Merge pull request #2013 from seefs001/fix/ci

feat: matrix ci

.dockerignore

@@ -5,4 +5,5 @@
 .gitignore
 Makefile
 docs
-.eslintcache
+.eslintcache
+.gocache

.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/workflows/electron-build.yml

@@ -0,0 +1,142 @@
+name: Build Electron App
+
+on:
+  push:
+    tags:
+      - '*'  # Triggers on version tags like v1.0.0
+  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 'one-api/common.Version=$(git describe --tags)' -extldflags '-static'" -o new-api
+
+      - name: Build Go binary (Windows)
+        if: runner.os == 'Windows'
+        run: |
+          go mod download
+          go build -ldflags "-s -w -X 'one-api/common.Version=$(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: Create Release
+        uses: softprops/action-gh-release@v2
+        with:
+          files: |
+            windows-build/*
+          draft: false
+          prerelease: false
+          overwrite_files: true
+        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 new-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 new-api-arm64
-
-      - name: Release
-        uses: softprops/action-gh-release@v1
-        if: startsWith(github.ref, 'refs/tags/')
-        with:
-          files: |
-            new-api
-            new-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 new-api-macos
-      - name: Release
-        uses: softprops/action-gh-release@v1
-        if: startsWith(github.ref, 'refs/tags/')
-        with:
-          files: new-api-macos
-          draft: true
-          generate_release_notes: true
-        env:
-          GITHUB_TOKEN: ${{ secrets.GITHUB_TOKEN }}

.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
+      - 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=$(git describe --tags) bun run build
+          cd ..
+      - name: Set up Go
+        uses: actions/setup-go@v3
+        with:
+          go-version: '>=1.25.1'
+      - name: Build Backend (amd64)
+        run: |
+          go mod download
+          VERSION=$(git describe --tags)
+          go build -ldflags "-s -w -X 'one-api/common.Version=$VERSION' -extldflags '-static'" -o new-api-$VERSION
+      - name: Build Backend (arm64)
+        run: |
+          sudo apt-get update
+          DEBIAN_FRONTEND=noninteractive sudo apt-get install -y gcc-aarch64-linux-gnu
+          VERSION=$(git describe --tags)
+          CC=aarch64-linux-gnu-gcc CGO_ENABLED=1 GOOS=linux GOARCH=arm64 go build -ldflags "-s -w -X 'one-api/common.Version=$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-*
+          draft: true
+          generate_release_notes: true
+        env:
+          GITHUB_TOKEN: ${{ secrets.GITHUB_TOKEN }}
+
+  macos:
+    name: macOS Release
+    runs-on: macos-latest
+    steps:
+      - name: Checkout
+        uses: actions/checkout@v3
+        with:
+          fetch-depth: 0
+      - uses: oven-sh/setup-bun@v2
+        with:
+          bun-version: latest
+      - name: Build Frontend
+        env:
+          CI: ""
+          NODE_OPTIONS: "--max-old-space-size=4096"
+        run: |
+          cd web
+          bun install
+          DISABLE_ESLINT_PLUGIN='true' VITE_REACT_APP_VERSION=$(git describe --tags) bun run build
+          cd ..
+      - name: Set up Go
+        uses: actions/setup-go@v3
+        with:
+          go-version: '>=1.25.1'
+      - name: Build Backend
+        run: |
+          go mod download
+          VERSION=$(git describe --tags)
+          go build -ldflags "-X 'one-api/common.Version=$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-*
+          draft: true
+          generate_release_notes: true
+        env:
+          GITHUB_TOKEN: ${{ secrets.GITHUB_TOKEN }}
+
+  windows:
+    name: Windows Release
+    runs-on: windows-latest
+    defaults:
+      run:
+        shell: bash
+    steps:
+      - name: Checkout
+        uses: actions/checkout@v3
+        with:
+          fetch-depth: 0
+      - uses: oven-sh/setup-bun@v2
+        with:
+          bun-version: latest
+      - name: Build Frontend
+        env:
+          CI: ""
+        run: |
+          cd web
+          bun install
+          DISABLE_ESLINT_PLUGIN='true' VITE_REACT_APP_VERSION=$(git describe --tags) bun run build
+          cd ..
+      - name: Set up Go
+        uses: actions/setup-go@v3
+        with:
+          go-version: '>=1.25.1'
+      - name: Build Backend
+        run: |
+          go mod download
+          VERSION=$(git describe --tags)
+          go build -ldflags "-s -w -X 'one-api/common.Version=$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
+          draft: true
+          generate_release_notes: true
+        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 new-api.exe
-      - name: Release
-        uses: softprops/action-gh-release@v1
-        if: startsWith(github.ref, 'refs/tags/')
-        with:
-          files: new-api.exe
-          draft: true
-          generate_release_notes: true
-        env:
-          GITHUB_TOKEN: ${{ secrets.GITHUB_TOKEN }}

.gitignore

@@ -9,6 +9,11 @@ logs
 web/dist
 .env
 one-api
+new-api
 .DS_Store
 tiktoken_cache
-.eslintcache
+.eslintcache
+.gocache
+
+electron/node_modules
+electron/dist

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
+
+ARG TARGETOS
+ARG TARGETARCH
+ENV GOOS=${TARGETOS:-linux} GOARCH=${TARGETARCH:-amd64}
 
-ENV GO111MODULE=on \
-    CGO_ENABLED=0 \
-    GOOS=linux
 
 WORKDIR /build
 

README.en.md

@@ -1,6 +1,10 @@
 <p align="right">
-   <a href="./README.md">中文</a> | <strong>English</strong> | <a href="./README.fr.md">Français</a>
+   <a href="./README.md">中文</a> | <strong>English</strong> | <a href="./README.fr.md">Français</a> | <a href="./README.ja.md">日本語</a>
 </p>
+
+> [!NOTE]
+> **MT (Machine Translation)**: This document is machine translated. For the most accurate information, please refer to the [Chinese version](./README.md).
+
 <div align="center">
 
 ![new-api](/web/public/logo.png)
@@ -75,7 +79,7 @@ New API offers a wide range of features, please refer to [Features Introduction]
 
 1. 🎨 Brand new UI interface
 2. 🌍 Multi-language support
-3. 💰 Online recharge functionality (YiPay)
+3. 💰 Online recharge functionality, currently supports EPay and Stripe
 4. 🔍 Support for querying usage quotas with keys (works with [neko-api-key-tool](https://github.com/Calcium-Ion/neko-api-key-tool))
 5. 🔄 Compatible with the original One API database
 6. 💵 Support for pay-per-use model pricing
@@ -85,18 +89,23 @@ New API offers a wide range of features, please refer to [Features Introduction]
 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:
+13. ⚡ Support for **OpenAI Responses** format, [API Documentation](https://docs.newapi.pro/api/openai-responses)
+14. ⚡ Support for **Claude Messages** format, [API Documentation](https://docs.newapi.pro/api/anthropic-chat)
+15. ⚡ Support for **Google Gemini** format, [API Documentation](https://docs.newapi.pro/api/google-gemini-chat/)
+16. 🧠 Support for setting reasoning effort through model name suffixes:
     1. OpenAI o-series models
         - Add `-high` suffix for high reasoning effort (e.g.: `o3-mini-high`)
         - Add `-medium` suffix for medium reasoning effort (e.g.: `o3-mini-medium`)
         - Add `-low` suffix for low reasoning effort (e.g.: `o3-mini-low`)
     2. Claude thinking models
         - Add `-thinking` suffix to enable thinking mode (e.g.: `claude-3-7-sonnet-20250219-thinking`)
-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:
+17. 🔄 Thinking-to-content functionality
+18. 🔄 Model rate limiting for users
+19. 🔄 Request format conversion functionality, supporting the following three format conversions:
+    1. OpenAI Chat Completions => Claude Messages
+    2. Claude Messages => OpenAI Chat Completions (can be used for Claude Code to call third-party models)
+    3. OpenAI Chat Completions => Gemini Chat
+20. 💰 Cache billing support, which allows billing at a set ratio when cache is hit:
     1. Set the `Prompt Cache Ratio` option in `System Settings-Operation Settings`
     2. Set `Prompt Cache Ratio` in the channel, range 0-1, e.g., setting to 0.5 means billing at 50% when cache is hit
     3. Supported channels:
@@ -115,7 +124,9 @@ This version supports multiple models, please refer to [API Documentation-Relay
 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
+7. Google Gemini format, [API Documentation](https://docs.newapi.pro/api/google-gemini-chat/)
+8. Dify, currently only supports chatflow
+9. For more interfaces, please refer to [API Documentation](https://docs.newapi.pro/api)
 
 ## Environment Variable Configuration
 
@@ -124,14 +135,12 @@ For detailed configuration instructions, please refer to [Installation Guide-Env
 - `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
+- `CRYPTO_SECRET`: Encryption key used for encrypting Redis database content
 - `AZURE_DEFAULT_API_VERSION`: Azure channel default API version, default is `2025-04-01-preview`
 - `NOTIFICATION_LIMIT_DURATION_MINUTE`: Notification limit duration, default is `10` minutes
 - `NOTIFY_LIMIT_COUNT`: Maximum number of user notifications within the specified duration, default is `2`
@@ -178,7 +187,7 @@ docker run --name new-api -d --restart always -p 3000:3000 -e SQL_DSN="root:1234
 ```
 
 ## 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**.
+Channel retry functionality has been implemented, you can set the number of retries in `Settings->Operation Settings->General Settings->Failure Retry Count`, **recommended to enable caching** functionality.
 
 ### Cache Configuration Method
 1. `REDIS_CONN_STRING`: Set Redis as cache
@@ -188,21 +197,21 @@ Channel retry functionality has been implemented, you can set the number of retr
 
 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)
+- [Chat API (Chat Completions)](https://docs.newapi.pro/api/openai-chat)
+- [Response API (Responses)](https://docs.newapi.pro/api/openai-responses)
+- [Image API (Image)](https://docs.newapi.pro/api/openai-image)
+- [Rerank API (Rerank)](https://docs.newapi.pro/api/jinaai-rerank)
+- [Realtime Chat API (Realtime)](https://docs.newapi.pro/api/openai-realtime)
+- [Claude Chat API](https://docs.newapi.pro/api/anthropic-chat)
+- [Google Gemini Chat API](https://docs.newapi.pro/api/google-gemini-chat)
 
 ## Related Projects
 - [One API](https://github.com/songquanpeng/one-api): Original project
 - [Midjourney-Proxy](https://github.com/novicezk/midjourney-proxy): Midjourney interface support
-- [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
 

README.fr.md

@@ -1,6 +1,10 @@
 <p align="right">
-   <a href="./README.md">中文</a> | <a href="./README.en.md">English</a> | <strong>Français</strong>
+   <a href="./README.md">中文</a> | <a href="./README.en.md">English</a> | <strong>Français</strong> | <a href="./README.ja.md">日本語</a>
 </p>
+
+> [!NOTE]
+> **MT (Traduction Automatique)**: Ce document est traduit automatiquement. Pour les informations les plus précises, veuillez vous référer à la [version chinoise](./README.md).
+
 <div align="center">
 
 ![new-api](/web/public/logo.png)
@@ -75,7 +79,7 @@ New API offre un large éventail de fonctionnalités, veuillez vous référer à
 
 1. 🎨 Nouvelle interface utilisateur
 2. 🌍 Prise en charge multilingue
-3. 💰 Fonctionnalité de recharge en ligne (YiPay)
+3. 💰 Fonctionnalité de recharge en ligne, prend actuellement en charge EPay et Stripe
 4. 🔍 Prise en charge de la recherche de quotas d'utilisation avec des clés (fonctionne avec [neko-api-key-tool](https://github.com/Calcium-Ion/neko-api-key-tool))
 5. 🔄 Compatible avec la base de données originale de One API
 6. 💵 Prise en charge de la tarification des modèles de paiement à l'utilisation
@@ -85,18 +89,23 @@ New API offre un large éventail de fonctionnalités, veuillez vous référer à
 10. 🤖 Prise en charge de plus de méthodes de connexion par autorisation (LinuxDO, Telegram, OIDC)
 11. 🔄 Prise en charge des modèles Rerank (Cohere et Jina), [Documentation de l'API](https://docs.newapi.pro/api/jinaai-rerank)
 12. ⚡ Prise en charge de l'API OpenAI Realtime (y compris les canaux Azure), [Documentation de l'API](https://docs.newapi.pro/api/openai-realtime)
-13. ⚡ Prise en charge du format Claude Messages, [Documentation de l'API](https://docs.newapi.pro/api/anthropic-chat)
-14. Prise en charge de l'accès à l'interface de discussion via la route /chat2link
-15. 🧠 Prise en charge de la définition de l'effort de raisonnement via les suffixes de nom de modèle :
+13. ⚡ Prise en charge du format **OpenAI Responses**, [Documentation de l'API](https://docs.newapi.pro/api/openai-responses)
+14. ⚡ Prise en charge du format **Claude Messages**, [Documentation de l'API](https://docs.newapi.pro/api/anthropic-chat)
+15. ⚡ Prise en charge du format **Google Gemini**, [Documentation de l'API](https://docs.newapi.pro/api/google-gemini-chat/)
+16. 🧠 Prise en charge de la définition de l'effort de raisonnement via les suffixes de nom de modèle :
     1. Modèles de la série o d'OpenAI
         - Ajouter le suffixe `-high` pour un effort de raisonnement élevé (par exemple : `o3-mini-high`)
         - Ajouter le suffixe `-medium` pour un effort de raisonnement moyen (par exemple : `o3-mini-medium`)
         - Ajouter le suffixe `-low` pour un effort de raisonnement faible (par exemple : `o3-mini-low`)
     2. Modèles de pensée de Claude
         - Ajouter le suffixe `-thinking` pour activer le mode de pensée (par exemple : `claude-3-7-sonnet-20250219-thinking`)
-16. 🔄 Fonctionnalité de la pensée au contenu
-17. 🔄 Limitation du débit du modèle pour les utilisateurs
-18. 💰 Prise en charge de la facturation du cache, qui permet de facturer à un ratio défini lorsque le cache est atteint :
+17. 🔄 Fonctionnalité de la pensée au contenu
+18. 🔄 Limitation du débit du modèle pour les utilisateurs
+19. 🔄 Fonctionnalité de conversion de format de requête, prenant en charge les trois conversions de format suivantes :
+    1. OpenAI Chat Completions => Claude Messages
+    2. Claude Messages => OpenAI Chat Completions (peut être utilisé pour Claude Code pour appeler des modèles tiers)
+    3. OpenAI Chat Completions => Gemini Chat
+20. 💰 Prise en charge de la facturation du cache, qui permet de facturer à un ratio défini lorsque le cache est atteint :
     1. Définir l'option `Ratio de cache d'invite` dans `Paramètres système->Paramètres de fonctionnement`
     2. Définir le `Ratio de cache d'invite` dans le canal, plage de 0 à 1, par exemple, le définir sur 0,5 signifie facturer à 50 % lorsque le cache est atteint
     3. Canaux pris en charge :
@@ -115,7 +124,9 @@ Cette version prend en charge plusieurs modèles, veuillez vous référer à [Do
 4. Canaux personnalisés, prenant en charge la saisie complète de l'adresse d'appel
 5. Modèles Rerank ([Cohere](https://cohere.ai/) et [Jina](https://jina.ai/)), [Documentation de l'API](https://docs.newapi.pro/api/jinaai-rerank)
 6. Format de messages Claude, [Documentation de l'API](https://docs.newapi.pro/api/anthropic-chat)
-7. Dify, ne prend actuellement en charge que chatflow
+7. Format Google Gemini, [Documentation de l'API](https://docs.newapi.pro/api/google-gemini-chat/)
+8. Dify, ne prend actuellement en charge que chatflow
+9. Pour plus d'interfaces, veuillez vous référer à la [Documentation de l'API](https://docs.newapi.pro/api)
 
 ## Configuration des variables d'environnement
 
@@ -124,14 +135,12 @@ Pour des instructions de configuration détaillées, veuillez vous référer à
 - `GENERATE_DEFAULT_TOKEN` : S'il faut générer des jetons initiaux pour les utilisateurs nouvellement enregistrés, la valeur par défaut est `false`
 - `STREAMING_TIMEOUT` : Délai d'expiration de la réponse en streaming, la valeur par défaut est de 300 secondes
 - `DIFY_DEBUG` : S'il faut afficher les informations sur le flux de travail et les nœuds pour les canaux Dify, la valeur par défaut est `true`
-- `FORCE_STREAM_OPTION` : S'il faut remplacer le paramètre client stream_options, la valeur par défaut est `true`
 - `GET_MEDIA_TOKEN` : S'il faut compter les jetons d'image, la valeur par défaut est `true`
 - `GET_MEDIA_TOKEN_NOT_STREAM` : S'il faut compter les jetons d'image dans les cas sans streaming, la valeur par défaut est `true`
 - `UPDATE_TASK` : S'il faut mettre à jour les tâches asynchrones (Midjourney, Suno), la valeur par défaut est `true`
-- `COHERE_SAFETY_SETTING` : Paramètres de sécurité du modèle Cohere, les options sont `NONE`, `CONTEXTUAL`, `STRICT`, la valeur par défaut est `NONE`
 - `GEMINI_VISION_MAX_IMAGE_NUM` : Nombre maximum d'images pour les modèles Gemini, la valeur par défaut est `16`
 - `MAX_FILE_DOWNLOAD_MB` : Taille maximale de téléchargement de fichier en Mo, la valeur par défaut est `20`
-- `CRYPTO_SECRET` : Clé de chiffrement utilisée pour chiffrer le contenu de la base de données
+- `CRYPTO_SECRET` : Clé de chiffrement utilisée pour chiffrer le contenu de la base de données Redis
 - `AZURE_DEFAULT_API_VERSION` : Version de l'API par défaut du canal Azure, la valeur par défaut est `2025-04-01-preview`
 - `NOTIFICATION_LIMIT_DURATION_MINUTE` : Durée de la limite de notification, la valeur par défaut est de `10` minutes
 - `NOTIFY_LIMIT_COUNT` : Nombre maximal de notifications utilisateur dans la durée spécifiée, la valeur par défaut est `2`
@@ -178,7 +187,7 @@ docker run --name new-api -d --restart always -p 3000:3000 -e SQL_DSN="root:1234
 ```
 
 ## Nouvelle tentative de canal et cache
-La fonctionnalité de nouvelle tentative de canal a été implémentée, vous pouvez définir le nombre de tentatives dans `Paramètres->Paramètres de fonctionnement->Paramètres généraux`. Il est **recommandé d'activer la mise en cache**.
+La fonctionnalité de nouvelle tentative de canal a été implémentée, vous pouvez définir le nombre de tentatives dans `Paramètres->Paramètres de fonctionnement->Paramètres généraux->Nombre de tentatives en cas d'échec`, **recommandé d'activer la fonctionnalité de mise en cache**.
 
 ### Méthode de configuration du cache
 1. `REDIS_CONN_STRING` : Définir Redis comme cache
@@ -188,21 +197,21 @@ La fonctionnalité de nouvelle tentative de canal a été implémentée, vous po
 
 Pour une documentation détaillée de l'API, veuillez vous référer à [Documentation de l'API](https://docs.newapi.pro/api) :
 
-- [API de discussion](https://docs.newapi.pro/api/openai-chat)
-- [API d'image](https://docs.newapi.pro/api/openai-image)
-- [API de rerank](https://docs.newapi.pro/api/jinaai-rerank)
-- [API en temps réel](https://docs.newapi.pro/api/openai-realtime)
-- [API de discussion Claude (messages)](https://docs.newapi.pro/api/anthropic-chat)
+- [API de discussion (Chat Completions)](https://docs.newapi.pro/api/openai-chat)
+- [API de réponse (Responses)](https://docs.newapi.pro/api/openai-responses)
+- [API d'image (Image)](https://docs.newapi.pro/api/openai-image)
+- [API de rerank (Rerank)](https://docs.newapi.pro/api/jinaai-rerank)
+- [API de discussion en temps réel (Realtime)](https://docs.newapi.pro/api/openai-realtime)
+- [API de discussion Claude](https://docs.newapi.pro/api/anthropic-chat)
+- [API de discussion Google Gemini](https://docs.newapi.pro/api/google-gemini-chat)
 
 ## Projets connexes
 - [One API](https://github.com/songquanpeng/one-api) : Projet original
 - [Midjourney-Proxy](https://github.com/novicezk/midjourney-proxy) : Prise en charge de l'interface Midjourney
-- [chatnio](https://github.com/Deeptrain-Community/chatnio) : Solution B/C unique d'IA de nouvelle génération
 - [neko-api-key-tool](https://github.com/Calcium-Ion/neko-api-key-tool) : Interroger le quota d'utilisation avec une clé
 
 Autres projets basés sur New API :
 - [new-api-horizon](https://github.com/Calcium-Ion/new-api-horizon) : Version optimisée hautes performances de New API
-- [VoAPI](https://github.com/VoAPI/VoAPI) : Version embellie du frontend basée sur New API
 
 ## Aide et support
 

README.ja.md

@@ -0,0 +1,226 @@
+<p align="right">
+   <a href="./README.md">中文</a> | <a href="./README.en.md">English</a> | <a href="./README.fr.md">Français</a> | <strong>日本語</strong>
+</p>
+
+> [!NOTE]
+> **MT（機械翻訳）**: この文書は機械翻訳されています。最も正確な情報については、[中国語版](./README.md)を参照してください。
+
+<div align="center">
+
+![new-api](/web/public/logo.png)
+
+# New API
+
+🍥次世代大規模モデルゲートウェイとAI資産管理システム
+
+<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>
+
+## 📝 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。
+
+<h2>🤝 信頼できるパートナー</h2>
+<p id="premium-sponsors">&nbsp;</p>
+<p align="center"><strong>順不同</strong></p>
+<p align="center">
+  <a href="https://www.cherry-ai.com/" target=_blank><img
+    src="./docs/images/cherry-studio.png" alt="Cherry Studio" height="120"
+  /></a>
+  <a href="https://bda.pku.edu.cn/" target=_blank><img
+    src="./docs/images/pku.png" alt="北京大学" height="120"
+  /></a>
+  <a href="https://www.compshare.cn/?ytag=GPU_yy_gh_newapi" target=_blank><img
+    src="./docs/images/ucloud.png" alt="UCloud 優刻得" height="120"
+  /></a>
+  <a href="https://www.aliyun.com/" target=_blank><img
+    src="./docs/images/aliyun.png" alt="Alibaba Cloud" height="120"
+  /></a>
+  <a href="https://io.net/" target=_blank><img
+    src="./docs/images/io-net.png" alt="IO.NET" height="120"
+  /></a>
+</p>
+<p>&nbsp;</p>
+
+## 📚 ドキュメント
+
+詳細なドキュメントは公式Wikiをご覧ください：[https://docs.newapi.pro/](https://docs.newapi.pro/)
+
+AIが生成したDeepWikiにもアクセスできます：
+[![Ask DeepWiki](https://deepwiki.com/badge.svg)](https://deepwiki.com/QuantumNous/new-api)
+
+## ✨ 主な機能
+
+New APIは豊富な機能を提供しています。詳細な機能については[機能説明](https://docs.newapi.pro/wiki/features-introduction)を参照してください：
+
+1. 🎨 全く新しいUIインターフェース
+2. 🌍 多言語サポート
+3. 💰 オンラインチャージ機能をサポート、現在EPayとStripeをサポート
+4. 🔍 キーによる使用量クォータの照会をサポート（[neko-api-key-tool](https://github.com/Calcium-Ion/neko-api-key-tool)と連携）
+5. 🔄 オリジナルのOne APIデータベースと互換性あり
+6. 💵 モデルの従量課金をサポート
+7. ⚖️ チャネルの重み付けランダムをサポート
+8. 📈 データダッシュボード（コンソール）
+9. 🔒 トークングループ化、モデル制限
+10. 🤖 より多くの認証ログイン方法をサポート（LinuxDO、Telegram、OIDC）
+11. 🔄 Rerankモデルをサポート（CohereとJina）、[API ドキュメント](https://docs.newapi.pro/api/jinaai-rerank)
+12. ⚡ OpenAI Realtime APIをサポート（Azureチャネルを含む）、[APIドキュメント](https://docs.newapi.pro/api/openai-realtime)
+13. ⚡ **OpenAI Responses**形式をサポート、[APIドキュメント](https://docs.newapi.pro/api/openai-responses)
+14. ⚡ **Claude Messages**形式をサポート、[APIドキュメント](https://docs.newapi.pro/api/anthropic-chat)
+15. ⚡ **Google Gemini**形式をサポート、[APIドキュメント](https://docs.newapi.pro/api/google-gemini-chat/)
+16. 🧠 モデル名のサフィックスを通じてreasoning effortを設定することをサポート：
+    1. OpenAI oシリーズモデル
+        - `-high`サフィックスを追加してhigh reasoning effortに設定（例：`o3-mini-high`）
+        - `-medium`サフィックスを追加してmedium reasoning effortに設定（例：`o3-mini-medium`）
+        - `-low`サフィックスを追加してlow reasoning effortに設定（例：`o3-mini-low`）
+    2. Claude思考モデル
+        - `-thinking`サフィックスを追加して思考モードを有効にする（例：`claude-3-7-sonnet-20250219-thinking`）
+17. 🔄 思考からコンテンツへの機能
+18. 🔄 ユーザーに対するモデルレート制限機能
+19. 🔄 リクエストフォーマット変換機能、以下の3つのフォーマット変換をサポート：
+    1. OpenAI Chat Completions => Claude Messages
+    2. Claude Messages => OpenAI Chat Completions（Claude Codeがサードパーティモデルを呼び出す際に使用可能）
+    3. OpenAI Chat Completions => Gemini Chat
+20. 💰 キャッシュ課金サポート、有効にするとキャッシュがヒットした際に設定された比率で課金できます：
+    1. `システム設定-運営設定`で`プロンプトキャッシュ倍率`オプションを設定
+    2. チャネルで`プロンプトキャッシュ倍率`を設定、範囲は0-1、例えば0.5に設定するとキャッシュがヒットした際に50%で課金
+    3. サポートされているチャネル：
+        - [x] OpenAI
+        - [x] Azure
+        - [x] DeepSeek
+        - [x] Claude
+
+## モデルサポート
+
+このバージョンは複数のモデルをサポートしています。詳細は[APIドキュメント-中継インターフェース](https://docs.newapi.pro/api)を参照してください：
+
+1. サードパーティモデル **gpts**（gpt-4-gizmo-*）
+2. サードパーティチャネル[Midjourney-Proxy(Plus)](https://github.com/novicezk/midjourney-proxy)インターフェース、[APIドキュメント](https://docs.newapi.pro/api/midjourney-proxy-image)
+3. サードパーティチャネル[Suno API](https://github.com/Suno-API/Suno-API)インターフェース、[APIドキュメント](https://docs.newapi.pro/api/suno-music)
+4. カスタムチャネル、完全な呼び出しアドレスの入力をサポート
+5. Rerankモデル（[Cohere](https://cohere.ai/)と[Jina](https://jina.ai/)）、[APIドキュメント](https://docs.newapi.pro/api/jinaai-rerank)
+6. Claude Messages形式、[APIドキュメント](https://docs.newapi.pro/api/anthropic-chat)
+7. Google Gemini形式、[APIドキュメント](https://docs.newapi.pro/api/google-gemini-chat/)
+8. Dify、現在はchatflowのみをサポート
+9. その他のインターフェースについては[APIドキュメント](https://docs.newapi.pro/api)を参照してください
+
+## 環境変数設定
+
+詳細な設定説明については[インストールガイド-環境変数設定](https://docs.newapi.pro/installation/environment-variables)を参照してください：
+
+- `GENERATE_DEFAULT_TOKEN`：新規登録ユーザーに初期トークンを生成するかどうか、デフォルトは`false`
+- `STREAMING_TIMEOUT`：ストリーミング応答のタイムアウト時間、デフォルトは300秒
+- `DIFY_DEBUG`：Difyチャネルがワークフローとノード情報を出力するかどうか、デフォルトは`true`
+- `GET_MEDIA_TOKEN`：画像トークンを統計するかどうか、デフォルトは`true`
+- `GET_MEDIA_TOKEN_NOT_STREAM`：非ストリーミングの場合に画像トークンを統計するかどうか、デフォルトは`true`
+- `UPDATE_TASK`：非同期タスク（Midjourney、Suno）を更新するかどうか、デフォルトは`true`
+- `GEMINI_VISION_MAX_IMAGE_NUM`：Geminiモデルの最大画像数、デフォルトは`16`
+- `MAX_FILE_DOWNLOAD_MB`: 最大ファイルダウンロードサイズ、単位MB、デフォルトは`20`
+- `CRYPTO_SECRET`：暗号化キー、Redisデータベースの内容を暗号化するために使用
+- `AZURE_DEFAULT_API_VERSION`：Azureチャネルのデフォルトのバージョン、デフォルトは`2025-04-01-preview`
+- `NOTIFICATION_LIMIT_DURATION_MINUTE`：メールなどの通知制限の継続時間、デフォルトは`10`分
+- `NOTIFY_LIMIT_COUNT`：指定された継続時間内のユーザー通知の最大数、デフォルトは`2`
+- `ERROR_LOG_ENABLED=true`: エラーログを記録して表示するかどうか、デフォルトは`false`
+
+## デプロイ
+
+詳細なデプロイガイドについては[インストールガイド-デプロイ方法](https://docs.newapi.pro/installation)を参照してください：
+
+> [!TIP]
+> 最新のDockerイメージ：`calciumion/new-api:latest`  
+
+### マルチマシンデプロイの注意事項
+- 環境変数`SESSION_SECRET`を設定する必要があります。そうしないとマルチマシンデプロイ時にログイン状態が不一致になります
+- Redisを共有する場合、`CRYPTO_SECRET`を設定する必要があります。そうしないとマルチマシンデプロイ時にRedisの内容を取得できません
+
+### デプロイ要件
+- ローカルデータベース（デフォルト）：SQLite（Dockerデプロイの場合は`/data`ディレクトリをマウントする必要があります）
+- リモートデータベース：MySQLバージョン >= 5.7.8、PgSQLバージョン >= 9.6
+
+### デプロイ方法
+
+#### 宝塔パネルのDocker機能を使用してデプロイ
+宝塔パネル（**9.2.0バージョン**以上）をインストールし、アプリケーションストアで**New-API**を見つけてインストールします。
+[画像付きチュートリアル](./docs/BT.md)
+
+#### Docker Composeを使用してデプロイ（推奨）
+```shell
+# プロジェクトをダウンロード
+git clone https://github.com/Calcium-Ion/new-api.git
+cd new-api
+# 必要に応じてdocker-compose.ymlを編集
+# 起動
+docker-compose up -d
+```
+
+#### Dockerイメージを直接使用
+```shell
+# SQLiteを使用
+docker run --name new-api -d --restart always -p 3000:3000 -e TZ=Asia/Shanghai -v /home/ubuntu/data/new-api:/data calciumion/new-api:latest
+
+# MySQLを使用
+docker run --name new-api -d --restart always -p 3000:3000 -e SQL_DSN="root:123456@tcp(localhost:3306)/oneapi" -e TZ=Asia/Shanghai -v /home/ubuntu/data/new-api:/data calciumion/new-api:latest
+```
+
+## チャネルリトライとキャッシュ
+チャネルリトライ機能はすでに実装されており、`設定->運営設定->一般設定->失敗リトライ回数`でリトライ回数を設定できます。**キャッシュ機能を有効にすることを推奨します**。
+
+### キャッシュ設定方法
+1. `REDIS_CONN_STRING`：Redisをキャッシュとして設定
+2. `MEMORY_CACHE_ENABLED`：メモリキャッシュを有効にする（Redisを設定した場合は手動設定不要）
+
+## APIドキュメント
+
+詳細なAPIドキュメントについては[APIドキュメント](https://docs.newapi.pro/api)を参照してください：
+
+- [チャットインターフェース（Chat Completions）](https://docs.newapi.pro/api/openai-chat)
+- [レスポンスインターフェース（Responses）](https://docs.newapi.pro/api/openai-responses)
+- [画像インターフェース（Image）](https://docs.newapi.pro/api/openai-image)
+- [再ランク付けインターフェース（Rerank）](https://docs.newapi.pro/api/jinaai-rerank)
+- [リアルタイム対話インターフェース（Realtime）](https://docs.newapi.pro/api/openai-realtime)
+- [Claudeチャットインターフェース](https://docs.newapi.pro/api/anthropic-chat)
+- [Google Geminiチャットインターフェース](https://docs.newapi.pro/api/google-gemini-chat)
+
+## 関連プロジェクト
+- [One API](https://github.com/songquanpeng/one-api)：オリジナルプロジェクト
+- [Midjourney-Proxy](https://github.com/novicezk/midjourney-proxy)：Midjourneyインターフェースサポート
+- [neko-api-key-tool](https://github.com/Calcium-Ion/neko-api-key-tool)：キーを使用して使用量クォータを照会
+
+New APIベースのその他のプロジェクト：
+- [new-api-horizon](https://github.com/Calcium-Ion/new-api-horizon)：New API高性能最適化版
+
+## ヘルプサポート
+
+問題がある場合は、[ヘルプサポート](https://docs.newapi.pro/support)を参照してください：
+- [コミュニティ交流](https://docs.newapi.pro/support/community-interaction)
+- [問題のフィードバック](https://docs.newapi.pro/support/feedback-issues)
+- [よくある質問](https://docs.newapi.pro/support/faq)
+
+## 🌟 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.md

