feat: ShouldPreserveThinkingSuffix (#2189)

fix(channel): 当没有可用密钥时返回错误而不是第一个密钥

.dockerignore

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

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

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

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

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

.github/workflows/electron-build.yml

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

.github/workflows/linux-release.yml

@@ -1,59 +0,0 @@
-name: Linux Release
-permissions:
-  contents: write
-
-on:
-  workflow_dispatch:
-    inputs:
-      name:
-        description: 'reason'
-        required: false
-  push:
-    tags:
-      - '*'
-      - '!*-alpha*'
-jobs:
-  release:
-    runs-on: ubuntu-latest
-    steps:
-      - name: Checkout
-        uses: actions/checkout@v3
-        with:
-          fetch-depth: 0
-      - uses: oven-sh/setup-bun@v2
-        with:
-          bun-version: latest
-      - name: Build Frontend
-        env:
-          CI: ""
-        run: |
-          cd web
-          bun install
-          DISABLE_ESLINT_PLUGIN='true' VITE_REACT_APP_VERSION=$(git describe --tags) bun run build
-          cd ..
-      - name: Set up Go
-        uses: actions/setup-go@v3
-        with:
-          go-version: '>=1.18.0'
-      - name: Build Backend (amd64)
-        run: |
-          go mod download
-          go build -ldflags "-s -w -X 'one-api/common.Version=$(git describe --tags)' -extldflags '-static'" -o 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 +1,136 @@
+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 'new-api/common.Version=$VERSION' -extldflags '-static'" -o new-api-$VERSION
+      - name: Build Backend (arm64)
+        run: |
+          sudo apt-get update
+          DEBIAN_FRONTEND=noninteractive sudo apt-get install -y gcc-aarch64-linux-gnu
+          VERSION=$(git describe --tags)
+          CC=aarch64-linux-gnu-gcc CGO_ENABLED=1 GOOS=linux GOARCH=arm64 go build -ldflags "-s -w -X 'new-api/common.Version=$VERSION' -extldflags '-static'" -o new-api-arm64-$VERSION
+      - name: Release
+        uses: softprops/action-gh-release@v2
+        if: startsWith(github.ref, 'refs/tags/')
+        with:
+          files: |
+            new-api-*
+        env:
+          GITHUB_TOKEN: ${{ secrets.GITHUB_TOKEN }}
+
+  macos:
+    name: macOS Release
+    runs-on: macos-latest
+    steps:
+      - name: Checkout
+        uses: actions/checkout@v3
+        with:
+          fetch-depth: 0
+      - uses: oven-sh/setup-bun@v2
+        with:
+          bun-version: latest
+      - name: Build Frontend
+        env:
+          CI: ""
+          NODE_OPTIONS: "--max-old-space-size=4096"
+        run: |
+          cd web
+          bun install
+          DISABLE_ESLINT_PLUGIN='true' VITE_REACT_APP_VERSION=$(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=$(git describe --tags)
+          go build -ldflags "-X 'new-api/common.Version=$VERSION'" -o new-api-macos-$VERSION
+      - name: Release
+        uses: softprops/action-gh-release@v2
+        if: startsWith(github.ref, 'refs/tags/')
+        with:
+          files: new-api-macos-*
+        env:
+          GITHUB_TOKEN: ${{ secrets.GITHUB_TOKEN }}
+
+  windows:
+    name: Windows Release
+    runs-on: windows-latest
+    defaults:
+      run:
+        shell: bash
+    steps:
+      - name: Checkout
+        uses: actions/checkout@v3
+        with:
+          fetch-depth: 0
+      - uses: oven-sh/setup-bun@v2
+        with:
+          bun-version: latest
+      - name: Build Frontend
+        env:
+          CI: ""
+        run: |
+          cd web
+          bun install
+          DISABLE_ESLINT_PLUGIN='true' VITE_REACT_APP_VERSION=$(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=$(git describe --tags)
+          go build -ldflags "-s -w -X 'new-api/common.Version=$VERSION'" -o new-api-$VERSION.exe
+      - name: Release
+        uses: softprops/action-gh-release@v2
+        if: startsWith(github.ref, 'refs/tags/')
+        with:
+          files: new-api-*.exe
+        env:
+          GITHUB_TOKEN: ${{ secrets.GITHUB_TOKEN }}
+
+

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

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

.github/workflows/windows-release.yml

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

@@ -1,5 +1,6 @@
 .idea
 .vscode
+.zed
 upload
 *.exe
 *.db
@@ -9,6 +10,12 @@ logs
 web/dist
 .env
 one-api
+new-api
+/__debug_bin*
 .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
 
@@ -21,15 +23,15 @@ RUN go mod download
 
 COPY . .
 COPY --from=builder /build/dist ./web/dist
-RUN go build -ldflags "-s -w -X 'one-api/common.Version=$(cat VERSION)'" -o one-api
+RUN go build -ldflags "-s -w -X 'github.com/QuantumNous/new-api/common.Version=$(cat VERSION)'" -o new-api
 
 FROM alpine
 
 RUN apk upgrade --no-cache \
-    && apk add --no-cache ca-certificates tzdata ffmpeg \
+    && apk add --no-cache ca-certificates tzdata \
     && update-ca-certificates
 
-COPY --from=builder2 /build/one-api /
+COPY --from=builder2 /build/new-api /
 EXPOSE 3000
 WORKDIR /data
-ENTRYPOINT ["/one-api"]
+ENTRYPOINT ["/new-api"]

README.en.md

@@ -89,22 +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. 🔄 Request format conversion functionality, supporting the following three format conversions:
+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
-19. 💰 Cache billing support, which allows billing at a set ratio when cache is hit:
+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:
@@ -134,14 +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`
@@ -188,7 +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
@@ -198,10 +197,11 @@ 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)
+- [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)
 

README.fr.md

@@ -89,22 +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. 🔄 Fonctionnalité de conversion de format de requête, prenant en charge les trois conversions de format suivantes :
+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
-19. 💰 Prise en charge de la facturation du cache, qui permet de facturer à un ratio défini lorsque le cache est atteint :
+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 :
@@ -134,14 +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`
@@ -188,7 +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
@@ -198,10 +197,11 @@ 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 (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)
 

README.ja.md

@@ -89,22 +89,23 @@ 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
 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. ⚡ Claude Messages形式をサポート、[APIドキュメント](https://docs.newapi.pro/api/anthropic-chat)
-14. /chat2linkルートを使用してチャット画面に入ることをサポート
-15. 🧠 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：
+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`）
-16. 🔄 思考からコンテンツへの機能
-17. 🔄 ユーザーに対するモデルレート制限機能
-18. 🔄 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：
+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
-19. 💰 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：
+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：
@@ -196,7 +197,8 @@ docker run --name new-api -d --restart always -p 3000:3000 -e SQL_DSN="root:1234
 
 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）](https://docs.newapi.pro/api/openai-chat)
+- [チャットインターフェース（Chat Completions）](https://docs.newapi.pro/api/openai-chat)
+- [レスポンスインターフェース（Responses）](https://docs.newapi.pro/api/openai-responses)
 - [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)

README.md

@@ -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：
@@ -140,6 +141,7 @@ New API提供了丰富的功能，详细特性请参考[特性说明](https://do
 - `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`
+- `TASK_PRICE_PATCH=sora-2-all,sora-2-pro-all`: 异步任务设置某些模型按次计费，多个模型用逗号分隔，例如`sora-2-all,sora-2-pro-all`，表示sora-2-all和sora-2-pro-all模型异步任务仅按次计费，不按秒等计费。
 
 ## 部署
 
@@ -164,12 +166,18 @@ New API提供了丰富的功能，详细特性请参考[特性说明](https://do
 
 #### 使用Docker Compose部署（推荐）
 ```shell
-# 下载项目
-git clone https://github.com/Calcium-Ion/new-api.git
+# 下载项目源码
+git clone https://github.com/QuantumNous/new-api.git
+
+# 进入项目目录
 cd new-api
-# 按需编辑docker-compose.yml
-# 启动
-docker-compose up -d
+
+# 根据需要编辑 docker-compose.yml 文件
+# 使用nano编辑器
+nano docker-compose.yml
+# 或使用vim编辑器
+# vim docker-compose.yml
+
 ```
 
 #### 直接使用Docker镜像
@@ -192,7 +200,8 @@ 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)

common/api_type.go

@@ -1,6 +1,6 @@
 package common
 
-import "one-api/constant"
+import "github.com/QuantumNous/new-api/constant"
 
 func ChannelType2APIType(channelType int) (int, bool) {
 	apiType := -1
@@ -69,6 +69,8 @@ func ChannelType2APIType(channelType int) (int, bool) {
 		apiType = constant.APITypeMoonshot
 	case constant.ChannelTypeSubmodel:
 		apiType = constant.APITypeSubmodel
+	case constant.ChannelTypeMiniMax:
+		apiType = constant.APITypeMiniMax
 	}
 	if apiType == -1 {
 		return constant.APITypeOpenAI, false

common/audio.go

@@ -0,0 +1,296 @@
+package common
+
+import (
+	"context"
+	"encoding/binary"
+	"fmt"
+	"io"
+
+	"github.com/abema/go-mp4"
+	"github.com/go-audio/aiff"
+	"github.com/go-audio/wav"
+	"github.com/jfreymuth/oggvorbis"
+	"github.com/mewkiz/flac"
+	"github.com/pkg/errors"
+	"github.com/tcolgate/mp3"
+	"github.com/yapingcat/gomedia/go-codec"
+)
+
+// GetAudioDuration 使用纯 Go 库获取音频文件的时长（秒）。
+// 它不再依赖外部的 ffmpeg 或 ffprobe 程序。
+func GetAudioDuration(ctx context.Context, f io.ReadSeeker, ext string) (duration float64, err error) {
+	SysLog(fmt.Sprintf("GetAudioDuration: ext=%s", ext))
+	// 根据文件扩展名选择解析器
+	switch ext {
+	case ".mp3":
+		duration, err = getMP3Duration(f)
+	case ".wav":
+		duration, err = getWAVDuration(f)
+	case ".flac":
+		duration, err = getFLACDuration(f)
+	case ".m4a", ".mp4":
+		duration, err = getM4ADuration(f)
+	case ".ogg", ".oga", ".opus":
+		duration, err = getOGGDuration(f)
+		if err != nil {
+			duration, err = getOpusDuration(f)
+		}
+	case ".aiff", ".aif", ".aifc":
+		duration, err = getAIFFDuration(f)
+	case ".webm":
+		duration, err = getWebMDuration(f)
+	case ".aac":
+		duration, err = getAACDuration(f)
+	default:
+		return 0, fmt.Errorf("unsupported audio format: %s", ext)
+	}
+	SysLog(fmt.Sprintf("GetAudioDuration: duration=%f", duration))
+	return duration, err
+}
+
+// getMP3Duration 解析 MP3 文件以获取时长。
+// 注意：对于 VBR (Variable Bitrate) MP3，这个估算可能不完全精确，但通常足够好。
+// FFmpeg 在这种情况下会扫描整个文件来获得精确值，但这里的库提供了快速估算。
+func getMP3Duration(r io.Reader) (float64, error) {
+	d := mp3.NewDecoder(r)
+	var f mp3.Frame
+	skipped := 0
+	duration := 0.0
+
+	for {
+		if err := d.Decode(&f, &skipped); err != nil {
+			if err == io.EOF {
+				break
+			}
+			return 0, errors.Wrap(err, "failed to decode mp3 frame")
+		}
+		duration += f.Duration().Seconds()
+	}
+	return duration, nil
+}
+
+// getWAVDuration 解析 WAV 文件头以获取时长。
+func getWAVDuration(r io.ReadSeeker) (float64, error) {
+	dec := wav.NewDecoder(r)
+	if !dec.IsValidFile() {
+		return 0, errors.New("invalid wav file")
+	}
+	d, err := dec.Duration()
+	if err != nil {
+		return 0, errors.Wrap(err, "failed to get wav duration")
+	}
+	return d.Seconds(), nil
+}
+
+// getFLACDuration 解析 FLAC 文件的 STREAMINFO 块。
+func getFLACDuration(r io.Reader) (float64, error) {
+	stream, err := flac.Parse(r)
+	if err != nil {
+		return 0, errors.Wrap(err, "failed to parse flac stream")
+	}
+	defer stream.Close()
+
+	// 时长 = 总采样数 / 采样率
+	duration := float64(stream.Info.NSamples) / float64(stream.Info.SampleRate)
+	return duration, nil
+}
+
+// getM4ADuration 解析 M4A/MP4 文件的 'mvhd' box。
+func getM4ADuration(r io.ReadSeeker) (float64, error) {
+	// go-mp4 库需要 ReadSeeker 接口
+	info, err := mp4.Probe(r)
+	if err != nil {
+		return 0, errors.Wrap(err, "failed to probe m4a/mp4 file")
+	}
+	// 时长 = Duration / Timescale
+	return float64(info.Duration) / float64(info.Timescale), nil
+}
+
+// getOGGDuration 解析 OGG/Vorbis 文件以获取时长。
+func getOGGDuration(r io.ReadSeeker) (float64, error) {
+	// 重置 reader 到开头
+	if _, err := r.Seek(0, io.SeekStart); err != nil {
+		return 0, errors.Wrap(err, "failed to seek ogg file")
+	}
+
+	reader, err := oggvorbis.NewReader(r)
+	if err != nil {
+		return 0, errors.Wrap(err, "failed to create ogg vorbis reader")
+	}
+
+	// 计算时长 = 总采样数 / 采样率
+	// 需要读取整个文件来获取总采样数
+	channels := reader.Channels()
+	sampleRate := reader.SampleRate()
+
+	// 估算方法：读取到文件结尾
+	var totalSamples int64
+	buf := make([]float32, 4096*channels)
+	for {
+		n, err := reader.Read(buf)
+		if err == io.EOF {
+			break
+		}
+		if err != nil {
+			return 0, errors.Wrap(err, "failed to read ogg samples")
+		}
+		totalSamples += int64(n / channels)
+	}
+
+	duration := float64(totalSamples) / float64(sampleRate)
+	return duration, nil
+}
+
+// getOpusDuration 解析 Opus 文件（在 OGG 容器中）以获取时长。
+func getOpusDuration(r io.ReadSeeker) (float64, error) {
+	// Opus 通常封装在 OGG 容器中
+	// 我们需要解析 OGG 页面来获取时长信息
+	if _, err := r.Seek(0, io.SeekStart); err != nil {
+		return 0, errors.Wrap(err, "failed to seek opus file")
+	}
+
+	// 读取 OGG 页面头部
+	var totalGranulePos int64
+	buf := make([]byte, 27) // OGG 页面头部最小大小
+
+	for {
+		n, err := r.Read(buf)
+		if err == io.EOF {
+			break
+		}
+		if err != nil {
+			return 0, errors.Wrap(err, "failed to read opus/ogg page")
+		}
+		if n < 27 {
+			break
+		}
+
+		// 检查 OGG 页面标识 "OggS"
+		if string(buf[0:4]) != "OggS" {
+			// 跳过一些字节继续寻找
+			if _, err := r.Seek(-26, io.SeekCurrent); err != nil {
+				break
+			}
+			continue
+		}
+
+		// 读取 granule position (字节 6-13, 小端序)
+		granulePos := int64(binary.LittleEndian.Uint64(buf[6:14]))
+		if granulePos > totalGranulePos {
+			totalGranulePos = granulePos
+		}
+
+		// 读取段表大小
+		numSegments := int(buf[26])
+		segmentTable := make([]byte, numSegments)
+		if _, err := io.ReadFull(r, segmentTable); err != nil {
+			break
+		}
+
+		// 计算页面数据大小并跳过
+		var pageSize int
+		for _, segSize := range segmentTable {
+			pageSize += int(segSize)
+		}
+		if _, err := r.Seek(int64(pageSize), io.SeekCurrent); err != nil {
+			break
+		}
+	}
+
+	// Opus 的采样率固定为 48000 Hz
+	duration := float64(totalGranulePos) / 48000.0
+	return duration, nil
+}
+
+// getAIFFDuration 解析 AIFF 文件头以获取时长。
+func getAIFFDuration(r io.ReadSeeker) (float64, error) {
+	if _, err := r.Seek(0, io.SeekStart); err != nil {
+		return 0, errors.Wrap(err, "failed to seek aiff file")
+	}
+
+	dec := aiff.NewDecoder(r)
+	if !dec.IsValidFile() {
+		return 0, errors.New("invalid aiff file")
+	}
+
+	d, err := dec.Duration()
+	if err != nil {
+		return 0, errors.Wrap(err, "failed to get aiff duration")
+	}
+
+	return d.Seconds(), nil
+}
+
+// getWebMDuration 解析 WebM 文件以获取时长。
+// WebM 使用 Matroska 容器格式
+func getWebMDuration(r io.ReadSeeker) (float64, error) {
+	if _, err := r.Seek(0, io.SeekStart); err != nil {
+		return 0, errors.Wrap(err, "failed to seek webm file")
+	}
+
+	// WebM/Matroska 文件的解析比较复杂
+	// 这里提供一个简化的实现，读取 EBML 头部
+	// 对于完整的 WebM 解析，可能需要使用专门的库
+
+	// 简单实现：查找 Duration 元素
+	// WebM Duration 的 Element ID 是 0x4489
+	// 这是一个简化版本，可能不适用于所有 WebM 文件
+	buf := make([]byte, 8192)
+	n, err := r.Read(buf)
+	if err != nil && err != io.EOF {
+		return 0, errors.Wrap(err, "failed to read webm file")
+	}
+
+	// 尝试查找 Duration 元素（这是一个简化的方法）
+	// 实际的 WebM 解析需要完整的 EBML 解析器
+	// 这里返回错误，建议使用专门的库
+	if n > 0 {
+		// 检查 EBML 标识
+		if len(buf) >= 4 && binary.BigEndian.Uint32(buf[0:4]) == 0x1A45DFA3 {
+			// 这是一个有效的 EBML 文件
+			// 但完整解析需要更复杂的逻辑
+			return 0, errors.New("webm duration parsing requires full EBML parser (consider using ffprobe for webm files)")
+		}
+	}
+
+	return 0, errors.New("failed to parse webm file")
+}
+
+// getAACDuration 解析 AAC (ADTS格式) 文件以获取时长。
+// 使用 gomedia 库来解析 AAC ADTS 帧
+func getAACDuration(r io.ReadSeeker) (float64, error) {
+	if _, err := r.Seek(0, io.SeekStart); err != nil {
+		return 0, errors.Wrap(err, "failed to seek aac file")
+	}
+
+	// 读取整个文件内容
+	data, err := io.ReadAll(r)
+	if err != nil {
+		return 0, errors.Wrap(err, "failed to read aac file")
+	}
+
+	var totalFrames int64
+	var sampleRate int
+
+	// 使用 gomedia 的 SplitAACFrame 函数来分割 AAC 帧
+	codec.SplitAACFrame(data, func(aac []byte) {
+		// 解析 ADTS 头部以获取采样率信息
+		if len(aac) >= 7 {
+			// 使用 ConvertADTSToASC 来获取音频配置信息
+			asc, err := codec.ConvertADTSToASC(aac)
+			if err == nil && sampleRate == 0 {
+				sampleRate = codec.AACSampleIdxToSample(int(asc.Sample_freq_index))
+			}
+			totalFrames++
+		}
+	})
+
+	if sampleRate == 0 || totalFrames == 0 {
+		return 0, errors.New("no valid aac frames found")
+	}
+
+	// 每个 AAC ADTS 帧包含 1024 个采样
+	totalSamples := totalFrames * 1024
+	duration := float64(totalSamples) / float64(sampleRate)
+	return duration, nil
+}

