:])
+			}
 			key = strings.TrimPrefix(key, "sk-")
 			parts = strings.Split(key, "-")
 			key = parts[0]
@@ -240,13 +247,20 @@ func TokenAuth() func(c *gin.Context) {
 			return
 		}
 
-		allowIpsMap := token.GetIpLimitsMap()
-		if len(allowIpsMap) != 0 {
+		allowIps := token.GetIpLimits()
+		if len(allowIps) > 0 {
 			clientIp := c.ClientIP()
-			if _, ok := allowIpsMap[clientIp]; !ok {
-				abortWithOpenAiMessage(c, http.StatusForbidden, "您的 IP 不在令牌允许访问的列表中")
+			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 {
+				abortWithOpenAiMessage(c, http.StatusForbidden, "您的 IP 不在令牌允许访问的列表中", types.ErrorCodeAccessDenied)
+				return
+			}
+			logger.LogDebug(c, "Client IP %s passed the token IP restrictions check", clientIp)
 		}
 
 		userCache, err := model.GetUserCache(token.UserId)
@@ -307,7 +321,8 @@ func SetupContextForToken(c *gin.Context, token *model.Token, parts ...string) e
 	} else {
 		c.Set("token_model_limit_enabled", false)
 	}
-	c.Set("token_group", token.Group)
+	common.SetContextKey(c, constant.ContextKeyTokenGroup, token.Group)
+	common.SetContextKey(c, constant.ContextKeyTokenCrossGroupRetry, token.CrossGroupRetry)
 	if len(parts) > 1 {
 		if model.IsAdmin(token.UserId) {
 			c.Set("specific_channel_id", parts[1])

middleware/body_cleanup.go

@@ -0,0 +1,18 @@
+package middleware
+
+import (
+	"github.com/QuantumNous/new-api/common"
+	"github.com/gin-gonic/gin"
+)
+
+// BodyStorageCleanup 请求体存储清理中间件
+// 在请求处理完成后自动清理磁盘/内存缓存
+func BodyStorageCleanup() gin.HandlerFunc {
+	return func(c *gin.Context) {
+		// 处理请求
+		c.Next()
+
+		// 请求结束后清理存储
+		common.CleanupBodyStorage(c)
+	}
+}

middleware/cors.go

@@ -1,6 +1,7 @@
 package middleware
 
 import (
+	"github.com/QuantumNous/new-api/common"
 	"github.com/gin-contrib/cors"
 	"github.com/gin-gonic/gin"
 )
@@ -13,3 +14,10 @@ func CORS() gin.HandlerFunc {
 	config.AllowHeaders = []string{"*"}
 	return cors.New(config)
 }
+
+func PoweredBy() gin.HandlerFunc {
+	return func(c *gin.Context) {
+		c.Header("X-New-Api-Version", common.Version)
+		c.Next()
+	}
+}