@@ -1,5 +1,5 @@
 <p align="right">
-   <strong>中文</strong> | <a href="./README.en.md">English</a> | <a href="./README.fr.md">Français</a>
+   <strong>中文</strong> | <a href="./README.en.md">English</a> | <a href="./README.fr.md">Français</a> | <a href="./README.ja.md">日本語</a>
 </p>
 <div align="center">
 
@@ -75,7 +75,7 @@ New API提供了丰富的功能，详细特性请参考[特性说明](https://do
 
 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）
+3. 💰 支持在线充值功能，当前支持易支付和Stripe
 4. 🔍 支持用key查询使用额度（配合[neko-api-key-tool](https://github.com/Calcium-Ion/neko-api-key-tool)）
 5. 🔄 兼容原版One API的数据库
 6. 💵 支持模型按次数收费
@@ -85,22 +85,23 @@ New API提供了丰富的功能，详细特性请参考[特性说明](https://do
 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：
+13. ⚡ 支持 **OpenAI Responses** 格式，[接口文档](https://docs.newapi.pro/api/openai-responses)
+14. ⚡ 支持 **Claude Messages** 格式，[接口文档](https://docs.newapi.pro/api/anthropic-chat)
+15. ⚡ 支持 **Google Gemini** 格式，[接口文档](https://docs.newapi.pro/api/google-gemini-chat/)
+16. 🧠 支持通过模型名称后缀设置 reasoning effort：
     1. OpenAI o系列模型
         - 添加后缀 `-high` 设置为 high reasoning effort (例如: `o3-mini-high`)
         - 添加后缀 `-medium` 设置为 medium reasoning effort (例如: `o3-mini-medium`)
         - 添加后缀 `-low` 设置为 low reasoning effort (例如: `o3-mini-low`)
     2. Claude 思考模型
         - 添加后缀 `-thinking` 启用思考模式 (例如: `claude-3-7-sonnet-20250219-thinking`)
-16. 🔄 思考转内容功能
-17. 🔄 针对用户的模型限流功能
-18. 🔄 请求格式转换功能，支持以下三种格式转换：
-    1. OpenAI Chat Completions => Claude Messages
+17. 🔄 思考转内容功能
+18. 🔄 针对用户的模型限流功能
+19. 🔄 请求格式转换功能，支持以下三种格式转换：
+    1. OpenAI Chat Completions => Claude Messages （OpenAI格式调用Claude模型）
     2. Clade Messages => OpenAI Chat Completions (可用于Claude Code调用第三方模型)
-    3. OpenAI Chat Completions => Gemini Chat
-19. 💰 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：
+    3. OpenAI Chat Completions => Gemini Chat （OpenAI格式调用Gemini模型）
+20. 💰 缓存计费支持，开启后可以在缓存命中时按照设定的比例计费：
     1. 在 `系统设置-运营设置` 中设置 `提示缓存倍率` 选项
     2. 在渠道中设置 `提示缓存倍率`，范围 0-1，例如设置为 0.5 表示缓存命中时按照 50% 计费
     3. 支持的渠道：
@@ -119,7 +120,9 @@ New API提供了丰富的功能，详细特性请参考[特性说明](https://do
 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
+7. Google Gemini格式，[接口文档](https://docs.newapi.pro/api/google-gemini-chat/)
+8. Dify，当前仅支持chatflow
+9. 更多接口请参考[接口文档](https://docs.newapi.pro/api)
 
 ## 环境变量配置
 
@@ -128,16 +131,14 @@ New API提供了丰富的功能，详细特性请参考[特性说明](https://do
 - `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
+- `CRYPTO_SECRET`：加密密钥，用于加密Redis数据库内容
 - `AZURE_DEFAULT_API_VERSION`：Azure渠道默认API版本，默认 `2025-04-01-preview`
-- `NOTIFICATION_LIMIT_DURATION_MINUTE`：通知限制持续时间，默认 `10`分钟
+- `NOTIFICATION_LIMIT_DURATION_MINUTE`：邮件等通知限制持续时间，默认 `10`分钟
 - `NOTIFY_LIMIT_COUNT`：用户通知在指定持续时间内的最大数量，默认 `2`
 - `ERROR_LOG_ENABLED=true`: 是否记录并显示错误日志，默认`false`
 