common/constants.go

@@ -159,14 +159,15 @@ var (
 	GlobalWebRateLimitNum      int
 	GlobalWebRateLimitDuration int64
 
+	CriticalRateLimitEnable   bool
+	CriticalRateLimitNum            = 20
+	CriticalRateLimitDuration int64 = 20 * 60
+
 	UploadRateLimitNum            = 10
 	UploadRateLimitDuration int64 = 60
 
 	DownloadRateLimitNum            = 10
 	DownloadRateLimitDuration int64 = 60
-
-	CriticalRateLimitNum            = 20
-	CriticalRateLimitDuration int64 = 20 * 60
 )
 
 var RateLimitKeyExpirationDuration = 20 * time.Minute

common/crypto.go

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

common/email.go

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

common/embed-file-system.go

@@ -2,9 +2,10 @@ package common
 
 import (
 	"embed"
-	"github.com/gin-contrib/static"
 	"io/fs"
 	"net/http"
+
+	"github.com/gin-contrib/static"
 )
 
 // Credit: https://github.com/gin-contrib/static/issues/19

common/endpoint_defaults.go

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

common/endpoint_type.go

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

common/gin.go

@@ -3,11 +3,14 @@ package common
 import (
 	"bytes"
 	"io"
+	"mime/multipart"
 	"net/http"
-	"one-api/constant"
+	"net/url"
 	"strings"
 	"time"
 
+	"github.com/QuantumNous/new-api/constant"
+
 	"github.com/gin-gonic/gin"
 )
 
@@ -37,7 +40,11 @@ func UnmarshalBodyReusable(c *gin.Context, v any) error {
 	//}
 	contentType := c.Request.Header.Get("Content-Type")
 	if strings.HasPrefix(contentType, "application/json") {
-		err = Unmarshal(requestBody, &v)
+		err = Unmarshal(requestBody, v)
+	} else if strings.Contains(contentType, gin.MIMEPOSTForm) {
+		err = parseFormData(requestBody, v)
+	} else if strings.Contains(contentType, gin.MIMEMultipartPOSTForm) {
+		err = parseMultipartFormData(c, requestBody, v)
 	} else {
 		// skip for now
 		// TODO: someday non json request have variant model, we will need to implementation this
@@ -113,3 +120,86 @@ 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
+}
+
+func processFormMap(formMap map[string]any, v any) error {
+	jsonData, err := Marshal(formMap)
+	if err != nil {
+		return err
+	}
+
+	err = Unmarshal(jsonData, v)
+	if err != nil {
+		return err
+	}
+
+	return nil
+}
+
+func parseFormData(data []byte, v any) error {
+	values, err := url.ParseQuery(string(data))
+	if err != nil {
+		return err
+	}
+	formMap := make(map[string]any)
+	for key, vals := range values {
+		if len(vals) == 1 {
+			formMap[key] = vals[0]
+		} else {
+			formMap[key] = vals
+		}
+	}
+
+	return processFormMap(formMap, v)
+}
+
+func parseMultipartFormData(c *gin.Context, data []byte, v any) error {
+	contentType := c.Request.Header.Get("Content-Type")
+	boundary := ""
+	if idx := strings.Index(contentType, "boundary="); idx != -1 {
+		boundary = contentType[idx+9:]
+	}
+
+	if boundary == "" {
+		return Unmarshal(data, v) // Fallback to JSON
+	}
+
+	reader := multipart.NewReader(bytes.NewReader(data), boundary)
+	form, err := reader.ReadForm(32 << 20) // 32 MB max memory
+	if err != nil {
+		return err
+	}
+	defer form.RemoveAll()
+	formMap := make(map[string]any)
+	for key, vals := range form.Value {
+		if len(vals) == 1 {
+			formMap[key] = vals[0]
+		} else {
+			formMap[key] = vals
+		}
+	}
+
+	return processFormMap(formMap, v)
+}

common/gopool.go

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

common/init.go

@@ -4,11 +4,13 @@ import (
 	"flag"
 	"fmt"
 	"log"
-	"one-api/constant"
 	"os"
 	"path/filepath"
 	"strconv"
+	"strings"
 	"time"
+
+	"github.com/QuantumNous/new-api/constant"
 )
 
 var (
@@ -19,10 +21,10 @@ var (
 )
 
 func printHelp() {
-	fmt.Println("New API " + Version + " - All in one API service for OpenAI API.")
-	fmt.Println("Copyright (C) 2023 JustSong. All rights reserved.")
-	fmt.Println("GitHub: https://github.com/songquanpeng/one-api")
-	fmt.Println("Usage: one-api [--port <port>] [--log-dir <log directory>] [--version] [--help]")
+	fmt.Println("NewAPI(Based OneAPI) " + Version + " - The next-generation LLM gateway and AI asset management system supports multiple languages.")
+	fmt.Println("Original Project: OneAPI by JustSong - https://github.com/songquanpeng/one-api")
+	fmt.Println("Maintainer: QuantumNous - https://github.com/QuantumNous/new-api")
+	fmt.Println("Usage: newapi [--port <port>] [--log-dir <log directory>] [--version] [--help]")
 }
 
 func InitEnv() {
@@ -97,6 +99,9 @@ func InitEnv() {
 	GlobalWebRateLimitNum = GetEnvOrDefault("GLOBAL_WEB_RATE_LIMIT", 60)
 	GlobalWebRateLimitDuration = int64(GetEnvOrDefault("GLOBAL_WEB_RATE_LIMIT_DURATION", 180))
 
+	CriticalRateLimitEnable = GetEnvOrDefaultBool("CRITICAL_RATE_LIMIT_ENABLE", true)
+	CriticalRateLimitNum = GetEnvOrDefault("CRITICAL_RATE_LIMIT", 20)
+	CriticalRateLimitDuration = int64(GetEnvOrDefault("CRITICAL_RATE_LIMIT_DURATION", 20*60))
 	initConstantEnv()
 }
 
@@ -117,4 +122,17 @@ func initConstantEnv() {
 	constant.GenerateDefaultToken = GetEnvOrDefaultBool("GENERATE_DEFAULT_TOKEN", false)
 	// 是否启用错误日志
 	constant.ErrorLogEnabled = GetEnvOrDefaultBool("ERROR_LOG_ENABLED", false)
+
+	soraPatchStr := GetEnvOrDefaultString("TASK_PRICE_PATCH", "")
+	if soraPatchStr != "" {
+		var taskPricePatches []string
+		soraPatches := strings.Split(soraPatchStr, ",")
+		for _, patch := range soraPatches {
+			trimmedPatch := strings.TrimSpace(patch)
+			if trimmedPatch != "" {
+				taskPricePatches = append(taskPricePatches, trimmedPatch)
+			}
+		}
+		constant.TaskPricePatches = taskPricePatches
+	}
 }

common/json.go

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

common/limiter/limiter.go

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

common/pprof.go

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

common/utils.go

@@ -1,8 +1,6 @@
 package common
 
 import (
-	"bytes"
-	"context"
 	crand "crypto/rand"
 	"encoding/base64"
 	"encoding/json"
@@ -232,10 +230,6 @@ func GetUUID() string {
 
 const keyChars = "0123456789abcdefghijklmnopqrstuvwxyzABCDEFGHIJKLMNOPQRSTUVWXYZ"
 
-func init() {
-	rand.New(rand.NewSource(time.Now().UnixNano()))
-}
-
 func GenerateRandomCharsKey(length int) (string, error) {
 	b := make([]byte, length)
 	maxI := big.NewInt(int64(len(keyChars)))
@@ -329,43 +323,6 @@ func SaveTmpFile(filename string, data io.Reader) (string, error) {
 	return f.Name(), nil
 }
 
-// GetAudioDuration returns the duration of an audio file in seconds.
-func GetAudioDuration(ctx context.Context, filename string, ext string) (float64, error) {
-	// ffprobe -v error -show_entries format=duration -of default=noprint_wrappers=1:nokey=1 {{input}}
-	c := exec.CommandContext(ctx, "ffprobe", "-v", "error", "-show_entries", "format=duration", "-of", "default=noprint_wrappers=1:nokey=1", filename)
-	output, err := c.Output()
-	if err != nil {
-		return 0, errors.Wrap(err, "failed to get audio duration")
-	}
-	durationStr := string(bytes.TrimSpace(output))
-	if durationStr == "N/A" {
-		// Create a temporary output file name
-		tmpFp, err := os.CreateTemp("", "audio-*"+ext)
-		if err != nil {
-			return 0, errors.Wrap(err, "failed to create temporary file")
-		}
-		tmpName := tmpFp.Name()
-		// Close immediately so ffmpeg can open the file on Windows.
-		_ = tmpFp.Close()
-		defer os.Remove(tmpName)
-
-		// ffmpeg -y -i filename -vcodec copy -acodec copy <tmpName>
-		ffmpegCmd := exec.CommandContext(ctx, "ffmpeg", "-y", "-i", filename, "-vcodec", "copy", "-acodec", "copy", tmpName)
-		if err := ffmpegCmd.Run(); err != nil {
-			return 0, errors.Wrap(err, "failed to run ffmpeg")
-		}
-
-		// Recalculate the duration of the new file
-		c = exec.CommandContext(ctx, "ffprobe", "-v", "error", "-show_entries", "format=duration", "-of", "default=noprint_wrappers=1:nokey=1", tmpName)
-		output, err := c.Output()
-		if err != nil {
-			return 0, errors.Wrap(err, "failed to get audio duration after ffmpeg")
-		}
-		durationStr = string(bytes.TrimSpace(output))
-	}
-	return strconv.ParseFloat(durationStr, 64)
-}
-
 // BuildURL concatenates base and endpoint, returns the complete url string
 func BuildURL(base string, endpoint string) string {
 	u, err := url.Parse(base)

common/verification.go

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

constant/api_type.go

@@ -33,5 +33,6 @@ const (
 	APITypeJimeng
 	APITypeMoonshot
 	APITypeSubmodel
+	APITypeMiniMax
 	APITypeDummy // this one is only for count, do not add any channel after this
 )

constant/channel.go

@@ -52,6 +52,7 @@ const (
 	ChannelTypeVidu           = 52
 	ChannelTypeSubmodel       = 53
 	ChannelTypeDoubaoVideo    = 54
+	ChannelTypeSora           = 55
 	ChannelTypeDummy          // this one is only for count, do not add any channel after this
 