middleware/distributor.go

@@ -97,30 +97,64 @@ func Distribute() func(c *gin.Context) {
 						common.SetContextKey(c, constant.ContextKeyUsingGroup, usingGroup)
 					}
 				}
-				channel, selectGroup, err = service.CacheGetRandomSatisfiedChannel(c, usingGroup, modelRequest.Model, 0)
-				if err != nil {
-					showGroup := usingGroup
-					if usingGroup == "auto" {
-						showGroup = fmt.Sprintf("auto(%s)", selectGroup)
+
+				if preferredChannelID, found := service.GetPreferredChannelByAffinity(c, modelRequest.Model, usingGroup); found {
+					preferred, err := model.CacheGetChannel(preferredChannelID)
+					if err == nil && preferred != nil && preferred.Status == common.ChannelStatusEnabled {
+						if usingGroup == "auto" {
+							userGroup := common.GetContextKeyString(c, constant.ContextKeyUserGroup)
+							autoGroups := service.GetUserAutoGroup(userGroup)
+							for _, g := range autoGroups {
+								if model.IsChannelEnabledForGroupModel(g, modelRequest.Model, preferred.Id) {
+									selectGroup = g
+									common.SetContextKey(c, constant.ContextKeyAutoGroup, g)
+									channel = preferred
+									service.MarkChannelAffinityUsed(c, g, preferred.Id)
+									break
+								}
+							}
+						} else if model.IsChannelEnabledForGroupModel(usingGroup, modelRequest.Model, preferred.Id) {
+							channel = preferred
+							selectGroup = usingGroup
+							service.MarkChannelAffinityUsed(c, usingGroup, preferred.Id)
+						}
 					}
-					message := fmt.Sprintf("获取分组 %s 下模型 %s 的可用渠道失败（distributor）: %s", showGroup, modelRequest.Model, err.Error())
-					// 如果错误，但是渠道不为空，说明是数据库一致性问题
-					//if channel != nil {
-					//	common.SysError(fmt.Sprintf("渠道不存在：%d", channel.Id))
-					//	message = "数据库一致性已被破坏，请联系管理员"
-					//}
-					abortWithOpenAiMessage(c, http.StatusServiceUnavailable, message, string(types.ErrorCodeModelNotFound))
-					return
 				}
+
 				if channel == nil {
-					abortWithOpenAiMessage(c, http.StatusServiceUnavailable, fmt.Sprintf("分组 %s 下模型 %s 无可用渠道（distributor）", usingGroup, modelRequest.Model), string(types.ErrorCodeModelNotFound))
-					return
+					channel, selectGroup, err = service.CacheGetRandomSatisfiedChannel(&service.RetryParam{
+						Ctx:        c,
+						ModelName:  modelRequest.Model,
+						TokenGroup: usingGroup,
+						Retry:      common.GetPointer(0),
+					})
+					if err != nil {
+						showGroup := usingGroup
+						if usingGroup == "auto" {
+							showGroup = fmt.Sprintf("auto(%s)", selectGroup)
+						}
+						message := fmt.Sprintf("获取分组 %s 下模型 %s 的可用渠道失败（distributor）: %s", showGroup, modelRequest.Model, err.Error())
+						// 如果错误，但是渠道不为空，说明是数据库一致性问题
+						//if channel != nil {
+						//	common.SysError(fmt.Sprintf("渠道不存在：%d", channel.Id))
+						//	message = "数据库一致性已被破坏，请联系管理员"
+						//}
+						abortWithOpenAiMessage(c, http.StatusServiceUnavailable, message, types.ErrorCodeModelNotFound)
+						return
+					}
+					if channel == nil {
+						abortWithOpenAiMessage(c, http.StatusServiceUnavailable, fmt.Sprintf("分组 %s 下模型 %s 无可用渠道（distributor）", usingGroup, modelRequest.Model), types.ErrorCodeModelNotFound)
+						return
+					}
 				}
 			}
 		}
 		common.SetContextKey(c, constant.ContextKeyRequestStartTime, time.Now())
 		SetupContextForSelectedChannel(c, channel, modelRequest.Model)
 		c.Next()
+		if channel != nil && c.Writer != nil && c.Writer.Status() < http.StatusBadRequest {
+			service.RecordChannelAffinity(c, channel.Id)
+		}
 	}
 }
 
@@ -157,7 +191,7 @@ func getModelRequest(c *gin.Context) (*ModelRequest, bool, error) {
 			}
 			midjourneyModel, mjErr, success := service.GetMjRequestModel(relayMode, &midjourneyRequest)
 			if mjErr != nil {
-				return nil, false, fmt.Errorf(mjErr.Description)
+				return nil, false, fmt.Errorf("%s", mjErr.Description)
 			}
 			if midjourneyModel == "" {
 				if !success {
@@ -181,6 +215,10 @@ 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" \
@@ -291,6 +329,10 @@ func getModelRequest(c *gin.Context) (*ModelRequest, bool, error) {
 		modelRequest.Group = req.Group
 		common.SetContextKey(c, constant.ContextKeyTokenGroup, modelRequest.Group)
 	}
+
+	if strings.HasPrefix(c.Request.URL.Path, "/v1/responses/compact") && modelRequest.Model != "" {
+		modelRequest.Model = ratio_setting.WithCompactModelSuffix(modelRequest.Model)
+	}
 	return &modelRequest, shouldSelectChannel, nil
 }
 

middleware/gzip.go

@@ -5,32 +5,69 @@ 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(c.Request.Body)
+			gzipReader, err := gzip.NewReader(origBody)
 			if err != nil {
+				_ = origBody.Close()
 				c.AbortWithStatus(http.StatusBadRequest)
 				return
 			}
-			defer gzipReader.Close()
-
-			// Replace the request body with the decompressed data
-			c.Request.Body = io.NopCloser(gzipReader)
+			// 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()
+				},
+			})
 			c.Request.Header.Del("Content-Encoding")
 		case "br":
-			reader := brotli.NewReader(c.Request.Body)
-			c.Request.Body = io.NopCloser(reader)
+			reader := brotli.NewReader(origBody)
+			c.Request.Body = wrapMaxBytes(&readCloser{
+				Reader: reader,
+				closeFn: func() error {
+					return origBody.Close()
+				},
+			})
 			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

