Merge branch 'sub' into feature/subscription

Return subscription epay pay success responses via ApiSuccess to include the consistent success field and align with error schema.

.dockerignore

@@ -5,4 +5,6 @@
 .gitignore
 Makefile
 docs
-.eslintcache
+.eslintcache
+.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
 
@@ -56,8 +67,6 @@
 # SESSION_SECRET=random_string
 
 # 其他配置
-# 渠道测试频率（单位：秒）
-# CHANNEL_TEST_FREQUENCY=10
 # 生成默认token
 # GENERATE_DEFAULT_TOKEN=false
 # Cohere 安全设置
@@ -65,11 +74,19 @@
 # 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
 # NODE_TYPE=master
+
+# 可信任重定向域名列表（逗号分隔，支持子域名匹配）
+# 用于验证支付成功/取消回调URL的域名安全性
+# 示例: example.com,myapp.io 将允许 example.com, sub.example.com, myapp.io 等
+# TRUSTED_REDIRECT_DOMAINS=example.com,myapp.io

.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/ISSUE_TEMPLATE/bug_report_en.md

@@ -0,0 +1,26 @@
+---
+name: Bug Report
+about: Describe the issue you encountered with clear and detailed language
+title: ''
+labels: bug
+assignees: ''
+
+---
+
+**Routine Checks**
+
+[//]: # (Remove the space in the box and fill with an x)
++ [ ] I have confirmed there are no similar issues currently
++ [ ] I have confirmed I have upgraded to the latest version
++ [ ] I have thoroughly read the project README, especially the FAQ section
++ [ ] I understand and am willing to follow up on this issue, assist with testing and provide feedback 
++ [ ] I understand and acknowledge the above, and understand that project maintainers have limited time and energy, **issues that do not follow the rules may be ignored or closed directly**
+
+**Issue Description**
+
+**Steps to Reproduce**
+
+**Expected Result**
+
+**Related Screenshots**
+If none, please delete this section.

.github/ISSUE_TEMPLATE/feature_request_en.md

@@ -0,0 +1,22 @@
+---
+name: Feature Request
+about: Describe the new feature you would like to add with clear and detailed language
+title: ''
+labels: enhancement
+assignees: ''
+
+---
+
+**Routine Checks**
+
+[//]: # (Remove the space in the box and fill with an x)
++ [ ] I have confirmed there are no similar issues currently
++ [ ] I have confirmed I have upgraded to the latest version
++ [ ] I have thoroughly read the project README and confirmed the current version cannot meet my needs
++ [ ] I understand and am willing to follow up on this issue, assist with testing and provide feedback
++ [ ] I understand and acknowledge the above, and understand that project maintainers have limited time and energy, **issues that do not follow the rules may be ignored or closed directly**
+
+**Feature Description**
+
+**Use Case**
+

.github/PULL_REQUEST_TEMPLATE/pull_request_template.md

@@ -13,7 +13,3 @@
 ### PR 描述
 
 **请在下方详细描述您的 PR，包括目的、实现细节等。**
-
-### **重要提示**
-
-**所有 PR 都必须提交到 `alpha` 分支。请确保您的 PR 目标分支是 `alpha`。**

.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/docker-image-alpha.yml

@@ -11,19 +11,42 @@ on:
         required: false
 
 jobs:
-  push_to_registries:
-    name: Push Docker image to multiple registries
-    runs-on: ubuntu-latest
+  build_single_arch:
+    name: Build & push (${{ matrix.arch }}) [native]
+    strategy:
+      fail-fast: false
+      matrix:
+        include:
+          - arch: amd64
+            platform: linux/amd64
+            runner: ubuntu-latest
+          - arch: arm64
+            platform: linux/arm64
+            runner: ubuntu-24.04-arm
+    runs-on: ${{ matrix.runner }}
     permissions:
       packages: write
       contents: read
     steps:
-      - name: Check out the repo
+      - name: Check out (shallow)
         uses: actions/checkout@v4
+        with:
+          fetch-depth: 1
 
-      - name: Save version info
+      - name: Determine alpha version
+        id: version
         run: |
-          echo "alpha-$(date +'%Y%m%d')-$(git rev-parse --short HEAD)" > VERSION
+          VERSION="alpha-$(date +'%Y%m%d')-$(git rev-parse --short HEAD)"
+          echo "$VERSION" > VERSION
+          echo "value=$VERSION" >> $GITHUB_OUTPUT
+          echo "VERSION=$VERSION" >> $GITHUB_ENV
+          echo "Publishing version: $VERSION for ${{ matrix.arch }}"
+
+      - name: Normalize GHCR repository
+        run: echo "GHCR_REPOSITORY=${GITHUB_REPOSITORY,,}" >> $GITHUB_ENV
+
+      - name: Set up Docker Buildx
+        uses: docker/setup-buildx-action@v3
 
       - name: Log in to Docker Hub
         uses: docker/login-action@v3
@@ -31,32 +54,98 @@ jobs:
           username: ${{ secrets.DOCKERHUB_USERNAME }}
           password: ${{ secrets.DOCKERHUB_TOKEN }}
 
-      - name: Log in to the Container registry
+      - name: Log in to GHCR
         uses: docker/login-action@v3
         with:
           registry: ghcr.io
           username: ${{ github.actor }}
           password: ${{ secrets.GITHUB_TOKEN }}
 
-      - name: Set up Docker Buildx
-        uses: docker/setup-buildx-action@v3
-
-      - name: Extract metadata (tags, labels) for Docker
+      - name: Extract metadata (labels)
         id: meta
         uses: docker/metadata-action@v5
         with:
           images: |
             calciumion/new-api
-            ghcr.io/${{ github.repository }}
-          tags: |
-            type=raw,value=alpha
-            type=raw,value=alpha-{{date 'YYYYMMDD'}}-{{sha}}
+            ghcr.io/${{ env.GHCR_REPOSITORY }}
 
-      - name: Build and push Docker images
-        uses: docker/build-push-action@v5
+      - name: Build & push single-arch (to both registries)
+        uses: docker/build-push-action@v6
         with:
           context: .
-          platforms: linux/amd64,linux/arm64
+          platforms: ${{ matrix.platform }}
           push: true
-          tags: ${{ steps.meta.outputs.tags }}
+          tags: |
+            calciumion/new-api:alpha-${{ matrix.arch }}
+            calciumion/new-api:${{ steps.version.outputs.value }}-${{ matrix.arch }}
+            ghcr.io/${{ env.GHCR_REPOSITORY }}:alpha-${{ matrix.arch }}
+            ghcr.io/${{ env.GHCR_REPOSITORY }}:${{ steps.version.outputs.value }}-${{ matrix.arch }}
           labels: ${{ steps.meta.outputs.labels }}
+          cache-from: type=gha
+          cache-to: type=gha,mode=max
+          provenance: false
+          sbom: false
+
+  create_manifests:
+    name: Create multi-arch manifests (Docker Hub + GHCR)
+    needs: [build_single_arch]
+    runs-on: ubuntu-latest
+    permissions:
+      packages: write
+      contents: read
+    steps:
+      - name: Check out (shallow)
+        uses: actions/checkout@v4
+        with:
+          fetch-depth: 1
+
+      - name: Normalize GHCR repository
+        run: echo "GHCR_REPOSITORY=${GITHUB_REPOSITORY,,}" >> $GITHUB_ENV
+
+      - name: Determine alpha version
+        id: version
+        run: |
+          VERSION="alpha-$(date +'%Y%m%d')-$(git rev-parse --short HEAD)"
+          echo "value=$VERSION" >> $GITHUB_OUTPUT
+          echo "VERSION=$VERSION" >> $GITHUB_ENV
+
+      - name: Log in to Docker Hub
+        uses: docker/login-action@v3
+        with:
+          username: ${{ secrets.DOCKERHUB_USERNAME }}
+          password: ${{ secrets.DOCKERHUB_TOKEN }}
+
+      - name: Create & push manifest (Docker Hub - alpha)
+        run: |
+          docker buildx imagetools create \
+            -t calciumion/new-api:alpha \
+            calciumion/new-api:alpha-amd64 \
+            calciumion/new-api:alpha-arm64
+
+      - name: Create & push manifest (Docker Hub - versioned alpha)
+        run: |
+          docker buildx imagetools create \
+            -t calciumion/new-api:${VERSION} \
+            calciumion/new-api:${VERSION}-amd64 \
+            calciumion/new-api:${VERSION}-arm64
+
+      - name: Log in to GHCR
+        uses: docker/login-action@v3
+        with:
+          registry: ghcr.io
+          username: ${{ github.actor }}
+          password: ${{ secrets.GITHUB_TOKEN }}
+
+      - name: Create & push manifest (GHCR - alpha)
+        run: |
+          docker buildx imagetools create \
+            -t ghcr.io/${GHCR_REPOSITORY}:alpha \
+            ghcr.io/${GHCR_REPOSITORY}:alpha-amd64 \
+            ghcr.io/${GHCR_REPOSITORY}:alpha-arm64
+
+      - name: Create & push manifest (GHCR - versioned alpha)
+        run: |
+          docker buildx imagetools create \
+            -t ghcr.io/${GHCR_REPOSITORY}:${VERSION} \
+            ghcr.io/${GHCR_REPOSITORY}:${VERSION}-amd64 \
+            ghcr.io/${GHCR_REPOSITORY}:${VERSION}-arm64

.github/workflows/docker-image-arm64.yml

@@ -1,26 +1,46 @@
-name: Publish Docker image (Multi Registries)
+name: Publish Docker image (Multi Registries, native amd64+arm64)
 
 on:
   push:
     tags:
       - '*'
+
 jobs:
-  push_to_registries:
-    name: Push Docker image to multiple registries
-    runs-on: ubuntu-latest
+  build_single_arch:
+    name: Build & push (${{ matrix.arch }}) [native]
+    strategy:
+      fail-fast: false
+      matrix:
+        include:
+          - arch: amd64
+            platform: linux/amd64
+            runner: ubuntu-latest
+          - arch: arm64
+            platform: linux/arm64
+            runner: ubuntu-24.04-arm
+    runs-on: ${{ matrix.runner }}
+
     permissions:
       packages: write
       contents: read
+
     steps:
-      - name: Check out the repo
+      - name: Check out (shallow)
         uses: actions/checkout@v4
+        with:
+          fetch-depth: 1
 
-      - name: Save version info
+      - name: Resolve tag & write VERSION
         run: |
-          git describe --tags > VERSION 
+          git fetch --tags --force --depth=1
+          TAG=${GITHUB_REF#refs/tags/}
+          echo "TAG=$TAG" >> $GITHUB_ENV
+          echo "$TAG" > VERSION
+          echo "Building tag: $TAG for ${{ matrix.arch }}"
 
-      - name: Set up QEMU
-        uses: docker/setup-qemu-action@v3
+
+#      - name: Normalize GHCR repository
+#        run: echo "GHCR_REPOSITORY=${GITHUB_REPOSITORY,,}" >> $GITHUB_ENV
 
       - name: Set up Docker Buildx
         uses: docker/setup-buildx-action@v3
@@ -31,26 +51,88 @@ jobs:
           username: ${{ secrets.DOCKERHUB_USERNAME }}
           password: ${{ secrets.DOCKERHUB_TOKEN }}
 
-      - name: Log in to the Container registry
-        uses: docker/login-action@v3
-        with:
-          registry: ghcr.io
-          username: ${{ github.actor }}
-          password: ${{ secrets.GITHUB_TOKEN }}
+#      - name: Log in to GHCR
+#        uses: docker/login-action@v3
+#        with:
+#          registry: ghcr.io
+#          username: ${{ github.actor }}
+#          password: ${{ secrets.GITHUB_TOKEN }}
 
-      - name: Extract metadata (tags, labels) for Docker
+      - name: Extract metadata (labels)
         id: meta
         uses: docker/metadata-action@v5
         with:
           images: |
             calciumion/new-api
-            ghcr.io/${{ github.repository }}
+#            ghcr.io/${{ env.GHCR_REPOSITORY }}
 
-      - name: Build and push Docker images
-        uses: docker/build-push-action@v5
+      - name: Build & push single-arch (to both registries)
+        uses: docker/build-push-action@v6
         with:
           context: .
-          platforms: linux/amd64,linux/arm64
+          platforms: ${{ matrix.platform }}
           push: true
-          tags: ${{ steps.meta.outputs.tags }}
-          labels: ${{ steps.meta.outputs.labels }}
+          tags: |
+            calciumion/new-api:${{ env.TAG }}-${{ matrix.arch }}
+            calciumion/new-api:latest-${{ matrix.arch }}
+#            ghcr.io/${{ env.GHCR_REPOSITORY }}:${{ env.TAG }}-${{ matrix.arch }}
+#            ghcr.io/${{ env.GHCR_REPOSITORY }}:latest-${{ matrix.arch }}
+          labels: ${{ steps.meta.outputs.labels }}
+          cache-from: type=gha
+          cache-to: type=gha,mode=max
+          provenance: false
+          sbom: false
+
+  create_manifests:
+    name: Create multi-arch manifests (Docker Hub)
+    needs: [build_single_arch]
+    runs-on: ubuntu-latest
+    if: startsWith(github.ref, 'refs/tags/')
+    steps:
+      - name: Extract tag
+        run: echo "TAG=${GITHUB_REF#refs/tags/}" >> $GITHUB_ENV
+#
+#      - name: Normalize GHCR repository
+#        run: echo "GHCR_REPOSITORY=${GITHUB_REPOSITORY,,}" >> $GITHUB_ENV
+
+      - name: Log in to Docker Hub
+        uses: docker/login-action@v3
+        with:
+          username: ${{ secrets.DOCKERHUB_USERNAME }}
+          password: ${{ secrets.DOCKERHUB_TOKEN }}
+
+      - name: Create & push manifest (Docker Hub - version)
+        run: |
+          docker buildx imagetools create \
+            -t calciumion/new-api:${TAG} \
+            calciumion/new-api:${TAG}-amd64 \
+            calciumion/new-api:${TAG}-arm64
+
+      - name: Create & push manifest (Docker Hub - latest)
+        run: |
+          docker buildx imagetools create \
+            -t calciumion/new-api:latest \
+            calciumion/new-api:latest-amd64 \
+            calciumion/new-api:latest-arm64
+
+      # ---- GHCR ----
+#      - name: Log in to GHCR
+#        uses: docker/login-action@v3
+#        with:
+#          registry: ghcr.io
+#          username: ${{ github.actor }}
+#          password: ${{ secrets.GITHUB_TOKEN }}
+
+#      - name: Create & push manifest (GHCR - version)
+#        run: |
+#          docker buildx imagetools create \
+#            -t ghcr.io/${GHCR_REPOSITORY}:${TAG} \
+#            ghcr.io/${GHCR_REPOSITORY}:${TAG}-amd64 \
+#            ghcr.io/${GHCR_REPOSITORY}:${TAG}-arm64
+#
+#      - name: Create & push manifest (GHCR - latest)
+#        run: |
+#          docker buildx imagetools create \
+#            -t ghcr.io/${GHCR_REPOSITORY}:latest \
+#            ghcr.io/${GHCR_REPOSITORY}:latest-amd64 \
+#            ghcr.io/${GHCR_REPOSITORY}:latest-arm64

.github/workflows/electron-build.yml

@@ -0,0 +1,141 @@
+name: Build Electron App
+
+on:
+  push:
+    tags:
+      - '*'  # Triggers on version tags like v1.0.0
+      - '!*-*'  # Ignore pre-release tags like v1.0.0-beta
+      - '!*-alpha*' # Ignore alpha tags like v1.0.0-alpha
+  workflow_dispatch:  # Allows manual triggering
+
+jobs:
+  build:
+    strategy:
+      matrix:
+        # os: [macos-latest, windows-latest]
+        os: [windows-latest]
+
+    runs-on: ${{ matrix.os }}
+    defaults:
+      run:
+        shell: bash
+
+    steps:
+      - name: Checkout code
+        uses: actions/checkout@v4
+        with:
+          fetch-depth: 0
+
+      - name: Setup Bun
+        uses: oven-sh/setup-bun@v2
+        with:
+          bun-version: latest
+
+      - name: Setup Node.js
+        uses: actions/setup-node@v4
+        with:
+          node-version: '20'
+
+      - name: Setup Go
+        uses: actions/setup-go@v5
+        with:
+          go-version: '>=1.25.1'
+
+      - name: Build frontend
+        env:
+          CI: ""
+          NODE_OPTIONS: "--max-old-space-size=4096"
+        run: |
+          cd web
+          bun install
+          DISABLE_ESLINT_PLUGIN='true' VITE_REACT_APP_VERSION=$(git describe --tags) bun run build
+          cd ..
+
+      # - name: Build Go binary (macos/Linux)
+      #   if: runner.os != 'Windows'
+      #   run: |
+      #     go mod download
+      #     go build -ldflags "-s -w -X 'new-api/common.Version=$(git describe --tags)' -extldflags '-static'" -o new-api
+
+      - name: Build Go binary (Windows)
+        if: runner.os == 'Windows'
+        run: |
+          go mod download
+          go build -ldflags "-s -w -X 'new-api/common.Version=$(git describe --tags)'" -o new-api.exe
+
+      - name: Update Electron version
+        run: |
+          cd electron
+          VERSION=$(git describe --tags)
+          VERSION=${VERSION#v}  # Remove 'v' prefix if present
+          # Convert to valid semver: take first 3 components and convert rest to prerelease format
+          # e.g., 0.9.3-patch.1 -> 0.9.3-patch.1
+          if [[ $VERSION =~ ^([0-9]+)\.([0-9]+)\.([0-9]+)(.*)$ ]]; then
+            MAJOR=${BASH_REMATCH[1]}
+            MINOR=${BASH_REMATCH[2]}
+            PATCH=${BASH_REMATCH[3]}
+            REST=${BASH_REMATCH[4]}
+          
+            VERSION="$MAJOR.$MINOR.$PATCH"
+          
+            # If there's extra content, append it without adding -dev
+            if [[ -n "$REST" ]]; then
+              VERSION="$VERSION$REST"
+            fi
+          fi
+          npm version $VERSION --no-git-tag-version --allow-same-version
+
+      - name: Install Electron dependencies
+        run: |
+          cd electron
+          npm install
+
+      # - name: Build Electron app (macOS)
+      #   if: runner.os == 'macOS'
+      #   run: |
+      #     cd electron
+      #     npm run build:mac
+      #   env:
+      #     CSC_IDENTITY_AUTO_DISCOVERY: false  # Skip code signing
+
+      - name: Build Electron app (Windows)
+        if: runner.os == 'Windows'
+        run: |
+          cd electron
+          npm run build:win
+
+      # - name: Upload artifacts (macOS)
+      #   if: runner.os == 'macOS'
+      #   uses: actions/upload-artifact@v4
+      #   with:
+      #     name: macos-build
+      #     path: |
+      #       electron/dist/*.dmg
+      #       electron/dist/*.zip
+
+      - name: Upload artifacts (Windows)
+        if: runner.os == 'Windows'
+        uses: actions/upload-artifact@v4
+        with:
+          name: windows-build
+          path: |
+            electron/dist/*.exe
+
+  release:
+    needs: build
+    runs-on: ubuntu-latest
+    if: startsWith(github.ref, 'refs/tags/')
+    permissions:
+      contents: write
+
+    steps:
+      - name: Download all artifacts
+        uses: actions/download-artifact@v4
+
+      - name: Upload to Release
+        uses: softprops/action-gh-release@v2
+        with:
+          files: |
+            windows-build/*
+        env:
+          GITHUB_TOKEN: ${{ secrets.GITHUB_TOKEN }}

.github/workflows/linux-release.yml

@@ -1,59 +0,0 @@
-name: Linux Release
-permissions:
-  contents: write
-
-on:
-  workflow_dispatch:
-    inputs:
-      name:
-        description: 'reason'
-        required: false
-  push:
-    tags:
-      - '*'
-      - '!*-alpha*'
-jobs:
-  release:
-    runs-on: ubuntu-latest
-    steps:
-      - name: Checkout
-        uses: actions/checkout@v3
-        with:
-          fetch-depth: 0
-      - uses: oven-sh/setup-bun@v2
-        with:
-          bun-version: latest
-      - name: Build Frontend
-        env:
-          CI: ""
-        run: |
-          cd web
-          bun install
-          DISABLE_ESLINT_PLUGIN='true' VITE_REACT_APP_VERSION=$(git describe --tags) bun run build
-          cd ..
-      - name: Set up Go
-        uses: actions/setup-go@v3
-        with:
-          go-version: '>=1.18.0'
-      - name: Build Backend (amd64)
-        run: |
-          go mod download
-          go build -ldflags "-s -w -X 'one-api/common.Version=$(git describe --tags)' -extldflags '-static'" -o one-api
-
-      - name: Build Backend (arm64)
-        run: |
-          sudo apt-get update
-          DEBIAN_FRONTEND=noninteractive sudo apt-get install -y gcc-aarch64-linux-gnu
-          CC=aarch64-linux-gnu-gcc CGO_ENABLED=1 GOOS=linux GOARCH=arm64 go build -ldflags "-s -w -X 'one-api/common.Version=$(git describe --tags)' -extldflags '-static'" -o one-api-arm64
-
-      - name: Release
-        uses: softprops/action-gh-release@v1
-        if: startsWith(github.ref, 'refs/tags/')
-        with:
-          files: |
-            one-api
-            one-api-arm64
-          draft: true
-          generate_release_notes: true
-        env:
-          GITHUB_TOKEN: ${{ secrets.GITHUB_TOKEN }}

.github/workflows/macos-release.yml

@@ -1,51 +0,0 @@
-name: macOS Release
-permissions:
-  contents: write
-
-on:
-  workflow_dispatch:
-    inputs:
-      name:
-        description: 'reason'
-        required: false
-  push:
-    tags:
-      - '*'
-      - '!*-alpha*'
-jobs:
-  release:
-    runs-on: macos-latest
-    steps:
-      - name: Checkout
-        uses: actions/checkout@v3
-        with:
-          fetch-depth: 0
-      - uses: oven-sh/setup-bun@v2
-        with:
-          bun-version: latest
-      - name: Build Frontend
-        env:
-          CI: ""
-          NODE_OPTIONS: "--max-old-space-size=4096"
-        run: |
-          cd web
-          bun install
-          DISABLE_ESLINT_PLUGIN='true' VITE_REACT_APP_VERSION=$(git describe --tags) bun run build
-          cd ..
-      - name: Set up Go
-        uses: actions/setup-go@v3
-        with:
-          go-version: '>=1.18.0'
-      - name: Build Backend
-        run: |
-          go mod download
-          go build -ldflags "-X 'one-api/common.Version=$(git describe --tags)'" -o one-api-macos
-      - name: Release
-        uses: softprops/action-gh-release@v1
-        if: startsWith(github.ref, 'refs/tags/')
-        with:
-          files: one-api-macos
-          draft: true
-          generate_release_notes: true
-        env:
-          GITHUB_TOKEN: ${{ secrets.GITHUB_TOKEN }}

.github/workflows/pr-target-branch-check.yml

@@ -1,21 +0,0 @@
-name: Check PR Branching Strategy
-on:
-  pull_request:
-    types: [opened, synchronize, reopened, edited]
-
-jobs:
-  check-branching-strategy:
-    runs-on: ubuntu-latest
-    steps:
-      - name: Enforce branching strategy
-        run: |
-          if [[ "${{ github.base_ref }}" == "main" ]]; then
-            if [[ "${{ github.head_ref }}" != "alpha" ]]; then
-              echo "Error: Pull requests to 'main' are only allowed from the 'alpha' branch."
-              exit 1
-            fi
-          elif [[ "${{ github.base_ref }}" != "alpha" ]]; then
-            echo "Error: Pull requests must be targeted to the 'alpha' or 'main' branch."
-            exit 1
-          fi
-          echo "Branching strategy check passed."

.github/workflows/release.yml

@@ -0,0 +1,142 @@
+name: Release (Linux, macOS, Windows)
+permissions:
+  contents: write
+
+on:
+  workflow_dispatch:
+    inputs:
+      name:
+        description: 'reason'
+        required: false
+  push:
+    tags:
+      - '*'
+      - '!*-alpha*'
+
+jobs:
+  linux:
+    name: Linux Release
+    runs-on: ubuntu-latest
+    steps:
+      - name: Checkout
+        uses: actions/checkout@v3
+        with:
+          fetch-depth: 0
+      - name: Determine Version
+        run: |
+          VERSION=$(git describe --tags)
+          echo "VERSION=$VERSION" >> $GITHUB_ENV
+      - uses: oven-sh/setup-bun@v2
+        with:
+          bun-version: latest
+      - name: Build Frontend
+        env:
+          CI: ""
+        run: |
+          cd web
+          bun install
+          DISABLE_ESLINT_PLUGIN='true' VITE_REACT_APP_VERSION=$VERSION bun run build
+          cd ..
+      - name: Set up Go
+        uses: actions/setup-go@v3
+        with:
+          go-version: '>=1.25.1'
+      - name: Build Backend (amd64)
+        run: |
+          go mod download
+          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
+          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
+        if: startsWith(github.ref, 'refs/tags/')
+        with:
+          files: |
+            new-api-*
+        env:
+          GITHUB_TOKEN: ${{ secrets.GITHUB_TOKEN }}
+
+  macos:
+    name: macOS Release
+    runs-on: macos-latest
+    steps:
+      - name: Checkout
+        uses: actions/checkout@v3
+        with:
+          fetch-depth: 0
+      - name: Determine Version
+        run: |
+          VERSION=$(git describe --tags)
+          echo "VERSION=$VERSION" >> $GITHUB_ENV
+      - uses: oven-sh/setup-bun@v2
+        with:
+          bun-version: latest
+      - name: Build Frontend
+        env:
+          CI: ""
+          NODE_OPTIONS: "--max-old-space-size=4096"
+        run: |
+          cd web
+          bun install
+          DISABLE_ESLINT_PLUGIN='true' VITE_REACT_APP_VERSION=$VERSION bun run build
+          cd ..
+      - name: Set up Go
+        uses: actions/setup-go@v3
+        with:
+          go-version: '>=1.25.1'
+      - name: Build Backend
+        run: |
+          go mod download
+          go build -ldflags "-X 'new-api/common.Version=$VERSION'" -o new-api-macos-$VERSION
+      - name: Release
+        uses: softprops/action-gh-release@v2
+        if: startsWith(github.ref, 'refs/tags/')
+        with:
+          files: new-api-macos-*
+        env:
+          GITHUB_TOKEN: ${{ secrets.GITHUB_TOKEN }}
+
+  windows:
+    name: Windows Release
+    runs-on: windows-latest
+    defaults:
+      run:
+        shell: bash
+    steps:
+      - name: Checkout
+        uses: actions/checkout@v3
+        with:
+          fetch-depth: 0
+      - name: Determine Version
+        run: |
+          VERSION=$(git describe --tags)
+          echo "VERSION=$VERSION" >> $GITHUB_ENV
+      - uses: oven-sh/setup-bun@v2
+        with:
+          bun-version: latest
+      - name: Build Frontend
+        env:
+          CI: ""
+        run: |
+          cd web
+          bun install
+          DISABLE_ESLINT_PLUGIN='true' VITE_REACT_APP_VERSION=$VERSION bun run build
+          cd ..
+      - name: Set up Go
+        uses: actions/setup-go@v3
+        with:
+          go-version: '>=1.25.1'
+      - name: Build Backend
+        run: |
+          go mod download
+          go build -ldflags "-s -w -X 'new-api/common.Version=$VERSION'" -o new-api-$VERSION.exe
+      - name: Release
+        uses: softprops/action-gh-release@v2
+        if: startsWith(github.ref, 'refs/tags/')
+        with:
+          files: new-api-*.exe
+        env:
+          GITHUB_TOKEN: ${{ secrets.GITHUB_TOKEN }}

.github/workflows/sync-to-gitee.yml

@@ -0,0 +1,91 @@
+name: Sync Release to Gitee
+
+permissions:
+  contents: read
+
+on:
+  workflow_dispatch:
+    inputs:
+      tag_name:
+        description: 'Release Tag to sync (e.g. v1.0.0)'
+        required: true
+        type: string
+
+# 配置你的 Gitee 仓库信息
+env:
+  GITEE_OWNER: 'QuantumNous'  # 修改为你的 Gitee 用户名
+  GITEE_REPO: 'new-api'                # 修改为你的 Gitee 仓库名
+
+jobs:
+  sync-to-gitee:
+    runs-on: sync
+    steps:
+      - name: Checkout
+        uses: actions/checkout@v3
+        with:
+          fetch-depth: 0
+
+      - name: Get Release Info
+        id: release_info
+        env:
+          GITHUB_TOKEN: ${{ secrets.GITHUB_TOKEN }}
+          TAG_NAME: ${{ github.event.inputs.tag_name }}
+        run: |
+          # 获取 release 信息
+          RELEASE_INFO=$(gh release view "$TAG_NAME" --json name,body,tagName,targetCommitish)
+          
+          RELEASE_NAME=$(echo "$RELEASE_INFO" | jq -r '.name')
+          TARGET_COMMITISH=$(echo "$RELEASE_INFO" | jq -r '.targetCommitish')
+          
+          # 使用多行字符串输出
+          {
+            echo "release_name=$RELEASE_NAME"
+            echo "target_commitish=$TARGET_COMMITISH"
+            echo "release_body<<EOF"
+            echo "$RELEASE_INFO" | jq -r '.body'
+            echo "EOF"
+          } >> $GITHUB_OUTPUT
+          
+          # 下载 release 的所有附件
+          gh release download "$TAG_NAME" --dir ./release_assets || echo "No assets to download"
+          
+          # 列出下载的文件
+          ls -la ./release_assets/ || echo "No assets directory"
+
+      - name: Create Gitee Release
+        id: create_release
+        uses: nICEnnnnnnnLee/action-gitee-release@v2.0.0
+        with:
+          gitee_action: create_release
+          gitee_owner: ${{ env.GITEE_OWNER }}
+          gitee_repo: ${{ env.GITEE_REPO }}
+          gitee_token: ${{ secrets.GITEE_TOKEN }}
+          gitee_tag_name: ${{ github.event.inputs.tag_name }}
+          gitee_release_name: ${{ steps.release_info.outputs.release_name }}
+          gitee_release_body: ${{ steps.release_info.outputs.release_body }}
+          gitee_target_commitish: ${{ steps.release_info.outputs.target_commitish }}
+
+      - name: Upload Assets to Gitee
+        if: hashFiles('release_assets/*') != ''
+        uses: nICEnnnnnnnLee/action-gitee-release@v2.0.0
+        with:
+          gitee_action: upload_asset
+          gitee_owner: ${{ env.GITEE_OWNER }}
+          gitee_repo: ${{ env.GITEE_REPO }}
+          gitee_token: ${{ secrets.GITEE_TOKEN }}
+          gitee_release_id: ${{ steps.create_release.outputs.release-id }}
+          gitee_upload_retry_times: 3
+          gitee_files: |
+            release_assets/*
+
+      - name: Cleanup
+        if: always()
+        run: |
+          rm -rf release_assets/
+
+      - name: Summary
+        if: success()
+        run: |
+          echo "✅ Successfully synced release ${{ github.event.inputs.tag_name }} to Gitee!"
+          echo "🔗 Gitee Release URL: https://gitee.com/${{ env.GITEE_OWNER }}/${{ env.GITEE_REPO }}/releases/tag/${{ github.event.inputs.tag_name }}"
+

.github/workflows/windows-release.yml

@@ -1,53 +0,0 @@
-name: Windows Release
-permissions:
-  contents: write
-
-on:
-  workflow_dispatch:
-    inputs:
-      name:
-        description: 'reason'
-        required: false
-  push:
-    tags:
-      - '*'
-      - '!*-alpha*'
-jobs:
-  release:
-    runs-on: windows-latest
-    defaults:
-      run:
-        shell: bash
-    steps:
-      - name: Checkout
-        uses: actions/checkout@v3
-        with:
-          fetch-depth: 0
-      - uses: oven-sh/setup-bun@v2
-        with:
-          bun-version: latest
-      - name: Build Frontend
-        env:
-          CI: ""
-        run: |
-          cd web
-          bun install
-          DISABLE_ESLINT_PLUGIN='true' VITE_REACT_APP_VERSION=$(git describe --tags) bun run build
-          cd ..
-      - name: Set up Go
-        uses: actions/setup-go@v3
-        with:
-          go-version: '>=1.18.0'
-      - name: Build Backend
-        run: |
-          go mod download
-          go build -ldflags "-s -w -X 'one-api/common.Version=$(git describe --tags)'" -o one-api.exe
-      - name: Release
-        uses: softprops/action-gh-release@v1
-        if: startsWith(github.ref, 'refs/tags/')
-        with:
-          files: one-api.exe
-          draft: true
-          generate_release_notes: true
-        env:
-          GITHUB_TOKEN: ${{ secrets.GITHUB_TOKEN }}

