Merge remote-tracking branch 'origin/main'

backend/internal/service/openai_ws_forwarder.go

@@ -864,7 +864,8 @@ func isOpenAIWSClientDisconnectError(err error) bool {
 		strings.Contains(message, "unexpected eof") ||
 		strings.Contains(message, "use of closed network connection") ||
 		strings.Contains(message, "connection reset by peer") ||
-		strings.Contains(message, "broken pipe")
+		strings.Contains(message, "broken pipe") ||
+		strings.Contains(message, "an established connection was aborted")
 }
 
 func classifyOpenAIWSReadFallbackReason(err error) string {

backend/internal/service/ops_concurrency.go

@@ -64,8 +64,12 @@ func (s *OpsService) getAccountsLoadMapBestEffort(ctx context.Context, accounts
 		if acc.ID <= 0 {
 			continue
 		}
-		if prev, ok := unique[acc.ID]; !ok || acc.Concurrency > prev {
-			unique[acc.ID] = acc.Concurrency
+		c := acc.Concurrency
+		if c <= 0 {
+			c = 1
+		}
+		if prev, ok := unique[acc.ID]; !ok || c > prev {
+			unique[acc.ID] = c
 		}
 	}
 

backend/internal/service/ops_metrics_collector.go

@@ -389,13 +389,9 @@ func (c *OpsMetricsCollector) collectConcurrencyQueueDepth(parentCtx context.Con
 		if acc.ID <= 0 {
 			continue
 		}
-		maxConc := acc.Concurrency
-		if maxConc < 0 {
-			maxConc = 0
-		}
 		batch = append(batch, AccountWithConcurrency{
 			ID:             acc.ID,
-			MaxConcurrency: maxConc,
+			MaxConcurrency: acc.Concurrency,
 		})
 	}
 	if len(batch) == 0 {

backend/internal/service/pricing_service.go

@@ -23,6 +23,17 @@ import (
 var (
 	openAIModelDatePattern     = regexp.MustCompile(`-\d{8}$`)
 	openAIModelBasePattern     = regexp.MustCompile(`^(gpt-\d+(?:\.\d+)?)(?:-|$)`)
+	openAIGPT54FallbackPricing = &LiteLLMModelPricing{
+		InputCostPerToken:               2.5e-06, // $2.5 per MTok
+		OutputCostPerToken:              1.5e-05, // $15 per MTok
+		CacheReadInputTokenCost:         2.5e-07, // $0.25 per MTok
+		LongContextInputTokenThreshold:  272000,
+		LongContextInputCostMultiplier:  2.0,
+		LongContextOutputCostMultiplier: 1.5,
+		LiteLLMProvider:                 "openai",
+		Mode:                            "chat",
+		SupportsPromptCaching:           true,
+	}
 )
 
 // LiteLLMModelPricing LiteLLM价格数据结构
@@ -33,6 +44,9 @@ type LiteLLMModelPricing struct {
 	CacheCreationInputTokenCost         float64 `json:"cache_creation_input_token_cost"`
 	CacheCreationInputTokenCostAbove1hr float64 `json:"cache_creation_input_token_cost_above_1hr"`
 	CacheReadInputTokenCost             float64 `json:"cache_read_input_token_cost"`
+	LongContextInputTokenThreshold      int     `json:"long_context_input_token_threshold,omitempty"`
+	LongContextInputCostMultiplier      float64 `json:"long_context_input_cost_multiplier,omitempty"`
+	LongContextOutputCostMultiplier     float64 `json:"long_context_output_cost_multiplier,omitempty"`
 	LiteLLMProvider                     string  `json:"litellm_provider"`
 	Mode                                string  `json:"mode"`
 	SupportsPromptCaching               bool    `json:"supports_prompt_caching"`
@@ -660,7 +674,8 @@ func (s *PricingService) matchByModelFamily(model string) *LiteLLMModelPricing {
 // 2. gpt-5.2-codex -> gpt-5.2（去掉后缀如 -codex, -mini, -max 等）
 // 3. gpt-5.2-20251222 -> gpt-5.2（去掉日期版本号）
 // 4. gpt-5.3-codex -> gpt-5.2-codex
-// 5. 最终回退到 DefaultTestModel (gpt-5.1-codex)
+// 5. gpt-5.4* -> 业务静态兜底价
+// 6. 最终回退到 DefaultTestModel (gpt-5.1-codex)
 func (s *PricingService) matchOpenAIModel(model string) *LiteLLMModelPricing {
 	if strings.HasPrefix(model, "gpt-5.3-codex-spark") {
 		if pricing, ok := s.pricingData["gpt-5.1-codex"]; ok {
@@ -690,6 +705,12 @@ func (s *PricingService) matchOpenAIModel(model string) *LiteLLMModelPricing {
 		}
 	}
 
