fix: restore doubao coding plan deprecation and regex ignored models lost during conflict resolution

# Conflicts:
#	web/src/components/table/channels/modals/EditChannelModal.jsx

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

@@ -27,9 +27,10 @@ jobs:
     permissions:
       packages: write
       contents: read
+      id-token: write
     steps:
       - name: Check out (shallow)
-        uses: actions/checkout@v4
+        uses: actions/checkout@34e114876b0b11c390a56381ad16ebd13914f8d5 # v4
         with:
           fetch-depth: 1
 
@@ -46,16 +47,16 @@ jobs:
         run: echo "GHCR_REPOSITORY=${GITHUB_REPOSITORY,,}" >> $GITHUB_ENV
 
       - name: Set up Docker Buildx
-        uses: docker/setup-buildx-action@v3
+        uses: docker/setup-buildx-action@8d2750c68a42422c14e847fe6c8ac0403b4cbd6f # v3
 
       - name: Log in to Docker Hub
-        uses: docker/login-action@v3
+        uses: docker/login-action@c94ce9fb468520275223c153574b00df6fe4bcc9 # v3
         with:
           username: ${{ secrets.DOCKERHUB_USERNAME }}
           password: ${{ secrets.DOCKERHUB_TOKEN }}
 
       - name: Log in to GHCR
-        uses: docker/login-action@v3
+        uses: docker/login-action@c94ce9fb468520275223c153574b00df6fe4bcc9 # v3
         with:
           registry: ghcr.io
           username: ${{ github.actor }}
@@ -63,14 +64,15 @@ jobs:
 
       - name: Extract metadata (labels)
         id: meta
-        uses: docker/metadata-action@v5
+        uses: docker/metadata-action@c299e40c65443455700f0fdfc63efafe5b349051 # v5
         with:
           images: |
             calciumion/new-api
             ghcr.io/${{ env.GHCR_REPOSITORY }}
 
       - name: Build & push single-arch (to both registries)
-        uses: docker/build-push-action@v6
+        id: build
+        uses: docker/build-push-action@10e90e3645eae34f1e60eeb005ba3a3d33f178e8 # v6
         with:
           context: .
           platforms: ${{ matrix.platform }}
@@ -83,8 +85,25 @@ jobs:
           labels: ${{ steps.meta.outputs.labels }}
           cache-from: type=gha
           cache-to: type=gha,mode=max
-          provenance: false
-          sbom: false
+          provenance: mode=max
+          sbom: true
+
+      - name: Install cosign
+        uses: sigstore/cosign-installer@398d4b0eeef1380460a10c8013a76f728fb906ac # v3
+
+      - name: Sign image with cosign
+        run: |
+          cosign sign --yes calciumion/new-api@${{ steps.build.outputs.digest }}
+          cosign sign --yes ghcr.io/${{ env.GHCR_REPOSITORY }}@${{ steps.build.outputs.digest }}
+
+      - name: Output digest
+        run: |
+          echo "### Docker Image Digest (${{ matrix.arch }})" >> $GITHUB_STEP_SUMMARY
+          echo '```' >> $GITHUB_STEP_SUMMARY
+          echo "calciumion/new-api:alpha-${{ matrix.arch }}" >> $GITHUB_STEP_SUMMARY
+          echo "ghcr.io/${{ env.GHCR_REPOSITORY }}:alpha-${{ matrix.arch }}" >> $GITHUB_STEP_SUMMARY
+          echo "${{ steps.build.outputs.digest }}" >> $GITHUB_STEP_SUMMARY
+          echo '```' >> $GITHUB_STEP_SUMMARY
 
   create_manifests:
     name: Create multi-arch manifests (Docker Hub + GHCR)
@@ -95,7 +114,7 @@ jobs:
       contents: read
     steps:
       - name: Check out (shallow)
-        uses: actions/checkout@v4
+        uses: actions/checkout@34e114876b0b11c390a56381ad16ebd13914f8d5 # v4
         with:
           fetch-depth: 1
 
@@ -110,7 +129,7 @@ jobs:
           echo "VERSION=$VERSION" >> $GITHUB_ENV
 
       - name: Log in to Docker Hub
-        uses: docker/login-action@v3
+        uses: docker/login-action@c94ce9fb468520275223c153574b00df6fe4bcc9 # v3
         with:
           username: ${{ secrets.DOCKERHUB_USERNAME }}
           password: ${{ secrets.DOCKERHUB_TOKEN }}
@@ -130,7 +149,7 @@ jobs:
             calciumion/new-api:${VERSION}-arm64
 
       - name: Log in to GHCR
-        uses: docker/login-action@v3
+        uses: docker/login-action@c94ce9fb468520275223c153574b00df6fe4bcc9 # v3
         with:
           registry: ghcr.io
           username: ${{ github.actor }}
@@ -149,3 +168,12 @@ jobs:
             -t ghcr.io/${GHCR_REPOSITORY}:${VERSION} \
             ghcr.io/${GHCR_REPOSITORY}:${VERSION}-amd64 \
             ghcr.io/${GHCR_REPOSITORY}:${VERSION}-arm64
+
+      - name: Output manifest digest
+        run: |
+          echo "### Multi-arch Manifest Digests" >> $GITHUB_STEP_SUMMARY
+          echo '```' >> $GITHUB_STEP_SUMMARY
+          docker buildx imagetools inspect calciumion/new-api:alpha >> $GITHUB_STEP_SUMMARY
+          echo "---" >> $GITHUB_STEP_SUMMARY
+          docker buildx imagetools inspect ghcr.io/${GHCR_REPOSITORY}:alpha >> $GITHUB_STEP_SUMMARY
+          echo '```' >> $GITHUB_STEP_SUMMARY

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

@@ -30,10 +30,11 @@ jobs:
     permissions:
       packages: write
       contents: read
+      id-token: write
 
     steps:
       - name: Check out
-        uses: actions/checkout@v4
+        uses: actions/checkout@34e114876b0b11c390a56381ad16ebd13914f8d5 # v4
         with:
           fetch-depth: ${{ github.event_name == 'workflow_dispatch' && 0 || 1 }}
           ref: ${{ github.event.inputs.tag || github.ref }}
@@ -59,16 +60,16 @@ jobs:
 #        run: echo "GHCR_REPOSITORY=${GITHUB_REPOSITORY,,}" >> $GITHUB_ENV
 
       - name: Set up Docker Buildx
-        uses: docker/setup-buildx-action@v3
+        uses: docker/setup-buildx-action@8d2750c68a42422c14e847fe6c8ac0403b4cbd6f # v3
 
       - name: Log in to Docker Hub
-        uses: docker/login-action@v3
+        uses: docker/login-action@c94ce9fb468520275223c153574b00df6fe4bcc9 # v3
         with:
           username: ${{ secrets.DOCKERHUB_USERNAME }}
           password: ${{ secrets.DOCKERHUB_TOKEN }}
 
 #      - name: Log in to GHCR
-#        uses: docker/login-action@v3
+#        uses: docker/login-action@c94ce9fb468520275223c153574b00df6fe4bcc9 # v3
 #        with:
 #          registry: ghcr.io
 #          username: ${{ github.actor }}
@@ -76,14 +77,15 @@ jobs:
 
       - name: Extract metadata (labels)
         id: meta
-        uses: docker/metadata-action@v5
+        uses: docker/metadata-action@c299e40c65443455700f0fdfc63efafe5b349051 # v5
         with:
           images: |
             calciumion/new-api
 #            ghcr.io/${{ env.GHCR_REPOSITORY }}
 
       - name: Build & push single-arch (to both registries)
-        uses: docker/build-push-action@v6
+        id: build
+        uses: docker/build-push-action@10e90e3645eae34f1e60eeb005ba3a3d33f178e8 # v6
         with:
           context: .
           platforms: ${{ matrix.platform }}
@@ -96,8 +98,22 @@ jobs:
           labels: ${{ steps.meta.outputs.labels }}
           cache-from: type=gha
           cache-to: type=gha,mode=max
-          provenance: false
-          sbom: false
+          provenance: mode=max
+          sbom: true
+
+      - name: Install cosign
+        uses: sigstore/cosign-installer@398d4b0eeef1380460a10c8013a76f728fb906ac # v3
+
+      - name: Sign image with cosign
+        run: cosign sign --yes calciumion/new-api@${{ steps.build.outputs.digest }}
+
+      - name: Output digest
+        run: |
+          echo "### Docker Image Digest (${{ matrix.arch }})" >> $GITHUB_STEP_SUMMARY
+          echo '```' >> $GITHUB_STEP_SUMMARY
+          echo "calciumion/new-api:${{ env.TAG }}-${{ matrix.arch }}" >> $GITHUB_STEP_SUMMARY
+          echo "${{ steps.build.outputs.digest }}" >> $GITHUB_STEP_SUMMARY
+          echo '```' >> $GITHUB_STEP_SUMMARY
 
   create_manifests:
     name: Create multi-arch manifests (Docker Hub)
@@ -117,7 +133,7 @@ jobs:
 #        run: echo "GHCR_REPOSITORY=${GITHUB_REPOSITORY,,}" >> $GITHUB_ENV
 
       - name: Log in to Docker Hub
-        uses: docker/login-action@v3
+        uses: docker/login-action@c94ce9fb468520275223c153574b00df6fe4bcc9 # v3
         with:
           username: ${{ secrets.DOCKERHUB_USERNAME }}
           password: ${{ secrets.DOCKERHUB_TOKEN }}
@@ -136,9 +152,16 @@ jobs:
             calciumion/new-api:latest-amd64 \
             calciumion/new-api:latest-arm64
 
+      - name: Output manifest digest
+        run: |
+          echo "### Multi-arch Manifest" >> $GITHUB_STEP_SUMMARY
+          echo '```' >> $GITHUB_STEP_SUMMARY
+          docker buildx imagetools inspect calciumion/new-api:${TAG} >> $GITHUB_STEP_SUMMARY
+          echo '```' >> $GITHUB_STEP_SUMMARY
+
       # ---- GHCR ----
 #      - name: Log in to GHCR
-#        uses: docker/login-action@v3
+#        uses: docker/login-action@c94ce9fb468520275223c153574b00df6fe4bcc9 # v3
 #        with:
 #          registry: ghcr.io
 #          username: ${{ github.actor }}

.github/workflows/release.yml

@@ -19,14 +19,14 @@ jobs:
     runs-on: ubuntu-latest
     steps:
       - name: Checkout
-        uses: actions/checkout@v3
+        uses: actions/checkout@34e114876b0b11c390a56381ad16ebd13914f8d5 # v4
         with:
           fetch-depth: 0
       - name: Determine Version
         run: |
           VERSION=$(git describe --tags)
           echo "VERSION=$VERSION" >> $GITHUB_ENV
-      - uses: oven-sh/setup-bun@v2
+      - uses: oven-sh/setup-bun@0c5077e51419868618aeaa5fe8019c62421857d6 # v2
         with:
           bun-version: latest
       - name: Build Frontend
@@ -38,7 +38,7 @@ jobs:
           DISABLE_ESLINT_PLUGIN='true' VITE_REACT_APP_VERSION=$VERSION bun run build
           cd ..
       - name: Set up Go
-        uses: actions/setup-go@v3
+        uses: actions/setup-go@40f1582b2485089dde7abd97c1529aa768e1baff # v5
         with:
           go-version: '>=1.25.1'
       - name: Build Backend (amd64)
@@ -50,12 +50,16 @@ jobs:
           sudo apt-get update
           DEBIAN_FRONTEND=noninteractive sudo apt-get install -y gcc-aarch64-linux-gnu
           CC=aarch64-linux-gnu-gcc CGO_ENABLED=1 GOOS=linux GOARCH=arm64 go build -ldflags "-s -w -X 'new-api/common.Version=$VERSION' -extldflags '-static'" -o new-api-arm64-$VERSION
+      - name: Generate checksums
+        run: sha256sum new-api-* > checksums-linux.txt
+
       - name: Release
-        uses: softprops/action-gh-release@v2
+        uses: softprops/action-gh-release@153bb8e04406b158c6c84fc1615b65b24149a1fe # v2
         if: startsWith(github.ref, 'refs/tags/')
         with:
           files: |
             new-api-*
+            checksums-linux.txt
         env:
           GITHUB_TOKEN: ${{ secrets.GITHUB_TOKEN }}
 
@@ -64,14 +68,14 @@ jobs:
     runs-on: macos-latest
     steps:
       - name: Checkout
-        uses: actions/checkout@v3
+        uses: actions/checkout@34e114876b0b11c390a56381ad16ebd13914f8d5 # v4
         with:
           fetch-depth: 0
       - name: Determine Version
         run: |
           VERSION=$(git describe --tags)
           echo "VERSION=$VERSION" >> $GITHUB_ENV
-      - uses: oven-sh/setup-bun@v2
+      - uses: oven-sh/setup-bun@0c5077e51419868618aeaa5fe8019c62421857d6 # v2
         with:
           bun-version: latest
       - name: Build Frontend
@@ -84,18 +88,23 @@ jobs:
           DISABLE_ESLINT_PLUGIN='true' VITE_REACT_APP_VERSION=$VERSION bun run build
           cd ..
       - name: Set up Go
-        uses: actions/setup-go@v3
+        uses: actions/setup-go@40f1582b2485089dde7abd97c1529aa768e1baff # v5
         with:
           go-version: '>=1.25.1'
       - name: Build Backend
         run: |
           go mod download
           go build -ldflags "-X 'new-api/common.Version=$VERSION'" -o new-api-macos-$VERSION
+      - name: Generate checksums
+        run: shasum -a 256 new-api-macos-* > checksums-macos.txt
+
       - name: Release
-        uses: softprops/action-gh-release@v2
+        uses: softprops/action-gh-release@153bb8e04406b158c6c84fc1615b65b24149a1fe # v2
         if: startsWith(github.ref, 'refs/tags/')
         with:
-          files: new-api-macos-*
+          files: |
+            new-api-macos-*
+            checksums-macos.txt
         env:
           GITHUB_TOKEN: ${{ secrets.GITHUB_TOKEN }}
 
@@ -107,14 +116,14 @@ jobs:
         shell: bash
     steps:
       - name: Checkout
-        uses: actions/checkout@v3
+        uses: actions/checkout@34e114876b0b11c390a56381ad16ebd13914f8d5 # v4
         with:
           fetch-depth: 0
       - name: Determine Version
         run: |
           VERSION=$(git describe --tags)
           echo "VERSION=$VERSION" >> $GITHUB_ENV
-      - uses: oven-sh/setup-bun@v2
+      - uses: oven-sh/setup-bun@0c5077e51419868618aeaa5fe8019c62421857d6 # v2
         with:
           bun-version: latest
       - name: Build Frontend
@@ -126,17 +135,22 @@ jobs:
           DISABLE_ESLINT_PLUGIN='true' VITE_REACT_APP_VERSION=$VERSION bun run build
           cd ..
       - name: Set up Go
-        uses: actions/setup-go@v3
+        uses: actions/setup-go@40f1582b2485089dde7abd97c1529aa768e1baff # v5
         with:
           go-version: '>=1.25.1'
       - name: Build Backend
         run: |
           go mod download
           go build -ldflags "-s -w -X 'new-api/common.Version=$VERSION'" -o new-api-$VERSION.exe
+      - name: Generate checksums
+        run: sha256sum new-api-*.exe > checksums-windows.txt
+
       - name: Release
-        uses: softprops/action-gh-release@v2
+        uses: softprops/action-gh-release@153bb8e04406b158c6c84fc1615b65b24149a1fe # v2
         if: startsWith(github.ref, 'refs/tags/')
         with:
-          files: new-api-*.exe
+          files: |
+            new-api-*.exe
+            checksums-windows.txt
         env:
           GITHUB_TOKEN: ${{ secrets.GITHUB_TOKEN }}

Dockerfile

@@ -1,4 +1,4 @@
-FROM oven/bun:latest AS builder
+FROM oven/bun:1@sha256:0733e50325078969732ebe3b15ce4c4be5082f18c4ac1a0f0ca4839c2e4e42a7 AS builder
 