.gitignore

@@ -1,5 +1,6 @@
 .idea
 .vscode
+.zed
 upload
 *.exe
 *.db
@@ -9,6 +10,20 @@ logs
 web/dist
 .env
 one-api
+new-api
+/__debug_bin*
 .DS_Store
 tiktoken_cache
-.eslintcache
+.eslintcache
+.gocache
+.gomodcache/
+.cache
+web/bun.lock
+plans
+
+electron/node_modules
+electron/dist
+data/
+.gomodcache/
+.gocache-temp
+.gopath

Dockerfile

@@ -9,10 +9,12 @@ COPY ./VERSION .
 RUN DISABLE_ESLINT_PLUGIN='true' VITE_REACT_APP_VERSION=$(cat VERSION) bun run build
 
 FROM golang:alpine AS builder2
+ENV GO111MODULE=on CGO_ENABLED=0
 
-ENV GO111MODULE=on \
-    CGO_ENABLED=0 \
-    GOOS=linux
+ARG TARGETOS
+ARG TARGETARCH
+ENV GOOS=${TARGETOS:-linux} GOARCH=${TARGETARCH:-amd64}
+ENV GOEXPERIMENT=greenteagc
 
 WORKDIR /build
 
@@ -21,15 +23,16 @@ RUN go mod download
 
 COPY . .
 COPY --from=builder /build/dist ./web/dist
-RUN go build -ldflags "-s -w -X 'one-api/common.Version=$(cat VERSION)'" -o one-api
+RUN go build -ldflags "-s -w -X 'github.com/QuantumNous/new-api/common.Version=$(cat VERSION)'" -o new-api
 
-FROM alpine
+FROM debian:bookworm-slim
 
-RUN apk upgrade --no-cache \
-    && apk add --no-cache ca-certificates tzdata ffmpeg \
+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/one-api /
+COPY --from=builder2 /build/new-api /
 EXPOSE 3000
 WORKDIR /data
-ENTRYPOINT ["/one-api"]
+ENTRYPOINT ["/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

@@ -1,216 +0,0 @@
-<p align="right">
-   <a href="./README.md">中文</a> | <strong>English</strong>
-</p>
-<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 (YiPay)
-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 Claude Messages format, [API Documentation](https://docs.newapi.pro/api/anthropic-chat)
-14. Support for entering chat interface via /chat2link route
-15. 🧠 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`)
-16. 🔄 Thinking-to-content functionality
-17. 🔄 Model rate limiting for users
-18. 💰 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. Dify, currently only supports chatflow
-
-## 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`
-- `FORCE_STREAM_OPTION`: Whether to override client stream_options parameter, 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`
-- `COHERE_SAFETY_SETTING`: Cohere model safety settings, options are `NONE`, `CONTEXTUAL`, `STRICT`, default is `NONE`
-- `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 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`. It is **recommended to enable caching**.
-
-### 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](https://docs.newapi.pro/api/openai-chat)
-- [Image API](https://docs.newapi.pro/api/openai-image)
-- [Rerank API](https://docs.newapi.pro/api/jinaai-rerank)
-- [Realtime API](https://docs.newapi.pro/api/openai-realtime)
-- [Claude Chat API (messages)](https://docs.newapi.pro/api/anthropic-chat)
-
-## Related Projects
-- [One API](https://github.com/songquanpeng/one-api): Original project
-- [Midjourney-Proxy](https://github.com/novicezk/midjourney-proxy): Midjourney interface support
-- [chatnio](https://github.com/Deeptrain-Community/chatnio): Next-generation AI one-stop B/C-end solution
-- [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
-- [VoAPI](https://github.com/VoAPI/VoAPI): Frontend beautified version based on 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

@@ -0,0 +1,468 @@
+<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**
+
+<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">
+    <img src="https://img.shields.io/github/license/Calcium-Ion/new-api?color=brightgreen" alt="licence">
+  </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="version">
+  </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="#-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]  
+> Il s'agit d'un projet open-source développé sur la base de [One API](https://github.com/songquanpeng/one-api)
+
+> [!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.
+
+---
+
+## 🤝 Partenaires de confiance
+
+<p align="center">
+  <em>Sans ordre particulier</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="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>
+
+---
+
+## 🙏 Remerciements spéciaux
+
+<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>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>
+
+---
+
+## 🚀 Démarrage rapide
+
+### Utilisation de Docker Compose (recommandé)
+
+```bash
+# Cloner le projet
+git clone https://github.com/QuantumNous/new-api.git
+cd new-api
+
+# Modifier la configuration docker-compose.yml
+nano docker-compose.yml
+
+# Démarrer le service
+docker-compose up -d
+```
+
+<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 ./data:/data \
+  calciumion/new-api:latest
+```
+
+> **💡 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`
+
+</details>
+
+---
+
+🎉 Après le déploiement, visitez `http://localhost:3000` pour commencer à utiliser!
+
+📖 Pour plus de méthodes de déploiement, veuillez vous référer à [Guide de déploiement](https://docs.newapi.pro/en/docs/installation)
+
+---
+
+## 📚 Documentation
+
+<div align="center">
+
+### 📖 [Documentation officielle](https://docs.newapi.pro/en/docs) | [![Demander à DeepWiki](https://deepwiki.com/badge.svg)](https://deepwiki.com/QuantumNous/new-api)
+
+</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
+
+<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

@@ -0,0 +1,468 @@
+<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**
+
+<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">
+    <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="#-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
+
+> [!NOTE]  
+> 本プロジェクトは、[One API](https://github.com/songquanpeng/one-api)をベースに二次開発されたオープンソースプロジェクトです
+
+> [!IMPORTANT]  
+> - 本プロジェクトは個人学習用のみであり、安定性の保証や技術サポートは提供しません。
+> - 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。
+
+---
+
+## 🤝 信頼できるパートナー
+
+<p align="center">
+  <em>順不同</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 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>
+
+---
+
+## 🙏 特別な感謝
+
+<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>
+
+---
+
+## 🚀 クイックスタート
+
+### Docker Composeを使用（推奨）
+
+```bash
+# プロジェクトをクローン
+git clone https://github.com/QuantumNous/new-api.git
+cd new-api
+
+# docker-compose.yml 設定を編集
+nano docker-compose.yml
+
+# サービスを起動
+docker-compose up -d
+```
+
+<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 ./data:/data \
+  calciumion/new-api:latest
+```
+
+> **💡 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`
+
+</details>
+
+---
+
+🎉 デプロイが完了したら、`http://localhost:3000` にアクセスして使用を開始してください！
+
+📖 その他のデプロイ方法については[デプロイガイド](https://docs.newapi.pro/ja/docs/installation)を参照してください。
+
+---
+
+## 📚 ドキュメント
+
+<div align="center">
+
+### 📖 [公式ドキュメント](https://docs.newapi.pro/ja/docs) | [![Ask DeepWiki](https://deepwiki.com/badge.svg)](https://deepwiki.com/QuantumNous/new-api)
+
+</div>
+
+**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>
-</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">
@@ -28,188 +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（易支付）
-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Claude Messages 格式，[接口文档](https://docs.newapi.pro/api/anthropic-chat)
-14. 支持使用路由/chat2link进入聊天界面
-15. 🧠 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`)
-16. 🔄 思考转内容功能
-17. 🔄 针对用户的模型限流功能
-18. 💰 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. Dify，当前仅支持chatflow
-
-## 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`
-- `FORCE_STREAM_OPTION`：是否覆盖客户端stream_options参数，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`
-- `COHERE_SAFETY_SETTING`：Cohere模型安全设置，可选值为 `NONE`, `CONTEXTUAL`, `STRICT`，默认 `NONE`
-- `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`：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
-git clone https://github.com/Calcium-Ion/new-api.git
+```bash
+# Clone the project
+git clone https://github.com/QuantumNous/new-api.git
 cd new-api
-# 按需编辑docker-compose.yml
-# 启动
+
+# Edit docker-compose.yml configuration
+nano 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`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）](https://docs.newapi.pro/api/openai-chat)
-- [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（messages）](https://docs.newapi.pro/api/anthropic-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
-- [chatnio](https://github.com/Deeptrain-Community/chatnio)：下一代AI一站式B/C端解决方案
-- [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

@@ -1,6 +1,6 @@
 package common
 
-import "one-api/constant"
+import "github.com/QuantumNous/new-api/constant"
 
 func ChannelType2APIType(channelType int) (int, bool) {
 	apiType := -1
@@ -67,6 +67,14 @@ func ChannelType2APIType(channelType int) (int, bool) {
 		apiType = constant.APITypeJimeng
 	case constant.ChannelTypeMoonshot:
 		apiType = constant.APITypeMoonshot
+	case constant.ChannelTypeSubmodel:
+		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

@@ -0,0 +1,347 @@
+package common
+
+import (
+	"context"
+	"encoding/binary"
+	"fmt"
+	"io"
+
+	"github.com/abema/go-mp4"
+	"github.com/go-audio/aiff"
+	"github.com/go-audio/wav"
+	"github.com/jfreymuth/oggvorbis"
+	"github.com/mewkiz/flac"
+	"github.com/pkg/errors"
+	"github.com/tcolgate/mp3"
+	"github.com/yapingcat/gomedia/go-codec"
+)
+
+// GetAudioDuration 使用纯 Go 库获取音频文件的时长（秒）。
+// 它不再依赖外部的 ffmpeg 或 ffprobe 程序。
+func GetAudioDuration(ctx context.Context, f io.ReadSeeker, ext string) (duration float64, err error) {
+	SysLog(fmt.Sprintf("GetAudioDuration: ext=%s", ext))
+	// 根据文件扩展名选择解析器
+	switch ext {
+	case ".mp3":
+		duration, err = getMP3Duration(f)
+	case ".wav":
+		duration, err = getWAVDuration(f)
+	case ".flac":
+		duration, err = getFLACDuration(f)
+	case ".m4a", ".mp4":
+		duration, err = getM4ADuration(f)
+	case ".ogg", ".oga", ".opus":
+		duration, err = getOGGDuration(f)
+		if err != nil {
+			duration, err = getOpusDuration(f)
+		}
+	case ".aiff", ".aif", ".aifc":
+		duration, err = getAIFFDuration(f)
+	case ".webm":
+		duration, err = getWebMDuration(f)
+	case ".aac":
+		duration, err = getAACDuration(f)
+	default:
+		return 0, fmt.Errorf("unsupported audio format: %s", ext)
+	}
+	SysLog(fmt.Sprintf("GetAudioDuration: duration=%f", duration))
+	return duration, err
+}
+
+// getMP3Duration 解析 MP3 文件以获取时长。
+// 注意：对于 VBR (Variable Bitrate) MP3，这个估算可能不完全精确，但通常足够好。
+// FFmpeg 在这种情况下会扫描整个文件来获得精确值，但这里的库提供了快速估算。
+func getMP3Duration(r io.Reader) (float64, error) {
+	d := mp3.NewDecoder(r)
+	var f mp3.Frame
+	skipped := 0
+	duration := 0.0
+
+	for {
+		if err := d.Decode(&f, &skipped); err != nil {
+			if err == io.EOF {
+				break
+			}
+			return 0, errors.Wrap(err, "failed to decode mp3 frame")
+		}
+		duration += f.Duration().Seconds()
+	}
+	return duration, nil
+}
+
+// getWAVDuration 解析 WAV 文件头以获取时长。
+func getWAVDuration(r io.ReadSeeker) (float64, error) {
+	// 1. 强制复位指针
+	r.Seek(0, io.SeekStart)
+
+	dec := wav.NewDecoder(r)
+
+	// IsValidFile 会读取 fmt 块
+	if !dec.IsValidFile() {
+		return 0, errors.New("invalid wav file")
+	}
+
+	// 尝试寻找 data 块
+	if err := dec.FwdToPCM(); err != nil {
+		return 0, errors.Wrap(err, "failed to find PCM data chunk")
+	}
+
+	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。
+func getFLACDuration(r io.Reader) (float64, error) {
+	stream, err := flac.Parse(r)
+	if err != nil {
+		return 0, errors.Wrap(err, "failed to parse flac stream")
+	}
+	defer stream.Close()
+
+	// 时长 = 总采样数 / 采样率
+	duration := float64(stream.Info.NSamples) / float64(stream.Info.SampleRate)
+	return duration, nil
+}
+
+// getM4ADuration 解析 M4A/MP4 文件的 'mvhd' box。
+func getM4ADuration(r io.ReadSeeker) (float64, error) {
+	// go-mp4 库需要 ReadSeeker 接口
+	info, err := mp4.Probe(r)
+	if err != nil {
+		return 0, errors.Wrap(err, "failed to probe m4a/mp4 file")
+	}
+	// 时长 = Duration / Timescale
+	return float64(info.Duration) / float64(info.Timescale), nil
+}
+
+// getOGGDuration 解析 OGG/Vorbis 文件以获取时长。
+func getOGGDuration(r io.ReadSeeker) (float64, error) {
+	// 重置 reader 到开头
+	if _, err := r.Seek(0, io.SeekStart); err != nil {
+		return 0, errors.Wrap(err, "failed to seek ogg file")
+	}
+
+	reader, err := oggvorbis.NewReader(r)
+	if err != nil {
+		return 0, errors.Wrap(err, "failed to create ogg vorbis reader")
+	}
+
+	// 计算时长 = 总采样数 / 采样率
+	// 需要读取整个文件来获取总采样数
+	channels := reader.Channels()
+	sampleRate := reader.SampleRate()
+
+	// 估算方法：读取到文件结尾
+	var totalSamples int64
+	buf := make([]float32, 4096*channels)
+	for {
+		n, err := reader.Read(buf)
+		if err == io.EOF {
+			break
+		}
+		if err != nil {
+			return 0, errors.Wrap(err, "failed to read ogg samples")
+		}
+		totalSamples += int64(n / channels)
+	}
+
+	duration := float64(totalSamples) / float64(sampleRate)
+	return duration, nil
+}
+
+// getOpusDuration 解析 Opus 文件（在 OGG 容器中）以获取时长。
+func getOpusDuration(r io.ReadSeeker) (float64, error) {
+	// Opus 通常封装在 OGG 容器中
+	// 我们需要解析 OGG 页面来获取时长信息
+	if _, err := r.Seek(0, io.SeekStart); err != nil {
+		return 0, errors.Wrap(err, "failed to seek opus file")
+	}
+
+	// 读取 OGG 页面头部
+	var totalGranulePos int64
+	buf := make([]byte, 27) // OGG 页面头部最小大小
+
+	for {
+		n, err := r.Read(buf)
+		if err == io.EOF {
+			break
+		}
+		if err != nil {
+			return 0, errors.Wrap(err, "failed to read opus/ogg page")
+		}
+		if n < 27 {
+			break
+		}
+
+		// 检查 OGG 页面标识 "OggS"
+		if string(buf[0:4]) != "OggS" {
+			// 跳过一些字节继续寻找
+			if _, err := r.Seek(-26, io.SeekCurrent); err != nil {
+				break
+			}
+			continue
+		}
+
+		// 读取 granule position (字节 6-13, 小端序)
+		granulePos := int64(binary.LittleEndian.Uint64(buf[6:14]))
+		if granulePos > totalGranulePos {
+			totalGranulePos = granulePos
+		}
+
+		// 读取段表大小
+		numSegments := int(buf[26])
+		segmentTable := make([]byte, numSegments)
+		if _, err := io.ReadFull(r, segmentTable); err != nil {
+			break
+		}
+
+		// 计算页面数据大小并跳过
+		var pageSize int
+		for _, segSize := range segmentTable {
+			pageSize += int(segSize)
+		}
+		if _, err := r.Seek(int64(pageSize), io.SeekCurrent); err != nil {
+			break
+		}
+	}
+
+	// Opus 的采样率固定为 48000 Hz
+	duration := float64(totalGranulePos) / 48000.0
+	return duration, nil
+}
+
+// getAIFFDuration 解析 AIFF 文件头以获取时长。
+func getAIFFDuration(r io.ReadSeeker) (float64, error) {
+	if _, err := r.Seek(0, io.SeekStart); err != nil {
+		return 0, errors.Wrap(err, "failed to seek aiff file")
+	}
+
+	dec := aiff.NewDecoder(r)
+	if !dec.IsValidFile() {
+		return 0, errors.New("invalid aiff file")
+	}
+
+	d, err := dec.Duration()
+	if err != nil {
+		return 0, errors.Wrap(err, "failed to get aiff duration")
+	}
+
+	return d.Seconds(), nil
+}
+
+// getWebMDuration 解析 WebM 文件以获取时长。
+// WebM 使用 Matroska 容器格式
+func getWebMDuration(r io.ReadSeeker) (float64, error) {
+	if _, err := r.Seek(0, io.SeekStart); err != nil {
+		return 0, errors.Wrap(err, "failed to seek webm file")
+	}
+
+	// WebM/Matroska 文件的解析比较复杂
+	// 这里提供一个简化的实现，读取 EBML 头部
+	// 对于完整的 WebM 解析，可能需要使用专门的库
+
+	// 简单实现：查找 Duration 元素
+	// WebM Duration 的 Element ID 是 0x4489
+	// 这是一个简化版本，可能不适用于所有 WebM 文件
+	buf := make([]byte, 8192)
+	n, err := r.Read(buf)
+	if err != nil && err != io.EOF {
+		return 0, errors.Wrap(err, "failed to read webm file")
+	}
+
+	// 尝试查找 Duration 元素（这是一个简化的方法）
+	// 实际的 WebM 解析需要完整的 EBML 解析器
+	// 这里返回错误，建议使用专门的库
+	if n > 0 {
+		// 检查 EBML 标识
+		if len(buf) >= 4 && binary.BigEndian.Uint32(buf[0:4]) == 0x1A45DFA3 {
+			// 这是一个有效的 EBML 文件
+			// 但完整解析需要更复杂的逻辑
+			return 0, errors.New("webm duration parsing requires full EBML parser (consider using ffprobe for webm files)")
+		}
+	}
+
+	return 0, errors.New("failed to parse webm file")
+}
+
+// getAACDuration 解析 AAC (ADTS格式) 文件以获取时长。
+// 使用 gomedia 库来解析 AAC ADTS 帧
+func getAACDuration(r io.ReadSeeker) (float64, error) {
+	if _, err := r.Seek(0, io.SeekStart); err != nil {
+		return 0, errors.Wrap(err, "failed to seek aac file")
+	}
+
+	// 读取整个文件内容
+	data, err := io.ReadAll(r)
+	if err != nil {
+		return 0, errors.Wrap(err, "failed to read aac file")
+	}
+
+	var totalFrames int64
+	var sampleRate int
+
+	// 使用 gomedia 的 SplitAACFrame 函数来分割 AAC 帧
+	codec.SplitAACFrame(data, func(aac []byte) {
+		// 解析 ADTS 头部以获取采样率信息
+		if len(aac) >= 7 {
+			// 使用 ConvertADTSToASC 来获取音频配置信息
+			asc, err := codec.ConvertADTSToASC(aac)
+			if err == nil && sampleRate == 0 {
+				sampleRate = codec.AACSampleIdxToSample(int(asc.Sample_freq_index))
+			}
+			totalFrames++
+		}
+	})
+
+	if sampleRate == 0 || totalFrames == 0 {
+		return 0, errors.New("no valid aac frames found")
+	}
+
+	// 每个 AAC ADTS 帧包含 1024 个采样
+	totalSamples := totalFrames * 1024
+	duration := float64(totalSamples) / float64(sampleRate)
+	return duration, nil
+}

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"
@@ -19,6 +20,7 @@ var TopUpLink = ""
 // var ChatLink = ""
 // var ChatLink2 = ""
 var QuotaPerUnit = 500 * 1000.0 // $0.002 / 1K tokens
+// 保留旧变量以兼容历史逻辑，实际展示由 general_setting.quota_display_type 控制
 var DisplayInCurrencyEnabled = true
 var DisplayTokenStatEnabled = true
 var DrawingEnabled = true
@@ -72,6 +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
@@ -120,6 +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
@@ -158,14 +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/crypto.go

@@ -4,6 +4,7 @@ import (
 	"crypto/hmac"
 	"crypto/sha256"
 	"encoding/hex"
+
 	"golang.org/x/crypto/bcrypt"
 )
 

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
@@ -86,5 +86,8 @@ func SendEmail(subject string, receiver string, content string) error {
 	} else {
 		err = smtp.SendMail(addr, auth, SMTPFrom, to, mail)
 	}
+	if err != nil {
+		SysError(fmt.Sprintf("failed to send email to %s: %v", receiver, err))
+	}
 	return err
 }

common/embed-file-system.go

@@ -2,9 +2,11 @@ package common
 
 import (
 	"embed"
-	"github.com/gin-contrib/static"
 	"io/fs"
 	"net/http"
+	"os"
+
+	"github.com/gin-contrib/static"
 )
 
 // Credit: https://github.com/gin-contrib/static/issues/19
@@ -13,7 +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
@@ -21,12 +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

@@ -1,6 +1,6 @@
 package common
 
-import "one-api/constant"
+import "github.com/QuantumNous/new-api/constant"
 
 // EndpointInfo 描述单个端点的默认请求信息
 // path: 上游路径
@@ -17,12 +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.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/endpoint_type.go

@@ -1,6 +1,6 @@
 package common
 
-import "one-api/constant"
+import "github.com/QuantumNous/new-api/constant"
 
 // GetEndpointTypesByChannelType 获取渠道最优先端点类型（所有的渠道都支持 OpenAI 端点）
 func GetEndpointTypesByChannelType(channelType int, modelName string) []constant.EndpointType {
@@ -26,6 +26,8 @@ func GetEndpointTypesByChannelType(channelType int, modelName string) []constant
 		endpointTypes = []constant.EndpointType{constant.EndpointTypeGemini, constant.EndpointTypeOpenAI}
 	case constant.ChannelTypeOpenRouter: // OpenRouter 只支持 OpenAI 端点
 		endpointTypes = []constant.EndpointType{constant.EndpointTypeOpenAI}
+	case constant.ChannelTypeSora:
+		endpointTypes = []constant.EndpointType{constant.EndpointTypeOpenAIVideo}
 	default:
 		if IsOpenAIResponseOnlyModel(modelName) {
 			endpointTypes = []constant.EndpointType{constant.EndpointTypeOpenAIResponse}

common/gin.go

@@ -2,29 +2,129 @@ package common
 
 import (
 	"bytes"
+	"fmt"
 	"io"
+	"mime"
+	"mime/multipart"
 	"net/http"
-	"one-api/constant"
+	"net/url"
 	"strings"
 	"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 {
@@ -37,7 +137,11 @@ func UnmarshalBodyReusable(c *gin.Context, v any) error {
 	//}
 	contentType := c.Request.Header.Get("Content-Type")
 	if strings.HasPrefix(contentType, "application/json") {
-		err = Unmarshal(requestBody, &v)
+		err = Unmarshal(requestBody, v)
+	} else if strings.Contains(contentType, gin.MIMEPOSTForm) {
+		err = parseFormData(requestBody, v)
+	} else if strings.Contains(contentType, gin.MIMEMultipartPOSTForm) {
+		err = parseMultipartFormData(c, requestBody, v)
 	} else {
 		// skip for now
 		// TODO: someday non json request have variant model, we will need to implementation this
@@ -113,3 +217,113 @@ func ApiSuccess(c *gin.Context, data any) {
 		"data":    data,
 	})
 }
+
+func ParseMultipartFormReusable(c *gin.Context) (*multipart.Form, error) {
+	requestBody, err := GetRequestBody(c)
+	if err != nil {
+		return nil, err
+	}
+
+	contentType := c.Request.Header.Get("Content-Type")
+	boundary, err := parseBoundary(contentType)
+	if err != nil {
+		return nil, err
+	}
+
+	reader := multipart.NewReader(bytes.NewReader(requestBody), boundary)
+	form, err := reader.ReadForm(multipartMemoryLimit())
+	if err != nil {
+		return nil, err
+	}
+
+	// Reset request body
+	c.Request.Body = io.NopCloser(bytes.NewBuffer(requestBody))
+	return form, nil
+}
+
+func processFormMap(formMap map[string]any, v any) error {
+	jsonData, err := Marshal(formMap)
+	if err != nil {
+		return err
+	}
+
+	err = Unmarshal(jsonData, v)
+	if err != nil {
+		return err
+	}
+
+	return nil
+}
+
+func parseFormData(data []byte, v any) error {
+	values, err := url.ParseQuery(string(data))
+	if err != nil {
+		return err
+	}
+	formMap := make(map[string]any)
+	for key, vals := range values {
+		if len(vals) == 1 {
+			formMap[key] = vals[0]
+		} else {
+			formMap[key] = vals
+		}
+	}
+
+	return processFormMap(formMap, v)
+}
+
+func parseMultipartFormData(c *gin.Context, data []byte, v any) error {
+	contentType := c.Request.Header.Get("Content-Type")
+	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(multipartMemoryLimit())
+	if err != nil {
+		return err
+	}
+	defer form.RemoveAll()
+	formMap := make(map[string]any)
+	for key, vals := range form.Value {
+		if len(vals) == 1 {
+			formMap[key] = vals[0]
+		} else {
+			formMap[key] = vals
+		}
+	}
+
+	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/gopool.go

@@ -3,8 +3,9 @@ package common
 import (
 	"context"
 	"fmt"
-	"github.com/bytedance/gopkg/util/gopool"
 	"math"
+
+	"github.com/bytedance/gopkg/util/gopool"
 )
 
 var relayGoPool gopool.Pool

common/init.go

@@ -4,11 +4,14 @@ import (
 	"flag"
 	"fmt"
 	"log"
-	"one-api/constant"
+	"net/http"
 	"os"
 	"path/filepath"
 	"strconv"
+	"strings"
 	"time"
+
+	"github.com/QuantumNous/new-api/constant"
 )
 
 var (
@@ -19,15 +22,20 @@ var (
 )
 
 func printHelp() {
-	fmt.Println("New API " + Version + " - All in one API service for OpenAI API.")
-	fmt.Println("Copyright (C) 2023 JustSong. All rights reserved.")
-	fmt.Println("GitHub: https://github.com/songquanpeng/one-api")
-	fmt.Println("Usage: one-api [--port <port>] [--log-dir <log directory>] [--version] [--help]")
+	fmt.Println("NewAPI(Based OneAPI) " + Version + " - The next-generation LLM gateway and AI asset management system supports multiple languages.")
+	fmt.Println("Original Project: OneAPI by JustSong - https://github.com/songquanpeng/one-api")
+	fmt.Println("Maintainer: QuantumNous - https://github.com/QuantumNous/new-api")
+	fmt.Println("Usage: newapi [--port <port>] [--log-dir <log directory>] [--version] [--help]")
 }
 
 func InitEnv() {
 	flag.Parse()
 
+	envVersion := os.Getenv("VERSION")
+	if envVersion != "" {
+		Version = envVersion
+	}
+
 	if *PrintVersion {
 		fmt.Println(Version)
 		os.Exit(0)
@@ -74,6 +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"))
@@ -83,6 +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")
@@ -97,17 +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)
@@ -117,4 +144,32 @@ 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 != "" {
+		var taskPricePatches []string
+		soraPatches := strings.Split(soraPatchStr, ",")
+		for _, patch := range soraPatches {
+			trimmedPatch := strings.TrimSpace(patch)
+			if trimmedPatch != "" {
+				taskPricePatches = append(taskPricePatches, trimmedPatch)
+			}
+		}
+		constant.TaskPricePatches = taskPricePatches
+	}
+
+	// Initialize trusted redirect domains for URL validation
+	trustedDomainsStr := GetEnvOrDefaultString("TRUSTED_REDIRECT_DOMAINS", "")
+	var trustedDomains []string
+	domains := strings.Split(trustedDomainsStr, ",")
+	for _, domain := range domains {
+		trimmedDomain := strings.TrimSpace(domain)
+		if trimmedDomain != "" {
+			// Normalize domain to lowercase
+			trustedDomains = append(trustedDomains, strings.ToLower(trimmedDomain))
+		}
+	}
+	constant.TrustedRedirectDomains = trustedDomains
 }

common/ip.go

@@ -0,0 +1,51 @@
+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
+	}
+
+	private := []net.IPNet{
+		{IP: net.IPv4(10, 0, 0, 0), Mask: net.CIDRMask(8, 32)},
+		{IP: net.IPv4(172, 16, 0, 0), Mask: net.CIDRMask(12, 32)},
+		{IP: net.IPv4(192, 168, 0, 0), Mask: net.CIDRMask(16, 32)},
+	}
+
+	for _, privateNet := range private {
+		if privateNet.Contains(ip) {
+			return true
+		}
+	}
+	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

@@ -3,6 +3,7 @@ package common
 import (
 	"bytes"
 	"encoding/json"
+	"io"
 )
 
 func Unmarshal(data []byte, v any) error {
@@ -13,7 +14,7 @@ func UnmarshalJsonStr(data string, v any) error {
 	return json.Unmarshal(StringToByteSlice(data), v)
 }
 
-func DecodeJson(reader *bytes.Reader, v any) error {
+func DecodeJson(reader io.Reader, v any) error {
 	return json.NewDecoder(reader).Decode(v)
 }
 
@@ -22,11 +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/limiter/limiter.go

@@ -4,9 +4,10 @@ import (
 	"context"
 	_ "embed"
 	"fmt"
-	"github.com/go-redis/redis/v8"
-	"one-api/common"
 	"sync"
+
+	"github.com/QuantumNous/new-api/common"
+	"github.com/go-redis/redis/v8"
 )
 
 //go:embed lua/rate_limit.lua

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/pprof.go

@@ -2,10 +2,11 @@ package common
 
 import (
 	"fmt"
-	"github.com/shirou/gopsutil/cpu"
 	"os"
 	"runtime/pprof"
 	"time"
+
+	"github.com/shirou/gopsutil/cpu"
 )
 