 )
@@ -112,6 +113,7 @@ var ChannelBaseURLs = []string{
 	"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{
@@ -166,6 +168,7 @@ var ChannelTypeNames = map[int]string{
 	ChannelTypeVidu:           "Vidu",
 	ChannelTypeSubmodel:       "Submodel",
 	ChannelTypeDoubaoVideo:    "DoubaoVideo",
+	ChannelTypeSora:           "Sora",
 }
 
 func GetChannelTypeName(channelType int) string {

constant/endpoint_type.go

@@ -10,6 +10,7 @@ const (
 	EndpointTypeJinaRerank      EndpointType = "jina-rerank"
 	EndpointTypeImageGeneration EndpointType = "image-generation"
 	EndpointTypeEmbeddings      EndpointType = "embeddings"
+	EndpointTypeOpenAIVideo     EndpointType = "openai-video"
 	//EndpointTypeMidjourney     EndpointType = "midjourney-proxy"
 	//EndpointTypeSuno           EndpointType = "suno-proxy"
 	//EndpointTypeKling          EndpointType = "kling"

constant/env.go

@@ -13,3 +13,6 @@ var NotifyLimitCount int
 var NotificationLimitDurationMinute int
 var GenerateDefaultToken bool
 var ErrorLogEnabled bool
+
+// temporary variable for sora patch, will be removed in future
+var TaskPricePatches []string

controller/billing.go

@@ -1,11 +1,11 @@
 package controller
 
 import (
+	"github.com/QuantumNous/new-api/common"
+	"github.com/QuantumNous/new-api/dto"
+	"github.com/QuantumNous/new-api/model"
+	"github.com/QuantumNous/new-api/setting/operation_setting"
 	"github.com/gin-gonic/gin"
-	"one-api/common"
-	"one-api/dto"
-	"one-api/model"
-	"one-api/setting/operation_setting"
 )
 
 func GetSubscription(c *gin.Context) {

controller/channel-billing.go

@@ -6,15 +6,16 @@ import (
 	"fmt"
 	"io"
 	"net/http"
-	"one-api/common"
-	"one-api/constant"
-	"one-api/model"
-	"one-api/service"
-	"one-api/setting/operation_setting"
-	"one-api/types"
 	"strconv"
 	"time"
 
+	"github.com/QuantumNous/new-api/common"
+	"github.com/QuantumNous/new-api/constant"
+	"github.com/QuantumNous/new-api/model"
+	"github.com/QuantumNous/new-api/service"
+	"github.com/QuantumNous/new-api/setting/operation_setting"
+	"github.com/QuantumNous/new-api/types"
+
 	"github.com/shopspring/decimal"
 
 	"github.com/gin-gonic/gin"
@@ -127,6 +128,14 @@ func GetAuthHeader(token string) http.Header {
 	return h
 }
 
+// GetClaudeAuthHeader get claude auth header
+func GetClaudeAuthHeader(token string) http.Header {
+	h := http.Header{}
+	h.Add("x-api-key", token)
+	h.Add("anthropic-version", "2023-06-01")
+	return h
+}
+
 func GetResponseBody(method, url string, channel *model.Channel, headers http.Header) ([]byte, error) {
 	req, err := http.NewRequest(method, url, nil)
 	if err != nil {

controller/channel-test.go

@@ -10,23 +10,24 @@ import (
 	"net/http"
 	"net/http/httptest"
 	"net/url"
-	"one-api/common"
-	"one-api/constant"
-	"one-api/dto"
-	"one-api/middleware"
-	"one-api/model"
-	"one-api/relay"
-	relaycommon "one-api/relay/common"
-	relayconstant "one-api/relay/constant"
-	"one-api/relay/helper"
-	"one-api/service"
-	"one-api/setting/operation_setting"
-	"one-api/types"
 	"strconv"
 	"strings"
 	"sync"
 	"time"
 
+	"github.com/QuantumNous/new-api/common"
+	"github.com/QuantumNous/new-api/constant"
+	"github.com/QuantumNous/new-api/dto"
+	"github.com/QuantumNous/new-api/middleware"
+	"github.com/QuantumNous/new-api/model"
+	"github.com/QuantumNous/new-api/relay"
+	relaycommon "github.com/QuantumNous/new-api/relay/common"
+	relayconstant "github.com/QuantumNous/new-api/relay/constant"
+	"github.com/QuantumNous/new-api/relay/helper"
+	"github.com/QuantumNous/new-api/service"
+	"github.com/QuantumNous/new-api/setting/operation_setting"
+	"github.com/QuantumNous/new-api/types"
+
 	"github.com/bytedance/gopkg/util/gopool"
 	"github.com/samber/lo"
 
@@ -59,6 +60,21 @@ func testChannel(channel *model.Channel, testModel string, endpointType string)
 	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
@@ -90,18 +106,6 @@ 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{
@@ -613,16 +617,20 @@ func TestAllChannels(c *gin.Context) {
 var autoTestChannelsOnce sync.Once
 
 func AutomaticallyTestChannels() {
+	// 只在Master节点定时测试渠道
+	if !common.IsMasterNode {
+		return
+	}
 	autoTestChannelsOnce.Do(func() {
 		for {
 			if !operation_setting.GetMonitorSetting().AutoTestChannelEnabled {
-				time.Sleep(10 * time.Minute)
+				time.Sleep(1 * time.Minute)
 				continue
 			}
-			frequency := operation_setting.GetMonitorSetting().AutoTestChannelMinutes
-			common.SysLog(fmt.Sprintf("automatically test channels with interval %d minutes", frequency))
 			for {
-				time.Sleep(time.Duration(frequency) * time.Minute)
+				frequency := operation_setting.GetMonitorSetting().AutoTestChannelMinutes
+				time.Sleep(time.Duration(int(math.Round(frequency))) * time.Minute)
+				common.SysLog(fmt.Sprintf("automatically test channels with interval %f minutes", frequency))
 				common.SysLog("automatically testing all channels")
 				_ = testAllChannels(false)
 				common.SysLog("automatically channel test finished")

controller/channel.go

@@ -4,14 +4,15 @@ import (
 	"encoding/json"
 	"fmt"
 	"net/http"
-	"one-api/common"
-	"one-api/constant"
-	"one-api/dto"
-	"one-api/model"
-	"one-api/service"
 	"strconv"
 	"strings"
 
+	"github.com/QuantumNous/new-api/common"
+	"github.com/QuantumNous/new-api/constant"
+	"github.com/QuantumNous/new-api/dto"
+	"github.com/QuantumNous/new-api/model"
+	"github.com/QuantumNous/new-api/service"
+
 	"github.com/gin-gonic/gin"
 )
 
@@ -198,9 +199,10 @@ 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 {
@@ -647,13 +649,15 @@ func DeleteDisabledChannel(c *gin.Context) {
 }
 
 type ChannelTag struct {
-	Tag          string  `json:"tag"`
-	NewTag       *string `json:"new_tag"`
-	Priority     *int64  `json:"priority"`
-	Weight       *uint   `json:"weight"`
-	ModelMapping *string `json:"model_mapping"`
-	Models       *string `json:"models"`
-	Groups       *string `json:"groups"`
+	Tag            string  `json:"tag"`
+	NewTag         *string `json:"new_tag"`
+	Priority       *int64  `json:"priority"`
+	Weight         *uint   `json:"weight"`
+	ModelMapping   *string `json:"model_mapping"`
+	Models         *string `json:"models"`
+	Groups         *string `json:"groups"`
+	ParamOverride  *string `json:"param_override"`
+	HeaderOverride *string `json:"header_override"`
 }
 
 func DisableTagChannels(c *gin.Context) {
@@ -719,7 +723,29 @@ func EditTagChannels(c *gin.Context) {
 		})
 		return
 	}
-	err = model.EditChannelByTag(channelTag.Tag, channelTag.NewTag, channelTag.ModelMapping, channelTag.Models, channelTag.Groups, channelTag.Priority, channelTag.Weight)
+	if channelTag.ParamOverride != nil {
+		trimmed := strings.TrimSpace(*channelTag.ParamOverride)
+		if trimmed != "" && !json.Valid([]byte(trimmed)) {
+			c.JSON(http.StatusOK, gin.H{
+				"success": false,
+				"message": "参数覆盖必须是合法的 JSON 格式",
+			})
+			return
+		}
+		channelTag.ParamOverride = common.GetPointer[string](trimmed)
+	}
+	if channelTag.HeaderOverride != nil {
+		trimmed := strings.TrimSpace(*channelTag.HeaderOverride)
+		if trimmed != "" && !json.Valid([]byte(trimmed)) {
+			c.JSON(http.StatusOK, gin.H{
+				"success": false,
+				"message": "请求头覆盖必须是合法的 JSON 格式",
+			})
+			return
+		}
+		channelTag.HeaderOverride = common.GetPointer[string](trimmed)
+	}
+	err = model.EditChannelByTag(channelTag.Tag, channelTag.NewTag, channelTag.ModelMapping, channelTag.Models, channelTag.Groups, channelTag.Priority, channelTag.Weight, channelTag.ParamOverride, channelTag.HeaderOverride)
 	if err != nil {
 		common.ApiError(c, err)
 		return

controller/console_migrate.go

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

controller/github.go

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

controller/group.go

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

controller/linuxdo.go

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

controller/log.go

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

controller/midjourney.go

@@ -7,15 +7,16 @@ import (
 	"fmt"
 	"io"
 	"net/http"
-	"one-api/common"
-	"one-api/dto"
-	"one-api/logger"
-	"one-api/model"
-	"one-api/service"
-	"one-api/setting"
-	"one-api/setting/system_setting"
 	"time"
 
+	"github.com/QuantumNous/new-api/common"
+	"github.com/QuantumNous/new-api/dto"
+	"github.com/QuantumNous/new-api/logger"
+	"github.com/QuantumNous/new-api/model"
+	"github.com/QuantumNous/new-api/service"
+	"github.com/QuantumNous/new-api/setting"
+	"github.com/QuantumNous/new-api/setting/system_setting"
+
 	"github.com/gin-gonic/gin"
 )
 

controller/misc.go

@@ -4,16 +4,17 @@ import (
 	"encoding/json"
 	"fmt"
 	"net/http"
-	"one-api/common"
-	"one-api/constant"
-	"one-api/middleware"
-	"one-api/model"
-	"one-api/setting"
-	"one-api/setting/console_setting"
-	"one-api/setting/operation_setting"
-	"one-api/setting/system_setting"
 	"strings"
 
+	"github.com/QuantumNous/new-api/common"
+	"github.com/QuantumNous/new-api/constant"
+	"github.com/QuantumNous/new-api/middleware"
+	"github.com/QuantumNous/new-api/model"
+	"github.com/QuantumNous/new-api/setting"
+	"github.com/QuantumNous/new-api/setting/console_setting"
+	"github.com/QuantumNous/new-api/setting/operation_setting"
+	"github.com/QuantumNous/new-api/setting/system_setting"
+
 	"github.com/gin-gonic/gin"
 )
 
@@ -43,6 +44,7 @@ func GetStatus(c *gin.Context) {
 	defer common.OptionMapRWMutex.RUnlock()
 
 	passkeySetting := system_setting.GetPasskeySettings()
+	legalSetting := system_setting.GetLegalSettings()
 
 	data := gin.H{
 		"version":                     common.Version,
@@ -108,6 +110,8 @@ 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
@@ -151,6 +155,24 @@ 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/missing_models.go

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

controller/model.go

@@ -2,21 +2,22 @@ package controller
 
 import (
 	"fmt"
+	"net/http"
+	"time"
+
+	"github.com/QuantumNous/new-api/common"
+	"github.com/QuantumNous/new-api/constant"
+	"github.com/QuantumNous/new-api/dto"
+	"github.com/QuantumNous/new-api/model"
+	"github.com/QuantumNous/new-api/relay"
+	"github.com/QuantumNous/new-api/relay/channel/ai360"
+	"github.com/QuantumNous/new-api/relay/channel/lingyiwanwu"
+	"github.com/QuantumNous/new-api/relay/channel/minimax"
+	"github.com/QuantumNous/new-api/relay/channel/moonshot"
+	relaycommon "github.com/QuantumNous/new-api/relay/common"
+	"github.com/QuantumNous/new-api/service"
 	"github.com/gin-gonic/gin"
 	"github.com/samber/lo"
-	"net/http"
-	"one-api/common"
-	"one-api/constant"
-	"one-api/dto"
-	"one-api/model"
-	"one-api/relay"
-	"one-api/relay/channel/ai360"
-	"one-api/relay/channel/lingyiwanwu"
-	"one-api/relay/channel/minimax"
-	"one-api/relay/channel/moonshot"
-	relaycommon "one-api/relay/common"
-	"one-api/setting"
-	"time"
 )
 
 // https://platform.openai.com/docs/api-reference/models/list
@@ -148,7 +149,7 @@ func ListModels(c *gin.Context, modelType int) {
 		}
 		var models []string
 		if tokenGroup == "auto" {
-			for _, autoGroup := range setting.AutoGroups {
+			for _, autoGroup := range service.GetUserAutoGroup(userGroup) {
 				groupModels := model.GetGroupEnabledModels(autoGroup)
 				for _, g := range groupModels {
 					if !common.StringsContains(models, g) {

controller/model_meta.go

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

controller/model_sync.go

@@ -13,8 +13,8 @@ import (
 	"sync"
 	"time"
 
-	"one-api/common"
-	"one-api/model"
+	"github.com/QuantumNous/new-api/common"
+	"github.com/QuantumNous/new-api/model"
 
 	"github.com/gin-gonic/gin"
 	"gorm.io/gorm"

controller/oidc.go

@@ -6,13 +6,14 @@ import (
 	"fmt"
 	"net/http"
 	"net/url"
-	"one-api/common"
-	"one-api/model"
-	"one-api/setting/system_setting"
 	"strconv"
 	"strings"
 	"time"
 