+	if strings.HasPrefix(model, "gpt-5.4") {
+		logger.With(zap.String("component", "service.pricing")).
+			Info(fmt.Sprintf("[Pricing] OpenAI fallback matched %s -> %s", model, "gpt-5.4(static)"))
+		return openAIGPT54FallbackPricing
+	}
+
 	// 最终回退到 DefaultTestModel
 	defaultModel := strings.ToLower(openai.DefaultTestModel)
 	if pricing, ok := s.pricingData[defaultModel]; ok {

backend/internal/service/pricing_service_test.go

@@ -51,3 +51,20 @@ func TestGetModelPricing_OpenAIFallbackMatchedLoggedAsInfo(t *testing.T) {
 	require.True(t, logSink.ContainsMessageAtLevel("[Pricing] OpenAI fallback matched gpt-5.3-codex -> gpt-5.2-codex", "info"))
 	require.False(t, logSink.ContainsMessageAtLevel("[Pricing] OpenAI fallback matched gpt-5.3-codex -> gpt-5.2-codex", "warn"))
 }
+
+func TestGetModelPricing_Gpt54UsesStaticFallbackWhenRemoteMissing(t *testing.T) {
+	svc := &PricingService{
+		pricingData: map[string]*LiteLLMModelPricing{
+			"gpt-5.1-codex": &LiteLLMModelPricing{InputCostPerToken: 1.25e-6},
+		},
+	}
+
+	got := svc.GetModelPricing("gpt-5.4")
+	require.NotNil(t, got)
+	require.InDelta(t, 2.5e-6, got.InputCostPerToken, 1e-12)
+	require.InDelta(t, 1.5e-5, got.OutputCostPerToken, 1e-12)
+	require.InDelta(t, 2.5e-7, got.CacheReadInputTokenCost, 1e-12)
+	require.Equal(t, 272000, got.LongContextInputTokenThreshold)
+	require.InDelta(t, 2.0, got.LongContextInputCostMultiplier, 1e-12)
+	require.InDelta(t, 1.5, got.LongContextOutputCostMultiplier, 1e-12)
+}

backend/internal/service/subscription_calculate_progress_test.go

@@ -34,7 +34,7 @@ func TestCalculateProgress_BasicFields(t *testing.T) {
 	assert.Equal(t, int64(100), progress.ID)
 	assert.Equal(t, "Premium", progress.GroupName)
 	assert.Equal(t, sub.ExpiresAt, progress.ExpiresAt)
-	assert.Equal(t, 29, progress.ExpiresInDays) // 约 30 天
+	assert.True(t, progress.ExpiresInDays == 29 || progress.ExpiresInDays == 30, "ExpiresInDays should be 29 or 30, got %d", progress.ExpiresInDays)
 	assert.Nil(t, progress.Daily, "无日限额时 Daily 应为 nil")
 	assert.Nil(t, progress.Weekly, "无周限额时 Weekly 应为 nil")
 	assert.Nil(t, progress.Monthly, "无月限额时 Monthly 应为 nil")

backend/migrations/067_add_account_load_factor.sql

+ALTER TABLE accounts ADD COLUMN IF NOT EXISTS load_factor INTEGER;