 // Monitor 定时监控cpu使用率，超过阈值输出pprof文件

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

@@ -0,0 +1,311 @@
+package common
+
+import (
+	"fmt"
+	"net"
+	"net/url"
+	"strconv"
+	"strings"
+)
+
+// SSRFProtection SSRF防护配置
+type SSRFProtection struct {
+	AllowPrivateIp         bool
+	DomainFilterMode       bool     // true: 白名单, false: 黑名单
+	DomainList             []string // domain format, e.g. example.com, *.example.com
+	IpFilterMode           bool     // true: 白名单, false: 黑名单
+	IpList                 []string // CIDR or single IP
+	AllowedPorts           []int    // 允许的端口范围
+	ApplyIPFilterForDomain bool     // 对域名启用IP过滤
+}
+
+// DefaultSSRFProtection 默认SSRF防护配置
+var DefaultSSRFProtection = &SSRFProtection{
+	AllowPrivateIp:   false,
+	DomainFilterMode: true,
+	DomainList:       []string{},
+	IpFilterMode:     true,
+	IpList:           []string{},
+	AllowedPorts:     []int{},
+}
+
+// isPrivateIP 检查IP是否为私有地址
+func isPrivateIP(ip net.IP) bool {
+	if ip.IsLoopback() || ip.IsLinkLocalUnicast() || ip.IsLinkLocalMulticast() {
+		return true
+	}
+
+	// 检查私有网段
+	private := []net.IPNet{
+		{IP: net.IPv4(10, 0, 0, 0), Mask: net.CIDRMask(8, 32)},     // 10.0.0.0/8
+		{IP: net.IPv4(172, 16, 0, 0), Mask: net.CIDRMask(12, 32)},  // 172.16.0.0/12
+		{IP: net.IPv4(192, 168, 0, 0), Mask: net.CIDRMask(16, 32)}, // 192.168.0.0/16
+		{IP: net.IPv4(127, 0, 0, 0), Mask: net.CIDRMask(8, 32)},    // 127.0.0.0/8
+		{IP: net.IPv4(169, 254, 0, 0), Mask: net.CIDRMask(16, 32)}, // 169.254.0.0/16 (链路本地)
+		{IP: net.IPv4(224, 0, 0, 0), Mask: net.CIDRMask(4, 32)},    // 224.0.0.0/4 (组播)
+		{IP: net.IPv4(240, 0, 0, 0), Mask: net.CIDRMask(4, 32)},    // 240.0.0.0/4 (保留)
+	}
+
+	for _, privateNet := range private {
+		if privateNet.Contains(ip) {
+			return true
+		}
+	}
+
+	// 检查IPv6私有地址
+	if ip.To4() == nil {
+		// IPv6 loopback
+		if ip.Equal(net.IPv6loopback) {
+			return true
+		}
+		// IPv6 link-local
+		if strings.HasPrefix(ip.String(), "fe80:") {
+			return true
+		}
+		// IPv6 unique local
+		if strings.HasPrefix(ip.String(), "fc") || strings.HasPrefix(ip.String(), "fd") {
+			return true
+		}
+	}
+
+	return false
+}
+
+// parsePortRanges 解析端口范围配置
+// 支持格式: "80", "443", "8000-9000"
+func parsePortRanges(portConfigs []string) ([]int, error) {
+	var ports []int
+
+	for _, config := range portConfigs {
+		config = strings.TrimSpace(config)
+		if config == "" {
+			continue
+		}
+
+		if strings.Contains(config, "-") {
+			// 处理端口范围 "8000-9000"
+			parts := strings.Split(config, "-")
+			if len(parts) != 2 {
+				return nil, fmt.Errorf("invalid port range format: %s", config)
+			}
+
+			startPort, err := strconv.Atoi(strings.TrimSpace(parts[0]))
+			if err != nil {
+				return nil, fmt.Errorf("invalid start port in range %s: %v", config, err)
+			}
+
+			endPort, err := strconv.Atoi(strings.TrimSpace(parts[1]))
+			if err != nil {
+				return nil, fmt.Errorf("invalid end port in range %s: %v", config, err)
+			}
+
+			if startPort > endPort {
+				return nil, fmt.Errorf("invalid port range %s: start port cannot be greater than end port", config)
+			}
+
+			if startPort < 1 || startPort > 65535 || endPort < 1 || endPort > 65535 {
+				return nil, fmt.Errorf("port range %s contains invalid port numbers (must be 1-65535)", config)
+			}
+
+			// 添加范围内的所有端口
+			for port := startPort; port <= endPort; port++ {
+				ports = append(ports, port)
+			}
+		} else {
+			// 处理单个端口 "80"
+			port, err := strconv.Atoi(config)
+			if err != nil {
+				return nil, fmt.Errorf("invalid port number: %s", config)
+			}
+
+			if port < 1 || port > 65535 {
+				return nil, fmt.Errorf("invalid port number %d (must be 1-65535)", port)
+			}
+
+			ports = append(ports, port)
+		}
+	}
+
+	return ports, nil
+}
+
+// isAllowedPort 检查端口是否被允许
+func (p *SSRFProtection) isAllowedPort(port int) bool {
+	if len(p.AllowedPorts) == 0 {
+		return true // 如果没有配置端口限制，则允许所有端口
+	}
+
+	for _, allowedPort := range p.AllowedPorts {
+		if port == allowedPort {
+			return true
+		}
+	}
+	return false
+}
+
+// isDomainWhitelisted 检查域名是否在白名单中
+func isDomainListed(domain string, list []string) bool {
+	if len(list) == 0 {
+		return false
+	}
+
+	domain = strings.ToLower(domain)
+	for _, item := range list {
+		item = strings.ToLower(strings.TrimSpace(item))
+		if item == "" {
+			continue
+		}
+		// 精确匹配
+		if domain == item {
+			return true
+		}
+		// 通配符匹配 (*.example.com)
+		if strings.HasPrefix(item, "*.") {
+			suffix := strings.TrimPrefix(item, "*.")
+			if strings.HasSuffix(domain, "."+suffix) || domain == suffix {
+				return true
+			}
+		}
+	}
+	return false
+}
+
+func (p *SSRFProtection) isDomainAllowed(domain string) bool {
+	listed := isDomainListed(domain, p.DomainList)
+	if p.DomainFilterMode { // 白名单
+		return listed
+	}
+	// 黑名单
+	return !listed
+}
+
+// isIPWhitelisted 检查IP是否在白名单中
+
+func isIPListed(ip net.IP, list []string) bool {
+	if len(list) == 0 {
+		return false
+	}
+
+	return IsIpInCIDRList(ip, list)
+}
+
+// IsIPAccessAllowed 检查IP是否允许访问
+func (p *SSRFProtection) IsIPAccessAllowed(ip net.IP) bool {
+	// 私有IP限制
+	if isPrivateIP(ip) && !p.AllowPrivateIp {
+		return false
+	}
+
+	listed := isIPListed(ip, p.IpList)
+	if p.IpFilterMode { // 白名单
+		return listed
+	}
+	// 黑名单
+	return !listed
+}
+
+// ValidateURL 验证URL是否安全
+func (p *SSRFProtection) ValidateURL(urlStr string) error {
+	// 解析URL
+	u, err := url.Parse(urlStr)
+	if err != nil {
+		return fmt.Errorf("invalid URL format: %v", err)
+	}
+
+	// 只允许HTTP/HTTPS协议
+	if u.Scheme != "http" && u.Scheme != "https" {
+		return fmt.Errorf("unsupported protocol: %s (only http/https allowed)", u.Scheme)
+	}
+
+	// 解析主机和端口
+	host, portStr, err := net.SplitHostPort(u.Host)
+	if err != nil {
+		// 没有端口，使用默认端口
+		host = u.Hostname()
+		if u.Scheme == "https" {
+			portStr = "443"
+		} else {
+			portStr = "80"
+		}
+	}
+
+	// 验证端口
+	port, err := strconv.Atoi(portStr)
+	if err != nil {
+		return fmt.Errorf("invalid port: %s", portStr)
+	}
+
+	if !p.isAllowedPort(port) {
+		return fmt.Errorf("port %d is not allowed", port)
+	}
+
+	// 如果 host 是 IP，则跳过域名检查
+	if ip := net.ParseIP(host); ip != nil {
+		if !p.IsIPAccessAllowed(ip) {
+			if isPrivateIP(ip) {
+				return fmt.Errorf("private IP address not allowed: %s", ip.String())
+			}
+			if p.IpFilterMode {
+				return fmt.Errorf("ip not in whitelist: %s", ip.String())
+			}
+			return fmt.Errorf("ip in blacklist: %s", ip.String())
+		}
+		return nil
+	}
+
+	// 先进行域名过滤
+	if !p.isDomainAllowed(host) {
+		if p.DomainFilterMode {
+			return fmt.Errorf("domain not in whitelist: %s", host)
+		}
+		return fmt.Errorf("domain in blacklist: %s", host)
+	}
+
+	// 若未启用对域名应用IP过滤，则到此通过
+	if !p.ApplyIPFilterForDomain {
+		return nil
+	}
+
+	// 解析域名对应IP并检查
+	ips, err := net.LookupIP(host)
+	if err != nil {
+		return fmt.Errorf("DNS resolution failed for %s: %v", host, err)
+	}
+	for _, ip := range ips {
+		if !p.IsIPAccessAllowed(ip) {
+			if isPrivateIP(ip) && !p.AllowPrivateIp {
+				return fmt.Errorf("private IP address not allowed: %s resolves to %s", host, ip.String())
+			}
+			if p.IpFilterMode {
+				return fmt.Errorf("ip not in whitelist: %s resolves to %s", host, ip.String())
+			}
+			return fmt.Errorf("ip in blacklist: %s resolves to %s", host, ip.String())
+		}
+	}
+	return nil
+}
+
+// ValidateURLWithFetchSetting 使用FetchSetting配置验证URL
+func ValidateURLWithFetchSetting(urlStr string, enableSSRFProtection, allowPrivateIp bool, domainFilterMode bool, ipFilterMode bool, domainList, ipList, allowedPorts []string, applyIPFilterForDomain bool) error {
+	// 如果SSRF防护被禁用，直接返回成功
+	if !enableSSRFProtection {
+		return nil
+	}
+
+	// 解析端口范围配置
+	allowedPortInts, err := parsePortRanges(allowedPorts)
+	if err != nil {
+		return fmt.Errorf("request reject - invalid port configuration: %v", err)
+	}
+
+	protection := &SSRFProtection{
+		AllowPrivateIp:         allowPrivateIp,
+		DomainFilterMode:       domainFilterMode,
+		DomainList:             domainList,
+		IpFilterMode:           ipFilterMode,
+		IpList:                 ipList,
+		AllowedPorts:           allowedPortInts,
+		ApplyIPFilterForDomain: applyIPFilterForDomain,
+	}
+	return protection.ValidateURL(urlStr)
+}

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 {
@@ -99,6 +106,16 @@ func GetJsonString(data any) string {
 	return string(b)
 }
 
+// NormalizeBillingPreference clamps the billing preference to valid values.
+func NormalizeBillingPreference(pref string) string {
+	switch strings.TrimSpace(pref) {
+	case "subscription_first", "wallet_first", "subscription_only", "wallet_only":
+		return strings.TrimSpace(pref)
+	default:
+		return "subscription_first"
+	}
+}
+
 // MaskEmail masks a user email to prevent PII leakage in logs
 // Returns "***masked***" if email is empty, otherwise shows only the domain part
 func MaskEmail(email string) string {
@@ -170,8 +187,7 @@ 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 +240,15 @@ 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/sys_log.go

@@ -2,9 +2,10 @@ package common
 
 import (
 	"fmt"
-	"github.com/gin-gonic/gin"
 	"os"
 	"time"
+
+	"github.com/gin-gonic/gin"
 )
 
 func SysLog(s string) {
@@ -22,3 +23,33 @@ func FatalLog(v ...any) {
 	_, _ = fmt.Fprintf(gin.DefaultErrorWriter, "[FATAL] %v | %v \n", t.Format("2006/01/02 - 15:04:05"), v)
 	os.Exit(1)
 }
+
+func LogStartupSuccess(startTime time.Time, port string) {
+
+	duration := time.Since(startTime)
+	durationMs := duration.Milliseconds()
+
+	// Get network IPs
+	networkIps := GetNetworkIps()
+
+	// Print blank line for spacing
+	fmt.Fprintf(gin.DefaultWriter, "\n")
+
+	// Print the main success message
+	fmt.Fprintf(gin.DefaultWriter, "  \033[32m%s %s\033[0m  ready in %d ms\n", SystemName, Version, durationMs)
+	fmt.Fprintf(gin.DefaultWriter, "\n")
+
+	// Skip fancy startup message in container environments
+	if !IsRunningInContainer() {
+		// Print local URL
+		fmt.Fprintf(gin.DefaultWriter, "  ➜  \033[1mLocal:\033[0m   http://localhost:%s/\n", port)
+	}
+
+	// Print network URLs
+	for _, ip := range networkIps {
+		fmt.Fprintf(gin.DefaultWriter, "  ➜  \033[1mNetwork:\033[0m http://%s:%s/\n", ip, port)
+	}
+
+	// Print blank line for spacing
+	fmt.Fprintf(gin.DefaultWriter, "\n")
+}

common/url_validator.go

@@ -0,0 +1,39 @@
+package common
+
+import (
+	"fmt"
+	"net/url"
+	"strings"
+
+	"github.com/QuantumNous/new-api/constant"
+)
+
+// ValidateRedirectURL validates that a redirect URL is safe to use.
+// It checks that:
+//   - The URL is properly formatted
+//   - The scheme is either http or https
+//   - The domain is in the trusted domains list (exact match or subdomain)
+//
+// Returns nil if the URL is valid and trusted, otherwise returns an error
+// describing why the validation failed.
+func ValidateRedirectURL(rawURL string) error {
+	// Parse the URL
+	parsedURL, err := url.Parse(rawURL)
+	if err != nil {
+		return fmt.Errorf("invalid URL format: %s", err.Error())
+	}
+
+	if parsedURL.Scheme != "http" && parsedURL.Scheme != "https" {
+		return fmt.Errorf("invalid URL scheme: only http and https are allowed")
+	}
+
+	domain := strings.ToLower(parsedURL.Hostname())
+
+	for _, trustedDomain := range constant.TrustedRedirectDomains {
+		if domain == trustedDomain || strings.HasSuffix(domain, "."+trustedDomain) {
+			return nil
+		}
+	}
+
+	return fmt.Errorf("domain %s is not in the trusted domains list", domain)
+}

common/url_validator_test.go

@@ -0,0 +1,134 @@
+package common
+
+import (
+	"testing"
+
+	"github.com/QuantumNous/new-api/constant"
+)
+
+func TestValidateRedirectURL(t *testing.T) {
+	// Save original trusted domains and restore after test
+	originalDomains := constant.TrustedRedirectDomains
+	defer func() {
+		constant.TrustedRedirectDomains = originalDomains
+	}()
+
+	tests := []struct {
+		name           string
+		url            string
+		trustedDomains []string
+		wantErr        bool
+		errContains    string
+	}{
+		// Valid cases
+		{
+			name:           "exact domain match with https",
+			url:            "https://example.com/success",
+			trustedDomains: []string{"example.com"},
+			wantErr:        false,
+		},
+		{
+			name:           "exact domain match with http",
+			url:            "http://example.com/callback",
+			trustedDomains: []string{"example.com"},
+			wantErr:        false,
+		},
+		{
+			name:           "subdomain match",
+			url:            "https://sub.example.com/success",
+			trustedDomains: []string{"example.com"},
+			wantErr:        false,
+		},
+		{
+			name:           "case insensitive domain",
+			url:            "https://EXAMPLE.COM/success",
+			trustedDomains: []string{"example.com"},
+			wantErr:        false,
+		},
+
+		// Invalid cases - untrusted domain
+		{
+			name:           "untrusted domain",
+			url:            "https://evil.com/phishing",
+			trustedDomains: []string{"example.com"},
+			wantErr:        true,
+			errContains:    "not in the trusted domains list",
+		},
+		{
+			name:           "suffix attack - fakeexample.com",
+			url:            "https://fakeexample.com/success",
+			trustedDomains: []string{"example.com"},
+			wantErr:        true,
+			errContains:    "not in the trusted domains list",
+		},
+		{
+			name:           "empty trusted domains list",
+			url:            "https://example.com/success",
+			trustedDomains: []string{},
+			wantErr:        true,
+			errContains:    "not in the trusted domains list",
+		},
+
+		// Invalid cases - scheme
+		{
+			name:           "javascript scheme",
+			url:            "javascript:alert('xss')",
+			trustedDomains: []string{"example.com"},
+			wantErr:        true,
+			errContains:    "invalid URL scheme",
+		},
+		{
+			name:           "data scheme",
+			url:            "data:text/html,<script>alert('xss')</script>",
+			trustedDomains: []string{"example.com"},
+			wantErr:        true,
+			errContains:    "invalid URL scheme",
+		},
+
+		// Edge cases
+		{
+			name:           "empty URL",
+			url:            "",
+			trustedDomains: []string{"example.com"},
+			wantErr:        true,
+			errContains:    "invalid URL scheme",
+		},
+	}
+
+	for _, tt := range tests {
+		t.Run(tt.name, func(t *testing.T) {
+			// Set up trusted domains for this test case
+			constant.TrustedRedirectDomains = tt.trustedDomains
+
+			err := ValidateRedirectURL(tt.url)
+
+			if tt.wantErr {
+				if err == nil {
+					t.Errorf("ValidateRedirectURL(%q) expected error containing %q, got nil", tt.url, tt.errContains)
+					return
+				}
+				if tt.errContains != "" && !contains(err.Error(), tt.errContains) {
+					t.Errorf("ValidateRedirectURL(%q) error = %q, want error containing %q", tt.url, err.Error(), tt.errContains)
+				}
+			} else {
+				if err != nil {
+					t.Errorf("ValidateRedirectURL(%q) unexpected error: %v", tt.url, err)
+				}
+			}
+		})
+	}
+}
+
+func contains(s, substr string) bool {
+	return len(s) >= len(substr) && (s == substr || len(substr) == 0 ||
+		(len(s) > 0 && len(substr) > 0 && findSubstring(s, substr)))
+}
+
+func findSubstring(s, substr string) bool {
+	for i := 0; i <= len(s)-len(substr); i++ {
+		if s[i:i+len(substr)] == substr {
+			return true
+		}
+	}
+	return false
+}

common/utils.go

@@ -1,8 +1,6 @@
 package common
 
 import (
-	"bytes"
-	"context"
 	crand "crypto/rand"
 	"encoding/base64"
 	"encoding/json"
@@ -68,6 +66,78 @@ func GetIp() (ip string) {
 	return
 }
 
+func GetNetworkIps() []string {
+	var networkIps []string
+	ips, err := net.InterfaceAddrs()
+	if err != nil {
+		log.Println(err)
+		return networkIps
+	}
+
+	for _, a := range ips {
+		if ipNet, ok := a.(*net.IPNet); ok && !ipNet.IP.IsLoopback() {
+			if ipNet.IP.To4() != nil {
+				ip := ipNet.IP.String()
+				// Include common private network ranges
+				if strings.HasPrefix(ip, "10.") ||
+					strings.HasPrefix(ip, "172.") ||
+					strings.HasPrefix(ip, "192.168.") {
+					networkIps = append(networkIps, ip)
+				}
+			}
+		}
+	}
+	return networkIps
+}
+
+// IsRunningInContainer detects if the application is running inside a container
+func IsRunningInContainer() bool {
+	// Method 1: Check for .dockerenv file (Docker containers)
+	if _, err := os.Stat("/.dockerenv"); err == nil {
+		return true
+	}
+
+	// Method 2: Check cgroup for container indicators
+	if data, err := os.ReadFile("/proc/1/cgroup"); err == nil {
+		content := string(data)
+		if strings.Contains(content, "docker") ||
+			strings.Contains(content, "containerd") ||
+			strings.Contains(content, "kubepods") ||
+			strings.Contains(content, "/lxc/") {
+			return true
+		}
+	}
+
+	// Method 3: Check environment variables commonly set by container runtimes
+	containerEnvVars := []string{
+		"KUBERNETES_SERVICE_HOST",
+		"DOCKER_CONTAINER",
+		"container",
+	}
+
+	for _, envVar := range containerEnvVars {
+		if os.Getenv(envVar) != "" {
+			return true
+		}
+	}
+
+	// Method 4: Check if init process is not the traditional init
+	if data, err := os.ReadFile("/proc/1/comm"); err == nil {
+		comm := strings.TrimSpace(string(data))
+		// In containers, process 1 is often not "init" or "systemd"
+		if comm != "init" && comm != "systemd" {
+			// Additional check: if it's a common container entrypoint
+			if strings.Contains(comm, "docker") ||
+				strings.Contains(comm, "containerd") ||
+				strings.Contains(comm, "runc") {
+				return true
+			}
+		}
+	}
+
+	return false
+}
+
 var sizeKB = 1024
 var sizeMB = sizeKB * 1024
 var sizeGB = sizeMB * 1024
@@ -123,8 +193,16 @@ func Interface2String(inter interface{}) string {
 		return fmt.Sprintf("%d", inter.(int))
 	case float64:
 		return fmt.Sprintf("%f", inter.(float64))
+	case bool:
+		if inter.(bool) {
+			return "true"
+		} else {
+			return "false"
+		}
+	case nil:
+		return ""
 	}
-	return "Not Implemented"
+	return fmt.Sprintf("%v", inter)
 }
 
 func UnescapeHTML(x string) interface{} {
@@ -139,11 +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)
@@ -152,10 +225,6 @@ func GetUUID() string {
 
 const keyChars = "0123456789abcdefghijklmnopqrstuvwxyzABCDEFGHIJKLMNOPQRSTUVWXYZ"
 
-func init() {
-	rand.New(rand.NewSource(time.Now().UnixNano()))
-}
-
 func GenerateRandomCharsKey(length int) (string, error) {
 	b := make([]byte, length)
 	maxI := big.NewInt(int64(len(keyChars)))
@@ -194,7 +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)
 }
 
@@ -249,43 +318,6 @@ func SaveTmpFile(filename string, data io.Reader) (string, error) {
 	return f.Name(), nil
 }
 
-// GetAudioDuration returns the duration of an audio file in seconds.
-func GetAudioDuration(ctx context.Context, filename string, ext string) (float64, error) {
-	// ffprobe -v error -show_entries format=duration -of default=noprint_wrappers=1:nokey=1 {{input}}
-	c := exec.CommandContext(ctx, "ffprobe", "-v", "error", "-show_entries", "format=duration", "-of", "default=noprint_wrappers=1:nokey=1", filename)
-	output, err := c.Output()
-	if err != nil {
-		return 0, errors.Wrap(err, "failed to get audio duration")
-	}
-  durationStr := string(bytes.TrimSpace(output))
-  if durationStr == "N/A" {
-    // Create a temporary output file name
-    tmpFp, err := os.CreateTemp("", "audio-*"+ext)
-    if err != nil {
-      return 0, errors.Wrap(err, "failed to create temporary file")
-    }
-    tmpName := tmpFp.Name()
-    // Close immediately so ffmpeg can open the file on Windows.
-    _ = tmpFp.Close()
-    defer os.Remove(tmpName)
-
-    // ffmpeg -y -i filename -vcodec copy -acodec copy <tmpName>
-    ffmpegCmd := exec.CommandContext(ctx, "ffmpeg", "-y", "-i", filename, "-vcodec", "copy", "-acodec", "copy", tmpName)
-    if err := ffmpegCmd.Run(); err != nil {
-      return 0, errors.Wrap(err, "failed to run ffmpeg")
-    }
-
-    // Recalculate the duration of the new file
-    c = exec.CommandContext(ctx, "ffprobe", "-v", "error", "-show_entries", "format=duration", "-of", "default=noprint_wrappers=1:nokey=1", tmpName)
-    output, err := c.Output()
-    if err != nil {
-      return 0, errors.Wrap(err, "failed to get audio duration after ffmpeg")
-    }
-    durationStr = string(bytes.TrimSpace(output))
-  }
-	return strconv.ParseFloat(durationStr, 64)
-}
-
 // BuildURL concatenates base and endpoint, returns the complete url string
 func BuildURL(base string, endpoint string) string {
 	u, err := url.Parse(base)

common/verification.go

@@ -1,10 +1,11 @@
 package common
 
 import (
-	"github.com/google/uuid"
 	"strings"
 	"sync"
 	"time"
+
+	"github.com/google/uuid"
 )
 
 type verificationValue struct {

constant/api_type.go

@@ -31,6 +31,10 @@ const (
 	APITypeXai
 	APITypeCoze
 	APITypeJimeng
-	APITypeMoonshot // this one is only for count, do not add any channel after this
-	APITypeDummy    // this one is only for count, do not add any channel after this
+	APITypeMoonshot
+	APITypeSubmodel
+	APITypeMiniMax
+	APITypeReplicate
+	APITypeCodex
+	APITypeDummy // this one is only for count, do not add any channel after this
 )

constant/channel.go

@@ -50,6 +50,11 @@ const (
 	ChannelTypeKling          = 50
 	ChannelTypeJimeng         = 51
 	ChannelTypeVidu           = 52
+	ChannelTypeSubmodel       = 53
+	ChannelTypeDoubaoVideo    = 54
+	ChannelTypeSora           = 55
+	ChannelTypeReplicate      = 56
+	ChannelTypeCodex          = 57
 	ChannelTypeDummy          // this one is only for count, do not add any channel after this
 
 )
@@ -108,4 +113,97 @@ var ChannelBaseURLs = []string{
 	"https://api.klingai.com",                   //50
 	"https://visual.volcengineapi.com",          //51
 	"https://api.vidu.cn",                       //52
+	"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{
+	ChannelTypeUnknown:        "Unknown",
+	ChannelTypeOpenAI:         "OpenAI",
+	ChannelTypeMidjourney:     "Midjourney",
+	ChannelTypeAzure:          "Azure",
+	ChannelTypeOllama:         "Ollama",
+	ChannelTypeMidjourneyPlus: "MidjourneyPlus",
+	ChannelTypeOpenAIMax:      "OpenAIMax",
+	ChannelTypeOhMyGPT:        "OhMyGPT",
+	ChannelTypeCustom:         "Custom",
+	ChannelTypeAILS:           "AILS",
+	ChannelTypeAIProxy:        "AIProxy",
+	ChannelTypePaLM:           "PaLM",
+	ChannelTypeAPI2GPT:        "API2GPT",
+	ChannelTypeAIGC2D:         "AIGC2D",
+	ChannelTypeAnthropic:      "Anthropic",
+	ChannelTypeBaidu:          "Baidu",
+	ChannelTypeZhipu:          "Zhipu",
+	ChannelTypeAli:            "Ali",
+	ChannelTypeXunfei:         "Xunfei",
+	ChannelType360:            "360",
+	ChannelTypeOpenRouter:     "OpenRouter",
+	ChannelTypeAIProxyLibrary: "AIProxyLibrary",
+	ChannelTypeFastGPT:        "FastGPT",
+	ChannelTypeTencent:        "Tencent",
+	ChannelTypeGemini:         "Gemini",
+	ChannelTypeMoonshot:       "Moonshot",
+	ChannelTypeZhipu_v4:       "ZhipuV4",
+	ChannelTypePerplexity:     "Perplexity",
+	ChannelTypeLingYiWanWu:    "LingYiWanWu",
+	ChannelTypeAws:            "AWS",
+	ChannelTypeCohere:         "Cohere",
+	ChannelTypeMiniMax:        "MiniMax",
+	ChannelTypeSunoAPI:        "SunoAPI",
+	ChannelTypeDify:           "Dify",
+	ChannelTypeJina:           "Jina",
+	ChannelCloudflare:         "Cloudflare",
+	ChannelTypeSiliconFlow:    "SiliconFlow",
+	ChannelTypeVertexAi:       "VertexAI",
+	ChannelTypeMistral:        "Mistral",
+	ChannelTypeDeepSeek:       "DeepSeek",
+	ChannelTypeMokaAI:         "MokaAI",
+	ChannelTypeVolcEngine:     "VolcEngine",
+	ChannelTypeBaiduV2:        "BaiduV2",
+	ChannelTypeXinference:     "Xinference",
+	ChannelTypeXai:            "xAI",
+	ChannelTypeCoze:           "Coze",
+	ChannelTypeKling:          "Kling",
+	ChannelTypeJimeng:         "Jimeng",
+	ChannelTypeVidu:           "Vidu",
+	ChannelTypeSubmodel:       "Submodel",
+	ChannelTypeDoubaoVideo:    "DoubaoVideo",
+	ChannelTypeSora:           "Sora",
+	ChannelTypeReplicate:      "Replicate",
+	ChannelTypeCodex:          "Codex",
+}
+
+func GetChannelTypeName(channelType int) string {
+	if name, ok := ChannelTypeNames[channelType]; ok {
+		return name
+	}
+	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

@@ -3,12 +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"
+	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

@@ -3,13 +3,24 @@ 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
+
+// TrustedRedirectDomains is a list of trusted domains for redirect URL validation.
+// Domains support subdomain matching (e.g., "example.com" matches "sub.example.com").
+var TrustedRedirectDomains []string

constant/task.go

@@ -11,8 +11,11 @@ const (
 	SunoActionMusic  = "MUSIC"
 	SunoActionLyrics = "LYRICS"
 
-	TaskActionGenerate     = "generate"
-	TaskActionTextGenerate = "textGenerate"
+	TaskActionGenerate          = "generate"
+	TaskActionTextGenerate      = "textGenerate"
+	TaskActionFirstTailGenerate = "firstTailGenerate"
+	TaskActionReferenceGenerate = "referenceGenerate"
+	TaskActionRemix             = "remixGenerate"
 )
 
 var SunoModel2Action = map[string]string{

controller/billing.go

@@ -1,10 +1,11 @@
 package controller
 
 import (
+	"github.com/QuantumNous/new-api/common"
+	"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"
-	"one-api/common"
-	"one-api/dto"
-	"one-api/model"
 )
 
 func GetSubscription(c *gin.Context) {
@@ -28,7 +29,7 @@ func GetSubscription(c *gin.Context) {
 		expiredTime = 0
 	}
 	if err != nil {
-		openAIError := dto.OpenAIError{
+		openAIError := types.OpenAIError{
 			Message: err.Error(),
 			Type:    "upstream_error",
 		}
@@ -39,8 +40,18 @@ func GetSubscription(c *gin.Context) {
 	}
 	quota := remainQuota + usedQuota
 	amount := float64(quota)
-	if common.DisplayInCurrencyEnabled {
-		amount /= common.QuotaPerUnit
+	// OpenAI 兼容接口中的 *_USD 字段含义保持“额度单位”对应值：
+	// 我们将其解释为以“站点展示类型”为准：
+	// - USD: 直接除以 QuotaPerUnit
+	// - CNY: 先转 USD 再乘汇率
+	// - TOKENS: 直接使用 tokens 数量
+	switch operation_setting.GetQuotaDisplayType() {
+	case operation_setting.QuotaDisplayTypeCNY:
+		amount = amount / common.QuotaPerUnit * operation_setting.USDExchangeRate
+	case operation_setting.QuotaDisplayTypeTokens:
+		// amount 保持 tokens 数值
+	default:
+		amount = amount / common.QuotaPerUnit
 	}
 	if token != nil && token.UnlimitedQuota {
 		amount = 100000000
@@ -70,7 +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",
 		}
@@ -80,8 +91,13 @@ func GetUsage(c *gin.Context) {
 		return
 	}
 	amount := float64(quota)
-	if common.DisplayInCurrencyEnabled {
-		amount /= common.QuotaPerUnit
+	switch operation_setting.GetQuotaDisplayType() {
+	case operation_setting.QuotaDisplayTypeCNY:
+		amount = amount / common.QuotaPerUnit * operation_setting.USDExchangeRate
+	case operation_setting.QuotaDisplayTypeTokens:
+		// tokens 保持原值
+	default:
+		amount = amount / common.QuotaPerUnit
 	}
 	usage := OpenAIUsageResponse{
 		Object:     "list",

controller/channel-billing.go

@@ -6,15 +6,16 @@ import (
 	"fmt"
 	"io"
 	"net/http"
-	"one-api/common"
-	"one-api/constant"
-	"one-api/model"
-	"one-api/service"
-	"one-api/setting"
-	"one-api/types"
 	"strconv"
 	"time"
 
+	"github.com/QuantumNous/new-api/common"
+	"github.com/QuantumNous/new-api/constant"
+	"github.com/QuantumNous/new-api/model"
+	"github.com/QuantumNous/new-api/service"
+	"github.com/QuantumNous/new-api/setting/operation_setting"
+	"github.com/QuantumNous/new-api/types"
+
 	"github.com/shopspring/decimal"
 
 	"github.com/gin-gonic/gin"
@@ -127,6 +128,14 @@ func GetAuthHeader(token string) http.Header {
 	return h
 }
 
+// GetClaudeAuthHeader get claude auth header
+func GetClaudeAuthHeader(token string) http.Header {
+	h := http.Header{}
+	h.Add("x-api-key", token)
+	h.Add("anthropic-version", "2023-06-01")
+	return h
+}
+
 func GetResponseBody(method, url string, channel *model.Channel, headers http.Header) ([]byte, error) {
 	req, err := http.NewRequest(method, url, nil)
 	if err != nil {
@@ -342,7 +351,7 @@ func updateChannelMoonshotBalance(channel *model.Channel) (float64, error) {
 		return 0, fmt.Errorf("failed to update moonshot balance, status: %v, code: %d, scode: %s", response.Status, response.Code, response.Scode)
 	}
 	availableBalanceCny := response.Data.AvailableBalance
-	availableBalanceUsd := decimal.NewFromFloat(availableBalanceCny).Div(decimal.NewFromFloat(setting.Price)).InexactFloat64()
+	availableBalanceUsd := decimal.NewFromFloat(availableBalanceCny).Div(decimal.NewFromFloat(operation_setting.Price)).InexactFloat64()
 	channel.UpdateBalance(availableBalanceUsd)
 	return availableBalanceUsd, nil
 }

controller/channel-test.go

@@ -10,23 +10,27 @@ import (
 	"net/http"
 	"net/http/httptest"
 	"net/url"
-	"one-api/common"
-	"one-api/constant"
-	"one-api/dto"
-	"one-api/middleware"
-	"one-api/model"
-	"one-api/relay"
-	relaycommon "one-api/relay/common"
-	relayconstant "one-api/relay/constant"
-	"one-api/relay/helper"
-	"one-api/service"
-	"one-api/types"
 	"strconv"
 	"strings"
 	"sync"
 	"time"
 