 WORKDIR /build
 COPY web/package.json .
@@ -8,7 +8,7 @@ COPY ./web .
 COPY ./VERSION .
 RUN DISABLE_ESLINT_PLUGIN='true' VITE_REACT_APP_VERSION=$(cat VERSION) bun run build
 
-FROM golang:alpine AS builder2
+FROM golang:1.26.1-alpine@sha256:2389ebfa5b7f43eeafbd6be0c3700cc46690ef842ad962f6c5bd6be49ed82039 AS builder2
 ENV GO111MODULE=on CGO_ENABLED=0
 
 ARG TARGETOS
@@ -25,7 +25,7 @@ COPY . .
 COPY --from=builder /build/dist ./web/dist
 RUN go build -ldflags "-s -w -X 'github.com/QuantumNous/new-api/common.Version=$(cat VERSION)'" -o new-api
 
-FROM debian:bookworm-slim
+FROM debian:bookworm-slim@sha256:f06537653ac770703bc45b4b113475bd402f451e85223f0f2837acbf89ab020a
 
 RUN apt-get update \
     && apt-get install -y --no-install-recommends ca-certificates tzdata libasan8 wget \

controller/channel_upstream_update.go

@@ -3,6 +3,7 @@ package controller
 import (
 	"fmt"
 	"net/http"
+	"regexp"
 	"slices"
 	"strings"
 	"sync"
@@ -169,10 +170,7 @@ func collectPendingUpstreamModelChangesFromModels(
 		upstreamSet[modelName] = struct{}{}
 	}
 
-	ignoredSet := make(map[string]struct{})
-	for _, modelName := range normalizeModelNames(ignoredModels) {
-		ignoredSet[modelName] = struct{}{}
-	}
+	normalizedIgnoredModels := normalizeModelNames(ignoredModels)
 
 	redirectSourceSet := make(map[string]struct{}, len(modelMapping))
 	redirectTargetSet := make(map[string]struct{}, len(modelMapping))
@@ -193,7 +191,13 @@ func collectPendingUpstreamModelChangesFromModels(
 		if _, ok := coveredUpstreamSet[modelName]; ok {
 			return false
 		}
-		if _, ok := ignoredSet[modelName]; ok {
+		if lo.ContainsBy(normalizedIgnoredModels, func(ignoredModel string) bool {
+			if regexBody, ok := strings.CutPrefix(ignoredModel, "regex:"); ok {
+				matched, err := regexp.MatchString(strings.TrimSpace(regexBody), modelName)
+				return err == nil && matched
+			}
+			return ignoredModel == modelName
+		}) {
 			return false
 		}
 		return true

controller/channel_upstream_update_test.go

@@ -111,6 +111,18 @@ func TestCollectPendingUpstreamModelChangesFromModels_WithModelMapping(t *testin
 	require.Equal(t, []string{"stale-model"}, pendingRemoveModels)
 }
 
+func TestCollectPendingUpstreamModelChangesFromModels_WithIgnoredRegexPatterns(t *testing.T) {
+	pendingAddModels, pendingRemoveModels := collectPendingUpstreamModelChangesFromModels(
+		[]string{"gpt-4o"},
+		[]string{"gpt-4o", "claude-3-5-sonnet", "sora-video", "gpt-4.1"},
+		[]string{"regex:^sora-.*$", "gpt-4.1"},
+		nil,
+	)
+
+	require.Equal(t, []string{"claude-3-5-sonnet"}, pendingAddModels)
+	require.Equal(t, []string{}, pendingRemoveModels)
+}
+
 func TestBuildUpstreamModelUpdateTaskNotificationContent_OmitOverflowDetails(t *testing.T) {
 	channelSummaries := make([]upstreamModelUpdateChannelSummary, 0, 12)
 	for i := 0; i < 12; i++ {

controller/oauth.go

@@ -190,7 +190,9 @@ func handleOAuthBind(c *gin.Context, provider oauth.Provider) {
 		}
 	}
 
-	common.ApiSuccessI18n(c, i18n.MsgOAuthBindSuccess, nil)
+	common.ApiSuccessI18n(c, i18n.MsgOAuthBindSuccess, gin.H{
+		"action": "bind",
+	})
 }
 
 // findOrCreateOAuthUser finds existing user or creates new user

dto/openai_request.go

@@ -393,7 +393,7 @@ func (m *MediaContent) GetVideoUrl() *MessageVideoUrl {
 
 type MessageImageUrl struct {
 	Url      string `json:"url"`
-	Detail   string `json:"detail"`
+	Detail   string `json:"detail,omitempty"`
 	MimeType string
 }
 

dto/openai_response.go

@@ -220,10 +220,12 @@ type CompletionsStreamResponse struct {
 }
 
 type Usage struct {
-	PromptTokens         int `json:"prompt_tokens"`
-	CompletionTokens     int `json:"completion_tokens"`
-	TotalTokens          int `json:"total_tokens"`
-	PromptCacheHitTokens int `json:"prompt_cache_hit_tokens,omitempty"`
+	PromptTokens         int    `json:"prompt_tokens"`
+	CompletionTokens     int    `json:"completion_tokens"`
+	TotalTokens          int    `json:"total_tokens"`
+	PromptCacheHitTokens int    `json:"prompt_cache_hit_tokens,omitempty"`
+	UsageSemantic        string `json:"usage_semantic,omitempty"`
+	UsageSource          string `json:"usage_source,omitempty"`
 
 	PromptTokensDetails    InputTokenDetails  `json:"prompt_tokens_details"`
 	CompletionTokenDetails OutputTokenDetails `json:"completion_tokens_details"`
@@ -251,7 +253,7 @@ type OpenAIVideoResponse struct {
 
 type InputTokenDetails struct {
 	CachedTokens         int `json:"cached_tokens"`
-	CachedCreationTokens int `json:"-"`
+	CachedCreationTokens int `json:"cached_creation_tokens,omitempty"`
 	TextTokens           int `json:"text_tokens"`
 	AudioTokens          int `json:"audio_tokens"`
 	ImageTokens          int `json:"image_tokens"`

middleware/distributor.go

@@ -101,8 +101,13 @@ func Distribute() func(c *gin.Context) {
 
 				if preferredChannelID, found := service.GetPreferredChannelByAffinity(c, modelRequest.Model, usingGroup); found {
 					preferred, err := model.CacheGetChannel(preferredChannelID)
-					if err == nil && preferred != nil && preferred.Status == common.ChannelStatusEnabled {
-						if usingGroup == "auto" {
+					if err == nil && preferred != nil {
+						if preferred.Status != common.ChannelStatusEnabled {
+							if service.ShouldSkipRetryAfterChannelAffinityFailure(c) {
+								abortWithOpenAiMessage(c, http.StatusForbidden, i18n.T(c, i18n.MsgDistributorChannelDisabled))
+								return
+							}
+						} else if usingGroup == "auto" {
 							userGroup := common.GetContextKeyString(c, constant.ContextKeyUserGroup)
 							autoGroups := service.GetUserAutoGroup(userGroup)
 							for _, g := range autoGroups {

relay/audio_handler.go

@@ -70,7 +70,7 @@ func AudioHelper(c *gin.Context, info *relaycommon.RelayInfo) (newAPIError *type
 	if usage.(*dto.Usage).CompletionTokenDetails.AudioTokens > 0 || usage.(*dto.Usage).PromptTokensDetails.AudioTokens > 0 {
 		service.PostAudioConsumeQuota(c, info, usage.(*dto.Usage), "")
 	} else {
-		postConsumeQuota(c, info, usage.(*dto.Usage))
+		service.PostTextConsumeQuota(c, info, usage.(*dto.Usage), nil)
 	}
 
 	return nil

relay/channel/claude/adaptor.go

@@ -5,6 +5,7 @@ import (
 	"fmt"
 	"io"
 	"net/http"
+	"net/url"
 
 	"github.com/QuantumNous/new-api/dto"
 	"github.com/QuantumNous/new-api/relay/channel"
@@ -41,11 +42,32 @@ func (a *Adaptor) Init(info *relaycommon.RelayInfo) {
 }
 
 func (a *Adaptor) GetRequestURL(info *relaycommon.RelayInfo) (string, error) {
-	baseURL := fmt.Sprintf("%s/v1/messages", info.ChannelBaseUrl)
-	if info.IsClaudeBetaQuery {
-		baseURL = baseURL + "?beta=true"
+	requestURL := fmt.Sprintf("%s/v1/messages", info.ChannelBaseUrl)
+	if !shouldAppendClaudeBetaQuery(info) {
+		return requestURL, nil
 	}
-	return baseURL, nil
+
+	parsedURL, err := url.Parse(requestURL)
+	if err != nil {
+		return "", err
+	}
+	query := parsedURL.Query()
+	query.Set("beta", "true")
+	parsedURL.RawQuery = query.Encode()
+	return parsedURL.String(), nil
+}
+
+func shouldAppendClaudeBetaQuery(info *relaycommon.RelayInfo) bool {
+	if info == nil {
+		return false
+	}
+	if info.IsClaudeBetaQuery {
+		return true
+	}
+	if info.ChannelOtherSettings.ClaudeBetaQuery {
+		return true
+	}
+	return false
 }
 
 func CommonClaudeHeadersOperation(c *gin.Context, req *http.Header, info *relaycommon.RelayInfo) {

relay/channel/claude/relay-claude.go

@@ -555,6 +555,35 @@ type ClaudeResponseInfo struct {
 	Done         bool
 }
 
+func cacheCreationTokensForOpenAIUsage(usage *dto.Usage) int {
+	if usage == nil {
+		return 0
+	}
+	splitCacheCreationTokens := usage.ClaudeCacheCreation5mTokens + usage.ClaudeCacheCreation1hTokens
+	if splitCacheCreationTokens == 0 {
+		return usage.PromptTokensDetails.CachedCreationTokens
+	}
+	if usage.PromptTokensDetails.CachedCreationTokens > splitCacheCreationTokens {
+		return usage.PromptTokensDetails.CachedCreationTokens
+	}
+	return splitCacheCreationTokens
+}
+
+func buildOpenAIStyleUsageFromClaudeUsage(usage *dto.Usage) dto.Usage {
+	if usage == nil {
+		return dto.Usage{}
+	}
+	clone := *usage
+	cacheCreationTokens := cacheCreationTokensForOpenAIUsage(usage)
+	totalInputTokens := usage.PromptTokens + usage.PromptTokensDetails.CachedTokens + cacheCreationTokens
+	clone.PromptTokens = totalInputTokens
+	clone.InputTokens = totalInputTokens
+	clone.TotalTokens = totalInputTokens + usage.CompletionTokens
+	clone.UsageSemantic = "openai"
+	clone.UsageSource = "anthropic"
+	return clone
+}
+
 func buildMessageDeltaPatchUsage(claudeResponse *dto.ClaudeResponse, claudeInfo *ClaudeResponseInfo) *dto.ClaudeUsage {
 	usage := &dto.ClaudeUsage{}
 	if claudeResponse != nil && claudeResponse.Usage != nil {
@@ -643,6 +672,7 @@ func FormatClaudeResponseInfo(claudeResponse *dto.ClaudeResponse, oaiResponse *d
 		// message_start, 获取usage
 		if claudeResponse.Message != nil && claudeResponse.Message.Usage != nil {
 			claudeInfo.Usage.PromptTokens = claudeResponse.Message.Usage.InputTokens
+			claudeInfo.Usage.UsageSemantic = "anthropic"
 			claudeInfo.Usage.PromptTokensDetails.CachedTokens = claudeResponse.Message.Usage.CacheReadInputTokens
 			claudeInfo.Usage.PromptTokensDetails.CachedCreationTokens = claudeResponse.Message.Usage.CacheCreationInputTokens
 			claudeInfo.Usage.ClaudeCacheCreation5mTokens = claudeResponse.Message.Usage.GetCacheCreation5mTokens()
@@ -661,6 +691,7 @@ func FormatClaudeResponseInfo(claudeResponse *dto.ClaudeResponse, oaiResponse *d
 	} else if claudeResponse.Type == "message_delta" {
 		// 最终的usage获取
 		if claudeResponse.Usage != nil {
+			claudeInfo.Usage.UsageSemantic = "anthropic"
 			if claudeResponse.Usage.InputTokens > 0 {
 				// 不叠加，只取最新的
 				claudeInfo.Usage.PromptTokens = claudeResponse.Usage.InputTokens
@@ -754,12 +785,16 @@ func HandleStreamFinalResponse(c *gin.Context, info *relaycommon.RelayInfo, clau
 		}
 		claudeInfo.Usage = service.ResponseText2Usage(c, claudeInfo.ResponseText.String(), info.UpstreamModelName, claudeInfo.Usage.PromptTokens)
 	}
+	if claudeInfo.Usage != nil {
+		claudeInfo.Usage.UsageSemantic = "anthropic"
+	}
 
 	if info.RelayFormat == types.RelayFormatClaude {
 		//
 	} else if info.RelayFormat == types.RelayFormatOpenAI {
 		if info.ShouldIncludeUsage {
-			response := helper.GenerateFinalUsageResponse(claudeInfo.ResponseId, claudeInfo.Created, info.UpstreamModelName, *claudeInfo.Usage)
+			openAIUsage := buildOpenAIStyleUsageFromClaudeUsage(claudeInfo.Usage)
+			response := helper.GenerateFinalUsageResponse(claudeInfo.ResponseId, claudeInfo.Created, info.UpstreamModelName, openAIUsage)
 			err := helper.ObjectData(c, response)
 			if err != nil {
 				common.SysLog("send final response failed: " + err.Error())
@@ -810,6 +845,7 @@ func HandleClaudeResponseData(c *gin.Context, info *relaycommon.RelayInfo, claud
 		claudeInfo.Usage.PromptTokens = claudeResponse.Usage.InputTokens
 		claudeInfo.Usage.CompletionTokens = claudeResponse.Usage.OutputTokens
 		claudeInfo.Usage.TotalTokens = claudeResponse.Usage.InputTokens + claudeResponse.Usage.OutputTokens
+		claudeInfo.Usage.UsageSemantic = "anthropic"
 		claudeInfo.Usage.PromptTokensDetails.CachedTokens = claudeResponse.Usage.CacheReadInputTokens
 		claudeInfo.Usage.PromptTokensDetails.CachedCreationTokens = claudeResponse.Usage.CacheCreationInputTokens
 		claudeInfo.Usage.ClaudeCacheCreation5mTokens = claudeResponse.Usage.GetCacheCreation5mTokens()
@@ -819,7 +855,7 @@ func HandleClaudeResponseData(c *gin.Context, info *relaycommon.RelayInfo, claud
 	switch info.RelayFormat {
 	case types.RelayFormatOpenAI:
 		openaiResponse := ResponseClaude2OpenAI(&claudeResponse)
-		openaiResponse.Usage = *claudeInfo.Usage
+		openaiResponse.Usage = buildOpenAIStyleUsageFromClaudeUsage(claudeInfo.Usage)
 		responseData, err = json.Marshal(openaiResponse)
 		if err != nil {
 			return types.NewError(err, types.ErrorCodeBadResponseBody)