backend/resources/model-pricing/model_prices_and_context_window.json

@@ -5140,6 +5140,39 @@
     "supports_vision": true,
     "supports_web_search": true
   },
+  "gpt-5.4": {
+    "cache_read_input_token_cost": 2.5e-07,
+    "input_cost_per_token": 2.5e-06,
+    "litellm_provider": "openai",
+    "max_input_tokens": 1050000,
+    "max_output_tokens": 128000,
+    "max_tokens": 128000,
+    "mode": "chat",
+    "output_cost_per_token": 1.5e-05,
+    "supported_endpoints": [
+      "/v1/chat/completions",
+      "/v1/responses"
+    ],
+    "supported_modalities": [
+      "text",
+      "image"
+    ],
+    "supported_output_modalities": [
+      "text",
+      "image"
+    ],
+    "supports_function_calling": true,
+    "supports_native_streaming": true,
+    "supports_parallel_function_calling": true,
+    "supports_pdf_input": true,
+    "supports_prompt_caching": true,
+    "supports_reasoning": true,
+    "supports_response_schema": true,
+    "supports_service_tier": true,
+    "supports_system_messages": true,
+    "supports_tool_choice": true,
+    "supports_vision": true
+  },
   "gpt-5.3-codex": {
     "cache_read_input_token_cost": 1.75e-07,
     "cache_read_input_token_cost_priority": 3.5e-07,

frontend/src/api/admin/accounts.ts

@@ -240,6 +240,18 @@ export async function clearRateLimit(id: number): Promise<Account> {
   return data
 }
 
+/**
+ * Reset account quota usage
+ * @param id - Account ID
+ * @returns Updated account
+ */
+export async function resetAccountQuota(id: number): Promise<Account> {
+  const { data } = await apiClient.post<Account>(
+    `/admin/accounts/${id}/reset-quota`
+  )
+  return data
+}
+
 /**
  * Get temporary unschedulable status
  * @param id - Account ID
@@ -576,6 +588,7 @@ export const accountsAPI = {
   getTodayStats,
   getBatchTodayStats,
   clearRateLimit,
+  resetAccountQuota,
   getTempUnschedulableStatus,
   resetTempUnschedulable,
   setSchedulable,

frontend/src/components/account/AccountCapacityCell.vue

@@ -71,6 +71,24 @@
         <span class="text-[9px] opacity-60">{{ rpmStrategyTag }}</span>
       </span>
     </div>
+
+    <!-- API Key 账号配额限制 -->
+    <div v-if="showQuotaLimit" class="flex items-center gap-1">
+      <span
+        :class="[
+          'inline-flex items-center gap-1 rounded-md px-1.5 py-0.5 text-[10px] font-medium',
+          quotaClass
+        ]"
+        :title="quotaTooltip"
+      >
+        <svg class="h-2.5 w-2.5" fill="none" viewBox="0 0 24 24" stroke="currentColor" stroke-width="2">
+          <path stroke-linecap="round" stroke-linejoin="round" d="M2.25 18.75a60.07 60.07 0 0115.797 2.101c.727.198 1.453-.342 1.453-1.096V18.75M3.75 4.5v.75A.75.75 0 013 6h-.75m0 0v-.375c0-.621.504-1.125 1.125-1.125H20.25M2.25 6v9m18-10.5v.75c0 .414.336.75.75.75h.75m-1.5-1.5h.375c.621 0 1.125.504 1.125 1.125v9.75c0 .621-.504 1.125-1.125 1.125h-.375m1.5-1.5H21a.75.75 0 00-.75.75v.75m0 0H3.75m0 0h-.375a1.125 1.125 0 01-1.125-1.125V15m1.5 1.5v-.75A.75.75 0 003 15h-.75M15 10.5a3 3 0 11-6 0 3 3 0 016 0zm3 0h.008v.008H18V10.5zm-12 0h.008v.008H6V10.5z" />
+        </svg>
+        <span class="font-mono">${{ formatCost(currentQuotaUsed) }}</span>
+        <span class="text-gray-400 dark:text-gray-500">/</span>
+        <span class="font-mono">${{ formatCost(account.quota_limit) }}</span>
+      </span>
+    </div>
   </div>
 </template>
 