+	"github.com/QuantumNous/new-api/common"
+	"github.com/QuantumNous/new-api/constant"
+	"github.com/QuantumNous/new-api/dto"
+	"github.com/QuantumNous/new-api/middleware"
+	"github.com/QuantumNous/new-api/model"
+	"github.com/QuantumNous/new-api/relay"
+	relaycommon "github.com/QuantumNous/new-api/relay/common"
+	relayconstant "github.com/QuantumNous/new-api/relay/constant"
+	"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"
+	"github.com/samber/lo"
 
 	"github.com/gin-gonic/gin"
 )
@@ -37,56 +41,81 @@ type testResult struct {
 	newAPIError *types.NewAPIError
 }
 
-func testChannel(channel *model.Channel, testModel string) testResult {
+func testChannel(channel *model.Channel, testModel string, endpointType string) testResult {
 	tik := time.Now()
-	if channel.Type == constant.ChannelTypeMidjourney {
-		return testResult{
-			localErr:    errors.New("midjourney channel test is not supported"),
-			newAPIError: nil,
-		}
+	var unsupportedTestChannelTypes = []int{
+		constant.ChannelTypeMidjourney,
+		constant.ChannelTypeMidjourneyPlus,
+		constant.ChannelTypeSunoAPI,
+		constant.ChannelTypeKling,
+		constant.ChannelTypeJimeng,
+		constant.ChannelTypeDoubaoVideo,
+		constant.ChannelTypeVidu,
 	}
-	if channel.Type == constant.ChannelTypeMidjourneyPlus {
+	if lo.Contains(unsupportedTestChannelTypes, channel.Type) {
+		channelTypeName := constant.GetChannelTypeName(channel.Type)
 		return testResult{
-			localErr:    errors.New("midjourney plus channel test is not supported"),
-			newAPIError: nil,
-		}
-	}
-	if channel.Type == constant.ChannelTypeSunoAPI {
-		return testResult{
-			localErr:    errors.New("suno channel test is not supported"),
-			newAPIError: nil,
-		}
-	}
-	if channel.Type == constant.ChannelTypeKling {
-		return testResult{
-			localErr:    errors.New("kling channel test is not supported"),
-			newAPIError: nil,
-		}
-	}
-	if channel.Type == constant.ChannelTypeJimeng {
-		return testResult{
-			localErr:    errors.New("jimeng channel test is not supported"),
-			newAPIError: nil,
-		}
-	}
-	if channel.Type == constant.ChannelTypeVidu {
-		return testResult{
-			localErr:    errors.New("vidu channel test is not supported"),
-			newAPIError: nil,
+			localErr: fmt.Errorf("%s channel test is not supported", channelTypeName),
 		}
 	}
 	w := httptest.NewRecorder()
 	c, _ := gin.CreateTestContext(w)
 
+	testModel = strings.TrimSpace(testModel)
+	if testModel == "" {
+		if channel.TestModel != nil && *channel.TestModel != "" {
+			testModel = strings.TrimSpace(*channel.TestModel)
+		} else {
+			models := channel.GetModels()
+			if len(models) > 0 {
+				testModel = strings.TrimSpace(models[0])
+			}
+			if testModel == "" {
+				testModel = "gpt-4o-mini"
+			}
+		}
+	}
+
 	requestPath := "/v1/chat/completions"
 
-	// 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
-		strings.Contains(testModel, "bge-") || // bge 系列模型
-		strings.Contains(testModel, "embed") ||
-		channel.Type == constant.ChannelTypeMokaAI { // 其他 embedding 模型
-		requestPath = "/v1/embeddings" // 修改请求路径
+	// 如果指定了端点类型，使用指定的端点类型
+	if endpointType != "" {
+		if endpointInfo, ok := common.GetDefaultEndpointInfo(constant.EndpointType(endpointType)); ok {
+			requestPath = endpointInfo.Path
+		}
+	} 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
+			strings.Contains(testModel, "bge-") || // bge 系列模型
+			strings.Contains(testModel, "embed") ||
+			channel.Type == constant.ChannelTypeMokaAI { // 其他 embedding 模型
+			requestPath = "/v1/embeddings" // 修改请求路径
+		}
+
+		// VolcEngine 图像生成模型
+		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{
@@ -96,18 +125,6 @@ func testChannel(channel *model.Channel, testModel string) testResult {
 		Header: make(http.Header),
 	}
 
-	if testModel == "" {
-		if channel.TestModel != nil && *channel.TestModel != "" {
-			testModel = *channel.TestModel
-		} else {
-			if len(channel.GetModels()) > 0 {
-				testModel = channel.GetModels()[0]
-			} else {
-				testModel = "gpt-4o-mini"
-			}
-		}
-	}
-
 	cache, err := model.GetUserCache(1)
 	if err != nil {
 		return testResult{
@@ -132,14 +149,59 @@ func testChannel(channel *model.Channel, testModel string) testResult {
 			newAPIError: newAPIError,
 		}
 	}
-	request := buildTestRequest(testModel)
 
-	// Determine relay format based on request path
-	relayFormat := types.RelayFormatOpenAI
-	if c.Request.URL.Path == "/v1/embeddings" {
-		relayFormat = types.RelayFormatEmbedding
+	// Determine relay format based on endpoint type or request path
+	var relayFormat types.RelayFormat
+	if endpointType != "" {
+		// 根据指定的端点类型设置 relayFormat
+		switch constant.EndpointType(endpointType) {
+		case constant.EndpointTypeOpenAI:
+			relayFormat = types.RelayFormatOpenAI
+		case constant.EndpointTypeOpenAIResponse:
+			relayFormat = types.RelayFormatOpenAIResponses
+		case constant.EndpointTypeOpenAIResponseCompact:
+			relayFormat = types.RelayFormatOpenAIResponsesCompaction
+		case constant.EndpointTypeAnthropic:
+			relayFormat = types.RelayFormatClaude
+		case constant.EndpointTypeGemini:
+			relayFormat = types.RelayFormatGemini
+		case constant.EndpointTypeJinaRerank:
+			relayFormat = types.RelayFormatRerank
+		case constant.EndpointTypeImageGeneration:
+			relayFormat = types.RelayFormatOpenAIImage
+		case constant.EndpointTypeEmbeddings:
+			relayFormat = types.RelayFormatEmbedding
+		default:
+			relayFormat = types.RelayFormatOpenAI
+		}
+	} else {
+		// 根据请求路径自动检测
+		relayFormat = types.RelayFormatOpenAI
+		if c.Request.URL.Path == "/v1/embeddings" {
+			relayFormat = types.RelayFormatEmbedding
+		}
+		if c.Request.URL.Path == "/v1/images/generations" {
+			relayFormat = types.RelayFormatOpenAIImage
+		}
+		if c.Request.URL.Path == "/v1/messages" {
+			relayFormat = types.RelayFormatClaude
+		}
+		if strings.Contains(c.Request.URL.Path, "/v1beta/models") {
+			relayFormat = types.RelayFormatGemini
+		}
+		if c.Request.URL.Path == "/v1/rerank" || c.Request.URL.Path == "/rerank" {
+			relayFormat = types.RelayFormatRerank
+		}
+		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, channel)
+
 	info, err := relaycommon.GenRelayInfo(c, relayFormat, request, nil)
 
 	if err != nil {
@@ -150,6 +212,7 @@ func testChannel(channel *model.Channel, testModel string) testResult {
 		}
 	}
 
+	info.IsChannelTest = true
 	info.InitChannelMeta(c)
 
 	err = helper.ModelMappedHelper(c, info, request)
@@ -162,9 +225,19 @@ func testChannel(channel *model.Channel, testModel string) testResult {
 	}
 
 	testModel = info.UpstreamModelName
-	request.Model = testModel
+	// 更新请求中的模型名称
+	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{
@@ -192,17 +265,81 @@ func testChannel(channel *model.Channel, testModel string) testResult {
 
 	var convertedRequest any
 	// 根据 RelayMode 选择正确的转换函数
-	if info.RelayMode == relayconstant.RelayModeEmbeddings {
-		// 创建一个 EmbeddingRequest
-		embeddingRequest := dto.EmbeddingRequest{
-			Input: request.Input,
-			Model: request.Model,
+	switch info.RelayMode {
+	case relayconstant.RelayModeEmbeddings:
+		// Embedding 请求 - request 已经是正确的类型
+		if embeddingReq, ok := request.(*dto.EmbeddingRequest); ok {
+			convertedRequest, err = adaptor.ConvertEmbeddingRequest(c, info, *embeddingReq)
+		} else {
+			return testResult{
+				context:     c,
+				localErr:    errors.New("invalid embedding request type"),
+				newAPIError: types.NewError(errors.New("invalid embedding request type"), types.ErrorCodeConvertRequestFailed),
+			}
+		}
+	case relayconstant.RelayModeImagesGenerations:
+		// 图像生成请求 - request 已经是正确的类型
+		if imageReq, ok := request.(*dto.ImageRequest); ok {
+			convertedRequest, err = adaptor.ConvertImageRequest(c, info, *imageReq)
+		} else {
+			return testResult{
+				context:     c,
+				localErr:    errors.New("invalid image request type"),
+				newAPIError: types.NewError(errors.New("invalid image request type"), types.ErrorCodeConvertRequestFailed),
+			}
+		}
+	case relayconstant.RelayModeRerank:
+		// Rerank 请求 - request 已经是正确的类型
+		if rerankReq, ok := request.(*dto.RerankRequest); ok {
+			convertedRequest, err = adaptor.ConvertRerankRequest(c, info.RelayMode, *rerankReq)
+		} else {
+			return testResult{
+				context:     c,
+				localErr:    errors.New("invalid rerank request type"),
+				newAPIError: types.NewError(errors.New("invalid rerank request type"), types.ErrorCodeConvertRequestFailed),
+			}
+		}
+	case relayconstant.RelayModeResponses:
+		// Response 请求 - request 已经是正确的类型
+		if responseReq, ok := request.(*dto.OpenAIResponsesRequest); ok {
+			convertedRequest, err = adaptor.ConvertOpenAIResponsesRequest(c, info, *responseReq)
+		} else {
+			return testResult{
+				context:     c,
+				localErr:    errors.New("invalid response request type"),
+				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 {
+			convertedRequest, err = adaptor.ConvertOpenAIRequest(c, info, generalReq)
+		} else {
+			return testResult{
+				context:     c,
+				localErr:    errors.New("invalid general request type"),
+				newAPIError: types.NewError(errors.New("invalid general request type"), types.ErrorCodeConvertRequestFailed),
+			}
 		}
-		// 调用专门用于 Embedding 的转换函数
-		convertedRequest, err = adaptor.ConvertEmbeddingRequest(c, info, embeddingRequest)
-	} else {
-		// 对其他所有请求类型（如 Chat），保持原有逻辑
-		convertedRequest, err = adaptor.ConvertOpenAIRequest(c, info, request)
 	}
 
 	if err != nil {
@@ -220,8 +357,29 @@ func testChannel(channel *model.Channel, testModel string) testResult {
 			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{
@@ -234,7 +392,17 @@ func testChannel(channel *model.Channel, testModel string) testResult {
 	if resp != nil {
 		httpResp = resp.(*http.Response)
 		if httpResp.StatusCode != http.StatusOK {
-			err := service.RelayErrorHandler(httpResp, true)
+			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,
@@ -267,7 +435,7 @@ func testChannel(channel *model.Channel, testModel string) testResult {
 			newAPIError: types.NewOpenAIError(err, types.ErrorCodeReadResponseBodyFailed, http.StatusInternalServerError),
 		}
 	}
-	info.PromptTokens = usage.PromptTokens
+	info.SetEstimatePromptTokens(usage.PromptTokens)
 
 	quota := 0
 	if !priceData.UsePrice {
@@ -305,24 +473,117 @@ func testChannel(channel *model.Channel, testModel string) testResult {
 	}
 }
 
-func buildTestRequest(model string) *dto.GeneralOpenAIRequest {
-	testRequest := &dto.GeneralOpenAIRequest{
-		Model:  "", // this will be set later
-		Stream: false,
+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) {
+		case constant.EndpointTypeEmbeddings:
+			// 返回 EmbeddingRequest
+			return &dto.EmbeddingRequest{
+				Model: model,
+				Input: []any{"hello world"},
+			}
+		case constant.EndpointTypeImageGeneration:
+			// 返回 ImageRequest
+			return &dto.ImageRequest{
+				Model:  model,
+				Prompt: "a cute cat",
+				N:      1,
+				Size:   "1024x1024",
+			}
+		case constant.EndpointTypeJinaRerank:
+			// 返回 RerankRequest
+			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,
+			}
+		case constant.EndpointTypeOpenAIResponse:
+			// 返回 OpenAIResponsesRequest
+			return &dto.OpenAIResponsesRequest{
+				Model: model,
+				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(16)
+			if constant.EndpointType(endpointType) == constant.EndpointTypeGemini {
+				maxTokens = 3000
+			}
+			return &dto.GeneralOpenAIRequest{
+				Model:  model,
+				Stream: false,
+				Messages: []dto.Message{
+					{
+						Role:    "user",
+						Content: "hi",
+					},
+				},
+				MaxTokens: maxTokens,
+			}
+		}
+	}
+
+	// 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") || // 其他 embedding 模型
-		strings.HasPrefix(model, "m3e") || // m3e 系列模型
+	if strings.Contains(strings.ToLower(model), "embedding") ||
+		strings.HasPrefix(model, "m3e") ||
 		strings.Contains(model, "bge-") {
-		testRequest.Model = model
-		// Embedding 请求
-		testRequest.Input = []any{"hello world"} // 修改为any，因为dto/openai_request.go 的ParseInput方法无法处理[]string类型
-		return testRequest
+		// 返回 EmbeddingRequest
+		return &dto.EmbeddingRequest{
+			Model: model,
+			Input: []any{"hello world"},
+		}
 	}
-	// 并非Embedding 模型
+
+	// 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,
+		Stream: false,
+		Messages: []dto.Message{
+			{
+				Role:    "user",
+				Content: "hi",
+			},
+		},
+	}
+
 	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
@@ -330,15 +591,9 @@ func buildTestRequest(model string) *dto.GeneralOpenAIRequest {
 	} else if strings.Contains(model, "gemini") {
 		testRequest.MaxTokens = 3000
 	} else {
-		testRequest.MaxTokens = 10
+		testRequest.MaxTokens = 16
 	}
 
-	testMessage := dto.Message{
-		Role:    "user",
-		Content: "hi",
-	}
-	testRequest.Model = model
-	testRequest.Messages = append(testRequest.Messages, testMessage)
 	return testRequest
 }
 
@@ -362,8 +617,9 @@ func TestChannel(c *gin.Context) {
 	//	}
 	//}()
 	testModel := c.Query("model")
+	endpointType := c.Query("endpoint_type")
 	tik := time.Now()
-	result := testChannel(channel, testModel)
+	result := testChannel(channel, testModel, endpointType)
 	if result.localErr != nil {
 		c.JSON(http.StatusOK, gin.H{
 			"success": false,
@@ -389,7 +645,6 @@ func TestChannel(c *gin.Context) {
 		"message": "",
 		"time":    consumedTime,
 	})
-	return
 }
 
 var testAllChannelsLock sync.Mutex
@@ -423,7 +678,7 @@ func testAllChannels(notify bool) error {
 		for _, channel := range channels {
 			isChannelEnabled := channel.Status == common.ChannelStatusEnabled
 			tik := time.Now()
-			result := testChannel(channel, "")
+			result := testChannel(channel, "", "")
 			tok := time.Now()
 			milliseconds := tok.Sub(tik).Milliseconds()
 
@@ -437,7 +692,7 @@ func testAllChannels(notify bool) error {
 			// 当错误检查通过，才检查响应时间
 			if common.AutomaticDisableChannelEnabled && !shouldBanChannel {
 				if milliseconds > disableThreshold {
-					err := errors.New(fmt.Sprintf("响应时间 %.2fs 超过阈值 %.2fs", float64(milliseconds)/1000.0, float64(disableThreshold)/1000.0))
+					err := fmt.Errorf("响应时间 %.2fs 超过阈值 %.2fs", float64(milliseconds)/1000.0, float64(disableThreshold)/1000.0)
 					newAPIError = types.NewOpenAIError(err, types.ErrorCodeChannelResponseTimeExceeded, http.StatusRequestTimeout)
 					shouldBanChannel = true
 				}
@@ -474,18 +729,32 @@ func TestAllChannels(c *gin.Context) {
 		"success": true,
 		"message": "",
 	})
-	return
 }
 
-func AutomaticallyTestChannels(frequency int) {
-	if frequency <= 0 {
-		common.SysLog("CHANNEL_TEST_FREQUENCY is not set or invalid, skipping automatic channel test")
+var autoTestChannelsOnce sync.Once
+
+func AutomaticallyTestChannels() {
+	// 只在Master节点定时测试渠道
+	if !common.IsMasterNode {
 		return
 	}
-	for {
-		time.Sleep(time.Duration(frequency) * time.Minute)
-		common.SysLog("testing all channels")
-		_ = testAllChannels(false)
-		common.SysLog("channel test finished")
-	}
+	autoTestChannelsOnce.Do(func() {
+		for {
+			if !operation_setting.GetMonitorSetting().AutoTestChannelEnabled {
+				time.Sleep(1 * time.Minute)
+				continue
+			}
+			for {
+				frequency := operation_setting.GetMonitorSetting().AutoTestChannelMinutes
+				time.Sleep(time.Duration(int(math.Round(frequency))) * time.Minute)
+				common.SysLog(fmt.Sprintf("automatically test channels with interval %f minutes", frequency))
+				common.SysLog("automatically testing all channels")
+				_ = testAllChannels(false)
+				common.SysLog("automatically channel test finished")
+				if !operation_setting.GetMonitorSetting().AutoTestChannelEnabled {
+					break
+				}
+			}
+		}
+	})
 }

controller/channel.go

@@ -1,23 +1,31 @@
 package controller
 
 import (
+	"context"
 	"encoding/json"
 	"fmt"
 	"net/http"
-	"one-api/common"
-	"one-api/constant"
-	"one-api/model"
 	"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"`
@@ -88,7 +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
 			}
@@ -162,6 +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 {
@@ -180,25 +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:
+		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]
-	if channel.Type == constant.ChannelTypeGemini {
-		body, err = GetResponseBody("GET", url, channel, GetAuthHeader(key)) // Use AuthHeader since Gemini now forces it
-	} else {
-		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
@@ -265,7 +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...)
 				}
@@ -380,6 +517,58 @@ func GetChannel(c *gin.Context) {
 	return
 }
 
+// GetChannelKey 获取渠道密钥（需要通过安全验证中间件）
+// 此函数依赖 SecureVerificationRequired 中间件，确保用户已通过安全验证
+func GetChannelKey(c *gin.Context) {
+	userId := c.GetInt("id")
+	channelId, err := strconv.Atoi(c.Param("id"))
+	if err != nil {
+		common.ApiError(c, fmt.Errorf("渠道ID格式错误: %v", err))
+		return
+	}
+
+	// 获取渠道信息（包含密钥）
+	channel, err := model.GetChannelById(channelId, true)
+	if err != nil {
+		common.ApiError(c, fmt.Errorf("获取渠道信息失败: %v", err))
+		return
+	}
+
+	if channel == nil {
+		common.ApiError(c, fmt.Errorf("渠道不存在"))
+		return
+	}
+
+	// 记录操作日志
+	model.RecordLog(userId, model.LogTypeSystem, fmt.Sprintf("查看渠道密钥信息 (渠道ID: %d)", channelId))
+
+	// 返回渠道密钥
+	c.JSON(http.StatusOK, gin.H{
+		"success": true,
+		"message": "获取成功",
+		"data": map[string]interface{}{
+			"key": channel.Key,
+		},
+	})
+}
+
+// validateTwoFactorAuth 统一的2FA验证函数
+func validateTwoFactorAuth(twoFA *model.TwoFA, code string) bool {
+	// 尝试验证TOTP
+	if cleanCode, err := common.ValidateNumericCode(code); err == nil {
+		if isValid, _ := twoFA.ValidateTOTPAndUpdateUsage(cleanCode); isValid {
+			return true
+		}
+	}
+
+	// 尝试验证备用码
+	if isValid, err := twoFA.ValidateBackupCodeAndUpdateUsage(code); err == nil && isValid {
+		return true
+	}
+
+	return false
+}
+
 // validateChannel 通用的渠道校验函数
 func validateChannel(channel *model.Channel, isAdd bool) error {
 	// 校验 channel settings
@@ -417,13 +606,65 @@ 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"`
-	Channel      *model.Channel        `json:"channel"`
+	Mode                      string                `json:"mode"`
+	MultiKeyMode              constant.MultiKeyMode `json:"multi_key_mode"`
+	BatchAddSetKeyPrefix2Name bool                  `json:"batch_add_set_key_prefix_2_name"`
+	Channel                   *model.Channel        `json:"channel"`
 }
 
 func getVertexArrayKeys(keys string) ([]string, error) {
@@ -481,7 +722,7 @@ func AddChannel(c *gin.Context) {
 	case "multi_to_single":
 		addChannelRequest.Channel.ChannelInfo.IsMultiKey = true
 		addChannelRequest.Channel.ChannelInfo.MultiKeyMode = addChannelRequest.MultiKeyMode
-		if addChannelRequest.Channel.Type == constant.ChannelTypeVertexAi {
+		if addChannelRequest.Channel.Type == constant.ChannelTypeVertexAi && addChannelRequest.Channel.GetOtherSettings().VertexKeyType != dto.VertexKeyTypeAPIKey {
 			array, err := getVertexArrayKeys(addChannelRequest.Channel.Key)
 			if err != nil {
 				c.JSON(http.StatusOK, gin.H{
@@ -506,7 +747,7 @@ func AddChannel(c *gin.Context) {
 		}
 		keys = []string{addChannelRequest.Channel.Key}
 	case "batch":
-		if addChannelRequest.Channel.Type == constant.ChannelTypeVertexAi {
+		if addChannelRequest.Channel.Type == constant.ChannelTypeVertexAi && addChannelRequest.Channel.GetOtherSettings().VertexKeyType != dto.VertexKeyTypeAPIKey {
 			// multi json
 			keys, err = getVertexArrayKeys(addChannelRequest.Channel.Key)
 			if err != nil {
@@ -536,6 +777,13 @@ func AddChannel(c *gin.Context) {
 		}
 		localChannel := addChannelRequest.Channel
 		localChannel.Key = key
+		if addChannelRequest.BatchAddSetKeyPrefix2Name && len(keys) > 1 {
+			keyPrefix := localChannel.Key
+			if len(localChannel.Key) > 8 {
+				keyPrefix = localChannel.Key[:8]
+			}
+			localChannel.Name = fmt.Sprintf("%s %s", localChannel.Name, keyPrefix)
+		}
 		channels = append(channels, *localChannel)
 	}
 	err = model.BatchInsertChannels(channels)
@@ -543,6 +791,7 @@ func AddChannel(c *gin.Context) {
 		common.ApiError(c, err)
 		return
 	}
+	service.ResetProxyClientCache()
 	c.JSON(http.StatusOK, gin.H{
 		"success": true,
 		"message": "",
@@ -582,13 +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) {
@@ -654,7 +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
@@ -761,7 +1034,7 @@ func UpdateChannel(c *gin.Context) {
 				}
 
 				// 处理 Vertex AI 的特殊情况
-				if channel.Type == constant.ChannelTypeVertexAi {
+				if channel.Type == constant.ChannelTypeVertexAi && channel.GetOtherSettings().VertexKeyType != dto.VertexKeyTypeAPIKey {
 					// 尝试解析新密钥为JSON数组
 					if strings.HasPrefix(strings.TrimSpace(channel.Key), "[") {
 						array, err := getVertexArrayKeys(channel.Key)
@@ -777,9 +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")
@@ -789,10 +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）
@@ -804,6 +1095,7 @@ func UpdateChannel(c *gin.Context) {
 		return
 	}
 	model.InitChannelCache()
+	service.ResetProxyClientCache()
 	channel.Key = ""
 	clearChannelInfo(&channel.Channel)
 	c.JSON(http.StatusOK, gin.H{
@@ -834,6 +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)
 
@@ -846,10 +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)
@@ -929,7 +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,
@@ -1013,8 +1344,8 @@ func CopyChannel(c *gin.Context) {
 // MultiKeyManageRequest represents the request for multi-key management operations
 type MultiKeyManageRequest struct {
 	ChannelId int    `json:"channel_id"`
-	Action    string `json:"action"`              // "disable_key", "enable_key", "delete_disabled_keys", "get_key_status"
-	KeyIndex  *int   `json:"key_index,omitempty"` // for disable_key and enable_key actions
+	Action    string `json:"action"`              // "disable_key", "enable_key", "delete_key", "delete_disabled_keys", "get_key_status"
+	KeyIndex  *int   `json:"key_index,omitempty"` // for disable_key, enable_key, and delete_key actions
 	Page      int    `json:"page,omitempty"`      // for get_key_status pagination
 	PageSize  int    `json:"page_size,omitempty"` // for get_key_status pagination
 	Status    *int   `json:"status,omitempty"`    // for get_key_status filtering: 1=enabled, 2=manual_disabled, 3=auto_disabled, nil=all
@@ -1342,6 +1673,86 @@ func ManageMultiKeys(c *gin.Context) {
 		})
 		return
 
+	case "delete_key":
+		if request.KeyIndex == nil {
+			c.JSON(http.StatusOK, gin.H{
+				"success": false,
+				"message": "未指定要删除的密钥索引",
+			})
+			return
+		}
+
+		keyIndex := *request.KeyIndex
+		if keyIndex < 0 || keyIndex >= channel.ChannelInfo.MultiKeySize {
+			c.JSON(http.StatusOK, gin.H{
+				"success": false,
+				"message": "密钥索引超出范围",
+			})
+			return
+		}
+
+		keys := channel.GetKeys()
+		var remainingKeys []string
+		var newStatusList = make(map[int]int)
+		var newDisabledTime = make(map[int]int64)
+		var newDisabledReason = make(map[int]string)
+
+		newIndex := 0
+		for i, key := range keys {
+			// 跳过要删除的密钥
+			if i == keyIndex {
+				continue
+			}
+
+			remainingKeys = append(remainingKeys, key)
+
+			// 保留其他密钥的状态信息，重新索引
+			if channel.ChannelInfo.MultiKeyStatusList != nil {
+				if status, exists := channel.ChannelInfo.MultiKeyStatusList[i]; exists && status != 1 {
+					newStatusList[newIndex] = status
+				}
+			}
+			if channel.ChannelInfo.MultiKeyDisabledTime != nil {
+				if t, exists := channel.ChannelInfo.MultiKeyDisabledTime[i]; exists {
+					newDisabledTime[newIndex] = t
+				}
+			}
+			if channel.ChannelInfo.MultiKeyDisabledReason != nil {
+				if r, exists := channel.ChannelInfo.MultiKeyDisabledReason[i]; exists {
+					newDisabledReason[newIndex] = r
+				}
+			}
+			newIndex++
+		}
+
+		if len(remainingKeys) == 0 {
+			c.JSON(http.StatusOK, gin.H{
+				"success": false,
+				"message": "不能删除最后一个密钥",
+			})
+			return
+		}
+
+		// Update channel with remaining keys
+		channel.Key = strings.Join(remainingKeys, "\n")
+		channel.ChannelInfo.MultiKeySize = len(remainingKeys)
+		channel.ChannelInfo.MultiKeyStatusList = newStatusList
+		channel.ChannelInfo.MultiKeyDisabledTime = newDisabledTime
+		channel.ChannelInfo.MultiKeyDisabledReason = newDisabledReason
+
+		err = channel.Update()
+		if err != nil {
+			common.ApiError(c, err)
+			return
+		}
+
+		model.InitChannelCache()
+		c.JSON(http.StatusOK, gin.H{
+			"success": true,
+			"message": "密钥已删除",
+		})
+		return
+
 	case "delete_disabled_keys":
 		keys := channel.GetKeys()
 		var remainingKeys []string
@@ -1419,3 +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 +1,88 @@
+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,
+		},
+	})
+}
+
+func GetChannelAffinityUsageCacheStats(c *gin.Context) {
+	ruleName := strings.TrimSpace(c.Query("rule_name"))
+	usingGroup := strings.TrimSpace(c.Query("using_group"))
+	keyFp := strings.TrimSpace(c.Query("key_fp"))
+
+	if ruleName == "" {
+		c.JSON(http.StatusBadRequest, gin.H{
+			"success": false,
+			"message": "missing param: rule_name",
+		})
+		return
+	}
+	if keyFp == "" {
+		c.JSON(http.StatusBadRequest, gin.H{
+			"success": false,
+			"message": "missing param: key_fp",
+		})
+		return
+	}
+
+	stats := service.GetChannelAffinityUsageCacheStats(ruleName, usingGroup, keyFp)
+	c.JSON(http.StatusOK, gin.H{
+		"success": true,
+		"message": "",
+		"data":    stats,
+	})
+}

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/console_migrate.go

@@ -5,8 +5,9 @@ package controller
 import (
 	"encoding/json"
 	"net/http"
-	"one-api/common"
-	"one-api/model"
+
+	"github.com/QuantumNous/new-api/common"
+	"github.com/QuantumNous/new-api/model"
 
 	"github.com/gin-gonic/gin"
 )

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

@@ -6,11 +6,12 @@ import (
 	"errors"
 	"fmt"
 	"net/http"
-	"one-api/common"
-	"one-api/model"
 	"strconv"
 	"time"
 
+	"github.com/QuantumNous/new-api/common"
+	"github.com/QuantumNous/new-api/model"
+
 	"github.com/gin-contrib/sessions"
 	"github.com/gin-gonic/gin"
 )
@@ -43,7 +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/group.go

@@ -2,9 +2,11 @@ package controller
 
 import (
 	"net/http"
-	"one-api/model"
-	"one-api/setting"
-	"one-api/setting/ratio_setting"
+
+	"github.com/QuantumNous/new-api/model"
+	"github.com/QuantumNous/new-api/service"
+	"github.com/QuantumNous/new-api/setting"
+	"github.com/QuantumNous/new-api/setting/ratio_setting"
 
 	"github.com/gin-gonic/gin"
 )
@@ -26,17 +28,17 @@ func GetUserGroups(c *gin.Context) {
 	userGroup := ""
 	userId := c.GetInt("id")
 	userGroup, _ = model.GetUserGroup(userId, false)
-	for groupName, ratio := range ratio_setting.GetGroupRatioCopy() {
+	userUsableGroups := service.GetUserUsableGroups(userGroup)
+	for groupName, _ := range ratio_setting.GetGroupRatioCopy() {
 		// UserUsableGroups contains the groups that the user can use
-		userUsableGroups := setting.GetUserUsableGroups(userGroup)
 		if desc, ok := userUsableGroups[groupName]; ok {
 			usableGroups[groupName] = map[string]interface{}{
-				"ratio": ratio,
+				"ratio": service.GetUserGroupRatio(userGroup, groupName),
 				"desc":  desc,
 			}
 		}
 	}
-	if setting.GroupInUserUsableGroups("auto") {
+	if _, ok := userUsableGroups["auto"]; ok {
 		usableGroups["auto"] = map[string]interface{}{
 			"ratio": "自动",
 			"desc":  setting.GetUsableGroupDescription("auto"),

controller/linuxdo.go

@@ -7,12 +7,13 @@ import (
 	"fmt"
 	"net/http"
 	"net/url"
-	"one-api/common"
-	"one-api/model"
 	"strconv"
 	"strings"
 	"time"
 
+	"github.com/QuantumNous/new-api/common"
+	"github.com/QuantumNous/new-api/model"
+
 	"github.com/gin-contrib/sessions"
 	"github.com/gin-gonic/gin"
 )
@@ -83,7 +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))
 
@@ -128,7 +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/log.go

@@ -2,10 +2,11 @@ package controller
 
 import (
 	"net/http"
-	"one-api/common"
-	"one-api/model"
 	"strconv"
 