@@ -182,7 +183,7 @@ docker run --name new-api -d --restart always -p 3000:3000 -e SQL_DSN="root:1234
 ```
 
 ## 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。
+渠道重试功能已经实现，可以在`设置->运营设置->通用设置->失败重试次数`设置重试次数，**建议开启缓存**功能。
 
 ### 缓存设置方法
 1. `REDIS_CONN_STRING`：设置Redis作为缓存
@@ -192,16 +193,17 @@ docker run --name new-api -d --restart always -p 3000:3000 -e SQL_DSN="root:1234
 
 详细接口文档请参考[接口文档](https://docs.newapi.pro/api)：
 
-- [聊天接口（Chat）](https://docs.newapi.pro/api/openai-chat)
+- [聊天接口（Chat Completions）](https://docs.newapi.pro/api/openai-chat)
+- [响应接口 （Responses）](https://docs.newapi.pro/api/openai-responses)
 - [图像接口（Image）](https://docs.newapi.pro/api/openai-image)
 - [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)
+- [Claude聊天接口](https://docs.newapi.pro/api/anthropic-chat)
+- [Google Gemini聊天接口](https://docs.newapi.pro/api/google-gemini-chat)
 
 ## 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：

common/constants.go

@@ -19,6 +19,7 @@ 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

common/database.go

@@ -12,4 +12,4 @@ var LogSqlType = DatabaseTypeSQLite // Default to SQLite for logging SQL queries
 var UsingMySQL = false
 var UsingClickHouse = false
 
-var SQLitePath = "one-api.db?_busy_timeout=30000"
+var SQLitePath = "one-api.db?_busy_timeout=30000"

common/gin.go

@@ -3,6 +3,7 @@ package common
 import (
 	"bytes"
 	"io"
+	"mime/multipart"
 	"net/http"
 	"one-api/constant"
 	"strings"
@@ -113,3 +114,26 @@ 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 := ""
+	if idx := strings.Index(contentType, "boundary="); idx != -1 {
+		boundary = contentType[idx+9:]
+	}
+
+	reader := multipart.NewReader(bytes.NewReader(requestBody), boundary)
+	form, err := reader.ReadForm(32 << 20) // 32 MB max memory
+	if err != nil {
+		return nil, err
+	}
+
+	// Reset request body
+	c.Request.Body = io.NopCloser(bytes.NewBuffer(requestBody))
+	return form, nil
+}

constant/api_type.go

@@ -31,7 +31,7 @@ const (
 	APITypeXai
 	APITypeCoze
 	APITypeJimeng
-     APITypeMoonshot
-     APITypeSubmodel
-     APITypeDummy    // this one is only for count, do not add any channel after this
+	APITypeMoonshot
+	APITypeSubmodel
+	APITypeDummy // this one is only for count, do not add any channel after this
 )

constant/channel.go

@@ -51,9 +51,10 @@ const (
 	ChannelTypeJimeng         = 51
 	ChannelTypeVidu           = 52
 	ChannelTypeSubmodel       = 53
+	ChannelTypeDoubaoVideo    = 54
+	ChannelTypeSora           = 55
 	ChannelTypeDummy          // this one is only for count, do not add any channel after this
 
-
 )
 
 var ChannelBaseURLs = []string{
@@ -111,4 +112,68 @@ var ChannelBaseURLs = []string{
 	"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
+}
+
+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",
+}
+
+func GetChannelTypeName(channelType int) string {
+	if name, ok := ChannelTypeNames[channelType]; ok {
+		return name
+	}
+	return "Unknown"
 }

controller/billing.go

@@ -5,6 +5,7 @@ import (
 	"one-api/common"
 	"one-api/dto"
 	"one-api/model"
+	"one-api/setting/operation_setting"
 )
 
 func GetSubscription(c *gin.Context) {
@@ -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
@@ -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

@@ -127,6 +127,14 @@ 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 {

controller/channel-test.go

@@ -28,6 +28,7 @@ import (
 	"time"
 
 	"github.com/bytedance/gopkg/util/gopool"
+	"github.com/samber/lo"
 
 	"github.com/gin-gonic/gin"
 )
@@ -40,45 +41,39 @@ type testResult struct {
 
 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"
 
 	// 如果指定了端点类型，使用指定的端点类型
@@ -110,18 +105,6 @@ func testChannel(channel *model.Channel, testModel string, endpointType string)
 		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{
@@ -639,10 +622,10 @@ func AutomaticallyTestChannels() {
 				time.Sleep(10 * time.Minute)
 				continue
 			}
-			frequency := operation_setting.GetMonitorSetting().AutoTestChannelMinutes
-			common.SysLog(fmt.Sprintf("automatically test channels with interval %d minutes", frequency))
 			for {
+				frequency := operation_setting.GetMonitorSetting().AutoTestChannelMinutes
 				time.Sleep(time.Duration(frequency) * time.Minute)
+				common.SysLog(fmt.Sprintf("automatically test channels with interval %d minutes", frequency))
 				common.SysLog("automatically testing all channels")
 				_ = testAllChannels(false)
 				common.SysLog("automatically channel test finished")

controller/channel.go

@@ -198,9 +198,10 @@ func FetchUpstreamModels(c *gin.Context) {
 	// 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 {
+	switch channel.Type {
+	case constant.ChannelTypeAnthropic:
+		body, err = GetResponseBody("GET", url, channel, GetClaudeAuthHeader(key))
+	default:
 		body, err = GetResponseBody("GET", url, channel, GetAuthHeader(key))
 	}
 	if err != nil {

controller/misc.go

@@ -43,6 +43,7 @@ func GetStatus(c *gin.Context) {
 	defer common.OptionMapRWMutex.RUnlock()
 
 	passkeySetting := system_setting.GetPasskeySettings()
+	legalSetting := system_setting.GetLegalSettings()
 
 	data := gin.H{
 		"version":                     common.Version,
@@ -66,18 +67,22 @@ func GetStatus(c *gin.Context) {
 		"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,
-		"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,
+		// 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,
@@ -104,6 +109,8 @@ func GetStatus(c *gin.Context) {
 		"passkey_user_verification":   passkeySetting.UserVerification,
 		"passkey_attachment":          passkeySetting.AttachmentPreference,
 		"setup":                       constant.Setup,
+		"user_agreement_enabled":      legalSetting.UserAgreement != "",
+		"privacy_policy_enabled":      legalSetting.PrivacyPolicy != "",
 	}
 
 	// 根据启用状态注入可选内容
@@ -147,6 +154,24 @@ 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()

controller/setup.go

@@ -178,4 +178,4 @@ func boolToString(b bool) string {
 		return "true"
 	}
 	return "false"
-}
+}

controller/task_video.go

@@ -13,6 +13,7 @@ import (
 	"one-api/relay"
 	"one-api/relay/channel"
 	relaycommon "one-api/relay/common"
+	"one-api/setting/ratio_setting"
 	"time"
 )
 
@@ -46,6 +47,11 @@ 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(),
+	}
+	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()))
@@ -91,6 +97,7 @@ func updateVideoSingleTask(ctx context.Context, adaptor channel.TaskAdaptor, cha
 		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 {
@@ -120,6 +127,91 @@ func updateVideoSingleTask(ctx context.Context, adaptor channel.TaskAdaptor, cha
 		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
+						user, err := model.GetUserById(task.UserId, false)
+						if err == nil {
+							groupRatio := ratio_setting.GetGroupRatio(user.Group)
+							userGroupRatio, hasUserGroupRatio := ratio_setting.GetGroupGroupRatio(user.Group, user.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:
 		task.Status = model.TaskStatusFailure
 		task.Progress = "100%"

controller/topup.go

@@ -86,8 +86,9 @@ func GetEpayClient() *epay.Client {
 
 func getPayMoney(amount int64, group string) float64 {
 	dAmount := decimal.NewFromInt(amount)
-
-	if !common.DisplayInCurrencyEnabled {
+	// 充值金额以“展示类型”为准：
+	// - USD/CNY: 前端传 amount 为金额单位；TOKENS: 前端传 tokens，需要换成 USD 金额
+	if operation_setting.GetQuotaDisplayType() == operation_setting.QuotaDisplayTypeTokens {
 		dQuotaPerUnit := decimal.NewFromFloat(common.QuotaPerUnit)
 		dAmount = dAmount.Div(dQuotaPerUnit)
 	}
@@ -115,7 +116,7 @@ func getPayMoney(amount int64, group string) float64 {
 
 func getMinTopup() int64 {
 	minTopup := operation_setting.MinTopUp
-	if !common.DisplayInCurrencyEnabled {
+	if operation_setting.GetQuotaDisplayType() == operation_setting.QuotaDisplayTypeTokens {
 		dMinTopup := decimal.NewFromInt(int64(minTopup))
 		dQuotaPerUnit := decimal.NewFromFloat(common.QuotaPerUnit)
 		minTopup = int(dMinTopup.Mul(dQuotaPerUnit).IntPart())
@@ -176,18 +177,19 @@ func RequestEpay(c *gin.Context) {
 		return
 	}
 	amount := req.Amount
-	if !common.DisplayInCurrencyEnabled {
+	if operation_setting.GetQuotaDisplayType() == operation_setting.QuotaDisplayTypeTokens {
 		dAmount := decimal.NewFromInt(int64(amount))
 		dQuotaPerUnit := decimal.NewFromFloat(common.QuotaPerUnit)
 		amount = dAmount.Div(dQuotaPerUnit).IntPart()
 	}
 	topUp := &model.TopUp{
-		UserId:     id,
-		Amount:     amount,
-		Money:      payMoney,
-		TradeNo:    tradeNo,
-		CreateTime: time.Now().Unix(),
-		Status:     "pending",
+		UserId:        id,
+		Amount:        amount,
+		Money:         payMoney,
+		TradeNo:       tradeNo,
+		PaymentMethod: req.PaymentMethod,
+		CreateTime:    time.Now().Unix(),
+		Status:        "pending",
 	}
 	err = topUp.Insert()
 	if err != nil {
@@ -235,8 +237,8 @@ func EpayNotify(c *gin.Context) {
 		_, err := c.Writer.Write([]byte("fail"))
 		if err != nil {
 			log.Println("易支付回调写入失败")
-			return
 		}
+		return
 	}
 	verifyInfo, err := client.Verify(params)
 	if err == nil && verifyInfo.VerifyStatus {
@@ -312,3 +314,76 @@ func RequestAmount(c *gin.Context) {
 	}
 	c.JSON(200, gin.H{"message": "success", "data": strconv.FormatFloat(payMoney, 'f', 2, 64)})
 }
+
+func GetUserTopUps(c *gin.Context) {
+	userId := c.GetInt("id")
+	pageInfo := common.GetPageQuery(c)
+	keyword := c.Query("keyword")
+
+	var (
+		topups []*model.TopUp
+		total  int64
+		err    error
+	)
+	if keyword != "" {
+		topups, total, err = model.SearchUserTopUps(userId, keyword, pageInfo)
+	} else {
+		topups, total, err = model.GetUserTopUps(userId, pageInfo)
+	}
+	if err != nil {
+		common.ApiError(c, err)
+		return
+	}
+
+	pageInfo.SetTotal(int(total))
+	pageInfo.SetItems(topups)
+	common.ApiSuccess(c, pageInfo)
+}
+
+// GetAllTopUps 管理员获取全平台充值记录
+func GetAllTopUps(c *gin.Context) {
+	pageInfo := common.GetPageQuery(c)
+	keyword := c.Query("keyword")
+
+	var (
+		topups []*model.TopUp
+		total  int64
+		err    error
+	)
+	if keyword != "" {
+		topups, total, err = model.SearchAllTopUps(keyword, pageInfo)
+	} else {
+		topups, total, err = model.GetAllTopUps(pageInfo)
+	}
+	if err != nil {
+		common.ApiError(c, err)
+		return
+	}
+
+	pageInfo.SetTotal(int(total))
+	pageInfo.SetItems(topups)
+	common.ApiSuccess(c, pageInfo)
+}
+
+type AdminCompleteTopupRequest struct {
+	TradeNo string `json:"trade_no"`
+}
+
+// AdminCompleteTopUp 管理员补单接口
+func AdminCompleteTopUp(c *gin.Context) {
+	var req AdminCompleteTopupRequest
+	if err := c.ShouldBindJSON(&req); err != nil || req.TradeNo == "" {
+		common.ApiErrorMsg(c, "参数错误")
+		return
+	}
+
+	// 订单级互斥，防止并发补单
+	LockOrder(req.TradeNo)
+	defer UnlockOrder(req.TradeNo)
+
+	if err := model.ManualCompleteTopUp(req.TradeNo); err != nil {
+		common.ApiError(c, err)
+		return
+	}
+	common.ApiSuccess(c, nil)
+}

controller/topup_stripe.go

@@ -83,12 +83,13 @@ func (*StripeAdaptor) RequestPay(c *gin.Context, req *StripePayRequest) {
 	}
 
 	topUp := &model.TopUp{
-		UserId:     id,
-		Amount:     req.Amount,
-		Money:      chargedMoney,
-		TradeNo:    referenceId,
-		CreateTime: time.Now().Unix(),
-		Status:     common.TopUpStatusPending,
+		UserId:        id,
+		Amount:        req.Amount,
+		Money:         chargedMoney,
+		TradeNo:       referenceId,
+		PaymentMethod: PaymentMethodStripe,
+		CreateTime:    time.Now().Unix(),
+		Status:        common.TopUpStatusPending,
 	}
 	err = topUp.Insert()
 	if err != nil {
@@ -258,7 +259,7 @@ func GetChargedAmount(count float64, user model.User) float64 {
 
 func getStripePayMoney(amount float64, group string) float64 {
 	originalAmount := amount
-	if !common.DisplayInCurrencyEnabled {
+	if operation_setting.GetQuotaDisplayType() == operation_setting.QuotaDisplayTypeTokens {
 		amount = amount / common.QuotaPerUnit
 	}
 	// Using float64 for monetary calculations is acceptable here due to the small amounts involved
@@ -279,7 +280,7 @@ func getStripePayMoney(amount float64, group string) float64 {
 
 func getStripeMinTopup() int64 {
 	minTopup := setting.StripeMinTopUp
-	if !common.DisplayInCurrencyEnabled {
+	if operation_setting.GetQuotaDisplayType() == operation_setting.QuotaDisplayTypeTokens {
 		minTopup = minTopup * int(common.QuotaPerUnit)
 	}
 	return int64(minTopup)

controller/user.go

@@ -1102,6 +1102,9 @@ type UpdateUserSettingRequest struct {
 	WebhookSecret              string  `json:"webhook_secret,omitempty"`
 	NotificationEmail          string  `json:"notification_email,omitempty"`
 	BarkUrl                    string  `json:"bark_url,omitempty"`
+	GotifyUrl                  string  `json:"gotify_url,omitempty"`
+	GotifyToken                string  `json:"gotify_token,omitempty"`
+	GotifyPriority             int     `json:"gotify_priority,omitempty"`
 	AcceptUnsetModelRatioModel bool    `json:"accept_unset_model_ratio_model"`
 	RecordIpLog                bool    `json:"record_ip_log"`
 }
@@ -1117,7 +1120,7 @@ func UpdateUserSetting(c *gin.Context) {
 	}
 
 	// 验证预警类型
-	if req.QuotaWarningType != dto.NotifyTypeEmail && req.QuotaWarningType != dto.NotifyTypeWebhook && req.QuotaWarningType != dto.NotifyTypeBark {
+	if req.QuotaWarningType != dto.NotifyTypeEmail && req.QuotaWarningType != dto.NotifyTypeWebhook && req.QuotaWarningType != dto.NotifyTypeBark && req.QuotaWarningType != dto.NotifyTypeGotify {
 		c.JSON(http.StatusOK, gin.H{
 			"success": false,
 			"message": "无效的预警类型",
@@ -1192,6 +1195,40 @@ func UpdateUserSetting(c *gin.Context) {
 		}
 	}
 
+	// 如果是Gotify类型，验证Gotify URL和Token
+	if req.QuotaWarningType == dto.NotifyTypeGotify {
+		if req.GotifyUrl == "" {
+			c.JSON(http.StatusOK, gin.H{
+				"success": false,
+				"message": "Gotify服务器地址不能为空",
+			})
+			return
+		}
+		if req.GotifyToken == "" {
+			c.JSON(http.StatusOK, gin.H{
+				"success": false,
+				"message": "Gotify令牌不能为空",
+			})
+			return
+		}
+		// 验证URL格式
+		if _, err := url.ParseRequestURI(req.GotifyUrl); err != nil {
+			c.JSON(http.StatusOK, gin.H{
+				"success": false,
+				"message": "无效的Gotify服务器地址",
+			})
+			return
+		}
+		// 检查是否是HTTP或HTTPS
+		if !strings.HasPrefix(req.GotifyUrl, "https://") && !strings.HasPrefix(req.GotifyUrl, "http://") {
+			c.JSON(http.StatusOK, gin.H{
+				"success": false,
+				"message": "Gotify服务器地址必须以http://或https://开头",
+			})
+			return
+		}
+	}
+
 	userId := c.GetInt("id")
 	user, err := model.GetUserById(userId, true)
 	if err != nil {
@@ -1225,6 +1262,18 @@ func UpdateUserSetting(c *gin.Context) {
 		settings.BarkUrl = req.BarkUrl
 	}
 
+	// 如果是Gotify类型，添加Gotify配置到设置中
+	if req.QuotaWarningType == dto.NotifyTypeGotify {
+		settings.GotifyUrl = req.GotifyUrl
+		settings.GotifyToken = req.GotifyToken
+		// Gotify优先级范围0-10，超出范围则使用默认值5
+		if req.GotifyPriority < 0 || req.GotifyPriority > 10 {
+			settings.GotifyPriority = 5
+		} else {
+			settings.GotifyPriority = req.GotifyPriority
+		}
+	}
+
 	// 更新用户设置
 	user.SetSetting(settings)
 	if err := user.Update(false); err != nil {

controller/video_proxy.go

@@ -0,0 +1,129 @@
+package controller
+
+import (
+	"fmt"
+	"io"
+	"net/http"
+	"one-api/logger"
+	"one-api/model"
+	"time"
+
+	"github.com/gin-gonic/gin"
+)
+
+func VideoProxy(c *gin.Context) {
+	taskID := c.Param("task_id")
+	if taskID == "" {
+		c.JSON(http.StatusBadRequest, gin.H{
+			"error": gin.H{
+				"message": "task_id is required",
+				"type":    "invalid_request_error",
+			},
+		})
+		return
+	}
+
+	task, exists, err := model.GetByOnlyTaskId(taskID)
+	if err != nil {
+		logger.LogError(c.Request.Context(), fmt.Sprintf("Failed to query task %s: %s", taskID, err.Error()))
+		c.JSON(http.StatusInternalServerError, gin.H{
+			"error": gin.H{
+				"message": "Failed to query task",
+				"type":    "server_error",
+			},
+		})
+		return
+	}
+	if !exists || task == nil {
+		logger.LogError(c.Request.Context(), fmt.Sprintf("Failed to get task %s: %s", taskID, err.Error()))
+		c.JSON(http.StatusNotFound, gin.H{
+			"error": gin.H{
+				"message": "Task not found",
+				"type":    "invalid_request_error",
+			},
+		})
+		return
+	}
+
+	if task.Status != model.TaskStatusSuccess {
+		c.JSON(http.StatusBadRequest, gin.H{
+			"error": gin.H{
+				"message": fmt.Sprintf("Task is not completed yet, current status: %s", task.Status),
+				"type":    "invalid_request_error",
+			},
+		})
+		return
+	}
+
+	channel, err := model.CacheGetChannel(task.ChannelId)
+	if err != nil {
+		logger.LogError(c.Request.Context(), fmt.Sprintf("Failed to get channel %d: %s", task.ChannelId, err.Error()))
+		c.JSON(http.StatusInternalServerError, gin.H{
+			"error": gin.H{
+				"message": "Failed to retrieve channel information",
+				"type":    "server_error",
+			},
+		})
+		return
+	}
+	baseURL := channel.GetBaseURL()
+	if baseURL == "" {
+		baseURL = "https://api.openai.com"
+	}
+	videoURL := fmt.Sprintf("%s/v1/videos/%s/content", baseURL, task.TaskID)
+
+	client := &http.Client{
+		Timeout: 60 * time.Second,
+	}
+
+	req, err := http.NewRequestWithContext(c.Request.Context(), http.MethodGet, videoURL, nil)
+	if err != nil {
+		logger.LogError(c.Request.Context(), fmt.Sprintf("Failed to create request for %s: %s", videoURL, err.Error()))
+		c.JSON(http.StatusInternalServerError, gin.H{
+			"error": gin.H{
+				"message": "Failed to create proxy request",
+				"type":    "server_error",
+			},
+		})
+		return
+	}
+
+	req.Header.Set("Authorization", "Bearer "+channel.Key)
+
+	resp, err := client.Do(req)
+	if err != nil {
+		logger.LogError(c.Request.Context(), fmt.Sprintf("Failed to fetch video from %s: %s", videoURL, err.Error()))
+		c.JSON(http.StatusBadGateway, gin.H{
+			"error": gin.H{
+				"message": "Failed to fetch video content",
+				"type":    "server_error",
+			},
+		})
+		return
+	}
+	defer resp.Body.Close()
+
+	if resp.StatusCode != http.StatusOK {
+		logger.LogError(c.Request.Context(), fmt.Sprintf("Upstream returned status %d for %s", resp.StatusCode, videoURL))
+		c.JSON(http.StatusBadGateway, gin.H{
+			"error": gin.H{
+				"message": fmt.Sprintf("Upstream service returned status %d", resp.StatusCode),
+				"type":    "server_error",
+			},
+		})
+		return
+	}
+
+	for key, values := range resp.Header {
+		for _, value := range values {
+			c.Writer.Header().Add(key, value)
+		}
+	}
+
+	c.Writer.Header().Set("Cache-Control", "public, max-age=86400") // Cache for 24 hours
+	c.Writer.WriteHeader(resp.StatusCode)
+	_, err = io.Copy(c.Writer, resp.Body)
+	if err != nil {
+		logger.LogError(c.Request.Context(), fmt.Sprintf("Failed to stream video content: %s", err.Error()))
+	}
+}

docker-compose.yml

@@ -1,4 +1,18 @@
-version: '3.4'
+# New-API Docker Compose Configuration
+# 
+# Quick Start:
+#   1. docker-compose up -d
+#   2. Access at http://localhost:3000
+#
+# Using MySQL instead of PostgreSQL:
+#   1. Comment out the postgres service and SQL_DSN line 15
+#   2. Uncomment the mysql service and SQL_DSN line 16
+#   3. Uncomment mysql in depends_on (line 28)
+#   4. Uncomment mysql_data in volumes section (line 64)
+#
+# ⚠️  IMPORTANT: Change all default passwords before deploying to production!
+
+version: '3.4' # For compatibility with older Docker versions
 
 services:
   new-api:
@@ -12,21 +26,22 @@ services:
       - ./data:/data
       - ./logs:/app/logs
     environment:
-      - SQL_DSN=root:123456@tcp(mysql:3306)/new-api  # Point to the mysql service
+      - SQL_DSN=postgresql://root:123456@postgres:5432/new-api # ⚠️ IMPORTANT: Change the password in production!
+#      - SQL_DSN=root:123456@tcp(mysql:3306)/new-api  # Point to the mysql service, uncomment if using MySQL
       - REDIS_CONN_STRING=redis://redis
       - TZ=Asia/Shanghai
       - ERROR_LOG_ENABLED=true # 是否启用错误日志记录
-    #      - STREAMING_TIMEOUT=300  # 流模式无响应超时时间，单位秒，默认120秒，如果出现空补全可以尝试改为更大值
-    #      - SESSION_SECRET=random_string  # 多机部署时设置，必须修改这个随机字符串！！！！！！！
-    #      - NODE_TYPE=slave  # Uncomment for slave node in multi-node deployment
-    #      - SYNC_FREQUENCY=60  # Uncomment if regular database syncing is needed
-    #      - FRONTEND_BASE_URL=https://openai.justsong.cn  # Uncomment for multi-node deployment with front-end URL
+      - BATCH_UPDATE_ENABLED=true  # 是否启用批量更新 batch update enabled
+#      - STREAMING_TIMEOUT=300  # 流模式无响应超时时间，单位秒，默认120秒，如果出现空补全可以尝试改为更大值 Streaming timeout in seconds, default is 120s. Increase if experiencing empty completions
+#      - SESSION_SECRET=random_string  # 多机部署时设置，必须修改这个随机字符串！！ multi-node deployment, set this to a random string!!!!!!!
+#      - SYNC_FREQUENCY=60  # Uncomment if regular database syncing is needed
 
     depends_on:
       - redis
-      - mysql
+      - postgres
+#      - mysql  # Uncomment if using MySQL
     healthcheck:
-      test: ["CMD-SHELL", "wget -q -O - http://localhost:3000/api/status | grep -o '\"success\":\\s*true' | awk -F: '{print $$2}'"]
+      test: ["CMD-SHELL", "wget -q -O - http://localhost:3000/api/status | grep -o '\"success\":\\s*true' || exit 1"]
       interval: 30s
       timeout: 10s
       retries: 3
@@ -36,17 +51,31 @@ services:
     container_name: redis
     restart: always
 
-  mysql:
-    image: mysql:8.2
-    container_name: mysql
+  postgres:
+    image: postgres:15
+    container_name: postgres
     restart: always
     environment:
-      MYSQL_ROOT_PASSWORD: 123456  # Ensure this matches the password in SQL_DSN
-      MYSQL_DATABASE: new-api
+      POSTGRES_USER: root
+      POSTGRES_PASSWORD: 123456  # ⚠️ IMPORTANT: Change this password in production!
+      POSTGRES_DB: new-api
     volumes:
-      - mysql_data:/var/lib/mysql
-    # ports:
-    #   - "3306:3306"  # If you want to access MySQL from outside Docker, uncomment
+      - pg_data:/var/lib/postgresql/data
+#    ports:
+#      - "5432:5432"  # Uncomment if you need to access PostgreSQL from outside Docker
+
+#  mysql:
+#    image: mysql:8.2
+#    container_name: mysql
+#    restart: always
+#    environment:
+#      MYSQL_ROOT_PASSWORD: 123456  # ⚠️ IMPORTANT: Change this password in production!
+#      MYSQL_DATABASE: new-api
+#    volumes:
+#      - mysql_data:/var/lib/mysql
+#    ports:
+#      - "3306:3306"  # Uncomment if you need to access MySQL from outside Docker
 
 volumes:
-  mysql_data:
+  pg_data:
+#  mysql_data:

docs/translation-glossary.md

@@ -0,0 +1,72 @@
+# 翻译术语表 (Translation Glossary)
+
+本文档为翻译贡献者提供项目中关键术语的标准翻译参考，以确保翻译的一致性和准确性。
+
+This document provides standard translation references for key terminology in the project to ensure consistency and accuracy for translation contributors.
+
+## 核心概念 (Core Concepts)
+
+| 中文 | English | 说明 | Description |
+|------|---------|------|-------------|
+| 倍率 | Ratio | 用于计算价格的乘数因子 | Multiplier factor used for price calculation |
+| 令牌 | Token | API访问凭证，也指模型处理的文本单元 | API access credentials or text units processed by models |
+| 渠道 | Channel | API服务提供商的接入通道 | Access channel for API service providers |
+| 分组 | Group | 用户或令牌的分类，影响价格倍率 | Classification of users or tokens, affecting price ratios |
+| 额度 | Quota | 用户可用的服务额度 | Available service quota for users |
+
+## 模型相关 (Model Related)
+
+| 中文 | English | 说明 | Description |
+|------|---------|------|-------------|
+| 提示 | Prompt | 模型输入内容 | Model input content |
+| 补全 | Completion | 模型输出内容 | Model output content |
+| 输入 | Input/Prompt | 发送给模型的内容 | Content sent to the model |
+| 输出 | Output/Completion | 模型返回的内容 | Content returned by the model |
+| 模型倍率 | Model Ratio | 不同模型的计费倍率 | Billing ratio for different models |
+| 补全倍率 | Completion Ratio | 输出内容的额外计费倍率 | Additional billing ratio for output content |
+| 固定价格 | Price per call | 按次计费的价格 | Fixed price per call |
+| 按量计费 | Pay-as-you-go | 根据使用量计费 | Billing based on usage |
+| 按次计费 | Pay-per-view | 每次调用固定价格 | Fixed price per invocation |
+
+## 用户管理 (User Management)
+
+| 中文 | English | 说明 | Description |
+|------|---------|------|-------------|
+| 超级管理员 | Root User | 最高权限管理员 | Administrator with highest privileges |
+| 管理员 | Admin User | 系统管理员 | System administrator |
+| 普通用户 | Normal User | 普通权限用户 | Regular user with standard privileges |
+
+## 充值与兑换 (Recharge & Redemption)
+
+| 中文 | English | 说明 | Description |
+|------|---------|------|-------------|
+| 充值 | Top Up | 为账户增加额度 | Add quota to account |
+| 兑换码 | Redemption Code | 可兑换额度的代码 | Code that can be redeemed for quota |
+
+## 渠道管理 (Channel Management)
+
+| 中文 | English | 说明 | Description |
+|------|---------|------|-------------|
+| 渠道 | Channel | API服务提供通道 | API service provider channel |
+| 密钥 | Key | API访问密钥 | API access key |
+| 优先级 | Priority | 渠道选择优先级 | Channel selection priority |
+| 权重 | Weight | 负载均衡权重 | Load balancing weight |
+| 代理 | Proxy | 代理服务器地址 | Proxy server address |
+| 模型重定向 | Model Mapping | 请求体中模型名称替换 | Model name replacement in request body |
+
+## 翻译注意事项 (Translation Guidelines)
+
+- **提示 (Prompt)** = 模型输入内容 / Model input content
+- **补全 (Completion)** = 模型输出内容 / Model output content
+- **倍率 (Ratio)** = 价格计算的乘数因子 / Multiplier factor for price calculation
+- **额度 (Quota)** = 可用的用户服务额度，有时也翻译为 Credit / Available service quota for users, sometimes also translated as Credit
+- **Token** = 根据上下文可能指 / Depending on context, may refer to:
+  - API访问令牌 (API Token)
+  - 模型处理的文本单元 (Text Token)
+  - 系统访问令牌 (Access Token)
+
+---
+
+**贡献说明**: 如发现术语翻译不一致或有更好的翻译建议，欢迎提交 Issue 或 Pull Request。
+
+**Contribution Note**: If you find any inconsistencies in terminology translations or have better translation suggestions, please feel free to submit an Issue or Pull Request.

dto/channel_settings.go

@@ -20,6 +20,9 @@ type ChannelOtherSettings struct {
 	AzureResponsesVersion string        `json:"azure_responses_version,omitempty"`
 	VertexKeyType         VertexKeyType `json:"vertex_key_type,omitempty"` // "json" or "api_key"
 	OpenRouterEnterprise  *bool         `json:"openrouter_enterprise,omitempty"`
+	AllowServiceTier      bool          `json:"allow_service_tier,omitempty"`      // 是否允许 service_tier 透传（默认过滤以避免额外计费）
+	DisableStore          bool          `json:"disable_store,omitempty"`           // 是否禁用 store 透传（默认允许透传，禁用后可能导致 Codex 无法使用）
+	AllowSafetyIdentifier bool          `json:"allow_safety_identifier,omitempty"` // 是否允许 safety_identifier 透传（默认过滤以保护用户隐私）
 }
 
 func (s *ChannelOtherSettings) IsOpenRouterEnterprise() bool {

dto/claude.go

@@ -195,12 +195,15 @@ type ClaudeRequest struct {
 	Temperature       *float64        `json:"temperature,omitempty"`
 	TopP              float64         `json:"top_p,omitempty"`
 	TopK              int             `json:"top_k,omitempty"`
-	//ClaudeMetadata    `json:"metadata,omitempty"`
 	Stream            bool            `json:"stream,omitempty"`
 	Tools             any             `json:"tools,omitempty"`
 	ContextManagement json.RawMessage `json:"context_management,omitempty"`
 	ToolChoice        any             `json:"tool_choice,omitempty"`
 	Thinking          *Thinking       `json:"thinking,omitempty"`
+	McpServers        json.RawMessage `json:"mcp_servers,omitempty"`
+	Metadata          json.RawMessage `json:"metadata,omitempty"`
+	// 服务层级字段，用于指定 API 服务等级。允许透传可能导致实际计费高于预期，默认应过滤
+	ServiceTier string `json:"service_tier,omitempty"`
 }
 
 func (c *ClaudeRequest) GetTokenCountMeta() *types.TokenCountMeta {

dto/gemini.go

@@ -2,11 +2,12 @@ package dto
 
 import (
 	"encoding/json"
-	"github.com/gin-gonic/gin"
 	"one-api/common"
 	"one-api/logger"
 	"one-api/types"
 	"strings"
+
+	"github.com/gin-gonic/gin"
 )
 
 type GeminiChatRequest struct {
@@ -273,6 +274,7 @@ type GeminiChatGenerationConfig struct {
 	ResponseModalities []string              `json:"responseModalities,omitempty"`
 	ThinkingConfig     *GeminiThinkingConfig `json:"thinkingConfig,omitempty"`
 	SpeechConfig       json.RawMessage       `json:"speechConfig,omitempty"` // RawMessage to allow flexible speech config
+	ImageConfig        json.RawMessage       `json:"imageConfig,omitempty"`  // RawMessage to allow flexible image config
 }
 
 type MediaResolution string
@@ -291,12 +293,13 @@ type GeminiChatSafetyRating struct {
 
 type GeminiChatPromptFeedback struct {
 	SafetyRatings []GeminiChatSafetyRating `json:"safetyRatings"`
+	BlockReason   *string                  `json:"blockReason,omitempty"`
 }
 
 type GeminiChatResponse struct {
-	Candidates     []GeminiChatCandidate    `json:"candidates"`
-	PromptFeedback GeminiChatPromptFeedback `json:"promptFeedback"`
-	UsageMetadata  GeminiUsageMetadata      `json:"usageMetadata"`
+	Candidates     []GeminiChatCandidate     `json:"candidates"`
+	PromptFeedback *GeminiChatPromptFeedback `json:"promptFeedback,omitempty"`
+	UsageMetadata  GeminiUsageMetadata       `json:"usageMetadata"`
 }
 
 type GeminiUsageMetadata struct {
@@ -326,6 +329,7 @@ type GeminiImageParameters struct {
 	SampleCount      int    `json:"sampleCount,omitempty"`
 	AspectRatio      string `json:"aspectRatio,omitempty"`
 	PersonGeneration string `json:"personGeneration,omitempty"`
+	ImageSize        string `json:"imageSize,omitempty"`
 }
 
 type GeminiImageResponse struct {

dto/openai_image.go

@@ -74,14 +74,15 @@ func (r ImageRequest) MarshalJSON() ([]byte, error) {
 		return nil, err
 	}
 
+	// 不能合并ExtraFields！！！！！！！！
 	// 合并 ExtraFields
-	for k, v := range r.Extra {
-		if _, exists := baseMap[k]; !exists {
-			baseMap[k] = v
-		}
-	}
+	//for k, v := range r.Extra {
+	//	if _, exists := baseMap[k]; !exists {