relay/channel/claude/relay_claude_test.go

@@ -173,3 +173,85 @@ func TestFormatClaudeResponseInfo_ContentBlockDelta(t *testing.T) {
 		t.Errorf("ResponseText = %q, want %q", claudeInfo.ResponseText.String(), "hello")
 	}
 }
+
+func TestBuildOpenAIStyleUsageFromClaudeUsage(t *testing.T) {
+	usage := &dto.Usage{
+		PromptTokens:     100,
+		CompletionTokens: 20,
+		PromptTokensDetails: dto.InputTokenDetails{
+			CachedTokens:         30,
+			CachedCreationTokens: 50,
+		},
+		ClaudeCacheCreation5mTokens: 10,
+		ClaudeCacheCreation1hTokens: 20,
+		UsageSemantic:               "anthropic",
+	}
+
+	openAIUsage := buildOpenAIStyleUsageFromClaudeUsage(usage)
+
+	if openAIUsage.PromptTokens != 180 {
+		t.Fatalf("PromptTokens = %d, want 180", openAIUsage.PromptTokens)
+	}
+	if openAIUsage.InputTokens != 180 {
+		t.Fatalf("InputTokens = %d, want 180", openAIUsage.InputTokens)
+	}
+	if openAIUsage.TotalTokens != 200 {
+		t.Fatalf("TotalTokens = %d, want 200", openAIUsage.TotalTokens)
+	}
+	if openAIUsage.UsageSemantic != "openai" {
+		t.Fatalf("UsageSemantic = %s, want openai", openAIUsage.UsageSemantic)
+	}
+	if openAIUsage.UsageSource != "anthropic" {
+		t.Fatalf("UsageSource = %s, want anthropic", openAIUsage.UsageSource)
+	}
+}
+
+func TestBuildOpenAIStyleUsageFromClaudeUsagePreservesCacheCreationRemainder(t *testing.T) {
+	tests := []struct {
+		name                    string
+		cachedCreationTokens    int
+		cacheCreationTokens5m   int
+		cacheCreationTokens1h   int
+		expectedTotalInputToken int
+	}{
+		{
+			name:                    "prefers aggregate when it includes remainder",
+			cachedCreationTokens:    50,
+			cacheCreationTokens5m:   10,
+			cacheCreationTokens1h:   20,
+			expectedTotalInputToken: 180,
+		},
+		{
+			name:                    "falls back to split tokens when aggregate missing",
+			cachedCreationTokens:    0,
+			cacheCreationTokens5m:   10,
+			cacheCreationTokens1h:   20,
+			expectedTotalInputToken: 160,
+		},
+	}
+
+	for _, tt := range tests {
+		t.Run(tt.name, func(t *testing.T) {
+			usage := &dto.Usage{
+				PromptTokens:     100,
+				CompletionTokens: 20,
+				PromptTokensDetails: dto.InputTokenDetails{
+					CachedTokens:         30,
+					CachedCreationTokens: tt.cachedCreationTokens,
+				},
+				ClaudeCacheCreation5mTokens: tt.cacheCreationTokens5m,
+				ClaudeCacheCreation1hTokens: tt.cacheCreationTokens1h,
+				UsageSemantic:               "anthropic",
+			}
+
+			openAIUsage := buildOpenAIStyleUsageFromClaudeUsage(usage)
+
+			if openAIUsage.PromptTokens != tt.expectedTotalInputToken {
+				t.Fatalf("PromptTokens = %d, want %d", openAIUsage.PromptTokens, tt.expectedTotalInputToken)
+			}
+			if openAIUsage.InputTokens != tt.expectedTotalInputToken {
+				t.Fatalf("InputTokens = %d, want %d", openAIUsage.InputTokens, tt.expectedTotalInputToken)
+			}
+		})
+	}
+}

relay/claude_handler.go

@@ -122,7 +122,7 @@ func ClaudeHelper(c *gin.Context, info *relaycommon.RelayInfo) (newAPIError *typ
 			return newApiErr
 		}
 
-		service.PostClaudeConsumeQuota(c, info, usage)
+		service.PostTextConsumeQuota(c, info, usage, nil)
 		return nil
 	}
 
@@ -190,6 +190,6 @@ func ClaudeHelper(c *gin.Context, info *relaycommon.RelayInfo) (newAPIError *typ
 		return newAPIError
 	}
 
-	service.PostClaudeConsumeQuota(c, info, usage.(*dto.Usage))
+	service.PostTextConsumeQuota(c, info, usage.(*dto.Usage), nil)
 	return nil
 }

relay/common/relay_info.go

@@ -338,15 +338,10 @@ func GenRelayInfoClaude(c *gin.Context, request dto.Request) *RelayInfo {
 	info.ClaudeConvertInfo = &ClaudeConvertInfo{
 		LastMessagesType: LastMessageTypeNone,
 	}
-	info.IsClaudeBetaQuery = c.Query("beta") == "true" || isClaudeBetaForced(c)
+	info.IsClaudeBetaQuery = c.Query("beta") == "true"
 	return info
 }
 
-func isClaudeBetaForced(c *gin.Context) bool {
-	channelOtherSettings, ok := common.GetContextKeyType[dto.ChannelOtherSettings](c, constant.ContextKeyChannelOtherSetting)
-	return ok && channelOtherSettings.ClaudeBetaQuery
-}
-
 func GenRelayInfoRerank(c *gin.Context, request *dto.RerankRequest) *RelayInfo {
 	info := genBaseRelayInfo(c, request)
 	info.RelayMode = relayconstant.RelayModeRerank

relay/compatible_handler.go

@@ -6,25 +6,20 @@ import (
 	"io"
 	"net/http"
 	"strings"
-	"time"
 
 	"github.com/QuantumNous/new-api/common"
 	"github.com/QuantumNous/new-api/constant"
 	"github.com/QuantumNous/new-api/dto"
 	"github.com/QuantumNous/new-api/logger"
-	"github.com/QuantumNous/new-api/model"
 	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/model_setting"
-	"github.com/QuantumNous/new-api/setting/operation_setting"
 	"github.com/QuantumNous/new-api/setting/ratio_setting"
 	"github.com/QuantumNous/new-api/types"
 	"github.com/samber/lo"
 
-	"github.com/shopspring/decimal"
-
 	"github.com/gin-gonic/gin"
 )
 
@@ -93,7 +88,7 @@ func TextHelper(c *gin.Context, info *relaycommon.RelayInfo) (newAPIError *types
 		if containAudioTokens && containsAudioRatios {
 			service.PostAudioConsumeQuota(c, info, usage, "")
 		} else {
-			postConsumeQuota(c, info, usage)
+			service.PostTextConsumeQuota(c, info, usage, nil)
 		}
 		return nil
 	}
@@ -216,293 +211,7 @@ func TextHelper(c *gin.Context, info *relaycommon.RelayInfo) (newAPIError *types
 	if containAudioTokens && containsAudioRatios {
 		service.PostAudioConsumeQuota(c, info, usage.(*dto.Usage), "")
 	} else {
-		postConsumeQuota(c, info, usage.(*dto.Usage))
+		service.PostTextConsumeQuota(c, info, usage.(*dto.Usage), nil)
 	}
 	return nil
 }
-
-func postConsumeQuota(ctx *gin.Context, relayInfo *relaycommon.RelayInfo, usage *dto.Usage, extraContent ...string) {
-	originUsage := usage
-	if usage == nil {
-		usage = &dto.Usage{
-			PromptTokens:     relayInfo.GetEstimatePromptTokens(),
-			CompletionTokens: 0,
-			TotalTokens:      relayInfo.GetEstimatePromptTokens(),
-		}
-		extraContent = append(extraContent, "上游无计费信息")
-	}
-
-	if originUsage != nil {
-		service.ObserveChannelAffinityUsageCacheByRelayFormat(ctx, usage, relayInfo.GetFinalRequestRelayFormat())
-	}
-
-	adminRejectReason := common.GetContextKeyString(ctx, constant.ContextKeyAdminRejectReason)
-
-	useTimeSeconds := time.Now().Unix() - relayInfo.StartTime.Unix()
-	promptTokens := usage.PromptTokens
-	cacheTokens := usage.PromptTokensDetails.CachedTokens
-	imageTokens := usage.PromptTokensDetails.ImageTokens
-	audioTokens := usage.PromptTokensDetails.AudioTokens
-	completionTokens := usage.CompletionTokens
-	cachedCreationTokens := usage.PromptTokensDetails.CachedCreationTokens
-
-	modelName := relayInfo.OriginModelName
-
-	tokenName := ctx.GetString("token_name")
-	completionRatio := relayInfo.PriceData.CompletionRatio
-	cacheRatio := relayInfo.PriceData.CacheRatio
-	imageRatio := relayInfo.PriceData.ImageRatio
-	modelRatio := relayInfo.PriceData.ModelRatio
-	groupRatio := relayInfo.PriceData.GroupRatioInfo.GroupRatio
-	modelPrice := relayInfo.PriceData.ModelPrice
-	cachedCreationRatio := relayInfo.PriceData.CacheCreationRatio
-
-	// Convert values to decimal for precise calculation
-	dPromptTokens := decimal.NewFromInt(int64(promptTokens))
-	dCacheTokens := decimal.NewFromInt(int64(cacheTokens))
-	dImageTokens := decimal.NewFromInt(int64(imageTokens))
-	dAudioTokens := decimal.NewFromInt(int64(audioTokens))
-	dCompletionTokens := decimal.NewFromInt(int64(completionTokens))
-	dCachedCreationTokens := decimal.NewFromInt(int64(cachedCreationTokens))
-	dCompletionRatio := decimal.NewFromFloat(completionRatio)
-	dCacheRatio := decimal.NewFromFloat(cacheRatio)
-	dImageRatio := decimal.NewFromFloat(imageRatio)
-	dModelRatio := decimal.NewFromFloat(modelRatio)
-	dGroupRatio := decimal.NewFromFloat(groupRatio)
-	dModelPrice := decimal.NewFromFloat(modelPrice)
-	dCachedCreationRatio := decimal.NewFromFloat(cachedCreationRatio)
-	dQuotaPerUnit := decimal.NewFromFloat(common.QuotaPerUnit)
-
-	ratio := dModelRatio.Mul(dGroupRatio)
-
-	// openai web search 工具计费
-	var dWebSearchQuota decimal.Decimal
-	var webSearchPrice float64
-	// response api 格式工具计费
-	if relayInfo.ResponsesUsageInfo != nil {
-		if webSearchTool, exists := relayInfo.ResponsesUsageInfo.BuiltInTools[dto.BuildInToolWebSearchPreview]; exists && webSearchTool.CallCount > 0 {
-			// 计算 web search 调用的配额 (配额 = 价格 * 调用次数 / 1000 * 分组倍率)
-			webSearchPrice = operation_setting.GetWebSearchPricePerThousand(modelName, webSearchTool.SearchContextSize)
-			dWebSearchQuota = decimal.NewFromFloat(webSearchPrice).
-				Mul(decimal.NewFromInt(int64(webSearchTool.CallCount))).
-				Div(decimal.NewFromInt(1000)).Mul(dGroupRatio).Mul(dQuotaPerUnit)
-			extraContent = append(extraContent, fmt.Sprintf("Web Search 调用 %d 次，上下文大小 %s，调用花费 %s",
-				webSearchTool.CallCount, webSearchTool.SearchContextSize, dWebSearchQuota.String()))
-		}
-	} else if strings.HasSuffix(modelName, "search-preview") {
-		// search-preview 模型不支持 response api
-		searchContextSize := ctx.GetString("chat_completion_web_search_context_size")
-		if searchContextSize == "" {
-			searchContextSize = "medium"
-		}
-		webSearchPrice = operation_setting.GetWebSearchPricePerThousand(modelName, searchContextSize)
-		dWebSearchQuota = decimal.NewFromFloat(webSearchPrice).
-			Div(decimal.NewFromInt(1000)).Mul(dGroupRatio).Mul(dQuotaPerUnit)
-		extraContent = append(extraContent, fmt.Sprintf("Web Search 调用 1 次，上下文大小 %s，调用花费 %s",
-			searchContextSize, dWebSearchQuota.String()))
-	}
-	// claude web search tool 计费
-	var dClaudeWebSearchQuota decimal.Decimal
-	var claudeWebSearchPrice float64
-	claudeWebSearchCallCount := ctx.GetInt("claude_web_search_requests")
-	if claudeWebSearchCallCount > 0 {
-		claudeWebSearchPrice = operation_setting.GetClaudeWebSearchPricePerThousand()
-		dClaudeWebSearchQuota = decimal.NewFromFloat(claudeWebSearchPrice).
-			Div(decimal.NewFromInt(1000)).Mul(dGroupRatio).Mul(dQuotaPerUnit).Mul(decimal.NewFromInt(int64(claudeWebSearchCallCount)))
-		extraContent = append(extraContent, fmt.Sprintf("Claude Web Search 调用 %d 次，调用花费 %s",
-			claudeWebSearchCallCount, dClaudeWebSearchQuota.String()))
-	}
-	// file search tool 计费
-	var dFileSearchQuota decimal.Decimal
-	var fileSearchPrice float64
-	if relayInfo.ResponsesUsageInfo != nil {
-		if fileSearchTool, exists := relayInfo.ResponsesUsageInfo.BuiltInTools[dto.BuildInToolFileSearch]; exists && fileSearchTool.CallCount > 0 {
-			fileSearchPrice = operation_setting.GetFileSearchPricePerThousand()
-			dFileSearchQuota = decimal.NewFromFloat(fileSearchPrice).
-				Mul(decimal.NewFromInt(int64(fileSearchTool.CallCount))).
-				Div(decimal.NewFromInt(1000)).Mul(dGroupRatio).Mul(dQuotaPerUnit)
-			extraContent = append(extraContent, fmt.Sprintf("File Search 调用 %d 次，调用花费 %s",
-				fileSearchTool.CallCount, dFileSearchQuota.String()))
-		}
-	}
-	var dImageGenerationCallQuota decimal.Decimal
-	var imageGenerationCallPrice float64
-	if ctx.GetBool("image_generation_call") {
-		imageGenerationCallPrice = operation_setting.GetGPTImage1PriceOnceCall(ctx.GetString("image_generation_call_quality"), ctx.GetString("image_generation_call_size"))
-		dImageGenerationCallQuota = decimal.NewFromFloat(imageGenerationCallPrice).Mul(dGroupRatio).Mul(dQuotaPerUnit)
-		extraContent = append(extraContent, fmt.Sprintf("Image Generation Call 花费 %s", dImageGenerationCallQuota.String()))
-	}
-
-	var quotaCalculateDecimal decimal.Decimal
-
-	var audioInputQuota decimal.Decimal
-	var audioInputPrice float64
-	isClaudeUsageSemantic := relayInfo.GetFinalRequestRelayFormat() == types.RelayFormatClaude
-	if !relayInfo.PriceData.UsePrice {
-		baseTokens := dPromptTokens
-		// 减去 cached tokens
-		// Anthropic API 的 input_tokens 已经不包含缓存 tokens，不需要减去
-		// OpenAI/OpenRouter 等 API 的 prompt_tokens 包含缓存 tokens，需要减去
-		var cachedTokensWithRatio decimal.Decimal
-		if !dCacheTokens.IsZero() {
-			if !isClaudeUsageSemantic {
-				baseTokens = baseTokens.Sub(dCacheTokens)
-			}
-			cachedTokensWithRatio = dCacheTokens.Mul(dCacheRatio)
-		}
-		var dCachedCreationTokensWithRatio decimal.Decimal
-		if !dCachedCreationTokens.IsZero() {
-			if !isClaudeUsageSemantic {
-				baseTokens = baseTokens.Sub(dCachedCreationTokens)
-			}
-			dCachedCreationTokensWithRatio = dCachedCreationTokens.Mul(dCachedCreationRatio)
-		}
-
-		// 减去 image tokens
-		var imageTokensWithRatio decimal.Decimal
-		if !dImageTokens.IsZero() {
-			baseTokens = baseTokens.Sub(dImageTokens)
-			imageTokensWithRatio = dImageTokens.Mul(dImageRatio)
-		}
-
-		// 减去 Gemini audio tokens
-		if !dAudioTokens.IsZero() {
-			audioInputPrice = operation_setting.GetGeminiInputAudioPricePerMillionTokens(modelName)
-			if audioInputPrice > 0 {
-				// 重新计算 base tokens
-				baseTokens = baseTokens.Sub(dAudioTokens)
-				audioInputQuota = decimal.NewFromFloat(audioInputPrice).Div(decimal.NewFromInt(1000000)).Mul(dAudioTokens).Mul(dGroupRatio).Mul(dQuotaPerUnit)
-				extraContent = append(extraContent, fmt.Sprintf("Audio Input 花费 %s", audioInputQuota.String()))
-			}
-		}
-		promptQuota := baseTokens.Add(cachedTokensWithRatio).
-			Add(imageTokensWithRatio).
-			Add(dCachedCreationTokensWithRatio)
-
-		completionQuota := dCompletionTokens.Mul(dCompletionRatio)
-
-		quotaCalculateDecimal = promptQuota.Add(completionQuota).Mul(ratio)
-
-		if !ratio.IsZero() && quotaCalculateDecimal.LessThanOrEqual(decimal.Zero) {
-			quotaCalculateDecimal = decimal.NewFromInt(1)
-		}
-	} else {
-		quotaCalculateDecimal = dModelPrice.Mul(dQuotaPerUnit).Mul(dGroupRatio)
-	}
-	// 添加 responses tools call 调用的配额
-	quotaCalculateDecimal = quotaCalculateDecimal.Add(dWebSearchQuota)
-	quotaCalculateDecimal = quotaCalculateDecimal.Add(dFileSearchQuota)
-	// 添加 audio input 独立计费
-	quotaCalculateDecimal = quotaCalculateDecimal.Add(audioInputQuota)
-	// 添加 image generation call 计费
-	quotaCalculateDecimal = quotaCalculateDecimal.Add(dImageGenerationCallQuota)
-
-	if len(relayInfo.PriceData.OtherRatios) > 0 {
-		for key, otherRatio := range relayInfo.PriceData.OtherRatios {
-			dOtherRatio := decimal.NewFromFloat(otherRatio)
-			quotaCalculateDecimal = quotaCalculateDecimal.Mul(dOtherRatio)
-			extraContent = append(extraContent, fmt.Sprintf("其他倍率 %s: %f", key, otherRatio))
-		}
-	}
-
-	quota := int(quotaCalculateDecimal.Round(0).IntPart())
-	totalTokens := promptTokens + completionTokens
-
-	//var logContent string
-
-	// record all the consume log even if quota is 0
-	if totalTokens == 0 {
-		// in this case, must be some error happened
-		// we cannot just return, because we may have to return the pre-consumed quota
-		quota = 0
-		extraContent = append(extraContent, "上游没有返回计费信息，无法扣费（可能是上游超时）")
-		logger.LogError(ctx, fmt.Sprintf("total tokens is 0, cannot consume quota, userId %d, channelId %d, "+
-			"tokenId %d, model %s， pre-consumed quota %d", relayInfo.UserId, relayInfo.ChannelId, relayInfo.TokenId, modelName, relayInfo.FinalPreConsumedQuota))
-	} else {
-		if !ratio.IsZero() && quota == 0 {
-			quota = 1
-		}
-		model.UpdateUserUsedQuotaAndRequestCount(relayInfo.UserId, quota)
-		model.UpdateChannelUsedQuota(relayInfo.ChannelId, quota)
-	}
-
-	if err := service.SettleBilling(ctx, relayInfo, quota); err != nil {
-		logger.LogError(ctx, "error settling billing: "+err.Error())
-	}
-
-	logModel := modelName
-	if strings.HasPrefix(logModel, "gpt-4-gizmo") {
-		logModel = "gpt-4-gizmo-*"
-		extraContent = append(extraContent, fmt.Sprintf("模型 %s", modelName))
-	}
-	if strings.HasPrefix(logModel, "gpt-4o-gizmo") {
-		logModel = "gpt-4o-gizmo-*"
-		extraContent = append(extraContent, fmt.Sprintf("模型 %s", modelName))
-	}
-	logContent := strings.Join(extraContent, ", ")
-	other := service.GenerateTextOtherInfo(ctx, relayInfo, modelRatio, groupRatio, completionRatio, cacheTokens, cacheRatio, modelPrice, relayInfo.PriceData.GroupRatioInfo.GroupSpecialRatio)
-	if adminRejectReason != "" {
-		other["reject_reason"] = adminRejectReason
-	}
-	// For chat-based calls to the Claude model, tagging is required. Using Claude's rendering logs, the two approaches handle input rendering differently.
-	if isClaudeUsageSemantic {
-		other["claude"] = true
-		other["usage_semantic"] = "anthropic"
-	}
-	if imageTokens != 0 {
-		other["image"] = true
-		other["image_ratio"] = imageRatio
-		other["image_output"] = imageTokens
-	}
-	if cachedCreationTokens != 0 {
-		other["cache_creation_tokens"] = cachedCreationTokens
-		other["cache_creation_ratio"] = cachedCreationRatio
-	}
-	if !dWebSearchQuota.IsZero() {
-		if relayInfo.ResponsesUsageInfo != nil {
-			if webSearchTool, exists := relayInfo.ResponsesUsageInfo.BuiltInTools[dto.BuildInToolWebSearchPreview]; exists {
-				other["web_search"] = true
-				other["web_search_call_count"] = webSearchTool.CallCount
-				other["web_search_price"] = webSearchPrice
-			}
-		} else if strings.HasSuffix(modelName, "search-preview") {
-			other["web_search"] = true
-			other["web_search_call_count"] = 1
-			other["web_search_price"] = webSearchPrice
-		}
-	} else if !dClaudeWebSearchQuota.IsZero() {
-		other["web_search"] = true
-		other["web_search_call_count"] = claudeWebSearchCallCount
-		other["web_search_price"] = claudeWebSearchPrice
-	}
-	if !dFileSearchQuota.IsZero() && relayInfo.ResponsesUsageInfo != nil {
-		if fileSearchTool, exists := relayInfo.ResponsesUsageInfo.BuiltInTools[dto.BuildInToolFileSearch]; exists {
-			other["file_search"] = true
-			other["file_search_call_count"] = fileSearchTool.CallCount
-			other["file_search_price"] = fileSearchPrice
-		}
-	}
-	if !audioInputQuota.IsZero() {
-		other["audio_input_seperate_price"] = true
-		other["audio_input_token_count"] = audioTokens
-		other["audio_input_price"] = audioInputPrice
-	}
-	if !dImageGenerationCallQuota.IsZero() {
-		other["image_generation_call"] = true
-		other["image_generation_call_price"] = imageGenerationCallPrice
-	}
-	model.RecordConsumeLog(ctx, relayInfo.UserId, model.RecordConsumeLogParams{
-		ChannelId:        relayInfo.ChannelId,
-		PromptTokens:     promptTokens,
-		CompletionTokens: completionTokens,
-		ModelName:        logModel,
-		TokenName:        tokenName,
-		Quota:            quota,
-		Content:          logContent,
-		TokenId:          relayInfo.TokenId,
-		UseTimeSeconds:   int(useTimeSeconds),
-		IsStream:         relayInfo.IsStream,
-		Group:            relayInfo.UsingGroup,
-		Other:            other,
-	})
-}