+	"github.com/QuantumNous/new-api/common"
+	"github.com/QuantumNous/new-api/model"
+
 	"github.com/gin-gonic/gin"
 )
 

controller/midjourney.go

@@ -7,14 +7,16 @@ import (
 	"fmt"
 	"io"
 	"net/http"
-	"one-api/common"
-	"one-api/dto"
-	"one-api/logger"
-	"one-api/model"
-	"one-api/service"
-	"one-api/setting"
 	"time"
 
+	"github.com/QuantumNous/new-api/common"
+	"github.com/QuantumNous/new-api/dto"
+	"github.com/QuantumNous/new-api/logger"
+	"github.com/QuantumNous/new-api/model"
+	"github.com/QuantumNous/new-api/service"
+	"github.com/QuantumNous/new-api/setting"
+	"github.com/QuantumNous/new-api/setting/system_setting"
+
 	"github.com/gin-gonic/gin"
 )
 
@@ -259,7 +261,7 @@ func GetAllMidjourney(c *gin.Context) {
 
 	if setting.MjForwardUrlEnabled {
 		for i, midjourney := range items {
-			midjourney.ImageUrl = setting.ServerAddress + "/mj/image/" + midjourney.MjId
+			midjourney.ImageUrl = system_setting.ServerAddress + "/mj/image/" + midjourney.MjId
 			items[i] = midjourney
 		}
 	}
@@ -284,7 +286,7 @@ func GetUserMidjourney(c *gin.Context) {
 
 	if setting.MjForwardUrlEnabled {
 		for i, midjourney := range items {
-			midjourney.ImageUrl = setting.ServerAddress + "/mj/image/" + midjourney.MjId
+			midjourney.ImageUrl = system_setting.ServerAddress + "/mj/image/" + midjourney.MjId
 			items[i] = midjourney
 		}
 	}

controller/misc.go

@@ -4,16 +4,17 @@ import (
 	"encoding/json"
 	"fmt"
 	"net/http"
-	"one-api/common"
-	"one-api/constant"
-	"one-api/middleware"
-	"one-api/model"
-	"one-api/setting"
-	"one-api/setting/console_setting"
-	"one-api/setting/operation_setting"
-	"one-api/setting/system_setting"
 	"strings"
 
+	"github.com/QuantumNous/new-api/common"
+	"github.com/QuantumNous/new-api/constant"
+	"github.com/QuantumNous/new-api/middleware"
+	"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/system_setting"
+
 	"github.com/gin-gonic/gin"
 )
 
@@ -39,6 +40,11 @@ func TestStatus(c *gin.Context) {
 func GetStatus(c *gin.Context) {
 
 	cs := console_setting.GetConsoleSetting()
+	common.OptionMapRWMutex.RLock()
+	defer common.OptionMapRWMutex.RUnlock()
+
+	passkeySetting := system_setting.GetPasskeySettings()
+	legalSetting := system_setting.GetLegalSettings()
 
 	data := gin.H{
 		"version":                     common.Version,
@@ -46,6 +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,
@@ -56,32 +64,32 @@ func GetStatus(c *gin.Context) {
 		"footer_html":                 common.Footer,
 		"wechat_qrcode":               common.WeChatAccountQRCodeImageURL,
 		"wechat_login":                common.WeChatAuthEnabled,
-		"server_address":              setting.ServerAddress,
-		"price":                       setting.Price,
-		"stripe_unit_price":           setting.StripeUnitPrice,
-		"min_topup":                   setting.MinTopUp,
-		"stripe_min_topup":            setting.StripeMinTopUp,
+		"server_address":              system_setting.ServerAddress,
 		"turnstile_check":             common.TurnstileCheckEnabled,
 		"turnstile_site_key":          common.TurnstileSiteKey,
 		"top_up_link":                 common.TopUpLink,
 		"docs_link":                   operation_setting.GetGeneralSetting().DocsLink,
 		"quota_per_unit":              common.QuotaPerUnit,
-		"display_in_currency":         common.DisplayInCurrencyEnabled,
-		"enable_batch_update":         common.BatchUpdateEnabled,
-		"enable_drawing":              common.DrawingEnabled,
-		"enable_task":                 common.TaskEnabled,
-		"enable_data_export":          common.DataExportEnabled,
-		"data_export_default_time":    common.DataExportDefaultTime,
-		"default_collapse_sidebar":    common.DefaultCollapseSidebar,
-		"enable_online_topup":         setting.PayAddress != "" && setting.EpayId != "" && setting.EpayKey != "",
-		"enable_stripe_topup":         setting.StripeApiSecret != "" && setting.StripeWebhookSecret != "" && setting.StripePriceId != "",
-		"mj_notify_enabled":           setting.MjNotifyEnabled,
-		"chats":                       setting.Chats,
-		"demo_site_enabled":           operation_setting.DemoSiteEnabled,
-		"self_use_mode_enabled":       operation_setting.SelfUseModeEnabled,
-		"default_use_auto_group":      setting.DefaultUseAutoGroup,
-		"pay_methods":                 setting.PayMethods,
-		"usd_exchange_rate":           setting.USDExchangeRate,
+		// 兼容旧前端：保留 display_in_currency，同时提供新的 quota_display_type
+		"display_in_currency":           operation_setting.IsCurrencyDisplay(),
+		"quota_display_type":            operation_setting.GetQuotaDisplayType(),
+		"custom_currency_symbol":        operation_setting.GetGeneralSetting().CustomCurrencySymbol,
+		"custom_currency_exchange_rate": operation_setting.GetGeneralSetting().CustomCurrencyExchangeRate,
+		"enable_batch_update":           common.BatchUpdateEnabled,
+		"enable_drawing":                common.DrawingEnabled,
+		"enable_task":                   common.TaskEnabled,
+		"enable_data_export":            common.DataExportEnabled,
+		"data_export_default_time":      common.DataExportDefaultTime,
+		"default_collapse_sidebar":      common.DefaultCollapseSidebar,
+		"mj_notify_enabled":             setting.MjNotifyEnabled,
+		"chats":                         setting.Chats,
+		"demo_site_enabled":             operation_setting.DemoSiteEnabled,
+		"self_use_mode_enabled":         operation_setting.SelfUseModeEnabled,
+		"default_use_auto_group":        setting.DefaultUseAutoGroup,
+
+		"usd_exchange_rate": operation_setting.USDExchangeRate,
+		"price":             operation_setting.Price,
+		"stripe_unit_price": setting.StripeUnitPrice,
 
 		// 面板启用开关
 		"api_info_enabled":      cs.ApiInfoEnabled,
@@ -89,10 +97,25 @@ func GetStatus(c *gin.Context) {
 		"announcements_enabled": cs.AnnouncementsEnabled,
 		"faq_enabled":           cs.FAQEnabled,
 
+		// 模块管理配置
+		"HeaderNavModules":    common.OptionMap["HeaderNavModules"],
+		"SidebarModulesAdmin": common.OptionMap["SidebarModulesAdmin"],
+
 		"oidc_enabled":                system_setting.GetOIDCSettings().Enabled,
 		"oidc_client_id":              system_setting.GetOIDCSettings().ClientId,
 		"oidc_authorization_endpoint": system_setting.GetOIDCSettings().AuthorizationEndpoint,
+		"passkey_login":               passkeySetting.Enabled,
+		"passkey_display_name":        passkeySetting.RPDisplayName,
+		"passkey_rp_id":               passkeySetting.RPID,
+		"passkey_origins":             passkeySetting.Origins,
+		"passkey_allow_insecure":      passkeySetting.AllowInsecureOrigin,
+		"passkey_user_verification":   passkeySetting.UserVerification,
+		"passkey_attachment":          passkeySetting.AttachmentPreference,
 		"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
@@ -136,6 +159,24 @@ func GetAbout(c *gin.Context) {
 	return
 }
 
+func GetUserAgreement(c *gin.Context) {
+	c.JSON(http.StatusOK, gin.H{
+		"success": true,
+		"message": "",
+		"data":    system_setting.GetLegalSettings().UserAgreement,
+	})
+	return
+}
+
+func GetPrivacyPolicy(c *gin.Context) {
+	c.JSON(http.StatusOK, gin.H{
+		"success": true,
+		"message": "",
+		"data":    system_setting.GetLegalSettings().PrivacyPolicy,
+	})
+	return
+}
+
 func GetMidjourney(c *gin.Context) {
 	common.OptionMapRWMutex.RLock()
 	defer common.OptionMapRWMutex.RUnlock()
@@ -247,7 +288,7 @@ func SendPasswordResetEmail(c *gin.Context) {
 	}
 	code := common.GenerateVerificationCode(0)
 	common.RegisterVerificationCodeWithKey(email, code, common.PasswordResetPurpose)
-	link := fmt.Sprintf("%s/user/reset?email=%s&token=%s", setting.ServerAddress, email, code)
+	link := fmt.Sprintf("%s/user/reset?email=%s&token=%s", system_setting.ServerAddress, email, code)
 	subject := fmt.Sprintf("%s密码重置", common.SystemName)
 	content := fmt.Sprintf("<p>您好，你正在进行%s密码重置。</p>"+
 		"<p>点击 <a href='%s'>此处</a> 进行密码重置。</p>"+

controller/missing_models.go

@@ -2,7 +2,8 @@ package controller
 
 import (
 	"net/http"
-	"one-api/model"
+
+	"github.com/QuantumNous/new-api/model"
 
 	"github.com/gin-gonic/gin"
 )

controller/model.go

@@ -2,21 +2,25 @@ package controller
 
 import (
 	"fmt"
+	"net/http"
+	"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"
+	"github.com/QuantumNous/new-api/relay/channel/ai360"
+	"github.com/QuantumNous/new-api/relay/channel/lingyiwanwu"
+	"github.com/QuantumNous/new-api/relay/channel/minimax"
+	"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"
-	"net/http"
-	"one-api/common"
-	"one-api/constant"
-	"one-api/dto"
-	"one-api/model"
-	"one-api/relay"
-	"one-api/relay/channel/ai360"
-	"one-api/relay/channel/lingyiwanwu"
-	"one-api/relay/channel/minimax"
-	"one-api/relay/channel/moonshot"
-	relaycommon "one-api/relay/common"
-	"one-api/setting"
-	"time"
 )
 
 // https://platform.openai.com/docs/api-reference/models/list
@@ -108,6 +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)
@@ -118,6 +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)
@@ -148,7 +169,7 @@ func ListModels(c *gin.Context, modelType int) {
 		}
 		var models []string
 		if tokenGroup == "auto" {
-			for _, autoGroup := range setting.AutoGroups {
+			for _, autoGroup := range service.GetUserAutoGroup(userGroup) {
 				groupModels := model.GetGroupEnabledModels(autoGroup)
 				for _, g := range groupModels {
 					if !common.StringsContains(models, g) {
@@ -160,6 +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)
@@ -174,6 +201,7 @@ func ListModels(c *gin.Context, modelType int) {
 			}
 		}
 	}
+
 	switch modelType {
 	case constant.ChannelTypeAnthropic:
 		useranthropicModels := make([]dto.AnthropicModel, len(userOpenAiModels))
@@ -207,6 +235,7 @@ func ListModels(c *gin.Context, modelType int) {
 		c.JSON(200, gin.H{
 			"success": true,
 			"data":    userOpenAiModels,
+			"object":  "list",
 		})
 	}
 }
@@ -247,7 +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_meta.go

@@ -6,9 +6,9 @@ import (
 	"strconv"
 	"strings"
 
-	"one-api/common"
-	"one-api/constant"
-	"one-api/model"
+	"github.com/QuantumNous/new-api/common"
+	"github.com/QuantumNous/new-api/constant"
+	"github.com/QuantumNous/new-api/model"
 
 	"github.com/gin-gonic/gin"
 )

controller/model_sync.go

@@ -0,0 +1,633 @@
+package controller
+
+import (
+	"context"
+	"encoding/json"
+	"errors"
+	"fmt"
+	"io"
+	"math/rand"
+	"net"
+	"net/http"
+	"strings"
+	"sync"
+	"time"
+
+	"github.com/QuantumNous/new-api/common"
+	"github.com/QuantumNous/new-api/model"
+
+	"github.com/gin-gonic/gin"
+	"gorm.io/gorm"
+)
+
+// 上游地址
+const (
+	upstreamModelsURL  = "https://basellm.github.io/llm-metadata/api/newapi/models.json"
+	upstreamVendorsURL = "https://basellm.github.io/llm-metadata/api/newapi/vendors.json"
+)
+
+func normalizeLocale(locale string) (string, bool) {
+	l := strings.ToLower(strings.TrimSpace(locale))
+	switch l {
+	case "en", "zh", "ja":
+		return l, true
+	default:
+		return "", false
+	}
+}
+
+func getUpstreamBase() string {
+	return common.GetEnvOrDefaultString("SYNC_UPSTREAM_BASE", "https://basellm.github.io/llm-metadata")
+}
+
+func getUpstreamURLs(locale string) (modelsURL, vendorsURL string) {
+	base := strings.TrimRight(getUpstreamBase(), "/")
+	if l, ok := normalizeLocale(locale); ok && l != "" {
+		return fmt.Sprintf("%s/api/i18n/%s/newapi/models.json", base, l),
+			fmt.Sprintf("%s/api/i18n/%s/newapi/vendors.json", base, l)
+	}
+	return fmt.Sprintf("%s/api/newapi/models.json", base), fmt.Sprintf("%s/api/newapi/vendors.json", base)
+}
+
+type upstreamEnvelope[T any] struct {
+	Success bool   `json:"success"`
+	Message string `json:"message"`
+	Data    []T    `json:"data"`
+}
+
+type upstreamModel struct {
+	Description string          `json:"description"`
+	Endpoints   json.RawMessage `json:"endpoints"`
+	Icon        string          `json:"icon"`
+	ModelName   string          `json:"model_name"`
+	NameRule    int             `json:"name_rule"`
+	Status      int             `json:"status"`
+	Tags        string          `json:"tags"`
+	VendorName  string          `json:"vendor_name"`
+}
+
+type upstreamVendor struct {
+	Description string `json:"description"`
+	Icon        string `json:"icon"`
+	Name        string `json:"name"`
+	Status      int    `json:"status"`
+}
+
+var (
+	etagCache  = make(map[string]string)
+	bodyCache  = make(map[string][]byte)
+	cacheMutex sync.RWMutex
+)
+
+type overwriteField struct {
+	ModelName string   `json:"model_name"`
+	Fields    []string `json:"fields"`
+}
+
+type syncRequest struct {
+	Overwrite []overwriteField `json:"overwrite"`
+	Locale    string           `json:"locale"`
+}
+
+func newHTTPClient() *http.Client {
+	timeoutSec := common.GetEnvOrDefault("SYNC_HTTP_TIMEOUT_SECONDS", 10)
+	dialer := &net.Dialer{Timeout: time.Duration(timeoutSec) * time.Second}
+	transport := &http.Transport{
+		MaxIdleConns:          100,
+		IdleConnTimeout:       90 * time.Second,
+		TLSHandshakeTimeout:   time.Duration(timeoutSec) * time.Second,
+		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 {
+			host = addr
+		}
+		if strings.HasSuffix(host, "github.io") {
+			if conn, err := dialer.DialContext(ctx, "tcp4", addr); err == nil {
+				return conn, nil
+			}
+			return dialer.DialContext(ctx, "tcp6", addr)
+		}
+		return dialer.DialContext(ctx, network, addr)
+	}
+	return &http.Client{Transport: transport}
+}
+
+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
+	attempts := common.GetEnvOrDefault("SYNC_HTTP_RETRY", 3)
+	if attempts < 1 {
+		attempts = 1
+	}
+	baseDelay := 200 * time.Millisecond
+	maxMB := common.GetEnvOrDefault("SYNC_HTTP_MAX_MB", 10)
+	maxBytes := int64(maxMB) << 20
+	for attempt := 0; attempt < attempts; attempt++ {
+		req, err := http.NewRequestWithContext(ctx, http.MethodGet, url, nil)
+		if err != nil {
+			return err
+		}
+		// ETag conditional request
+		cacheMutex.RLock()
+		if et := etagCache[url]; et != "" {
+			req.Header.Set("If-None-Match", et)
+		}
+		cacheMutex.RUnlock()
+
+		resp, err := getHTTPClient().Do(req)
+		if err != nil {
+			lastErr = err
+			// backoff with jitter
+			sleep := baseDelay * time.Duration(1<<attempt)
+			jitter := time.Duration(rand.Intn(150)) * time.Millisecond
+			time.Sleep(sleep + jitter)
+			continue
+		}
+		func() {
+			defer resp.Body.Close()
+			switch resp.StatusCode {
+			case http.StatusOK:
+				// read body into buffer for caching and flexible decode
+				limited := io.LimitReader(resp.Body, maxBytes)
+				buf, err := io.ReadAll(limited)
+				if err != nil {
+					lastErr = err
+					return
+				}
+				// cache body and ETag
+				cacheMutex.Lock()
+				if et := resp.Header.Get("ETag"); et != "" {
+					etagCache[url] = et
+				}
+				bodyCache[url] = buf
+				cacheMutex.Unlock()
+
+				// Try decode as envelope first
+				if err := json.Unmarshal(buf, out); err != nil {
+					// Try decode as pure array
+					var arr []T
+					if err2 := json.Unmarshal(buf, &arr); err2 != nil {
+						lastErr = err
+						return
+					}
+					out.Success = true
+					out.Data = arr
+					out.Message = ""
+				} else {
+					if !out.Success && len(out.Data) == 0 && out.Message == "" {
+						out.Success = true
+					}
+				}
+				lastErr = nil
+			case http.StatusNotModified:
+				// use cache
+				cacheMutex.RLock()
+				buf := bodyCache[url]
+				cacheMutex.RUnlock()
+				if len(buf) == 0 {
+					lastErr = errors.New("cache miss for 304 response")
+					return
+				}
+				if err := json.Unmarshal(buf, out); err != nil {
+					var arr []T
+					if err2 := json.Unmarshal(buf, &arr); err2 != nil {
+						lastErr = err
+						return
+					}
+					out.Success = true
+					out.Data = arr
+					out.Message = ""
+				} else {
+					if !out.Success && len(out.Data) == 0 && out.Message == "" {
+						out.Success = true
+					}
+				}
+				lastErr = nil
+			default:
+				lastErr = errors.New(resp.Status)
+			}
+		}()
+		if lastErr == nil {
+			return nil
+		}
+		sleep := baseDelay * time.Duration(1<<attempt)
+		jitter := time.Duration(rand.Intn(150)) * time.Millisecond
+		time.Sleep(sleep + jitter)
+	}
+	return lastErr
+}
+
+func ensureVendorID(vendorName string, vendorByName map[string]upstreamVendor, vendorIDCache map[string]int, createdVendors *int) int {
+	if vendorName == "" {
+		return 0
+	}
+	if id, ok := vendorIDCache[vendorName]; ok {
+		return id
+	}
+	var existing model.Vendor
+	if err := model.DB.Where("name = ?", vendorName).First(&existing).Error; err == nil {
+		vendorIDCache[vendorName] = existing.Id
+		return existing.Id
+	}
+	uv := vendorByName[vendorName]
+	v := &model.Vendor{
+		Name:        vendorName,
+		Description: uv.Description,
+		Icon:        coalesce(uv.Icon, ""),
+		Status:      chooseStatus(uv.Status, 1),
+	}
+	if err := v.Insert(); err == nil {
+		*createdVendors++
+		vendorIDCache[vendorName] = v.Id
+		return v.Id
+	}
+	vendorIDCache[vendorName] = 0
+	return 0
+}
+
+// SyncUpstreamModels 同步上游模型与供应商：
+// - 默认仅创建「未配置模型」
+// - 可通过 overwrite 选择性覆盖更新本地已有模型的字段（前提：sync_official <> 0）
+func SyncUpstreamModels(c *gin.Context) {
+	var req syncRequest
+	// 允许空体
+	_ = c.ShouldBindJSON(&req)
+	// 1) 获取未配置模型列表
+	missing, err := model.GetMissingModels()
+	if err != nil {
+		c.JSON(http.StatusOK, gin.H{"success": false, "message": err.Error()})
+		return
+	}
+
+	// 若既无缺失模型需要创建，也未指定覆盖更新字段，则无需请求上游数据，直接返回
+	if len(missing) == 0 && len(req.Overwrite) == 0 {
+		modelsURL, vendorsURL := getUpstreamURLs(req.Locale)
+		c.JSON(http.StatusOK, gin.H{
+			"success": true,
+			"data": gin.H{
+				"created_models":  0,
+				"created_vendors": 0,
+				"updated_models":  0,
+				"skipped_models":  []string{},
+				"created_list":    []string{},
+				"updated_list":    []string{},
+				"source": gin.H{
+					"locale":      req.Locale,
+					"models_url":  modelsURL,
+					"vendors_url": vendorsURL,
+				},
+			},
+		})
+		return
+	}
+
+	// 2) 拉取上游 vendors 与 models
+	timeoutSec := common.GetEnvOrDefault("SYNC_HTTP_TIMEOUT_SECONDS", 15)
+	ctx, cancel := context.WithTimeout(c.Request.Context(), time.Duration(timeoutSec)*time.Second)
+	defer cancel()
+
+	modelsURL, vendorsURL := getUpstreamURLs(req.Locale)
+	var vendorsEnv upstreamEnvelope[upstreamVendor]
+	var modelsEnv upstreamEnvelope[upstreamModel]
+	var fetchErr error
+	var wg sync.WaitGroup
+	wg.Add(2)
+	go func() {
+		defer wg.Done()
+		// vendor 失败不拦截
+		_ = fetchJSON(ctx, vendorsURL, &vendorsEnv)
+	}()
+	go func() {
+		defer wg.Done()
+		if err := fetchJSON(ctx, modelsURL, &modelsEnv); err != nil {
+			fetchErr = err
+		}
+	}()
+	wg.Wait()
+	if fetchErr != nil {
+		c.JSON(http.StatusOK, gin.H{"success": false, "message": "获取上游模型失败: " + fetchErr.Error(), "locale": req.Locale, "source_urls": gin.H{"models_url": modelsURL, "vendors_url": vendorsURL}})
+		return
+	}
+
+	// 建立映射
+	vendorByName := make(map[string]upstreamVendor)
+	for _, v := range vendorsEnv.Data {
+		if v.Name != "" {
+			vendorByName[v.Name] = v
+		}
+	}
+	modelByName := make(map[string]upstreamModel)
+	for _, m := range modelsEnv.Data {
+		if m.ModelName != "" {
+			modelByName[m.ModelName] = m
+		}
+	}
+
+	// 3) 执行同步：仅创建缺失模型；若上游缺失该模型则跳过
+	createdModels := 0
+	createdVendors := 0
+	updatedModels := 0
+	skipped := make([]string, 0)
+	createdList := make([]string, 0)
+	updatedList := make([]string, 0)
+
+	// 本地缓存：vendorName -> id
+	vendorIDCache := make(map[string]int)
+
+	for _, name := range missing {
+		up, ok := modelByName[name]
+		if !ok {
+			skipped = append(skipped, name)
+			continue
+		}
+
+		// 若本地已存在且设置为不同步，则跳过（极端情况：缺失列表与本地状态不同步时）
+		var existing model.Model
+		if err := model.DB.Where("model_name = ?", name).First(&existing).Error; err == nil {
+			if existing.SyncOfficial == 0 {
+				skipped = append(skipped, name)
+				continue
+			}
+		}
+
+		// 确保 vendor 存在
+		vendorID := ensureVendorID(up.VendorName, vendorByName, vendorIDCache, &createdVendors)
+
+		// 创建模型
+		mi := &model.Model{
+			ModelName:   name,
+			Description: up.Description,
+			Icon:        up.Icon,
+			Tags:        up.Tags,
+			VendorID:    vendorID,
+			Status:      chooseStatus(up.Status, 1),
+			NameRule:    up.NameRule,
+		}
+		if err := mi.Insert(); err == nil {
+			createdModels++
+			createdList = append(createdList, name)
+		} else {
+			skipped = append(skipped, name)
+		}
+	}
+
+	// 4) 处理可选覆盖（更新本地已有模型的差异字段）
+	if len(req.Overwrite) > 0 {
+		// vendorIDCache 已用于创建阶段，可复用
+		for _, ow := range req.Overwrite {
+			up, ok := modelByName[ow.ModelName]
+			if !ok {
+				continue
+			}
+			var local model.Model
+			if err := model.DB.Where("model_name = ?", ow.ModelName).First(&local).Error; err != nil {
+				continue
+			}
+
+			// 跳过被禁用官方同步的模型
+			if local.SyncOfficial == 0 {
+				continue
+			}
+
+			// 映射 vendor
+			newVendorID := ensureVendorID(up.VendorName, vendorByName, vendorIDCache, &createdVendors)
+
+			// 应用字段覆盖（事务）
+			_ = model.DB.Transaction(func(tx *gorm.DB) error {
+				needUpdate := false
+				if containsField(ow.Fields, "description") {
+					local.Description = up.Description
+					needUpdate = true
+				}
+				if containsField(ow.Fields, "icon") {
+					local.Icon = up.Icon
+					needUpdate = true
+				}
+				if containsField(ow.Fields, "tags") {
+					local.Tags = up.Tags
+					needUpdate = true
+				}
+				if containsField(ow.Fields, "vendor") {
+					local.VendorID = newVendorID
+					needUpdate = true
+				}
+				if containsField(ow.Fields, "name_rule") {
+					local.NameRule = up.NameRule
+					needUpdate = true
+				}
+				if containsField(ow.Fields, "status") {
+					local.Status = chooseStatus(up.Status, local.Status)
+					needUpdate = true
+				}
+				if !needUpdate {
+					return nil
+				}
+				if err := tx.Save(&local).Error; err != nil {
+					return err
+				}
+				updatedModels++
+				updatedList = append(updatedList, ow.ModelName)
+				return nil
+			})
+		}
+	}
+
+	c.JSON(http.StatusOK, gin.H{
+		"success": true,
+		"data": gin.H{
+			"created_models":  createdModels,
+			"created_vendors": createdVendors,
+			"updated_models":  updatedModels,
+			"skipped_models":  skipped,
+			"created_list":    createdList,
+			"updated_list":    updatedList,
+			"source": gin.H{
+				"locale":      req.Locale,
+				"models_url":  modelsURL,
+				"vendors_url": vendorsURL,
+			},
+		},
+	})
+}
+
+func containsField(fields []string, key string) bool {
+	key = strings.ToLower(strings.TrimSpace(key))
+	for _, f := range fields {
+		if strings.ToLower(strings.TrimSpace(f)) == key {
+			return true
+		}
+	}
+	return false
+}
+
+func coalesce(a, b string) string {
+	if strings.TrimSpace(a) != "" {
+		return a
+	}
+	return b
+}
+
+func chooseStatus(primary, fallback int) int {
+	if primary == 0 && fallback != 0 {
+		return fallback
+	}
+	if primary != 0 {
+		return primary
+	}
+	return 1
+}
+
+// SyncUpstreamPreview 预览上游与本地的差异（仅用于弹窗选择）
+func SyncUpstreamPreview(c *gin.Context) {
+	// 1) 拉取上游数据
+	timeoutSec := common.GetEnvOrDefault("SYNC_HTTP_TIMEOUT_SECONDS", 15)
+	ctx, cancel := context.WithTimeout(c.Request.Context(), time.Duration(timeoutSec)*time.Second)
+	defer cancel()
+
+	locale := c.Query("locale")
+	modelsURL, vendorsURL := getUpstreamURLs(locale)
+
+	var vendorsEnv upstreamEnvelope[upstreamVendor]
+	var modelsEnv upstreamEnvelope[upstreamModel]
+	var fetchErr error
+	var wg sync.WaitGroup
+	wg.Add(2)
+	go func() {
+		defer wg.Done()
+		_ = fetchJSON(ctx, vendorsURL, &vendorsEnv)
+	}()
+	go func() {
+		defer wg.Done()
+		if err := fetchJSON(ctx, modelsURL, &modelsEnv); err != nil {
+			fetchErr = err
+		}
+	}()
+	wg.Wait()
+	if fetchErr != nil {
+		c.JSON(http.StatusOK, gin.H{"success": false, "message": "获取上游模型失败: " + fetchErr.Error(), "locale": locale, "source_urls": gin.H{"models_url": modelsURL, "vendors_url": vendorsURL}})
+		return
+	}
+
+	vendorByName := make(map[string]upstreamVendor)
+	for _, v := range vendorsEnv.Data {
+		if v.Name != "" {
+			vendorByName[v.Name] = v
+		}
+	}
+	modelByName := make(map[string]upstreamModel)
+	upstreamNames := make([]string, 0, len(modelsEnv.Data))
+	for _, m := range modelsEnv.Data {
+		if m.ModelName != "" {
+			modelByName[m.ModelName] = m
+			upstreamNames = append(upstreamNames, m.ModelName)
+		}
+	}
+
+	// 2) 本地已有模型
+	var locals []model.Model
+	if len(upstreamNames) > 0 {
+		_ = model.DB.Where("model_name IN ? AND sync_official <> 0", upstreamNames).Find(&locals).Error
+	}
+
+	// 本地 vendor 名称映射
+	vendorIdSet := make(map[int]struct{})
+	for _, m := range locals {
+		if m.VendorID != 0 {
+			vendorIdSet[m.VendorID] = struct{}{}
+		}
+	}
+	vendorIDs := make([]int, 0, len(vendorIdSet))
+	for id := range vendorIdSet {
+		vendorIDs = append(vendorIDs, id)
+	}
+	idToVendorName := make(map[int]string)
+	if len(vendorIDs) > 0 {
+		var dbVendors []model.Vendor
+		_ = model.DB.Where("id IN ?", vendorIDs).Find(&dbVendors).Error
+		for _, v := range dbVendors {
+			idToVendorName[v.Id] = v.Name
+		}
+	}
+
+	// 3) 缺失且上游存在的模型
+	missingList, _ := model.GetMissingModels()
+	var missing []string
+	for _, name := range missingList {
+		if _, ok := modelByName[name]; ok {
+			missing = append(missing, name)
+		}
+	}
+
+	// 4) 计算冲突字段
+	type conflictField struct {
+		Field    string      `json:"field"`
+		Local    interface{} `json:"local"`
+		Upstream interface{} `json:"upstream"`
+	}
+	type conflictItem struct {
+		ModelName string          `json:"model_name"`
+		Fields    []conflictField `json:"fields"`
+	}
+
+	var conflicts []conflictItem
+	for _, local := range locals {
+		up, ok := modelByName[local.ModelName]
+		if !ok {
+			continue
+		}
+		fields := make([]conflictField, 0, 6)
+		if strings.TrimSpace(local.Description) != strings.TrimSpace(up.Description) {
+			fields = append(fields, conflictField{Field: "description", Local: local.Description, Upstream: up.Description})
+		}
+		if strings.TrimSpace(local.Icon) != strings.TrimSpace(up.Icon) {
+			fields = append(fields, conflictField{Field: "icon", Local: local.Icon, Upstream: up.Icon})
+		}
+		if strings.TrimSpace(local.Tags) != strings.TrimSpace(up.Tags) {
+			fields = append(fields, conflictField{Field: "tags", Local: local.Tags, Upstream: up.Tags})
+		}
+		// vendor 对比使用名称
+		localVendor := idToVendorName[local.VendorID]
+		if strings.TrimSpace(localVendor) != strings.TrimSpace(up.VendorName) {
+			fields = append(fields, conflictField{Field: "vendor", Local: localVendor, Upstream: up.VendorName})
+		}
+		if local.NameRule != up.NameRule {
+			fields = append(fields, conflictField{Field: "name_rule", Local: local.NameRule, Upstream: up.NameRule})
+		}
+		if local.Status != chooseStatus(up.Status, local.Status) {
+			fields = append(fields, conflictField{Field: "status", Local: local.Status, Upstream: up.Status})
+		}
+		if len(fields) > 0 {
+			conflicts = append(conflicts, conflictItem{ModelName: local.ModelName, Fields: fields})
+		}
+	}
+
+	c.JSON(http.StatusOK, gin.H{
+		"success": true,
+		"data": gin.H{
+			"missing":   missing,
+			"conflicts": conflicts,
+			"source": gin.H{
+				"locale":      locale,
+				"models_url":  modelsURL,
+				"vendors_url": vendorsURL,
+			},
+		},
+	})
+}

controller/oidc.go

@@ -6,14 +6,14 @@ import (
 	"fmt"
 	"net/http"
 	"net/url"
-	"one-api/common"
-	"one-api/model"
-	"one-api/setting"
-	"one-api/setting/system_setting"
 	"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"
 )
@@ -45,7 +45,7 @@ func getOidcUserInfoByCode(code string) (*OidcUser, error) {
 	values.Set("client_secret", system_setting.GetOIDCSettings().ClientSecret)
 	values.Set("code", code)
 	values.Set("grant_type", "authorization_code")
-	values.Set("redirect_uri", fmt.Sprintf("%s/oauth/oidc", setting.ServerAddress))
+	values.Set("redirect_uri", fmt.Sprintf("%s/oauth/oidc", system_setting.ServerAddress))
 	formData := values.Encode()
 	req, err := http.NewRequest("POST", system_setting.GetOIDCSettings().TokenEndpoint, strings.NewReader(formData))
 	if err != nil {

controller/option.go

@@ -2,15 +2,18 @@ package controller
 
 import (
 	"encoding/json"
+	"fmt"
 	"net/http"
-	"one-api/common"
-	"one-api/model"
-	"one-api/setting"
-	"one-api/setting/console_setting"
-	"one-api/setting/ratio_setting"
-	"one-api/setting/system_setting"
 	"strings"
 