+	//		baseMap[k] = v
+	//	}
+	//}
 
-	return json.Marshal(baseMap)
+	return common.Marshal(baseMap)
 }
 
 func GetJSONFieldNames(t reflect.Type) map[string]struct{} {

dto/openai_request.go

@@ -57,6 +57,18 @@ type GeneralOpenAIRequest struct {
 	Dimensions          int               `json:"dimensions,omitempty"`
 	Modalities          json.RawMessage   `json:"modalities,omitempty"`
 	Audio               json.RawMessage   `json:"audio,omitempty"`
+	// 安全标识符，用于帮助 OpenAI 检测可能违反使用政策的应用程序用户
+	// 注意：此字段会向 OpenAI 发送用户标识信息，默认过滤以保护用户隐私
+	SafetyIdentifier string `json:"safety_identifier,omitempty"`
+	// Whether or not to store the output of this chat completion request for use in our model distillation or evals products.
+	// 是否存储此次请求数据供 OpenAI 用于评估和优化产品
+	// 注意：默认过滤此字段以保护用户隐私，但过滤后可能导致 Codex 无法正常使用
+	Store json.RawMessage `json:"store,omitempty"`
+	// Used by OpenAI to cache responses for similar requests to optimize your cache hit rates. Replaces the user field
+	PromptCacheKey string          `json:"prompt_cache_key,omitempty"`
+	LogitBias      json.RawMessage `json:"logit_bias,omitempty"`
+	Metadata       json.RawMessage `json:"metadata,omitempty"`
+	Prediction     json.RawMessage `json:"prediction,omitempty"`
 	// gemini
 	ExtraBody json.RawMessage `json:"extra_body,omitempty"`
 	//xai
@@ -75,6 +87,12 @@ type GeneralOpenAIRequest struct {
 	WebSearch json.RawMessage `json:"web_search,omitempty"`
 	// doubao,zhipu_v4
 	THINKING json.RawMessage `json:"thinking,omitempty"`
+	// pplx Params
+	SearchDomainFilter     json.RawMessage `json:"search_domain_filter,omitempty"`
+	SearchRecencyFilter    string          `json:"search_recency_filter,omitempty"`
+	ReturnImages           bool            `json:"return_images,omitempty"`
+	ReturnRelatedQuestions bool            `json:"return_related_questions,omitempty"`
+	SearchMode             string          `json:"search_mode,omitempty"`
 }
 
 func (r *GeneralOpenAIRequest) GetTokenCountMeta() *types.TokenCountMeta {
@@ -775,19 +793,20 @@ type OpenAIResponsesRequest struct {
 	ParallelToolCalls  json.RawMessage `json:"parallel_tool_calls,omitempty"`
 	PreviousResponseID string          `json:"previous_response_id,omitempty"`
 	Reasoning          *Reasoning      `json:"reasoning,omitempty"`
-	ServiceTier        string          `json:"service_tier,omitempty"`
-	Store              json.RawMessage `json:"store,omitempty"`
-	PromptCacheKey     json.RawMessage `json:"prompt_cache_key,omitempty"`
-	Stream             bool            `json:"stream,omitempty"`
-	Temperature        float64         `json:"temperature,omitempty"`
-	Text               json.RawMessage `json:"text,omitempty"`
-	ToolChoice         json.RawMessage `json:"tool_choice,omitempty"`
-	Tools              json.RawMessage `json:"tools,omitempty"` // 需要处理的参数很少，MCP 参数太多不确定，所以用 map
-	TopP               float64         `json:"top_p,omitempty"`
-	Truncation         string          `json:"truncation,omitempty"`
-	User               string          `json:"user,omitempty"`
-	MaxToolCalls       uint            `json:"max_tool_calls,omitempty"`
-	Prompt             json.RawMessage `json:"prompt,omitempty"`
+	// 服务层级字段，用于指定 API 服务等级。允许透传可能导致实际计费高于预期，默认应过滤
+	ServiceTier    string          `json:"service_tier,omitempty"`
+	Store          json.RawMessage `json:"store,omitempty"`
+	PromptCacheKey json.RawMessage `json:"prompt_cache_key,omitempty"`
+	Stream         bool            `json:"stream,omitempty"`
+	Temperature    float64         `json:"temperature,omitempty"`
+	Text           json.RawMessage `json:"text,omitempty"`
+	ToolChoice     json.RawMessage `json:"tool_choice,omitempty"`
+	Tools          json.RawMessage `json:"tools,omitempty"` // 需要处理的参数很少，MCP 参数太多不确定，所以用 map
+	TopP           float64         `json:"top_p,omitempty"`
+	Truncation     string          `json:"truncation,omitempty"`
+	User           string          `json:"user,omitempty"`
+	MaxToolCalls   uint            `json:"max_tool_calls,omitempty"`
+	Prompt         json.RawMessage `json:"prompt,omitempty"`
 }
 
 func (r *OpenAIResponsesRequest) GetTokenCountMeta() *types.TokenCountMeta {

dto/openai_response.go

@@ -233,6 +233,16 @@ type Usage struct {
 	Cost any `json:"cost,omitempty"`
 }
 
+type OpenAIVideoResponse struct {
+	Id        string `json:"id" example:"file-abc123"`
+	Object    string `json:"object" example:"file"`
+	Bytes     int64  `json:"bytes" example:"120000"`
+	CreatedAt int64  `json:"created_at" example:"1677610602"`
+	ExpiresAt int64  `json:"expires_at" example:"1677614202"`
+	Filename  string `json:"filename" example:"mydata.jsonl"`
+	Purpose   string `json:"purpose" example:"fine-tune"`
+}
+
 type InputTokenDetails struct {
 	CachedTokens         int `json:"cached_tokens"`
 	CachedCreationTokens int `json:"-"`

dto/user_settings.go

@@ -7,6 +7,9 @@ type UserSetting struct {
 	WebhookSecret         string  `json:"webhook_secret,omitempty"`                 // WebhookSecret webhook密钥
 	NotificationEmail     string  `json:"notification_email,omitempty"`             // NotificationEmail 通知邮箱地址
 	BarkUrl               string  `json:"bark_url,omitempty"`                       // BarkUrl Bark推送URL
+	GotifyUrl             string  `json:"gotify_url,omitempty"`                     // GotifyUrl Gotify服务器地址
+	GotifyToken           string  `json:"gotify_token,omitempty"`                   // GotifyToken Gotify应用令牌
+	GotifyPriority        int     `json:"gotify_priority"`                          // GotifyPriority Gotify消息优先级
 	AcceptUnsetRatioModel bool    `json:"accept_unset_model_ratio_model,omitempty"` // AcceptUnsetRatioModel 是否接受未设置价格的模型
 	RecordIpLog           bool    `json:"record_ip_log,omitempty"`                  // 是否记录请求和错误日志IP
 	SidebarModules        string  `json:"sidebar_modules,omitempty"`                // SidebarModules 左侧边栏模块配置
@@ -16,4 +19,5 @@ var (
 	NotifyTypeEmail   = "email"   // Email 邮件
 	NotifyTypeWebhook = "webhook" // Webhook
 	NotifyTypeBark    = "bark"    // Bark 推送
+	NotifyTypeGotify  = "gotify"  // Gotify 推送
 )

electron/README.md

@@ -0,0 +1,73 @@
+# New API Electron Desktop App
+
+This directory contains the Electron wrapper for New API, providing a native desktop application with system tray support for Windows, macOS, and Linux.
+
+## Prerequisites
+
+### 1. Go Binary (Required)
+The Electron app requires the compiled Go binary to function. You have two options:
+
+**Option A: Use existing binary (without Go installed)**
+```bash
+# If you have a pre-built binary (e.g., new-api-macos)
+cp ../new-api-macos ../new-api
+```
+
+**Option B: Build from source (requires Go)**
+TODO
+
+### 3. Electron Dependencies
+```bash
+cd electron
+npm install
+```
+
+## Development
+
+Run the app in development mode:
+```bash
+npm start
+```
+
+This will:
+- Start the Go backend on port 3000
+- Open an Electron window with DevTools enabled
+- Create a system tray icon (menu bar on macOS)
+- Store database in `../data/new-api.db`
+
+## Building for Production
+
+### Quick Build
+```bash
+# Ensure Go binary exists in parent directory
+ls ../new-api  # Should exist
+
+# Build for current platform
+npm run build
+
+# Platform-specific builds
+npm run build:mac    # Creates .dmg and .zip
+npm run build:win    # Creates .exe installer
+npm run build:linux  # Creates .AppImage and .deb
+```
+
+### Build Output
+- Built applications are in `electron/dist/`
+- macOS: `.dmg` (installer) and `.zip` (portable)
+- Windows: `.exe` (installer) and portable exe
+- Linux: `.AppImage` and `.deb`
+
+## Configuration
+
+### Port
+Default port is 3000. To change, edit `main.js`:
+```javascript
+const PORT = 3000; // Change to desired port
+```
+
+### Database Location
+- **Development**: `../data/new-api.db` (project directory)
+- **Production**:
+  - macOS: `~/Library/Application Support/New API/data/`
+  - Windows: `%APPDATA%/New API/data/`
+  - Linux: `~/.config/New API/data/`

electron/build.sh

@@ -0,0 +1,41 @@
+#!/bin/bash
+
+set -e
+
+echo "Building New API Electron App..."
+
+echo "Step 1: Building frontend..."
+cd ../web
+DISABLE_ESLINT_PLUGIN='true' bun run build
+cd ../electron
+
+echo "Step 2: Building Go backend..."
+cd ..
+
+if [[ "$OSTYPE" == "darwin"* ]]; then
+    echo "Building for macOS..."
+    CGO_ENABLED=1 go build -ldflags="-s -w" -o new-api
+    cd electron
+    npm install
+    npm run build:mac
+elif [[ "$OSTYPE" == "linux-gnu"* ]]; then
+    echo "Building for Linux..."
+    CGO_ENABLED=1 go build -ldflags="-s -w" -o new-api
+    cd electron
+    npm install
+    npm run build:linux
+elif [[ "$OSTYPE" == "msys" || "$OSTYPE" == "cygwin" || "$OSTYPE" == "win32" ]]; then
+    echo "Building for Windows..."
+    CGO_ENABLED=1 go build -ldflags="-s -w" -o new-api.exe
+    cd electron
+    npm install
+    npm run build:win
+else
+    echo "Unknown OS, building for current platform..."
+    CGO_ENABLED=1 go build -ldflags="-s -w" -o new-api
+    cd electron
+    npm install
+    npm run build
+fi
+
+echo "Build complete! Check electron/dist/ for output."

electron/create-tray-icon.js

@@ -0,0 +1,60 @@
+// Create a simple tray icon for macOS
+// Run: node create-tray-icon.js
+
+const fs = require('fs');
+const { createCanvas } = require('canvas');
+
+function createTrayIcon() {
+  // For macOS, we'll use a Template image (black and white)
+  // Size should be 22x22 for Retina displays (@2x would be 44x44)
+  const canvas = createCanvas(22, 22);
+  const ctx = canvas.getContext('2d');
+
+  // Clear canvas
+  ctx.clearRect(0, 0, 22, 22);
+
+  // Draw a simple "API" icon
+  ctx.fillStyle = '#000000';
+  ctx.font = 'bold 10px system-ui';
+  ctx.textAlign = 'center';
+  ctx.textBaseline = 'middle';
+  ctx.fillText('API', 11, 11);
+
+  // Save as PNG
+  const buffer = canvas.toBuffer('image/png');
+  fs.writeFileSync('tray-icon.png', buffer);
+
+  // For Template images on macOS (will adapt to menu bar theme)
+  fs.writeFileSync('tray-iconTemplate.png', buffer);
+  fs.writeFileSync('tray-iconTemplate@2x.png', buffer);
+
+  console.log('Tray icon created successfully!');
+}
+
+// Check if canvas is installed
+try {
+  createTrayIcon();
+} catch (err) {
+  console.log('Canvas module not installed.');
+  console.log('For now, creating a placeholder. Install canvas with: npm install canvas');
+
+  // Create a minimal 1x1 transparent PNG as placeholder
+  const minimalPNG = Buffer.from([
+    0x89, 0x50, 0x4E, 0x47, 0x0D, 0x0A, 0x1A, 0x0A,
+    0x00, 0x00, 0x00, 0x0D, 0x49, 0x48, 0x44, 0x52,
+    0x00, 0x00, 0x00, 0x01, 0x00, 0x00, 0x00, 0x01,
+    0x01, 0x03, 0x00, 0x00, 0x00, 0x25, 0xDB, 0x56,
+    0xCA, 0x00, 0x00, 0x00, 0x03, 0x50, 0x4C, 0x54,
+    0x45, 0x00, 0x00, 0x00, 0xA7, 0x7A, 0x3D, 0xDA,
+    0x00, 0x00, 0x00, 0x01, 0x74, 0x52, 0x4E, 0x53,
+    0x00, 0x40, 0xE6, 0xD8, 0x66, 0x00, 0x00, 0x00,
+    0x0A, 0x49, 0x44, 0x41, 0x54, 0x08, 0x1D, 0x62,
+    0x00, 0x00, 0x00, 0x00, 0x00, 0x01, 0x00, 0x00,
+    0x00, 0x01, 0x0A, 0x2D, 0xCB, 0x59, 0x00, 0x00,
+    0x00, 0x00, 0x49, 0x45, 0x4E, 0x44, 0xAE, 0x42,
+    0x60, 0x82
+  ]);
+
+  fs.writeFileSync('tray-icon.png', minimalPNG);
+  console.log('Created placeholder tray icon.');
+}

electron/entitlements.mac.plist

@@ -0,0 +1,18 @@
+<?xml version="1.0" encoding="UTF-8"?>
+<!DOCTYPE plist PUBLIC "-//Apple//DTD PLIST 1.0//EN" "http://www.apple.com/DTDs/PropertyList-1.0.dtd">
+<plist version="1.0">
+<dict>
+    <key>com.apple.security.cs.allow-unsigned-executable-memory</key>
+    <true/>
+    <key>com.apple.security.cs.allow-jit</key>
+    <true/>
+    <key>com.apple.security.cs.disable-library-validation</key>
+    <true/>
+    <key>com.apple.security.cs.allow-dyld-environment-variables</key>
+    <true/>
+    <key>com.apple.security.network.client</key>
+    <true/>
+    <key>com.apple.security.network.server</key>
+    <true/>
+</dict>
+</plist>

electron/main.js

@@ -0,0 +1,590 @@
+const { app, BrowserWindow, dialog, Tray, Menu, shell } = require('electron');
+const { spawn } = require('child_process');
+const path = require('path');
+const http = require('http');
+const fs = require('fs');
+
+let mainWindow;
+let serverProcess;
+let tray = null;
+let serverErrorLogs = [];
+const PORT = 3000;
+const DEV_FRONTEND_PORT = 5173; // Vite dev server port
+
+// 保存日志到文件并打开
+function saveAndOpenErrorLog() {
+  try {
+    const timestamp = new Date().toISOString().replace(/[:.]/g, '-');
+    const logFileName = `new-api-crash-${timestamp}.log`;
+    const logDir = app.getPath('logs');
+    const logFilePath = path.join(logDir, logFileName);
+    
+    // 确保日志目录存在
+    if (!fs.existsSync(logDir)) {
+      fs.mkdirSync(logDir, { recursive: true });
+    }
+    
+    // 写入日志
+    const logContent = `New API 崩溃日志
+生成时间: ${new Date().toLocaleString('zh-CN')}
+平台: ${process.platform}
+架构: ${process.arch}
+应用版本: ${app.getVersion()}
+
+━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━
+
+完整错误日志:
+
+${serverErrorLogs.join('\n')}
+
+━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━
+
+日志文件位置: ${logFilePath}
+`;
+    
+    fs.writeFileSync(logFilePath, logContent, 'utf8');
+    
+    // 打开日志文件
+    shell.openPath(logFilePath).then((error) => {
+      if (error) {
+        console.error('Failed to open log file:', error);
+        // 如果打开文件失败，至少显示文件位置
+        shell.showItemInFolder(logFilePath);
+      }
+    });
+    
+    return logFilePath;
+  } catch (err) {
+    console.error('Failed to save error log:', err);
+    return null;
+  }
+}
+
+// 分析错误日志，识别常见错误并提供解决方案
+function analyzeError(errorLogs) {
+  const allLogs = errorLogs.join('\n');
+  
+  // 检测端口占用错误
+  if (allLogs.includes('failed to start HTTP server') || 
+      allLogs.includes('bind: address already in use') ||
+      allLogs.includes('listen tcp') && allLogs.includes('bind: address already in use')) {
+    return {
+      type: '端口被占用',
+      title: '端口 ' + PORT + ' 被占用',
+      message: '无法启动服务器，端口已被其他程序占用',
+      solution: `可能的解决方案：\n\n1. 关闭占用端口 ${PORT} 的其他程序\n2. 检查是否已经运行了另一个 New API 实例\n3. 使用以下命令查找占用端口的进程：\n   Mac/Linux: lsof -i :${PORT}\n   Windows: netstat -ano | findstr :${PORT}\n4. 重启电脑以释放端口`
+    };
+  }
+  
+  // 检测数据库错误
+  if (allLogs.includes('database is locked') || 
+      allLogs.includes('unable to open database')) {
+    return {
+      type: '数据文件被占用',
+      title: '无法访问数据文件',
+      message: '应用的数据文件正被其他程序占用',
+      solution: '可能的解决方案：\n\n1. 检查是否已经打开了另一个 New API 窗口\n   - 查看任务栏/Dock 中是否有其他 New API 图标\n   - 查看系统托盘（Windows）或菜单栏（Mac）中是否有 New API 图标\n\n2. 如果刚刚关闭过应用，请等待 10 秒后再试\n\n3. 重启电脑以释放被占用的文件\n\n4. 如果问题持续，可以尝试：\n   - 退出所有 New API 实例\n   - 删除数据目录中的临时文件（.db-shm 和 .db-wal）\n   - 重新启动应用'
+    };
+  }
+  
+  // 检测权限错误
+  if (allLogs.includes('permission denied') || 
+      allLogs.includes('access denied')) {
+    return {
+      type: '权限错误',
+      title: '权限不足',
+      message: '程序没有足够的权限执行操作',
+      solution: '可能的解决方案：\n\n1. 以管理员/root权限运行程序\n2. 检查数据目录的读写权限\n3. 检查可执行文件的权限\n4. 在 Mac 上，检查安全性与隐私设置'
+    };
+  }
+  
+  // 检测网络错误
+  if (allLogs.includes('network is unreachable') || 
+      allLogs.includes('no such host') ||
+      allLogs.includes('connection refused')) {
+    return {
+      type: '网络错误',
+      title: '网络连接失败',
+      message: '无法建立网络连接',
+      solution: '可能的解决方案：\n\n1. 检查网络连接是否正常\n2. 检查防火墙设置\n3. 检查代理配置\n4. 确认目标服务器地址正确'
+    };
+  }
+  
+  // 检测配置文件错误
+  if (allLogs.includes('invalid configuration') || 
+      allLogs.includes('failed to parse config') ||
+      allLogs.includes('yaml') || allLogs.includes('json') && allLogs.includes('parse')) {
+    return {
+      type: '配置错误',
+      title: '配置文件错误',
+      message: '配置文件格式不正确或包含无效配置',
+      solution: '可能的解决方案：\n\n1. 检查配置文件格式是否正确\n2. 恢复默认配置\n3. 删除配置文件让程序重新生成\n4. 查看文档了解正确的配置格式'
+    };
+  }
+  
+  // 检测内存不足
+  if (allLogs.includes('out of memory') || 
+      allLogs.includes('cannot allocate memory')) {
+    return {
+      type: '内存不足',
+      title: '系统内存不足',
+      message: '程序运行时内存不足',
+      solution: '可能的解决方案：\n\n1. 关闭其他占用内存的程序\n2. 增加系统可用内存\n3. 重启电脑释放内存\n4. 检查是否存在内存泄漏'
+    };
+  }
+  
+  // 检测文件不存在错误
+  if (allLogs.includes('no such file or directory') || 
+      allLogs.includes('cannot find the file')) {
+    return {
+      type: '文件缺失',
+      title: '找不到必需的文件',
+      message: '缺少程序运行所需的文件',
+      solution: '可能的解决方案：\n\n1. 重新安装应用程序\n2. 检查安装目录是否完整\n3. 确保所有依赖文件都存在\n4. 检查文件路径是否正确'
+    };
+  }
+  
+  return null;
+}
+
+function getBinaryPath() {
+  const isDev = process.env.NODE_ENV === 'development';
+  const platform = process.platform;
+
+  if (isDev) {
+    const binaryName = platform === 'win32' ? 'new-api.exe' : 'new-api';
+    return path.join(__dirname, '..', binaryName);
+  }
+
+  let binaryName;
+  switch (platform) {
+    case 'win32':
+      binaryName = 'new-api.exe';
+      break;
+    case 'darwin':
+      binaryName = 'new-api';
+      break;
+    case 'linux':
+      binaryName = 'new-api';
+      break;
+    default:
+      binaryName = 'new-api';
+  }
+
+  return path.join(process.resourcesPath, 'bin', binaryName);
+}
+
+// Check if a server is available with retry logic
+function checkServerAvailability(port, maxRetries = 30, retryDelay = 1000) {
+  return new Promise((resolve, reject) => {
+    let currentAttempt = 0;
+    
+    const tryConnect = () => {
+      currentAttempt++;
+      
+      if (currentAttempt % 5 === 1 && currentAttempt > 1) {
+        console.log(`Attempting to connect to port ${port}... (attempt ${currentAttempt}/${maxRetries})`);
+      }
+      
+      const req = http.get({
+        hostname: '127.0.0.1', // Use IPv4 explicitly instead of 'localhost' to avoid IPv6 issues
+        port: port,
+        timeout: 10000
+      }, (res) => {
+        // Server responded, connection successful
+        req.destroy();
+        console.log(`✓ Successfully connected to port ${port} (status: ${res.statusCode})`);
+        resolve();
+      });
+
+      req.on('error', (err) => {
+        if (currentAttempt >= maxRetries) {
+          reject(new Error(`Failed to connect to port ${port} after ${maxRetries} attempts: ${err.message}`));
+        } else {
+          setTimeout(tryConnect, retryDelay);
+        }
+      });
+
+      req.on('timeout', () => {
+        req.destroy();
+        if (currentAttempt >= maxRetries) {
+          reject(new Error(`Connection timeout on port ${port} after ${maxRetries} attempts`));
+        } else {
+          setTimeout(tryConnect, retryDelay);
+        }
+      });
+    };
+    
+    tryConnect();
+  });
+}
+
+function startServer() {
+  return new Promise((resolve, reject) => {
+    const isDev = process.env.NODE_ENV === 'development';
+
+    const userDataPath = app.getPath('userData');
+    const dataDir = path.join(userDataPath, 'data');
+    
+    // 设置环境变量供 preload.js 使用
+    process.env.ELECTRON_DATA_DIR = dataDir;
+    
+    if (isDev) {
+      // 开发模式：假设开发者手动启动了 Go 后端和前端开发服务器
+      // 只需要等待前端开发服务器就绪
+      console.log('Development mode: skipping server startup');
+      console.log('Please make sure you have started:');
+      console.log('  1. Go backend: go run main.go (port 3000)');
+      console.log('  2. Frontend dev server: cd web && bun dev (port 5173)');
+      console.log('');
+      console.log('Checking if servers are running...');
+      
+      // First check if both servers are accessible
+      checkServerAvailability(DEV_FRONTEND_PORT)
+        .then(() => {
+          console.log('✓ Frontend dev server is accessible on port 5173');
+          resolve();
+        })
+        .catch((err) => {
+          console.error(`✗ Cannot connect to frontend dev server on port ${DEV_FRONTEND_PORT}`);
+          console.error('Please make sure the frontend dev server is running:');
+          console.error('  cd web && bun dev');
+          reject(err);
+        });
+      return;
+    }
+
+    // 生产模式：启动二进制服务器
+    const env = { ...process.env, PORT: PORT.toString() };
+
+    if (!fs.existsSync(dataDir)) {
+      fs.mkdirSync(dataDir, { recursive: true });
+    }
+
+    env.SQLITE_PATH = path.join(dataDir, 'new-api.db');
+    
+    console.log('━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━');
+    console.log('📁 您的数据存储位置：');
+    console.log('   ' + dataDir);
+    console.log('   💡 备份提示：复制此目录即可备份所有数据');
+    console.log('━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━');
+
+    const binaryPath = getBinaryPath();
+    const workingDir = process.resourcesPath;
+    
+    console.log('Starting server from:', binaryPath);
+
+    serverProcess = spawn(binaryPath, [], {
+      env,
+      cwd: workingDir
+    });
+
+    serverProcess.stdout.on('data', (data) => {
+      console.log(`Server: ${data}`);
+    });
+
+    serverProcess.stderr.on('data', (data) => {
+      const errorMsg = data.toString();
+      console.error(`Server Error: ${errorMsg}`);
+      serverErrorLogs.push(errorMsg);
+      // 只保留最近的100条错误日志
+      if (serverErrorLogs.length > 100) {
+        serverErrorLogs.shift();
+      }
+    });
+
+    serverProcess.on('error', (err) => {
+      console.error('Failed to start server:', err);
+      reject(err);
+    });
+
+    serverProcess.on('close', (code) => {
+      console.log(`Server process exited with code ${code}`);
+      
+      // 如果退出代码不是0，说明服务器异常退出
+      if (code !== 0 && code !== null) {
+        const errorDetails = serverErrorLogs.length > 0 
+          ? serverErrorLogs.slice(-20).join('\n') 
+          : '没有捕获到错误日志';
+        
+        // 分析错误类型
+        const knownError = analyzeError(serverErrorLogs);
+        
+        let dialogOptions;
+        if (knownError) {
+          // 识别到已知错误，显示友好的错误信息和解决方案
+          dialogOptions = {
+            type: 'error',
+            title: knownError.title,
+            message: knownError.message,
+            detail: `${knownError.solution}\n\n━━━━━━━━━━━━━━━━━━━━━━\n\n退出代码: ${code}\n\n错误类型: ${knownError.type}\n\n最近的错误日志:\n${errorDetails}`,
+            buttons: ['退出应用', '查看完整日志'],
+            defaultId: 0,
+            cancelId: 0
+          };
+        } else {
+          // 未识别的错误，显示通用错误信息
+          dialogOptions = {
+            type: 'error',
+            title: '服务器崩溃',
+            message: '服务器进程异常退出',
+            detail: `退出代码: ${code}\n\n最近的错误信息:\n${errorDetails}`,
+            buttons: ['退出应用', '查看完整日志'],
+            defaultId: 0,
+            cancelId: 0
+          };
+        }
+        
+        dialog.showMessageBox(dialogOptions).then((result) => {
+          if (result.response === 1) {
+            // 用户选择查看详情，保存并打开日志文件
+            const logPath = saveAndOpenErrorLog();
+            
+            // 显示确认对话框
+            const confirmMessage = logPath 
+              ? `日志已保存到:\n${logPath}\n\n日志文件已在默认文本编辑器中打开。\n\n点击"退出"关闭应用程序。`
+              : '日志保存失败，但已在控制台输出。\n\n点击"退出"关闭应用程序。';
+            
+            dialog.showMessageBox({
+              type: 'info',
+              title: '日志已保存',
+              message: confirmMessage,
+              buttons: ['退出'],
+              defaultId: 0
+            }).then(() => {
+              app.isQuitting = true;
+              app.quit();
+            });
+            
+            // 同时在控制台输出
+            console.log('=== 完整错误日志 ===');
+            console.log(serverErrorLogs.join('\n'));
+          } else {
+            // 用户选择直接退出
+            app.isQuitting = true;
+            app.quit();
+          }
+        });
+      } else {
+        // 正常退出（code为0或null），直接关闭窗口
+        if (mainWindow && !mainWindow.isDestroyed()) {
+          mainWindow.close();
+        }
+      }
+    });
+
+    checkServerAvailability(PORT)
+      .then(() => {
+        console.log('✓ Backend server is accessible on port 3000');
+        resolve();
+      })
+      .catch((err) => {
+        console.error('✗ Failed to connect to backend server');
+        reject(err);
+      });
+  });
+}
+
+function createWindow() {
+  const isDev = process.env.NODE_ENV === 'development';
+  const loadPort = isDev ? DEV_FRONTEND_PORT : PORT;
+  
+  mainWindow = new BrowserWindow({
+    width: 1080,
+    height: 720,
+    webPreferences: {
+      preload: path.join(__dirname, 'preload.js'),
+      nodeIntegration: false,
+      contextIsolation: true
+    },
+    title: 'New API',
+    icon: path.join(__dirname, 'icon.png')
+  });
+
+  mainWindow.loadURL(`http://127.0.0.1:${loadPort}`);
+  
+  console.log(`Loading from: http://127.0.0.1:${loadPort}`);
+
+  if (isDev) {
+    mainWindow.webContents.openDevTools();
+  }
+
+  // Close to tray instead of quitting
+  mainWindow.on('close', (event) => {
+    if (!app.isQuitting) {
+      event.preventDefault();
+      mainWindow.hide();
+      if (process.platform === 'darwin') {
+        app.dock.hide();
+      }
+    }
+  });
+
+  mainWindow.on('closed', () => {
+    mainWindow = null;
+  });
+}
+
+function createTray() {
+  // Use template icon for macOS (black with transparency, auto-adapts to theme)
+  // Use colored icon for Windows
+  const trayIconPath = process.platform === 'darwin'
+    ? path.join(__dirname, 'tray-iconTemplate.png')
+    : path.join(__dirname, 'tray-icon-windows.png');
+
+  tray = new Tray(trayIconPath);
+
+  const contextMenu = Menu.buildFromTemplate([
+    {
+      label: 'Show New API',
+      click: () => {
+        if (mainWindow === null) {
+          createWindow();
+        } else {
+          mainWindow.show();
+          if (process.platform === 'darwin') {
+            app.dock.show();
+          }
+        }
+      }
+    },
+    { type: 'separator' },
+    {
+      label: 'Quit',
+      click: () => {
+        app.isQuitting = true;
+        app.quit();
+      }
+    }
+  ]);
+
+  tray.setToolTip('New API');
+  tray.setContextMenu(contextMenu);
+
+  // On macOS, clicking the tray icon shows the window
+  tray.on('click', () => {
+    if (mainWindow === null) {
+      createWindow();
+    } else {
+      mainWindow.isVisible() ? mainWindow.hide() : mainWindow.show();
+      if (mainWindow.isVisible() && process.platform === 'darwin') {
+        app.dock.show();
+      }
+    }
+  });
+}
+
+app.whenReady().then(async () => {
+  try {
+    await startServer();
+    createTray();
+    createWindow();
+  } catch (err) {
+    console.error('Failed to start application:', err);
+    
+    // 分析启动失败的错误
+    const knownError = analyzeError(serverErrorLogs);
+    
+    if (knownError) {
+      dialog.showMessageBox({
+        type: 'error',
+        title: knownError.title,
+        message: `启动失败: ${knownError.message}`,
+        detail: `${knownError.solution}\n\n━━━━━━━━━━━━━━━━━━━━━━\n\n错误信息: ${err.message}\n\n错误类型: ${knownError.type}`,
+        buttons: ['退出', '查看完整日志'],
+        defaultId: 0,
+        cancelId: 0
+      }).then((result) => {
+        if (result.response === 1) {
+          // 用户选择查看日志
+          const logPath = saveAndOpenErrorLog();
+          
+          const confirmMessage = logPath 
+            ? `日志已保存到:\n${logPath}\n\n日志文件已在默认文本编辑器中打开。\n\n点击"退出"关闭应用程序。`
+            : '日志保存失败，但已在控制台输出。\n\n点击"退出"关闭应用程序。';
+          
+          dialog.showMessageBox({
+            type: 'info',
+            title: '日志已保存',
+            message: confirmMessage,
+            buttons: ['退出'],
+            defaultId: 0
+          }).then(() => {
+            app.quit();
+          });
+          
+          console.log('=== 完整错误日志 ===');
+          console.log(serverErrorLogs.join('\n'));
+        } else {
+          app.quit();
+        }
+      });
+    } else {
+      dialog.showMessageBox({
+        type: 'error',
+        title: '启动失败',
+        message: '无法启动服务器',
+        detail: `错误信息: ${err.message}\n\n请检查日志获取更多信息。`,
+        buttons: ['退出', '查看完整日志'],
+        defaultId: 0,
+        cancelId: 0
+      }).then((result) => {
+        if (result.response === 1) {
+          // 用户选择查看日志
+          const logPath = saveAndOpenErrorLog();
+          
+          const confirmMessage = logPath 
+            ? `日志已保存到:\n${logPath}\n\n日志文件已在默认文本编辑器中打开。\n\n点击"退出"关闭应用程序。`
+            : '日志保存失败，但已在控制台输出。\n\n点击"退出"关闭应用程序。';
+          
+          dialog.showMessageBox({
+            type: 'info',
+            title: '日志已保存',
+            message: confirmMessage,
+            buttons: ['退出'],
+            defaultId: 0
+          }).then(() => {
+            app.quit();
+          });
+          
+          console.log('=== 完整错误日志 ===');
+          console.log(serverErrorLogs.join('\n'));
+        } else {
+          app.quit();
+        }
+      });
+    }
+  }
+});
+
+app.on('window-all-closed', () => {
+  // Don't quit when window is closed, keep running in tray
+  // Only quit when explicitly choosing Quit from tray menu
+});
+
+app.on('activate', () => {
+  if (BrowserWindow.getAllWindows().length === 0) {
+    createWindow();
+  }
+});
+
+app.on('before-quit', (event) => {
+  if (serverProcess) {
+    event.preventDefault();
+
+    console.log('Shutting down server...');
+    serverProcess.kill('SIGTERM');
+
+    setTimeout(() => {
+      if (serverProcess) {
+        serverProcess.kill('SIGKILL');
+      }
+      app.exit();
+    }, 5000);
+
+    serverProcess.on('close', () => {
+      serverProcess = null;
+      app.exit();
+    });
+  }
+});

electron/package.json