@@ -286,6 +304,48 @@ const rpmTooltip = computed(() => {
   }
 })
 
+// 是否显示配额限制（仅 apikey 类型且设置了 quota_limit）
+const showQuotaLimit = computed(() => {
+  return (
+    props.account.type === 'apikey' &&
+    props.account.quota_limit !== undefined &&
+    props.account.quota_limit !== null &&
+    props.account.quota_limit > 0
+  )
+})
+
+// 当前已用配额
+const currentQuotaUsed = computed(() => props.account.quota_used ?? 0)
+
+// 配额状态样式
+const quotaClass = computed(() => {
+  if (!showQuotaLimit.value) return ''
+
+  const used = currentQuotaUsed.value
+  const limit = props.account.quota_limit || 0
+
+  if (used >= limit) {
+    return 'bg-red-100 text-red-700 dark:bg-red-900/30 dark:text-red-400'
+  }
+  if (used >= limit * 0.8) {
+    return 'bg-yellow-100 text-yellow-700 dark:bg-yellow-900/30 dark:text-yellow-400'
+  }
+  return 'bg-emerald-100 text-emerald-700 dark:bg-emerald-900/30 dark:text-emerald-400'
+})
+
+// 配额提示文字
+const quotaTooltip = computed(() => {
+  if (!showQuotaLimit.value) return ''
+
+  const used = currentQuotaUsed.value
+  const limit = props.account.quota_limit || 0
+
+  if (used >= limit) {
+    return t('admin.accounts.capacity.quota.exceeded')
+  }
+  return t('admin.accounts.capacity.quota.normal')
+})
+
 // 格式化费用显示
 const formatCost = (value: number | null | undefined) => {
   if (value === null || value === undefined) return '0'

frontend/src/components/account/BulkEditAccountModal.vue

@@ -469,7 +469,7 @@
       </div>
 
       <!-- Concurrency & Priority -->
-      <div class="grid grid-cols-2 gap-4 border-t border-gray-200 pt-4 dark:border-dark-600 lg:grid-cols-3">
+      <div class="grid grid-cols-2 gap-4 border-t border-gray-200 pt-4 dark:border-dark-600 lg:grid-cols-4">
         <div>
           <div class="mb-3 flex items-center justify-between">
             <label
@@ -496,8 +496,39 @@
             class="input"
             :class="!enableConcurrency && 'cursor-not-allowed opacity-50'"
             aria-labelledby="bulk-edit-concurrency-label"
+            @input="concurrency = Math.max(1, concurrency || 1)"
           />
         </div>
+        <div>
+          <div class="mb-3 flex items-center justify-between">
+            <label
+              id="bulk-edit-load-factor-label"
+              class="input-label mb-0"
+              for="bulk-edit-load-factor-enabled"
+            >
+              {{ t('admin.accounts.loadFactor') }}
+            </label>
+            <input
+              v-model="enableLoadFactor"
+              id="bulk-edit-load-factor-enabled"
+              type="checkbox"
+              aria-controls="bulk-edit-load-factor"
+              class="rounded border-gray-300 text-primary-600 focus:ring-primary-500"
+            />
+          </div>
+          <input
+            v-model.number="loadFactor"
+            id="bulk-edit-load-factor"
+            type="number"
+            min="1"
+            :disabled="!enableLoadFactor"
+            class="input"
+            :class="!enableLoadFactor && 'cursor-not-allowed opacity-50'"
+            aria-labelledby="bulk-edit-load-factor-label"
+            @input="loadFactor = (loadFactor &amp;&amp; loadFactor >= 1) ? loadFactor : null"
+          />
+          <p class="input-hint">{{ t('admin.accounts.loadFactorHint') }}</p>
+        </div>
         <div>
           <div class="mb-3 flex items-center justify-between">
             <label
@@ -869,6 +900,7 @@ const enableCustomErrorCodes = ref(false)
 const enableInterceptWarmup = ref(false)
 const enableProxy = ref(false)
 const enableConcurrency = ref(false)
+const enableLoadFactor = ref(false)
 const enablePriority = ref(false)
 const enableRateMultiplier = ref(false)
 const enableStatus = ref(false)
@@ -889,6 +921,7 @@ const customErrorCodeInput = ref<number | null>(null)
 const interceptWarmupRequests = ref(false)
 const proxyId = ref<number | null>(null)
 const concurrency = ref(1)
+const loadFactor = ref<number | null>(null)
 const priority = ref(1)
 const rateMultiplier = ref(1)
 const status = ref<'active' | 'inactive'>('active')
@@ -918,6 +951,7 @@ const allModels = [
   { value: 'claude-3-haiku-20240307', label: 'Claude 3 Haiku' },
   { value: 'gpt-5.3-codex', label: 'GPT-5.3 Codex' },
   { value: 'gpt-5.3-codex-spark', label: 'GPT-5.3 Codex Spark' },
+  { value: 'gpt-5.4', label: 'GPT-5.4' },
   { value: 'gpt-5.2-2025-12-11', label: 'GPT-5.2' },
   { value: 'gpt-5.2-codex', label: 'GPT-5.2 Codex' },
   { value: 'gpt-5.1-codex-max', label: 'GPT-5.1 Codex Max' },
@@ -1032,6 +1066,12 @@ const presetMappings = [
     to: 'gpt-5.3-codex-spark',
     color: 'bg-emerald-100 text-emerald-700 hover:bg-emerald-200 dark:bg-emerald-900/30 dark:text-emerald-400'
   },
+  {
+    label: 'GPT-5.4',
+    from: 'gpt-5.4',
+    to: 'gpt-5.4',
+    color: 'bg-rose-100 text-rose-700 hover:bg-rose-200 dark:bg-rose-900/30 dark:text-rose-400'
+  },
   {
     label: '5.2→5.3',
     from: 'gpt-5.2-codex',
@@ -1195,6 +1235,12 @@ const buildUpdatePayload = (): Record<string, unknown> | null => {
     updates.concurrency = concurrency.value
   }
 