+	"github.com/QuantumNous/new-api/common"
+	"github.com/QuantumNous/new-api/model"
+	"github.com/QuantumNous/new-api/setting/system_setting"
+
 	"github.com/gin-contrib/sessions"
 	"github.com/gin-gonic/gin"
 )

controller/option.go

@@ -4,14 +4,15 @@ import (
 	"encoding/json"
 	"fmt"
 	"net/http"
-	"one-api/common"
-	"one-api/model"
-	"one-api/setting"
-	"one-api/setting/console_setting"
-	"one-api/setting/ratio_setting"
-	"one-api/setting/system_setting"
 	"strings"
 
+	"github.com/QuantumNous/new-api/common"
+	"github.com/QuantumNous/new-api/model"
+	"github.com/QuantumNous/new-api/setting"
+	"github.com/QuantumNous/new-api/setting/console_setting"
+	"github.com/QuantumNous/new-api/setting/ratio_setting"
+	"github.com/QuantumNous/new-api/setting/system_setting"
+
 	"github.com/gin-gonic/gin"
 )
 

controller/passkey.go

@@ -7,10 +7,10 @@ import (
 	"strconv"
 	"time"
 
-	"one-api/common"
-	"one-api/model"
-	passkeysvc "one-api/service/passkey"
-	"one-api/setting/system_setting"
+	"github.com/QuantumNous/new-api/common"
+	"github.com/QuantumNous/new-api/model"
+	passkeysvc "github.com/QuantumNous/new-api/service/passkey"
+	"github.com/QuantumNous/new-api/setting/system_setting"
 
 	"github.com/gin-contrib/sessions"
 	"github.com/gin-gonic/gin"

controller/playground.go

@@ -3,13 +3,14 @@ package controller
 import (
 	"errors"
 	"fmt"
-	"one-api/common"
-	"one-api/constant"
-	"one-api/middleware"
-	"one-api/model"
-	"one-api/types"
 	"time"
 
+	"github.com/QuantumNous/new-api/common"
+	"github.com/QuantumNous/new-api/constant"
+	"github.com/QuantumNous/new-api/middleware"
+	"github.com/QuantumNous/new-api/model"
+	"github.com/QuantumNous/new-api/types"
+
 	"github.com/gin-gonic/gin"
 )
 
@@ -30,7 +31,7 @@ func Playground(c *gin.Context) {
 		return
 	}
 
-	group := c.GetString("group")
+	group := common.GetContextKeyString(c, constant.ContextKeyUsingGroup)
 	modelName := c.GetString("original_model")
 
 	userId := c.GetInt("id")

controller/prefill_group.go

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

controller/pricing.go

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

controller/ratio_config.go

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

controller/ratio_sync.go

@@ -7,14 +7,15 @@ import (
 	"io"
 	"net"
 	"net/http"
-	"one-api/logger"
 	"strings"
 	"sync"
 	"time"
 
-	"one-api/dto"
-	"one-api/model"
-	"one-api/setting/ratio_setting"
+	"github.com/QuantumNous/new-api/logger"
+
+	"github.com/QuantumNous/new-api/dto"
+	"github.com/QuantumNous/new-api/model"
+	"github.com/QuantumNous/new-api/setting/ratio_setting"
 
 	"github.com/gin-gonic/gin"
 )

controller/redemption.go

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

controller/relay.go

@@ -6,21 +6,22 @@ import (
 	"io"
 	"log"
 	"net/http"
-	"one-api/common"
-	"one-api/constant"
-	"one-api/dto"
-	"one-api/logger"
-	"one-api/middleware"
-	"one-api/model"
-	"one-api/relay"
-	relaycommon "one-api/relay/common"
-	relayconstant "one-api/relay/constant"
-	"one-api/relay/helper"
-	"one-api/service"
-	"one-api/setting"
-	"one-api/types"
 	"strings"
 
+	"github.com/QuantumNous/new-api/common"
+	"github.com/QuantumNous/new-api/constant"
+	"github.com/QuantumNous/new-api/dto"
+	"github.com/QuantumNous/new-api/logger"
+	"github.com/QuantumNous/new-api/middleware"
+	"github.com/QuantumNous/new-api/model"
+	"github.com/QuantumNous/new-api/relay"
+	relaycommon "github.com/QuantumNous/new-api/relay/common"
+	relayconstant "github.com/QuantumNous/new-api/relay/constant"
+	"github.com/QuantumNous/new-api/relay/helper"
+	"github.com/QuantumNous/new-api/service"
+	"github.com/QuantumNous/new-api/setting"
+	"github.com/QuantumNous/new-api/types"
+
 	"github.com/bytedance/gopkg/util/gopool"
 
 	"github.com/gin-gonic/gin"
@@ -83,6 +84,7 @@ func Relay(c *gin.Context, relayFormat types.RelayFormat) {
 
 	defer func() {
 		if newAPIError != nil {
+			logger.LogError(c, fmt.Sprintf("relay error: %s", newAPIError.Error()))
 			newAPIError.SetMessage(common.MessageWithRequestId(newAPIError.Error(), requestId))
 			switch relayFormat {
 			case types.RelayFormatOpenAIRealtime:
@@ -139,9 +141,13 @@ func Relay(c *gin.Context, relayFormat types.RelayFormat) {
 
 	// common.SetContextKey(c, constant.ContextKeyTokenCountMeta, meta)
 
-	newAPIError = service.PreConsumeQuota(c, priceData.ShouldPreConsumedQuota, relayInfo)
-	if newAPIError != nil {
-		return
+	if priceData.FreeModel {
+		logger.LogInfo(c, fmt.Sprintf("模型 %s 免费，跳过预扣费", relayInfo.OriginModelName))
+	} else {
+		newAPIError = service.PreConsumeQuota(c, priceData.QuotaToPreConsume, relayInfo)
+		if newAPIError != nil {
+			return
+		}
 	}
 
 	defer func() {
@@ -219,12 +225,12 @@ func getChannel(c *gin.Context, group, originalModel string, retryCount int) (*m
 			AutoBan: &autoBanInt,
 		}, nil
 	}
-	channel, selectGroup, err := model.CacheGetRandomSatisfiedChannel(c, group, originalModel, retryCount)
+	channel, selectGroup, err := service.CacheGetRandomSatisfiedChannel(c, group, originalModel, retryCount)
 	if err != nil {
 		return nil, types.NewError(fmt.Errorf("获取分组 %s 下模型 %s 的可用渠道失败（retry）: %s", selectGroup, originalModel, err.Error()), types.ErrorCodeGetChannelFailed, types.ErrOptionWithSkipRetry())
 	}
 	if channel == nil {
-		return nil, types.NewError(fmt.Errorf("分组 %s 下模型 %s 的可用渠道不存在（数据库一致性已被破坏，retry）", selectGroup, originalModel), types.ErrorCodeGetChannelFailed, types.ErrOptionWithSkipRetry())
+		return nil, types.NewError(fmt.Errorf("分组 %s 下模型 %s 的可用渠道不存在（retry）", selectGroup, originalModel), types.ErrorCodeGetChannelFailed, types.ErrOptionWithSkipRetry())
 	}
 	newAPIError := middleware.SetupContextForSelectedChannel(c, channel, originalModel)
 	if newAPIError != nil {
@@ -276,7 +282,7 @@ func shouldRetry(c *gin.Context, openaiErr *types.NewAPIError, retryTimes int) b
 }
 
 func processChannelError(c *gin.Context, channelError types.ChannelError, err *types.NewAPIError) {
-	logger.LogError(c, fmt.Sprintf("relay error (channel #%d, status code: %d): %s", channelError.ChannelId, err.StatusCode, err.Error()))
+	logger.LogError(c, fmt.Sprintf("channel error (channel #%d, status code: %d): %s", channelError.ChannelId, err.StatusCode, err.Error()))
 	// 不要使用context获取渠道信息，异步处理时可能会出现渠道信息不一致的情况
 	// do not use context to get channel info, there may be inconsistent channel info when processing asynchronously
 	if service.ShouldDisableChannel(channelError.ChannelId, err) && channelError.AutoBan {
@@ -294,6 +300,9 @@ func processChannelError(c *gin.Context, channelError types.ChannelError, err *t
 		userGroup := c.GetString("group")
 		channelId := c.GetInt("channel_id")
 		other := make(map[string]interface{})
+		if c.Request != nil && c.Request.URL != nil {
+			other["request_path"] = c.Request.URL.Path
+		}
 		other["error_type"] = err.GetErrorType()
 		other["error_code"] = err.GetErrorCode()
 		other["status_code"] = err.StatusCode

controller/secure_verification.go

@@ -3,12 +3,13 @@ package controller
 import (
 	"fmt"
 	"net/http"
-	"one-api/common"
-	"one-api/model"
-	passkeysvc "one-api/service/passkey"
-	"one-api/setting/system_setting"
 	"time"
 
+	"github.com/QuantumNous/new-api/common"
+	"github.com/QuantumNous/new-api/model"
+	passkeysvc "github.com/QuantumNous/new-api/service/passkey"
+	"github.com/QuantumNous/new-api/setting/system_setting"
+
 	"github.com/gin-contrib/sessions"
 	"github.com/gin-gonic/gin"
 )

controller/setup.go

@@ -1,12 +1,13 @@
 package controller
 
 import (
-	"github.com/gin-gonic/gin"
-	"one-api/common"
-	"one-api/constant"
-	"one-api/model"
-	"one-api/setting/operation_setting"
 	"time"
+
+	"github.com/QuantumNous/new-api/common"
+	"github.com/QuantumNous/new-api/constant"
+	"github.com/QuantumNous/new-api/model"
+	"github.com/QuantumNous/new-api/setting/operation_setting"
+	"github.com/gin-gonic/gin"
 )
 
 type Setup struct {

controller/task.go

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

controller/task_video.go

@@ -5,16 +5,17 @@ import (
 	"encoding/json"
 	"fmt"
 	"io"
-	"one-api/common"
-	"one-api/constant"
-	"one-api/dto"
-	"one-api/logger"
-	"one-api/model"
-	"one-api/relay"
-	"one-api/relay/channel"
-	relaycommon "one-api/relay/common"
-	"one-api/setting/ratio_setting"
 	"time"
+
+	"github.com/QuantumNous/new-api/common"
+	"github.com/QuantumNous/new-api/constant"
+	"github.com/QuantumNous/new-api/dto"
+	"github.com/QuantumNous/new-api/logger"
+	"github.com/QuantumNous/new-api/model"
+	"github.com/QuantumNous/new-api/relay"
+	"github.com/QuantumNous/new-api/relay/channel"
+	relaycommon "github.com/QuantumNous/new-api/relay/common"
+	"github.com/QuantumNous/new-api/setting/ratio_setting"
 )
 
 func UpdateVideoTaskAll(ctx context.Context, platform constant.TaskPlatform, taskChannelM map[int][]string, taskM map[string]*model.Task) error {
@@ -47,6 +48,11 @@ 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()))
@@ -82,26 +88,39 @@ func updateVideoSingleTask(ctx context.Context, adaptor channel.TaskAdaptor, cha
 		return fmt.Errorf("readAll failed for task %s: %w", taskId, err)
 	}
 
+	logger.LogDebug(ctx, fmt.Sprintf("UpdateVideoSingleTask response: %s", string(responseBody)))
+
 	taskResult := &relaycommon.TaskInfo{}
 	// try parse as New API response format
 	var responseItems dto.TaskResponse[model.Task]
-	if err = json.Unmarshal(responseBody, &responseItems); err == nil && responseItems.IsSuccess() {
+	if err = common.Unmarshal(responseBody, &responseItems); err == nil && responseItems.IsSuccess() {
+		logger.LogDebug(ctx, fmt.Sprintf("UpdateVideoSingleTask parsed as new api response format: %+v", responseItems))
 		t := responseItems.Data
 		taskResult.TaskID = t.TaskID
 		taskResult.Status = string(t.Status)
 		taskResult.Url = t.FailReason
 		taskResult.Progress = t.Progress
 		taskResult.Reason = t.FailReason
+		task.Data = t.Data
 	} else if taskResult, err = adaptor.ParseTaskResult(responseBody); err != nil {
 		return fmt.Errorf("parseTaskResult failed for task %s: %w", taskId, err)
 	} else {
 		task.Data = redactVideoResponseBody(responseBody)
 	}
 
+	logger.LogDebug(ctx, fmt.Sprintf("UpdateVideoSingleTask taskResult: %+v", taskResult))
+
 	now := time.Now().Unix()
 	if taskResult.Status == "" {
-		return fmt.Errorf("task %s status is empty", taskId)
+		//return fmt.Errorf("task %s status is empty", taskId)
+		taskResult = relaycommon.FailTaskInfo("upstream returned empty status")
 	}
+
+	// 记录原本的状态，防止重复退款
+	shouldRefund := false
+	quota := task.Quota
+	preStatus := task.Status
+
 	task.Status = model.TaskStatus(taskResult.Status)
 	switch taskResult.Status {
 	case model.TaskStatusSubmitted:
@@ -130,14 +149,19 @@ func updateVideoSingleTask(ctx context.Context, adaptor channel.TaskAdaptor, cha
 				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)
+						group := task.Group
+						if group == "" {
+							user, err := model.GetUserById(task.UserId, false)
+							if err == nil {
+								group = user.Group
+							}
+						}
+						if group != "" {
+							groupRatio := ratio_setting.GetGroupRatio(group)
+							userGroupRatio, hasUserGroupRatio := ratio_setting.GetGroupGroupRatio(group, group)
 
 							var finalGroupRatio float64
 							if hasUserGroupRatio {
@@ -207,6 +231,7 @@ func updateVideoSingleTask(ctx context.Context, adaptor channel.TaskAdaptor, cha
 			}
 		}
 	case model.TaskStatusFailure:
+		logger.LogJson(ctx, fmt.Sprintf("Task %s failed", taskId), task)
 		task.Status = model.TaskStatusFailure
 		task.Progress = "100%"
 		if task.FinishTime == 0 {
@@ -214,13 +239,13 @@ func updateVideoSingleTask(ctx context.Context, adaptor channel.TaskAdaptor, cha
 		}
 		task.FailReason = taskResult.Reason
 		logger.LogInfo(ctx, fmt.Sprintf("Task %s failed: %s", task.TaskID, task.FailReason))
-		quota := task.Quota
+		taskResult.Progress = "100%"
 		if quota != 0 {
-			if err := model.IncreaseUserQuota(task.UserId, quota, false); err != nil {
-				logger.LogError(ctx, "Failed to increase user quota: "+err.Error())
+			if preStatus != model.TaskStatusFailure {
+				shouldRefund = true
+			} else {
+				logger.LogWarn(ctx, fmt.Sprintf("Task %s already in failure status, skip refund", task.TaskID))
 			}
-			logContent := fmt.Sprintf("Video async task failed %s, refund %s", task.TaskID, logger.LogQuota(quota))
-			model.RecordLog(task.UserId, model.LogTypeSystem, logContent)
 		}
 	default:
 		return fmt.Errorf("unknown task status %s for task %s", taskResult.Status, taskId)
@@ -230,6 +255,16 @@ func updateVideoSingleTask(ctx context.Context, adaptor channel.TaskAdaptor, cha
 	}
 	if err := task.Update(); err != nil {
 		common.SysLog("UpdateVideoTask task error: " + err.Error())
+		shouldRefund = false
+	}
+
+	if shouldRefund {
+		// 任务失败且之前状态不是失败才退还额度，防止重复退还
+		if err := model.IncreaseUserQuota(task.UserId, quota, false); err != nil {
+			logger.LogWarn(ctx, "Failed to increase user quota: "+err.Error())
+		}
+		logContent := fmt.Sprintf("Video async task failed %s, refund %s", task.TaskID, logger.LogQuota(quota))
+		model.RecordLog(task.UserId, model.LogTypeSystem, logContent)
 	}
 
 	return nil

controller/telegram.go

@@ -6,10 +6,11 @@ import (
 	"encoding/hex"
 	"io"
 	"net/http"
-	"one-api/common"
-	"one-api/model"
 	"sort"
 