relay/embedding_handler.go

@@ -82,6 +82,6 @@ func EmbeddingHelper(c *gin.Context, info *relaycommon.RelayInfo) (newAPIError *
 		service.ResetStatusCode(newAPIError, statusCodeMappingStr)
 		return newAPIError
 	}
-	postConsumeQuota(c, info, usage.(*dto.Usage))
+	service.PostTextConsumeQuota(c, info, usage.(*dto.Usage), nil)
 	return nil
 }

relay/gemini_handler.go

@@ -194,7 +194,7 @@ func GeminiHelper(c *gin.Context, info *relaycommon.RelayInfo) (newAPIError *typ
 		return openaiErr
 	}
 
-	postConsumeQuota(c, info, usage.(*dto.Usage))
+	service.PostTextConsumeQuota(c, info, usage.(*dto.Usage), nil)
 	return nil
 }
 
@@ -288,6 +288,6 @@ func GeminiEmbeddingHandler(c *gin.Context, info *relaycommon.RelayInfo) (newAPI
 		return openaiErr
 	}
 
-	postConsumeQuota(c, info, usage.(*dto.Usage))
+	service.PostTextConsumeQuota(c, info, usage.(*dto.Usage), nil)
 	return nil
 }

relay/image_handler.go

@@ -141,6 +141,6 @@ func ImageHelper(c *gin.Context, info *relaycommon.RelayInfo) (newAPIError *type
 		logContent = append(logContent, fmt.Sprintf("生成数量 %d", imageN))
 	}
 
-	postConsumeQuota(c, info, usage.(*dto.Usage), logContent...)
+	service.PostTextConsumeQuota(c, info, usage.(*dto.Usage), logContent)
 	return nil
 }

relay/rerank_handler.go

@@ -96,6 +96,6 @@ func RerankHelper(c *gin.Context, info *relaycommon.RelayInfo) (newAPIError *typ
 		service.ResetStatusCode(newAPIError, statusCodeMappingStr)
 		return newAPIError
 	}
-	postConsumeQuota(c, info, usage.(*dto.Usage))
+	service.PostTextConsumeQuota(c, info, usage.(*dto.Usage), nil)
 	return nil
 }

relay/responses_handler.go

@@ -145,7 +145,7 @@ func ResponsesHelper(c *gin.Context, info *relaycommon.RelayInfo) (newAPIError *
 			info.PriceData = originPriceData
 			return types.NewError(err, types.ErrorCodeModelPriceError, types.ErrOptionWithSkipRetry())
 		}
-		postConsumeQuota(c, info, usageDto)
+		service.PostTextConsumeQuota(c, info, usageDto, nil)
 
 		info.OriginModelName = originModelName
 		info.PriceData = originPriceData
@@ -155,7 +155,7 @@ func ResponsesHelper(c *gin.Context, info *relaycommon.RelayInfo) (newAPIError *
 	if strings.HasPrefix(info.OriginModelName, "gpt-4o-audio") {
 		service.PostAudioConsumeQuota(c, info, usageDto, "")
 	} else {
-		postConsumeQuota(c, info, usageDto)
+		service.PostTextConsumeQuota(c, info, usageDto, nil)
 	}
 	return nil
 }

service/channel_affinity.go

@@ -610,14 +610,17 @@ func ShouldSkipRetryAfterChannelAffinityFailure(c *gin.Context) bool {
 		return false
 	}
 	v, ok := c.Get(ginKeyChannelAffinitySkipRetry)
+	if ok {
+		b, ok := v.(bool)
+		if ok {
+			return b
+		}
+	}
+	meta, ok := getChannelAffinityMeta(c)
 	if !ok {
 		return false
 	}
-	b, ok := v.(bool)
-	if !ok {
-		return false
-	}
-	return b
+	return meta.SkipRetry
 }
 
 func MarkChannelAffinityUsed(c *gin.Context, selectedGroup string, channelID int) {

service/channel_affinity_template_test.go

@@ -116,6 +116,66 @@ func TestApplyChannelAffinityOverrideTemplate_MergeOperations(t *testing.T) {
 	require.Equal(t, "trim_prefix", secondOp["mode"])
 }
 
+func TestShouldSkipRetryAfterChannelAffinityFailure(t *testing.T) {
+	tests := []struct {
+		name string
+		ctx  func() *gin.Context
+		want bool
+	}{
+		{
+			name: "nil context",
+			ctx: func() *gin.Context {
+				return nil
+			},
+			want: false,
+		},
+		{
+			name: "explicit skip retry flag in context",
+			ctx: func() *gin.Context {
+				ctx := buildChannelAffinityTemplateContextForTest(channelAffinityMeta{
+					RuleName:   "rule-explicit-flag",
+					SkipRetry:  false,
+					UsingGroup: "default",
+					ModelName:  "gpt-5",
+				})
+				ctx.Set(ginKeyChannelAffinitySkipRetry, true)
+				return ctx
+			},
+			want: true,
+		},
+		{
+			name: "fallback to matched rule meta",
+			ctx: func() *gin.Context {
+				return buildChannelAffinityTemplateContextForTest(channelAffinityMeta{
+					RuleName:   "rule-skip-retry",
+					SkipRetry:  true,
+					UsingGroup: "default",
+					ModelName:  "gpt-5",
+				})
+			},
+			want: true,
+		},
+		{
+			name: "no flag and no skip retry meta",
+			ctx: func() *gin.Context {
+				return buildChannelAffinityTemplateContextForTest(channelAffinityMeta{
+					RuleName:   "rule-no-skip-retry",
+					SkipRetry:  false,
+					UsingGroup: "default",
+					ModelName:  "gpt-5",
+				})
+			},
+			want: false,
+		},
+	}
+
+	for _, tt := range tests {
+		t.Run(tt.name, func(t *testing.T) {
+			require.Equal(t, tt.want, ShouldSkipRetryAfterChannelAffinityFailure(tt.ctx()))
+		})
+	}
+}
+
 func TestChannelAffinityHitCodexTemplatePassHeadersEffective(t *testing.T) {
 	gin.SetMode(gin.TestMode)
 

service/convert.go

@@ -223,6 +223,25 @@ func generateStopBlock(index int) *dto.ClaudeResponse {
 	}
 }
 
+func buildClaudeUsageFromOpenAIUsage(oaiUsage *dto.Usage) *dto.ClaudeUsage {
+	if oaiUsage == nil {
+		return nil
+	}
+	usage := &dto.ClaudeUsage{
+		InputTokens:              oaiUsage.PromptTokens,
+		OutputTokens:             oaiUsage.CompletionTokens,
+		CacheCreationInputTokens: oaiUsage.PromptTokensDetails.CachedCreationTokens,
+		CacheReadInputTokens:     oaiUsage.PromptTokensDetails.CachedTokens,
+	}
+	if oaiUsage.ClaudeCacheCreation5mTokens > 0 || oaiUsage.ClaudeCacheCreation1hTokens > 0 {
+		usage.CacheCreation = &dto.ClaudeCacheCreationUsage{
+			Ephemeral5mInputTokens: oaiUsage.ClaudeCacheCreation5mTokens,
+			Ephemeral1hInputTokens: oaiUsage.ClaudeCacheCreation1hTokens,
+		}
+	}
+	return usage
+}
+
 func StreamResponseOpenAI2Claude(openAIResponse *dto.ChatCompletionsStreamResponse, info *relaycommon.RelayInfo) []*dto.ClaudeResponse {
 	if info.ClaudeConvertInfo.Done {
 		return nil
@@ -391,13 +410,8 @@ func StreamResponseOpenAI2Claude(openAIResponse *dto.ChatCompletionsStreamRespon
 			}
 			if oaiUsage != nil {
 				claudeResponses = append(claudeResponses, &dto.ClaudeResponse{
-					Type: "message_delta",
-					Usage: &dto.ClaudeUsage{
-						InputTokens:              oaiUsage.PromptTokens,
-						OutputTokens:             oaiUsage.CompletionTokens,
-						CacheCreationInputTokens: oaiUsage.PromptTokensDetails.CachedCreationTokens,
-						CacheReadInputTokens:     oaiUsage.PromptTokensDetails.CachedTokens,
-					},
+					Type:  "message_delta",
+					Usage: buildClaudeUsageFromOpenAIUsage(oaiUsage),
 					Delta: &dto.ClaudeMediaMessage{
 						StopReason: common.GetPointer[string](stopReasonOpenAI2Claude(info.FinishReason)),
 					},
@@ -419,13 +433,8 @@ func StreamResponseOpenAI2Claude(openAIResponse *dto.ChatCompletionsStreamRespon
 			oaiUsage := info.ClaudeConvertInfo.Usage
 			if oaiUsage != nil {
 				claudeResponses = append(claudeResponses, &dto.ClaudeResponse{
-					Type: "message_delta",
-					Usage: &dto.ClaudeUsage{
-						InputTokens:              oaiUsage.PromptTokens,
-						OutputTokens:             oaiUsage.CompletionTokens,
-						CacheCreationInputTokens: oaiUsage.PromptTokensDetails.CachedCreationTokens,
-						CacheReadInputTokens:     oaiUsage.PromptTokensDetails.CachedTokens,
-					},
+					Type:  "message_delta",
+					Usage: buildClaudeUsageFromOpenAIUsage(oaiUsage),
 					Delta: &dto.ClaudeMediaMessage{
 						StopReason: common.GetPointer[string](stopReasonOpenAI2Claude(info.FinishReason)),
 					},
@@ -555,13 +564,8 @@ func StreamResponseOpenAI2Claude(openAIResponse *dto.ChatCompletionsStreamRespon
 			}
 			if oaiUsage != nil {
 				claudeResponses = append(claudeResponses, &dto.ClaudeResponse{
-					Type: "message_delta",
-					Usage: &dto.ClaudeUsage{
-						InputTokens:              oaiUsage.PromptTokens,
-						OutputTokens:             oaiUsage.CompletionTokens,
-						CacheCreationInputTokens: oaiUsage.PromptTokensDetails.CachedCreationTokens,
-						CacheReadInputTokens:     oaiUsage.PromptTokensDetails.CachedTokens,
-					},
+					Type:  "message_delta",
+					Usage: buildClaudeUsageFromOpenAIUsage(oaiUsage),
 					Delta: &dto.ClaudeMediaMessage{
 						StopReason: common.GetPointer[string](stopReasonOpenAI2Claude(info.FinishReason)),
 					},

service/log_info_generate.go

@@ -73,6 +73,7 @@ func GenerateTextOtherInfo(ctx *gin.Context, relayInfo *relaycommon.RelayInfo, m
 	other["admin_info"] = adminInfo
 	appendRequestPath(ctx, relayInfo, other)
 	appendRequestConversionChain(relayInfo, other)
+	appendFinalRequestFormat(relayInfo, other)
 	appendBillingInfo(relayInfo, other)
 	appendParamOverrideInfo(relayInfo, other)
 	return other
@@ -167,6 +168,17 @@ func appendRequestConversionChain(relayInfo *relaycommon.RelayInfo, other map[st
 	other["request_conversion"] = chain
 }
 