+  if (enableLoadFactor.value) {
+    // 空值/NaN/0 时发送 0（后端约定 <= 0 表示清除）
+    const lf = loadFactor.value
+    updates.load_factor = (lf != null && !Number.isNaN(lf) && lf > 0) ? lf : 0
+  }
+
   if (enablePriority.value) {
     updates.priority = priority.value
   }
@@ -1340,6 +1386,7 @@ const handleSubmit = async () => {
     enableInterceptWarmup.value ||
     enableProxy.value ||
     enableConcurrency.value ||
+    enableLoadFactor.value ||
     enablePriority.value ||
     enableRateMultiplier.value ||
     enableStatus.value ||
@@ -1430,6 +1477,7 @@ watch(
       enableInterceptWarmup.value = false
       enableProxy.value = false
       enableConcurrency.value = false
+      enableLoadFactor.value = false
       enablePriority.value = false
       enableRateMultiplier.value = false
       enableStatus.value = false
@@ -1446,6 +1494,7 @@ watch(
       interceptWarmupRequests.value = false
       proxyId.value = null
       concurrency.value = 1
+      loadFactor.value = null
       priority.value = 1
       rateMultiplier.value = 1
       status.value = 'active'

frontend/src/components/account/CreateAccountModal.vue

@@ -1227,6 +1227,9 @@
 
       </div>
 
+      <!-- API Key 账号配额限制 -->
+      <QuotaLimitCard v-if="form.type === 'apikey'" v-model="editQuotaLimit" />
+
       <!-- Temp Unschedulable Rules -->
       <div class="border-t border-gray-200 pt-4 dark:border-dark-600 space-y-4">
         <div class="mb-3 flex items-center justify-between">
@@ -1749,10 +1752,18 @@
         <ProxySelector v-model="form.proxy_id" :proxies="proxies" />
       </div>
 