+	"github.com/QuantumNous/new-api/common"
+	"github.com/QuantumNous/new-api/model"
+
 	"github.com/gin-contrib/sessions"
 	"github.com/gin-gonic/gin"
 )

controller/token.go

@@ -2,11 +2,12 @@ package controller
 
 import (
 	"net/http"
-	"one-api/common"
-	"one-api/model"
 	"strconv"
 	"strings"
 
+	"github.com/QuantumNous/new-api/common"
+	"github.com/QuantumNous/new-api/model"
+
 	"github.com/gin-gonic/gin"
 )
 

controller/topup.go

@@ -4,17 +4,18 @@ import (
 	"fmt"
 	"log"
 	"net/url"
-	"one-api/common"
-	"one-api/logger"
-	"one-api/model"
-	"one-api/service"
-	"one-api/setting"
-	"one-api/setting/operation_setting"
-	"one-api/setting/system_setting"
 	"strconv"
 	"sync"
 	"time"
 
+	"github.com/QuantumNous/new-api/common"
+	"github.com/QuantumNous/new-api/logger"
+	"github.com/QuantumNous/new-api/model"
+	"github.com/QuantumNous/new-api/service"
+	"github.com/QuantumNous/new-api/setting"
+	"github.com/QuantumNous/new-api/setting/operation_setting"
+	"github.com/QuantumNous/new-api/setting/system_setting"
+
 	"github.com/Calcium-Ion/go-epay/epay"
 	"github.com/gin-gonic/gin"
 	"github.com/samber/lo"
@@ -50,6 +51,8 @@ func GetTopUpInfo(c *gin.Context) {
 	data := gin.H{
 		"enable_online_topup": operation_setting.PayAddress != "" && operation_setting.EpayId != "" && operation_setting.EpayKey != "",
 		"enable_stripe_topup": setting.StripeApiSecret != "" && setting.StripeWebhookSecret != "" && setting.StripePriceId != "",
+		"enable_creem_topup":  setting.CreemApiKey != "" && setting.CreemProducts != "[]",
+		"creem_products":      setting.CreemProducts,
 		"pay_methods":         payMethods,
 		"min_topup":           operation_setting.MinTopUp,
 		"stripe_min_topup":    setting.StripeMinTopUp,
@@ -183,12 +186,13 @@ func RequestEpay(c *gin.Context) {
 		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 {
@@ -236,8 +240,8 @@ 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 {
@@ -313,3 +317,76 @@ 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_creem.go

@@ -0,0 +1,461 @@
+package controller
+
+import (
+	"bytes"
+	"crypto/hmac"
+	"crypto/sha256"
+	"encoding/hex"
+	"encoding/json"
+	"fmt"
+	"io"
+	"log"
+	"net/http"
+	"github.com/QuantumNous/new-api/common"
+	"github.com/QuantumNous/new-api/model"
+	"github.com/QuantumNous/new-api/setting"
+	"time"
+
+	"github.com/gin-gonic/gin"
+	"github.com/thanhpk/randstr"
+)
+
+const (
+	PaymentMethodCreem   = "creem"
+	CreemSignatureHeader = "creem-signature"
+)
+
+var creemAdaptor = &CreemAdaptor{}
+
+// 生成HMAC-SHA256签名
+func generateCreemSignature(payload string, secret string) string {
+	h := hmac.New(sha256.New, []byte(secret))
+	h.Write([]byte(payload))
+	return hex.EncodeToString(h.Sum(nil))
+}
+
+// 验证Creem webhook签名
+func verifyCreemSignature(payload string, signature string, secret string) bool {
+	if secret == "" {
+		log.Printf("Creem webhook secret not set")
+		if setting.CreemTestMode {
+			log.Printf("Skip Creem webhook sign verify in test mode")
+			return true
+		}
+		return false
+	}
+
+	expectedSignature := generateCreemSignature(payload, secret)
+	return hmac.Equal([]byte(signature), []byte(expectedSignature))
+}
+
+type CreemPayRequest struct {
+	ProductId     string `json:"product_id"`
+	PaymentMethod string `json:"payment_method"`
+}
+
+type CreemProduct struct {
+	ProductId string  `json:"productId"`
+	Name      string  `json:"name"`
+	Price     float64 `json:"price"`
+	Currency  string  `json:"currency"`
+	Quota     int64   `json:"quota"`
+}
+
+type CreemAdaptor struct {
+}
+
+func (*CreemAdaptor) RequestPay(c *gin.Context, req *CreemPayRequest) {
+	if req.PaymentMethod != PaymentMethodCreem {
+		c.JSON(200, gin.H{"message": "error", "data": "不支持的支付渠道"})
+		return
+	}
+
+	if req.ProductId == "" {
+		c.JSON(200, gin.H{"message": "error", "data": "请选择产品"})
+		return
+	}
+
+	// 解析产品列表
+	var products []CreemProduct
+	err := json.Unmarshal([]byte(setting.CreemProducts), &products)
+	if err != nil {
+		log.Println("解析Creem产品列表失败", err)
+		c.JSON(200, gin.H{"message": "error", "data": "产品配置错误"})
+		return
+	}
+
+	// 查找对应的产品
+	var selectedProduct *CreemProduct
+	for _, product := range products {
+		if product.ProductId == req.ProductId {
+			selectedProduct = &product
+			break
+		}
+	}
+
+	if selectedProduct == nil {
+		c.JSON(200, gin.H{"message": "error", "data": "产品不存在"})
+		return
+	}
+
+	id := c.GetInt("id")
+	user, _ := model.GetUserById(id, false)
+
+	// 生成唯一的订单引用ID
+	reference := fmt.Sprintf("creem-api-ref-%d-%d-%s", user.Id, time.Now().UnixMilli(), randstr.String(4))
+	referenceId := "ref_" + common.Sha1([]byte(reference))
+
+	// 先创建订单记录，使用产品配置的金额和充值额度
+	topUp := &model.TopUp{
+		UserId:     id,
+		Amount:     selectedProduct.Quota, // 充值额度
+		Money:      selectedProduct.Price, // 支付金额
+		TradeNo:    referenceId,
+		CreateTime: time.Now().Unix(),
+		Status:     common.TopUpStatusPending,
+	}
+	err = topUp.Insert()
+	if err != nil {
+		log.Printf("创建Creem订单失败: %v", err)
+		c.JSON(200, gin.H{"message": "error", "data": "创建订单失败"})
+		return
+	}
+
+	// 创建支付链接，传入用户邮箱
+	checkoutUrl, err := genCreemLink(referenceId, selectedProduct, user.Email, user.Username)
+	if err != nil {
+		log.Printf("获取Creem支付链接失败: %v", err)
+		c.JSON(200, gin.H{"message": "error", "data": "拉起支付失败"})
+		return
+	}
+
+	log.Printf("Creem订单创建成功 - 用户ID: %d, 订单号: %s, 产品: %s, 充值额度: %d, 支付金额: %.2f",
+		id, referenceId, selectedProduct.Name, selectedProduct.Quota, selectedProduct.Price)
+
+	c.JSON(200, gin.H{
+		"message": "success",
+		"data": gin.H{
+			"checkout_url": checkoutUrl,
+			"order_id":     referenceId,
+		},
+	})
+}
+
+func RequestCreemPay(c *gin.Context) {
+	var req CreemPayRequest
+
+	// 读取body内容用于打印，同时保留原始数据供后续使用
+	bodyBytes, err := io.ReadAll(c.Request.Body)
+	if err != nil {
+		log.Printf("read creem pay req body err: %v", err)
+		c.JSON(200, gin.H{"message": "error", "data": "read query error"})
+		return
+	}
+
+	// 打印body内容
+	log.Printf("creem pay request body: %s", string(bodyBytes))
+
+	// 重新设置body供后续的ShouldBindJSON使用
+	c.Request.Body = io.NopCloser(bytes.NewReader(bodyBytes))
+
+	err = c.ShouldBindJSON(&req)
+	if err != nil {
+		c.JSON(200, gin.H{"message": "error", "data": "参数错误"})
+		return
+	}
+	creemAdaptor.RequestPay(c, &req)
+}
+
+// 新的Creem Webhook结构体，匹配实际的webhook数据格式
+type CreemWebhookEvent struct {
+	Id        string `json:"id"`
+	EventType string `json:"eventType"`
+	CreatedAt int64  `json:"created_at"`
+	Object    struct {
+		Id        string `json:"id"`
+		Object    string `json:"object"`
+		RequestId string `json:"request_id"`
+		Order     struct {
+			Object      string `json:"object"`
+			Id          string `json:"id"`
+			Customer    string `json:"customer"`
+			Product     string `json:"product"`
+			Amount      int    `json:"amount"`
+			Currency    string `json:"currency"`
+			SubTotal    int    `json:"sub_total"`
+			TaxAmount   int    `json:"tax_amount"`
+			AmountDue   int    `json:"amount_due"`
+			AmountPaid  int    `json:"amount_paid"`
+			Status      string `json:"status"`
+			Type        string `json:"type"`
+			Transaction string `json:"transaction"`
+			CreatedAt   string `json:"created_at"`
+			UpdatedAt   string `json:"updated_at"`
+			Mode        string `json:"mode"`
+		} `json:"order"`
+		Product struct {
+			Id                string  `json:"id"`
+			Object            string  `json:"object"`
+			Name              string  `json:"name"`
+			Description       string  `json:"description"`
+			Price             int     `json:"price"`
+			Currency          string  `json:"currency"`
+			BillingType       string  `json:"billing_type"`
+			BillingPeriod     string  `json:"billing_period"`
+			Status            string  `json:"status"`
+			TaxMode           string  `json:"tax_mode"`
+			TaxCategory       string  `json:"tax_category"`
+			DefaultSuccessUrl *string `json:"default_success_url"`
+			CreatedAt         string  `json:"created_at"`
+			UpdatedAt         string  `json:"updated_at"`
+			Mode              string  `json:"mode"`
+		} `json:"product"`
+		Units    int `json:"units"`
+		Customer struct {
+			Id        string `json:"id"`
+			Object    string `json:"object"`
+			Email     string `json:"email"`
+			Name      string `json:"name"`
+			Country   string `json:"country"`
+			CreatedAt string `json:"created_at"`
+			UpdatedAt string `json:"updated_at"`
+			Mode      string `json:"mode"`
+		} `json:"customer"`
+		Status   string            `json:"status"`
+		Metadata map[string]string `json:"metadata"`
+		Mode     string            `json:"mode"`
+	} `json:"object"`
+}
+
+// 保留旧的结构体作为兼容
+type CreemWebhookData struct {
+	Type string `json:"type"`
+	Data struct {
+		RequestId string            `json:"request_id"`
+		Status    string            `json:"status"`
+		Metadata  map[string]string `json:"metadata"`
+	} `json:"data"`
+}
+
+func CreemWebhook(c *gin.Context) {
+	// 读取body内容用于打印，同时保留原始数据供后续使用
+	bodyBytes, err := io.ReadAll(c.Request.Body)
+	if err != nil {
+		log.Printf("读取Creem Webhook请求body失败: %v", err)
+		c.AbortWithStatus(http.StatusBadRequest)
+		return
+	}
+
+	// 获取签名头
+	signature := c.GetHeader(CreemSignatureHeader)
+
+	// 打印关键信息（避免输出完整敏感payload）
+	log.Printf("Creem Webhook - URI: %s", c.Request.RequestURI)
+	if setting.CreemTestMode {
+		log.Printf("Creem Webhook - Signature: %s , Body: %s", signature, bodyBytes)
+	} else if signature == "" {
+		log.Printf("Creem Webhook缺少签名头")
+		c.AbortWithStatus(http.StatusUnauthorized)
+		return
+	}
+
+	// 验证签名
+	if !verifyCreemSignature(string(bodyBytes), signature, setting.CreemWebhookSecret) {
+		log.Printf("Creem Webhook签名验证失败")
+		c.AbortWithStatus(http.StatusUnauthorized)
+		return
+	}
+
+	log.Printf("Creem Webhook签名验证成功")
+
+	// 重新设置body供后续的ShouldBindJSON使用
+	c.Request.Body = io.NopCloser(bytes.NewReader(bodyBytes))
+
+	// 解析新格式的webhook数据
+	var webhookEvent CreemWebhookEvent
+	if err := c.ShouldBindJSON(&webhookEvent); err != nil {
+		log.Printf("解析Creem Webhook参数失败: %v", err)
+		c.AbortWithStatus(http.StatusBadRequest)
+		return
+	}
+
+	log.Printf("Creem Webhook解析成功 - EventType: %s, EventId: %s", webhookEvent.EventType, webhookEvent.Id)
+
+	// 根据事件类型处理不同的webhook
+	switch webhookEvent.EventType {
+	case "checkout.completed":
+		handleCheckoutCompleted(c, &webhookEvent)
+	default:
+		log.Printf("忽略Creem Webhook事件类型: %s", webhookEvent.EventType)
+		c.Status(http.StatusOK)
+	}
+}
+
+// 处理支付完成事件
+func handleCheckoutCompleted(c *gin.Context, event *CreemWebhookEvent) {
+	// 验证订单状态
+	if event.Object.Order.Status != "paid" {
+		log.Printf("订单状态不是已支付: %s, 跳过处理", event.Object.Order.Status)
+		c.Status(http.StatusOK)
+		return
+	}
+
+	// 获取引用ID（这是我们创建订单时传递的request_id）
+	referenceId := event.Object.RequestId
+	if referenceId == "" {
+		log.Println("Creem Webhook缺少request_id字段")
+		c.AbortWithStatus(http.StatusBadRequest)
+		return
+	}
+
+	// 验证订单类型，目前只处理一次性付款
+	if event.Object.Order.Type != "onetime" {
+		log.Printf("暂不支持的订单类型: %s, 跳过处理", event.Object.Order.Type)
+		c.Status(http.StatusOK)
+		return
+	}
+
+	// 记录详细的支付信息
+	log.Printf("处理Creem支付完成 - 订单号: %s, Creem订单ID: %s, 支付金额: %d %s, 客户邮箱: <redacted>, 产品: %s",
+		referenceId,
+		event.Object.Order.Id,
+		event.Object.Order.AmountPaid,
+		event.Object.Order.Currency,
+		event.Object.Product.Name)
+
+	// 查询本地订单确认存在
+	topUp := model.GetTopUpByTradeNo(referenceId)
+	if topUp == nil {
+		log.Printf("Creem充值订单不存在: %s", referenceId)
+		c.AbortWithStatus(http.StatusBadRequest)
+		return
+	}
+
+	if topUp.Status != common.TopUpStatusPending {
+		log.Printf("Creem充值订单状态错误: %s, 当前状态: %s", referenceId, topUp.Status)
+		c.Status(http.StatusOK) // 已处理过的订单，返回成功避免重复处理
+		return
+	}
+
+	// 处理充值，传入客户邮箱和姓名信息
+	customerEmail := event.Object.Customer.Email
+	customerName := event.Object.Customer.Name
+
+	// 防护性检查，确保邮箱和姓名不为空字符串
+	if customerEmail == "" {
+		log.Printf("警告：Creem回调中客户邮箱为空 - 订单号: %s", referenceId)
+	}
+	if customerName == "" {
+		log.Printf("警告：Creem回调中客户姓名为空 - 订单号: %s", referenceId)
+	}
+
+	err := model.RechargeCreem(referenceId, customerEmail, customerName)
+	if err != nil {
+		log.Printf("Creem充值处理失败: %s, 订单号: %s", err.Error(), referenceId)
+		c.AbortWithStatus(http.StatusInternalServerError)
+		return
+	}
+
+	log.Printf("Creem充值成功 - 订单号: %s, 充值额度: %d, 支付金额: %.2f",
+		referenceId, topUp.Amount, topUp.Money)
+	c.Status(http.StatusOK)
+}
+
+type CreemCheckoutRequest struct {
+	ProductId string `json:"product_id"`
+	RequestId string `json:"request_id"`
+	Customer  struct {
+		Email string `json:"email"`
+	} `json:"customer"`
+	Metadata map[string]string `json:"metadata,omitempty"`
+}
+
+type CreemCheckoutResponse struct {
+	CheckoutUrl string `json:"checkout_url"`
+	Id          string `json:"id"`
+}
+
+func genCreemLink(referenceId string, product *CreemProduct, email string, username string) (string, error) {
+	if setting.CreemApiKey == "" {
+		return "", fmt.Errorf("未配置Creem API密钥")
+	}
+
+	// 根据测试模式选择 API 端点
+	apiUrl := "https://api.creem.io/v1/checkouts"
+	if setting.CreemTestMode {
+		apiUrl = "https://test-api.creem.io/v1/checkouts"
+		log.Printf("使用Creem测试环境: %s", apiUrl)
+	}
+
+	// 构建请求数据，确保包含用户邮箱
+	requestData := CreemCheckoutRequest{
+		ProductId: product.ProductId,
+		RequestId: referenceId, // 这个作为订单ID传递给Creem
+		Customer: struct {
+			Email string `json:"email"`
+		}{
+			Email: email, // 用户邮箱会在支付页面预填充
+		},
+		Metadata: map[string]string{
+			"username":     username,
+			"reference_id": referenceId,
+			"product_name": product.Name,
+			"quota":        fmt.Sprintf("%d", product.Quota),
+		},
+	}
+
+	// 序列化请求数据
+	jsonData, err := json.Marshal(requestData)
+	if err != nil {
+		return "", fmt.Errorf("序列化请求数据失败: %v", err)
+	}
+
+	// 创建 HTTP 请求
+	req, err := http.NewRequest("POST", apiUrl, bytes.NewBuffer(jsonData))
+	if err != nil {
+		return "", fmt.Errorf("创建HTTP请求失败: %v", err)
+	}
+
+	// 设置请求头
+	req.Header.Set("Content-Type", "application/json")
+	req.Header.Set("x-api-key", setting.CreemApiKey)
+
+	log.Printf("发送Creem支付请求 - URL: %s, 产品ID: %s, 用户邮箱: %s, 订单号: %s",
+		apiUrl, product.ProductId, email, referenceId)
+
+	// 发送请求
+	client := &http.Client{
+		Timeout: 30 * time.Second,
+	}
+	resp, err := client.Do(req)
+	if err != nil {
+		return "", fmt.Errorf("发送HTTP请求失败: %v", err)
+	}
+	defer resp.Body.Close()
+
+	// 读取响应
+	body, err := io.ReadAll(resp.Body)
+	if err != nil {
+		return "", fmt.Errorf("读取响应失败: %v", err)
+	}
+
+	log.Printf("Creem API resp - status code: %d, resp: %s", resp.StatusCode, string(body))
+
+	// 检查响应状态
+	if resp.StatusCode/100 != 2 {
+		return "", fmt.Errorf("Creem API http status %d ", resp.StatusCode)
+	}
+	// 解析响应
+	var checkoutResp CreemCheckoutResponse
+	err = json.Unmarshal(body, &checkoutResp)
+	if err != nil {
+		return "", fmt.Errorf("解析响应失败: %v", err)
+	}
+
+	if checkoutResp.CheckoutUrl == "" {
+		return "", fmt.Errorf("Creem API resp no checkout url ")
+	}
+
+	log.Printf("Creem 支付链接创建成功 - 订单号: %s, 支付链接: %s", referenceId, checkoutResp.CheckoutUrl)
+	return checkoutResp.CheckoutUrl, nil
+}