middleware/rate-limit.go

@@ -102,7 +102,10 @@ func GlobalAPIRateLimit() func(c *gin.Context) {
 }
 
 func CriticalRateLimit() func(c *gin.Context) {
-	return rateLimitFactory(common.CriticalRateLimitNum, common.CriticalRateLimitDuration, "CT")
+	if common.CriticalRateLimitEnable {
+		return rateLimitFactory(common.CriticalRateLimitNum, common.CriticalRateLimitDuration, "CT")
+	}
+	return defNext
 }
 
 func DownloadRateLimit() func(c *gin.Context) {

middleware/utils.go

@@ -5,13 +5,14 @@ import (
 
 	"github.com/QuantumNous/new-api/common"
 	"github.com/QuantumNous/new-api/logger"
+	"github.com/QuantumNous/new-api/types"
 	"github.com/gin-gonic/gin"
 )
 
-func abortWithOpenAiMessage(c *gin.Context, statusCode int, message string, code ...string) {
+func abortWithOpenAiMessage(c *gin.Context, statusCode int, message string, code ...types.ErrorCode) {
 	codeStr := ""
 	if len(code) > 0 {
-		codeStr = code[0]
+		codeStr = string(code[0])
 	}
 	userId := c.GetInt("id")
 	c.JSON(statusCode, gin.H{

model/channel.go

@@ -138,9 +138,11 @@ func (channel *Channel) GetNextEnabledKey() (string, int, *types.NewAPIError) {
 			enabledIdx = append(enabledIdx, i)
 		}
 	}
-	// If no specific status list or none enabled, fall back to first key
+	// If no specific status list or none enabled, return an explicit error so caller can
+	// properly handle a channel with no available keys (e.g. mark channel disabled).
+	// Returning the first key here caused requests to keep using an already-disabled key.
 	if len(enabledIdx) == 0 {
-		return keys[0], 0, nil
+		return "", 0, types.NewError(errors.New("no enabled keys"), types.ErrorCodeChannelNoAvailableKey)
 	}
 
 	switch channel.ChannelInfo.MultiKeyMode {
@@ -252,6 +254,9 @@ 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
 }
 
@@ -270,13 +275,17 @@ func GetAllChannels(startIdx int, num int, selectAll bool, idSort bool) ([]*Chan
 	return channels, err
 }
 
-func GetChannelsByTag(tag string, idSort bool) ([]*Channel, error) {
+func GetChannelsByTag(tag string, idSort bool, selectAll bool) ([]*Channel, error) {
 	var channels []*Channel
 	order := "priority desc"
 	if idSort {
 		order = "id desc"
 	}
-	err := DB.Where("tag = ?", tag).Order(order).Find(&channels).Error
+	query := DB.Where("tag = ?", tag).Order(order)
+	if !selectAll {
+		query = query.Omit("key")
+	}
+	err := query.Find(&channels).Error
 	return channels, err
 }
 
@@ -688,7 +697,7 @@ func DisableChannelByTag(tag string) error {
 	return err
 }
 
-func EditChannelByTag(tag string, newTag *string, modelMapping *string, models *string, group *string, priority *int64, weight *uint) error {
+func EditChannelByTag(tag string, newTag *string, modelMapping *string, models *string, group *string, priority *int64, weight *uint, paramOverride *string, headerOverride *string) error {
 	updateData := Channel{}
 	shouldReCreateAbilities := false
 	updatedTag := tag
@@ -714,13 +723,19 @@ func EditChannelByTag(tag string, newTag *string, modelMapping *string, models *
 	if weight != nil {
 		updateData.Weight = weight
 	}
+	if paramOverride != nil {
+		updateData.ParamOverride = paramOverride
+	}
+	if headerOverride != nil {
+		updateData.HeaderOverride = headerOverride
+	}
 
 	err := DB.Model(&Channel{}).Where("tag = ?", tag).Updates(updateData).Error
 	if err != nil {
 		return err
 	}
 	if shouldReCreateAbilities {
-		channels, err := GetChannelsByTag(updatedTag, false)
+		channels, err := GetChannelsByTag(updatedTag, false, false)
 		if err == nil {
 			for _, channel := range channels {
 				err = channel.UpdateAbilities(nil)