@@ -0,0 +1,101 @@
+{
+  "name": "new-api-electron",
+  "version": "1.0.0",
+  "description": "New API - AI Model Gateway Desktop Application",
+  "main": "main.js",
+  "scripts": {
+    "start-app": "electron .",
+    "dev-app": "cross-env NODE_ENV=development electron .",
+    "build": "electron-builder",
+    "build:mac": "electron-builder --mac",
+    "build:win": "electron-builder --win",
+    "build:linux": "electron-builder --linux"
+  },
+  "keywords": [
+    "ai",
+    "api",
+    "gateway",
+    "openai",
+    "claude"
+  ],
+  "author": "QuantumNous",
+  "repository": {
+    "type": "git",
+    "url": "https://github.com/QuantumNous/new-api"
+  },
+  "devDependencies": {
+    "cross-env": "^7.0.3",
+    "electron": "35.7.5",
+    "electron-builder": "^24.9.1"
+  },
+  "build": {
+    "appId": "com.newapi.desktop",
+    "productName": "New-API-App",
+    "publish": null,
+    "directories": {
+      "output": "dist"
+    },
+    "files": [
+      "main.js",
+      "preload.js",
+      "icon.png",
+      "tray-iconTemplate.png",
+      "tray-iconTemplate@2x.png",
+      "tray-icon-windows.png"
+    ],
+    "mac": {
+      "category": "public.app-category.developer-tools",
+      "icon": "icon.png",
+      "identity": null,
+      "hardenedRuntime": false,
+      "gatekeeperAssess": false,
+      "entitlements": "entitlements.mac.plist",
+      "entitlementsInherit": "entitlements.mac.plist",
+      "target": [
+        "dmg",
+        "zip"
+      ],
+      "extraResources": [
+        {
+          "from": "../new-api",
+          "to": "bin/new-api"
+        },
+        {
+          "from": "../web/dist",
+          "to": "web/dist"
+        }
+      ]
+    },
+    "win": {
+      "icon": "icon.png",
+      "target": [
+        "nsis",
+        "portable"
+      ],
+      "extraResources": [
+        {
+          "from": "../new-api.exe",
+          "to": "bin/new-api.exe"
+        }
+      ]
+    },
+    "linux": {
+      "icon": "icon.png",
+      "target": [
+        "AppImage",
+        "deb"
+      ],
+      "category": "Development",
+      "extraResources": [
+        {
+          "from": "../new-api",
+          "to": "bin/new-api"
+        }
+      ]
+    },
+    "nsis": {
+      "oneClick": false,
+      "allowToChangeInstallationDirectory": true
+    }
+  }
+}

electron/preload.js

@@ -0,0 +1,18 @@
+const { contextBridge } = require('electron');
+
+// 获取数据目录路径（用于显示给用户）
+// 优先使用主进程设置的真实路径，如果没有则回退到手动拼接
+function getDataDirPath() {
+  // 如果主进程已设置真实路径，直接使用
+  if (process.env.ELECTRON_DATA_DIR) {
+    return process.env.ELECTRON_DATA_DIR;
+  }
+}
+
+contextBridge.exposeInMainWorld('electron', {
+  isElectron: true,
+  version: process.versions.electron,
+  platform: process.platform,
+  versions: process.versions,
+  dataDir: getDataDirPath()
+});

go.mod

@@ -1,9 +1,7 @@
 module one-api
 
 // +heroku goVersion go1.18
-go 1.24.0
-
-toolchain go1.24.6
+go 1.25.1
 
 require (
 	github.com/Calcium-Ion/go-epay v0.0.4
@@ -13,7 +11,7 @@ require (
 	github.com/aws/aws-sdk-go-v2/credentials v1.17.11
 	github.com/aws/aws-sdk-go-v2/service/bedrockruntime v1.33.0
 	github.com/aws/smithy-go v1.22.5
-	github.com/bytedance/gopkg v0.0.0-20220118071334-3db87571198b
+	github.com/bytedance/gopkg v0.1.3
 	github.com/gin-contrib/cors v1.7.2
 	github.com/gin-contrib/gzip v0.0.6
 	github.com/gin-contrib/sessions v0.0.5
@@ -23,7 +21,7 @@ require (
 	github.com/go-playground/validator/v10 v10.20.0
 	github.com/go-redis/redis/v8 v8.11.5
 	github.com/go-webauthn/webauthn v0.14.0
-	github.com/golang-jwt/jwt v3.2.2+incompatible
+	github.com/golang-jwt/jwt/v5 v5.3.0
 	github.com/google/uuid v1.6.0
 	github.com/gorilla/websocket v1.5.0
 	github.com/jinzhu/copier v0.4.0
@@ -53,11 +51,10 @@ require (
 	github.com/aws/aws-sdk-go-v2/internal/configsources v1.4.2 // indirect
 	github.com/aws/aws-sdk-go-v2/internal/endpoints/v2 v2.7.2 // indirect
 	github.com/boombuler/barcode v1.1.0 // indirect
-	github.com/bytedance/sonic v1.11.6 // indirect
-	github.com/bytedance/sonic/loader v0.1.1 // indirect
+	github.com/bytedance/sonic v1.14.1 // indirect
+	github.com/bytedance/sonic/loader v0.3.0 // indirect
 	github.com/cespare/xxhash/v2 v2.3.0 // indirect
-	github.com/cloudwego/base64x v0.1.4 // indirect
-	github.com/cloudwego/iasm v0.2.0 // indirect
+	github.com/cloudwego/base64x v0.1.6 // indirect
 	github.com/dgryski/go-rendezvous v0.0.0-20200823014737-9f7001d12a5f // indirect
 	github.com/dlclark/regexp2 v1.11.5 // indirect
 	github.com/dustin/go-humanize v1.0.1 // indirect
@@ -71,7 +68,6 @@ require (
 	github.com/go-sql-driver/mysql v1.7.0 // indirect
 	github.com/go-webauthn/x v0.1.25 // indirect
 	github.com/goccy/go-json v0.10.2 // indirect
-	github.com/golang-jwt/jwt/v5 v5.3.0 // indirect
 	github.com/google/go-cmp v0.6.0 // indirect
 	github.com/google/go-tpm v0.9.5 // indirect
 	github.com/gorilla/context v1.1.1 // indirect
@@ -84,7 +80,7 @@ require (
 	github.com/jinzhu/inflection v1.0.0 // indirect
 	github.com/jinzhu/now v1.1.5 // indirect
 	github.com/json-iterator/go v1.1.12 // indirect
-	github.com/klauspost/cpuid/v2 v2.2.9 // indirect
+	github.com/klauspost/cpuid/v2 v2.3.0 // indirect
 	github.com/leodido/go-urn v1.4.0 // indirect
 	github.com/mattn/go-isatty v0.0.20 // indirect
 	github.com/mitchellh/mapstructure v1.5.0 // indirect
@@ -100,7 +96,7 @@ require (
 	github.com/ugorji/go/codec v1.2.12 // indirect
 	github.com/x448/float16 v0.8.4 // indirect
 	github.com/yusufpapurcu/wmi v1.2.3 // indirect
-	golang.org/x/arch v0.12.0 // indirect
+	golang.org/x/arch v0.21.0 // indirect
 	golang.org/x/exp v0.0.0-20240404231335-c0f41cb1a7a0 // indirect
 	golang.org/x/sys v0.36.0 // indirect
 	golang.org/x/text v0.29.0 // indirect

go.sum

@@ -23,18 +23,16 @@ github.com/aws/smithy-go v1.22.5/go.mod h1:t1ufH5HMublsJYulve2RKmHDC15xu1f26kHCp
 github.com/boombuler/barcode v1.0.1-0.20190219062509-6c824513bacc/go.mod h1:paBWMcWSl3LHKBqUq+rly7CNSldXjb2rDl3JlRe0mD8=
 github.com/boombuler/barcode v1.1.0 h1:ChaYjBR63fr4LFyGn8E8nt7dBSt3MiU3zMOZqFvVkHo=
 github.com/boombuler/barcode v1.1.0/go.mod h1:paBWMcWSl3LHKBqUq+rly7CNSldXjb2rDl3JlRe0mD8=
-github.com/bytedance/gopkg v0.0.0-20220118071334-3db87571198b h1:LTGVFpNmNHhj0vhOlfgWueFJ32eK9blaIlHR2ciXOT0=
-github.com/bytedance/gopkg v0.0.0-20220118071334-3db87571198b/go.mod h1:2ZlV9BaUH4+NXIBF0aMdKKAnHTzqH+iMU4KUjAbL23Q=
-github.com/bytedance/sonic v1.11.6 h1:oUp34TzMlL+OY1OUWxHqsdkgC/Zfc85zGqw9siXjrc0=
-github.com/bytedance/sonic v1.11.6/go.mod h1:LysEHSvpvDySVdC2f87zGWf6CIKJcAvqab1ZaiQtds4=
-github.com/bytedance/sonic/loader v0.1.1 h1:c+e5Pt1k/cy5wMveRDyk2X4B9hF4g7an8N3zCYjJFNM=
-github.com/bytedance/sonic/loader v0.1.1/go.mod h1:ncP89zfokxS5LZrJxl5z0UJcsk4M4yY2JpfqGeCtNLU=
+github.com/bytedance/gopkg v0.1.3 h1:TPBSwH8RsouGCBcMBktLt1AymVo2TVsBVCY4b6TnZ/M=
+github.com/bytedance/gopkg v0.1.3/go.mod h1:576VvJ+eJgyCzdjS+c4+77QF3p7ubbtiKARP3TxducM=
+github.com/bytedance/sonic v1.14.1 h1:FBMC0zVz5XUmE4z9wF4Jey0An5FueFvOsTKKKtwIl7w=
+github.com/bytedance/sonic v1.14.1/go.mod h1:gi6uhQLMbTdeP0muCnrjHLeCUPyb70ujhnNlhOylAFc=
+github.com/bytedance/sonic/loader v0.3.0 h1:dskwH8edlzNMctoruo8FPTJDF3vLtDT0sXZwvZJyqeA=
+github.com/bytedance/sonic/loader v0.3.0/go.mod h1:N8A3vUdtUebEY2/VQC0MyhYeKUFosQU6FxH2JmUe6VI=
 github.com/cespare/xxhash/v2 v2.3.0 h1:UL815xU9SqsFlibzuggzjXhog7bL6oX9BbNZnL2UFvs=
 github.com/cespare/xxhash/v2 v2.3.0/go.mod h1:VGX0DQ3Q6kWi7AoAeZDth3/j3BFtOZR5XLFGgcrjCOs=
-github.com/cloudwego/base64x v0.1.4 h1:jwCgWpFanWmN8xoIUHa2rtzmkd5J2plF/dnLS6Xd/0Y=
-github.com/cloudwego/base64x v0.1.4/go.mod h1:0zlkT4Wn5C6NdauXdJRhSKRlJvmclQ1hhJgA0rcu/8w=
-github.com/cloudwego/iasm v0.2.0 h1:1KNIy1I1H9hNNFEEH3DVnI4UujN+1zjpuk6gwHLTssg=
-github.com/cloudwego/iasm v0.2.0/go.mod h1:8rXZaNYT2n95jn+zTI1sDr+IgcD2GVs0nlbbQPiEFhY=
+github.com/cloudwego/base64x v0.1.6 h1:t11wG9AECkCDk5fMSoxmufanudBtJ+/HemLstXDLI2M=
+github.com/cloudwego/base64x v0.1.6/go.mod h1:OFcloc187FXDaYHvrNIjxSe8ncn0OOM8gEHfghB2IPU=
 github.com/creack/pty v1.1.9/go.mod h1:oKZEueFk5CKHvIhNR5MUki03XCEU+Q6VDXinZuGJ33E=
 github.com/davecgh/go-spew v1.1.0/go.mod h1:J7Y8YcW2NihsgmVo/mv3lAwl/skON4iLHjSsI+c5H38=
 github.com/davecgh/go-spew v1.1.1 h1:vj9j/u1bqnvCEfJOwUhtlOARqs3+rkHYY13jYWTU97c=
@@ -142,10 +140,8 @@ github.com/joho/godotenv v1.5.1/go.mod h1:f4LDr5Voq0i2e/R5DDNOoa2zzDfwtkZa6DnEwA
 github.com/json-iterator/go v1.1.9/go.mod h1:KdQUCv79m/52Kvf8AW2vK1V8akMuk1QjK/uOdHXbAo4=
 github.com/json-iterator/go v1.1.12 h1:PV8peI4a0ysnczrg+LtxykD8LfKY9ML6u2jnxaEnrnM=
 github.com/json-iterator/go v1.1.12/go.mod h1:e30LSqwooZae/UwlEbR2852Gd8hjQvJoHmT4TnhNGBo=
-github.com/klauspost/cpuid/v2 v2.0.9/go.mod h1:FInQzS24/EEf25PyTYn52gqo7WaD8xa0213Md/qVLRg=
-github.com/klauspost/cpuid/v2 v2.2.9 h1:66ze0taIn2H33fBvCkXuv9BmCwDfafmiIVpKV9kKGuY=
-github.com/klauspost/cpuid/v2 v2.2.9/go.mod h1:rqkxqrZ1EhYM9G+hXH7YdowN5R5RGN6NK4QwQ3WMXF8=
-github.com/knz/go-libedit v1.10.1/go.mod h1:MZTVkCWyz0oBc7JOWP3wNAzd002ZbM/5hgShxwh4x8M=
+github.com/klauspost/cpuid/v2 v2.3.0 h1:S4CRMLnYUhGeDFDqkGriYKdfoFlDnMtqTiI/sFzhA9Y=
+github.com/klauspost/cpuid/v2 v2.3.0/go.mod h1:hqwkgyIinND0mEev00jJYCxPNVRVXFQeu1XKlok6oO0=
 github.com/kr/pretty v0.1.0/go.mod h1:dAy3ld7l9f0ibDNOQOHHMYYIIbhfbHSm3C4ZsoJORNo=
 github.com/kr/pretty v0.2.1/go.mod h1:ipq/a2n7PKx3OHsz4KJII5eveXtPO4qwEXGdVfWzfnI=
 github.com/kr/pretty v0.3.0 h1:WgNl7dwNpEZ6jJ9k1snq4pZsg7DOEN8hP9Xw0Tsjwk0=
@@ -248,9 +244,8 @@ github.com/yusufpapurcu/wmi v1.2.3 h1:E1ctvB7uKFMOJw3fdOW32DwGE9I7t++CRUEMKvFoFi
 github.com/yusufpapurcu/wmi v1.2.3/go.mod h1:SBZ9tNy3G9/m5Oi98Zks0QjeHVDvuK0qfxQmPyzfmi0=
 go.uber.org/mock v0.6.0 h1:hyF9dfmbgIX5EfOdasqLsWD6xqpNZlXblLB/Dbnwv3Y=
 go.uber.org/mock v0.6.0/go.mod h1:KiVJ4BqZJaMj4svdfmHM0AUx4NJYO8ZNpPnZn1Z+BBU=
-golang.org/x/arch v0.0.0-20210923205945-b76863e36670/go.mod h1:5om86z9Hs0C8fWVUuoMHwpExlXzs5Tkyp9hOrfG7pp8=
-golang.org/x/arch v0.12.0 h1:UsYJhbzPYGsT0HbEdmYcqtCv8UNGvnaL561NnIUvaKg=
-golang.org/x/arch v0.12.0/go.mod h1:FEVrYAQjsQXMVJ1nsMoVVXPZg6p2JE2mx8psSWTDQys=
+golang.org/x/arch v0.21.0 h1:iTC9o7+wP6cPWpDWkivCvQFGAHDQ59SrSxsLPcnkArw=
+golang.org/x/arch v0.21.0/go.mod h1:dNHoOeKiyja7GTvF9NJS1l3Z2yntpQNzgrjh1cU103A=
 golang.org/x/crypto v0.0.0-20210711020723-a769d52b0f97/go.mod h1:GvvjBRRGRdwPK5ydBHafDWAxML/pGHZbMvKqRZ5+Abc=
 golang.org/x/crypto v0.42.0 h1:chiH31gIWm57EkTXpwnqf8qeuMUi0yekh6mT2AvFlqI=
 golang.org/x/crypto v0.42.0/go.mod h1:4+rDnOTJhQCx2q7/j6rAN5XDw8kPjeaXEUR2eL94ix8=
@@ -262,7 +257,6 @@ golang.org/x/net v0.0.0-20210226172049-e18ecbb05110/go.mod h1:m0MpNAwzfU5UDzcl9v
 golang.org/x/net v0.0.0-20210520170846-37e1c6afe023/go.mod h1:9nx3DQGgdP8bBQD5qxJ1jj9UTztislL4KSBs9R2vV5Y=
 golang.org/x/net v0.43.0 h1:lat02VYK2j4aLzMzecihNvTlJNQUq316m2Mr9rnM6YE=
 golang.org/x/net v0.43.0/go.mod h1:vhO1fvI4dGsIjh73sWfUVjj3N7CA9WkKJNQm2svM6Jg=
-golang.org/x/sync v0.0.0-20210220032951-036812b2e83c/go.mod h1:RxMgew5VJxzue5/jJTE5uejpjVlOe/izrB70Jof72aM=
 golang.org/x/sync v0.17.0 h1:l60nONMj9l5drqw6jlhIELNv9I0A4OFgRsG9k2oT9Ug=
 golang.org/x/sync v0.17.0/go.mod h1:9KTHXmSnoGruLpwFjVSX0lNNA75CykiMECbovNTZqGI=
 golang.org/x/sys v0.0.0-20190916202348-b4ddaad3f8a3/go.mod h1:h1NjWce9XRLGQEsW7wpKNCjG9DtNlClVuFLEZdDNbEs=
@@ -272,7 +266,6 @@ golang.org/x/sys v0.0.0-20210423082822-04245dca01da/go.mod h1:h1NjWce9XRLGQEsW7w
 golang.org/x/sys v0.0.0-20210615035016-665e8c7367d1/go.mod h1:oPkhp1MJrh7nUepCBck5+mAzfO9JrbApNNgaTdGDITg=
 golang.org/x/sys v0.0.0-20210630005230-0f9fa26af87c/go.mod h1:oPkhp1MJrh7nUepCBck5+mAzfO9JrbApNNgaTdGDITg=
 golang.org/x/sys v0.0.0-20210806184541-e5e7981a1069/go.mod h1:oPkhp1MJrh7nUepCBck5+mAzfO9JrbApNNgaTdGDITg=
-golang.org/x/sys v0.0.0-20220110181412-a018aaa089fe/go.mod h1:oPkhp1MJrh7nUepCBck5+mAzfO9JrbApNNgaTdGDITg=
 golang.org/x/sys v0.6.0/go.mod h1:oPkhp1MJrh7nUepCBck5+mAzfO9JrbApNNgaTdGDITg=
 golang.org/x/sys v0.8.0/go.mod h1:oPkhp1MJrh7nUepCBck5+mAzfO9JrbApNNgaTdGDITg=
 golang.org/x/sys v0.11.0/go.mod h1:oPkhp1MJrh7nUepCBck5+mAzfO9JrbApNNgaTdGDITg=
@@ -320,5 +313,3 @@ modernc.org/memory v1.5.0 h1:N+/8c5rE6EqugZwHii4IFsaJ7MUhoWX07J5tC/iI5Ds=
 modernc.org/memory v1.5.0/go.mod h1:PkUhL0Mugw21sHPeskwZW4D6VscE/GQJOnIpCnW6pSU=
 modernc.org/sqlite v1.23.1 h1:nrSBg4aRQQwq59JpvGEQ15tNxoO5pX/kUjcRNwSAGQM=
 modernc.org/sqlite v1.23.1/go.mod h1:OrDj17Mggn6MhE+iPbBNf7RGKODDE9NFT0f3EwDzJqk=
-nullprogram.com/x/optparse v1.0.0/go.mod h1:KdyPE+Igbe0jQUrVfMqDMeJQIJZEuyV7pjYmp6pbG50=
-rsc.io/pdf v0.1.1/go.mod h1:n8OzWcQ6Sp37PL01nO98y4iUCRdTGarVfzxY20ICaU4=

logger/logger.go

@@ -7,6 +7,7 @@ import (
 	"io"
 	"log"
 	"one-api/common"
+	"one-api/setting/operation_setting"
 	"os"
 	"path/filepath"
 	"sync"
@@ -92,18 +93,55 @@ func logHelper(ctx context.Context, level string, msg string) {
 }
 
 func LogQuota(quota int) string {
-	if common.DisplayInCurrencyEnabled {
-		return fmt.Sprintf("＄%.6f 额度", float64(quota)/common.QuotaPerUnit)
-	} else {
+	// 新逻辑：根据额度展示类型输出
+	q := float64(quota)
+	switch operation_setting.GetQuotaDisplayType() {
+	case operation_setting.QuotaDisplayTypeCNY:
+		usd := q / common.QuotaPerUnit
+		cny := usd * operation_setting.USDExchangeRate
+		return fmt.Sprintf("¥%.6f 额度", cny)
+	case operation_setting.QuotaDisplayTypeCustom:
+		usd := q / common.QuotaPerUnit
+		rate := operation_setting.GetGeneralSetting().CustomCurrencyExchangeRate
+		symbol := operation_setting.GetGeneralSetting().CustomCurrencySymbol
+		if symbol == "" {
+			symbol = "¤"
+		}
+		if rate <= 0 {
+			rate = 1
+		}
+		v := usd * rate
+		return fmt.Sprintf("%s%.6f 额度", symbol, v)
+	case operation_setting.QuotaDisplayTypeTokens:
 		return fmt.Sprintf("%d 点额度", quota)
+	default: // USD
+		return fmt.Sprintf("＄%.6f 额度", q/common.QuotaPerUnit)
 	}
 }
 
 func FormatQuota(quota int) string {
-	if common.DisplayInCurrencyEnabled {
-		return fmt.Sprintf("＄%.6f", float64(quota)/common.QuotaPerUnit)
-	} else {
+	q := float64(quota)
+	switch operation_setting.GetQuotaDisplayType() {
+	case operation_setting.QuotaDisplayTypeCNY:
+		usd := q / common.QuotaPerUnit
+		cny := usd * operation_setting.USDExchangeRate
+		return fmt.Sprintf("¥%.6f", cny)
+	case operation_setting.QuotaDisplayTypeCustom:
+		usd := q / common.QuotaPerUnit
+		rate := operation_setting.GetGeneralSetting().CustomCurrencyExchangeRate
+		symbol := operation_setting.GetGeneralSetting().CustomCurrencySymbol
+		if symbol == "" {
+			symbol = "¤"
+		}
+		if rate <= 0 {
+			rate = 1
+		}
+		v := usd * rate
+		return fmt.Sprintf("%s%.6f", symbol, v)
+	case operation_setting.QuotaDisplayTypeTokens:
 		return fmt.Sprintf("%d", quota)
+	default:
+		return fmt.Sprintf("＄%.6f", q/common.QuotaPerUnit)
 	}
 }
 

middleware/distributor.go

@@ -165,10 +165,45 @@ func getModelRequest(c *gin.Context) (*ModelRequest, bool, error) {
 		}
 		c.Set("platform", string(constant.TaskPlatformSuno))
 		c.Set("relay_mode", relayMode)
+	} else if strings.Contains(c.Request.URL.Path, "/v1/videos") {
+		//curl https://api.openai.com/v1/videos \
+		//  -H "Authorization: Bearer $OPENAI_API_KEY" \
+		//  -F "model=sora-2" \
+		//  -F "prompt=A calico cat playing a piano on stage"
+		//	-F input_reference="@image.jpg"
+		relayMode := relayconstant.RelayModeUnknown
+		if c.Request.Method == http.MethodPost {
+			relayMode = relayconstant.RelayModeVideoSubmit
+			contentType := c.Request.Header.Get("Content-Type")
+			if strings.HasPrefix(contentType, "multipart/form-data") {
+				form, err := common.ParseMultipartFormReusable(c)
+				if err != nil {
+					return nil, false, errors.New("无效的video请求, " + err.Error())
+				}
+				defer form.RemoveAll()
+				if form != nil {
+					if values, ok := form.Value["model"]; ok && len(values) > 0 {
+						modelRequest.Model = values[0]
+					}
+				}
+			} else if strings.HasPrefix(contentType, "application/json") {
+				err = common.UnmarshalBodyReusable(c, &modelRequest)
+				if err != nil {
+					return nil, false, errors.New("无效的video请求, " + err.Error())
+				}
+			}
+		} else if c.Request.Method == http.MethodGet {
+			relayMode = relayconstant.RelayModeVideoFetchByID
+			shouldSelectChannel = false
+		}
+		c.Set("relay_mode", relayMode)
 	} else if strings.Contains(c.Request.URL.Path, "/v1/video/generations") {
 		relayMode := relayconstant.RelayModeUnknown
 		if c.Request.Method == http.MethodPost {
 			err = common.UnmarshalBodyReusable(c, &modelRequest)
+			if err != nil {
+				return nil, false, errors.New("video无效的请求, " + err.Error())
+			}
 			relayMode = relayconstant.RelayModeVideoSubmit
 		} else if c.Request.Method == http.MethodGet {
 			relayMode = relayconstant.RelayModeVideoFetchByID

model/channel.go

@@ -46,7 +46,7 @@ type Channel struct {
 	Setting           *string `json:"setting" gorm:"type:text"` // 渠道额外设置
 	ParamOverride     *string `json:"param_override" gorm:"type:text"`
 	HeaderOverride    *string `json:"header_override" gorm:"type:text"`
-	Remark            string  `json:"remark,omitempty" gorm:"type:varchar(255)" validate:"max=255"`
+	Remark            *string `json:"remark" gorm:"type:varchar(255)" validate:"max=255"`
 	// add after v0.8.5
 	ChannelInfo ChannelInfo `json:"channel_info" gorm:"type:json"`
 

model/option.go

@@ -240,7 +240,15 @@ func updateOptionMap(key string, value string) (err error) {
 		case "LogConsumeEnabled":
 			common.LogConsumeEnabled = boolValue
 		case "DisplayInCurrencyEnabled":
-			common.DisplayInCurrencyEnabled = boolValue
+			// 兼容旧字段：同步到新配置 general_setting.quota_display_type（运行时生效）
+			// true -> USD, false -> TOKENS
+			newVal := "USD"
+			if !boolValue {
+				newVal = "TOKENS"
+			}
+			if cfg := config.GlobalConfig.Get("general_setting"); cfg != nil {
+				_ = config.UpdateConfigFromMap(cfg, map[string]string{"quota_display_type": newVal})
+			}
 		case "DisplayTokenStatEnabled":
 			common.DisplayTokenStatEnabled = boolValue
 		case "DrawingEnabled":

model/topup.go

@@ -6,18 +6,20 @@ import (
 	"one-api/common"
 	"one-api/logger"
 
+	"github.com/shopspring/decimal"
 	"gorm.io/gorm"
 )
 
 type TopUp struct {
-	Id           int     `json:"id"`
-	UserId       int     `json:"user_id" gorm:"index"`
-	Amount       int64   `json:"amount"`
-	Money        float64 `json:"money"`
-	TradeNo      string  `json:"trade_no" gorm:"unique;type:varchar(255);index"`
-	CreateTime   int64   `json:"create_time"`
-	CompleteTime int64   `json:"complete_time"`
-	Status       string  `json:"status"`
+	Id            int     `json:"id"`
+	UserId        int     `json:"user_id" gorm:"index"`
+	Amount        int64   `json:"amount"`
+	Money         float64 `json:"money"`
+	TradeNo       string  `json:"trade_no" gorm:"unique;type:varchar(255);index"`
+	PaymentMethod string  `json:"payment_method" gorm:"type:varchar(50)"`
+	CreateTime    int64   `json:"create_time"`
+	CompleteTime  int64   `json:"complete_time"`
+	Status        string  `json:"status"`
 }
 
 func (topUp *TopUp) Insert() error {
@@ -99,3 +101,206 @@ func Recharge(referenceId string, customerId string) (err error) {
 
 	return nil
 }
+
+func GetUserTopUps(userId int, pageInfo *common.PageInfo) (topups []*TopUp, total int64, err error) {
+	// Start transaction
+	tx := DB.Begin()
+	if tx.Error != nil {
+		return nil, 0, tx.Error
+	}
+	defer func() {
+		if r := recover(); r != nil {
+			tx.Rollback()
+		}
+	}()
+
+	// Get total count within transaction
+	err = tx.Model(&TopUp{}).Where("user_id = ?", userId).Count(&total).Error
+	if err != nil {
+		tx.Rollback()
+		return nil, 0, err
+	}
+
+	// Get paginated topups within same transaction
+	err = tx.Where("user_id = ?", userId).Order("id desc").Limit(pageInfo.GetPageSize()).Offset(pageInfo.GetStartIdx()).Find(&topups).Error
+	if err != nil {
+		tx.Rollback()
+		return nil, 0, err
+	}
+
+	// Commit transaction
+	if err = tx.Commit().Error; err != nil {
+		return nil, 0, err
+	}
+
+	return topups, total, nil
+}
+
+// GetAllTopUps 获取全平台的充值记录（管理员使用）
+func GetAllTopUps(pageInfo *common.PageInfo) (topups []*TopUp, total int64, err error) {
+	tx := DB.Begin()
+	if tx.Error != nil {
+		return nil, 0, tx.Error
+	}
+	defer func() {
+		if r := recover(); r != nil {
+			tx.Rollback()
+		}
+	}()
+
+	if err = tx.Model(&TopUp{}).Count(&total).Error; err != nil {
+		tx.Rollback()
+		return nil, 0, err
+	}
+
+	if err = tx.Order("id desc").Limit(pageInfo.GetPageSize()).Offset(pageInfo.GetStartIdx()).Find(&topups).Error; err != nil {
+		tx.Rollback()
+		return nil, 0, err
+	}
+
+	if err = tx.Commit().Error; err != nil {
+		return nil, 0, err
+	}
+
+	return topups, total, nil
+}
+
+// SearchUserTopUps 按订单号搜索某用户的充值记录
+func SearchUserTopUps(userId int, keyword string, pageInfo *common.PageInfo) (topups []*TopUp, total int64, err error) {
+	tx := DB.Begin()
+	if tx.Error != nil {
+		return nil, 0, tx.Error
+	}
+	defer func() {
+		if r := recover(); r != nil {
+			tx.Rollback()
+		}
+	}()
+
+	query := tx.Model(&TopUp{}).Where("user_id = ?", userId)
+	if keyword != "" {
+		like := "%%" + keyword + "%%"
+		query = query.Where("trade_no LIKE ?", like)
+	}
+
+	if err = query.Count(&total).Error; err != nil {
+		tx.Rollback()
+		return nil, 0, err
+	}
+
+	if err = query.Order("id desc").Limit(pageInfo.GetPageSize()).Offset(pageInfo.GetStartIdx()).Find(&topups).Error; err != nil {
+		tx.Rollback()
+		return nil, 0, err
+	}
+
+	if err = tx.Commit().Error; err != nil {
+		return nil, 0, err
+	}
+	return topups, total, nil
+}
+
+// SearchAllTopUps 按订单号搜索全平台充值记录（管理员使用）
+func SearchAllTopUps(keyword string, pageInfo *common.PageInfo) (topups []*TopUp, total int64, err error) {
+	tx := DB.Begin()
+	if tx.Error != nil {
+		return nil, 0, tx.Error
+	}
+	defer func() {
+		if r := recover(); r != nil {
+			tx.Rollback()
+		}
+	}()
+
+	query := tx.Model(&TopUp{})
+	if keyword != "" {
+		like := "%%" + keyword + "%%"
+		query = query.Where("trade_no LIKE ?", like)
+	}
+
+	if err = query.Count(&total).Error; err != nil {
+		tx.Rollback()
+		return nil, 0, err
+	}
+
+	if err = query.Order("id desc").Limit(pageInfo.GetPageSize()).Offset(pageInfo.GetStartIdx()).Find(&topups).Error; err != nil {
+		tx.Rollback()
+		return nil, 0, err
+	}
+
+	if err = tx.Commit().Error; err != nil {
+		return nil, 0, err
+	}
+	return topups, total, nil
+}
+
+// ManualCompleteTopUp 管理员手动完成订单并给用户充值
+func ManualCompleteTopUp(tradeNo string) error {
+	if tradeNo == "" {
+		return errors.New("未提供订单号")
+	}
+
+	refCol := "`trade_no`"
+	if common.UsingPostgreSQL {
+		refCol = `"trade_no"`
+	}
+
+	var userId int
+	var quotaToAdd int
+	var payMoney float64
+
+	err := DB.Transaction(func(tx *gorm.DB) error {
+		topUp := &TopUp{}
+		// 行级锁，避免并发补单
+		if err := tx.Set("gorm:query_option", "FOR UPDATE").Where(refCol+" = ?", tradeNo).First(topUp).Error; err != nil {
+			return errors.New("充值订单不存在")
+		}
+
+		// 幂等处理：已成功直接返回
+		if topUp.Status == common.TopUpStatusSuccess {
+			return nil
+		}
+
+		if topUp.Status != common.TopUpStatusPending {
+			return errors.New("订单状态不是待支付，无法补单")
+		}
+
+		// 计算应充值额度：
+		// - Stripe 订单：Money 代表经分组倍率换算后的美元数量，直接 * QuotaPerUnit
+		// - 其他订单（如易支付）：Amount 为美元数量，* QuotaPerUnit
+		if topUp.PaymentMethod == "stripe" {
+			dQuotaPerUnit := decimal.NewFromFloat(common.QuotaPerUnit)
+			quotaToAdd = int(decimal.NewFromFloat(topUp.Money).Mul(dQuotaPerUnit).IntPart())
+		} else {
+			dAmount := decimal.NewFromInt(topUp.Amount)
+			dQuotaPerUnit := decimal.NewFromFloat(common.QuotaPerUnit)
+			quotaToAdd = int(dAmount.Mul(dQuotaPerUnit).IntPart())
+		}
+		if quotaToAdd <= 0 {
+			return errors.New("无效的充值额度")
+		}
+
+		// 标记完成
+		topUp.CompleteTime = common.GetTimestamp()
+		topUp.Status = common.TopUpStatusSuccess
+		if err := tx.Save(topUp).Error; err != nil {
+			return err
+		}
+
+		// 增加用户额度（立即写库，保持一致性）
+		if err := tx.Model(&User{}).Where("id = ?", topUp.UserId).Update("quota", gorm.Expr("quota + ?", quotaToAdd)).Error; err != nil {
+			return err
+		}
+
+		userId = topUp.UserId
+		payMoney = topUp.Money
+		return nil
+	})
+
+	if err != nil {
+		return err
+	}
+
+	// 事务外记录日志，避免阻塞
+	RecordLog(userId, LogTypeTopup, fmt.Sprintf("管理员补单成功，充值金额: %v，支付金额：%f", logger.FormatQuota(quotaToAdd), payMoney))
+	return nil
+}

relay/channel/adapter.go

@@ -4,6 +4,7 @@ import (
 	"io"
 	"net/http"
 	"one-api/dto"
+	"one-api/model"
 	relaycommon "one-api/relay/common"
 	"one-api/types"
 
@@ -49,3 +50,7 @@ type TaskAdaptor interface {
 
 	ParseTaskResult(respBody []byte) (*relaycommon.TaskInfo, error)
 }
+
+type OpenAIVideoConverter interface {
+	ConvertToOpenAIVideo(originTask *model.Task) (*relaycommon.OpenAIVideo, error)
+}

relay/channel/api_request.go

@@ -14,6 +14,7 @@ import (
 	"one-api/service"
 	"one-api/setting/operation_setting"
 	"one-api/types"
+	"strings"
 	"sync"
 	"time"
 
@@ -36,6 +37,26 @@ func SetupApiRequestHeader(info *common.RelayInfo, c *gin.Context, req *http.Hea
 	}
 }
 
+// processHeaderOverride 处理请求头覆盖，支持变量替换
+// 支持的变量：{api_key}
+func processHeaderOverride(info *common.RelayInfo) (map[string]string, error) {
+	headerOverride := make(map[string]string)
+	for k, v := range info.HeadersOverride {
+		str, ok := v.(string)
+		if !ok {
+			return nil, types.NewError(nil, types.ErrorCodeChannelHeaderOverrideInvalid)
+		}
+
+		// 替换支持的变量
+		if strings.Contains(str, "{api_key}") {
+			str = strings.ReplaceAll(str, "{api_key}", info.ApiKey)
+		}
+
+		headerOverride[k] = str
+	}
+	return headerOverride, nil
+}
+
 func DoApiRequest(a Adaptor, c *gin.Context, info *common.RelayInfo, requestBody io.Reader) (*http.Response, error) {
 	fullRequestURL, err := a.GetRequestURL(info)
 	if err != nil {
@@ -49,13 +70,9 @@ func DoApiRequest(a Adaptor, c *gin.Context, info *common.RelayInfo, requestBody
 		return nil, fmt.Errorf("new request failed: %w", err)
 	}
 	headers := req.Header
-	headerOverride := make(map[string]string)
-	for k, v := range info.HeadersOverride {
-		if str, ok := v.(string); ok {
-			headerOverride[k] = str
-		} else {
-			return nil, types.NewError(err, types.ErrorCodeChannelHeaderOverrideInvalid)
-		}
+	headerOverride, err := processHeaderOverride(info)
+	if err != nil {
+		return nil, err
 	}
 	for key, value := range headerOverride {
 		headers.Set(key, value)
@@ -86,13 +103,9 @@ func DoFormRequest(a Adaptor, c *gin.Context, info *common.RelayInfo, requestBod
 	// set form data
 	req.Header.Set("Content-Type", c.Request.Header.Get("Content-Type"))
 	headers := req.Header
-	headerOverride := make(map[string]string)
-	for k, v := range info.HeadersOverride {
-		if str, ok := v.(string); ok {
-			headerOverride[k] = str
-		} else {
-			return nil, types.NewError(err, types.ErrorCodeChannelHeaderOverrideInvalid)
-		}
+	headerOverride, err := processHeaderOverride(info)
+	if err != nil {
+		return nil, err
 	}
 	for key, value := range headerOverride {
 		headers.Set(key, value)
@@ -114,6 +127,13 @@ func DoWssRequest(a Adaptor, c *gin.Context, info *common.RelayInfo, requestBody
 		return nil, fmt.Errorf("get request url failed: %w", err)
 	}
 	targetHeader := http.Header{}
+	headerOverride, err := processHeaderOverride(info)
+	if err != nil {
+		return nil, err
+	}
+	for key, value := range headerOverride {
+		targetHeader.Set(key, value)
+	}
 	err = a.SetupRequestHeader(c, &targetHeader, info)
 	if err != nil {
 		return nil, fmt.Errorf("setup request header failed: %w", err)

relay/channel/aws/adaptor.go

@@ -7,7 +7,6 @@ import (
 	"one-api/dto"
 	"one-api/relay/channel/claude"
 	relaycommon "one-api/relay/common"
-	"one-api/setting/model_setting"
 	"one-api/types"
 
 	"github.com/gin-gonic/gin"
@@ -52,11 +51,7 @@ func (a *Adaptor) GetRequestURL(info *relaycommon.RelayInfo) (string, error) {
 }
 
 func (a *Adaptor) SetupRequestHeader(c *gin.Context, req *http.Header, info *relaycommon.RelayInfo) error {
-	anthropicBeta := c.Request.Header.Get("anthropic-beta")
-	if anthropicBeta != "" {
-		req.Set("anthropic-beta", anthropicBeta)
-	}
-	model_setting.GetClaudeSettings().WriteHeaders(info.OriginModelName, req)
+	claude.CommonClaudeHeadersOperation(c, req, info)
 	return nil
 }
 

relay/channel/claude/adaptor.go

@@ -64,6 +64,15 @@ func (a *Adaptor) GetRequestURL(info *relaycommon.RelayInfo) (string, error) {
 	return baseURL, nil
 }
 
+func CommonClaudeHeadersOperation(c *gin.Context, req *http.Header, info *relaycommon.RelayInfo) {
+	// common headers operation
+	anthropicBeta := c.Request.Header.Get("anthropic-beta")
+	if anthropicBeta != "" {
+		req.Set("anthropic-beta", anthropicBeta)
+	}
+	model_setting.GetClaudeSettings().WriteHeaders(info.OriginModelName, req)
+}
+
 func (a *Adaptor) SetupRequestHeader(c *gin.Context, req *http.Header, info *relaycommon.RelayInfo) error {
 	channel.SetupApiRequestHeader(info, c, req)
 	req.Set("x-api-key", info.ApiKey)
@@ -72,11 +81,7 @@ func (a *Adaptor) SetupRequestHeader(c *gin.Context, req *http.Header, info *rel
 		anthropicVersion = "2023-06-01"
 	}
 	req.Set("anthropic-version", anthropicVersion)
-	anthropicBeta := c.Request.Header.Get("anthropic-beta")
-	if anthropicBeta != "" {
-		req.Set("anthropic-beta", anthropicBeta)
-	}
-	model_setting.GetClaudeSettings().WriteHeaders(info.OriginModelName, req)
+	CommonClaudeHeadersOperation(c, req, info)
 	return nil
 }
 

relay/channel/gemini/adaptor.go

@@ -67,8 +67,12 @@ func (a *Adaptor) ConvertImageRequest(c *gin.Context, info *relaycommon.RelayInf