controller/topup_stripe.go

@@ -5,15 +5,16 @@ import (
 	"io"
 	"log"
 	"net/http"
-	"one-api/common"
-	"one-api/model"
-	"one-api/setting"
-	"one-api/setting/operation_setting"
-	"one-api/setting/system_setting"
 	"strconv"
 	"strings"
 	"time"
 
+	"github.com/QuantumNous/new-api/common"
+	"github.com/QuantumNous/new-api/model"
+	"github.com/QuantumNous/new-api/setting"
+	"github.com/QuantumNous/new-api/setting/operation_setting"
+	"github.com/QuantumNous/new-api/setting/system_setting"
+
 	"github.com/gin-gonic/gin"
 	"github.com/stripe/stripe-go/v81"
 	"github.com/stripe/stripe-go/v81/checkout/session"
@@ -83,12 +84,13 @@ 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 {
@@ -218,7 +220,7 @@ func genStripeLink(referenceId string, customerId string, email string, amount i
 	params := &stripe.CheckoutSessionParams{
 		ClientReferenceID: stripe.String(referenceId),
 		SuccessURL:        stripe.String(system_setting.ServerAddress + "/console/log"),
-		CancelURL:         stripe.String(system_setting.ServerAddress + "/topup"),
+		CancelURL:         stripe.String(system_setting.ServerAddress + "/console/topup"),
 		LineItems: []*stripe.CheckoutSessionLineItemParams{
 			{
 				Price:    stripe.String(setting.StripePriceId),

controller/twofa.go

@@ -4,10 +4,11 @@ import (
 	"errors"
 	"fmt"
 	"net/http"
-	"one-api/common"
-	"one-api/model"
 	"strconv"
 
+	"github.com/QuantumNous/new-api/common"
+	"github.com/QuantumNous/new-api/model"
+
 	"github.com/gin-contrib/sessions"
 	"github.com/gin-gonic/gin"
 )

controller/uptime_kuma.go

@@ -5,11 +5,12 @@ import (
 	"encoding/json"
 	"errors"
 	"net/http"
-	"one-api/setting/console_setting"
 	"strconv"
 	"strings"
 	"time"
 
+	"github.com/QuantumNous/new-api/setting/console_setting"
+
 	"github.com/gin-gonic/gin"
 	"golang.org/x/sync/errgroup"
 )

controller/usedata.go

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

controller/user.go

@@ -5,16 +5,18 @@ import (
 	"fmt"
 	"net/http"
 	"net/url"
-	"one-api/common"
-	"one-api/dto"
-	"one-api/logger"
-	"one-api/model"
-	"one-api/setting"
 	"strconv"
 	"strings"
 	"sync"
 
-	"one-api/constant"
+	"github.com/QuantumNous/new-api/common"
+	"github.com/QuantumNous/new-api/dto"
+	"github.com/QuantumNous/new-api/logger"
+	"github.com/QuantumNous/new-api/model"
+	"github.com/QuantumNous/new-api/service"
+	"github.com/QuantumNous/new-api/setting"
+
+	"github.com/QuantumNous/new-api/constant"
 
 	"github.com/gin-contrib/sessions"
 	"github.com/gin-gonic/gin"
@@ -578,7 +580,7 @@ func GetUserModels(c *gin.Context) {
 		common.ApiError(c, err)
 		return
 	}
-	groups := setting.GetUserUsableGroups(user.Group)
+	groups := service.GetUserUsableGroups(user.Group)
 	var models []string
 	for group := range groups {
 		for _, g := range model.GetGroupEnabledModels(group) {

controller/vendor_meta.go

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

controller/video_proxy.go

@@ -0,0 +1,177 @@
+package controller
+
+import (
+	"fmt"
+	"io"
+	"net/http"
+	"net/url"
+	"time"
+
+	"github.com/QuantumNous/new-api/constant"
+	"github.com/QuantumNous/new-api/logger"
+	"github.com/QuantumNous/new-api/model"
+
+	"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: %v", taskID, err))
+		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 task %s: not found", taskID))
+		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"
+	}
+
+	var videoURL string
+	client := &http.Client{
+		Timeout: 60 * time.Second,
+	}
+
+	req, err := http.NewRequestWithContext(c.Request.Context(), http.MethodGet, "", nil)
+	if err != nil {
+		logger.LogError(c.Request.Context(), fmt.Sprintf("Failed to create request: %s", err.Error()))
+		c.JSON(http.StatusInternalServerError, gin.H{
+			"error": gin.H{
+				"message": "Failed to create proxy request",
+				"type":    "server_error",
+			},
+		})
+		return
+	}
+
+	switch channel.Type {
+	case constant.ChannelTypeGemini:
+		apiKey := task.PrivateData.Key
+		if apiKey == "" {
+			logger.LogError(c.Request.Context(), fmt.Sprintf("Missing stored API key for Gemini task %s", taskID))
+			c.JSON(http.StatusInternalServerError, gin.H{
+				"error": gin.H{
+					"message": "API key not stored for task",
+					"type":    "server_error",
+				},
+			})
+			return
+		}
+
+		videoURL, err = getGeminiVideoURL(channel, task, apiKey)
+		if err != nil {
+			logger.LogError(c.Request.Context(), fmt.Sprintf("Failed to resolve Gemini video URL for task %s: %s", taskID, err.Error()))
+			c.JSON(http.StatusBadGateway, gin.H{
+				"error": gin.H{
+					"message": "Failed to resolve Gemini video URL",
+					"type":    "server_error",
+				},
+			})
+			return
+		}
+		req.Header.Set("x-goog-api-key", apiKey)
+	case constant.ChannelTypeAli:
+		// Video URL is directly in task.FailReason
+		videoURL = task.FailReason
+	default:
+		// Default (Sora, etc.): Use original logic
+		videoURL = fmt.Sprintf("%s/v1/videos/%s/content", baseURL, task.TaskID)
+		req.Header.Set("Authorization", "Bearer "+channel.Key)
+	}
+
+	req.URL, err = url.Parse(videoURL)
+	if err != nil {
+		logger.LogError(c.Request.Context(), fmt.Sprintf("Failed to parse URL %s: %s", videoURL, err.Error()))
+		c.JSON(http.StatusInternalServerError, gin.H{
+			"error": gin.H{
+				"message": "Failed to create proxy request",
+				"type":    "server_error",
+			},
+		})
+		return
+	}
+
+	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()))
+	}
+}

controller/video_proxy_gemini.go

@@ -0,0 +1,158 @@
+package controller
+
+import (
+	"encoding/json"
+	"fmt"
+	"io"
+	"strconv"
+	"strings"
+
+	"github.com/QuantumNous/new-api/constant"
+	"github.com/QuantumNous/new-api/model"
+	"github.com/QuantumNous/new-api/relay"
+)
+
+func getGeminiVideoURL(channel *model.Channel, task *model.Task, apiKey string) (string, error) {
+	if channel == nil || task == nil {
+		return "", fmt.Errorf("invalid channel or task")
+	}
+
+	if url := extractGeminiVideoURLFromTaskData(task); url != "" {
+		return ensureAPIKey(url, apiKey), nil
+	}
+
+	baseURL := constant.ChannelBaseURLs[channel.Type]
+	if channel.GetBaseURL() != "" {
+		baseURL = channel.GetBaseURL()
+	}
+
+	adaptor := relay.GetTaskAdaptor(constant.TaskPlatform(strconv.Itoa(channel.Type)))
+	if adaptor == nil {
+		return "", fmt.Errorf("gemini task adaptor not found")
+	}
+
+	if apiKey == "" {
+		return "", fmt.Errorf("api key not available for task")
+	}
+
+	resp, err := adaptor.FetchTask(baseURL, apiKey, map[string]any{
+		"task_id": task.TaskID,
+		"action":  task.Action,
+	})
+	if err != nil {
+		return "", fmt.Errorf("fetch task failed: %w", err)
+	}
+	defer resp.Body.Close()
+
+	body, err := io.ReadAll(resp.Body)
+	if err != nil {
+		return "", fmt.Errorf("read task response failed: %w", err)
+	}
+
+	taskInfo, parseErr := adaptor.ParseTaskResult(body)
+	if parseErr == nil && taskInfo != nil && taskInfo.RemoteUrl != "" {
+		return ensureAPIKey(taskInfo.RemoteUrl, apiKey), nil
+	}
+
+	if url := extractGeminiVideoURLFromPayload(body); url != "" {
+		return ensureAPIKey(url, apiKey), nil
+	}
+
+	if parseErr != nil {
+		return "", fmt.Errorf("parse task result failed: %w", parseErr)
+	}
+
+	return "", fmt.Errorf("gemini video url not found")
+}
+
+func extractGeminiVideoURLFromTaskData(task *model.Task) string {
+	if task == nil || len(task.Data) == 0 {
+		return ""
+	}
+	var payload map[string]any
+	if err := json.Unmarshal(task.Data, &payload); err != nil {
+		return ""
+	}
+	return extractGeminiVideoURLFromMap(payload)
+}
+
+func extractGeminiVideoURLFromPayload(body []byte) string {
+	var payload map[string]any
+	if err := json.Unmarshal(body, &payload); err != nil {
+		return ""
+	}
+	return extractGeminiVideoURLFromMap(payload)
+}
+
+func extractGeminiVideoURLFromMap(payload map[string]any) string {
+	if payload == nil {
+		return ""
+	}
+	if uri, ok := payload["uri"].(string); ok && uri != "" {
+		return uri
+	}
+	if resp, ok := payload["response"].(map[string]any); ok {
+		if uri := extractGeminiVideoURLFromResponse(resp); uri != "" {
+			return uri
+		}
+	}
+	return ""
+}
+
+func extractGeminiVideoURLFromResponse(resp map[string]any) string {
+	if resp == nil {
+		return ""
+	}
+	if gvr, ok := resp["generateVideoResponse"].(map[string]any); ok {
+		if uri := extractGeminiVideoURLFromGeneratedSamples(gvr); uri != "" {
+			return uri
+		}
+	}
+	if videos, ok := resp["videos"].([]any); ok {
+		for _, video := range videos {
+			if vm, ok := video.(map[string]any); ok {
+				if uri, ok := vm["uri"].(string); ok && uri != "" {
+					return uri
+				}
+			}
+		}
+	}
+	if uri, ok := resp["video"].(string); ok && uri != "" {
+		return uri
+	}
+	if uri, ok := resp["uri"].(string); ok && uri != "" {
+		return uri
+	}
+	return ""
+}
+
+func extractGeminiVideoURLFromGeneratedSamples(gvr map[string]any) string {
+	if gvr == nil {
+		return ""
+	}
+	if samples, ok := gvr["generatedSamples"].([]any); ok {
+		for _, sample := range samples {
+			if sm, ok := sample.(map[string]any); ok {
+				if video, ok := sm["video"].(map[string]any); ok {
+					if uri, ok := video["uri"].(string); ok && uri != "" {
+						return uri
+					}
+				}
+			}
+		}
+	}
+	return ""
+}
+
+func ensureAPIKey(uri, key string) string {
+	if key == "" || uri == "" {
+		return uri
+	}
+	if strings.Contains(uri, "key=") {
+		return uri
+	}
+	if strings.Contains(uri, "?") {
+		return fmt.Sprintf("%s&key=%s", uri, key)
+	}
+	return fmt.Sprintf("%s?key=%s", uri, key)
+}