model/channel_satisfy.go

@@ -0,0 +1,71 @@
+package model
+
+import (
+	"github.com/QuantumNous/new-api/common"
+	"github.com/QuantumNous/new-api/setting/ratio_setting"
+)
+
+func IsChannelEnabledForGroupModel(group string, modelName string, channelID int) bool {
+	if group == "" || modelName == "" || channelID <= 0 {
+		return false
+	}
+	if !common.MemoryCacheEnabled {
+		return isChannelEnabledForGroupModelDB(group, modelName, channelID)
+	}
+
+	channelSyncLock.RLock()
+	defer channelSyncLock.RUnlock()
+
+	if group2model2channels == nil {
+		return false
+	}
+
+	if isChannelIDInList(group2model2channels[group][modelName], channelID) {
+		return true
+	}
+	normalized := ratio_setting.FormatMatchingModelName(modelName)
+	if normalized != "" && normalized != modelName {
+		return isChannelIDInList(group2model2channels[group][normalized], channelID)
+	}
+	return false
+}
+
+func IsChannelEnabledForAnyGroupModel(groups []string, modelName string, channelID int) bool {
+	if len(groups) == 0 {
+		return false
+	}
+	for _, g := range groups {
+		if IsChannelEnabledForGroupModel(g, modelName, channelID) {
+			return true
+		}
+	}
+	return false
+}
+
+func isChannelEnabledForGroupModelDB(group string, modelName string, channelID int) bool {
+	var count int64
+	err := DB.Model(&Ability{}).
+		Where(commonGroupCol+" = ? and model = ? and channel_id = ? and enabled = ?", group, modelName, channelID, true).
+		Count(&count).Error
+	if err == nil && count > 0 {
+		return true
+	}
+	normalized := ratio_setting.FormatMatchingModelName(modelName)
+	if normalized == "" || normalized == modelName {
+		return false
+	}
+	count = 0
+	err = DB.Model(&Ability{}).
+		Where(commonGroupCol+" = ? and model = ? and channel_id = ? and enabled = ?", group, normalized, channelID, true).
+		Count(&count).Error
+	return err == nil && count > 0
+}
+
+func isChannelIDInList(list []int, channelID int) bool {
+	for _, id := range list {
+		if id == channelID {
+			return true
+		}
+	}
+	return false
+}