+func appendFinalRequestFormat(relayInfo *relaycommon.RelayInfo, other map[string]interface{}) {
+	if relayInfo == nil || other == nil {
+		return
+	}
+	if relayInfo.GetFinalRequestRelayFormat() == types.RelayFormatClaude {
+		// claude indicates the final upstream request format is Claude Messages.
+		// Frontend log rendering uses this to keep the original Claude input display.
+		other["claude"] = true
+	}
+}
+
 func GenerateWssOtherInfo(ctx *gin.Context, relayInfo *relaycommon.RelayInfo, usage *dto.RealtimeUsage, modelRatio, groupRatio, completionRatio, audioRatio, audioCompletionRatio, modelPrice, userGroupRatio float64) map[string]interface{} {
 	info := GenerateTextOtherInfo(ctx, relayInfo, modelRatio, groupRatio, completionRatio, 0, 0.0, modelPrice, userGroupRatio)
 	info["ws"] = true

service/quota.go

@@ -235,108 +235,6 @@ func PostWssConsumeQuota(ctx *gin.Context, relayInfo *relaycommon.RelayInfo, mod
 	})
 }
 
-func PostClaudeConsumeQuota(ctx *gin.Context, relayInfo *relaycommon.RelayInfo, usage *dto.Usage) {
-	if usage != nil {
-		ObserveChannelAffinityUsageCacheByRelayFormat(ctx, usage, relayInfo.GetFinalRequestRelayFormat())
-	}
-
-	useTimeSeconds := time.Now().Unix() - relayInfo.StartTime.Unix()
-	promptTokens := usage.PromptTokens
-	completionTokens := usage.CompletionTokens
-	modelName := relayInfo.OriginModelName
-
-	tokenName := ctx.GetString("token_name")
-	completionRatio := relayInfo.PriceData.CompletionRatio
-	modelRatio := relayInfo.PriceData.ModelRatio
-	groupRatio := relayInfo.PriceData.GroupRatioInfo.GroupRatio
-	modelPrice := relayInfo.PriceData.ModelPrice
-	cacheRatio := relayInfo.PriceData.CacheRatio
-	cacheTokens := usage.PromptTokensDetails.CachedTokens
-
-	cacheCreationRatio := relayInfo.PriceData.CacheCreationRatio
-	cacheCreationRatio5m := relayInfo.PriceData.CacheCreation5mRatio
-	cacheCreationRatio1h := relayInfo.PriceData.CacheCreation1hRatio
-	cacheCreationTokens := usage.PromptTokensDetails.CachedCreationTokens
-	cacheCreationTokens5m := usage.ClaudeCacheCreation5mTokens
-	cacheCreationTokens1h := usage.ClaudeCacheCreation1hTokens
-
-	if relayInfo.ChannelType == constant.ChannelTypeOpenRouter {
-		promptTokens -= cacheTokens
-		isUsingCustomSettings := relayInfo.PriceData.UsePrice || hasCustomModelRatio(modelName, relayInfo.PriceData.ModelRatio)
-		if cacheCreationTokens == 0 && relayInfo.PriceData.CacheCreationRatio != 1 && usage.Cost != 0 && !isUsingCustomSettings {
-			maybeCacheCreationTokens := CalcOpenRouterCacheCreateTokens(*usage, relayInfo.PriceData)
-			if maybeCacheCreationTokens >= 0 && promptTokens >= maybeCacheCreationTokens {
-				cacheCreationTokens = maybeCacheCreationTokens
-			}
-		}
-		promptTokens -= cacheCreationTokens
-	}
-
-	calculateQuota := 0.0
-	if !relayInfo.PriceData.UsePrice {
-		calculateQuota = float64(promptTokens)
-		calculateQuota += float64(cacheTokens) * cacheRatio
-		calculateQuota += float64(cacheCreationTokens5m) * cacheCreationRatio5m
-		calculateQuota += float64(cacheCreationTokens1h) * cacheCreationRatio1h
-		remainingCacheCreationTokens := cacheCreationTokens - cacheCreationTokens5m - cacheCreationTokens1h
-		if remainingCacheCreationTokens > 0 {
-			calculateQuota += float64(remainingCacheCreationTokens) * cacheCreationRatio
-		}
-		calculateQuota += float64(completionTokens) * completionRatio
-		calculateQuota = calculateQuota * groupRatio * modelRatio
-	} else {
-		calculateQuota = modelPrice * common.QuotaPerUnit * groupRatio
-	}
-
-	if modelRatio != 0 && calculateQuota <= 0 {
-		calculateQuota = 1
-	}
-
-	quota := int(calculateQuota)
-
-	totalTokens := promptTokens + completionTokens
-
-	var logContent string
-	// record all the consume log even if quota is 0
-	if totalTokens == 0 {
-		// in this case, must be some error happened
-		// we cannot just return, because we may have to return the pre-consumed quota
-		quota = 0
-		logContent += fmt.Sprintf("（可能是上游出错）")
-		logger.LogError(ctx, fmt.Sprintf("total tokens is 0, cannot consume quota, userId %d, channelId %d, "+
-			"tokenId %d, model %s， pre-consumed quota %d", relayInfo.UserId, relayInfo.ChannelId, relayInfo.TokenId, modelName, relayInfo.FinalPreConsumedQuota))
-	} else {
-		model.UpdateUserUsedQuotaAndRequestCount(relayInfo.UserId, quota)
-		model.UpdateChannelUsedQuota(relayInfo.ChannelId, quota)
-	}
-
-	if err := SettleBilling(ctx, relayInfo, quota); err != nil {
-		logger.LogError(ctx, "error settling billing: "+err.Error())
-	}
-
-	other := GenerateClaudeOtherInfo(ctx, relayInfo, modelRatio, groupRatio, completionRatio,
-		cacheTokens, cacheRatio,
-		cacheCreationTokens, cacheCreationRatio,
-		cacheCreationTokens5m, cacheCreationRatio5m,
-		cacheCreationTokens1h, cacheCreationRatio1h,
-		modelPrice, relayInfo.PriceData.GroupRatioInfo.GroupSpecialRatio)
-	model.RecordConsumeLog(ctx, relayInfo.UserId, model.RecordConsumeLogParams{
-		ChannelId:        relayInfo.ChannelId,
-		PromptTokens:     promptTokens,
-		CompletionTokens: completionTokens,
-		ModelName:        modelName,
-		TokenName:        tokenName,
-		Quota:            quota,
-		Content:          logContent,
-		TokenId:          relayInfo.TokenId,
-		UseTimeSeconds:   int(useTimeSeconds),
-		IsStream:         relayInfo.IsStream,
-		Group:            relayInfo.UsingGroup,
-		Other:            other,
-	})
-
-}
-
 func CalcOpenRouterCacheCreateTokens(usage dto.Usage, priceData types.PriceData) int {
 	if priceData.CacheCreationRatio == 1 {
 		return 0