controller/wechat.go

@@ -5,11 +5,12 @@ import (
 	"errors"
 	"fmt"
 	"net/http"
-	"one-api/common"
-	"one-api/model"
 	"strconv"
 	"time"
 
+	"github.com/QuantumNous/new-api/common"
+	"github.com/QuantumNous/new-api/model"
+
 	"github.com/gin-contrib/sessions"
 	"github.com/gin-gonic/gin"
 )

docker-compose.yml

@@ -30,11 +30,14 @@ services:
 #      - 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
-      - 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!!!!!!!
+      - ERROR_LOG_ENABLED=true # 是否启用错误日志记录 (Whether to enable error log recording)
+      - BATCH_UPDATE_ENABLED=true  # 是否启用批量更新 (Whether to enable batch update)
+#      - 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
+#      - GOOGLE_ANALYTICS_ID=G-XXXXXXXXXX  # Google Analytics 的测量 ID (Google Analytics Measurement ID)
+#      - UMAMI_WEBSITE_ID=xxxxxxxx-xxxx-xxxx-xxxx-xxxxxxxxxxxx  # Umami 网站 ID (Umami Website ID)
+#      - UMAMI_SCRIPT_URL=https://analytics.umami.is/script.js  # Umami 脚本 URL，默认为官方地址 (Umami Script URL, defaults to official URL)
 
     depends_on:
       - redis

docs/translation-glossary.fr.md

@@ -0,0 +1,107 @@
+# Glossaire Français (French Glossary)
+
+Ce document fournit des traductions standards françaises pour la terminologie clé du projet afin d'assurer la cohérence et la précision des traductions.
+
+This document provides standard French translations for key project terminology to ensure consistency and accuracy in translations.
+
+## Concepts de Base (Core Concepts)
+
+- L'utilisation d'émojis dans les traductions est autorisée s'ils sont présents dans l'original
+- L'utilisation de termes purement techniques est autorisée s'ils sont présents dans l'original
+- L'utilisation de termes techniques en anglais est autorisée s'ils sont largement utilisés dans l'environnement technique francophone (par exemple, API)
+
+| Chinois | Français | Anglais | Description |
+|---------|----------|---------|-------------|
+| 倍率 | Ratio | Ratio/Multiplier | Multiplicateur utilisé pour le calcul des prix. **Important :** Dans le contexte des calculs de prix, toujours utiliser "Ratio" plutôt que "Multiplicateur" pour assurer la cohérence terminologique |
+| 令牌 | Jeton | Token | Identifiants d'accès API ou unités de texte traitées par les modèles |
+| 渠道 | Canal | Channel | Canal d'accès aux fournisseurs d'API |
+| 分组 | Groupe | Group | Classification des utilisateurs ou des jetons |
+| 额度 | Quota | Quota | Quota de services disponible pour l'utilisateur |
+
+## Modèles (Model Related)
+
+| Chinois | Français | Anglais | Description |
+|---------|----------|---------|-------------|
+| 提示 | Invite | Prompt | Contenu d'entrée du modèle |
+| 补全 | Complétion | Completion | Contenu de sortie du modèle. **Important :** Ne pas utiliser "Achèvement" ou "Finalisation" - uniquement "Complétion" pour correspondre à la terminologie technique |
+| 输入 | Entrée | Input/Prompt | Contenu envoyé au modèle |
+| 输出 | Sortie | Output/Completion | Contenu retourné par le modèle |
+| 模型倍率 | Ratio du modèle | Model Ratio | Ratio de tarification pour différents modèles |
+| 补全倍率 | Ratio de complétion | Completion Ratio | Ratio de tarification supplémentaire pour la sortie |
+| 固定价格 | Prix fixe | Price per call | Prix par appel |
+| 按量计费 | Paiement à l'utilisation | Pay-as-you-go | Tarification basée sur l'utilisation |
+| 按次计费 | Paiement par appel | Pay-per-view | Prix fixe par appel |
+
+## Gestion des Utilisateurs (User Management)
+
+| Chinois | Français | Anglais | Description |
+|---------|----------|---------|-------------|
+| 超级管理员 | Super-administrateur | Root User | Administrateur avec les privilèges les plus élevés |
+| 管理员 | Administrateur | Admin User | Administrateur système |
+| 普通用户 | Utilisateur normal | Normal User | Utilisateur avec privilèges standards |
+
+## Recharge et Échange (Recharge & Redemption)
+
+| Chinois | Français | Anglais | Description |
+|---------|----------|---------|-------------|
+| 充值 | Recharge | Top Up | Ajout de quota au compte |
+| 兑换码 | Code d'échange | Redemption Code | Code qui peut être échangé contre du quota |
+
+## Gestion des Canaux (Channel Management)
+
+| Chinois | Français | Anglais | Description |
+|---------|----------|---------|-------------|
+| 渠道 | Canal | Channel | Canal du fournisseur d'API |
+| API密钥 | Clé API | API Key | Clé d'accès API. **Important :** Utiliser "Clé API" au lieu de "Jeton API" pour plus de précision et conformément à la terminologie technique francophone établie. Le terme "Clé" reflète mieux la fonctionnalité d'accès aux ressources, tandis que "Jeton" est plus souvent associé aux unités de texte dans le contexte du traitement des modèles linguistiques. |
+| 优先级 | Priorité | Priority | Priorité de sélection du canal |
+| 权重 | Poids | Weight | Poids d'équilibrage de charge |
+| 代理 | Proxy | Proxy | Adresse du serveur proxy |
+| 模型重定向 | Redirection de modèle | Model Mapping | Remplacement du nom du modèle dans le corps de la requête |
+| 供应商 | Fournisseur | Provider/Vendor | Fournisseur de services ou d'API |
+
+## Sécurité (Security Related)
+
+| Chinois | Français | Anglais | Description |
+|---------|----------|---------|-------------|
+| 两步验证 | Authentification à deux facteurs | Two-Factor Authentication | Méthode de vérification de sécurité supplémentaire pour les comptes |
+| 2FA | 2FA | Two-Factor Authentication | Abréviation de l'authentification à deux facteurs |
+
+## Recommandations de Traduction (Translation Guidelines)
+
+### Variantes Contextuelles de Traduction
+
+**Invite/Entrée (Prompt/Input)**
+
+- **Invite** : Lors de l'interaction avec les LLM, dans l'interface utilisateur, lors de la description de l'interaction avec le modèle
+- **Entrée** : Dans la tarification, la documentation technique, la description du processus de traitement des données
+- **Règle** : S'il s'agit de l'expérience utilisateur et de l'interaction avec l'IA → "Invite", s'il s'agit du processus technique ou des calculs → "Entrée"
+
+**Jeton (Token)**
+
+- Jeton d'accès API (API Token)
+- Unité de texte traitée par le modèle (Text Token)
+- Jeton d'accès système (Access Token)
+
+**Quota (Quota)**
+
+- Quota de services disponible pour l'utilisateur
+- Parfois traduit comme "Crédit"
+
+### Particularités de la Langue Française
+
+- **Formes plurielles** : Nécessite une implémentation correcte des formes plurielles (_one, _other)
+- **Accords grammaticaux** : Attention aux accords grammaticaux dans les termes techniques
+- **Genre grammatical** : Accord du genre des termes techniques (par exemple, "modèle" - masculin, "canal" - masculin)
+
+### Termes Standardisés
+
+- **Complétion (Completion)** : Contenu de sortie du modèle
+- **Ratio (Ratio)** : Multiplicateur pour le calcul des prix
+- **Code d'échange (Redemption Code)** : Utilisé au lieu de "Code d'échange" pour plus de précision
+- **Fournisseur (Provider/Vendor)** : Organisation ou service fournissant des API ou des modèles d'IA
+
+---
+
+**Note pour les contributeurs :** Si vous trouvez des incohérences dans les traductions de terminologie ou si vous avez de meilleures suggestions de traduction pour le français, n'hésitez pas à créer une Issue ou une Pull Request.
+
+**Contribution Note for French:** If you find any inconsistencies in terminology translations or have better translation suggestions for French, please feel free to submit an Issue or Pull Request.

docs/translation-glossary.md

@@ -54,6 +54,20 @@ This document provides standard translation references for key terminology in th
 | 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 |
 
+## 安全相关 (Security Related)
+
+| 中文 | English | 说明 | Description |
+|------|---------|------|-------------|
+| 两步验证 | Two-Factor Authentication | 为账户提供额外安全保护的验证方式 | Additional security verification method for accounts |
+| 2FA | Two-Factor Authentication | 两步验证的缩写 | Abbreviation for Two-Factor Authentication |
+
+## 计费相关 (Billing Related)
+
+| 中文 | English | 说明 | Description |
+|------|---------|------|-------------|
+| 倍率 | Ratio | 价格计算的乘数因子 | Multiplier factor used for price calculation |
+| 倍率 | Multiplier | 价格计算的乘数因子（同义词） | Multiplier factor used for price calculation (synonym) |
+
 ## 翻译注意事项 (Translation Guidelines)
 
 - **提示 (Prompt)** = 模型输入内容 / Model input content

docs/translation-glossary.ru.md

@@ -0,0 +1,107 @@
+# Русский глоссарий (Russian Glossary)
+
+Данный раздел предоставляет стандартные переводы ключевой терминологии проекта на русский язык для обеспечения согласованности и точности переводов.
+
+This section provides standard Russian translations for key project terminology to ensure consistency and accuracy in translations.
+
+## Основные концепции (Core Concepts)
+
+- Допускается использовать символы Emoji в переводе, если они были в оригинале.
+- Допускается использование сугубо технических терминов, если они были в оригинале.
+- Допускается использование технических терминов на английском языке, если они широко используются в русскоязычной технической среде (например, API).
+
+| Китайский | Русский | Английский | Описание |
+|-----------|--------|-----------|----------|
+| 倍率 | Коэффициент | Ratio/Multiplier | Множитель для расчета цены. **Важно:** В контексте расчетов цен всегда использовать "Коэффициент", а не "Множитель" для обеспечения консистентности терминологии |
+| 令牌 | Токен | Token | Учетные данные API или текстовые единицы |
+| 渠道 | Канал | Channel | Канал доступа к поставщику API |
+| 分组 | Группа | Group | Классификация пользователей или токенов |
+| 额度 | Квота | Quota | Доступная квота услуг для пользователя |
+
+## Модели (Model Related)
+
+| Китайский | Русский | Английский | Описание |
+|-----------|--------|-----------|----------|
+| 提示 | Промпт/Ввод | Prompt | Содержимое ввода в модель |
+| 补全 | Вывод | Completion | Содержимое вывода модели. **Важно:** Не использовать "Дополнение" или "Завершение" - только "Вывод" для соответствия технической терминологии |
+| 输入 | Ввод | Input/Prompt | Содержимое, отправляемое в модель |
+| 输出 | Вывод | Output/Completion | Содержимое, возвращаемое моделью |
+| 模型倍率 | Коэффициент модели | Model Ratio | Коэффициент тарификации для разных моделей |
+| 补全倍率 | Коэффициент вывода | Completion Ratio | Дополнительный коэффициент тарификации для вывода |
+| 固定价格 | Цена за запрос | Price per call | Цена за один вызов |
+| 按量计费 | Оплата по объему | Pay-as-you-go | Тарификация на основе использования |
+| 按次计费 | Оплата за запрос | Pay-per-view | Фиксированная цена за вызов |
+
+## Управление пользователями (User Management)
+
+| Китайский | Русский | Английский | Описание |
+|-----------|--------|-----------|----------|
+| 超级管理员 | Суперадминистратор | Root User | Администратор с наивысшими привилегиями |
+| 管理员 | Администратор | Admin User | Системный администратор |
+| 普通用户 | Обычный пользователь | Normal User | Пользователь со стандартными привилегиями |
+
+## Пополнение и обмен (Recharge & Redemption)
+
+| Китайский | Русский | Английский | Описание |
+|-----------|--------|-----------|----------|
+| 充值 | Пополнение | Top Up | Добавление квоты на аккаунт |
+| 兑换码 | Код купона | Redemption Code | Код, который можно обменять на квоту |
+
+## Управление каналами (Channel Management)
+
+| Китайский | Русский | Английский | Описание |
+|-----------|--------|-----------|----------|
+| 渠道 | Канал | Channel | Канал поставщика API |
+| API密钥 | API ключ | API Key | Ключ доступа к API. **Важно:** Использовать "API ключ" вместо "API токен" для большей точности и соответствия общепринятой русскоязычной технической терминологии. Термин "ключ" более точно отражает функционал доступа к ресурсам, в то время как "токен" чаще ассоциируется с текстовыми единицами в контексте обработки языковых моделей. |
+| 优先级 | Приоритет | Priority | Приоритет выбора канала |
+| 权重 | Вес | Weight | Вес балансировки нагрузки |
+| 代理 | Прокси | Proxy | Адрес прокси-сервера |
+| 模型重定向 | Перенаправление модели | Model Mapping | Замена имени модели в теле запроса |
+| 供应商 | Поставщик | Provider/Vendor | Поставщик услуг или API |
+
+## Безопасность (Security Related)
+
+| Китайский | Русский | Английский | Описание |
+|-----------|--------|-----------|----------|
+| 两步验证 | Двухфакторная аутентификация | Two-Factor Authentication | Дополнительный метод проверки безопасности для аккаунтов |
+| 2FA | 2FA | Two-Factor Authentication | Аббревиатура двухфакторной аутентификации |
+
+## Рекомендации по переводу (Translation Guidelines)
+
+### Контекстуальные варианты перевода
+
+**Промпт/Ввод (Prompt/Input)**
+
+- **Промпт**: При общении с LLM, в пользовательском интерфейсе, при описании взаимодействия с моделью
+- **Ввод**: При тарификации, технической документации, описании процесса обработки данных
+- **Правило**: Если речь о пользовательском опыте и взаимодействии с AI → "Промпт", если о техническом процессе или расчетах → "Ввод"
+
+**Token**
+
+- API токен доступа (API Token)
+- Текстовая единица, обрабатываемая моделью (Text Token)
+- Токен доступа к системе (Access Token)
+
+**Квота (Quota)**
+
+- Доступная квота услуг пользователя
+- Иногда переводится как "Кредит"
+
+### Особенности русского языка
+
+- **Множественные формы**: Требуется правильная реализация множественных форм (_one,_few, _many,_other)
+- **Падежные окончания**: Внимательное отношение к падежным окончаниям в технических терминах
+- **Грамматический род**: Согласование рода технических терминов (например, "модель" - женский род, "канал" - мужской род)
+
+### Стандартизированные термины
+
+- **Вывод (Completion)**: Содержимое вывода модели
+- **Коэффициент (Ratio)**: Множитель для расчета цены
+- **Код купона (Redemption Code)**: Используется вместо "Код обмена" для большей точности
+- **Поставщик (Provider/Vendor)**: Организация или сервис, предоставляющий API или AI-модели
+
+---
+
+**Примечание для участников:** При обнаружении несогласованности в переводах терминологии или наличии лучших предложений по переводу, не стесняйтесь создавать Issue или Pull Request.
+
+**Contribution Note for Russian:** If you find any inconsistencies in terminology translations or have better translation suggestions for Russian, please feel free to submit an Issue or Pull Request.