+	"github.com/QuantumNous/new-api/common"
+	"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"
+
 	"github.com/gin-gonic/gin"
 )
 
@@ -18,7 +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{
@@ -35,8 +42,13 @@ func GetOptions(c *gin.Context) {
 	return
 }
 
+type OptionUpdateRequest struct {
+	Key   string `json:"key"`
+	Value any    `json:"value"`
+}
+
 func UpdateOption(c *gin.Context) {
-	var option model.Option
+	var option OptionUpdateRequest
 	err := json.NewDecoder(c.Request.Body).Decode(&option)
 	if err != nil {
 		c.JSON(http.StatusBadRequest, gin.H{
@@ -45,6 +57,16 @@ func UpdateOption(c *gin.Context) {
 		})
 		return
 	}
+	switch option.Value.(type) {
+	case bool:
+		option.Value = common.Interface2String(option.Value.(bool))
+	case float64:
+		option.Value = common.Interface2String(option.Value.(float64))
+	case int:
+		option.Value = common.Interface2String(option.Value.(int))
+	default:
+		option.Value = fmt.Sprintf("%v", option.Value)
+	}
 	switch option.Key {
 	case "GitHubOAuthEnabled":
 		if option.Value == "true" && common.GitHubClientId == "" {
@@ -54,6 +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{
@@ -104,7 +134,7 @@ func UpdateOption(c *gin.Context) {
 			return
 		}
 	case "GroupRatio":
-		err = ratio_setting.CheckGroupRatio(option.Value)
+		err = ratio_setting.CheckGroupRatio(option.Value.(string))
 		if err != nil {
 			c.JSON(http.StatusOK, gin.H{
 				"success": false,
@@ -112,8 +142,53 @@ func UpdateOption(c *gin.Context) {
 			})
 			return
 		}
+	case "ImageRatio":
+		err = ratio_setting.UpdateImageRatioByJSONString(option.Value.(string))
+		if err != nil {
+			c.JSON(http.StatusOK, gin.H{
+				"success": false,
+				"message": "图片倍率设置失败: " + err.Error(),
+			})
+			return
+		}
+	case "AudioRatio":
+		err = ratio_setting.UpdateAudioRatioByJSONString(option.Value.(string))
+		if err != nil {
+			c.JSON(http.StatusOK, gin.H{
+				"success": false,
+				"message": "音频倍率设置失败: " + err.Error(),
+			})
+			return
+		}
+	case "AudioCompletionRatio":
+		err = ratio_setting.UpdateAudioCompletionRatioByJSONString(option.Value.(string))
+		if err != nil {
+			c.JSON(http.StatusOK, gin.H{
+				"success": false,
+				"message": "音频补全倍率设置失败: " + err.Error(),
+			})
+			return
+		}
 	case "ModelRequestRateLimitGroup":
-		err = setting.CheckModelRequestRateLimitGroup(option.Value)
+		err = setting.CheckModelRequestRateLimitGroup(option.Value.(string))
+		if err != nil {
+			c.JSON(http.StatusOK, gin.H{
+				"success": false,
+				"message": err.Error(),
+			})
+			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,
@@ -122,7 +197,7 @@ func UpdateOption(c *gin.Context) {
 			return
 		}
 	case "console_setting.api_info":
-		err = console_setting.ValidateConsoleSettings(option.Value, "ApiInfo")
+		err = console_setting.ValidateConsoleSettings(option.Value.(string), "ApiInfo")
 		if err != nil {
 			c.JSON(http.StatusOK, gin.H{
 				"success": false,
@@ -131,7 +206,7 @@ func UpdateOption(c *gin.Context) {
 			return
 		}
 	case "console_setting.announcements":
-		err = console_setting.ValidateConsoleSettings(option.Value, "Announcements")
+		err = console_setting.ValidateConsoleSettings(option.Value.(string), "Announcements")
 		if err != nil {
 			c.JSON(http.StatusOK, gin.H{
 				"success": false,
@@ -140,7 +215,7 @@ func UpdateOption(c *gin.Context) {
 			return
 		}
 	case "console_setting.faq":
-		err = console_setting.ValidateConsoleSettings(option.Value, "FAQ")
+		err = console_setting.ValidateConsoleSettings(option.Value.(string), "FAQ")
 		if err != nil {
 			c.JSON(http.StatusOK, gin.H{
 				"success": false,
@@ -149,7 +224,7 @@ func UpdateOption(c *gin.Context) {
 			return
 		}
 	case "console_setting.uptime_kuma_groups":
-		err = console_setting.ValidateConsoleSettings(option.Value, "UptimeKumaGroups")
+		err = console_setting.ValidateConsoleSettings(option.Value.(string), "UptimeKumaGroups")
 		if err != nil {
 			c.JSON(http.StatusOK, gin.H{
 				"success": false,
@@ -158,7 +233,7 @@ func UpdateOption(c *gin.Context) {
 			return
 		}
 	}
-	err = model.UpdateOption(option.Key, option.Value)
+	err = model.UpdateOption(option.Key, option.Value.(string))
 	if err != nil {
 		common.ApiError(c, err)
 		return

controller/passkey.go

@@ -0,0 +1,497 @@
+package controller
+
+import (
+	"errors"
+	"fmt"
+	"net/http"
+	"strconv"
+	"time"
+
+	"github.com/QuantumNous/new-api/common"
+	"github.com/QuantumNous/new-api/model"
+	passkeysvc "github.com/QuantumNous/new-api/service/passkey"
+	"github.com/QuantumNous/new-api/setting/system_setting"
+
+	"github.com/gin-contrib/sessions"
+	"github.com/gin-gonic/gin"
+	"github.com/go-webauthn/webauthn/protocol"
+	webauthnlib "github.com/go-webauthn/webauthn/webauthn"
+)
+
+func PasskeyRegisterBegin(c *gin.Context) {
+	if !system_setting.GetPasskeySettings().Enabled {
+		c.JSON(http.StatusOK, gin.H{
+			"success": false,
+			"message": "管理员未启用 Passkey 登录",
+		})
+		return
+	}
+
+	user, err := getSessionUser(c)
+	if err != nil {
+		c.JSON(http.StatusUnauthorized, gin.H{
+			"success": false,
+			"message": err.Error(),
+		})
+		return
+	}
+
+	credential, err := model.GetPasskeyByUserID(user.Id)
+	if err != nil && !errors.Is(err, model.ErrPasskeyNotFound) {
+		common.ApiError(c, err)
+		return
+	}
+	if errors.Is(err, model.ErrPasskeyNotFound) {
+		credential = nil
+	}
+
+	wa, err := passkeysvc.BuildWebAuthn(c.Request)
+	if err != nil {
+		common.ApiError(c, err)
+		return
+	}
+
+	waUser := passkeysvc.NewWebAuthnUser(user, credential)
+	var options []webauthnlib.RegistrationOption
+	if credential != nil {
+		descriptor := credential.ToWebAuthnCredential().Descriptor()
+		options = append(options, webauthnlib.WithExclusions([]protocol.CredentialDescriptor{descriptor}))
+	}
+
+	creation, sessionData, err := wa.BeginRegistration(waUser, options...)
+	if err != nil {
+		common.ApiError(c, err)
+		return
+	}
+
+	if err := passkeysvc.SaveSessionData(c, passkeysvc.RegistrationSessionKey, sessionData); err != nil {
+		common.ApiError(c, err)
+		return
+	}
+
+	c.JSON(http.StatusOK, gin.H{
+		"success": true,
+		"message": "",
+		"data": gin.H{
+			"options": creation,
+		},
+	})
+}
+
+func PasskeyRegisterFinish(c *gin.Context) {
+	if !system_setting.GetPasskeySettings().Enabled {
+		c.JSON(http.StatusOK, gin.H{
+			"success": false,
+			"message": "管理员未启用 Passkey 登录",
+		})
+		return
+	}
+
+	user, err := getSessionUser(c)
+	if err != nil {
+		c.JSON(http.StatusUnauthorized, gin.H{
+			"success": false,
+			"message": err.Error(),
+		})
+		return
+	}
+
+	wa, err := passkeysvc.BuildWebAuthn(c.Request)
+	if err != nil {
+		common.ApiError(c, err)
+		return
+	}
+
+	credentialRecord, err := model.GetPasskeyByUserID(user.Id)
+	if err != nil && !errors.Is(err, model.ErrPasskeyNotFound) {
+		common.ApiError(c, err)
+		return
+	}
+	if errors.Is(err, model.ErrPasskeyNotFound) {
+		credentialRecord = nil
+	}
+
+	sessionData, err := passkeysvc.PopSessionData(c, passkeysvc.RegistrationSessionKey)
+	if err != nil {
+		common.ApiError(c, err)
+		return
+	}
+
+	waUser := passkeysvc.NewWebAuthnUser(user, credentialRecord)
+	credential, err := wa.FinishRegistration(waUser, *sessionData, c.Request)
+	if err != nil {
+		common.ApiError(c, err)
+		return
+	}
+
+	passkeyCredential := model.NewPasskeyCredentialFromWebAuthn(user.Id, credential)
+	if passkeyCredential == nil {
+		common.ApiErrorMsg(c, "无法创建 Passkey 凭证")
+		return
+	}
+
+	if err := model.UpsertPasskeyCredential(passkeyCredential); err != nil {
+		common.ApiError(c, err)
+		return
+	}
+
+	c.JSON(http.StatusOK, gin.H{
+		"success": true,
+		"message": "Passkey 注册成功",
+	})
+}
+
+func PasskeyDelete(c *gin.Context) {
+	user, err := getSessionUser(c)
+	if err != nil {
+		c.JSON(http.StatusUnauthorized, gin.H{
+			"success": false,
+			"message": err.Error(),
+		})
+		return
+	}
+
+	if err := model.DeletePasskeyByUserID(user.Id); err != nil {
+		common.ApiError(c, err)
+		return
+	}
+
+	c.JSON(http.StatusOK, gin.H{
+		"success": true,
+		"message": "Passkey 已解绑",
+	})
+}
+
+func PasskeyStatus(c *gin.Context) {
+	user, err := getSessionUser(c)
+	if err != nil {
+		c.JSON(http.StatusUnauthorized, gin.H{
+			"success": false,
+			"message": err.Error(),
+		})
+		return
+	}
+
+	credential, err := model.GetPasskeyByUserID(user.Id)
+	if errors.Is(err, model.ErrPasskeyNotFound) {
+		c.JSON(http.StatusOK, gin.H{
+			"success": true,
+			"message": "",
+			"data": gin.H{
+				"enabled": false,
+			},
+		})
+		return
+	}
+	if err != nil {
+		common.ApiError(c, err)
+		return
+	}
+
+	data := gin.H{
+		"enabled":      true,
+		"last_used_at": credential.LastUsedAt,
+	}
+
+	c.JSON(http.StatusOK, gin.H{
+		"success": true,
+		"message": "",
+		"data":    data,
+	})
+}
+
+func PasskeyLoginBegin(c *gin.Context) {
+	if !system_setting.GetPasskeySettings().Enabled {
+		c.JSON(http.StatusOK, gin.H{
+			"success": false,
+			"message": "管理员未启用 Passkey 登录",
+		})
+		return
+	}
+
+	wa, err := passkeysvc.BuildWebAuthn(c.Request)
+	if err != nil {
+		common.ApiError(c, err)
+		return
+	}
+
+	assertion, sessionData, err := wa.BeginDiscoverableLogin()
+	if err != nil {
+		common.ApiError(c, err)
+		return
+	}
+
+	if err := passkeysvc.SaveSessionData(c, passkeysvc.LoginSessionKey, sessionData); err != nil {
+		common.ApiError(c, err)
+		return
+	}
+
+	c.JSON(http.StatusOK, gin.H{
+		"success": true,
+		"message": "",
+		"data": gin.H{
+			"options": assertion,
+		},
+	})
+}
+
+func PasskeyLoginFinish(c *gin.Context) {
+	if !system_setting.GetPasskeySettings().Enabled {
+		c.JSON(http.StatusOK, gin.H{
+			"success": false,
+			"message": "管理员未启用 Passkey 登录",
+		})
+		return
+	}
+
+	wa, err := passkeysvc.BuildWebAuthn(c.Request)
+	if err != nil {
+		common.ApiError(c, err)
+		return
+	}
+
+	sessionData, err := passkeysvc.PopSessionData(c, passkeysvc.LoginSessionKey)
+	if err != nil {
+		common.ApiError(c, err)
+		return
+	}
+
+	handler := func(rawID, userHandle []byte) (webauthnlib.User, error) {
+		// 首先通过凭证ID查找用户
+		credential, err := model.GetPasskeyByCredentialID(rawID)
+		if err != nil {
+			return nil, fmt.Errorf("未找到 Passkey 凭证: %w", err)
+		}
+
+		// 通过凭证获取用户
+		user := &model.User{Id: credential.UserID}
+		if err := user.FillUserById(); err != nil {
+			return nil, fmt.Errorf("用户信息获取失败: %w", err)
+		}
+
+		if user.Status != common.UserStatusEnabled {
+			return nil, errors.New("该用户已被禁用")
+		}
+
+		if len(userHandle) > 0 {
+			userID, parseErr := strconv.Atoi(string(userHandle))
+			if parseErr != nil {
+				// 记录异常但继续验证，因为某些客户端可能使用非数字格式
+				common.SysLog(fmt.Sprintf("PasskeyLogin: userHandle parse error for credential, length: %d", len(userHandle)))
+			} else if userID != user.Id {
+				return nil, errors.New("用户句柄与凭证不匹配")
+			}
+		}
+
+		return passkeysvc.NewWebAuthnUser(user, credential), nil
+	}
+
+	waUser, credential, err := wa.FinishPasskeyLogin(handler, *sessionData, c.Request)
+	if err != nil {
+		common.ApiError(c, err)
+		return
+	}
+
+	userWrapper, ok := waUser.(*passkeysvc.WebAuthnUser)
+	if !ok {
+		common.ApiErrorMsg(c, "Passkey 登录状态异常")
+		return
+	}
+
+	modelUser := userWrapper.ModelUser()
+	if modelUser == nil {
+		common.ApiErrorMsg(c, "Passkey 登录状态异常")
+		return
+	}
+
+	if modelUser.Status != common.UserStatusEnabled {
+		common.ApiErrorMsg(c, "该用户已被禁用")
+		return
+	}
+
+	// 更新凭证信息
+	updatedCredential := model.NewPasskeyCredentialFromWebAuthn(modelUser.Id, credential)
+	if updatedCredential == nil {
+		common.ApiErrorMsg(c, "Passkey 凭证更新失败")
+		return
+	}
+	now := time.Now()
+	updatedCredential.LastUsedAt = &now
+	if err := model.UpsertPasskeyCredential(updatedCredential); err != nil {
+		common.ApiError(c, err)
+		return
+	}
+
+	setupLogin(modelUser, c)
+	return
+}
+
+func AdminResetPasskey(c *gin.Context) {
+	id, err := strconv.Atoi(c.Param("id"))
+	if err != nil {
+		common.ApiErrorMsg(c, "无效的用户 ID")
+		return
+	}
+
+	user := &model.User{Id: id}
+	if err := user.FillUserById(); err != nil {
+		common.ApiError(c, err)
+		return
+	}
+
+	if _, err := model.GetPasskeyByUserID(user.Id); err != nil {
+		if errors.Is(err, model.ErrPasskeyNotFound) {
+			c.JSON(http.StatusOK, gin.H{
+				"success": false,
+				"message": "该用户尚未绑定 Passkey",
+			})
+			return
+		}
+		common.ApiError(c, err)
+		return
+	}
+
+	if err := model.DeletePasskeyByUserID(user.Id); err != nil {
+		common.ApiError(c, err)
+		return
+	}
+
+	c.JSON(http.StatusOK, gin.H{
+		"success": true,
+		"message": "Passkey 已重置",
+	})
+}
+
+func PasskeyVerifyBegin(c *gin.Context) {
+	if !system_setting.GetPasskeySettings().Enabled {
+		c.JSON(http.StatusOK, gin.H{
+			"success": false,
+			"message": "管理员未启用 Passkey 登录",
+		})
+		return
+	}
+
+	user, err := getSessionUser(c)
+	if err != nil {
+		c.JSON(http.StatusUnauthorized, gin.H{
+			"success": false,
+			"message": err.Error(),
+		})
+		return
+	}
+
+	credential, err := model.GetPasskeyByUserID(user.Id)
+	if err != nil {
+		c.JSON(http.StatusOK, gin.H{
+			"success": false,
+			"message": "该用户尚未绑定 Passkey",
+		})
+		return
+	}
+
+	wa, err := passkeysvc.BuildWebAuthn(c.Request)
+	if err != nil {
+		common.ApiError(c, err)
+		return
+	}
+
+	waUser := passkeysvc.NewWebAuthnUser(user, credential)
+	assertion, sessionData, err := wa.BeginLogin(waUser)
+	if err != nil {
+		common.ApiError(c, err)
+		return
+	}
+
+	if err := passkeysvc.SaveSessionData(c, passkeysvc.VerifySessionKey, sessionData); err != nil {
+		common.ApiError(c, err)
+		return
+	}
+
+	c.JSON(http.StatusOK, gin.H{
+		"success": true,
+		"message": "",
+		"data": gin.H{
+			"options": assertion,
+		},
+	})
+}
+
+func PasskeyVerifyFinish(c *gin.Context) {
+	if !system_setting.GetPasskeySettings().Enabled {
+		c.JSON(http.StatusOK, gin.H{
+			"success": false,
+			"message": "管理员未启用 Passkey 登录",
+		})
+		return
+	}
+
+	user, err := getSessionUser(c)
+	if err != nil {
+		c.JSON(http.StatusUnauthorized, gin.H{
+			"success": false,
+			"message": err.Error(),
+		})
+		return
+	}
+
+	wa, err := passkeysvc.BuildWebAuthn(c.Request)
+	if err != nil {
+		common.ApiError(c, err)
+		return
+	}
+
+	credential, err := model.GetPasskeyByUserID(user.Id)
+	if err != nil {
+		c.JSON(http.StatusOK, gin.H{
+			"success": false,
+			"message": "该用户尚未绑定 Passkey",
+		})
+		return
+	}
+
+	sessionData, err := passkeysvc.PopSessionData(c, passkeysvc.VerifySessionKey)
+	if err != nil {
+		common.ApiError(c, err)
+		return
+	}
+
+	waUser := passkeysvc.NewWebAuthnUser(user, credential)
+	_, err = wa.FinishLogin(waUser, *sessionData, c.Request)
+	if err != nil {
+		common.ApiError(c, err)
+		return
+	}
+
+	// 更新凭证的最后使用时间
+	now := time.Now()
+	credential.LastUsedAt = &now
+	if err := model.UpsertPasskeyCredential(credential); err != nil {
+		common.ApiError(c, err)
+		return
+	}
+
+	c.JSON(http.StatusOK, gin.H{
+		"success": true,
+		"message": "Passkey 验证成功",
+	})
+}
+
+func getSessionUser(c *gin.Context) (*model.User, error) {
+	session := sessions.Default(c)
+	idRaw := session.Get("id")
+	if idRaw == nil {
+		return nil, errors.New("未登录")
+	}
+	id, ok := idRaw.(int)
+	if !ok {
+		return nil, errors.New("无效的会话信息")
+	}
+	user := &model.User{Id: id}
+	if err := user.FillUserById(); err != nil {
+		return nil, err
+	}
+	if user.Status != common.UserStatusEnabled {
+		return nil, errors.New("该用户已被禁用")
+	}
+	return user, nil
+}

controller/performance.go

@@ -0,0 +1,201 @@
+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 +1,38 @@
+//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 (显式转换以兼容 FreeBSD，其字段类型为 int64)
+	bsize := uint64(stat.Bsize)
+	info.Total = uint64(stat.Blocks) * bsize
+	info.Free = uint64(stat.Bavail) * bsize
+	info.Used = info.Total - uint64(stat.Bfree)*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 +3,11 @@ package controller
 import (
 	"errors"
 	"fmt"
-	"one-api/common"
-	"one-api/constant"
-	"one-api/middleware"
-	"one-api/model"
-	"one-api/types"
-	"time"
+
+	"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"
 )
@@ -30,8 +29,11 @@ func Playground(c *gin.Context) {
 		return
 	}
 
-	group := c.GetString("group")
-	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")
 
@@ -45,16 +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/prefill_group.go

@@ -3,8 +3,8 @@ package controller
 import (
 	"strconv"
 
-	"one-api/common"
-	"one-api/model"
+	"github.com/QuantumNous/new-api/common"
+	"github.com/QuantumNous/new-api/model"
 
 	"github.com/gin-gonic/gin"
 )

controller/pricing.go

@@ -1,9 +1,9 @@
 package controller
 
 import (
-	"one-api/model"
-	"one-api/setting"
-	"one-api/setting/ratio_setting"
+	"github.com/QuantumNous/new-api/model"
+	"github.com/QuantumNous/new-api/service"
+	"github.com/QuantumNous/new-api/setting/ratio_setting"
 
 	"github.com/gin-gonic/gin"
 )
@@ -30,7 +30,7 @@ func GetPricing(c *gin.Context) {
 		}
 	}
 
-	usableGroup = setting.GetUserUsableGroups(group)
+	usableGroup = service.GetUserUsableGroups(group)
 	// check groupRatio contains usableGroup
 	for group := range ratio_setting.GetGroupRatioCopy() {
 		if _, ok := usableGroup[group]; !ok {
@@ -45,7 +45,7 @@ func GetPricing(c *gin.Context) {
 		"group_ratio":        groupRatio,
 		"usable_group":       usableGroup,
 		"supported_endpoint": model.GetSupportedEndpointMap(),
-		"auto_groups":        setting.AutoGroups,
+		"auto_groups":        service.GetUserAutoGroup(group),
 	})
 }
 

controller/ratio_config.go

@@ -1,24 +1,25 @@
 package controller
 
 import (
-    "net/http"
-    "one-api/setting/ratio_setting"
+	"net/http"
 
-    "github.com/gin-gonic/gin"
+	"github.com/QuantumNous/new-api/setting/ratio_setting"
+
+	"github.com/gin-gonic/gin"
 )
 
 func GetRatioConfig(c *gin.Context) {
-    if !ratio_setting.IsExposeRatioEnabled() {
-        c.JSON(http.StatusForbidden, gin.H{
-            "success": false,
-            "message": "倍率配置接口未启用",
-        })
-        return
-    }
+	if !ratio_setting.IsExposeRatioEnabled() {
+		c.JSON(http.StatusForbidden, gin.H{
+			"success": false,
+			"message": "倍率配置接口未启用",
+		})
+		return
+	}
 
-    c.JSON(http.StatusOK, gin.H{
-        "success": true,
-        "message": "",
-        "data":    ratio_setting.GetExposedData(),
-    })
-} 
+	c.JSON(http.StatusOK, gin.H{
+		"success": true,
+		"message": "",
+		"data":    ratio_setting.GetExposedData(),
+	})
+}

controller/ratio_sync.go

@@ -4,15 +4,19 @@ import (
 	"context"
 	"encoding/json"
 	"fmt"
+	"io"
+	"net"
 	"net/http"
-	"one-api/logger"
 	"strings"
 	"sync"
 	"time"
 
-	"one-api/dto"
-	"one-api/model"
-	"one-api/setting/ratio_setting"
+	"github.com/QuantumNous/new-api/common"
+	"github.com/QuantumNous/new-api/logger"
+
+	"github.com/QuantumNous/new-api/dto"
+	"github.com/QuantumNous/new-api/model"
+	"github.com/QuantumNous/new-api/setting/ratio_setting"
 
 	"github.com/gin-gonic/gin"
 )
@@ -21,8 +25,26 @@ const (
 	defaultTimeoutSeconds = 10
 	defaultEndpoint       = "/api/ratio_config"
 	maxConcurrentFetches  = 8
+	maxRatioConfigBytes   = 10 << 20 // 10MB
+	floatEpsilon          = 1e-9
 )
 
+func nearlyEqual(a, b float64) bool {
+	if a > b {
+		return a-b < floatEpsilon
+	}
+	return b-a < floatEpsilon
+}
+
+func valuesEqual(a, b interface{}) bool {
+	af, aok := a.(float64)
+	bf, bok := b.(float64)
+	if aok && bok {
+		return nearlyEqual(af, bf)
+	}
+	return a == b
+}
+
 var ratioTypes = []string{"model_ratio", "completion_ratio", "cache_ratio", "model_price"}
 
 type upstreamResult struct {
@@ -87,7 +109,26 @@ func FetchUpstreamRatios(c *gin.Context) {
 
 	sem := make(chan struct{}, maxConcurrentFetches)
 
-	client := &http.Client{Transport: &http.Transport{MaxIdleConns: 100, IdleConnTimeout: 90 * time.Second, TLSHandshakeTimeout: 10 * time.Second, ExpectContinueTimeout: 1 * time.Second}}
+	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 {
+			host = addr
+		}
+		// 对 github.io 优先尝试 IPv4，失败则回退 IPv6
+		if strings.HasSuffix(host, "github.io") {
+			if conn, err := dialer.DialContext(ctx, "tcp4", addr); err == nil {
+				return conn, nil
+			}
+			return dialer.DialContext(ctx, "tcp6", addr)
+		}
+		return dialer.DialContext(ctx, network, addr)
+	}
+	client := &http.Client{Transport: transport}
 
 	for _, chn := range upstreams {
 		wg.Add(1)
@@ -98,12 +139,17 @@ func FetchUpstreamRatios(c *gin.Context) {
 			defer func() { <-sem }()
 
 			endpoint := chItem.Endpoint
-			if endpoint == "" {
-				endpoint = defaultEndpoint
-			} else if !strings.HasPrefix(endpoint, "/") {
-				endpoint = "/" + endpoint
+			var fullURL string
+			if strings.HasPrefix(endpoint, "http://") || strings.HasPrefix(endpoint, "https://") {
+				fullURL = endpoint
+			} else {
+				if endpoint == "" {
+					endpoint = defaultEndpoint
+				} else if !strings.HasPrefix(endpoint, "/") {
+					endpoint = "/" + endpoint
+				}
+				fullURL = chItem.BaseURL + endpoint
 			}
-			fullURL := chItem.BaseURL + endpoint
 
 			uniqueName := chItem.Name
 			if chItem.ID != 0 {
@@ -120,10 +166,19 @@ func FetchUpstreamRatios(c *gin.Context) {
 				return
 			}
 
-			resp, err := client.Do(httpReq)
-			if err != nil {
-				logger.LogWarn(c.Request.Context(), "http error on "+chItem.Name+": "+err.Error())
-				ch <- upstreamResult{Name: uniqueName, Err: err.Error()}
+			// 简单重试：最多 3 次，指数退避
+			var resp *http.Response
+			var lastErr error
+			for attempt := 0; attempt < 3; attempt++ {
+				resp, lastErr = client.Do(httpReq)
+				if lastErr == nil {
+					break
+				}
+				time.Sleep(time.Duration(200*(1<<attempt)) * time.Millisecond)
+			}
+			if lastErr != nil {
+				logger.LogWarn(c.Request.Context(), "http error on "+chItem.Name+": "+lastErr.Error())
+				ch <- upstreamResult{Name: uniqueName, Err: lastErr.Error()}
 				return
 			}
 			defer resp.Body.Close()
@@ -132,6 +187,12 @@ func FetchUpstreamRatios(c *gin.Context) {
 				ch <- upstreamResult{Name: uniqueName, Err: resp.Status}
 				return
 			}
+
+			// Content-Type 和响应体大小校验
+			if ct := resp.Header.Get("Content-Type"); ct != "" && !strings.Contains(strings.ToLower(ct), "application/json") {
+				logger.LogWarn(c.Request.Context(), "unexpected content-type from "+chItem.Name+": "+ct)
+			}
+			limited := io.LimitReader(resp.Body, maxRatioConfigBytes)
 			// 兼容两种上游接口格式：
 			//  type1: /api/ratio_config -> data 为 map[string]any，包含 model_ratio/completion_ratio/cache_ratio/model_price
 			//  type2: /api/pricing      -> data 为 []Pricing 列表，需要转换为与 type1 相同的 map 格式
@@ -141,7 +202,7 @@ func FetchUpstreamRatios(c *gin.Context) {
 				Message string          `json:"message"`
 			}
 
-			if err := json.NewDecoder(resp.Body).Decode(&body); err != nil {
+			if err := json.NewDecoder(limited).Decode(&body); err != nil {
 				logger.LogWarn(c.Request.Context(), "json decode failed from "+chItem.Name+": "+err.Error())
 				ch <- upstreamResult{Name: uniqueName, Err: err.Error()}
 				return
@@ -152,6 +213,8 @@ func FetchUpstreamRatios(c *gin.Context) {
 				return
 			}
 
+			// 若 Data 为空，将继续按 type1 尝试解析（与多数静态 ratio_config 兼容）
+
 			// 尝试按 type1 解析
 			var type1Data map[string]any
 			if err := json.Unmarshal(body.Data, &type1Data); err == nil {
@@ -357,9 +420,9 @@ func buildDifferences(localData map[string]any, successfulChannels []struct {
 						upstreamValue = val
 						hasUpstreamValue = true
 
-						if localValue != nil && localValue != val {
+						if localValue != nil && !valuesEqual(localValue, val) {
 							hasDifference = true
-						} else if localValue == val {
+						} else if valuesEqual(localValue, val) {
 							upstreamValue = "same"
 						}
 					}
@@ -466,6 +529,13 @@ func GetSyncableChannels(c *gin.Context) {
 		}
 	}
 
+	syncableChannels = append(syncableChannels, dto.SyncableChannel{
+		ID:      -100,
+		Name:    "官方倍率预设",
+		BaseURL: "https://basellm.github.io",
+		Status:  1,
+	})
+
 	c.JSON(http.StatusOK, gin.H{
 		"success": true,
 		"message": "",

controller/redemption.go

@@ -3,11 +3,12 @@ package controller
 import (
 	"errors"
 	"net/http"
-	"one-api/common"
-	"one-api/model"
 	"strconv"
 	"unicode/utf8"
 
+	"github.com/QuantumNous/new-api/common"
+	"github.com/QuantumNous/new-api/model"
+
 	"github.com/gin-gonic/gin"
 )
 

controller/relay.go

@@ -2,26 +2,30 @@ package controller
 
 import (
 	"bytes"
+	"errors"
 	"fmt"
-	"github.com/bytedance/gopkg/util/gopool"
 	"io"
 	"log"
 	"net/http"
-	"one-api/common"
-	"one-api/constant"
-	"one-api/dto"
-	"one-api/logger"
-	"one-api/middleware"
-	"one-api/model"
-	"one-api/relay"
-	relaycommon "one-api/relay/common"
-	relayconstant "one-api/relay/constant"
-	"one-api/relay/helper"
-	"one-api/service"
-	"one-api/setting"
-	"one-api/types"
 	"strings"
 