 			aspectRatio = size
 		} else {
 			switch size {
-			case "1024x1024":
+			case "256x256", "512x512", "1024x1024":
 				aspectRatio = "1:1"
+			case "1536x1024":
+				aspectRatio = "3:2"
+			case "1024x1536":
+				aspectRatio = "2:3"
 			case "1024x1792":
 				aspectRatio = "9:16"
 			case "1792x1024":
@@ -91,6 +95,28 @@ func (a *Adaptor) ConvertImageRequest(c *gin.Context, info *relaycommon.RelayInf
 		},
 	}
 
+	// Set imageSize when quality parameter is specified
+	// Map quality parameter to imageSize (only supported by Standard and Ultra models)
+	// quality values: auto, high, medium, low (for gpt-image-1), hd, standard (for dall-e-3)
+	// imageSize values: 1K (default), 2K
+	// https://ai.google.dev/gemini-api/docs/imagen
+	// https://platform.openai.com/docs/api-reference/images/create
+	if request.Quality != "" {
+		imageSize := "1K" // default
+		switch request.Quality {
+		case "hd", "high":
+			imageSize = "2K"
+		case "2K":
+			imageSize = "2K"
+		case "standard", "medium", "low", "auto", "1K":
+			imageSize = "1K"
+		default:
+			// unknown quality value, default to 1K
+			imageSize = "1K"
+		}
+		geminiRequest.Parameters.ImageSize = imageSize
+	}
+
 	return geminiRequest, nil
 }
 

relay/channel/gemini/relay-gemini.go

@@ -961,9 +961,15 @@ func GeminiChatStreamHandler(c *gin.Context, info *relaycommon.RelayInfo, resp *
 			// send first response
 			emptyResponse := helper.GenerateStartEmptyResponse(id, createAt, info.UpstreamModelName, nil)
 			if response.IsToolCall() {
-				emptyResponse.Choices[0].Delta.ToolCalls = make([]dto.ToolCallResponse, 1)
-				emptyResponse.Choices[0].Delta.ToolCalls[0] = *response.GetFirstToolCall()
-				emptyResponse.Choices[0].Delta.ToolCalls[0].Function.Arguments = ""
+				if len(emptyResponse.Choices) > 0 && len(response.Choices) > 0 {
+					toolCalls := response.Choices[0].Delta.ToolCalls
+					copiedToolCalls := make([]dto.ToolCallResponse, len(toolCalls))
+					for idx := range toolCalls {
+						copiedToolCalls[idx] = toolCalls[idx]
+						copiedToolCalls[idx].Function.Arguments = ""
+					}
+					emptyResponse.Choices[0].Delta.ToolCalls = copiedToolCalls
+				}
 				finishReason = constant.FinishReasonToolCalls
 				err = handleStream(c, info, emptyResponse)
 				if err != nil {
@@ -1044,7 +1050,12 @@ func GeminiChatHandler(c *gin.Context, info *relaycommon.RelayInfo, resp *http.R
 		return nil, types.NewOpenAIError(err, types.ErrorCodeBadResponseBody, http.StatusInternalServerError)
 	}
 	if len(geminiResponse.Candidates) == 0 {
-		return nil, types.NewOpenAIError(errors.New("no candidates returned"), types.ErrorCodeBadResponseBody, http.StatusInternalServerError)
+		//return nil, types.NewOpenAIError(errors.New("no candidates returned"), types.ErrorCodeBadResponseBody, http.StatusInternalServerError)
+		if geminiResponse.PromptFeedback != nil && geminiResponse.PromptFeedback.BlockReason != nil {
+			return nil, types.NewOpenAIError(errors.New("request blocked by Gemini API: "+*geminiResponse.PromptFeedback.BlockReason), types.ErrorCodePromptBlocked, http.StatusBadRequest)
+		} else {
+			return nil, types.NewOpenAIError(errors.New("empty response from Gemini API"), types.ErrorCodeEmptyResponse, http.StatusInternalServerError)
+		}
 	}
 	fullTextResponse := responseGeminiChat2OpenAI(c, &geminiResponse)
 	fullTextResponse.Model = info.UpstreamModelName

relay/channel/jina/adaptor.go

@@ -76,6 +76,7 @@ func (a *Adaptor) ConvertRerankRequest(c *gin.Context, relayMode int, request dt
 }
 
 func (a *Adaptor) ConvertEmbeddingRequest(c *gin.Context, info *relaycommon.RelayInfo, request dto.EmbeddingRequest) (any, error) {
+	request.EncodingFormat = ""
 	return request, nil
 }
 

relay/channel/ollama/adaptor.go

@@ -18,7 +18,9 @@ import (
 type Adaptor struct {
 }
 
-func (a *Adaptor) ConvertGeminiRequest(*gin.Context, *relaycommon.RelayInfo, *dto.GeminiChatRequest) (any, error) { return nil, errors.New("not implemented") }
+func (a *Adaptor) ConvertGeminiRequest(*gin.Context, *relaycommon.RelayInfo, *dto.GeminiChatRequest) (any, error) {
+	return nil, errors.New("not implemented")
+}
 
 func (a *Adaptor) ConvertClaudeRequest(c *gin.Context, info *relaycommon.RelayInfo, request *dto.ClaudeRequest) (any, error) {
 	openaiAdaptor := openai.Adaptor{}
@@ -33,17 +35,25 @@ func (a *Adaptor) ConvertClaudeRequest(c *gin.Context, info *relaycommon.RelayIn
 	return openAIChatToOllamaChat(c, openaiRequest.(*dto.GeneralOpenAIRequest))
 }
 
-func (a *Adaptor) ConvertAudioRequest(c *gin.Context, info *relaycommon.RelayInfo, request dto.AudioRequest) (io.Reader, error) { return nil, errors.New("not implemented") }
+func (a *Adaptor) ConvertAudioRequest(c *gin.Context, info *relaycommon.RelayInfo, request dto.AudioRequest) (io.Reader, error) {
+	return nil, errors.New("not implemented")
+}
 
-func (a *Adaptor) ConvertImageRequest(c *gin.Context, info *relaycommon.RelayInfo, request dto.ImageRequest) (any, error) { return nil, errors.New("not implemented") }
+func (a *Adaptor) ConvertImageRequest(c *gin.Context, info *relaycommon.RelayInfo, request dto.ImageRequest) (any, error) {
+	return nil, errors.New("not implemented")
+}
 
 func (a *Adaptor) Init(info *relaycommon.RelayInfo) {
 }
 
 func (a *Adaptor) GetRequestURL(info *relaycommon.RelayInfo) (string, error) {
-    if info.RelayMode == relayconstant.RelayModeEmbeddings { return info.ChannelBaseUrl + "/api/embed", nil }
-    if strings.Contains(info.RequestURLPath, "/v1/completions") || info.RelayMode == relayconstant.RelayModeCompletions { return info.ChannelBaseUrl + "/api/generate", nil }
-    return info.ChannelBaseUrl + "/api/chat", nil
+	if info.RelayMode == relayconstant.RelayModeEmbeddings {
+		return info.ChannelBaseUrl + "/api/embed", nil
+	}
+	if strings.Contains(info.RequestURLPath, "/v1/completions") || info.RelayMode == relayconstant.RelayModeCompletions {
+		return info.ChannelBaseUrl + "/api/generate", nil
+	}
+	return info.ChannelBaseUrl + "/api/chat", nil
 }
 
 func (a *Adaptor) SetupRequestHeader(c *gin.Context, req *http.Header, info *relaycommon.RelayInfo) error {
@@ -53,7 +63,9 @@ func (a *Adaptor) SetupRequestHeader(c *gin.Context, req *http.Header, info *rel
 }
 
 func (a *Adaptor) ConvertOpenAIRequest(c *gin.Context, info *relaycommon.RelayInfo, request *dto.GeneralOpenAIRequest) (any, error) {
-	if request == nil { return nil, errors.New("request is nil") }
+	if request == nil {
+		return nil, errors.New("request is nil")
+	}
 	// decide generate or chat
 	if strings.Contains(info.RequestURLPath, "/v1/completions") || info.RelayMode == relayconstant.RelayModeCompletions {
 		return openAIToGenerate(c, request)
@@ -69,7 +81,9 @@ func (a *Adaptor) ConvertEmbeddingRequest(c *gin.Context, info *relaycommon.Rela
 	return requestOpenAI2Embeddings(request), nil
 }
 
-func (a *Adaptor) ConvertOpenAIResponsesRequest(c *gin.Context, info *relaycommon.RelayInfo, request dto.OpenAIResponsesRequest) (any, error) { return nil, errors.New("not implemented") }
+func (a *Adaptor) ConvertOpenAIResponsesRequest(c *gin.Context, info *relaycommon.RelayInfo, request dto.OpenAIResponsesRequest) (any, error) {
+	return nil, errors.New("not implemented")
+}
 
 func (a *Adaptor) DoRequest(c *gin.Context, info *relaycommon.RelayInfo, requestBody io.Reader) (any, error) {
 	return channel.DoApiRequest(a, c, info, requestBody)

relay/channel/ollama/dto.go

@@ -5,12 +5,12 @@ import (
 )
 
 type OllamaChatMessage struct {
-	Role      string            `json:"role"`
-	Content   string            `json:"content,omitempty"`
-	Images    []string          `json:"images,omitempty"`
-	ToolCalls []OllamaToolCall  `json:"tool_calls,omitempty"`
-	ToolName  string            `json:"tool_name,omitempty"`
-	Thinking  json.RawMessage   `json:"thinking,omitempty"`
+	Role      string           `json:"role"`
+	Content   string           `json:"content,omitempty"`
+	Images    []string         `json:"images,omitempty"`
+	ToolCalls []OllamaToolCall `json:"tool_calls,omitempty"`
+	ToolName  string           `json:"tool_name,omitempty"`
+	Thinking  json.RawMessage  `json:"thinking,omitempty"`
 }
 
 type OllamaToolFunction struct {
@@ -20,7 +20,7 @@ type OllamaToolFunction struct {
 }
 
 type OllamaTool struct {
-	Type     string            `json:"type"`
+	Type     string             `json:"type"`
 	Function OllamaToolFunction `json:"function"`
 }
 
@@ -43,28 +43,27 @@ type OllamaChatRequest struct {
 }
 
 type OllamaGenerateRequest struct {
-	Model     string         `json:"model"`
-	Prompt    string         `json:"prompt,omitempty"`
-	Suffix    string         `json:"suffix,omitempty"`
-	Images    []string       `json:"images,omitempty"`
-	Format    interface{}    `json:"format,omitempty"`
-	Stream    bool           `json:"stream,omitempty"`
-	Options   map[string]any `json:"options,omitempty"`
-	KeepAlive interface{}    `json:"keep_alive,omitempty"`
+	Model     string          `json:"model"`
+	Prompt    string          `json:"prompt,omitempty"`
+	Suffix    string          `json:"suffix,omitempty"`
+	Images    []string        `json:"images,omitempty"`
+	Format    interface{}     `json:"format,omitempty"`
+	Stream    bool            `json:"stream,omitempty"`
+	Options   map[string]any  `json:"options,omitempty"`
+	KeepAlive interface{}     `json:"keep_alive,omitempty"`
 	Think     json.RawMessage `json:"think,omitempty"`
 }
 
 type OllamaEmbeddingRequest struct {
-	Model     string         `json:"model"`
-	Input     interface{}    `json:"input"`
-	Options   map[string]any `json:"options,omitempty"`
+	Model      string         `json:"model"`
+	Input      interface{}    `json:"input"`
+	Options    map[string]any `json:"options,omitempty"`
 	Dimensions int            `json:"dimensions,omitempty"`
 }
 
 type OllamaEmbeddingResponse struct {
-	Error           string        `json:"error,omitempty"`
-	Model           string        `json:"model"`
-	Embeddings      [][]float64   `json:"embeddings"`
-	PromptEvalCount int           `json:"prompt_eval_count,omitempty"`
+	Error           string      `json:"error,omitempty"`
+	Model           string      `json:"model"`
+	Embeddings      [][]float64 `json:"embeddings"`
+	PromptEvalCount int         `json:"prompt_eval_count,omitempty"`
 }
-

relay/channel/ollama/relay-ollama.go

@@ -35,13 +35,27 @@ func openAIChatToOllamaChat(c *gin.Context, r *dto.GeneralOpenAIRequest) (*Ollam
 	}
 
 	// options mapping
-	if r.Temperature != nil { chatReq.Options["temperature"] = r.Temperature }
-	if r.TopP != 0 { chatReq.Options["top_p"] = r.TopP }
-	if r.TopK != 0 { chatReq.Options["top_k"] = r.TopK }
-	if r.FrequencyPenalty != 0 { chatReq.Options["frequency_penalty"] = r.FrequencyPenalty }
-	if r.PresencePenalty != 0 { chatReq.Options["presence_penalty"] = r.PresencePenalty }
-	if r.Seed != 0 { chatReq.Options["seed"] = int(r.Seed) }
-	if mt := r.GetMaxTokens(); mt != 0 { chatReq.Options["num_predict"] = int(mt) }
+	if r.Temperature != nil {
+		chatReq.Options["temperature"] = r.Temperature
+	}
+	if r.TopP != 0 {
+		chatReq.Options["top_p"] = r.TopP
+	}
+	if r.TopK != 0 {
+		chatReq.Options["top_k"] = r.TopK
+	}
+	if r.FrequencyPenalty != 0 {
+		chatReq.Options["frequency_penalty"] = r.FrequencyPenalty
+	}
+	if r.PresencePenalty != 0 {
+		chatReq.Options["presence_penalty"] = r.PresencePenalty
+	}
+	if r.Seed != 0 {
+		chatReq.Options["seed"] = int(r.Seed)
+	}
+	if mt := r.GetMaxTokens(); mt != 0 {
+		chatReq.Options["num_predict"] = int(mt)
+	}
 
 	if r.Stop != nil {
 		switch v := r.Stop.(type) {
@@ -50,21 +64,27 @@ func openAIChatToOllamaChat(c *gin.Context, r *dto.GeneralOpenAIRequest) (*Ollam
 		case []string:
 			chatReq.Options["stop"] = v
 		case []any:
-			arr := make([]string,0,len(v))
-			for _, i := range v { if s,ok:=i.(string); ok { arr = append(arr,s) } }
-			if len(arr)>0 { chatReq.Options["stop"] = arr }
+			arr := make([]string, 0, len(v))
+			for _, i := range v {
+				if s, ok := i.(string); ok {
+					arr = append(arr, s)
+				}
+			}
+			if len(arr) > 0 {
+				chatReq.Options["stop"] = arr
+			}
 		}
 	}
 
 	if len(r.Tools) > 0 {
-		tools := make([]OllamaTool,0,len(r.Tools))
+		tools := make([]OllamaTool, 0, len(r.Tools))
 		for _, t := range r.Tools {
 			tools = append(tools, OllamaTool{Type: "function", Function: OllamaToolFunction{Name: t.Function.Name, Description: t.Function.Description, Parameters: t.Function.Parameters}})
 		}
 		chatReq.Tools = tools
 	}
 
-	chatReq.Messages = make([]OllamaChatMessage,0,len(r.Messages))
+	chatReq.Messages = make([]OllamaChatMessage, 0, len(r.Messages))
 	for _, m := range r.Messages {
 		var textBuilder strings.Builder
 		var images []string
@@ -79,14 +99,20 @@ func openAIChatToOllamaChat(c *gin.Context, r *dto.GeneralOpenAIRequest) (*Ollam
 						var base64Data string
 						if strings.HasPrefix(img.Url, "http") {
 							fileData, err := service.GetFileBase64FromUrl(c, img.Url, "fetch image for ollama chat")
-							if err != nil { return nil, err }
+							if err != nil {
+								return nil, err
+							}
 							base64Data = fileData.Base64Data
 						} else if strings.HasPrefix(img.Url, "data:") {
-							if idx := strings.Index(img.Url, ","); idx != -1 && idx+1 < len(img.Url) { base64Data = img.Url[idx+1:] }
+							if idx := strings.Index(img.Url, ","); idx != -1 && idx+1 < len(img.Url) {
+								base64Data = img.Url[idx+1:]
+							}
 						} else {
 							base64Data = img.Url
 						}
-						if base64Data != "" { images = append(images, base64Data) }
+						if base64Data != "" {
+							images = append(images, base64Data)
+						}
 					}
 				} else if part.Type == dto.ContentTypeText {
 					textBuilder.WriteString(part.Text)
@@ -94,16 +120,24 @@ func openAIChatToOllamaChat(c *gin.Context, r *dto.GeneralOpenAIRequest) (*Ollam
 			}
 		}
 		cm := OllamaChatMessage{Role: m.Role, Content: textBuilder.String()}
-		if len(images)>0 { cm.Images = images }
-		if m.Role == "tool" && m.Name != nil { cm.ToolName = *m.Name }
+		if len(images) > 0 {
+			cm.Images = images
+		}
+		if m.Role == "tool" && m.Name != nil {
+			cm.ToolName = *m.Name
+		}
 		if m.ToolCalls != nil && len(m.ToolCalls) > 0 {
 			parsed := m.ParseToolCalls()
 			if len(parsed) > 0 {
-				calls := make([]OllamaToolCall,0,len(parsed))
+				calls := make([]OllamaToolCall, 0, len(parsed))
 				for _, tc := range parsed {
 					var args interface{}
-					if tc.Function.Arguments != "" { _ = json.Unmarshal([]byte(tc.Function.Arguments), &args) }
-					if args==nil { args = map[string]any{} }
+					if tc.Function.Arguments != "" {
+						_ = json.Unmarshal([]byte(tc.Function.Arguments), &args)
+					}
+					if args == nil {
+						args = map[string]any{}
+					}
 					oc := OllamaToolCall{}
 					oc.Function.Name = tc.Function.Name
 					oc.Function.Arguments = args
@@ -132,28 +166,67 @@ func openAIToGenerate(c *gin.Context, r *dto.GeneralOpenAIRequest) (*OllamaGener
 			gen.Prompt = v
 		case []any:
 			var sb strings.Builder
-			for _, it := range v { if s,ok:=it.(string); ok { sb.WriteString(s) } }
+			for _, it := range v {
+				if s, ok := it.(string); ok {
+					sb.WriteString(s)
+				}
+			}
 			gen.Prompt = sb.String()
 		default:
 			gen.Prompt = fmt.Sprintf("%v", r.Prompt)
 		}
 	}
-	if r.Suffix != nil { if s,ok:=r.Suffix.(string); ok { gen.Suffix = s } }
-	if r.ResponseFormat != nil {
-		if r.ResponseFormat.Type == "json" { gen.Format = "json" } else if r.ResponseFormat.Type == "json_schema" { var schema any; _ = json.Unmarshal(r.ResponseFormat.JsonSchema,&schema); gen.Format=schema }
+	if r.Suffix != nil {
+		if s, ok := r.Suffix.(string); ok {
+			gen.Suffix = s
+		}
+	}
+	if r.ResponseFormat != nil {
+		if r.ResponseFormat.Type == "json" {
+			gen.Format = "json"
+		} else if r.ResponseFormat.Type == "json_schema" {
+			var schema any
+			_ = json.Unmarshal(r.ResponseFormat.JsonSchema, &schema)
+			gen.Format = schema
+		}
+	}
+	if r.Temperature != nil {
+		gen.Options["temperature"] = r.Temperature
+	}
+	if r.TopP != 0 {
+		gen.Options["top_p"] = r.TopP
+	}
+	if r.TopK != 0 {
+		gen.Options["top_k"] = r.TopK
+	}
+	if r.FrequencyPenalty != 0 {
+		gen.Options["frequency_penalty"] = r.FrequencyPenalty
+	}
+	if r.PresencePenalty != 0 {
+		gen.Options["presence_penalty"] = r.PresencePenalty
+	}
+	if r.Seed != 0 {
+		gen.Options["seed"] = int(r.Seed)
+	}
+	if mt := r.GetMaxTokens(); mt != 0 {
+		gen.Options["num_predict"] = int(mt)
 	}
-	if r.Temperature != nil { gen.Options["temperature"] = r.Temperature }
-	if r.TopP != 0 { gen.Options["top_p"] = r.TopP }
-	if r.TopK != 0 { gen.Options["top_k"] = r.TopK }
-	if r.FrequencyPenalty != 0 { gen.Options["frequency_penalty"] = r.FrequencyPenalty }
-	if r.PresencePenalty != 0 { gen.Options["presence_penalty"] = r.PresencePenalty }
-	if r.Seed != 0 { gen.Options["seed"] = int(r.Seed) }
-	if mt := r.GetMaxTokens(); mt != 0 { gen.Options["num_predict"] = int(mt) }
 	if r.Stop != nil {
 		switch v := r.Stop.(type) {
-		case string: gen.Options["stop"] = []string{v}
-		case []string: gen.Options["stop"] = v
-		case []any: arr:=make([]string,0,len(v)); for _,i:= range v { if s,ok:=i.(string); ok { arr=append(arr,s) } }; if len(arr)>0 { gen.Options["stop"]=arr }
+		case string:
+			gen.Options["stop"] = []string{v}
+		case []string:
+			gen.Options["stop"] = v
+		case []any:
+			arr := make([]string, 0, len(v))
+			for _, i := range v {
+				if s, ok := i.(string); ok {
+					arr = append(arr, s)
+				}
+			}
+			if len(arr) > 0 {
+				gen.Options["stop"] = arr
+			}
 		}
 	}
 	return gen, nil
@@ -161,30 +234,51 @@ func openAIToGenerate(c *gin.Context, r *dto.GeneralOpenAIRequest) (*OllamaGener
 
 func requestOpenAI2Embeddings(r dto.EmbeddingRequest) *OllamaEmbeddingRequest {
 	opts := map[string]any{}
-	if r.Temperature != nil { opts["temperature"] = r.Temperature }
-	if r.TopP != 0 { opts["top_p"] = r.TopP }
-	if r.FrequencyPenalty != 0 { opts["frequency_penalty"] = r.FrequencyPenalty }
-	if r.PresencePenalty != 0 { opts["presence_penalty"] = r.PresencePenalty }
-	if r.Seed != 0 { opts["seed"] = int(r.Seed) }
-	if r.Dimensions != 0 { opts["dimensions"] = r.Dimensions }
+	if r.Temperature != nil {
+		opts["temperature"] = r.Temperature
+	}
+	if r.TopP != 0 {
+		opts["top_p"] = r.TopP
+	}
+	if r.FrequencyPenalty != 0 {
+		opts["frequency_penalty"] = r.FrequencyPenalty
+	}
+	if r.PresencePenalty != 0 {
+		opts["presence_penalty"] = r.PresencePenalty
+	}
+	if r.Seed != 0 {
+		opts["seed"] = int(r.Seed)
+	}
+	if r.Dimensions != 0 {
+		opts["dimensions"] = r.Dimensions
+	}
 	input := r.ParseInput()
-	if len(input)==1 { return &OllamaEmbeddingRequest{Model:r.Model, Input: input[0], Options: opts, Dimensions:r.Dimensions} }
-	return &OllamaEmbeddingRequest{Model:r.Model, Input: input, Options: opts, Dimensions:r.Dimensions}
+	if len(input) == 1 {
+		return &OllamaEmbeddingRequest{Model: r.Model, Input: input[0], Options: opts, Dimensions: r.Dimensions}
+	}
+	return &OllamaEmbeddingRequest{Model: r.Model, Input: input, Options: opts, Dimensions: r.Dimensions}
 }
 
 func ollamaEmbeddingHandler(c *gin.Context, info *relaycommon.RelayInfo, resp *http.Response) (*dto.Usage, *types.NewAPIError) {
 	var oResp OllamaEmbeddingResponse
 	body, err := io.ReadAll(resp.Body)
-	if err != nil { return nil, types.NewOpenAIError(err, types.ErrorCodeBadResponseBody, http.StatusInternalServerError) }
+	if err != nil {
+		return nil, types.NewOpenAIError(err, types.ErrorCodeBadResponseBody, http.StatusInternalServerError)
+	}
 	service.CloseResponseBodyGracefully(resp)
-	if err = common.Unmarshal(body, &oResp); err != nil { return nil, types.NewOpenAIError(err, types.ErrorCodeBadResponseBody, http.StatusInternalServerError) }
-	if oResp.Error != "" { return nil, types.NewOpenAIError(fmt.Errorf("ollama error: %s", oResp.Error), types.ErrorCodeBadResponseBody, http.StatusInternalServerError) }
-	data := make([]dto.OpenAIEmbeddingResponseItem,0,len(oResp.Embeddings))
-	for i, emb := range oResp.Embeddings { data = append(data, dto.OpenAIEmbeddingResponseItem{Index:i,Object:"embedding",Embedding:emb}) }
-	usage := &dto.Usage{PromptTokens: oResp.PromptEvalCount, CompletionTokens:0, TotalTokens: oResp.PromptEvalCount}
-	embResp := &dto.OpenAIEmbeddingResponse{Object:"list", Data:data, Model: info.UpstreamModelName, Usage:*usage}
+	if err = common.Unmarshal(body, &oResp); err != nil {
+		return nil, types.NewOpenAIError(err, types.ErrorCodeBadResponseBody, http.StatusInternalServerError)
+	}
+	if oResp.Error != "" {
+		return nil, types.NewOpenAIError(fmt.Errorf("ollama error: %s", oResp.Error), types.ErrorCodeBadResponseBody, http.StatusInternalServerError)
+	}
+	data := make([]dto.OpenAIEmbeddingResponseItem, 0, len(oResp.Embeddings))
+	for i, emb := range oResp.Embeddings {
+		data = append(data, dto.OpenAIEmbeddingResponseItem{Index: i, Object: "embedding", Embedding: emb})
+	}
+	usage := &dto.Usage{PromptTokens: oResp.PromptEvalCount, CompletionTokens: 0, TotalTokens: oResp.PromptEvalCount}
+	embResp := &dto.OpenAIEmbeddingResponse{Object: "list", Data: data, Model: info.UpstreamModelName, Usage: *usage}
 	out, _ := common.Marshal(embResp)
 	service.IOCopyBytesGracefully(c, resp, out)
 	return usage, nil
 }
-

relay/channel/ollama/stream.go

@@ -1,210 +1,278 @@
 package ollama
 
 import (
-    "bufio"
-    "encoding/json"
-    "fmt"
-    "io"
-    "net/http"
-    "one-api/common"
-    "one-api/dto"
-    "one-api/logger"
-    relaycommon "one-api/relay/common"
-    "one-api/relay/helper"
-    "one-api/service"
-    "one-api/types"
-    "strings"
-    "time"
+	"bufio"
+	"encoding/json"
+	"fmt"
+	"io"
+	"net/http"
+	"one-api/common"
+	"one-api/dto"
+	"one-api/logger"
+	relaycommon "one-api/relay/common"
+	"one-api/relay/helper"
+	"one-api/service"
+	"one-api/types"
+	"strings"
+	"time"
 
-    "github.com/gin-gonic/gin"
+	"github.com/gin-gonic/gin"
 )
 
 type ollamaChatStreamChunk struct {
-    Model            string `json:"model"`
-    CreatedAt        string `json:"created_at"`
-    // chat
-    Message *struct {
-        Role      string `json:"role"`
-        Content   string `json:"content"`
-        Thinking  json.RawMessage `json:"thinking"`
-        ToolCalls []struct {
-            Function struct {
-                Name      string      `json:"name"`
-                Arguments interface{} `json:"arguments"`
-            } `json:"function"`
-        } `json:"tool_calls"`
-    } `json:"message"`
-    // generate
-    Response string `json:"response"`
-    Done         bool    `json:"done"`
-    DoneReason   string  `json:"done_reason"`
-    TotalDuration int64  `json:"total_duration"`
-    LoadDuration  int64  `json:"load_duration"`
-    PromptEvalCount int  `json:"prompt_eval_count"`
-    EvalCount       int  `json:"eval_count"`
-    PromptEvalDuration int64 `json:"prompt_eval_duration"`
-    EvalDuration       int64 `json:"eval_duration"`
+	Model     string `json:"model"`
+	CreatedAt string `json:"created_at"`
+	// chat
+	Message *struct {
+		Role      string          `json:"role"`
+		Content   string          `json:"content"`
+		Thinking  json.RawMessage `json:"thinking"`
+		ToolCalls []struct {
+			Function struct {
+				Name      string      `json:"name"`
+				Arguments interface{} `json:"arguments"`
+			} `json:"function"`
+		} `json:"tool_calls"`
+	} `json:"message"`
+	// generate
+	Response           string `json:"response"`
+	Done               bool   `json:"done"`
+	DoneReason         string `json:"done_reason"`
+	TotalDuration      int64  `json:"total_duration"`
+	LoadDuration       int64  `json:"load_duration"`
+	PromptEvalCount    int    `json:"prompt_eval_count"`
+	EvalCount          int    `json:"eval_count"`
+	PromptEvalDuration int64  `json:"prompt_eval_duration"`
+	EvalDuration       int64  `json:"eval_duration"`
 }
 
 func toUnix(ts string) int64 {
-    if ts == "" { return time.Now().Unix() }
-    // try time.RFC3339 or with nanoseconds
-    t, err := time.Parse(time.RFC3339Nano, ts)
-    if err != nil { t2, err2 := time.Parse(time.RFC3339, ts); if err2==nil { return t2.Unix() }; return time.Now().Unix() }
-    return t.Unix()
+	if ts == "" {
+		return time.Now().Unix()
+	}
+	// try time.RFC3339 or with nanoseconds
+	t, err := time.Parse(time.RFC3339Nano, ts)
+	if err != nil {
+		t2, err2 := time.Parse(time.RFC3339, ts)
+		if err2 == nil {
+			return t2.Unix()
+		}
+		return time.Now().Unix()
+	}
+	return t.Unix()
 }
 
 func ollamaStreamHandler(c *gin.Context, info *relaycommon.RelayInfo, resp *http.Response) (*dto.Usage, *types.NewAPIError) {
-    if resp == nil || resp.Body == nil { return nil, types.NewOpenAIError(fmt.Errorf("empty response"), types.ErrorCodeBadResponse, http.StatusBadRequest) }
-    defer service.CloseResponseBodyGracefully(resp)
+	if resp == nil || resp.Body == nil {
+		return nil, types.NewOpenAIError(fmt.Errorf("empty response"), types.ErrorCodeBadResponse, http.StatusBadRequest)
+	}
+	defer service.CloseResponseBodyGracefully(resp)
 
-    helper.SetEventStreamHeaders(c)
-    scanner := bufio.NewScanner(resp.Body)
-    usage := &dto.Usage{}
-    var model = info.UpstreamModelName
-    var responseId = common.GetUUID()
-    var created = time.Now().Unix()
-    var toolCallIndex int
-    start := helper.GenerateStartEmptyResponse(responseId, created, model, nil)
-    if data, err := common.Marshal(start); err == nil { _ = helper.StringData(c, string(data)) }
+	helper.SetEventStreamHeaders(c)
+	scanner := bufio.NewScanner(resp.Body)
+	usage := &dto.Usage{}
+	var model = info.UpstreamModelName
+	var responseId = common.GetUUID()
+	var created = time.Now().Unix()
+	var toolCallIndex int
+	start := helper.GenerateStartEmptyResponse(responseId, created, model, nil)
+	if data, err := common.Marshal(start); err == nil {
+		_ = helper.StringData(c, string(data))
+	}
 
-    for scanner.Scan() {
-        line := scanner.Text()
-        line = strings.TrimSpace(line)
-        if line == "" { continue }
-        var chunk ollamaChatStreamChunk
-        if err := json.Unmarshal([]byte(line), &chunk); err != nil {
-            logger.LogError(c, "ollama stream json decode error: "+err.Error()+" line="+line)
-            return usage, types.NewOpenAIError(err, types.ErrorCodeBadResponseBody, http.StatusInternalServerError)
-        }
-        if chunk.Model != "" { model = chunk.Model }
-        created = toUnix(chunk.CreatedAt)
+	for scanner.Scan() {
+		line := scanner.Text()
+		line = strings.TrimSpace(line)
+		if line == "" {
+			continue
+		}
+		var chunk ollamaChatStreamChunk
+		if err := json.Unmarshal([]byte(line), &chunk); err != nil {
+			logger.LogError(c, "ollama stream json decode error: "+err.Error()+" line="+line)
+			return usage, types.NewOpenAIError(err, types.ErrorCodeBadResponseBody, http.StatusInternalServerError)
+		}
+		if chunk.Model != "" {
+			model = chunk.Model
+		}
+		created = toUnix(chunk.CreatedAt)
 
-        if !chunk.Done {
-            // delta content
-            var content string
-            if chunk.Message != nil { content = chunk.Message.Content } else { content = chunk.Response }
-            delta := dto.ChatCompletionsStreamResponse{
-                Id:      responseId,
-                Object:  "chat.completion.chunk",
-                Created: created,
-                Model:   model,
-                Choices: []dto.ChatCompletionsStreamResponseChoice{ {
-                    Index: 0,
-                    Delta: dto.ChatCompletionsStreamResponseChoiceDelta{ Role: "assistant" },
-                } },
-            }
-            if content != "" { delta.Choices[0].Delta.SetContentString(content) }
-            if chunk.Message != nil && len(chunk.Message.Thinking) > 0 {
-                raw := strings.TrimSpace(string(chunk.Message.Thinking))
-                if raw != "" && raw != "null" { delta.Choices[0].Delta.SetReasoningContent(raw) }
-            }
-            // tool calls
-            if chunk.Message != nil && len(chunk.Message.ToolCalls) > 0 {
-                delta.Choices[0].Delta.ToolCalls = make([]dto.ToolCallResponse,0,len(chunk.Message.ToolCalls))
-                for _, tc := range chunk.Message.ToolCalls {
-                    // arguments -> string
-                    argBytes, _ := json.Marshal(tc.Function.Arguments)
-                    toolId := fmt.Sprintf("call_%d", toolCallIndex)
-                    tr := dto.ToolCallResponse{ID:toolId, Type:"function", Function: dto.FunctionResponse{Name: tc.Function.Name, Arguments: string(argBytes)}}
-                    tr.SetIndex(toolCallIndex)
-                    toolCallIndex++
-                    delta.Choices[0].Delta.ToolCalls = append(delta.Choices[0].Delta.ToolCalls, tr)
-                }
-            }
-            if data, err := common.Marshal(delta); err == nil { _ = helper.StringData(c, string(data)) }
-            continue
-        }
-        // done frame
-        // finalize once and break loop
-        usage.PromptTokens = chunk.PromptEvalCount
-        usage.CompletionTokens = chunk.EvalCount
-        usage.TotalTokens = usage.PromptTokens + usage.CompletionTokens
-    finishReason := chunk.DoneReason