service/text_quota.go

@@ -0,0 +1,427 @@
+package service
+
+import (
+	"fmt"
+	"strings"
+	"time"
+
+	"github.com/QuantumNous/new-api/common"
+	"github.com/QuantumNous/new-api/constant"
+	"github.com/QuantumNous/new-api/dto"
+	"github.com/QuantumNous/new-api/logger"
+	"github.com/QuantumNous/new-api/model"
+	relaycommon "github.com/QuantumNous/new-api/relay/common"
+	"github.com/QuantumNous/new-api/setting/operation_setting"
+	"github.com/QuantumNous/new-api/types"
+
+	"github.com/gin-gonic/gin"
+	"github.com/shopspring/decimal"
+)
+
+type textQuotaSummary struct {
+	PromptTokens             int
+	CompletionTokens         int
+	TotalTokens              int
+	CacheTokens              int
+	CacheCreationTokens      int
+	CacheCreationTokens5m    int
+	CacheCreationTokens1h    int
+	ImageTokens              int
+	AudioTokens              int
+	ModelName                string
+	TokenName                string
+	UseTimeSeconds           int64
+	CompletionRatio          float64
+	CacheRatio               float64
+	ImageRatio               float64
+	ModelRatio               float64
+	GroupRatio               float64
+	ModelPrice               float64
+	CacheCreationRatio       float64
+	CacheCreationRatio5m     float64
+	CacheCreationRatio1h     float64
+	Quota                    int
+	IsClaudeUsageSemantic    bool
+	UsageSemantic            string
+	WebSearchPrice           float64
+	WebSearchCallCount       int
+	ClaudeWebSearchPrice     float64
+	ClaudeWebSearchCallCount int
+	FileSearchPrice          float64
+	FileSearchCallCount      int
+	AudioInputPrice          float64
+	ImageGenerationCallPrice float64
+}
+
+func cacheWriteTokensTotal(summary textQuotaSummary) int {
+	if summary.CacheCreationTokens5m > 0 || summary.CacheCreationTokens1h > 0 {
+		splitCacheWriteTokens := summary.CacheCreationTokens5m + summary.CacheCreationTokens1h
+		if summary.CacheCreationTokens > splitCacheWriteTokens {
+			return summary.CacheCreationTokens
+		}
+		return splitCacheWriteTokens
+	}
+	return summary.CacheCreationTokens
+}
+
+func isLegacyClaudeDerivedOpenAIUsage(relayInfo *relaycommon.RelayInfo, usage *dto.Usage) bool {
+	if relayInfo == nil || usage == nil {
+		return false
+	}
+	if relayInfo.GetFinalRequestRelayFormat() == types.RelayFormatClaude {
+		return false
+	}
+	if usage.UsageSource != "" || usage.UsageSemantic != "" {
+		return false
+	}
+	return usage.ClaudeCacheCreation5mTokens > 0 || usage.ClaudeCacheCreation1hTokens > 0
+}
+
+func calculateTextQuotaSummary(ctx *gin.Context, relayInfo *relaycommon.RelayInfo, usage *dto.Usage) textQuotaSummary {
+	summary := textQuotaSummary{
+		ModelName:            relayInfo.OriginModelName,
+		TokenName:            ctx.GetString("token_name"),
+		UseTimeSeconds:       time.Now().Unix() - relayInfo.StartTime.Unix(),
+		CompletionRatio:      relayInfo.PriceData.CompletionRatio,
+		CacheRatio:           relayInfo.PriceData.CacheRatio,
+		ImageRatio:           relayInfo.PriceData.ImageRatio,
+		ModelRatio:           relayInfo.PriceData.ModelRatio,
+		GroupRatio:           relayInfo.PriceData.GroupRatioInfo.GroupRatio,
+		ModelPrice:           relayInfo.PriceData.ModelPrice,
+		CacheCreationRatio:   relayInfo.PriceData.CacheCreationRatio,
+		CacheCreationRatio5m: relayInfo.PriceData.CacheCreation5mRatio,
+		CacheCreationRatio1h: relayInfo.PriceData.CacheCreation1hRatio,
+		UsageSemantic:        usageSemanticFromUsage(relayInfo, usage),
+	}
+	summary.IsClaudeUsageSemantic = summary.UsageSemantic == "anthropic"
+
+	if usage == nil {
+		usage = &dto.Usage{
+			PromptTokens:     relayInfo.GetEstimatePromptTokens(),
+			CompletionTokens: 0,
+			TotalTokens:      relayInfo.GetEstimatePromptTokens(),
+		}
+	}
+
+	summary.PromptTokens = usage.PromptTokens
+	summary.CompletionTokens = usage.CompletionTokens
+	summary.TotalTokens = usage.PromptTokens + usage.CompletionTokens
+	summary.CacheTokens = usage.PromptTokensDetails.CachedTokens
+	summary.CacheCreationTokens = usage.PromptTokensDetails.CachedCreationTokens
+	summary.CacheCreationTokens5m = usage.ClaudeCacheCreation5mTokens
+	summary.CacheCreationTokens1h = usage.ClaudeCacheCreation1hTokens
+	summary.ImageTokens = usage.PromptTokensDetails.ImageTokens
+	summary.AudioTokens = usage.PromptTokensDetails.AudioTokens
+	legacyClaudeDerived := isLegacyClaudeDerivedOpenAIUsage(relayInfo, usage)
+
+	if relayInfo.ChannelMeta != nil && relayInfo.ChannelType == constant.ChannelTypeOpenRouter {
+		summary.PromptTokens -= summary.CacheTokens
+		isUsingCustomSettings := relayInfo.PriceData.UsePrice || hasCustomModelRatio(summary.ModelName, relayInfo.PriceData.ModelRatio)
+		if summary.CacheCreationTokens == 0 && relayInfo.PriceData.CacheCreationRatio != 1 && usage.Cost != 0 && !isUsingCustomSettings {
+			maybeCacheCreationTokens := CalcOpenRouterCacheCreateTokens(*usage, relayInfo.PriceData)
+			if maybeCacheCreationTokens >= 0 && summary.PromptTokens >= maybeCacheCreationTokens {
+				summary.CacheCreationTokens = maybeCacheCreationTokens
+			}
+		}
+		summary.PromptTokens -= summary.CacheCreationTokens
+	}
+
+	dPromptTokens := decimal.NewFromInt(int64(summary.PromptTokens))
+	dCacheTokens := decimal.NewFromInt(int64(summary.CacheTokens))
+	dImageTokens := decimal.NewFromInt(int64(summary.ImageTokens))
+	dAudioTokens := decimal.NewFromInt(int64(summary.AudioTokens))
+	dCompletionTokens := decimal.NewFromInt(int64(summary.CompletionTokens))
+	dCachedCreationTokens := decimal.NewFromInt(int64(summary.CacheCreationTokens))
+	dCompletionRatio := decimal.NewFromFloat(summary.CompletionRatio)
+	dCacheRatio := decimal.NewFromFloat(summary.CacheRatio)
+	dImageRatio := decimal.NewFromFloat(summary.ImageRatio)
+	dModelRatio := decimal.NewFromFloat(summary.ModelRatio)
+	dGroupRatio := decimal.NewFromFloat(summary.GroupRatio)
+	dModelPrice := decimal.NewFromFloat(summary.ModelPrice)
+	dCacheCreationRatio := decimal.NewFromFloat(summary.CacheCreationRatio)
+	dCacheCreationRatio5m := decimal.NewFromFloat(summary.CacheCreationRatio5m)
+	dCacheCreationRatio1h := decimal.NewFromFloat(summary.CacheCreationRatio1h)
+	dQuotaPerUnit := decimal.NewFromFloat(common.QuotaPerUnit)
+
+	ratio := dModelRatio.Mul(dGroupRatio)
+
+	var dWebSearchQuota decimal.Decimal
+	if relayInfo.ResponsesUsageInfo != nil {
+		if webSearchTool, exists := relayInfo.ResponsesUsageInfo.BuiltInTools[dto.BuildInToolWebSearchPreview]; exists && webSearchTool.CallCount > 0 {
+			summary.WebSearchCallCount = webSearchTool.CallCount
+			summary.WebSearchPrice = operation_setting.GetWebSearchPricePerThousand(summary.ModelName, webSearchTool.SearchContextSize)
+			dWebSearchQuota = decimal.NewFromFloat(summary.WebSearchPrice).
+				Mul(decimal.NewFromInt(int64(webSearchTool.CallCount))).
+				Div(decimal.NewFromInt(1000)).Mul(dGroupRatio).Mul(dQuotaPerUnit)
+		}
+	} else if strings.HasSuffix(summary.ModelName, "search-preview") {
+		searchContextSize := ctx.GetString("chat_completion_web_search_context_size")
+		if searchContextSize == "" {
+			searchContextSize = "medium"
+		}
+		summary.WebSearchCallCount = 1
+		summary.WebSearchPrice = operation_setting.GetWebSearchPricePerThousand(summary.ModelName, searchContextSize)
+		dWebSearchQuota = decimal.NewFromFloat(summary.WebSearchPrice).
+			Div(decimal.NewFromInt(1000)).Mul(dGroupRatio).Mul(dQuotaPerUnit)
+	}
+
+	var dClaudeWebSearchQuota decimal.Decimal
+	summary.ClaudeWebSearchCallCount = ctx.GetInt("claude_web_search_requests")
+	if summary.ClaudeWebSearchCallCount > 0 {
+		summary.ClaudeWebSearchPrice = operation_setting.GetClaudeWebSearchPricePerThousand()
+		dClaudeWebSearchQuota = decimal.NewFromFloat(summary.ClaudeWebSearchPrice).
+			Div(decimal.NewFromInt(1000)).Mul(dGroupRatio).Mul(dQuotaPerUnit).
+			Mul(decimal.NewFromInt(int64(summary.ClaudeWebSearchCallCount)))
+	}
+
+	var dFileSearchQuota decimal.Decimal
+	if relayInfo.ResponsesUsageInfo != nil {
+		if fileSearchTool, exists := relayInfo.ResponsesUsageInfo.BuiltInTools[dto.BuildInToolFileSearch]; exists && fileSearchTool.CallCount > 0 {
+			summary.FileSearchCallCount = fileSearchTool.CallCount
+			summary.FileSearchPrice = operation_setting.GetFileSearchPricePerThousand()
+			dFileSearchQuota = decimal.NewFromFloat(summary.FileSearchPrice).
+				Mul(decimal.NewFromInt(int64(fileSearchTool.CallCount))).
+				Div(decimal.NewFromInt(1000)).Mul(dGroupRatio).Mul(dQuotaPerUnit)
+		}
+	}
+
+	var dImageGenerationCallQuota decimal.Decimal
+	if ctx.GetBool("image_generation_call") {
+		summary.ImageGenerationCallPrice = operation_setting.GetGPTImage1PriceOnceCall(ctx.GetString("image_generation_call_quality"), ctx.GetString("image_generation_call_size"))
+		dImageGenerationCallQuota = decimal.NewFromFloat(summary.ImageGenerationCallPrice).Mul(dGroupRatio).Mul(dQuotaPerUnit)
+	}
+
+	var audioInputQuota decimal.Decimal
+	if !relayInfo.PriceData.UsePrice {
+		baseTokens := dPromptTokens
+
+		var cachedTokensWithRatio decimal.Decimal
+		if !dCacheTokens.IsZero() {
+			if !summary.IsClaudeUsageSemantic && !legacyClaudeDerived {
+				baseTokens = baseTokens.Sub(dCacheTokens)
+			}
+			cachedTokensWithRatio = dCacheTokens.Mul(dCacheRatio)
+		}
+
+		var cachedCreationTokensWithRatio decimal.Decimal
+		hasSplitCacheCreationTokens := summary.CacheCreationTokens5m > 0 || summary.CacheCreationTokens1h > 0
+		if !dCachedCreationTokens.IsZero() || hasSplitCacheCreationTokens {
+			if !summary.IsClaudeUsageSemantic && !legacyClaudeDerived {
+				baseTokens = baseTokens.Sub(dCachedCreationTokens)
+				cachedCreationTokensWithRatio = dCachedCreationTokens.Mul(dCacheCreationRatio)
+			} else {
+				remaining := summary.CacheCreationTokens - summary.CacheCreationTokens5m - summary.CacheCreationTokens1h
+				if remaining < 0 {
+					remaining = 0
+				}
+				cachedCreationTokensWithRatio = decimal.NewFromInt(int64(remaining)).Mul(dCacheCreationRatio)
+				cachedCreationTokensWithRatio = cachedCreationTokensWithRatio.Add(decimal.NewFromInt(int64(summary.CacheCreationTokens5m)).Mul(dCacheCreationRatio5m))
+				cachedCreationTokensWithRatio = cachedCreationTokensWithRatio.Add(decimal.NewFromInt(int64(summary.CacheCreationTokens1h)).Mul(dCacheCreationRatio1h))
+			}
+		}
+
+		var imageTokensWithRatio decimal.Decimal
+		if !dImageTokens.IsZero() {
+			baseTokens = baseTokens.Sub(dImageTokens)
+			imageTokensWithRatio = dImageTokens.Mul(dImageRatio)
+		}
+
+		if !dAudioTokens.IsZero() {
+			summary.AudioInputPrice = operation_setting.GetGeminiInputAudioPricePerMillionTokens(summary.ModelName)
+			if summary.AudioInputPrice > 0 {
+				baseTokens = baseTokens.Sub(dAudioTokens)
+				audioInputQuota = decimal.NewFromFloat(summary.AudioInputPrice).
+					Div(decimal.NewFromInt(1000000)).Mul(dAudioTokens).Mul(dGroupRatio).Mul(dQuotaPerUnit)
+			}
+		}
+
+		promptQuota := baseTokens.Add(cachedTokensWithRatio).Add(imageTokensWithRatio).Add(cachedCreationTokensWithRatio)
+		completionQuota := dCompletionTokens.Mul(dCompletionRatio)
+		quotaCalculateDecimal := promptQuota.Add(completionQuota).Mul(ratio)
+		quotaCalculateDecimal = quotaCalculateDecimal.Add(dWebSearchQuota)
+		quotaCalculateDecimal = quotaCalculateDecimal.Add(dClaudeWebSearchQuota)
+		quotaCalculateDecimal = quotaCalculateDecimal.Add(dFileSearchQuota)
+		quotaCalculateDecimal = quotaCalculateDecimal.Add(audioInputQuota)
+		quotaCalculateDecimal = quotaCalculateDecimal.Add(dImageGenerationCallQuota)
+
+		if len(relayInfo.PriceData.OtherRatios) > 0 {
+			for _, otherRatio := range relayInfo.PriceData.OtherRatios {
+				quotaCalculateDecimal = quotaCalculateDecimal.Mul(decimal.NewFromFloat(otherRatio))
+			}
+		}
+
+		if !ratio.IsZero() && quotaCalculateDecimal.LessThanOrEqual(decimal.Zero) {
+			quotaCalculateDecimal = decimal.NewFromInt(1)
+		}
+		summary.Quota = int(quotaCalculateDecimal.Round(0).IntPart())
+	} else {
+		quotaCalculateDecimal := dModelPrice.Mul(dQuotaPerUnit).Mul(dGroupRatio)
+		quotaCalculateDecimal = quotaCalculateDecimal.Add(dWebSearchQuota)
+		quotaCalculateDecimal = quotaCalculateDecimal.Add(dClaudeWebSearchQuota)
+		quotaCalculateDecimal = quotaCalculateDecimal.Add(dFileSearchQuota)
+		quotaCalculateDecimal = quotaCalculateDecimal.Add(audioInputQuota)
+		quotaCalculateDecimal = quotaCalculateDecimal.Add(dImageGenerationCallQuota)
+		if len(relayInfo.PriceData.OtherRatios) > 0 {
+			for _, otherRatio := range relayInfo.PriceData.OtherRatios {
+				quotaCalculateDecimal = quotaCalculateDecimal.Mul(decimal.NewFromFloat(otherRatio))
+			}
+		}
+		summary.Quota = int(quotaCalculateDecimal.Round(0).IntPart())
+	}
+
+	if summary.TotalTokens == 0 {
+		summary.Quota = 0
+	} else if !ratio.IsZero() && summary.Quota == 0 {
+		summary.Quota = 1
+	}
+
+	return summary
+}
+
+func usageSemanticFromUsage(relayInfo *relaycommon.RelayInfo, usage *dto.Usage) string {
+	if usage != nil && usage.UsageSemantic != "" {
+		return usage.UsageSemantic
+	}
+	if relayInfo != nil && relayInfo.GetFinalRequestRelayFormat() == types.RelayFormatClaude {
+		return "anthropic"
+	}
+	return "openai"
+}
+
+func PostTextConsumeQuota(ctx *gin.Context, relayInfo *relaycommon.RelayInfo, usage *dto.Usage, extraContent []string) {
+	originUsage := usage
+	if usage == nil {
+		extraContent = append(extraContent, "上游无计费信息")
+	}
+	if originUsage != nil {
+		ObserveChannelAffinityUsageCacheByRelayFormat(ctx, usage, relayInfo.GetFinalRequestRelayFormat())
+	}
+
+	adminRejectReason := common.GetContextKeyString(ctx, constant.ContextKeyAdminRejectReason)
+	summary := calculateTextQuotaSummary(ctx, relayInfo, usage)
+
+	if summary.WebSearchCallCount > 0 {
+		extraContent = append(extraContent, fmt.Sprintf("Web Search 调用 %d 次，调用花费 %s", summary.WebSearchCallCount, decimal.NewFromFloat(summary.WebSearchPrice).Mul(decimal.NewFromInt(int64(summary.WebSearchCallCount))).Div(decimal.NewFromInt(1000)).Mul(decimal.NewFromFloat(summary.GroupRatio)).Mul(decimal.NewFromFloat(common.QuotaPerUnit)).String()))
+	}
+	if summary.ClaudeWebSearchCallCount > 0 {
+		extraContent = append(extraContent, fmt.Sprintf("Claude Web Search 调用 %d 次，调用花费 %s", summary.ClaudeWebSearchCallCount, decimal.NewFromFloat(summary.ClaudeWebSearchPrice).Div(decimal.NewFromInt(1000)).Mul(decimal.NewFromFloat(summary.GroupRatio)).Mul(decimal.NewFromFloat(common.QuotaPerUnit)).Mul(decimal.NewFromInt(int64(summary.ClaudeWebSearchCallCount))).String()))
+	}
+	if summary.FileSearchCallCount > 0 {
+		extraContent = append(extraContent, fmt.Sprintf("File Search 调用 %d 次，调用花费 %s", summary.FileSearchCallCount, decimal.NewFromFloat(summary.FileSearchPrice).Mul(decimal.NewFromInt(int64(summary.FileSearchCallCount))).Div(decimal.NewFromInt(1000)).Mul(decimal.NewFromFloat(summary.GroupRatio)).Mul(decimal.NewFromFloat(common.QuotaPerUnit)).String()))
+	}
+	if summary.AudioInputPrice > 0 && summary.AudioTokens > 0 {
+		extraContent = append(extraContent, fmt.Sprintf("Audio Input 花费 %s", decimal.NewFromFloat(summary.AudioInputPrice).Div(decimal.NewFromInt(1000000)).Mul(decimal.NewFromInt(int64(summary.AudioTokens))).Mul(decimal.NewFromFloat(summary.GroupRatio)).Mul(decimal.NewFromFloat(common.QuotaPerUnit)).String()))
+	}
+	if summary.ImageGenerationCallPrice > 0 {
+		extraContent = append(extraContent, fmt.Sprintf("Image Generation Call 花费 %s", decimal.NewFromFloat(summary.ImageGenerationCallPrice).Mul(decimal.NewFromFloat(summary.GroupRatio)).Mul(decimal.NewFromFloat(common.QuotaPerUnit)).String()))
+	}
+
+	if summary.TotalTokens == 0 {
+		extraContent = append(extraContent, "上游没有返回计费信息，无法扣费（可能是上游超时）")
+		logger.LogError(ctx, fmt.Sprintf("total tokens is 0, cannot consume quota, userId %d, channelId %d, tokenId %d, model %s， pre-consumed quota %d", relayInfo.UserId, relayInfo.ChannelId, relayInfo.TokenId, summary.ModelName, relayInfo.FinalPreConsumedQuota))
+	} else {
+		model.UpdateUserUsedQuotaAndRequestCount(relayInfo.UserId, summary.Quota)
+		model.UpdateChannelUsedQuota(relayInfo.ChannelId, summary.Quota)
+	}
+
+	if err := SettleBilling(ctx, relayInfo, summary.Quota); err != nil {
+		logger.LogError(ctx, "error settling billing: "+err.Error())
+	}
+
+	logModel := summary.ModelName
+	if strings.HasPrefix(logModel, "gpt-4-gizmo") {
+		logModel = "gpt-4-gizmo-*"
+		extraContent = append(extraContent, fmt.Sprintf("模型 %s", summary.ModelName))
+	}
+	if strings.HasPrefix(logModel, "gpt-4o-gizmo") {
+		logModel = "gpt-4o-gizmo-*"
+		extraContent = append(extraContent, fmt.Sprintf("模型 %s", summary.ModelName))
+	}
+
+	logContent := strings.Join(extraContent, ", ")
+	var other map[string]interface{}
+	if summary.IsClaudeUsageSemantic {
+		other = GenerateClaudeOtherInfo(ctx, relayInfo,
+			summary.ModelRatio, summary.GroupRatio, summary.CompletionRatio,
+			summary.CacheTokens, summary.CacheRatio,
+			summary.CacheCreationTokens, summary.CacheCreationRatio,
+			summary.CacheCreationTokens5m, summary.CacheCreationRatio5m,
+			summary.CacheCreationTokens1h, summary.CacheCreationRatio1h,
+			summary.ModelPrice, relayInfo.PriceData.GroupRatioInfo.GroupSpecialRatio)
+		other["usage_semantic"] = "anthropic"
+	} else {
+		other = GenerateTextOtherInfo(ctx, relayInfo, summary.ModelRatio, summary.GroupRatio, summary.CompletionRatio, summary.CacheTokens, summary.CacheRatio, summary.ModelPrice, relayInfo.PriceData.GroupRatioInfo.GroupSpecialRatio)
+	}
+	if adminRejectReason != "" {
+		other["reject_reason"] = adminRejectReason
+	}
+	if summary.ImageTokens != 0 {
+		other["image"] = true
+		other["image_ratio"] = summary.ImageRatio
+		other["image_output"] = summary.ImageTokens
+	}
+	if summary.WebSearchCallCount > 0 {
+		other["web_search"] = true
+		other["web_search_call_count"] = summary.WebSearchCallCount
+		other["web_search_price"] = summary.WebSearchPrice
+	} else if summary.ClaudeWebSearchCallCount > 0 {
+		other["web_search"] = true
+		other["web_search_call_count"] = summary.ClaudeWebSearchCallCount
+		other["web_search_price"] = summary.ClaudeWebSearchPrice
+	}
+	if summary.FileSearchCallCount > 0 {
+		other["file_search"] = true
+		other["file_search_call_count"] = summary.FileSearchCallCount
+		other["file_search_price"] = summary.FileSearchPrice
+	}
+	if summary.AudioInputPrice > 0 && summary.AudioTokens > 0 {
+		other["audio_input_seperate_price"] = true
+		other["audio_input_token_count"] = summary.AudioTokens
+		other["audio_input_price"] = summary.AudioInputPrice
+	}
+	if summary.ImageGenerationCallPrice > 0 {
+		other["image_generation_call"] = true
+		other["image_generation_call_price"] = summary.ImageGenerationCallPrice
+	}
+	if summary.CacheCreationTokens > 0 {
+		other["cache_creation_tokens"] = summary.CacheCreationTokens
+		other["cache_creation_ratio"] = summary.CacheCreationRatio
+	}
+	if summary.CacheCreationTokens5m > 0 {
+		other["cache_creation_tokens_5m"] = summary.CacheCreationTokens5m
+		other["cache_creation_ratio_5m"] = summary.CacheCreationRatio5m
+	}
+	if summary.CacheCreationTokens1h > 0 {
+		other["cache_creation_tokens_1h"] = summary.CacheCreationTokens1h
+		other["cache_creation_ratio_1h"] = summary.CacheCreationRatio1h
+	}
+	cacheWriteTokens := cacheWriteTokensTotal(summary)
+	if cacheWriteTokens > 0 {
+		// cache_write_tokens: normalized cache creation total for UI display.
+		// If split 5m/1h values are present, this is their sum; otherwise it falls back
+		// to cache_creation_tokens.
+		other["cache_write_tokens"] = cacheWriteTokens
+	}
+	if relayInfo.GetFinalRequestRelayFormat() != types.RelayFormatClaude && usage != nil && usage.UsageSource != "" && usage.InputTokens > 0 {
+		// input_tokens_total: explicit normalized total input used by the usage log UI.
+		// Only write this field when upstream/current conversion has already provided a
+		// reliable total input value and tagged the usage source. Do not infer it from
+		// prompt/cache fields here, otherwise old upstream payloads may be double-counted.
+		other["input_tokens_total"] = usage.InputTokens
+	}
+
+	model.RecordConsumeLog(ctx, relayInfo.UserId, model.RecordConsumeLogParams{
+		ChannelId:        relayInfo.ChannelId,
+		PromptTokens:     summary.PromptTokens,
+		CompletionTokens: summary.CompletionTokens,
+		ModelName:        logModel,
+		TokenName:        summary.TokenName,
+		Quota:            summary.Quota,
+		Content:          logContent,
+		TokenId:          relayInfo.TokenId,
+		UseTimeSeconds:   int(summary.UseTimeSeconds),
+		IsStream:         relayInfo.IsStream,
+		Group:            relayInfo.UsingGroup,
+		Other:            other,
+	})
+}