+	"github.com/QuantumNous/new-api/common"
+	"github.com/QuantumNous/new-api/constant"
+	"github.com/QuantumNous/new-api/dto"
+	"github.com/QuantumNous/new-api/logger"
+	"github.com/QuantumNous/new-api/middleware"
+	"github.com/QuantumNous/new-api/model"
+	"github.com/QuantumNous/new-api/relay"
+	relaycommon "github.com/QuantumNous/new-api/relay/common"
+	relayconstant "github.com/QuantumNous/new-api/relay/constant"
+	"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"
+
 	"github.com/gin-gonic/gin"
 	"github.com/gorilla/websocket"
 )
@@ -41,7 +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)
@@ -62,8 +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
@@ -82,6 +86,7 @@ func Relay(c *gin.Context, relayFormat types.RelayFormat) {
 
 	defer func() {
 		if newAPIError != nil {
+			logger.LogError(c, fmt.Sprintf("relay error: %s", newAPIError.Error()))
 			newAPIError.SetMessage(common.MessageWithRequestId(newAPIError.Error(), requestId))
 			switch relayFormat {
 			case types.RelayFormatOpenAIRealtime:
@@ -101,7 +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
 	}
 
@@ -111,9 +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, ", ")))
@@ -122,13 +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 {
@@ -138,28 +156,52 @@ func Relay(c *gin.Context, relayFormat types.RelayFormat) {
 
 	// common.SetContextKey(c, constant.ContextKeyTokenCountMeta, meta)
 
-	preConsumedQuota, newAPIError := service.PreConsumeQuota(c, priceData.ShouldPreConsumedQuota, relayInfo)
-	if newAPIError != nil {
-		return
+	if priceData.FreeModel {
+		logger.LogInfo(c, fmt.Sprintf("模型 %s 免费，跳过预扣费", relayInfo.OriginModelName))
+	} else {
+		newAPIError = service.PreConsumeBilling(c, priceData.QuotaToPreConsume, relayInfo)
+		if newAPIError != nil {
+			return
+		}
 	}
 
 	defer func() {
 		// Only return quota if downstream failed and quota was actually pre-consumed
-		if newAPIError != nil && preConsumedQuota != 0 {
-			service.ReturnPreConsumedQuota(c, relayInfo, preConsumedQuota)
+		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 {
@@ -177,9 +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
 		}
 	}
@@ -204,8 +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 {
@@ -218,14 +289,18 @@ func getChannel(c *gin.Context, group, originalModel string, retryCount int) (*m
 			AutoBan: &autoBanInt,
 		}, nil
 	}
-	channel, selectGroup, err := model.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（数据库一致性已被破坏，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
 	}
@@ -236,6 +311,9 @@ func shouldRetry(c *gin.Context, openaiErr *types.NewAPIError, retryTimes int) b
 	if openaiErr == nil {
 		return false
 	}
+	if service.ShouldSkipRetryAfterChannelAffinityFailure(c) {
+		return false
+	}
 	if types.IsChannelError(openaiErr) {
 		return true
 	}
@@ -248,42 +326,25 @@ 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("relay error (channel #%d, status code: %d): %s", channelError.ChannelId, err.StatusCode, err.Error()))
-
-	gopool.Go(func() {
-		// 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 {
-			service.DisableChannel(channelError, err.Error())
-		}
-	})
+	logger.LogError(c, fmt.Sprintf("channel error (channel #%d, status code: %d): %s", channelError.ChannelId, err.StatusCode, err.Error()))
+	// 不要使用context获取渠道信息，异步处理时可能会出现渠道信息不一致的情况
+	// do not use context to get channel info, there may be inconsistent channel info when processing asynchronously
+	if service.ShouldDisableChannel(channelError.ChannelType, err) && channelError.AutoBan {
+		gopool.Go(func() {
+			service.DisableChannel(channelError, err.ErrorWithStatusCode())
+		})
+	}
 
 	if constant.ErrorLogEnabled && types.IsRecordErrorLog(err) {
 		// 保存错误日志到mysql中
@@ -294,6 +355,9 @@ func processChannelError(c *gin.Context, channelError types.ChannelError, err *t
 		userGroup := c.GetString("group")
 		channelId := c.GetInt("channel_id")
 		other := make(map[string]interface{})
+		if c.Request != nil && c.Request.URL != nil {
+			other["request_path"] = c.Request.URL.Path
+		}
 		other["error_type"] = err.GetErrorType()
 		other["error_code"] = err.GetErrorCode()
 		other["status_code"] = err.StatusCode
@@ -307,8 +371,9 @@ 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)
 	}
 
 }
@@ -357,7 +422,7 @@ 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:   "",
@@ -369,7 +434,7 @@ 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:   "",
@@ -383,16 +448,23 @@ func RelayNotFound(c *gin.Context) {
 func RelayTask(c *gin.Context) {
 	retryTimes := common.RetryTimes
 	channelId := c.GetInt("channel_id")
-	relayMode := c.GetInt("relay_mode")
-	group := c.GetString("group")
-	originalModel := c.GetString("original_model")
 	c.Set("use_channel", []string{fmt.Sprintf("%d", channelId)})
-	taskErr := taskRelayHandler(c, relayMode)
+	relayInfo, err := relaycommon.GenRelayInfo(c, types.RelayFormatTask, nil, nil)
+	if err != nil {
+		return
+	}
+	taskErr := taskRelayHandler(c, relayInfo)
 	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)
@@ -402,12 +474,20 @@ 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, relayMode)
+		taskErr = taskRelayHandler(c, relayInfo)
 	}
 	useChannel := c.GetStringSlice("use_channel")
 	if len(useChannel) > 1 {
@@ -422,13 +502,13 @@ func RelayTask(c *gin.Context) {
 	}
 }
 
-func taskRelayHandler(c *gin.Context, relayMode int) *dto.TaskError {
+func taskRelayHandler(c *gin.Context, relayInfo *relaycommon.RelayInfo) *dto.TaskError {
 	var err *dto.TaskError
-	switch relayMode {
+	switch relayInfo.RelayMode {
 	case relayconstant.RelayModeSunoFetch, relayconstant.RelayModeSunoFetchByID, relayconstant.RelayModeVideoFetchByID:
-		err = relay.RelayTaskFetch(c, relayMode)
+		err = relay.RelayTaskFetch(c, relayInfo.RelayMode)
 	default:
-		err = relay.RelayTaskSubmit(c, relayMode)
+		err = relay.RelayTaskSubmit(c, relayInfo)
 	}
 	return err
 }
@@ -437,6 +517,9 @@ func shouldRetryTaskRelay(c *gin.Context, channelId int, taskErr *dto.TaskError,
 	if taskErr == nil {
 		return false
 	}
+	if service.ShouldSkipRetryAfterChannelAffinityFailure(c) {
+		return false
+	}
 	if retryTimes <= 0 {
 		return false
 	}

controller/secure_verification.go

@@ -0,0 +1,314 @@
+package controller
+
+import (
+	"fmt"
+	"net/http"
+	"time"
+
+	"github.com/QuantumNous/new-api/common"
+	"github.com/QuantumNous/new-api/model"
+	passkeysvc "github.com/QuantumNous/new-api/service/passkey"
+	"github.com/QuantumNous/new-api/setting/system_setting"
+
+	"github.com/gin-contrib/sessions"
+	"github.com/gin-gonic/gin"
+)
+
+const (
+	// SecureVerificationSessionKey 安全验证的 session key
+	SecureVerificationSessionKey = "secure_verified_at"
+	// SecureVerificationTimeout 验证有效期（秒）
+	SecureVerificationTimeout = 300 // 5分钟
+)
+
+type UniversalVerifyRequest struct {
+	Method string `json:"method"` // "2fa" 或 "passkey"
+	Code   string `json:"code,omitempty"`
+}
+
+type VerificationStatusResponse struct {
+	Verified  bool  `json:"verified"`
+	ExpiresAt int64 `json:"expires_at,omitempty"`
+}
+
+// UniversalVerify 通用验证接口
+// 支持 2FA 和 Passkey 验证，验证成功后在 session 中记录时间戳
+func UniversalVerify(c *gin.Context) {
+	userId := c.GetInt("id")
+	if userId == 0 {
+		c.JSON(http.StatusUnauthorized, gin.H{
+			"success": false,
+			"message": "未登录",
+		})
+		return
+	}
+
+	var req UniversalVerifyRequest
+	if err := c.ShouldBindJSON(&req); err != nil {
+		common.ApiError(c, fmt.Errorf("参数错误: %v", err))
+		return
+	}
+
+	// 获取用户信息
+	user := &model.User{Id: userId}
+	if err := user.FillUserById(); err != nil {
+		common.ApiError(c, fmt.Errorf("获取用户信息失败: %v", err))
+		return
+	}
+
+	if user.Status != common.UserStatusEnabled {
+		common.ApiError(c, fmt.Errorf("该用户已被禁用"))
+		return
+	}
+
+	// 检查用户的验证方式
+	twoFA, _ := model.GetTwoFAByUserId(userId)
+	has2FA := twoFA != nil && twoFA.IsEnabled
+
+	passkey, passkeyErr := model.GetPasskeyByUserID(userId)
+	hasPasskey := passkeyErr == nil && passkey != nil
+
+	if !has2FA && !hasPasskey {
+		common.ApiError(c, fmt.Errorf("用户未启用2FA或Passkey"))
+		return
+	}
+
+	// 根据验证方式进行验证
+	var verified bool
+	var verifyMethod string
+
+	switch req.Method {
+	case "2fa":
+		if !has2FA {
+			common.ApiError(c, fmt.Errorf("用户未启用2FA"))
+			return
+		}
+		if req.Code == "" {
+			common.ApiError(c, fmt.Errorf("验证码不能为空"))
+			return
+		}
+		verified = validateTwoFactorAuth(twoFA, req.Code)
+		verifyMethod = "2FA"
+
+	case "passkey":
+		if !hasPasskey {
+			common.ApiError(c, fmt.Errorf("用户未启用Passkey"))
+			return
+		}
+		// Passkey 验证需要先调用 PasskeyVerifyBegin 和 PasskeyVerifyFinish
+		// 这里只是验证 Passkey 验证流程是否已经完成
+		// 实际上，前端应该先调用这两个接口，然后再调用本接口
+		verified = true // Passkey 验证逻辑已在 PasskeyVerifyFinish 中完成
+		verifyMethod = "Passkey"
+
+	default:
+		common.ApiError(c, fmt.Errorf("不支持的验证方式: %s", req.Method))
+		return
+	}
+
+	if !verified {
+		common.ApiError(c, fmt.Errorf("验证失败，请检查验证码"))
+		return
+	}
+
+	// 验证成功，在 session 中记录时间戳
+	session := sessions.Default(c)
+	now := time.Now().Unix()
+	session.Set(SecureVerificationSessionKey, now)
+	if err := session.Save(); err != nil {
+		common.ApiError(c, fmt.Errorf("保存验证状态失败: %v", err))
+		return
+	}
+
+	// 记录日志
+	model.RecordLog(userId, model.LogTypeSystem, fmt.Sprintf("通用安全验证成功 (验证方式: %s)", verifyMethod))
+
+	c.JSON(http.StatusOK, gin.H{
+		"success": true,
+		"message": "验证成功",
+		"data": gin.H{
+			"verified":   true,
+			"expires_at": now + SecureVerificationTimeout,
+		},
+	})
+}
+
+// GetVerificationStatus 获取验证状态
+func GetVerificationStatus(c *gin.Context) {
+	userId := c.GetInt("id")
+	if userId == 0 {
+		c.JSON(http.StatusUnauthorized, gin.H{
+			"success": false,
+			"message": "未登录",
+		})
+		return
+	}
+
+	session := sessions.Default(c)
+	verifiedAtRaw := session.Get(SecureVerificationSessionKey)
+
+	if verifiedAtRaw == nil {
+		c.JSON(http.StatusOK, gin.H{
+			"success": true,
+			"message": "",
+			"data": VerificationStatusResponse{
+				Verified: false,
+			},
+		})
+		return
+	}
+
+	verifiedAt, ok := verifiedAtRaw.(int64)
+	if !ok {
+		c.JSON(http.StatusOK, gin.H{
+			"success": true,
+			"message": "",
+			"data": VerificationStatusResponse{
+				Verified: false,
+			},
+		})
+		return
+	}
+
+	elapsed := time.Now().Unix() - verifiedAt
+	if elapsed >= SecureVerificationTimeout {
+		// 验证已过期
+		session.Delete(SecureVerificationSessionKey)
+		_ = session.Save()
+		c.JSON(http.StatusOK, gin.H{
+			"success": true,
+			"message": "",
+			"data": VerificationStatusResponse{
+				Verified: false,
+			},
+		})
+		return
+	}
+
+	c.JSON(http.StatusOK, gin.H{
+		"success": true,
+		"message": "",
+		"data": VerificationStatusResponse{
+			Verified:  true,
+			ExpiresAt: verifiedAt + SecureVerificationTimeout,
+		},
+	})
+}
+
+// CheckSecureVerification 检查是否已通过安全验证
+// 返回 true 表示验证有效，false 表示需要重新验证
+func CheckSecureVerification(c *gin.Context) bool {
+	session := sessions.Default(c)
+	verifiedAtRaw := session.Get(SecureVerificationSessionKey)
+
+	if verifiedAtRaw == nil {
+		return false
+	}
+
+	verifiedAt, ok := verifiedAtRaw.(int64)
+	if !ok {
+		return false
+	}
+
+	elapsed := time.Now().Unix() - verifiedAt
+	if elapsed >= SecureVerificationTimeout {
+		// 验证已过期，清除 session
+		session.Delete(SecureVerificationSessionKey)
+		_ = session.Save()
+		return false
+	}
+
+	return true
+}
+
+// PasskeyVerifyAndSetSession Passkey 验证完成后设置 session
+// 这是一个辅助函数，供 PasskeyVerifyFinish 调用
+func PasskeyVerifyAndSetSession(c *gin.Context) {
+	session := sessions.Default(c)
+	now := time.Now().Unix()
+	session.Set(SecureVerificationSessionKey, now)
+	_ = session.Save()
+}
+
+// PasskeyVerifyForSecure 用于安全验证的 Passkey 验证流程
+// 整合了 begin 和 finish 流程
+func PasskeyVerifyForSecure(c *gin.Context) {
+	if !system_setting.GetPasskeySettings().Enabled {
+		c.JSON(http.StatusOK, gin.H{
+			"success": false,
+			"message": "管理员未启用 Passkey 登录",
+		})
+		return
+	}
+
+	userId := c.GetInt("id")
+	if userId == 0 {
+		c.JSON(http.StatusUnauthorized, gin.H{
+			"success": false,
+			"message": "未登录",
+		})
+		return
+	}
+
+	user := &model.User{Id: userId}
+	if err := user.FillUserById(); err != nil {
+		common.ApiError(c, fmt.Errorf("获取用户信息失败: %v", err))
+		return
+	}
+
+	if user.Status != common.UserStatusEnabled {
+		common.ApiError(c, fmt.Errorf("该用户已被禁用"))
+		return
+	}
+
+	credential, err := model.GetPasskeyByUserID(userId)
+	if err != nil {
+		c.JSON(http.StatusOK, gin.H{
+			"success": false,
+			"message": "该用户尚未绑定 Passkey",
+		})
+		return
+	}
+
+	wa, err := passkeysvc.BuildWebAuthn(c.Request)
+	if err != nil {
+		common.ApiError(c, err)
+		return
+	}
+
+	waUser := passkeysvc.NewWebAuthnUser(user, credential)
+	sessionData, err := passkeysvc.PopSessionData(c, passkeysvc.VerifySessionKey)
+	if err != nil {
+		common.ApiError(c, err)
+		return
+	}
+
+	_, err = wa.FinishLogin(waUser, *sessionData, c.Request)
+	if err != nil {
+		common.ApiError(c, err)
+		return
+	}
+
+	// 更新凭证的最后使用时间
+	now := time.Now()
+	credential.LastUsedAt = &now
+	if err := model.UpsertPasskeyCredential(credential); err != nil {
+		common.ApiError(c, err)
+		return
+	}
+
+	// 验证成功，设置 session
+	PasskeyVerifyAndSetSession(c)
+
+	// 记录日志
+	model.RecordLog(userId, model.LogTypeSystem, "Passkey 安全验证成功")
+
+	c.JSON(http.StatusOK, gin.H{
+		"success": true,
+		"message": "Passkey 验证成功",
+		"data": gin.H{
+			"verified":   true,
+			"expires_at": time.Now().Unix() + SecureVerificationTimeout,
+		},
+	})
+}

controller/setup.go

@@ -1,12 +1,13 @@
 package controller
 
 import (
-	"github.com/gin-gonic/gin"
-	"one-api/common"
-	"one-api/constant"
-	"one-api/model"
-	"one-api/setting/operation_setting"
 	"time"
+
+	"github.com/QuantumNous/new-api/common"
+	"github.com/QuantumNous/new-api/constant"
+	"github.com/QuantumNous/new-api/model"
+	"github.com/QuantumNous/new-api/setting/operation_setting"
+	"github.com/gin-gonic/gin"
 )
 
 type Setup struct {
@@ -53,7 +54,7 @@ func GetSetup(c *gin.Context) {
 func PostSetup(c *gin.Context) {
 	// Check if setup is already completed
 	if constant.Setup {
-		c.JSON(400, gin.H{
+		c.JSON(200, gin.H{
 			"success": false,
 			"message": "系统已经初始化完成",
 		})
@@ -66,7 +67,7 @@ func PostSetup(c *gin.Context) {
 	var req SetupRequest
 	err := c.ShouldBindJSON(&req)
 	if err != nil {
-		c.JSON(400, gin.H{
+		c.JSON(200, gin.H{
 			"success": false,
 			"message": "请求参数有误",
 		})
@@ -77,7 +78,7 @@ func PostSetup(c *gin.Context) {
 	if !rootExists {
 		// Validate username length: max 12 characters to align with model.User validation
 		if len(req.Username) > 12 {
-			c.JSON(400, gin.H{
+			c.JSON(200, gin.H{
 				"success": false,
 				"message": "用户名长度不能超过12个字符",
 			})
@@ -85,7 +86,7 @@ func PostSetup(c *gin.Context) {
 		}
 		// Validate password
 		if req.Password != req.ConfirmPassword {
-			c.JSON(400, gin.H{
+			c.JSON(200, gin.H{
 				"success": false,
 				"message": "两次输入的密码不一致",
 			})
@@ -93,7 +94,7 @@ func PostSetup(c *gin.Context) {
 		}
 
 		if len(req.Password) < 8 {
-			c.JSON(400, gin.H{
+			c.JSON(200, gin.H{
 				"success": false,
 				"message": "密码长度至少为8个字符",
 			})
@@ -103,7 +104,7 @@ func PostSetup(c *gin.Context) {
 		// Create root user
 		hashedPassword, err := common.Password2Hash(req.Password)
 		if err != nil {
-			c.JSON(500, gin.H{
+			c.JSON(200, gin.H{
 				"success": false,
 				"message": "系统错误: " + err.Error(),
 			})
@@ -120,7 +121,7 @@ func PostSetup(c *gin.Context) {
 		}
 		err = model.DB.Create(&rootUser).Error
 		if err != nil {
-			c.JSON(500, gin.H{
+			c.JSON(200, gin.H{
 				"success": false,
 				"message": "创建管理员账号失败: " + err.Error(),
 			})
@@ -135,7 +136,7 @@ func PostSetup(c *gin.Context) {
 	// Save operation modes to database for persistence
 	err = model.UpdateOption("SelfUseModeEnabled", boolToString(req.SelfUseModeEnabled))
 	if err != nil {
-		c.JSON(500, gin.H{
+		c.JSON(200, gin.H{
 			"success": false,
 			"message": "保存自用模式设置失败: " + err.Error(),
 		})
@@ -144,7 +145,7 @@ func PostSetup(c *gin.Context) {
 
 	err = model.UpdateOption("DemoSiteEnabled", boolToString(req.DemoSiteEnabled))
 	if err != nil {
-		c.JSON(500, gin.H{
+		c.JSON(200, gin.H{
 			"success": false,
 			"message": "保存演示站点模式设置失败: " + err.Error(),
 		})
@@ -160,7 +161,7 @@ func PostSetup(c *gin.Context) {
 	}
 	err = model.DB.Create(&setup).Error
 	if err != nil {
-		c.JSON(500, gin.H{
+		c.JSON(200, gin.H{
 			"success": false,
 			"message": "系统初始化失败: " + err.Error(),
 		})

controller/subscription.go

@@ -0,0 +1,367 @@
+package controller
+
+import (
+	"strconv"
+	"strings"
+
+	"github.com/QuantumNous/new-api/common"
+	"github.com/QuantumNous/new-api/model"
+	"github.com/QuantumNous/new-api/setting/ratio_setting"
+	"github.com/gin-gonic/gin"
+	"gorm.io/gorm"
+)
+
+// ---- Shared types ----
+
+type SubscriptionPlanDTO struct {
+	Plan model.SubscriptionPlan `json:"plan"`
+}
+
+type BillingPreferenceRequest struct {
+	BillingPreference string `json:"billing_preference"`
+}
+
+// ---- User APIs ----
+
+func GetSubscriptionPlans(c *gin.Context) {
+	var plans []model.SubscriptionPlan
+	if err := model.DB.Where("enabled = ?", true).Order("sort_order desc, id desc").Find(&plans).Error; err != nil {
+		common.ApiError(c, err)
+		return
+	}
+	result := make([]SubscriptionPlanDTO, 0, len(plans))
+	for _, p := range plans {
+		result = append(result, SubscriptionPlanDTO{
+			Plan: p,
+		})
+	}
+	common.ApiSuccess(c, result)
+}
+
+func GetSubscriptionSelf(c *gin.Context) {
+	userId := c.GetInt("id")
+	settingMap, _ := model.GetUserSetting(userId, false)
+	pref := common.NormalizeBillingPreference(settingMap.BillingPreference)
+
+	// Get all subscriptions (including expired)
+	allSubscriptions, err := model.GetAllUserSubscriptions(userId)
+	if err != nil {
+		allSubscriptions = []model.SubscriptionSummary{}
+	}
+
+	// Get active subscriptions for backward compatibility
+	activeSubscriptions, err := model.GetAllActiveUserSubscriptions(userId)
+	if err != nil {
+		activeSubscriptions = []model.SubscriptionSummary{}
+	}
+
+	common.ApiSuccess(c, gin.H{
+		"billing_preference": pref,
+		"subscriptions":      activeSubscriptions, // all active subscriptions
+		"all_subscriptions":  allSubscriptions,    // all subscriptions including expired
+	})
+}
+
+func UpdateSubscriptionPreference(c *gin.Context) {
+	userId := c.GetInt("id")
+	var req BillingPreferenceRequest
+	if err := c.ShouldBindJSON(&req); err != nil {
+		common.ApiErrorMsg(c, "参数错误")
+		return
+	}
+	pref := common.NormalizeBillingPreference(req.BillingPreference)
+
+	user, err := model.GetUserById(userId, true)
+	if err != nil {
+		common.ApiError(c, err)
+		return
+	}
+	current := user.GetSetting()
+	current.BillingPreference = pref
+	user.SetSetting(current)
+	if err := user.Update(false); err != nil {
+		common.ApiError(c, err)
+		return
+	}
+	common.ApiSuccess(c, gin.H{"billing_preference": pref})
+}
+
+// ---- Admin APIs ----
+
+func AdminListSubscriptionPlans(c *gin.Context) {
+	var plans []model.SubscriptionPlan
+	if err := model.DB.Order("sort_order desc, id desc").Find(&plans).Error; err != nil {
+		common.ApiError(c, err)
+		return
+	}
+	result := make([]SubscriptionPlanDTO, 0, len(plans))
+	for _, p := range plans {
+		result = append(result, SubscriptionPlanDTO{
+			Plan: p,
+		})
+	}
+	common.ApiSuccess(c, result)
+}
+
+type AdminUpsertSubscriptionPlanRequest struct {
+	Plan model.SubscriptionPlan `json:"plan"`
+}
+
+func AdminCreateSubscriptionPlan(c *gin.Context) {
+	var req AdminUpsertSubscriptionPlanRequest
+	if err := c.ShouldBindJSON(&req); err != nil {
+		common.ApiErrorMsg(c, "参数错误")
+		return
+	}
+	req.Plan.Id = 0
+	if strings.TrimSpace(req.Plan.Title) == "" {
+		common.ApiErrorMsg(c, "套餐标题不能为空")
+		return
+	}
+	if req.Plan.Currency == "" {
+		req.Plan.Currency = "USD"
+	}
+	req.Plan.Currency = "USD"
+	if req.Plan.DurationUnit == "" {
+		req.Plan.DurationUnit = model.SubscriptionDurationMonth
+	}
+	if req.Plan.DurationValue <= 0 && req.Plan.DurationUnit != model.SubscriptionDurationCustom {
+		req.Plan.DurationValue = 1
+	}
+	if req.Plan.MaxPurchasePerUser < 0 {
+		common.ApiErrorMsg(c, "购买上限不能为负数")
+		return
+	}
+	if req.Plan.TotalAmount < 0 {
+		common.ApiErrorMsg(c, "总额度不能为负数")
+		return
+	}
+	req.Plan.UpgradeGroup = strings.TrimSpace(req.Plan.UpgradeGroup)
+	if req.Plan.UpgradeGroup != "" {
+		if _, ok := ratio_setting.GetGroupRatioCopy()[req.Plan.UpgradeGroup]; !ok {
+			common.ApiErrorMsg(c, "升级分组不存在")
+			return
+		}
+	}
+	req.Plan.QuotaResetPeriod = model.NormalizeResetPeriod(req.Plan.QuotaResetPeriod)
+	if req.Plan.QuotaResetPeriod == model.SubscriptionResetCustom && req.Plan.QuotaResetCustomSeconds <= 0 {
+		common.ApiErrorMsg(c, "自定义重置周期需大于0秒")
+		return
+	}
+	err := model.DB.Create(&req.Plan).Error
+	if err != nil {
+		common.ApiError(c, err)
+		return
+	}
+	model.InvalidateSubscriptionPlanCache(req.Plan.Id)
+	common.ApiSuccess(c, req.Plan)
+}
+
+func AdminUpdateSubscriptionPlan(c *gin.Context) {
+	id, _ := strconv.Atoi(c.Param("id"))
+	if id <= 0 {
+		common.ApiErrorMsg(c, "无效的ID")
+		return
+	}
+	var req AdminUpsertSubscriptionPlanRequest
+	if err := c.ShouldBindJSON(&req); err != nil {
+		common.ApiErrorMsg(c, "参数错误")
+		return
+	}
+	if strings.TrimSpace(req.Plan.Title) == "" {
+		common.ApiErrorMsg(c, "套餐标题不能为空")
+		return
+	}
+	req.Plan.Id = id
+	if req.Plan.Currency == "" {
+		req.Plan.Currency = "USD"
+	}
+	req.Plan.Currency = "USD"
+	if req.Plan.DurationUnit == "" {
+		req.Plan.DurationUnit = model.SubscriptionDurationMonth
+	}
+	if req.Plan.DurationValue <= 0 && req.Plan.DurationUnit != model.SubscriptionDurationCustom {
+		req.Plan.DurationValue = 1
+	}
+	if req.Plan.MaxPurchasePerUser < 0 {
+		common.ApiErrorMsg(c, "购买上限不能为负数")
+		return
+	}
+	if req.Plan.TotalAmount < 0 {
+		common.ApiErrorMsg(c, "总额度不能为负数")
+		return
+	}
+	req.Plan.UpgradeGroup = strings.TrimSpace(req.Plan.UpgradeGroup)
+	if req.Plan.UpgradeGroup != "" {
+		if _, ok := ratio_setting.GetGroupRatioCopy()[req.Plan.UpgradeGroup]; !ok {
+			common.ApiErrorMsg(c, "升级分组不存在")
+			return
+		}
+	}
+	req.Plan.QuotaResetPeriod = model.NormalizeResetPeriod(req.Plan.QuotaResetPeriod)
+	if req.Plan.QuotaResetPeriod == model.SubscriptionResetCustom && req.Plan.QuotaResetCustomSeconds <= 0 {
+		common.ApiErrorMsg(c, "自定义重置周期需大于0秒")
+		return
+	}
+
+	err := model.DB.Transaction(func(tx *gorm.DB) error {
+		// update plan (allow zero values updates with map)
+		updateMap := map[string]interface{}{
+			"title":                      req.Plan.Title,
+			"subtitle":                   req.Plan.Subtitle,
+			"price_amount":               req.Plan.PriceAmount,
+			"currency":                   req.Plan.Currency,
+			"duration_unit":              req.Plan.DurationUnit,
+			"duration_value":             req.Plan.DurationValue,
+			"custom_seconds":             req.Plan.CustomSeconds,
+			"enabled":                    req.Plan.Enabled,
+			"sort_order":                 req.Plan.SortOrder,
+			"stripe_price_id":            req.Plan.StripePriceId,
+			"creem_product_id":           req.Plan.CreemProductId,
+			"max_purchase_per_user":      req.Plan.MaxPurchasePerUser,
+			"total_amount":               req.Plan.TotalAmount,
+			"upgrade_group":              req.Plan.UpgradeGroup,
+			"quota_reset_period":         req.Plan.QuotaResetPeriod,
+			"quota_reset_custom_seconds": req.Plan.QuotaResetCustomSeconds,
+			"updated_at":                 common.GetTimestamp(),
+		}
+		if err := tx.Model(&model.SubscriptionPlan{}).Where("id = ?", id).Updates(updateMap).Error; err != nil {
+			return err
+		}
+		return nil
+	})
+	if err != nil {
+		common.ApiError(c, err)
+		return
+	}
+	model.InvalidateSubscriptionPlanCache(id)
+	common.ApiSuccess(c, nil)
+}
+
+type AdminUpdateSubscriptionPlanStatusRequest struct {
+	Enabled *bool `json:"enabled"`
+}
+
+func AdminUpdateSubscriptionPlanStatus(c *gin.Context) {
+	id, _ := strconv.Atoi(c.Param("id"))
+	if id <= 0 {
+		common.ApiErrorMsg(c, "无效的ID")
+		return
+	}
+	var req AdminUpdateSubscriptionPlanStatusRequest
+	if err := c.ShouldBindJSON(&req); err != nil || req.Enabled == nil {
+		common.ApiErrorMsg(c, "参数错误")
+		return
+	}
+	if err := model.DB.Model(&model.SubscriptionPlan{}).Where("id = ?", id).Update("enabled", *req.Enabled).Error; err != nil {
+		common.ApiError(c, err)
+		return
+	}
+	model.InvalidateSubscriptionPlanCache(id)
+	common.ApiSuccess(c, nil)
+}
+
+type AdminBindSubscriptionRequest struct {
+	UserId int `json:"user_id"`
+	PlanId int `json:"plan_id"`
+}
+
+func AdminBindSubscription(c *gin.Context) {
+	var req AdminBindSubscriptionRequest
+	if err := c.ShouldBindJSON(&req); err != nil || req.UserId <= 0 || req.PlanId <= 0 {
+		common.ApiErrorMsg(c, "参数错误")
+		return
+	}
+	msg, err := model.AdminBindSubscription(req.UserId, req.PlanId, "")
+	if err != nil {
+		common.ApiError(c, err)
+		return
+	}
+	if msg != "" {
+		common.ApiSuccess(c, gin.H{"message": msg})
+		return
+	}
+	common.ApiSuccess(c, nil)
+}
+
+// ---- Admin: user subscription management ----
+
+func AdminListUserSubscriptions(c *gin.Context) {
+	userId, _ := strconv.Atoi(c.Param("id"))
+	if userId <= 0 {
+		common.ApiErrorMsg(c, "无效的用户ID")
+		return
+	}
+	subs, err := model.GetAllUserSubscriptions(userId)
+	if err != nil {
+		common.ApiError(c, err)
+		return
+	}
+	common.ApiSuccess(c, subs)
+}
+
+type AdminCreateUserSubscriptionRequest struct {
+	PlanId int `json:"plan_id"`
+}
+
+// AdminCreateUserSubscription creates a new user subscription from a plan (no payment).
+func AdminCreateUserSubscription(c *gin.Context) {
+	userId, _ := strconv.Atoi(c.Param("id"))
+	if userId <= 0 {
+		common.ApiErrorMsg(c, "无效的用户ID")
+		return
+	}
+	var req AdminCreateUserSubscriptionRequest
+	if err := c.ShouldBindJSON(&req); err != nil || req.PlanId <= 0 {
+		common.ApiErrorMsg(c, "参数错误")
+		return
+	}
+	msg, err := model.AdminBindSubscription(userId, req.PlanId, "")
+	if err != nil {
+		common.ApiError(c, err)
+		return
+	}
+	if msg != "" {
+		common.ApiSuccess(c, gin.H{"message": msg})
+		return
+	}
+	common.ApiSuccess(c, nil)
+}
+
+// AdminInvalidateUserSubscription cancels a user subscription immediately.
+func AdminInvalidateUserSubscription(c *gin.Context) {
+	subId, _ := strconv.Atoi(c.Param("id"))
+	if subId <= 0 {
+		common.ApiErrorMsg(c, "无效的订阅ID")
+		return
+	}
+	msg, err := model.AdminInvalidateUserSubscription(subId)
+	if err != nil {
+		common.ApiError(c, err)
+		return
+	}
+	if msg != "" {
+		common.ApiSuccess(c, gin.H{"message": msg})
+		return
+	}
+	common.ApiSuccess(c, nil)
+}
+
+// AdminDeleteUserSubscription hard-deletes a user subscription.
+func AdminDeleteUserSubscription(c *gin.Context) {
+	subId, _ := strconv.Atoi(c.Param("id"))
+	if subId <= 0 {
+		common.ApiErrorMsg(c, "无效的订阅ID")
+		return
+	}
+	msg, err := model.AdminDeleteUserSubscription(subId)
+	if err != nil {
+		common.ApiError(c, err)
+		return
+	}
+	if msg != "" {
+		common.ApiSuccess(c, gin.H{"message": msg})
+		return
+	}
+	common.ApiSuccess(c, nil)
+}