model/checkin.go

@@ -0,0 +1,179 @@
+package model
+
+import (
+	"errors"
+	"math/rand"
+	"time"
+
+	"github.com/QuantumNous/new-api/common"
+	"github.com/QuantumNous/new-api/setting/operation_setting"
+	"gorm.io/gorm"
+)
+
+// Checkin 签到记录
+type Checkin struct {
+	Id           int    `json:"id" gorm:"primaryKey;autoIncrement"`
+	UserId       int    `json:"user_id" gorm:"not null;uniqueIndex:idx_user_checkin_date"`
+	CheckinDate  string `json:"checkin_date" gorm:"type:varchar(10);not null;uniqueIndex:idx_user_checkin_date"` // 格式: YYYY-MM-DD
+	QuotaAwarded int    `json:"quota_awarded" gorm:"not null"`
+	CreatedAt    int64  `json:"created_at" gorm:"bigint"`
+}
+
+// CheckinRecord 用于API返回的签到记录（不包含敏感字段）
+type CheckinRecord struct {
+	CheckinDate  string `json:"checkin_date"`
+	QuotaAwarded int    `json:"quota_awarded"`
+}
+
+func (Checkin) TableName() string {
+	return "checkins"
+}
+
+// GetUserCheckinRecords 获取用户在指定日期范围内的签到记录
+func GetUserCheckinRecords(userId int, startDate, endDate string) ([]Checkin, error) {
+	var records []Checkin
+	err := DB.Where("user_id = ? AND checkin_date >= ? AND checkin_date <= ?",
+		userId, startDate, endDate).
+		Order("checkin_date DESC").
+		Find(&records).Error
+	return records, err
+}
+
+// HasCheckedInToday 检查用户今天是否已签到
+func HasCheckedInToday(userId int) (bool, error) {
+	today := time.Now().Format("2006-01-02")
+	var count int64
+	err := DB.Model(&Checkin{}).
+		Where("user_id = ? AND checkin_date = ?", userId, today).
+		Count(&count).Error
+	return count > 0, err
+}
+
+// UserCheckin 执行用户签到
+// MySQL 和 PostgreSQL 使用事务保证原子性
+// SQLite 不支持嵌套事务，使用顺序操作 + 手动回滚
+func UserCheckin(userId int) (*Checkin, error) {
+	setting := operation_setting.GetCheckinSetting()
+	if !setting.Enabled {
+		return nil, errors.New("签到功能未启用")
+	}
+
+	// 检查今天是否已签到
+	hasChecked, err := HasCheckedInToday(userId)
+	if err != nil {
+		return nil, err
+	}
+	if hasChecked {
+		return nil, errors.New("今日已签到")
+	}
+
+	// 计算随机额度奖励
+	quotaAwarded := setting.MinQuota
+	if setting.MaxQuota > setting.MinQuota {
+		quotaAwarded = setting.MinQuota + rand.Intn(setting.MaxQuota-setting.MinQuota+1)
+	}
+
+	today := time.Now().Format("2006-01-02")
+	checkin := &Checkin{
+		UserId:       userId,
+		CheckinDate:  today,
+		QuotaAwarded: quotaAwarded,
+		CreatedAt:    time.Now().Unix(),
+	}
+
+	// 根据数据库类型选择不同的策略
+	if common.UsingSQLite {
+		// SQLite 不支持嵌套事务，使用顺序操作 + 手动回滚
+		return userCheckinWithoutTransaction(checkin, userId, quotaAwarded)
+	}
+
+	// MySQL 和 PostgreSQL 支持事务，使用事务保证原子性
+	return userCheckinWithTransaction(checkin, userId, quotaAwarded)
+}
+
+// userCheckinWithTransaction 使用事务执行签到（适用于 MySQL 和 PostgreSQL）
+func userCheckinWithTransaction(checkin *Checkin, userId int, quotaAwarded int) (*Checkin, error) {
+	err := DB.Transaction(func(tx *gorm.DB) error {
+		// 步骤1: 创建签到记录
+		// 数据库有唯一约束 (user_id, checkin_date)，可以防止并发重复签到
+		if err := tx.Create(checkin).Error; err != nil {
+			return errors.New("签到失败，请稍后重试")
+		}
+
+		// 步骤2: 在事务中增加用户额度
+		if err := tx.Model(&User{}).Where("id = ?", userId).
+			Update("quota", gorm.Expr("quota + ?", quotaAwarded)).Error; err != nil {
+			return errors.New("签到失败：更新额度出错")
+		}
+
+		return nil
+	})
+
+	if err != nil {
+		return nil, err
+	}
+
+	// 事务成功后，异步更新缓存
+	go func() {
+		_ = cacheIncrUserQuota(userId, int64(quotaAwarded))
+	}()
+
+	return checkin, nil
+}
+
+// userCheckinWithoutTransaction 不使用事务执行签到（适用于 SQLite）
+func userCheckinWithoutTransaction(checkin *Checkin, userId int, quotaAwarded int) (*Checkin, error) {
+	// 步骤1: 创建签到记录
+	// 数据库有唯一约束 (user_id, checkin_date)，可以防止并发重复签到
+	if err := DB.Create(checkin).Error; err != nil {
+		return nil, errors.New("签到失败，请稍后重试")
+	}
+
+	// 步骤2: 增加用户额度
+	// 使用 db=true 强制直接写入数据库，不使用批量更新
+	if err := IncreaseUserQuota(userId, quotaAwarded, true); err != nil {
+		// 如果增加额度失败，需要回滚签到记录
+		DB.Delete(checkin)
+		return nil, errors.New("签到失败：更新额度出错")
+	}
+
+	return checkin, nil
+}
+
+// GetUserCheckinStats 获取用户签到统计信息
+func GetUserCheckinStats(userId int, month string) (map[string]interface{}, error) {
+	// 获取指定月份的所有签到记录
+	startDate := month + "-01"
+	endDate := month + "-31"
+
+	records, err := GetUserCheckinRecords(userId, startDate, endDate)
+	if err != nil {
+		return nil, err
+	}
+
+	// 转换为不包含敏感字段的记录
+	checkinRecords := make([]CheckinRecord, len(records))
+	for i, r := range records {
+		checkinRecords[i] = CheckinRecord{
+			CheckinDate:  r.CheckinDate,
+			QuotaAwarded: r.QuotaAwarded,
+		}
+	}
+
+	// 检查今天是否已签到
+	hasCheckedToday, _ := HasCheckedInToday(userId)
+
+	// 获取用户所有时间的签到统计
+	var totalCheckins int64
+	var totalQuota int64
+	DB.Model(&Checkin{}).Where("user_id = ?", userId).Count(&totalCheckins)
+	DB.Model(&Checkin{}).Where("user_id = ?", userId).Select("COALESCE(SUM(quota_awarded), 0)").Scan(&totalQuota)
+
+	return map[string]interface{}{
+		"total_quota":      totalQuota,      // 所有时间累计获得的额度
+		"total_checkins":   totalCheckins,   // 所有时间累计签到次数
+		"checkin_count":    len(records),    // 本月签到次数
+		"checked_in_today": hasCheckedToday, // 今天是否已签到
+		"records":          checkinRecords,  // 本月签到记录详情（不含id和user_id）
+	}, nil
+}