service/text_quota_test.go

@@ -0,0 +1,206 @@
+package service
+
+import (
+	"net/http/httptest"
+	"testing"
+	"time"
+
+	"github.com/QuantumNous/new-api/dto"
+	relaycommon "github.com/QuantumNous/new-api/relay/common"
+	"github.com/QuantumNous/new-api/types"
+
+	"github.com/gin-gonic/gin"
+	"github.com/stretchr/testify/require"
+)
+
+func TestCalculateTextQuotaSummaryUnifiedForClaudeSemantic(t *testing.T) {
+	gin.SetMode(gin.TestMode)
+	w := httptest.NewRecorder()
+	ctx, _ := gin.CreateTestContext(w)
+
+	usage := &dto.Usage{
+		PromptTokens:     1000,
+		CompletionTokens: 200,
+		PromptTokensDetails: dto.InputTokenDetails{
+			CachedTokens:         100,
+			CachedCreationTokens: 50,
+		},
+		ClaudeCacheCreation5mTokens: 10,
+		ClaudeCacheCreation1hTokens: 20,
+	}
+
+	priceData := types.PriceData{
+		ModelRatio:           1,
+		CompletionRatio:      2,
+		CacheRatio:           0.1,
+		CacheCreationRatio:   1.25,
+		CacheCreation5mRatio: 1.25,
+		CacheCreation1hRatio: 2,
+		GroupRatioInfo: types.GroupRatioInfo{
+			GroupRatio: 1,
+		},
+	}
+
+	chatRelayInfo := &relaycommon.RelayInfo{
+		RelayFormat:             types.RelayFormatOpenAI,
+		FinalRequestRelayFormat: types.RelayFormatClaude,
+		OriginModelName:         "claude-3-7-sonnet",
+		PriceData:               priceData,
+		StartTime:               time.Now(),
+	}
+	messageRelayInfo := &relaycommon.RelayInfo{
+		RelayFormat:             types.RelayFormatClaude,
+		FinalRequestRelayFormat: types.RelayFormatClaude,
+		OriginModelName:         "claude-3-7-sonnet",
+		PriceData:               priceData,
+		StartTime:               time.Now(),
+	}
+
+	chatSummary := calculateTextQuotaSummary(ctx, chatRelayInfo, usage)
+	messageSummary := calculateTextQuotaSummary(ctx, messageRelayInfo, usage)
+
+	require.Equal(t, messageSummary.Quota, chatSummary.Quota)
+	require.Equal(t, messageSummary.CacheCreationTokens5m, chatSummary.CacheCreationTokens5m)
+	require.Equal(t, messageSummary.CacheCreationTokens1h, chatSummary.CacheCreationTokens1h)
+	require.True(t, chatSummary.IsClaudeUsageSemantic)
+	require.Equal(t, 1488, chatSummary.Quota)
+}
+
+func TestCalculateTextQuotaSummaryUsesSplitClaudeCacheCreationRatios(t *testing.T) {
+	gin.SetMode(gin.TestMode)
+	w := httptest.NewRecorder()
+	ctx, _ := gin.CreateTestContext(w)
+
+	relayInfo := &relaycommon.RelayInfo{
+		RelayFormat:             types.RelayFormatOpenAI,
+		FinalRequestRelayFormat: types.RelayFormatClaude,
+		OriginModelName:         "claude-3-7-sonnet",
+		PriceData: types.PriceData{
+			ModelRatio:           1,
+			CompletionRatio:      1,
+			CacheRatio:           0,
+			CacheCreationRatio:   1,
+			CacheCreation5mRatio: 2,
+			CacheCreation1hRatio: 3,
+			GroupRatioInfo: types.GroupRatioInfo{
+				GroupRatio: 1,
+			},
+		},
+		StartTime: time.Now(),
+	}
+
+	usage := &dto.Usage{
+		PromptTokens:     100,
+		CompletionTokens: 0,
+		PromptTokensDetails: dto.InputTokenDetails{
+			CachedCreationTokens: 10,
+		},
+		ClaudeCacheCreation5mTokens: 2,
+		ClaudeCacheCreation1hTokens: 3,
+	}
+
+	summary := calculateTextQuotaSummary(ctx, relayInfo, usage)
+
+	// 100 + remaining(5)*1 + 2*2 + 3*3 = 118
+	require.Equal(t, 118, summary.Quota)
+}
+
+func TestCalculateTextQuotaSummaryUsesAnthropicUsageSemanticFromUpstreamUsage(t *testing.T) {
+	gin.SetMode(gin.TestMode)
+	w := httptest.NewRecorder()
+	ctx, _ := gin.CreateTestContext(w)
+
+	relayInfo := &relaycommon.RelayInfo{
+		RelayFormat:     types.RelayFormatOpenAI,
+		OriginModelName: "claude-3-7-sonnet",
+		PriceData: types.PriceData{
+			ModelRatio:           1,
+			CompletionRatio:      2,
+			CacheRatio:           0.1,
+			CacheCreationRatio:   1.25,
+			CacheCreation5mRatio: 1.25,
+			CacheCreation1hRatio: 2,
+			GroupRatioInfo: types.GroupRatioInfo{
+				GroupRatio: 1,
+			},
+		},
+		StartTime: time.Now(),
+	}
+
+	usage := &dto.Usage{
+		PromptTokens:     1000,
+		CompletionTokens: 200,
+		UsageSemantic:    "anthropic",
+		PromptTokensDetails: dto.InputTokenDetails{
+			CachedTokens:         100,
+			CachedCreationTokens: 50,
+		},
+		ClaudeCacheCreation5mTokens: 10,
+		ClaudeCacheCreation1hTokens: 20,
+	}
+
+	summary := calculateTextQuotaSummary(ctx, relayInfo, usage)
+
+	require.True(t, summary.IsClaudeUsageSemantic)
+	require.Equal(t, "anthropic", summary.UsageSemantic)
+	require.Equal(t, 1488, summary.Quota)
+}
+
+func TestCacheWriteTokensTotal(t *testing.T) {
+	t.Run("split cache creation", func(t *testing.T) {
+		summary := textQuotaSummary{
+			CacheCreationTokens:   50,
+			CacheCreationTokens5m: 10,
+			CacheCreationTokens1h: 20,
+		}
+		require.Equal(t, 50, cacheWriteTokensTotal(summary))
+	})
+
+	t.Run("legacy cache creation", func(t *testing.T) {
+		summary := textQuotaSummary{CacheCreationTokens: 50}
+		require.Equal(t, 50, cacheWriteTokensTotal(summary))
+	})
+
+	t.Run("split cache creation without aggregate remainder", func(t *testing.T) {
+		summary := textQuotaSummary{
+			CacheCreationTokens5m: 10,
+			CacheCreationTokens1h: 20,
+		}
+		require.Equal(t, 30, cacheWriteTokensTotal(summary))
+	})
+}
+
+func TestCalculateTextQuotaSummaryHandlesLegacyClaudeDerivedOpenAIUsage(t *testing.T) {
+	gin.SetMode(gin.TestMode)
+	w := httptest.NewRecorder()
+	ctx, _ := gin.CreateTestContext(w)
+
+	relayInfo := &relaycommon.RelayInfo{
+		RelayFormat:     types.RelayFormatOpenAI,
+		OriginModelName: "claude-3-7-sonnet",
+		PriceData: types.PriceData{
+			ModelRatio:           1,
+			CompletionRatio:      5,
+			CacheRatio:           0.1,
+			CacheCreationRatio:   1.25,
+			CacheCreation5mRatio: 1.25,
+			CacheCreation1hRatio: 2,
+			GroupRatioInfo:       types.GroupRatioInfo{GroupRatio: 1},
+		},
+		StartTime: time.Now(),
+	}
+
+	usage := &dto.Usage{
+		PromptTokens:     62,
+		CompletionTokens: 95,
+		PromptTokensDetails: dto.InputTokenDetails{
+			CachedTokens: 3544,
+		},
+		ClaudeCacheCreation5mTokens: 586,
+	}
+
+	summary := calculateTextQuotaSummary(ctx, relayInfo, usage)
+
+	// 62 + 3544*0.1 + 586*1.25 + 95*5 = 1624.9 => 1624
+	require.Equal(t, 1624, summary.Quota)
+}

setting/operation_setting/channel_affinity_setting.go

@@ -88,7 +88,7 @@ var channelAffinitySetting = ChannelAffinitySetting{
 			ValueRegex:            "",
 			TTLSeconds:            0,
 			ParamOverrideTemplate: buildPassHeaderTemplate(codexCliPassThroughHeaders),
-			SkipRetryOnFailure:    false,
+			SkipRetryOnFailure:    true,
 			IncludeUsingGroup:     true,
 			IncludeRuleName:       true,
 			UserAgentInclude:      nil,
@@ -103,7 +103,7 @@ var channelAffinitySetting = ChannelAffinitySetting{
 			ValueRegex:            "",
 			TTLSeconds:            0,
 			ParamOverrideTemplate: buildPassHeaderTemplate(claudeCliPassThroughHeaders),
-			SkipRetryOnFailure:    false,
+			SkipRetryOnFailure:    true,
 			IncludeUsingGroup:     true,
 			IncludeRuleName:       true,
 			UserAgentInclude:      nil,

setting/performance_setting/config.go

@@ -36,7 +36,7 @@ var performanceSetting = PerformanceSetting{
 	MonitorEnabled:         true,
 	MonitorCPUThreshold:    90,
 	MonitorMemoryThreshold: 90,
-	MonitorDiskThreshold:   90,
+	MonitorDiskThreshold:   95,
 }
 
 func init() {

web/src/components/auth/OAuth2Callback.jsx

@@ -56,7 +56,7 @@ const OAuth2Callback = (props) => {
         return;
       }
 
-      if (message === 'bind') {
+      if (data?.action === 'bind') {
         showSuccess(t('绑定成功！'));
         navigate('/console/personal');
       } else {

web/src/components/table/channels/ChannelsColumnDefs.jsx

@@ -538,19 +538,24 @@ export const getChannelsColumns = ({
                 </Tooltip>
                 <Tooltip
                   content={
-                    t('剩余额度') +
-                    ': ' +
-                    renderQuotaWithAmount(record.balance) +
-                    t('，点击更新')
+                    record.type === 57
+                      ? t('查看 Codex 帐号信息与用量')
+                      : t('剩余额度') +
+                        ': ' +
+                        renderQuotaWithAmount(record.balance) +
+                        t('，点击更新')
                   }
                 >
                   <Tag
-                    color='white'
-                    type='ghost'
+                    color={record.type === 57 ? 'light-blue' : 'white'}
+                    type={record.type === 57 ? 'light' : 'ghost'}
                     shape='circle'
+                    className={record.type === 57 ? 'cursor-pointer' : ''}
                     onClick={() => updateChannelBalance(record)}
                   >
-                    {renderQuotaWithAmount(record.balance)}
+                    {record.type === 57
+                      ? t('帐号信息')
+                      : renderQuotaWithAmount(record.balance)}
                   </Tag>
                 </Tooltip>
               </Space>

web/src/components/table/channels/modals/CodexUsageModal.jsx

@@ -22,9 +22,11 @@ import {
   Modal,
   Button,
   Progress,
-  Tag,
   Typography,
   Spin,
+  Tag,
+  Descriptions,
+  Collapse,
 } from '@douyinfe/semi-ui';
 import { API, showError } from '../../../../helpers';
 
@@ -128,6 +130,87 @@ const formatUnixSeconds = (unixSeconds) => {
   }
 };
 
+const getDisplayText = (value) => {
+  if (value == null) return '';
+  return String(value).trim();
+};
+
+const formatAccountTypeLabel = (value, t) => {
+  const tt = typeof t === 'function' ? t : (v) => v;
+  const normalized = normalizePlanType(value);
+  switch (normalized) {
+    case 'free':
+      return 'Free';
+    case 'plus':
+      return 'Plus';
+    case 'pro':
+      return 'Pro';
+    case 'team':
+      return 'Team';
+    case 'enterprise':
+      return 'Enterprise';
+    default:
+      return getDisplayText(value) || tt('未识别');
+  }
+};
+
+const getAccountTypeTagColor = (value) => {
+  const normalized = normalizePlanType(value);
+  switch (normalized) {
+    case 'enterprise':
+      return 'green';
+    case 'team':
+      return 'cyan';
+    case 'pro':
+      return 'blue';
+    case 'plus':
+      return 'violet';
+    case 'free':
+      return 'amber';
+    default:
+      return 'grey';
+  }
+};
+
+const resolveUsageStatusTag = (t, rateLimit) => {
+  const tt = typeof t === 'function' ? t : (v) => v;
+  if (!rateLimit || Object.keys(rateLimit).length === 0) {
+    return <Tag color='grey'>{tt('待确认')}</Tag>;
+  }
+  if (rateLimit?.allowed && !rateLimit?.limit_reached) {
+    return <Tag color='green'>{tt('可用')}</Tag>;
+  }
+  return <Tag color='red'>{tt('受限')}</Tag>;
+};
+
+const AccountInfoValue = ({ t, value, onCopy, monospace = false }) => {
+  const tt = typeof t === 'function' ? t : (v) => v;
+  const text = getDisplayText(value);
+  const hasValue = text !== '';
+
+  return (
+    <div className='flex min-w-0 items-start justify-between gap-2'>
+      <div
+        className={`min-w-0 flex-1 break-all text-xs leading-5 text-semi-color-text-1 ${
+          monospace ? 'font-mono' : ''
+        }`}
+      >
+        {hasValue ? text : '-'}
+      </div>
+      <Button
+        size='small'
+        type='tertiary'
+        theme='borderless'
+        className='shrink-0 px-1 text-xs'
+        disabled={!hasValue}
+        onClick={() => onCopy?.(text)}
+      >
+        {tt('复制')}
+      </Button>
+    </div>
+  );
+};
+
 const RateLimitWindowCard = ({ t, title, windowData }) => {
   const tt = typeof t === 'function' ? t : (v) => v;
   const hasWindowData =
@@ -181,50 +264,100 @@ const RateLimitWindowCard = ({ t, title, windowData }) => {
 