controller/subscription_payment_creem.go

@@ -0,0 +1,129 @@
+package controller
+
+import (
+	"bytes"
+	"io"
+	"log"
+	"time"
+
+	"github.com/QuantumNous/new-api/common"
+	"github.com/QuantumNous/new-api/model"
+	"github.com/QuantumNous/new-api/setting"
+	"github.com/QuantumNous/new-api/setting/operation_setting"
+	"github.com/gin-gonic/gin"
+	"github.com/thanhpk/randstr"
+)
+
+type SubscriptionCreemPayRequest struct {
+	PlanId int `json:"plan_id"`
+}
+
+func SubscriptionRequestCreemPay(c *gin.Context) {
+	var req SubscriptionCreemPayRequest
+
+	// Keep body for debugging consistency (like RequestCreemPay)
+	bodyBytes, err := io.ReadAll(c.Request.Body)
+	if err != nil {
+		log.Printf("read subscription creem pay req body err: %v", err)
+		c.JSON(200, gin.H{"message": "error", "data": "read query error"})
+		return
+	}
+	c.Request.Body = io.NopCloser(bytes.NewReader(bodyBytes))
+
+	if err := c.ShouldBindJSON(&req); err != nil || req.PlanId <= 0 {
+		c.JSON(200, gin.H{"message": "error", "data": "参数错误"})
+		return
+	}
+
+	plan, err := model.GetSubscriptionPlanById(req.PlanId)
+	if err != nil {
+		common.ApiError(c, err)
+		return
+	}
+	if !plan.Enabled {
+		common.ApiErrorMsg(c, "套餐未启用")
+		return
+	}
+	if plan.CreemProductId == "" {
+		common.ApiErrorMsg(c, "该套餐未配置 CreemProductId")
+		return
+	}
+	if setting.CreemWebhookSecret == "" && !setting.CreemTestMode {
+		common.ApiErrorMsg(c, "Creem Webhook 未配置")
+		return
+	}
+
+	userId := c.GetInt("id")
+	user, err := model.GetUserById(userId, false)
+	if err != nil {
+		common.ApiError(c, err)
+		return
+	}
+	if user == nil {
+		common.ApiErrorMsg(c, "用户不存在")
+		return
+	}
+
+	if plan.MaxPurchasePerUser > 0 {
+		count, err := model.CountUserSubscriptionsByPlan(userId, plan.Id)
+		if err != nil {
+			common.ApiError(c, err)
+			return
+		}
+		if count >= int64(plan.MaxPurchasePerUser) {
+			common.ApiErrorMsg(c, "已达到该套餐购买上限")
+			return
+		}
+	}
+
+	reference := "sub-creem-ref-" + randstr.String(6)
+	referenceId := "sub_ref_" + common.Sha1([]byte(reference+time.Now().String()+user.Username))
+
+	// create pending order first
+	order := &model.SubscriptionOrder{
+		UserId:        userId,
+		PlanId:        plan.Id,
+		Money:         plan.PriceAmount,
+		TradeNo:       referenceId,
+		PaymentMethod: PaymentMethodCreem,
+		CreateTime:    time.Now().Unix(),
+		Status:        common.TopUpStatusPending,
+	}
+	if err := order.Insert(); err != nil {
+		c.JSON(200, gin.H{"message": "error", "data": "创建订单失败"})
+		return
+	}
+
+	// Reuse Creem checkout generator by building a lightweight product reference.
+	currency := "USD"
+	switch operation_setting.GetGeneralSetting().QuotaDisplayType {
+	case operation_setting.QuotaDisplayTypeCNY:
+		currency = "CNY"
+	case operation_setting.QuotaDisplayTypeUSD:
+		currency = "USD"
+	default:
+		currency = "USD"
+	}
+	product := &CreemProduct{
+		ProductId: plan.CreemProductId,
+		Name:      plan.Title,
+		Price:     plan.PriceAmount,
+		Currency:  currency,
+		Quota:     0,
+	}
+
+	checkoutUrl, err := genCreemLink(referenceId, product, user.Email, user.Username)
+	if err != nil {
+		log.Printf("获取Creem支付链接失败: %v", err)
+		c.JSON(200, gin.H{"message": "error", "data": "拉起支付失败"})
+		return
+	}
+
+	c.JSON(200, gin.H{
+		"message": "success",
+		"data": gin.H{
+			"checkout_url": checkoutUrl,
+			"order_id":     referenceId,
+		},
+	})
+}

controller/subscription_payment_epay.go

@@ -0,0 +1,196 @@
+package controller
+
+import (
+	"fmt"
+	"net/http"
+	"net/url"
+	"strconv"
+	"time"
+
+	"github.com/Calcium-Ion/go-epay/epay"
+	"github.com/QuantumNous/new-api/common"
+	"github.com/QuantumNous/new-api/model"
+	"github.com/QuantumNous/new-api/service"
+	"github.com/QuantumNous/new-api/setting/operation_setting"
+	"github.com/QuantumNous/new-api/setting/system_setting"
+	"github.com/gin-gonic/gin"
+	"github.com/samber/lo"
+)
+
+type SubscriptionEpayPayRequest struct {
+	PlanId        int    `json:"plan_id"`
+	PaymentMethod string `json:"payment_method"`
+}
+
+func SubscriptionRequestEpay(c *gin.Context) {
+	var req SubscriptionEpayPayRequest
+	if err := c.ShouldBindJSON(&req); err != nil || req.PlanId <= 0 {
+		common.ApiErrorMsg(c, "参数错误")
+		return
+	}
+
+	plan, err := model.GetSubscriptionPlanById(req.PlanId)
+	if err != nil {
+		common.ApiError(c, err)
+		return
+	}
+	if !plan.Enabled {
+		common.ApiErrorMsg(c, "套餐未启用")
+		return
+	}
+	if plan.PriceAmount < 0.01 {
+		common.ApiErrorMsg(c, "套餐金额过低")
+		return
+	}
+	if !operation_setting.ContainsPayMethod(req.PaymentMethod) {
+		common.ApiErrorMsg(c, "支付方式不存在")
+		return
+	}
+
+	userId := c.GetInt("id")
+	if plan.MaxPurchasePerUser > 0 {
+		count, err := model.CountUserSubscriptionsByPlan(userId, plan.Id)
+		if err != nil {
+			common.ApiError(c, err)
+			return
+		}
+		if count >= int64(plan.MaxPurchasePerUser) {
+			common.ApiErrorMsg(c, "已达到该套餐购买上限")
+			return
+		}
+	}
+
+	callBackAddress := service.GetCallbackAddress()
+	returnUrl, err := url.Parse(callBackAddress + "/api/subscription/epay/return")
+	if err != nil {
+		common.ApiErrorMsg(c, "回调地址配置错误")
+		return
+	}
+	notifyUrl, err := url.Parse(callBackAddress + "/api/subscription/epay/notify")
+	if err != nil {
+		common.ApiErrorMsg(c, "回调地址配置错误")
+		return
+	}
+
+	tradeNo := fmt.Sprintf("%s%d", common.GetRandomString(6), time.Now().Unix())
+	tradeNo = fmt.Sprintf("SUBUSR%dNO%s", userId, tradeNo)
+
+	client := GetEpayClient()
+	if client == nil {
+		common.ApiErrorMsg(c, "当前管理员未配置支付信息")
+		return
+	}
+
+	order := &model.SubscriptionOrder{
+		UserId:        userId,
+		PlanId:        plan.Id,
+		Money:         plan.PriceAmount,
+		TradeNo:       tradeNo,
+		PaymentMethod: req.PaymentMethod,
+		CreateTime:    time.Now().Unix(),
+		Status:        common.TopUpStatusPending,
+	}
+	if err := order.Insert(); err != nil {
+		common.ApiErrorMsg(c, "创建订单失败")
+		return
+	}
+	uri, params, err := client.Purchase(&epay.PurchaseArgs{
+		Type:           req.PaymentMethod,
+		ServiceTradeNo: tradeNo,
+		Name:           fmt.Sprintf("SUB:%s", plan.Title),
+		Money:          strconv.FormatFloat(plan.PriceAmount, 'f', 2, 64),
+		Device:         epay.PC,
+		NotifyUrl:      notifyUrl,
+		ReturnUrl:      returnUrl,
+	})
+	if err != nil {
+		_ = model.ExpireSubscriptionOrder(tradeNo)
+		common.ApiErrorMsg(c, "拉起支付失败")
+		return
+	}
+	common.ApiSuccess(c, gin.H{"data": params, "url": uri})
+}
+
+func SubscriptionEpayNotify(c *gin.Context) {
+	if err := c.Request.ParseForm(); err != nil {
+		_, _ = c.Writer.Write([]byte("fail"))
+		return
+	}
+	params := lo.Reduce(lo.Keys(c.Request.PostForm), func(r map[string]string, t string, i int) map[string]string {
+		r[t] = c.Request.PostForm.Get(t)
+		return r
+	}, map[string]string{})
+	if len(params) == 0 {
+		params = lo.Reduce(lo.Keys(c.Request.URL.Query()), func(r map[string]string, t string, i int) map[string]string {
+			r[t] = c.Request.URL.Query().Get(t)
+			return r
+		}, map[string]string{})
+	}
+
+	client := GetEpayClient()
+	if client == nil {
+		_, _ = c.Writer.Write([]byte("fail"))
+		return
+	}
+	verifyInfo, err := client.Verify(params)
+	if err != nil || !verifyInfo.VerifyStatus {
+		_, _ = c.Writer.Write([]byte("fail"))
+		return
+	}
+
+	if verifyInfo.TradeStatus != epay.StatusTradeSuccess {
+		_, _ = c.Writer.Write([]byte("fail"))
+		return
+	}
+
+	LockOrder(verifyInfo.ServiceTradeNo)
+	defer UnlockOrder(verifyInfo.ServiceTradeNo)
+
+	if err := model.CompleteSubscriptionOrder(verifyInfo.ServiceTradeNo, common.GetJsonString(verifyInfo)); err != nil {
+		_, _ = c.Writer.Write([]byte("fail"))
+		return
+	}
+
+	_, _ = c.Writer.Write([]byte("success"))
+}
+
+// SubscriptionEpayReturn handles browser return after payment.
+// It verifies the payload and completes the order, then redirects to console.
+func SubscriptionEpayReturn(c *gin.Context) {
+	if err := c.Request.ParseForm(); err != nil {
+		c.Redirect(http.StatusFound, system_setting.ServerAddress+"/console/subscription?pay=fail")
+		return
+	}
+	params := lo.Reduce(lo.Keys(c.Request.PostForm), func(r map[string]string, t string, i int) map[string]string {
+		r[t] = c.Request.PostForm.Get(t)
+		return r
+	}, map[string]string{})
+	if len(params) == 0 {
+		params = lo.Reduce(lo.Keys(c.Request.URL.Query()), func(r map[string]string, t string, i int) map[string]string {
+			r[t] = c.Request.URL.Query().Get(t)
+			return r
+		}, map[string]string{})
+	}
+
+	client := GetEpayClient()
+	if client == nil {
+		c.Redirect(http.StatusFound, system_setting.ServerAddress+"/console/subscription?pay=fail")
+		return
+	}
+	verifyInfo, err := client.Verify(params)
+	if err != nil || !verifyInfo.VerifyStatus {
+		c.Redirect(http.StatusFound, system_setting.ServerAddress+"/console/subscription?pay=fail")
+		return
+	}
+	if verifyInfo.TradeStatus == epay.StatusTradeSuccess {
+		LockOrder(verifyInfo.ServiceTradeNo)
+		defer UnlockOrder(verifyInfo.ServiceTradeNo)
+		if err := model.CompleteSubscriptionOrder(verifyInfo.ServiceTradeNo, common.GetJsonString(verifyInfo)); err != nil {
+			c.Redirect(http.StatusFound, system_setting.ServerAddress+"/console/subscription?pay=fail")
+			return
+		}
+		c.Redirect(http.StatusFound, system_setting.ServerAddress+"/console/subscription?pay=success")
+		return
+	}
+	c.Redirect(http.StatusFound, system_setting.ServerAddress+"/console/subscription?pay=pending")
+}

controller/subscription_payment_stripe.go

@@ -0,0 +1,138 @@
+package controller
+
+import (
+	"fmt"
+	"log"
+	"net/http"
+	"strings"
+	"time"
+
+	"github.com/QuantumNous/new-api/common"
+	"github.com/QuantumNous/new-api/model"
+	"github.com/QuantumNous/new-api/setting"
+	"github.com/QuantumNous/new-api/setting/system_setting"
+	"github.com/gin-gonic/gin"
+	"github.com/stripe/stripe-go/v81"
+	"github.com/stripe/stripe-go/v81/checkout/session"
+	"github.com/thanhpk/randstr"
+)
+
+type SubscriptionStripePayRequest struct {
+	PlanId int `json:"plan_id"`
+}
+
+func SubscriptionRequestStripePay(c *gin.Context) {
+	var req SubscriptionStripePayRequest
+	if err := c.ShouldBindJSON(&req); err != nil || req.PlanId <= 0 {
+		common.ApiErrorMsg(c, "参数错误")
+		return
+	}
+
+	plan, err := model.GetSubscriptionPlanById(req.PlanId)
+	if err != nil {
+		common.ApiError(c, err)
+		return
+	}
+	if !plan.Enabled {
+		common.ApiErrorMsg(c, "套餐未启用")
+		return
+	}
+	if plan.StripePriceId == "" {
+		common.ApiErrorMsg(c, "该套餐未配置 StripePriceId")
+		return
+	}
+	if !strings.HasPrefix(setting.StripeApiSecret, "sk_") && !strings.HasPrefix(setting.StripeApiSecret, "rk_") {
+		common.ApiErrorMsg(c, "Stripe 未配置或密钥无效")
+		return
+	}
+	if setting.StripeWebhookSecret == "" {
+		common.ApiErrorMsg(c, "Stripe Webhook 未配置")
+		return
+	}
+
+	userId := c.GetInt("id")
+	user, err := model.GetUserById(userId, false)
+	if err != nil {
+		common.ApiError(c, err)
+		return
+	}
+	if user == nil {
+		common.ApiErrorMsg(c, "用户不存在")
+		return
+	}
+
+	if plan.MaxPurchasePerUser > 0 {
+		count, err := model.CountUserSubscriptionsByPlan(userId, plan.Id)
+		if err != nil {
+			common.ApiError(c, err)
+			return
+		}
+		if count >= int64(plan.MaxPurchasePerUser) {
+			common.ApiErrorMsg(c, "已达到该套餐购买上限")
+			return
+		}
+	}
+
+	reference := fmt.Sprintf("sub-stripe-ref-%d-%d-%s", user.Id, time.Now().UnixMilli(), randstr.String(4))
+	referenceId := "sub_ref_" + common.Sha1([]byte(reference))
+
+	payLink, err := genStripeSubscriptionLink(referenceId, user.StripeCustomer, user.Email, plan.StripePriceId)
+	if err != nil {
+		log.Println("获取Stripe Checkout支付链接失败", err)
+		c.JSON(http.StatusOK, gin.H{"message": "error", "data": "拉起支付失败"})
+		return
+	}
+
+	order := &model.SubscriptionOrder{
+		UserId:        userId,
+		PlanId:        plan.Id,
+		Money:         plan.PriceAmount,
+		TradeNo:       referenceId,
+		PaymentMethod: PaymentMethodStripe,
+		CreateTime:    time.Now().Unix(),
+		Status:        common.TopUpStatusPending,
+	}
+	if err := order.Insert(); err != nil {
+		c.JSON(http.StatusOK, gin.H{"message": "error", "data": "创建订单失败"})
+		return
+	}
+
+	c.JSON(http.StatusOK, gin.H{
+		"message": "success",
+		"data": gin.H{
+			"pay_link": payLink,
+		},
+	})
+}
+
+func genStripeSubscriptionLink(referenceId string, customerId string, email string, priceId string) (string, error) {
+	stripe.Key = setting.StripeApiSecret
+
+	params := &stripe.CheckoutSessionParams{
+		ClientReferenceID: stripe.String(referenceId),
+		SuccessURL:        stripe.String(system_setting.ServerAddress + "/console/topup"),
+		CancelURL:         stripe.String(system_setting.ServerAddress + "/console/topup"),
+		LineItems: []*stripe.CheckoutSessionLineItemParams{
+			{
+				Price:    stripe.String(priceId),
+				Quantity: stripe.Int64(1),
+			},
+		},
+		Mode: stripe.String(string(stripe.CheckoutSessionModeSubscription)),
+	}
+
+	if "" == customerId {
+		if "" != email {
+			params.CustomerEmail = stripe.String(email)
+		}
+		params.CustomerCreation = stripe.String(string(stripe.CheckoutSessionCustomerCreationAlways))
+	} else {
+		params.Customer = stripe.String(customerId)
+	}
+
+	result, err := session.New(params)
+	if err != nil {
+		return "", err
+	}
+	return result.URL, nil
+}

controller/task.go

@@ -7,16 +7,17 @@ import (
 	"fmt"
 	"io"
 	"net/http"
-	"one-api/common"
-	"one-api/constant"
-	"one-api/dto"
-	"one-api/logger"
-	"one-api/model"
-	"one-api/relay"
 	"sort"
 	"strconv"
 	"time"
 
+	"github.com/QuantumNous/new-api/common"
+	"github.com/QuantumNous/new-api/constant"
+	"github.com/QuantumNous/new-api/dto"
+	"github.com/QuantumNous/new-api/logger"
+	"github.com/QuantumNous/new-api/model"
+	"github.com/QuantumNous/new-api/relay"
+
 	"github.com/gin-gonic/gin"
 	"github.com/samber/lo"
 )
@@ -28,7 +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)
@@ -87,7 +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
@@ -115,9 +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
@@ -139,7 +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

@@ -5,15 +5,17 @@ import (
 	"encoding/json"
 	"fmt"
 	"io"
-	"one-api/common"
-	"one-api/constant"
-	"one-api/dto"
-	"one-api/logger"
-	"one-api/model"
-	"one-api/relay"
-	"one-api/relay/channel"
-	relaycommon "one-api/relay/common"
 	"time"
+
+	"github.com/QuantumNous/new-api/common"
+	"github.com/QuantumNous/new-api/constant"
+	"github.com/QuantumNous/new-api/dto"
+	"github.com/QuantumNous/new-api/logger"
+	"github.com/QuantumNous/new-api/model"
+	"github.com/QuantumNous/new-api/relay"
+	"github.com/QuantumNous/new-api/relay/channel"
+	relaycommon "github.com/QuantumNous/new-api/relay/common"
+	"github.com/QuantumNous/new-api/setting/ratio_setting"
 )
 
 func UpdateVideoTaskAll(ctx context.Context, platform constant.TaskPlatform, taskChannelM map[int][]string, taskM map[string]*model.Task) error {
@@ -46,6 +48,12 @@ func updateVideoTaskAll(ctx context.Context, platform constant.TaskPlatform, cha
 	if adaptor == nil {
 		return fmt.Errorf("video adaptor not found")
 	}
+	info := &relaycommon.RelayInfo{}
+	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 {
 			logger.LogError(ctx, fmt.Sprintf("Failed to update video task %s: %s", taskId, err.Error()))
@@ -59,16 +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)
 	}
@@ -81,26 +96,39 @@ func updateVideoSingleTask(ctx context.Context, adaptor channel.TaskAdaptor, cha
 		return fmt.Errorf("readAll failed for task %s: %w", taskId, err)
 	}
 
+	logger.LogDebug(ctx, fmt.Sprintf("UpdateVideoSingleTask response: %s", string(responseBody)))
+
 	taskResult := &relaycommon.TaskInfo{}
 	// try parse as New API response format
 	var responseItems dto.TaskResponse[model.Task]
-	if err = json.Unmarshal(responseBody, &responseItems); err == nil && responseItems.IsSuccess() {
+	if err = common.Unmarshal(responseBody, &responseItems); err == nil && responseItems.IsSuccess() {
+		logger.LogDebug(ctx, fmt.Sprintf("UpdateVideoSingleTask parsed as new api response format: %+v", responseItems))
 		t := responseItems.Data
 		taskResult.TaskID = t.TaskID
 		taskResult.Status = string(t.Status)
 		taskResult.Url = t.FailReason
 		taskResult.Progress = t.Progress
 		taskResult.Reason = t.FailReason
+		task.Data = t.Data
 	} else if taskResult, err = adaptor.ParseTaskResult(responseBody); err != nil {
 		return fmt.Errorf("parseTaskResult failed for task %s: %w", taskId, err)
 	} else {
-		task.Data = responseBody
+		task.Data = redactVideoResponseBody(responseBody)
 	}
 
+	logger.LogDebug(ctx, fmt.Sprintf("UpdateVideoSingleTask taskResult: %+v", taskResult))
+
 	now := time.Now().Unix()
 	if taskResult.Status == "" {
-		return fmt.Errorf("task %s status is empty", taskId)
+		//return fmt.Errorf("task %s status is empty", taskId)
+		taskResult = relaycommon.FailTaskInfo("upstream returned empty status")
 	}
+
+	// 记录原本的状态，防止重复退款
+	shouldRefund := false
+	quota := task.Quota
+	preStatus := task.Status
+
 	task.Status = model.TaskStatus(taskResult.Status)
 	switch taskResult.Status {
 	case model.TaskStatusSubmitted:
@@ -113,12 +141,105 @@ func updateVideoSingleTask(ctx context.Context, adaptor channel.TaskAdaptor, cha
 			task.StartTime = now
 		}
 	case model.TaskStatusSuccess:
-		task.Progress =	 "100%"
+		task.Progress = "100%"
 		if task.FinishTime == 0 {
 			task.FinishTime = now
 		}
-		task.FailReason = taskResult.Url
+		if !(len(taskResult.Url) > 5 && taskResult.Url[:5] == "data:") {
+			task.FailReason = taskResult.Url
+		}
+
+		// 如果返回了 total_tokens 并且配置了模型倍率(非固定价格),则重新计费
+		if taskResult.TotalTokens > 0 {
+			// 获取模型名称
+			var taskData map[string]interface{}
+			if err := json.Unmarshal(task.Data, &taskData); err == nil {
+				if modelName, ok := taskData["model"].(string); ok && modelName != "" {
+					// 获取模型价格和倍率
+					modelRatio, hasRatioSetting, _ := ratio_setting.GetModelRatio(modelName)
+					// 只有配置了倍率(非固定价格)时才按 token 重新计费
+					if hasRatioSetting && modelRatio > 0 {
+						// 获取用户和组的倍率信息
+						group := task.Group
+						if group == "" {
+							user, err := model.GetUserById(task.UserId, false)
+							if err == nil {
+								group = user.Group
+							}
+						}
+						if group != "" {
+							groupRatio := ratio_setting.GetGroupRatio(group)
+							userGroupRatio, hasUserGroupRatio := ratio_setting.GetGroupGroupRatio(group, group)
+
+							var finalGroupRatio float64
+							if hasUserGroupRatio {
+								finalGroupRatio = userGroupRatio
+							} else {
+								finalGroupRatio = groupRatio
+							}
+
+							// 计算实际应扣费额度: totalTokens * modelRatio * groupRatio
+							actualQuota := int(float64(taskResult.TotalTokens) * modelRatio * finalGroupRatio)
+
+							// 计算差额
+							preConsumedQuota := task.Quota
+							quotaDelta := actualQuota - preConsumedQuota
+
+							if quotaDelta > 0 {
+								// 需要补扣费
+								logger.LogInfo(ctx, fmt.Sprintf("视频任务 %s 预扣费后补扣费：%s（实际消耗：%s，预扣费：%s，tokens：%d）",
+									task.TaskID,
+									logger.LogQuota(quotaDelta),
+									logger.LogQuota(actualQuota),
+									logger.LogQuota(preConsumedQuota),
+									taskResult.TotalTokens,
+								))
+								if err := model.DecreaseUserQuota(task.UserId, quotaDelta); err != nil {
+									logger.LogError(ctx, fmt.Sprintf("补扣费失败: %s", err.Error()))
+								} else {
+									model.UpdateUserUsedQuotaAndRequestCount(task.UserId, quotaDelta)
+									model.UpdateChannelUsedQuota(task.ChannelId, quotaDelta)
+									task.Quota = actualQuota // 更新任务记录的实际扣费额度
+
+									// 记录消费日志
+									logContent := fmt.Sprintf("视频任务成功补扣费，模型倍率 %.2f，分组倍率 %.2f，tokens %d，预扣费 %s，实际扣费 %s，补扣费 %s",
+										modelRatio, finalGroupRatio, taskResult.TotalTokens,
+										logger.LogQuota(preConsumedQuota), logger.LogQuota(actualQuota), logger.LogQuota(quotaDelta))
+									model.RecordLog(task.UserId, model.LogTypeSystem, logContent)
+								}
+							} else if quotaDelta < 0 {
+								// 需要退还多扣的费用
+								refundQuota := -quotaDelta
+								logger.LogInfo(ctx, fmt.Sprintf("视频任务 %s 预扣费后返还：%s（实际消耗：%s，预扣费：%s，tokens：%d）",
+									task.TaskID,
+									logger.LogQuota(refundQuota),
+									logger.LogQuota(actualQuota),
+									logger.LogQuota(preConsumedQuota),
+									taskResult.TotalTokens,
+								))
+								if err := model.IncreaseUserQuota(task.UserId, refundQuota, false); err != nil {
+									logger.LogError(ctx, fmt.Sprintf("退还预扣费失败: %s", err.Error()))
+								} else {
+									task.Quota = actualQuota // 更新任务记录的实际扣费额度
+
+									// 记录退款日志
+									logContent := fmt.Sprintf("视频任务成功退还多扣费用，模型倍率 %.2f，分组倍率 %.2f，tokens %d，预扣费 %s，实际扣费 %s，退还 %s",
+										modelRatio, finalGroupRatio, taskResult.TotalTokens,
+										logger.LogQuota(preConsumedQuota), logger.LogQuota(actualQuota), logger.LogQuota(refundQuota))
+									model.RecordLog(task.UserId, model.LogTypeSystem, logContent)
+								}
+							} else {
+								// quotaDelta == 0, 预扣费刚好准确
+								logger.LogInfo(ctx, fmt.Sprintf("视频任务 %s 预扣费准确（%s，tokens：%d）",
+									task.TaskID, logger.LogQuota(actualQuota), taskResult.TotalTokens))
+							}
+						}
+					}
+				}
+			}
+		}
 	case model.TaskStatusFailure:
+		logger.LogJson(ctx, fmt.Sprintf("Task %s failed", taskId), task)
 		task.Status = model.TaskStatusFailure
 		task.Progress = "100%"
 		if task.FinishTime == 0 {
@@ -126,13 +247,13 @@ func updateVideoSingleTask(ctx context.Context, adaptor channel.TaskAdaptor, cha
 		}
 		task.FailReason = taskResult.Reason
 		logger.LogInfo(ctx, fmt.Sprintf("Task %s failed: %s", task.TaskID, task.FailReason))
-		quota := task.Quota
+		taskResult.Progress = "100%"
 		if quota != 0 {
-			if err := model.IncreaseUserQuota(task.UserId, quota, false); err != nil {
-				logger.LogError(ctx, "Failed to increase user quota: "+err.Error())
+			if preStatus != model.TaskStatusFailure {
+				shouldRefund = true
+			} else {
+				logger.LogWarn(ctx, fmt.Sprintf("Task %s already in failure status, skip refund", task.TaskID))
 			}
-			logContent := fmt.Sprintf("Video async task failed %s, refund %s", task.TaskID, logger.LogQuota(quota))
-			model.RecordLog(task.UserId, model.LogTypeSystem, logContent)
 		}
 	default:
 		return fmt.Errorf("unknown task status %s for task %s", taskResult.Status, taskId)
@@ -142,7 +263,51 @@ func updateVideoSingleTask(ctx context.Context, adaptor channel.TaskAdaptor, cha
 	}
 	if err := task.Update(); err != nil {
 		common.SysLog("UpdateVideoTask task error: " + err.Error())
+		shouldRefund = false
+	}
+
+	if shouldRefund {
+		// 任务失败且之前状态不是失败才退还额度，防止重复退还
+		if err := model.IncreaseUserQuota(task.UserId, quota, false); err != nil {
+			logger.LogWarn(ctx, "Failed to increase user quota: "+err.Error())
+		}
+		logContent := fmt.Sprintf("Video async task failed %s, refund %s", task.TaskID, logger.LogQuota(quota))
+		model.RecordLog(task.UserId, model.LogTypeSystem, logContent)
 	}
 
 	return nil
 }
+
+func redactVideoResponseBody(body []byte) []byte {
+	var m map[string]any
+	if err := json.Unmarshal(body, &m); err != nil {
+		return body
+	}
+	resp, _ := m["response"].(map[string]any)
+	if resp != nil {
+		delete(resp, "bytesBase64Encoded")
+		if v, ok := resp["video"].(string); ok {
+			resp["video"] = truncateBase64(v)
+		}
+		if vs, ok := resp["videos"].([]any); ok {
+			for i := range vs {
+				if vm, ok := vs[i].(map[string]any); ok {
+					delete(vm, "bytesBase64Encoded")
+				}
+			}
+		}
+	}
+	b, err := json.Marshal(m)
+	if err != nil {
+		return body
+	}
+	return b
+}
+
+func truncateBase64(s string) string {
+	const maxKeep = 256
+	if len(s) <= maxKeep {
+		return s
+	}
+	return s[:maxKeep] + "..."
+}

controller/telegram.go

@@ -6,10 +6,11 @@ import (
 	"encoding/hex"
 	"io"
 	"net/http"
-	"one-api/common"
-	"one-api/model"
 	"sort"
 
+	"github.com/QuantumNous/new-api/common"
+	"github.com/QuantumNous/new-api/model"
+
 	"github.com/gin-contrib/sessions"
 	"github.com/gin-gonic/gin"
 )
@@ -65,7 +66,7 @@ func TelegramBind(c *gin.Context) {
 		return
 	}
 
-	c.Redirect(302, "/setting")
+	c.Redirect(302, "/console/personal")
 }
 
 func TelegramLogin(c *gin.Context) {

controller/token.go

@@ -1,12 +1,14 @@
 package controller
 
 import (
+	"fmt"
 	"net/http"
-	"one-api/common"
-	"one-api/model"
 	"strconv"
 	"strings"
 
+	"github.com/QuantumNous/new-api/common"
+	"github.com/QuantumNous/new-api/model"
+
 	"github.com/gin-gonic/gin"
 )
 
@@ -141,13 +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{
@@ -170,6 +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 {
@@ -207,13 +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)
@@ -247,6 +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 {
@@ -258,7 +297,6 @@ func UpdateToken(c *gin.Context) {
 		"message": "",
 		"data":    cleanToken,
 	})
-	return
 }
 
 type TokenBatch struct {