dto/audio.go

@@ -1,17 +1,22 @@
 package dto
 
 import (
-	"one-api/types"
+	"encoding/json"
+
+	"github.com/QuantumNous/new-api/types"
 
 	"github.com/gin-gonic/gin"
 )
 
 type AudioRequest struct {
-	Model          string  `json:"model"`
-	Input          string  `json:"input"`
-	Voice          string  `json:"voice"`
-	Speed          float64 `json:"speed,omitempty"`
-	ResponseFormat string  `json:"response_format,omitempty"`
+	Model          string          `json:"model"`
+	Input          string          `json:"input"`
+	Voice          string          `json:"voice"`
+	Instructions   string          `json:"instructions,omitempty"`
+	ResponseFormat string          `json:"response_format,omitempty"`
+	Speed          float64         `json:"speed,omitempty"`
+	StreamFormat   string          `json:"stream_format,omitempty"`
+	Metadata       json.RawMessage `json:"metadata,omitempty"`
 }
 
 func (r *AudioRequest) GetTokenCountMeta() *types.TokenCountMeta {

dto/channel_settings.go

@@ -16,6 +16,13 @@ const (
 	VertexKeyTypeAPIKey VertexKeyType = "api_key"
 )
 
+type AwsKeyType string
+
+const (
+	AwsKeyTypeAKSK   AwsKeyType = "ak_sk" // 默认
+	AwsKeyTypeApiKey AwsKeyType = "api_key"
+)
+
 type ChannelOtherSettings struct {
 	AzureResponsesVersion string        `json:"azure_responses_version,omitempty"`
 	VertexKeyType         VertexKeyType `json:"vertex_key_type,omitempty"` // "json" or "api_key"
@@ -23,6 +30,7 @@ type ChannelOtherSettings struct {
 	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）
+	AwsKeyType            AwsKeyType    `json:"aws_key_type,omitempty"`
 }
 
 func (s *ChannelOtherSettings) IsOpenRouterEnterprise() bool {

dto/claude.go

@@ -3,10 +3,11 @@ package dto
 import (
 	"encoding/json"
 	"fmt"
-	"one-api/common"
-	"one-api/types"
 	"strings"
 
+	"github.com/QuantumNous/new-api/common"
+	"github.com/QuantumNous/new-api/types"
+
 	"github.com/gin-gonic/gin"
 )
 
@@ -23,7 +24,7 @@ type ClaudeMediaMessage struct {
 	StopReason   *string              `json:"stop_reason,omitempty"`
 	PartialJson  *string              `json:"partial_json,omitempty"`
 	Role         string               `json:"role,omitempty"`
-	Thinking     string               `json:"thinking,omitempty"`
+	Thinking     *string              `json:"thinking,omitempty"`
 	Signature    string               `json:"signature,omitempty"`
 	Delta        string               `json:"delta,omitempty"`
 	CacheControl json.RawMessage      `json:"cache_control,omitempty"`
@@ -147,6 +148,10 @@ func (c *ClaudeMessage) SetStringContent(content string) {
 	c.Content = content
 }
 
+func (c *ClaudeMessage) SetContent(content any) {
+	c.Content = content
+}
+
 func (c *ClaudeMessage) ParseContent() ([]ClaudeMediaMessage, error) {
 	return common.Any2Type[[]ClaudeMediaMessage](c.Content)
 }
@@ -505,11 +510,44 @@ func (c *ClaudeResponse) GetClaudeError() *types.ClaudeError {
 }
 
 type ClaudeUsage struct {
-	InputTokens              int                  `json:"input_tokens"`
-	CacheCreationInputTokens int                  `json:"cache_creation_input_tokens"`
-	CacheReadInputTokens     int                  `json:"cache_read_input_tokens"`
-	OutputTokens             int                  `json:"output_tokens"`
-	ServerToolUse            *ClaudeServerToolUse `json:"server_tool_use,omitempty"`
+	InputTokens              int                       `json:"input_tokens"`
+	CacheCreationInputTokens int                       `json:"cache_creation_input_tokens"`
+	CacheReadInputTokens     int                       `json:"cache_read_input_tokens"`
+	OutputTokens             int                       `json:"output_tokens"`
+	CacheCreation            *ClaudeCacheCreationUsage `json:"cache_creation,omitempty"`
+	// claude cache 1h
+	ClaudeCacheCreation5mTokens int                  `json:"claude_cache_creation_5_m_tokens"`
+	ClaudeCacheCreation1hTokens int                  `json:"claude_cache_creation_1_h_tokens"`
+	ServerToolUse               *ClaudeServerToolUse `json:"server_tool_use,omitempty"`
+}
+
+type ClaudeCacheCreationUsage struct {
+	Ephemeral5mInputTokens int `json:"ephemeral_5m_input_tokens,omitempty"`
+	Ephemeral1hInputTokens int `json:"ephemeral_1h_input_tokens,omitempty"`
+}
+
+func (u *ClaudeUsage) GetCacheCreation5mTokens() int {
+	if u == nil || u.CacheCreation == nil {
+		return 0
+	}
+	return u.CacheCreation.Ephemeral5mInputTokens
+}
+
+func (u *ClaudeUsage) GetCacheCreation1hTokens() int {
+	if u == nil || u.CacheCreation == nil {
+		return 0
+	}
+	return u.CacheCreation.Ephemeral1hInputTokens
+}
+
+func (u *ClaudeUsage) GetCacheCreationTotalTokens() int {
+	if u == nil {
+		return 0
+	}
+	if u.CacheCreationInputTokens > 0 {
+		return u.CacheCreationInputTokens
+	}
+	return u.GetCacheCreation5mTokens() + u.GetCacheCreation1hTokens()
 }
 
 type ClaudeServerToolUse struct {

dto/embedding.go

@@ -1,9 +1,10 @@
 package dto
 
 import (
-	"one-api/types"
 	"strings"
 
+	"github.com/QuantumNous/new-api/types"
+
 	"github.com/gin-gonic/gin"
 )
 

dto/error.go

@@ -1,6 +1,6 @@
 package dto
 
-import "one-api/types"
+import "github.com/QuantumNous/new-api/types"
 
 type OpenAIError struct {
 	Message string `json:"message"`

dto/gemini.go

@@ -2,15 +2,17 @@ package dto
 
 import (
 	"encoding/json"
-	"one-api/common"
-	"one-api/logger"
-	"one-api/types"
 	"strings"
 
+	"github.com/QuantumNous/new-api/common"
+	"github.com/QuantumNous/new-api/logger"
+	"github.com/QuantumNous/new-api/types"
+
 	"github.com/gin-gonic/gin"
 )
 
 type GeminiChatRequest struct {
+	Requests           []GeminiChatRequest        `json:"requests,omitempty"` // For batch requests
 	Contents           []GeminiChatContent        `json:"contents"`
 	SafetySettings     []GeminiChatSafetySettings `json:"safetySettings,omitempty"`
 	GenerationConfig   GeminiChatGenerationConfig `json:"generationConfig,omitempty"`
@@ -293,12 +295,13 @@ 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 {
@@ -328,6 +331,7 @@ 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

@@ -2,11 +2,12 @@ package dto
 
 import (
 	"encoding/json"
-	"one-api/common"
-	"one-api/types"
 	"reflect"
 	"strings"
 
+	"github.com/QuantumNous/new-api/common"
+	"github.com/QuantumNous/new-api/types"
+
 	"github.com/gin-gonic/gin"
 )
 
@@ -26,7 +27,8 @@ type ImageRequest struct {
 	OutputCompression json.RawMessage `json:"output_compression,omitempty"`
 	PartialImages     json.RawMessage `json:"partial_images,omitempty"`
 	// Stream            bool            `json:"stream,omitempty"`
-	Watermark *bool `json:"watermark,omitempty"`
+	Watermark *bool           `json:"watermark,omitempty"`
+	Image     json.RawMessage `json:"image,omitempty"`
 	// 用匿名参数接收额外参数
 	Extra map[string]json.RawMessage `json:"-"`
 }

dto/openai_request.go

@@ -3,10 +3,11 @@ package dto
 import (
 	"encoding/json"
 	"fmt"
-	"one-api/common"
-	"one-api/types"
 	"strings"
 
+	"github.com/QuantumNous/new-api/common"
+	"github.com/QuantumNous/new-api/types"
+
 	"github.com/gin-gonic/gin"
 )
 
@@ -87,6 +88,12 @@ 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 {
@@ -225,10 +232,13 @@ func (r *GeneralOpenAIRequest) GetSystemRoleName() string {
 	return "system"
 }
 
+const CustomType = "custom"
+
 type ToolCallRequest struct {
 	ID       string          `json:"id,omitempty"`
 	Type     string          `json:"type"`
-	Function FunctionRequest `json:"function"`
+	Function FunctionRequest `json:"function,omitempty"`
+	Custom   json.RawMessage `json:"custom,omitempty"`
 }
 
 type FunctionRequest struct {

dto/openai_response.go

@@ -3,7 +3,8 @@ package dto
 import (
 	"encoding/json"
 	"fmt"
-	"one-api/types"
+
+	"github.com/QuantumNous/new-api/types"
 )
 
 const (
@@ -229,10 +230,25 @@ type Usage struct {
 	InputTokens            int                `json:"input_tokens"`
 	OutputTokens           int                `json:"output_tokens"`
 	InputTokensDetails     *InputTokenDetails `json:"input_tokens_details"`
+
+	// claude cache 1h
+	ClaudeCacheCreation5mTokens int `json:"claude_cache_creation_5_m_tokens"`
+	ClaudeCacheCreation1hTokens int `json:"claude_cache_creation_1_h_tokens"`
+
 	// OpenRouter Params
 	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/openai_video.go

@@ -0,0 +1,52 @@
+package dto
+
+import (
+	"strconv"
+	"strings"
+)
+
+const (
+	VideoStatusUnknown    = "unknown"
+	VideoStatusQueued     = "queued"
+	VideoStatusInProgress = "in_progress"
+	VideoStatusCompleted  = "completed"
+	VideoStatusFailed     = "failed"
+)
+
+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"` // Should use VideoStatus constants: VideoStatusQueued, VideoStatusInProgress, VideoStatusCompleted, VideoStatusFailed
+	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"`
+}
+
+func (m *OpenAIVideo) SetProgressStr(progress string) {
+	progress = strings.TrimSuffix(progress, "%")
+	m.Progress, _ = strconv.Atoi(progress)
+}
+func (m *OpenAIVideo) SetMetadata(k string, v any) {
+	if m.Metadata == nil {
+		m.Metadata = make(map[string]any)
+	}
+	m.Metadata[k] = v
+}
+func NewOpenAIVideo() *OpenAIVideo {
+	return &OpenAIVideo{
+		Object: "video",
+	}
+}
+
+type OpenAIVideoError struct {
+	Message string `json:"message"`
+	Code    string `json:"code"`
+}

dto/pricing.go

@@ -1,6 +1,6 @@
 package dto
 
-import "one-api/constant"
+import "github.com/QuantumNous/new-api/constant"
 
 // 这里不好动就不动了，本来想独立出来的（
 type OpenAIModels struct {

dto/realtime.go

@@ -1,6 +1,6 @@
 package dto
 
-import "one-api/types"
+import "github.com/QuantumNous/new-api/types"
 
 const (
 	RealtimeEventTypeError              = "error"

dto/request_common.go

@@ -1,8 +1,8 @@
 package dto
 
 import (
+	"github.com/QuantumNous/new-api/types"
 	"github.com/gin-gonic/gin"
-	"one-api/types"
 )
 
 type Request interface {

dto/rerank.go

@@ -2,9 +2,10 @@ package dto
 
 import (
 	"fmt"
-	"github.com/gin-gonic/gin"
-	"one-api/types"
 	"strings"
+
+	"github.com/QuantumNous/new-api/types"
+	"github.com/gin-gonic/gin"
 )
 
 type RerankRequest struct {

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>