model/log.go

@@ -56,8 +56,10 @@ func formatUserLogs(logs []*Log) {
 		var otherMap map[string]interface{}
 		otherMap, _ = common.StrToMap(logs[i].Other)
 		if otherMap != nil {
-			// delete admin
+			// Remove admin-only debug fields.
 			delete(otherMap, "admin_info")
+			delete(otherMap, "request_conversion")
+			delete(otherMap, "reject_reason")
 		}
 		logs[i].Other = common.MapToJsonStr(otherMap)
 		logs[i].Id = logs[i].Id % 1024

model/main.go

@@ -267,6 +267,7 @@ func migrateDB() error {
 		&Setup{},
 		&TwoFA{},
 		&TwoFABackupCode{},
+		&Checkin{},
 	)
 	if err != nil {
 		return err
@@ -300,6 +301,7 @@ func migrateDBFast() error {
 		{&Setup{}, "Setup"},
 		{&TwoFA{}, "TwoFA"},
 		{&TwoFABackupCode{}, "TwoFABackupCode"},
+		{&Checkin{}, "Checkin"},
 	}
 	// 动态计算migration数量，确保errChan缓冲区足够大
 	errChan := make(chan error, len(migrations))

model/option.go

@@ -9,6 +9,7 @@ import (
 	"github.com/QuantumNous/new-api/setting"
 	"github.com/QuantumNous/new-api/setting/config"
 	"github.com/QuantumNous/new-api/setting/operation_setting"
+	"github.com/QuantumNous/new-api/setting/performance_setting"
 	"github.com/QuantumNous/new-api/setting/ratio_setting"
 	"github.com/QuantumNous/new-api/setting/system_setting"
 )
@@ -143,6 +144,8 @@ func InitOptionMap() {
 	common.OptionMap["SensitiveWords"] = setting.SensitiveWordsToString()
 	common.OptionMap["StreamCacheQueueLength"] = strconv.Itoa(setting.StreamCacheQueueLength)
 	common.OptionMap["AutomaticDisableKeywords"] = operation_setting.AutomaticDisableKeywordsToString()
+	common.OptionMap["AutomaticDisableStatusCodes"] = operation_setting.AutomaticDisableStatusCodesToString()
+	common.OptionMap["AutomaticRetryStatusCodes"] = operation_setting.AutomaticRetryStatusCodesToString()
 	common.OptionMap["ExposeRatioEnabled"] = strconv.FormatBool(ratio_setting.IsExposeRatioEnabled())
 
 	// 自动添加所有注册的模型配置
@@ -444,6 +447,10 @@ func updateOptionMap(key string, value string) (err error) {
 		setting.SensitiveWordsFromString(value)
 	case "AutomaticDisableKeywords":
 		operation_setting.AutomaticDisableKeywordsFromString(value)
+	case "AutomaticDisableStatusCodes":
+		err = operation_setting.AutomaticDisableStatusCodesFromString(value)
+	case "AutomaticRetryStatusCodes":
+		err = operation_setting.AutomaticRetryStatusCodesFromString(value)
 	case "StreamCacheQueueLength":
 		setting.StreamCacheQueueLength, _ = strconv.Atoi(value)
 	case "PayMethods":
@@ -474,5 +481,11 @@ func handleConfigUpdate(key, value string) bool {
 	}
 	config.UpdateConfigFromMap(cfg, configMap)
 
+	// 特定配置的后处理
+	if configName == "performance_setting" {
+		// 同步磁盘缓存配置到 common 包
+		performance_setting.UpdateAndSync()
+	}
+
 	return true // 已处理
 }