-    if finishReason == "" { finishReason = "stop" }
-        // emit stop delta
-        if stop := helper.GenerateStopResponse(responseId, created, model, finishReason); stop != nil {
-            if data, err := common.Marshal(stop); err == nil { _ = helper.StringData(c, string(data)) }
-        }
-        // emit usage frame
-        if final := helper.GenerateFinalUsageResponse(responseId, created, model, *usage); final != nil {
-            if data, err := common.Marshal(final); err == nil { _ = helper.StringData(c, string(data)) }
-        }
-        // send [DONE]
-        helper.Done(c)
-        break
-    }
-    if err := scanner.Err(); err != nil && err != io.EOF { logger.LogError(c, "ollama stream scan error: "+err.Error()) }
-    return usage, nil
+		if !chunk.Done {
+			// delta content
+			var content string
+			if chunk.Message != nil {
+				content = chunk.Message.Content
+			} else {
+				content = chunk.Response
+			}
+			delta := dto.ChatCompletionsStreamResponse{
+				Id:      responseId,
+				Object:  "chat.completion.chunk",
+				Created: created,
+				Model:   model,
+				Choices: []dto.ChatCompletionsStreamResponseChoice{{
+					Index: 0,
+					Delta: dto.ChatCompletionsStreamResponseChoiceDelta{Role: "assistant"},
+				}},
+			}
+			if content != "" {
+				delta.Choices[0].Delta.SetContentString(content)
+			}
+			if chunk.Message != nil && len(chunk.Message.Thinking) > 0 {
+				raw := strings.TrimSpace(string(chunk.Message.Thinking))
+				if raw != "" && raw != "null" {
+					delta.Choices[0].Delta.SetReasoningContent(raw)
+				}
+			}
+			// tool calls
+			if chunk.Message != nil && len(chunk.Message.ToolCalls) > 0 {
+				delta.Choices[0].Delta.ToolCalls = make([]dto.ToolCallResponse, 0, len(chunk.Message.ToolCalls))
+				for _, tc := range chunk.Message.ToolCalls {
+					// arguments -> string
+					argBytes, _ := json.Marshal(tc.Function.Arguments)
+					toolId := fmt.Sprintf("call_%d", toolCallIndex)
+					tr := dto.ToolCallResponse{ID: toolId, Type: "function", Function: dto.FunctionResponse{Name: tc.Function.Name, Arguments: string(argBytes)}}
+					tr.SetIndex(toolCallIndex)
+					toolCallIndex++
+					delta.Choices[0].Delta.ToolCalls = append(delta.Choices[0].Delta.ToolCalls, tr)
+				}
+			}
+			if data, err := common.Marshal(delta); err == nil {
+				_ = helper.StringData(c, string(data))
+			}
+			continue
+		}
+		// done frame
+		// finalize once and break loop
+		usage.PromptTokens = chunk.PromptEvalCount
+		usage.CompletionTokens = chunk.EvalCount
+		usage.TotalTokens = usage.PromptTokens + usage.CompletionTokens
+		finishReason := chunk.DoneReason
+		if finishReason == "" {
+			finishReason = "stop"
+		}
+		// emit stop delta
+		if stop := helper.GenerateStopResponse(responseId, created, model, finishReason); stop != nil {
+			if data, err := common.Marshal(stop); err == nil {
+				_ = helper.StringData(c, string(data))
+			}
+		}
+		// emit usage frame
+		if final := helper.GenerateFinalUsageResponse(responseId, created, model, *usage); final != nil {
+			if data, err := common.Marshal(final); err == nil {
+				_ = helper.StringData(c, string(data))
+			}
+		}
+		// send [DONE]
+		helper.Done(c)
+		break
+	}
+	if err := scanner.Err(); err != nil && err != io.EOF {
+		logger.LogError(c, "ollama stream scan error: "+err.Error())
+	}
+	return usage, nil
 }
 
 // non-stream handler for chat/generate
 func ollamaChatHandler(c *gin.Context, info *relaycommon.RelayInfo, resp *http.Response) (*dto.Usage, *types.NewAPIError) {
-    body, err := io.ReadAll(resp.Body)
-    if err != nil { return nil, types.NewOpenAIError(err, types.ErrorCodeReadResponseBodyFailed, http.StatusInternalServerError) }
-    service.CloseResponseBodyGracefully(resp)
-    raw := string(body)
-    if common.DebugEnabled { println("ollama non-stream raw resp:", raw) }
+	body, err := io.ReadAll(resp.Body)
+	if err != nil {
+		return nil, types.NewOpenAIError(err, types.ErrorCodeReadResponseBodyFailed, http.StatusInternalServerError)
+	}
+	service.CloseResponseBodyGracefully(resp)
+	raw := string(body)
+	if common.DebugEnabled {
+		println("ollama non-stream raw resp:", raw)
+	}
 
-    lines := strings.Split(raw, "\n")
-    var (
-        aggContent strings.Builder
-        reasoningBuilder strings.Builder
-        lastChunk ollamaChatStreamChunk
-        parsedAny bool
-    )
-    for _, ln := range lines {
-        ln = strings.TrimSpace(ln)
-        if ln == "" { continue }
-        var ck ollamaChatStreamChunk
-        if err := json.Unmarshal([]byte(ln), &ck); err != nil {
-            if len(lines) == 1 { return nil, types.NewOpenAIError(err, types.ErrorCodeBadResponseBody, http.StatusInternalServerError) }
-            continue
-        }
-        parsedAny = true
-        lastChunk = ck
-        if ck.Message != nil && len(ck.Message.Thinking) > 0 {
-            raw := strings.TrimSpace(string(ck.Message.Thinking))
-            if raw != "" && raw != "null" { reasoningBuilder.WriteString(raw) }
-        }
-        if ck.Message != nil && ck.Message.Content != "" { aggContent.WriteString(ck.Message.Content) } else if ck.Response != "" { aggContent.WriteString(ck.Response) }
-    }
+	lines := strings.Split(raw, "\n")
+	var (
+		aggContent       strings.Builder
+		reasoningBuilder strings.Builder
+		lastChunk        ollamaChatStreamChunk
+		parsedAny        bool
+	)
+	for _, ln := range lines {
+		ln = strings.TrimSpace(ln)
+		if ln == "" {
+			continue
+		}
+		var ck ollamaChatStreamChunk
+		if err := json.Unmarshal([]byte(ln), &ck); err != nil {
+			if len(lines) == 1 {
+				return nil, types.NewOpenAIError(err, types.ErrorCodeBadResponseBody, http.StatusInternalServerError)
+			}
+			continue
+		}
+		parsedAny = true
+		lastChunk = ck
+		if ck.Message != nil && len(ck.Message.Thinking) > 0 {
+			raw := strings.TrimSpace(string(ck.Message.Thinking))
+			if raw != "" && raw != "null" {
+				reasoningBuilder.WriteString(raw)
+			}
+		}
+		if ck.Message != nil && ck.Message.Content != "" {
+			aggContent.WriteString(ck.Message.Content)
+		} else if ck.Response != "" {
+			aggContent.WriteString(ck.Response)
+		}
+	}
 
-    if !parsedAny {
-        var single ollamaChatStreamChunk
-        if err := json.Unmarshal(body, &single); err != nil { return nil, types.NewOpenAIError(err, types.ErrorCodeBadResponseBody, http.StatusInternalServerError) }
-        lastChunk = single
-        if single.Message != nil {
-            if len(single.Message.Thinking) > 0 { raw := strings.TrimSpace(string(single.Message.Thinking)); if raw != "" && raw != "null" { reasoningBuilder.WriteString(raw) } }
-            aggContent.WriteString(single.Message.Content)
-        } else { aggContent.WriteString(single.Response) }
-    }
+	if !parsedAny {
+		var single ollamaChatStreamChunk
+		if err := json.Unmarshal(body, &single); err != nil {
+			return nil, types.NewOpenAIError(err, types.ErrorCodeBadResponseBody, http.StatusInternalServerError)
+		}
+		lastChunk = single
+		if single.Message != nil {
+			if len(single.Message.Thinking) > 0 {
+				raw := strings.TrimSpace(string(single.Message.Thinking))
+				if raw != "" && raw != "null" {
+					reasoningBuilder.WriteString(raw)
+				}
+			}
+			aggContent.WriteString(single.Message.Content)
+		} else {
+			aggContent.WriteString(single.Response)
+		}
+	}
 
-    model := lastChunk.Model
-    if model == "" { model = info.UpstreamModelName }
-    created := toUnix(lastChunk.CreatedAt)
-    usage := &dto.Usage{PromptTokens: lastChunk.PromptEvalCount, CompletionTokens: lastChunk.EvalCount, TotalTokens: lastChunk.PromptEvalCount + lastChunk.EvalCount}
-    content := aggContent.String()
-    finishReason := lastChunk.DoneReason
-    if finishReason == "" { finishReason = "stop" }
+	model := lastChunk.Model
+	if model == "" {
+		model = info.UpstreamModelName
+	}
+	created := toUnix(lastChunk.CreatedAt)
+	usage := &dto.Usage{PromptTokens: lastChunk.PromptEvalCount, CompletionTokens: lastChunk.EvalCount, TotalTokens: lastChunk.PromptEvalCount + lastChunk.EvalCount}
+	content := aggContent.String()
+	finishReason := lastChunk.DoneReason
+	if finishReason == "" {
+		finishReason = "stop"
+	}
 
-    msg := dto.Message{Role: "assistant", Content: contentPtr(content)}
-    if rc := reasoningBuilder.String(); rc != "" { msg.ReasoningContent = rc }
-    full := dto.OpenAITextResponse{
-        Id:      common.GetUUID(),
-        Model:   model,
-        Object:  "chat.completion",
-        Created: created,
-        Choices: []dto.OpenAITextResponseChoice{ {
-            Index: 0,
-            Message: msg,
-            FinishReason: finishReason,
-        } },
-        Usage: *usage,
-    }
-    out, _ := common.Marshal(full)
-    service.IOCopyBytesGracefully(c, resp, out)
-    return usage, nil
+	msg := dto.Message{Role: "assistant", Content: contentPtr(content)}
+	if rc := reasoningBuilder.String(); rc != "" {
+		msg.ReasoningContent = rc
+	}
+	full := dto.OpenAITextResponse{
+		Id:      common.GetUUID(),
+		Model:   model,
+		Object:  "chat.completion",
+		Created: created,
+		Choices: []dto.OpenAITextResponseChoice{{
+			Index:        0,
+			Message:      msg,
+			FinishReason: finishReason,
+		}},
+		Usage: *usage,
+	}
+	out, _ := common.Marshal(full)
+	service.IOCopyBytesGracefully(c, resp, out)
+	return usage, nil
 }
 
-func contentPtr(s string) *string { if s=="" { return nil }; return &s }
+func contentPtr(s string) *string {
+	if s == "" {
+		return nil
+	}
+	return &s
+}

relay/channel/openai/relay-openai.go

@@ -163,13 +163,10 @@ func OaiStreamHandler(c *gin.Context, info *relaycommon.RelayInfo, resp *http.Re
 	if !containStreamUsage {
 		usage = service.ResponseText2Usage(responseTextBuilder.String(), info.UpstreamModelName, info.PromptTokens)
 		usage.CompletionTokens += toolCount * 7
-	} else {
-		if info.ChannelType == constant.ChannelTypeDeepSeek {
-			if usage.PromptCacheHitTokens != 0 {
-				usage.PromptTokensDetails.CachedTokens = usage.PromptCacheHitTokens
-			}
-		}
 	}
+
+	applyUsagePostProcessing(info, usage, nil)
+
 	HandleFinalResponse(c, info, lastStreamData, responseId, createAt, model, systemFingerprint, usage, containStreamUsage)
 
 	return usage, nil
@@ -233,6 +230,8 @@ func OpenaiHandler(c *gin.Context, info *relaycommon.RelayInfo, resp *http.Respo
 		usageModified = true
 	}
 
+	applyUsagePostProcessing(info, &simpleResponse.Usage, responseBody)
+
 	switch info.RelayFormat {
 	case types.RelayFormatOpenAI:
 		if usageModified {
@@ -631,5 +630,60 @@ func OpenaiHandlerWithUsage(c *gin.Context, info *relaycommon.RelayInfo, resp *h
 		usageResp.PromptTokensDetails.ImageTokens += usageResp.InputTokensDetails.ImageTokens
 		usageResp.PromptTokensDetails.TextTokens += usageResp.InputTokensDetails.TextTokens
 	}
+	applyUsagePostProcessing(info, &usageResp.Usage, responseBody)
 	return &usageResp.Usage, nil
 }
+
+func applyUsagePostProcessing(info *relaycommon.RelayInfo, usage *dto.Usage, responseBody []byte) {
+	if info == nil || usage == nil {
+		return
+	}
+
+	switch info.ChannelType {
+	case constant.ChannelTypeDeepSeek:
+		if usage.PromptTokensDetails.CachedTokens == 0 && usage.PromptCacheHitTokens != 0 {
+			usage.PromptTokensDetails.CachedTokens = usage.PromptCacheHitTokens
+		}
+	case constant.ChannelTypeZhipu_v4:
+		if usage.PromptTokensDetails.CachedTokens == 0 {
+			if usage.InputTokensDetails != nil && usage.InputTokensDetails.CachedTokens > 0 {
+				usage.PromptTokensDetails.CachedTokens = usage.InputTokensDetails.CachedTokens
+			} else if cachedTokens, ok := extractCachedTokensFromBody(responseBody); ok {
+				usage.PromptTokensDetails.CachedTokens = cachedTokens
+			} else if usage.PromptCacheHitTokens > 0 {
+				usage.PromptTokensDetails.CachedTokens = usage.PromptCacheHitTokens
+			}
+		}
+	}
+}
+
+func extractCachedTokensFromBody(body []byte) (int, bool) {
+	if len(body) == 0 {
+		return 0, false
+	}
+
+	var payload struct {
+		Usage struct {
+			PromptTokensDetails struct {
+				CachedTokens *int `json:"cached_tokens"`
+			} `json:"prompt_tokens_details"`
+			CachedTokens         *int `json:"cached_tokens"`
+			PromptCacheHitTokens *int `json:"prompt_cache_hit_tokens"`
+		} `json:"usage"`
+	}
+
+	if err := json.Unmarshal(body, &payload); err != nil {
+		return 0, false
+	}
+
+	if payload.Usage.PromptTokensDetails.CachedTokens != nil {
+		return *payload.Usage.PromptTokensDetails.CachedTokens, true
+	}
+	if payload.Usage.CachedTokens != nil {
+		return *payload.Usage.CachedTokens, true
+	}
+	if payload.Usage.PromptCacheHitTokens != nil {
+		return *payload.Usage.PromptCacheHitTokens, true
+	}
+	return 0, false
+}

relay/channel/openai/relay_responses.go

@@ -115,7 +115,11 @@ func OaiResponsesStreamHandler(c *gin.Context, info *relaycommon.RelayInfo, resp
 				if streamResponse.Item != nil {
 					switch streamResponse.Item.Type {
 					case dto.BuildInCallWebSearchCall:
-						info.ResponsesUsageInfo.BuiltInTools[dto.BuildInToolWebSearchPreview].CallCount++
+						if info != nil && info.ResponsesUsageInfo != nil && info.ResponsesUsageInfo.BuiltInTools != nil {
+							if webSearchTool, exists := info.ResponsesUsageInfo.BuiltInTools[dto.BuildInToolWebSearchPreview]; exists && webSearchTool != nil {
+								webSearchTool.CallCount++
+							}
+						}
 					}
 				}
 			}

relay/channel/perplexity/adaptor.go

@@ -22,10 +22,9 @@ func (a *Adaptor) ConvertGeminiRequest(*gin.Context, *relaycommon.RelayInfo, *dt
 	return nil, errors.New("not implemented")
 }
 
-func (a *Adaptor) ConvertClaudeRequest(*gin.Context, *relaycommon.RelayInfo, *dto.ClaudeRequest) (any, error) {
-	//TODO implement me
-	panic("implement me")
-	return nil, nil
+func (a *Adaptor) ConvertClaudeRequest(c *gin.Context, info *relaycommon.RelayInfo, req *dto.ClaudeRequest) (any, error) {
+	adaptor := openai.Adaptor{}
+	return adaptor.ConvertClaudeRequest(c, info, req)
 }
 
 func (a *Adaptor) ConvertAudioRequest(c *gin.Context, info *relaycommon.RelayInfo, request dto.AudioRequest) (io.Reader, error) {
@@ -80,11 +79,8 @@ func (a *Adaptor) DoRequest(c *gin.Context, info *relaycommon.RelayInfo, request
 }
 
 func (a *Adaptor) DoResponse(c *gin.Context, resp *http.Response, info *relaycommon.RelayInfo) (usage any, err *types.NewAPIError) {
-	if info.IsStream {
-		usage, err = openai.OaiStreamHandler(c, info, resp)
-	} else {
-		usage, err = openai.OpenaiHandler(c, info, resp)
-	}
+	adaptor := openai.Adaptor{}
+	usage, err = adaptor.DoResponse(c, resp, info)
 	return
 }
 

relay/channel/perplexity/constants.go

@@ -2,6 +2,7 @@ package perplexity
 
 var ModelList = []string{
 	"llama-3-sonar-small-32k-chat", "llama-3-sonar-small-32k-online", "llama-3-sonar-large-32k-chat", "llama-3-sonar-large-32k-online", "llama-3-8b-instruct", "llama-3-70b-instruct", "mixtral-8x7b-instruct",
+	"sonar", "sonar-pro", "sonar-reasoning",
 }
 
 var ChannelName = "perplexity"

relay/channel/perplexity/relay-perplexity.go

@@ -11,11 +11,18 @@ func requestOpenAI2Perplexity(request dto.GeneralOpenAIRequest) *dto.GeneralOpen
 		})
 	}
 	return &dto.GeneralOpenAIRequest{
-		Model:       request.Model,
-		Stream:      request.Stream,
-		Messages:    messages,
-		Temperature: request.Temperature,
-		TopP:        request.TopP,
-		MaxTokens:   request.GetMaxTokens(),
+		Model:                  request.Model,
+		Stream:                 request.Stream,
+		Messages:               messages,
+		Temperature:            request.Temperature,
+		TopP:                   request.TopP,
+		MaxTokens:              request.GetMaxTokens(),
+		FrequencyPenalty:       request.FrequencyPenalty,
+		PresencePenalty:        request.PresencePenalty,
+		SearchDomainFilter:     request.SearchDomainFilter,
+		SearchRecencyFilter:    request.SearchRecencyFilter,
+		ReturnImages:           request.ReturnImages,
+		ReturnRelatedQuestions: request.ReturnRelatedQuestions,
+		SearchMode:             request.SearchMode,
 	}
 }

relay/channel/siliconflow/adaptor.go

@@ -61,6 +61,16 @@ func (a *Adaptor) SetupRequestHeader(c *gin.Context, req *http.Header, info *rel
 }
 
 func (a *Adaptor) ConvertOpenAIRequest(c *gin.Context, info *relaycommon.RelayInfo, request *dto.GeneralOpenAIRequest) (any, error) {
+	// SiliconFlow requires messages array for FIM requests, even if client doesn't send it
+	if (request.Prefix != nil || request.Suffix != nil) && len(request.Messages) == 0 {
+		// Add an empty user message to satisfy SiliconFlow's requirement
+		request.Messages = []dto.Message{
+			{
+				Role:    "user",
+				Content: "",
+			},
+		}
+	}
 	return request, nil
 }
 

relay/channel/submodel/constants.go

@@ -13,4 +13,4 @@ var ModelList = []string{
 	"deepseek-ai/DeepSeek-V3.1",
 }
 
-const ChannelName = "submodel"
+const ChannelName = "submodel"

relay/channel/task/doubao/adaptor.go

@@ -0,0 +1,248 @@
+package doubao
+
+import (
+	"bytes"
+	"encoding/json"
+	"fmt"
+	"io"
+	"net/http"
+	"one-api/constant"
+	"one-api/dto"
+	"one-api/model"
+	"one-api/relay/channel"
+	relaycommon "one-api/relay/common"
+	"one-api/service"
+
+	"github.com/gin-gonic/gin"
+	"github.com/pkg/errors"
+)
+
+// ============================
+// Request / Response structures
+// ============================
+
+type ContentItem struct {
+	Type     string    `json:"type"`                // "text" or "image_url"
+	Text     string    `json:"text,omitempty"`      // for text type
+	ImageURL *ImageURL `json:"image_url,omitempty"` // for image_url type
+}
+
+type ImageURL struct {
+	URL string `json:"url"`
+}
+
+type requestPayload struct {
+	Model   string        `json:"model"`
+	Content []ContentItem `json:"content"`
+}
+
+type responsePayload struct {
+	ID string `json:"id"` // task_id
+}
+
+type responseTask struct {
+	ID      string `json:"id"`
+	Model   string `json:"model"`
+	Status  string `json:"status"`
+	Content struct {
+		VideoURL string `json:"video_url"`
+	} `json:"content"`
+	Seed            int    `json:"seed"`
+	Resolution      string `json:"resolution"`
+	Duration        int    `json:"duration"`
+	Ratio           string `json:"ratio"`
+	FramesPerSecond int    `json:"framespersecond"`
+	Usage           struct {
+		CompletionTokens int `json:"completion_tokens"`
+		TotalTokens      int `json:"total_tokens"`
+	} `json:"usage"`
+	CreatedAt int64 `json:"created_at"`
+	UpdatedAt int64 `json:"updated_at"`
+}
+
+// ============================
+// Adaptor implementation
+// ============================
+
+type TaskAdaptor struct {
+	ChannelType int
+	apiKey      string
+	baseURL     string
+}
+
+func (a *TaskAdaptor) Init(info *relaycommon.RelayInfo) {
+	a.ChannelType = info.ChannelType
+	a.baseURL = info.ChannelBaseUrl
+	a.apiKey = info.ApiKey
+}
+
+// ValidateRequestAndSetAction parses body, validates fields and sets default action.
+func (a *TaskAdaptor) ValidateRequestAndSetAction(c *gin.Context, info *relaycommon.RelayInfo) (taskErr *dto.TaskError) {
+	// Accept only POST /v1/video/generations as "generate" action.
+	return relaycommon.ValidateBasicTaskRequest(c, info, constant.TaskActionGenerate)
+}
+
+// BuildRequestURL constructs the upstream URL.
+func (a *TaskAdaptor) BuildRequestURL(info *relaycommon.RelayInfo) (string, error) {
+	return fmt.Sprintf("%s/api/v3/contents/generations/tasks", a.baseURL), nil
+}
+
+// BuildRequestHeader sets required headers.
+func (a *TaskAdaptor) BuildRequestHeader(c *gin.Context, req *http.Request, info *relaycommon.RelayInfo) error {
+	req.Header.Set("Content-Type", "application/json")
+	req.Header.Set("Accept", "application/json")
+	req.Header.Set("Authorization", "Bearer "+a.apiKey)
+	return nil
+}
+
+// BuildRequestBody converts request into Doubao specific format.
+func (a *TaskAdaptor) BuildRequestBody(c *gin.Context, info *relaycommon.RelayInfo) (io.Reader, error) {
+	v, exists := c.Get("task_request")
+	if !exists {
+		return nil, fmt.Errorf("request not found in context")
+	}
+	req := v.(relaycommon.TaskSubmitReq)
+
+	body, err := a.convertToRequestPayload(&req)
+	if err != nil {
+		return nil, errors.Wrap(err, "convert request payload failed")
+	}
+	data, err := json.Marshal(body)
+	if err != nil {
+		return nil, err
+	}
+	return bytes.NewReader(data), nil
+}
+
+// DoRequest delegates to common helper.
+func (a *TaskAdaptor) DoRequest(c *gin.Context, info *relaycommon.RelayInfo, requestBody io.Reader) (*http.Response, error) {
+	return channel.DoTaskApiRequest(a, c, info, requestBody)
+}
+
+// DoResponse handles upstream response, returns taskID etc.
+func (a *TaskAdaptor) DoResponse(c *gin.Context, resp *http.Response, info *relaycommon.RelayInfo) (taskID string, taskData []byte, taskErr *dto.TaskError) {
+	responseBody, err := io.ReadAll(resp.Body)
+	if err != nil {
+		taskErr = service.TaskErrorWrapper(err, "read_response_body_failed", http.StatusInternalServerError)
+		return
+	}
+	_ = resp.Body.Close()
+
+	// Parse Doubao response
+	var dResp responsePayload
+	if err := json.Unmarshal(responseBody, &dResp); err != nil {
+		taskErr = service.TaskErrorWrapper(errors.Wrapf(err, "body: %s", responseBody), "unmarshal_response_body_failed", http.StatusInternalServerError)
+		return
+	}
+
+	if dResp.ID == "" {
+		taskErr = service.TaskErrorWrapper(fmt.Errorf("task_id is empty"), "invalid_response", http.StatusInternalServerError)
+		return
+	}
+
+	c.JSON(http.StatusOK, gin.H{"task_id": dResp.ID})
+	return dResp.ID, responseBody, nil
+}
+
+// FetchTask fetch task status
+func (a *TaskAdaptor) FetchTask(baseUrl, key string, body map[string]any) (*http.Response, error) {
+	taskID, ok := body["task_id"].(string)
+	if !ok {
+		return nil, fmt.Errorf("invalid task_id")
+	}
+
+	uri := fmt.Sprintf("%s/api/v3/contents/generations/tasks/%s", baseUrl, taskID)
+
+	req, err := http.NewRequest(http.MethodGet, uri, nil)
+	if err != nil {
+		return nil, err
+	}
+
+	req.Header.Set("Accept", "application/json")
+	req.Header.Set("Content-Type", "application/json")
+	req.Header.Set("Authorization", "Bearer "+key)
+
+	return service.GetHttpClient().Do(req)
+}
+
+func (a *TaskAdaptor) GetModelList() []string {
+	return ModelList
+}
+
+func (a *TaskAdaptor) GetChannelName() string {
+	return ChannelName
+}
+
+func (a *TaskAdaptor) convertToRequestPayload(req *relaycommon.TaskSubmitReq) (*requestPayload, error) {
+	r := requestPayload{
+		Model:   req.Model,
+		Content: []ContentItem{},
+	}
+
+	// Add text prompt
+	if req.Prompt != "" {
+		r.Content = append(r.Content, ContentItem{
+			Type: "text",
+			Text: req.Prompt,
+		})
+	}
+
+	// Add images if present
+	if req.HasImage() {
+		for _, imgURL := range req.Images {
+			r.Content = append(r.Content, ContentItem{
+				Type: "image_url",
+				ImageURL: &ImageURL{
+					URL: imgURL,
+				},
+			})
+		}
+	}
+
+	// TODO: Add support for additional parameters from metadata
+	// such as ratio, duration, seed, etc.
+	// metadata := req.Metadata
+	// if metadata != nil {
+	//     // Parse and apply metadata parameters
+	// }
+
+	return &r, nil
+}
+
+func (a *TaskAdaptor) ParseTaskResult(respBody []byte) (*relaycommon.TaskInfo, error) {
+	resTask := responseTask{}
+	if err := json.Unmarshal(respBody, &resTask); err != nil {
+		return nil, errors.Wrap(err, "unmarshal task result failed")
+	}
+
+	taskResult := relaycommon.TaskInfo{
+		Code: 0,
+	}
+
+	// Map Doubao status to internal status
+	switch resTask.Status {
+	case "pending", "queued":
+		taskResult.Status = model.TaskStatusQueued
+		taskResult.Progress = "10%"
+	case "processing":
+		taskResult.Status = model.TaskStatusInProgress
+		taskResult.Progress = "50%"
+	case "succeeded":
+		taskResult.Status = model.TaskStatusSuccess
+		taskResult.Progress = "100%"
+		taskResult.Url = resTask.Content.VideoURL
+		// 解析 usage 信息用于按倍率计费
+		taskResult.CompletionTokens = resTask.Usage.CompletionTokens
+		taskResult.TotalTokens = resTask.Usage.TotalTokens
+	case "failed":
+		taskResult.Status = model.TaskStatusFailure
+		taskResult.Progress = "100%"
+		taskResult.Reason = "task failed"
+	default:
+		// Unknown status, treat as processing
+		taskResult.Status = model.TaskStatusInProgress
+		taskResult.Progress = "30%"
+	}
+
+	return &taskResult, nil
+}

relay/channel/task/doubao/constants.go

@@ -0,0 +1,9 @@
+package doubao
+
+var ModelList = []string{
+	"doubao-seedance-1-0-pro-250528",
+	"doubao-seedance-1-0-lite-t2v",
+	"doubao-seedance-1-0-lite-i2v",
+}
+
+var ChannelName = "doubao-video"

relay/channel/task/kling/adaptor.go

@@ -7,13 +7,15 @@ import (
 	"io"
 	"net/http"
 	"one-api/model"
+	"strconv"
 	"strings"
 	"time"
 
+	"github.com/bytedance/gopkg/util/logger"
 	"github.com/samber/lo"
 
 	"github.com/gin-gonic/gin"
-	"github.com/golang-jwt/jwt"
+	"github.com/golang-jwt/jwt/v5"
 	"github.com/pkg/errors"
 
 	"one-api/constant"
@@ -303,14 +305,6 @@ func (a *TaskAdaptor) createJWTToken() (string, error) {
 	return a.createJWTTokenWithKey(a.apiKey)
 }
 
-//func (a *TaskAdaptor) createJWTTokenWithKey(apiKey string) (string, error) {
-//	parts := strings.Split(apiKey, "|")
-//	if len(parts) != 2 {
-//		return "", fmt.Errorf("invalid API key format, expected 'access_key,secret_key'")
-//	}
-//	return a.createJWTTokenWithKey(strings.TrimSpace(parts[0]), strings.TrimSpace(parts[1]))
-//}
-
 func (a *TaskAdaptor) createJWTTokenWithKey(apiKey string) (string, error) {
 	if isNewAPIRelay(apiKey) {
 		return apiKey, nil // new api relay
@@ -369,3 +363,50 @@ func (a *TaskAdaptor) ParseTaskResult(respBody []byte) (*relaycommon.TaskInfo, e
 func isNewAPIRelay(apiKey string) bool {
 	return strings.HasPrefix(apiKey, "sk-")
 }
+
+func (a *TaskAdaptor) ConvertToOpenAIVideo(originTask *model.Task) (*relaycommon.OpenAIVideo, error) {
+	var klingResp responsePayload
+	if err := json.Unmarshal(originTask.Data, &klingResp); err != nil {
+		return nil, errors.Wrap(err, "unmarshal kling task data failed")
+	}
+
+	convertProgress := func(progress string) int {
+		progress = strings.TrimSuffix(progress, "%")
+		p, err := strconv.Atoi(progress)
+		if err != nil {
+			logger.Warnf("convert progress failed, progress: %s, err: %v", progress, err)
+		}
+		return p
+	}
+
+	openAIVideo := &relaycommon.OpenAIVideo{
+		ID:     klingResp.Data.TaskId,
+		Object: "video",
+		//Model:       "kling-v1", //todo save model
+		Status:      string(originTask.Status),
+		CreatedAt:   klingResp.Data.CreatedAt,
+		CompletedAt: klingResp.Data.UpdatedAt,
+		Metadata:    make(map[string]any),
+		Progress:    convertProgress(originTask.Progress),
+	}
+
+	// 处理视频 URL
+	if len(klingResp.Data.TaskResult.Videos) > 0 {
+		video := klingResp.Data.TaskResult.Videos[0]
+		if video.Url != "" {
+			openAIVideo.Metadata["url"] = video.Url
+		}
+		if video.Duration != "" {
+			openAIVideo.Seconds = video.Duration
+		}
+	}
+
+	if klingResp.Code != 0 && klingResp.Message != "" {
+		openAIVideo.Error = &relaycommon.OpenAIVideoError{
+			Message: klingResp.Message,
+			Code:    fmt.Sprintf("%d", klingResp.Code),
+		}
+	}
+
+	return openAIVideo, nil
+}

relay/channel/task/sora/adaptor.go

@@ -0,0 +1,195 @@
+package sora
+
+import (
+	"bytes"
+	"encoding/json"
+	"fmt"
+	"io"
+	"net/http"
+	"one-api/common"
+	"one-api/dto"
+	"one-api/model"
+	"one-api/relay/channel"
+	relaycommon "one-api/relay/common"
+	"one-api/service"
+	"one-api/setting/system_setting"
+
+	"github.com/gin-gonic/gin"
+	"github.com/pkg/errors"
+)
+
+// ============================
+// Request / Response structures
+// ============================
+
+type ContentItem struct {
+	Type     string    `json:"type"`                // "text" or "image_url"
+	Text     string    `json:"text,omitempty"`      // for text type
+	ImageURL *ImageURL `json:"image_url,omitempty"` // for image_url type
+}
+
+type ImageURL struct {
+	URL string `json:"url"`
+}
+
+type responseTask struct {
+	ID                 string `json:"id"`
+	TaskID             string `json:"task_id,omitempty"` //兼容旧接口
+	Object             string `json:"object"`
+	Model              string `json:"model"`
+	Status             string `json:"status"`
+	Progress           int    `json:"progress"`
+	CreatedAt          int64  `json:"created_at"`
+	CompletedAt        int64  `json:"completed_at,omitempty"`
+	ExpiresAt          int64  `json:"expires_at,omitempty"`
+	Seconds            string `json:"seconds,omitempty"`
+	Size               string `json:"size,omitempty"`
+	RemixedFromVideoID string `json:"remixed_from_video_id,omitempty"`
+	Error              *struct {
+		Message string `json:"message"`
+		Code    string `json:"code"`
+	} `json:"error,omitempty"`
+}
+
+// ============================
+// Adaptor implementation
+// ============================
+
+type TaskAdaptor struct {
+	ChannelType int
+	apiKey      string
+	baseURL     string
+}
+
+func (a *TaskAdaptor) Init(info *relaycommon.RelayInfo) {
+	a.ChannelType = info.ChannelType
+	a.baseURL = info.ChannelBaseUrl
+	a.apiKey = info.ApiKey
+}
+
+func (a *TaskAdaptor) ValidateRequestAndSetAction(c *gin.Context, info *relaycommon.RelayInfo) (taskErr *dto.TaskError) {
+	return relaycommon.ValidateMultipartDirect(c, info)
+}
+
+func (a *TaskAdaptor) BuildRequestURL(info *relaycommon.RelayInfo) (string, error) {
+	return fmt.Sprintf("%s/v1/videos", a.baseURL), nil
+}
+
+// BuildRequestHeader sets required headers.