 const CodexUsageView = ({ t, record, payload, onCopy, onRefresh }) => {
   const tt = typeof t === 'function' ? t : (v) => v;
+  const [showRawJson, setShowRawJson] = useState(false);
   const data = payload?.data ?? null;
   const rateLimit = data?.rate_limit ?? {};
   const { fiveHourWindow, weeklyWindow } = resolveRateLimitWindows(data);
-
-  const allowed = !!rateLimit?.allowed;
-  const limitReached = !!rateLimit?.limit_reached;
   const upstreamStatus = payload?.upstream_status;
-
-  const statusTag =
-    allowed && !limitReached ? (
-      <Tag color='green'>{tt('可用')}</Tag>
-    ) : (
-      <Tag color='red'>{tt('受限')}</Tag>
-    );
+  const accountType = data?.plan_type ?? rateLimit?.plan_type;
+  const accountTypeLabel = formatAccountTypeLabel(accountType, tt);
+  const accountTypeTagColor = getAccountTypeTagColor(accountType);
+  const statusTag = resolveUsageStatusTag(tt, rateLimit);
+  const userId = data?.user_id;
+  const email = data?.email;
+  const accountId = data?.account_id;
+  const errorMessage =
+    payload?.success === false ? getDisplayText(payload?.message) || tt('获取用量失败') : '';
 
   const rawText =
     typeof data === 'string' ? data : JSON.stringify(data ?? payload, null, 2);
 
   return (
-    <div className='flex flex-col gap-3'>
-      <div className='flex flex-wrap items-center justify-between gap-2'>
-        <Text type='tertiary' size='small'>
-          {tt('渠道：')}
-          {record?.name || '-'} ({tt('编号：')}
-          {record?.id || '-'})
-        </Text>
-        <div className='flex items-center gap-2'>
-          {statusTag}
-          <Button
-            size='small'
-            type='tertiary'
-            theme='borderless'
-            onClick={onRefresh}
-          >
+    <div className='flex flex-col gap-4'>
+      {errorMessage && (
+        <div className='rounded-xl border border-red-200 bg-red-50 px-4 py-3 text-sm text-red-700'>
+          {errorMessage}
+        </div>
+      )}
+
+      <div className='rounded-xl border border-semi-color-border bg-semi-color-bg-0 p-3'>
+        <div className='flex flex-wrap items-start justify-between gap-2'>
+          <div className='min-w-0'>
+            <div className='text-xs font-medium text-semi-color-text-2'>
+              {tt('Codex 帐号')}
+            </div>
+            <div className='mt-2 flex flex-wrap items-center gap-2'>
+              <Tag
+                color={accountTypeTagColor}
+                type='light'
+                shape='circle'
+                size='large'
+                className='font-semibold'
+              >
+                {accountTypeLabel}
+              </Tag>
+              {statusTag}
+              <Tag color='grey' type='light' shape='circle'>
+                {tt('上游状态码：')}
+                {upstreamStatus ?? '-'}
+              </Tag>
+            </div>
+          </div>
+          <Button size='small' type='tertiary' theme='outline' onClick={onRefresh}>
             {tt('刷新')}
           </Button>
         </div>
+
+        <div className='mt-2 rounded-lg bg-semi-color-fill-0 px-3 py-2'>
+          <Descriptions>
+            <Descriptions.Item itemKey='User ID'>
+              <AccountInfoValue
+                t={tt}
+                value={userId}
+                onCopy={onCopy}
+                monospace={true}
+              />
+            </Descriptions.Item>
+            <Descriptions.Item itemKey={tt('邮箱')}>
+              <AccountInfoValue t={tt} value={email} onCopy={onCopy} />
+            </Descriptions.Item>
+            <Descriptions.Item itemKey='Account ID'>
+              <AccountInfoValue
+                t={tt}
+                value={accountId}
+                onCopy={onCopy}
+                monospace={true}
+              />
+            </Descriptions.Item>
+          </Descriptions>
+        </div>
+
+        <div className='mt-2 text-xs text-semi-color-text-2'>
+          {tt('渠道：')}
+          {record?.name || '-'} ({tt('编号：')}
+          {record?.id || '-'})
+        </div>
       </div>
 
-      <div className='flex flex-wrap items-center justify-between gap-2'>
-        <Text type='tertiary' size='small'>
-          {tt('上游状态码：')}
-          {upstreamStatus ?? '-'}
-        </Text>
+      <div>
+        <div className='mb-2'>
+          <div className='text-sm font-semibold text-semi-color-text-0'>
+            {tt('额度窗口')}
+          </div>
+          <Text type='tertiary' size='small'>
+            {tt('用于观察当前帐号在 Codex 上游的限额使用情况')}
+          </Text>
+        </div>
       </div>
 
       <div className='grid grid-cols-1 gap-3 md:grid-cols-2'>
@@ -240,23 +373,30 @@ const CodexUsageView = ({ t, record, payload, onCopy, onRefresh }) => {
         />
       </div>
 
-      <div>
-        <div className='mb-1 flex items-center justify-between gap-2'>
-          <div className='text-sm font-medium'>{tt('原始 JSON')}</div>
-          <Button
-            size='small'
-            type='primary'
-            theme='outline'
-            onClick={() => onCopy?.(rawText)}
-            disabled={!rawText}
-          >
-            {tt('复制')}
-          </Button>
-        </div>
-        <pre className='max-h-[50vh] overflow-auto rounded-lg bg-semi-color-fill-0 p-3 text-xs text-semi-color-text-0'>
-          {rawText}
-        </pre>
-      </div>
+      <Collapse
+        activeKey={showRawJson ? ['raw-json'] : []}
+        onChange={(activeKey) => {
+          const keys = Array.isArray(activeKey) ? activeKey : [activeKey];
+          setShowRawJson(keys.includes('raw-json'));
+        }}
+      >
+        <Collapse.Panel header={tt('原始 JSON')} itemKey='raw-json'>
+          <div className='mb-2 flex justify-end'>
+            <Button
+              size='small'
+              type='primary'
+              theme='outline'
+              onClick={() => onCopy?.(rawText)}
+              disabled={!rawText}
+            >
+              {tt('复制')}
+            </Button>
+          </div>
+          <pre className='max-h-[50vh] overflow-y-auto rounded-lg bg-semi-color-fill-0 p-3 text-xs text-semi-color-text-0'>
+            {rawText}
+          </pre>
+        </Collapse.Panel>
+      </Collapse>
     </div>
   );
 };
@@ -351,7 +491,7 @@ export const openCodexUsageModal = ({ t, record, payload, onCopy }) => {
   const tt = typeof t === 'function' ? t : (v) => v;
 
   Modal.info({
-    title: tt('Codex 用量'),
+    title: tt('Codex 帐号与用量'),
     centered: true,
     width: 900,
     style: { maxWidth: '95vw' },

web/src/constants/channel-affinity-template.constants.js

@@ -68,7 +68,7 @@ export const CHANNEL_AFFINITY_RULE_TEMPLATES = {
     param_override_template: CODEX_CLI_HEADER_PASSTHROUGH_TEMPLATE,
     value_regex: '',
     ttl_seconds: 0,
-    skip_retry_on_failure: false,
+    skip_retry_on_failure: true,
     include_using_group: true,
     include_rule_name: true,
   },
@@ -80,7 +80,7 @@ export const CHANNEL_AFFINITY_RULE_TEMPLATES = {
     param_override_template: CLAUDE_CLI_HEADER_PASSTHROUGH_TEMPLATE,
     value_regex: '',
     ttl_seconds: 0,
-    skip_retry_on_failure: false,
+    skip_retry_on_failure: true,
     include_using_group: true,
     include_rule_name: true,
   },

web/src/i18n/locales/en.json

@@ -1507,6 +1507,8 @@
     "收益统计": "Income statistics",
     "收起": "Collapse",
     "收起侧边栏": "Collapse sidebar",
+    "向左展开": "Expand left",
+    "向右展开": "Expand right",
     "收起内容": "Collapse content",
     "放大": "Upscalers",
     "放大编辑": "Expand editor",
@@ -3220,6 +3222,12 @@
     "高级设置": "Advanced Settings",
     "高级选项": "Advanced Options",
     "高级配置": "Advanced Configuration",
+    "核心配置": "Core Configuration",
+    "创建渠道所需的基本信息": "Basic information needed to create a channel",
+    "请求配置": "Request Configuration",
+    "渠道行为": "Channel Behavior",
+    "额外设置": "Extra Settings",
+    "上游模型管理": "Upstream Model Management",
     "黑名单": "Blacklist",
     "默认": "Default",
     "默认 API 版本": "Default API Version",
@@ -3337,6 +3345,8 @@
     "输入价格：{{symbol}}{{price}} / 1M tokens": "Input Price: {{symbol}}{{price}} / 1M tokens",
     "输出价格 {{symbol}}{{price}} / 1M tokens": "Output Price {{symbol}}{{price}} / 1M tokens",
     "输出价格：{{symbol}}{{price}} / 1M tokens": "Output Price: {{symbol}}{{price}} / 1M tokens",
-    "输出价格：{{symbol}}{{total}} / 1M tokens": "Output Price: {{symbol}}{{total}} / 1M tokens"
+    "输出价格：{{symbol}}{{total}} / 1M tokens": "Output Price: {{symbol}}{{total}} / 1M tokens",
+    "例如：gpt-4.1-nano,regex:^claude-.*$,regex:^sora-.*$": "Example: gpt-4.1-nano,regex:^claude-.*$,regex:^sora-.*$",
+    "支持精确匹配；使用 regex: 开头可按正则匹配。": "Supports exact matching. Use a regex: prefix for regex matching."
   }
 }

web/src/i18n/locales/fr.json

@@ -1495,6 +1495,8 @@
     "收益统计": "Statistiques sur les revenus",
     "收起": "Réduire",
     "收起侧边栏": "Réduire la barre latérale",
+    "向左展开": "Développer à gauche",
+    "向右展开": "Développer à droite",
     "收起内容": "Réduire le contenu",
     "放大": "Upscalers",
     "放大编辑": "Développer l'éditeur",
@@ -3164,6 +3166,12 @@
     "高级设置": "Paramètres avancés",
     "高级选项": "Options avancées",
     "高级配置": "Advanced Configuration",
+    "核心配置": "Configuration principale",
+    "创建渠道所需的基本信息": "Informations de base pour créer un canal",
+    "请求配置": "Configuration des requêtes",
+    "渠道行为": "Comportement du canal",
+    "额外设置": "Paramètres supplémentaires",
+    "上游模型管理": "Gestion des modèles amont",
     "黑名单": "Liste noire",
     "默认": "Par défaut",
     "默认 API 版本": "Version de l'API par défaut",

web/src/i18n/locales/ja.json

@@ -1478,6 +1478,8 @@
     "收益统计": "収益統計",
     "收起": "折りたたみ",
     "收起侧边栏": "サイドバー折りたたみ",
+    "向左展开": "左に展開",
+    "向右展开": "右に展開",
     "收起内容": "コンテンツ折りたたみ",
     "放大": "アップスケール",
     "放大编辑": "エディタで開く",
@@ -3145,6 +3147,12 @@
     "高级设置": "詳細設定",
     "高级选项": "高度なオプション",
     "高级配置": "Advanced Configuration",
+    "核心配置": "基本設定",
+    "创建渠道所需的基本信息": "チャネル作成に必要な基本情報",
+    "请求配置": "リクエスト設定",
+    "渠道行为": "チャネル動作",
+    "额外设置": "追加設定",
+    "上游模型管理": "上流モデル管理",
     "黑名单": "ブラックリスト",
     "默认": "デフォルト",
     "默认 API 版本": "デフォルトAPIバージョン",

web/src/i18n/locales/ru.json

@@ -1507,6 +1507,8 @@
     "收益统计": "Статистика доходов",
     "收起": "Свернуть",
     "收起侧边栏": "Свернуть боковую панель",
+    "向左展开": "Развернуть влево",
+    "向右展开": "Развернуть вправо",
     "收起内容": "Свернуть содержимое",
     "放大": "Увеличить",
     "放大编辑": "Увеличить и редактировать",
@@ -3178,6 +3180,12 @@
     "高级设置": "Расширенные настройки",
     "高级选项": "Расширенные параметры",
     "高级配置": "Advanced Configuration",
+    "核心配置": "Основные настройки",
+    "创建渠道所需的基本信息": "Основная информация для создания канала",
+    "请求配置": "Настройки запросов",
+    "渠道行为": "Поведение канала",
+    "额外设置": "Дополнительные настройки",
+    "上游模型管理": "Управление моделями апстрима",
     "黑名单": "Черный список",
     "默认": "По умолчанию",
     "默认 API 版本": "Версия API по умолчанию",

web/src/i18n/locales/vi.json

@@ -1479,6 +1479,8 @@
     "收益统计": "Thống kê thu nhập",
     "收起": "Thu gọn",
     "收起侧边栏": "Thu gọn thanh bên",
+    "向左展开": "Mở rộng sang trái",
+    "向右展开": "Mở rộng sang phải",
     "收起内容": "Thu gọn nội dung",
     "放大": "Upscalers",
     "放大编辑": "Mở rộng trình chỉnh sửa",
@@ -3716,6 +3718,12 @@
     "高级设置": "Cài đặt nâng cao",
     "高级选项": "Tùy chọn nâng cao",
     "高级配置": "Advanced Configuration",
+    "核心配置": "Cấu hình cốt lõi",
+    "创建渠道所需的基本信息": "Thông tin cơ bản cần thiết để tạo kênh",
+    "请求配置": "Cấu hình yêu cầu",
+    "渠道行为": "Hành vi kênh",
+    "额外设置": "Cài đặt bổ sung",
+    "上游模型管理": "Quản lý mô hình thượng nguồn",
     "黑名单": "Danh sách đen",
     "默认": "Mặc định",
     "默认 API 版本": "Phiên bản API mặc định",

web/src/i18n/locales/zh-TW.json

@@ -1190,6 +1190,8 @@
     "收益统计": "收益統計",
     "收起": "收起",
     "收起侧边栏": "收起側邊欄",
+    "向左展开": "向左展開",
+    "向右展开": "向右展開",
     "收起内容": "收起內容",
     "放大": "放大",
     "放大编辑": "放大編輯",
@@ -2653,6 +2655,12 @@
     "验证配置错误": "驗證設定錯誤",
     "高级设置": "進階設定",
     "高级配置": "進階設定",
+    "核心配置": "核心設定",
+    "创建渠道所需的基本信息": "建立頻道所需的基本資訊",
+    "请求配置": "請求設定",
+    "渠道行为": "頻道行為",
+    "额外设置": "額外設定",
+    "上游模型管理": "上游模型管理",
     "黑名单": "黑名單",
     "默认": "預設",
     "默认 API 版本": "預設 API 版本",

web/src/index.css

@@ -971,3 +971,26 @@ html.dark .with-pastel-balls::before {
 .semi-datepicker-range-input {
   border-radius: 10px !important;
 }
+
+@keyframes slideInLeft {
+  from {
+    transform: translateX(-100%);
+    opacity: 0;
+  }
+  to {
+    transform: translateX(0);
+    opacity: 1;
+  }
+}
+
+/* Channel advanced settings side panel animations */
+@keyframes slideInRight {
+  from {
+    transform: translateX(100%);
+    opacity: 0;
+  }
+  to {
+    transform: translateX(0);
+    opacity: 1;
+  }
+}

web/src/pages/Setting/Performance/SettingsPerformance.jsx

@@ -71,7 +71,7 @@ export default function SettingsPerformance(props) {
     'performance_setting.monitor_enabled': false,
     'performance_setting.monitor_cpu_threshold': 90,
     'performance_setting.monitor_memory_threshold': 90,
-    'performance_setting.monitor_disk_threshold': 90,
+    'performance_setting.monitor_disk_threshold': 95,
   });
   const refForm = useRef();
   const [inputsRow, setInputsRow] = useState(inputs);