+func (a *TaskAdaptor) BuildRequestHeader(c *gin.Context, req *http.Request, info *relaycommon.RelayInfo) error {
+	req.Header.Set("Authorization", "Bearer "+a.apiKey)
+	req.Header.Set("Content-Type", c.Request.Header.Get("Content-Type"))
+	return nil
+}
+
+func (a *TaskAdaptor) BuildRequestBody(c *gin.Context, info *relaycommon.RelayInfo) (io.Reader, error) {
+	cachedBody, err := common.GetRequestBody(c)
+	if err != nil {
+		return nil, errors.Wrap(err, "get_request_body_failed")
+	}
+	return bytes.NewReader(cachedBody), nil
+}
+
+// DoRequest delegates to common helper.
+func (a *TaskAdaptor) DoRequest(c *gin.Context, info *relaycommon.RelayInfo, requestBody io.Reader) (*http.Response, error) {
+	return channel.DoTaskApiRequest(a, c, info, requestBody)
+}
+
+// DoResponse handles upstream response, returns taskID etc.
+func (a *TaskAdaptor) DoResponse(c *gin.Context, resp *http.Response, _ *relaycommon.RelayInfo) (taskID string, taskData []byte, taskErr *dto.TaskError) {
+	responseBody, err := io.ReadAll(resp.Body)
+	if err != nil {
+		taskErr = service.TaskErrorWrapper(err, "read_response_body_failed", http.StatusInternalServerError)
+		return
+	}
+	_ = resp.Body.Close()
+
+	// Parse Sora response
+	var dResp responseTask
+	if err := json.Unmarshal(responseBody, &dResp); err != nil {
+		taskErr = service.TaskErrorWrapper(errors.Wrapf(err, "body: %s", responseBody), "unmarshal_response_body_failed", http.StatusInternalServerError)
+		return
+	}
+
+	if dResp.ID == "" {
+		if dResp.TaskID == "" {
+			taskErr = service.TaskErrorWrapper(fmt.Errorf("task_id is empty"), "invalid_response", http.StatusInternalServerError)
+			return
+		}
+		dResp.ID = dResp.TaskID
+		dResp.TaskID = ""
+	}
+
+	c.JSON(http.StatusOK, dResp)
+	return dResp.ID, responseBody, nil
+}
+
+// FetchTask fetch task status
+func (a *TaskAdaptor) FetchTask(baseUrl, key string, body map[string]any) (*http.Response, error) {
+	taskID, ok := body["task_id"].(string)
+	if !ok {
+		return nil, fmt.Errorf("invalid task_id")
+	}
+
+	uri := fmt.Sprintf("%s/v1/videos/%s", baseUrl, taskID)
+
+	req, err := http.NewRequest(http.MethodGet, uri, nil)
+	if err != nil {
+		return nil, err
+	}
+
+	req.Header.Set("Authorization", "Bearer "+key)
+
+	return service.GetHttpClient().Do(req)
+}
+
+func (a *TaskAdaptor) GetModelList() []string {
+	return ModelList
+}
+
+func (a *TaskAdaptor) GetChannelName() string {
+	return ChannelName
+}
+
+func (a *TaskAdaptor) ParseTaskResult(respBody []byte) (*relaycommon.TaskInfo, error) {
+	resTask := responseTask{}
+	if err := json.Unmarshal(respBody, &resTask); err != nil {
+		return nil, errors.Wrap(err, "unmarshal task result failed")
+	}
+
+	taskResult := relaycommon.TaskInfo{
+		Code: 0,
+	}
+
+	switch resTask.Status {
+	case "queued", "pending":
+		taskResult.Status = model.TaskStatusQueued
+	case "processing", "in_progress":
+		taskResult.Status = model.TaskStatusInProgress
+	case "completed":
+		taskResult.Status = model.TaskStatusSuccess
+		taskResult.Url = fmt.Sprintf("%s/v1/videos/%s/content", system_setting.ServerAddress, resTask.ID)
+	case "failed", "cancelled":
+		taskResult.Status = model.TaskStatusFailure
+		if resTask.Error != nil {
+			taskResult.Reason = resTask.Error.Message
+		} else {
+			taskResult.Reason = "task failed"
+		}
+	default:
+	}
+	if resTask.Progress > 0 && resTask.Progress < 100 {
+		taskResult.Progress = fmt.Sprintf("%d%%", resTask.Progress)
+	}
+
+	return &taskResult, nil
+}
+
+func (a *TaskAdaptor) ConvertToOpenAIVideo(task *model.Task) (*relaycommon.OpenAIVideo, error) {
+	openAIVideo := &relaycommon.OpenAIVideo{}
+	err := json.Unmarshal(task.Data, openAIVideo)
+	if err != nil {
+		return nil, errors.Wrap(err, "unmarshal to OpenAIVideo failed")
+	}
+	return openAIVideo, nil
+}

relay/channel/task/sora/constants.go

@@ -0,0 +1,8 @@
+package sora
+
+var ModelList = []string{
+	"sora-2",
+	"sora-2-pro",
+}
+
+var ChannelName = "sora"

relay/channel/vertex/adaptor.go

@@ -91,7 +91,43 @@ func (a *Adaptor) getRequestUrl(info *relaycommon.RelayInfo, modelName, suffix s
 		}
 		a.AccountCredentials = *adc
 
-		if a.RequestMode == RequestModeLlama {
+		if a.RequestMode == RequestModeGemini {
+			if region == "global" {
+				return fmt.Sprintf(
+					"https://aiplatform.googleapis.com/v1/projects/%s/locations/global/publishers/google/models/%s:%s",
+					adc.ProjectID,
+					modelName,
+					suffix,
+				), nil
+			} else {
+				return fmt.Sprintf(
+					"https://%s-aiplatform.googleapis.com/v1/projects/%s/locations/%s/publishers/google/models/%s:%s",
+					region,
+					adc.ProjectID,
+					region,
+					modelName,
+					suffix,
+				), nil
+			}
+		} else if a.RequestMode == RequestModeClaude {
+			if region == "global" {
+				return fmt.Sprintf(
+					"https://aiplatform.googleapis.com/v1/projects/%s/locations/global/publishers/anthropic/models/%s:%s",
+					adc.ProjectID,
+					modelName,
+					suffix,
+				), nil
+			} else {
+				return fmt.Sprintf(
+					"https://%s-aiplatform.googleapis.com/v1/projects/%s/locations/%s/publishers/anthropic/models/%s:%s",
+					region,
+					adc.ProjectID,
+					region,
+					modelName,
+					suffix,
+				), nil
+			}
+		} else if a.RequestMode == RequestModeLlama {
 			return fmt.Sprintf(
 				"https://%s-aiplatform.googleapis.com/v1beta1/projects/%s/locations/%s/endpoints/openapi/chat/completions",
 				region,
@@ -99,42 +135,33 @@ func (a *Adaptor) getRequestUrl(info *relaycommon.RelayInfo, modelName, suffix s
 				region,
 			), nil
 		}
-
-		if region == "global" {
-			return fmt.Sprintf(
-				"https://aiplatform.googleapis.com/v1/projects/%s/locations/global/publishers/google/models/%s:%s",
-				adc.ProjectID,
-				modelName,
-				suffix,
-			), nil
-		} else {
-			return fmt.Sprintf(
-				"https://%s-aiplatform.googleapis.com/v1/projects/%s/locations/%s/publishers/google/models/%s:%s",
-				region,
-				adc.ProjectID,
-				region,
-				modelName,
-				suffix,
-			), nil
-		}
 	} else {
+		var keyPrefix string
+		if strings.HasSuffix(suffix, "?alt=sse") {
+			keyPrefix = "&"
+		} else {
+			keyPrefix = "?"
+		}
 		if region == "global" {
 			return fmt.Sprintf(
-				"https://aiplatform.googleapis.com/v1/publishers/google/models/%s:%s?key=%s",
+				"https://aiplatform.googleapis.com/v1/publishers/google/models/%s:%s%skey=%s",
 				modelName,
 				suffix,
+				keyPrefix,
 				info.ApiKey,
 			), nil
 		} else {
 			return fmt.Sprintf(
-				"https://%s-aiplatform.googleapis.com/v1/publishers/google/models/%s:%s?key=%s",
+				"https://%s-aiplatform.googleapis.com/v1/publishers/google/models/%s:%s%skey=%s",
 				region,
 				modelName,
 				suffix,
+				keyPrefix,
 				info.ApiKey,
 			), nil
 		}
 	}
+	return "", errors.New("unsupported request mode")
 }
 
 func (a *Adaptor) GetRequestURL(info *relaycommon.RelayInfo) (string, error) {
@@ -188,7 +215,7 @@ func (a *Adaptor) SetupRequestHeader(c *gin.Context, req *http.Header, info *rel
 		}
 		req.Set("Authorization", "Bearer "+accessToken)
 	}
-  if a.AccountCredentials.ProjectID != "" {
+	if a.AccountCredentials.ProjectID != "" {
 		req.Set("x-goog-user-project", a.AccountCredentials.ProjectID)
 	}
 	return nil

relay/channel/vertex/service_account.go

@@ -13,7 +13,7 @@ import (
 	"strings"
 
 	"github.com/bytedance/gopkg/cache/asynccache"
-	"github.com/golang-jwt/jwt"
+	"github.com/golang-jwt/jwt/v5"
 
 	"fmt"
 	"time"

relay/channel/zhipu/relay-zhipu.go

@@ -17,7 +17,7 @@ import (
 	"time"
 
 	"github.com/gin-gonic/gin"
-	"github.com/golang-jwt/jwt"
+	"github.com/golang-jwt/jwt/v5"
 )
 
 // https://open.bigmodel.cn/doc/api#chatglm_std

relay/claude_handler.go

@@ -112,6 +112,12 @@ func ClaudeHelper(c *gin.Context, info *relaycommon.RelayInfo) (newAPIError *typ
 			return types.NewError(err, types.ErrorCodeConvertRequestFailed, types.ErrOptionWithSkipRetry())
 		}
 
+		// remove disabled fields for Claude API
+		jsonData, err = relaycommon.RemoveDisabledFields(jsonData, info.ChannelOtherSettings)
+		if err != nil {
+			return types.NewError(err, types.ErrorCodeConvertRequestFailed, types.ErrOptionWithSkipRetry())
+		}
+
 		// apply param override
 		if len(info.ParamOverride) > 0 {
 			jsonData, err = relaycommon.ApplyParamOverride(jsonData, info.ParamOverride)

relay/common/relay_info.go

@@ -261,6 +261,7 @@ var streamSupportedChannels = map[int]bool{
 	constant.ChannelTypeXai:        true,
 	constant.ChannelTypeDeepSeek:   true,
 	constant.ChannelTypeBaiduV2:    true,
+	constant.ChannelTypeZhipu_v4:   true,
 }
 
 func GenRelayInfoWs(c *gin.Context, ws *websocket.Conn) *RelayInfo {
@@ -500,10 +501,73 @@ func (t TaskSubmitReq) HasImage() bool {
 }
 
 type TaskInfo struct {
-	Code     int    `json:"code"`
-	TaskID   string `json:"task_id"`
-	Status   string `json:"status"`
-	Reason   string `json:"reason,omitempty"`
-	Url      string `json:"url,omitempty"`
-	Progress string `json:"progress,omitempty"`
+	Code             int    `json:"code"`
+	TaskID           string `json:"task_id"`
+	Status           string `json:"status"`
+	Reason           string `json:"reason,omitempty"`
+	Url              string `json:"url,omitempty"`
+	Progress         string `json:"progress,omitempty"`
+	CompletionTokens int    `json:"completion_tokens,omitempty"` // 用于按倍率计费
+	TotalTokens      int    `json:"total_tokens,omitempty"`      // 用于按倍率计费
+}
+
+// RemoveDisabledFields 从请求 JSON 数据中移除渠道设置中禁用的字段
+// service_tier: 服务层级字段，可能导致额外计费（OpenAI、Claude、Responses API 支持）
+// store: 数据存储授权字段，涉及用户隐私（仅 OpenAI、Responses API 支持，默认允许透传，禁用后可能导致 Codex 无法使用）
+// safety_identifier: 安全标识符，用于向 OpenAI 报告违规用户（仅 OpenAI 支持，涉及用户隐私）
+func RemoveDisabledFields(jsonData []byte, channelOtherSettings dto.ChannelOtherSettings) ([]byte, error) {
+	var data map[string]interface{}
+	if err := common.Unmarshal(jsonData, &data); err != nil {
+		common.SysError("RemoveDisabledFields Unmarshal error :" + err.Error())
+		return jsonData, nil
+	}
+
+	// 默认移除 service_tier，除非明确允许（避免额外计费风险）
+	if !channelOtherSettings.AllowServiceTier {
+		if _, exists := data["service_tier"]; exists {
+			delete(data, "service_tier")
+		}
+	}
+
+	// 默认允许 store 透传，除非明确禁用（禁用可能影响 Codex 使用）
+	if channelOtherSettings.DisableStore {
+		if _, exists := data["store"]; exists {
+			delete(data, "store")
+		}
+	}
+
+	// 默认移除 safety_identifier，除非明确允许（保护用户隐私，避免向 OpenAI 报告用户信息）
+	if !channelOtherSettings.AllowSafetyIdentifier {
+		if _, exists := data["safety_identifier"]; exists {
+			delete(data, "safety_identifier")
+		}
+	}
+
+	jsonDataAfter, err := common.Marshal(data)
+	if err != nil {
+		common.SysError("RemoveDisabledFields Marshal error :" + err.Error())
+		return jsonData, nil
+	}
+	return jsonDataAfter, nil
+}
+
+type OpenAIVideo struct {
+	ID                 string            `json:"id"`
+	TaskID             string            `json:"task_id,omitempty"` //兼容旧接口 待废弃
+	Object             string            `json:"object"`
+	Model              string            `json:"model"`
+	Status             string            `json:"status"`
+	Progress           int               `json:"progress"`
+	CreatedAt          int64             `json:"created_at"`
+	CompletedAt        int64             `json:"completed_at,omitempty"`
+	ExpiresAt          int64             `json:"expires_at,omitempty"`
+	Seconds            string            `json:"seconds,omitempty"`
+	Size               string            `json:"size,omitempty"`
+	RemixedFromVideoID string            `json:"remixed_from_video_id,omitempty"`
+	Error              *OpenAIVideoError `json:"error,omitempty"`
+	Metadata           map[string]any    `json:"metadata,omitempty"`
+}
+type OpenAIVideoError struct {
+	Message string `json:"message"`
+	Code    string `json:"code"`
 }

relay/common/relay_utils.go

@@ -6,9 +6,11 @@ import (
 	"one-api/common"
 	"one-api/constant"
 	"one-api/dto"
+	"strconv"
 	"strings"
 
 	"github.com/gin-gonic/gin"
+	"github.com/samber/lo"
 )
 
 type HasPrompt interface {
@@ -52,7 +54,7 @@ func createTaskError(err error, code string, statusCode int, localError bool) *d
 	}
 }
 
-func storeTaskRequest(c *gin.Context, info *RelayInfo, action string, requestObj interface{}) {
+func storeTaskRequest(c *gin.Context, info *RelayInfo, action string, requestObj TaskSubmitReq) {
 	info.Action = action
 	c.Set("task_request", requestObj)
 }
@@ -64,9 +66,167 @@ func validatePrompt(prompt string) *dto.TaskError {
 	return nil
 }
 
-func ValidateBasicTaskRequest(c *gin.Context, info *RelayInfo, action string) *dto.TaskError {
+func validateMultipartTaskRequest(c *gin.Context, info *RelayInfo, action string) (TaskSubmitReq, error) {
 	var req TaskSubmitReq
-	if err := common.UnmarshalBodyReusable(c, &req); err != nil {
+	if _, err := c.MultipartForm(); err != nil {
+		return req, err
+	}
+
+	formData := c.Request.PostForm
+	req = TaskSubmitReq{
+		Prompt:   formData.Get("prompt"),
+		Model:    formData.Get("model"),
+		Mode:     formData.Get("mode"),
+		Image:    formData.Get("image"),
+		Size:     formData.Get("size"),
+		Metadata: make(map[string]interface{}),
+	}
+
+	if durationStr := formData.Get("seconds"); durationStr != "" {
+		if duration, err := strconv.Atoi(durationStr); err == nil {
+			req.Duration = duration
+		}
+	}
+
+	if images := formData["images"]; len(images) > 0 {
+		req.Images = images
+	}
+
+	for key, values := range formData {
+		if len(values) > 0 && !isKnownTaskField(key) {
+			if intVal, err := strconv.Atoi(values[0]); err == nil {
+				req.Metadata[key] = intVal
+			} else if floatVal, err := strconv.ParseFloat(values[0], 64); err == nil {
+				req.Metadata[key] = floatVal
+			} else {
+				req.Metadata[key] = values[0]
+			}
+		}
+	}
+	return req, nil
+}
+
+func ValidateMultipartDirect(c *gin.Context, info *RelayInfo) *dto.TaskError {
+	contentType := c.GetHeader("Content-Type")
+	var prompt string
+	var model string
+	var seconds int
+	var size string
+	var hasInputReference bool
+
+	if strings.HasPrefix(contentType, "multipart/form-data") {
+		form, err := common.ParseMultipartFormReusable(c)
+		if err != nil {
+			return createTaskError(err, "invalid_multipart_form", http.StatusBadRequest, true)
+		}
+		defer form.RemoveAll()
+
+		prompts, ok := form.Value["prompt"]
+		if !ok || len(prompts) == 0 {
+			return createTaskError(fmt.Errorf("prompt field is required"), "missing_prompt", http.StatusBadRequest, true)
+		}
+		prompt = prompts[0]
+
+		if _, ok := form.Value["model"]; !ok {
+			return createTaskError(fmt.Errorf("model field is required"), "missing_model", http.StatusBadRequest, true)
+		}
+		model = form.Value["model"][0]
+
+		if _, ok := form.File["input_reference"]; ok {
+			hasInputReference = true
+		}
+
+		if ss, ok := form.Value["seconds"]; ok {
+			sInt := common.String2Int(ss[0])
+			if sInt > seconds {
+				seconds = common.String2Int(ss[0])
+			}
+		}
+
+		if sz, ok := form.Value["size"]; ok {
+			size = sz[0]
+		}
+	} else {
+		var req TaskSubmitReq
+		if err := common.UnmarshalBodyReusable(c, &req); err != nil {
+			return createTaskError(err, "invalid_json", http.StatusBadRequest, true)
+		}
+
+		prompt = req.Prompt
+		model = req.Model
+		seconds = req.Duration
+
+		if strings.TrimSpace(req.Model) == "" {
+			return createTaskError(fmt.Errorf("model field is required"), "missing_model", http.StatusBadRequest, true)
+		}
+
+		if req.HasImage() {
+			hasInputReference = true
+		}
+	}
+
+	if taskErr := validatePrompt(prompt); taskErr != nil {
+		return taskErr
+	}
+
+	action := constant.TaskActionTextGenerate
+	if hasInputReference {
+		action = constant.TaskActionGenerate
+	}
+	if strings.HasPrefix(model, "sora-2") {
+
+		if size == "" {
+			size = "720x1280"
+		}
+
+		if seconds <= 0 {
+			seconds = 4
+		}
+
+		if model == "sora-2" && !lo.Contains([]string{"720x1280", "1280x720"}, size) {
+			return createTaskError(fmt.Errorf("sora-2 size is invalid"), "invalid_size", http.StatusBadRequest, true)
+		}
+		if model == "sora-2-pro" && !lo.Contains([]string{"720x1280", "1280x720", "1792x1024", "1024x1792"}, size) {
+			return createTaskError(fmt.Errorf("sora-2 size is invalid"), "invalid_size", http.StatusBadRequest, true)
+		}
+		info.PriceData.OtherRatios = map[string]float64{
+			"seconds": float64(seconds),
+			"size":    1,
+		}
+		if lo.Contains([]string{"1792x1024", "1024x1792"}, size) {
+			info.PriceData.OtherRatios["size"] = 1.666667
+		}
+	}
+
+	info.Action = action
+
+	return nil
+}
+
+func isKnownTaskField(field string) bool {
+	knownFields := map[string]bool{
+		"prompt":          true,
+		"model":           true,
+		"mode":            true,
+		"image":           true,
+		"images":          true,
+		"size":            true,
+		"duration":        true,
+		"input_reference": true, // Sora 特有字段
+	}
+	return knownFields[field]
+}
+
+func ValidateBasicTaskRequest(c *gin.Context, info *RelayInfo, action string) *dto.TaskError {
+	var err error
+	contentType := c.GetHeader("Content-Type")
+	var req TaskSubmitReq
+	if strings.HasPrefix(contentType, "multipart/form-data") {
+		req, err = validateMultipartTaskRequest(c, info, action)
+		if err != nil {
+			return createTaskError(err, "invalid_multipart_form", http.StatusBadRequest, true)
+		}
+	} else if err := common.UnmarshalBodyReusable(c, &req); err != nil {
 		return createTaskError(err, "invalid_request", http.StatusBadRequest, true)
 	}
 

relay/compatible_handler.go

@@ -135,6 +135,12 @@ func TextHelper(c *gin.Context, info *relaycommon.RelayInfo) (newAPIError *types
 			return types.NewError(err, types.ErrorCodeJsonMarshalFailed, types.ErrOptionWithSkipRetry())
 		}
 
+		// remove disabled fields for OpenAI API
+		jsonData, err = relaycommon.RemoveDisabledFields(jsonData, info.ChannelOtherSettings)
+		if err != nil {
+			return types.NewError(err, types.ErrorCodeConvertRequestFailed, types.ErrOptionWithSkipRetry())
+		}
+
 		// apply param override
 		if len(info.ParamOverride) > 0 {
 			jsonData, err = relaycommon.ApplyParamOverride(jsonData, info.ParamOverride)

relay/helper/price.go

@@ -114,7 +114,7 @@ func ModelPriceHelperPerCall(c *gin.Context, info *relaycommon.RelayInfo) types.
 	modelPrice, success := ratio_setting.GetModelPrice(info.OriginModelName, true)
 	// 如果没有配置价格，则使用默认价格
 	if !success {
-		defaultPrice, ok := ratio_setting.GetDefaultModelRatioMap()[info.OriginModelName]
+		defaultPrice, ok := ratio_setting.GetDefaultModelPriceMap()[info.OriginModelName]
 		if !ok {
 			modelPrice = 0.1
 		} else {

relay/helper/valid_request.go

@@ -275,7 +275,9 @@ func GetAndValidateTextRequest(c *gin.Context, relayMode int) (*dto.GeneralOpenA
 			return nil, errors.New("field prompt is required")
 		}
 	case relayconstant.RelayModeChatCompletions:
-		if len(textRequest.Messages) == 0 {
+		// For FIM (Fill-in-the-middle) requests with prefix/suffix, messages is optional
+		// It will be filled by provider-specific adaptors if needed (e.g., SiliconFlow)。Or it is allowed by model vendor(s) (e.g., DeepSeek)
+		if len(textRequest.Messages) == 0 && textRequest.Prefix == nil && textRequest.Suffix == nil {
 			return nil, errors.New("field messages is required")
 		}
 	case relayconstant.RelayModeEmbeddings:

relay/relay_adaptor.go

@@ -1,6 +1,7 @@
 package relay
 
 import (
+	"github.com/gin-gonic/gin"
 	"one-api/constant"
 	"one-api/relay/channel"
 	"one-api/relay/channel/ali"
@@ -24,8 +25,11 @@ import (
 	"one-api/relay/channel/palm"
 	"one-api/relay/channel/perplexity"
 	"one-api/relay/channel/siliconflow"
+	"one-api/relay/channel/submodel"
+	taskdoubao "one-api/relay/channel/task/doubao"
 	taskjimeng "one-api/relay/channel/task/jimeng"
 	"one-api/relay/channel/task/kling"
+	tasksora "one-api/relay/channel/task/sora"
 	"one-api/relay/channel/task/suno"
 	taskvertex "one-api/relay/channel/task/vertex"
 	taskVidu "one-api/relay/channel/task/vidu"
@@ -37,8 +41,6 @@ import (
 	"one-api/relay/channel/zhipu"
 	"one-api/relay/channel/zhipu_4v"
 	"strconv"
-    "one-api/relay/channel/submodel"
-	"github.com/gin-gonic/gin"
 )
 
 func GetAdaptor(apiType int) channel.Adaptor {
@@ -134,6 +136,10 @@ func GetTaskAdaptor(platform constant.TaskPlatform) channel.TaskAdaptor {
 			return &taskvertex.TaskAdaptor{}
 		case constant.ChannelTypeVidu:
 			return &taskVidu.TaskAdaptor{}
+		case constant.ChannelTypeDoubaoVideo:
+			return &taskdoubao.TaskAdaptor{}
+		case constant.ChannelTypeSora:
+			return &tasksora.TaskAdaptor{}
 		}
 	}
 	return nil

relay/relay_task.go

@@ -11,6 +11,7 @@ import (
 	"one-api/constant"
 	"one-api/dto"
 	"one-api/model"
+	"one-api/relay/channel"
 	relaycommon "one-api/relay/common"
 	relayconstant "one-api/relay/constant"
 	"one-api/service"
@@ -53,7 +54,7 @@ func RelayTaskSubmit(c *gin.Context, info *relaycommon.RelayInfo) (taskErr *dto.
 	}
 	modelPrice, success := ratio_setting.GetModelPrice(modelName, true)
 	if !success {
-		defaultPrice, ok := ratio_setting.GetDefaultModelRatioMap()[modelName]
+		defaultPrice, ok := ratio_setting.GetDefaultModelPriceMap()[modelName]
 		if !ok {
 			modelPrice = 0.1
 		} else {
@@ -70,6 +71,14 @@ func RelayTaskSubmit(c *gin.Context, info *relaycommon.RelayInfo) (taskErr *dto.
 	} else {
 		ratio = modelPrice * groupRatio
 	}
+	if len(info.PriceData.OtherRatios) > 0 {
+		for _, ra := range info.PriceData.OtherRatios {
+			if 1.0 != ra {
+				ratio *= ra
+			}
+		}
+	}
+	println(fmt.Sprintf("model: %s, model_price: %.4f, group: %s, group_ratio: %.4f, final_ratio: %.4f", modelName, modelPrice, info.UsingGroup, groupRatio, ratio))
 	userQuota, err := model.GetUserQuota(info.UserId, false)
 	if err != nil {
 		taskErr = service.TaskErrorWrapper(err, "get_user_quota_failed", http.StatusInternalServerError)
@@ -138,11 +147,22 @@ func RelayTaskSubmit(c *gin.Context, info *relaycommon.RelayInfo) (taskErr *dto.
 			}
 			if quota != 0 {
 				tokenName := c.GetString("token_name")
-				gRatio := groupRatio
-				if hasUserGroupRatio {
-					gRatio = userGroupRatio
+				//gRatio := groupRatio
+				//if hasUserGroupRatio {
+				//	gRatio = userGroupRatio
+				//}
+				logContent := fmt.Sprintf("操作 %s", info.Action)
+				if len(info.PriceData.OtherRatios) > 0 {
+					var contents []string
+					for key, ra := range info.PriceData.OtherRatios {
+						if 1.0 != ra {
+							contents = append(contents, fmt.Sprintf("%s: %.2f", key, ra))
+						}
+					}
+					if len(contents) > 0 {
+						logContent = fmt.Sprintf("%s, 计算参数：%s", logContent, strings.Join(contents, ", "))
+					}
 				}
-				logContent := fmt.Sprintf("模型固定价格 %.2f，分组倍率 %.2f，操作 %s", modelPrice, gRatio, info.Action)
 				other := make(map[string]interface{})
 				other["model_price"] = modelPrice
 				other["group_ratio"] = groupRatio
@@ -362,11 +382,34 @@ func videoFetchByIDRespBodyBuilder(c *gin.Context) (respBody []byte, taskResp *d
 		}
 	}()
 
-	if len(respBody) == 0 {
-		respBody, err = json.Marshal(dto.TaskResponse[any]{
-			Code: "success",
-			Data: TaskModel2Dto(originTask),
-		})
+	if len(respBody) != 0 {
+		return
+	}
+
+	if strings.HasPrefix(c.Request.RequestURI, "/v1/videos/") {
+		adaptor := GetTaskAdaptor(originTask.Platform)
+		if adaptor == nil {
+			taskResp = service.TaskErrorWrapperLocal(fmt.Errorf("invalid channel id: %d", originTask.ChannelId), "invalid_channel_id", http.StatusBadRequest)
+			return
+		}
+		if converter, ok := adaptor.(channel.OpenAIVideoConverter); ok {
+			openAIVideo, err := converter.ConvertToOpenAIVideo(originTask)
+			if err != nil {
+				taskResp = service.TaskErrorWrapper(err, "convert_to_openai_video_failed", http.StatusInternalServerError)
+				return
+			}
+			respBody, _ = json.Marshal(openAIVideo)
+			return
+		}
+		taskResp = service.TaskErrorWrapperLocal(errors.New(fmt.Sprintf("not_implemented:%s", originTask.Platform)), "not_implemented", http.StatusNotImplemented)
+		return
+	}
+	respBody, err = json.Marshal(dto.TaskResponse[any]{
+		Code: "success",
+		Data: TaskModel2Dto(originTask),
+	})
+	if err != nil {
+		taskResp = service.TaskErrorWrapper(err, "marshal_response_failed", http.StatusInternalServerError)
 	}
 	return
 }

relay/responses_handler.go

@@ -56,6 +56,13 @@ func ResponsesHelper(c *gin.Context, info *relaycommon.RelayInfo) (newAPIError *
 		if err != nil {
 			return types.NewError(err, types.ErrorCodeConvertRequestFailed, types.ErrOptionWithSkipRetry())
 		}
+
+		// remove disabled fields for OpenAI Responses API
+		jsonData, err = relaycommon.RemoveDisabledFields(jsonData, info.ChannelOtherSettings)
+		if err != nil {
+			return types.NewError(err, types.ErrorCodeConvertRequestFailed, types.ErrOptionWithSkipRetry())
+		}
+
 		// apply param override
 		if len(info.ParamOverride) > 0 {
 			jsonData, err = relaycommon.ApplyParamOverride(jsonData, info.ParamOverride)

router/api-router.go

@@ -20,6 +20,8 @@ func SetApiRouter(router *gin.Engine) {
 		apiRouter.GET("/models", middleware.UserAuth(), controller.DashboardListModels)
 		apiRouter.GET("/status/test", middleware.AdminAuth(), controller.TestStatus)
 		apiRouter.GET("/notice", controller.GetNotice)
+		apiRouter.GET("/user-agreement", controller.GetUserAgreement)
+		apiRouter.GET("/privacy-policy", controller.GetPrivacyPolicy)
 		apiRouter.GET("/about", controller.GetAbout)
 		//apiRouter.GET("/midjourney", controller.GetMidjourney)
 		apiRouter.GET("/home_page_content", controller.GetHomePageContent)
@@ -73,6 +75,7 @@ func SetApiRouter(router *gin.Engine) {
 				selfRoute.DELETE("/passkey", controller.PasskeyDelete)
 				selfRoute.GET("/aff", controller.GetAffCode)
 				selfRoute.GET("/topup/info", controller.GetTopUpInfo)
+				selfRoute.GET("/topup/self", controller.GetUserTopUps)
 				selfRoute.POST("/topup", middleware.CriticalRateLimit(), controller.TopUp)
 				selfRoute.POST("/pay", middleware.CriticalRateLimit(), controller.RequestEpay)
 				selfRoute.POST("/amount", controller.RequestAmount)
@@ -93,6 +96,8 @@ func SetApiRouter(router *gin.Engine) {
 			adminRoute.Use(middleware.AdminAuth())
 			{
 				adminRoute.GET("/", controller.GetAllUsers)
+				adminRoute.GET("/topup", controller.GetAllTopUps)
+				adminRoute.POST("/topup/complete", controller.AdminCompleteTopUp)
 				adminRoute.GET("/search", controller.SearchUsers)
 				adminRoute.GET("/:id", controller.GetUser)
 				adminRoute.POST("/", controller.CreateUser)

router/video-router.go

@@ -9,11 +9,18 @@ import (
 
 func SetVideoRouter(router *gin.Engine) {
 	videoV1Router := router.Group("/v1")
+	videoV1Router.GET("/videos/:task_id/content", controller.VideoProxy)
 	videoV1Router.Use(middleware.TokenAuth(), middleware.Distribute())
 	{
 		videoV1Router.POST("/video/generations", controller.RelayTask)
 		videoV1Router.GET("/video/generations/:task_id", controller.RelayTask)
 	}
+	// openai compatible API video routes
+	// docs: https://platform.openai.com/docs/api-reference/videos/create
+	{
+		videoV1Router.POST("/videos", controller.RelayTask)
+		videoV1Router.GET("/videos/:task_id", controller.RelayTask)
+	}
 
 	klingV1Router := router.Group("/kling/v1")
 	klingV1Router.Use(middleware.KlingRequestConvert(), middleware.TokenAuth(), middleware.Distribute())

service/channel.go

@@ -75,6 +75,8 @@ func ShouldDisableChannel(channelType int, err *types.NewAPIError) bool {
 		return true
 	case "pre_consume_token_quota_failed":
 		return true
+	case "Arrearage":
+		return true
 	}
 	switch oaiErr.Type {
 	case "insufficient_quota":

service/convert.go

@@ -636,9 +636,6 @@ func extractTextFromGeminiParts(parts []dto.GeminiPart) string {
 func ResponseOpenAI2Gemini(openAIResponse *dto.OpenAITextResponse, info *relaycommon.RelayInfo) *dto.GeminiChatResponse {
 	geminiResponse := &dto.GeminiChatResponse{
 		Candidates: make([]dto.GeminiChatCandidate, 0, len(openAIResponse.Choices)),
-		PromptFeedback: dto.GeminiChatPromptFeedback{
-			SafetyRatings: []dto.GeminiChatSafetyRating{},
-		},
 		UsageMetadata: dto.GeminiUsageMetadata{
 			PromptTokenCount:     openAIResponse.PromptTokens,
 			CandidatesTokenCount: openAIResponse.CompletionTokens,
@@ -735,9 +732,6 @@ func StreamResponseOpenAI2Gemini(openAIResponse *dto.ChatCompletionsStreamRespon
 
 	geminiResponse := &dto.GeminiChatResponse{
 		Candidates: make([]dto.GeminiChatCandidate, 0, len(openAIResponse.Choices)),
-		PromptFeedback: dto.GeminiChatPromptFeedback{
-			SafetyRatings: []dto.GeminiChatSafetyRating{},
-		},
 		UsageMetadata: dto.GeminiUsageMetadata{
 			PromptTokenCount:     info.PromptTokens,
 			CandidatesTokenCount: 0, // 流式响应中可能没有完整的 usage 信息

service/download.go

@@ -45,7 +45,7 @@ func DoWorkerRequest(req *WorkerRequest) (*http.Response, error) {
 		return nil, fmt.Errorf("failed to marshal worker payload: %v", err)
 	}
 
-	return http.Post(workerUrl, "application/json", bytes.NewBuffer(workerPayload))
+	return GetHttpClient().Post(workerUrl, "application/json", bytes.NewBuffer(workerPayload))
 }
 
 func DoDownloadRequest(originUrl string, reason ...string) (resp *http.Response, err error) {
@@ -64,6 +64,6 @@ func DoDownloadRequest(originUrl string, reason ...string) (resp *http.Response,
 		}
 
 		common.SysLog(fmt.Sprintf("downloading from origin: %s, reason: %s", common.MaskSensitiveInfo(originUrl), strings.Join(reason, ", ")))
-		return http.Get(originUrl)
+		return GetHttpClient().Get(originUrl)
 	}
 }