-      <div class="grid grid-cols-2 gap-4 lg:grid-cols-3">
+      <div class="grid grid-cols-2 gap-4 lg:grid-cols-4">
         <div>
           <label class="input-label">{{ t('admin.accounts.concurrency') }}</label>
-          <input v-model.number="form.concurrency" type="number" min="1" class="input" />
+          <input v-model.number="form.concurrency" type="number" min="1" class="input"
+            @input="form.concurrency = Math.max(1, form.concurrency || 1)" />
+        </div>
+        <div>
+          <label class="input-label">{{ t('admin.accounts.loadFactor') }}</label>
+          <input v-model.number="form.load_factor" type="number" min="1"
+            class="input" :placeholder="String(form.concurrency || 1)"
+            @input="form.load_factor = (form.load_factor &amp;&amp; form.load_factor >= 1) ? form.load_factor : null" />
+          <p class="input-hint">{{ t('admin.accounts.loadFactorHint') }}</p>
         </div>
         <div>
           <label class="input-label">{{ t('admin.accounts.priority') }}</label>
@@ -2337,11 +2348,12 @@ import Icon from '@/components/icons/Icon.vue'
 import ProxySelector from '@/components/common/ProxySelector.vue'
 import GroupSelector from '@/components/common/GroupSelector.vue'
 import ModelWhitelistSelector from '@/components/account/ModelWhitelistSelector.vue'
+import QuotaLimitCard from '@/components/account/QuotaLimitCard.vue'
 import { applyInterceptWarmup } from '@/components/account/credentialsBuilder'
 import { formatDateTimeLocalInput, parseDateTimeLocalInput } from '@/utils/format'
 import { createStableObjectKeyResolver } from '@/utils/stableObjectKey'
 import {
-  OPENAI_WS_MODE_CTX_POOL,
+  // OPENAI_WS_MODE_CTX_POOL,
   OPENAI_WS_MODE_OFF,
   OPENAI_WS_MODE_PASSTHROUGH,
   isOpenAIWSModeEnabled,
@@ -2460,6 +2472,7 @@ const accountCategory = ref<'oauth-based' | 'apikey'>('oauth-based') // UI selec
 const addMethod = ref<AddMethod>('oauth') // For oauth-based: 'oauth' or 'setup-token'
 const apiKeyBaseUrl = ref('https://api.anthropic.com')
 const apiKeyValue = ref('')
+const editQuotaLimit = ref<number | null>(null)
 const modelMappings = ref<ModelMapping[]>([])
 const modelRestrictionMode = ref<'whitelist' | 'mapping'>('whitelist')
 const allowedModels = ref<string[]>([])
@@ -2542,7 +2555,8 @@ const geminiSelectedTier = computed(() => {
 
 const openAIWSModeOptions = computed(() => [
   { value: OPENAI_WS_MODE_OFF, label: t('admin.accounts.openai.wsModeOff') },
-  { value: OPENAI_WS_MODE_CTX_POOL, label: t('admin.accounts.openai.wsModeCtxPool') },
+  // TODO: ctx_pool 选项暂时隐藏，待测试完成后恢复
+  // { value: OPENAI_WS_MODE_CTX_POOL, label: t('admin.accounts.openai.wsModeCtxPool') },
   { value: OPENAI_WS_MODE_PASSTHROUGH, label: t('admin.accounts.openai.wsModePassthrough') }
 ])
 
@@ -2632,6 +2646,7 @@ const form = reactive({
   credentials: {} as Record<string, unknown>,
   proxy_id: null as number | null,
   concurrency: 10,
+  load_factor: null as number | null,
   priority: 1,
   rate_multiplier: 1,
   group_ids: [] as number[],
@@ -3111,6 +3126,7 @@ const resetForm = () => {
   form.credentials = {}
   form.proxy_id = null
   form.concurrency = 10
+  form.load_factor = null
   form.priority = 1
   form.rate_multiplier = 1
   form.group_ids = []
@@ -3119,6 +3135,7 @@ const resetForm = () => {
   addMethod.value = 'oauth'
   apiKeyBaseUrl.value = 'https://api.anthropic.com'
   apiKeyValue.value = ''
+  editQuotaLimit.value = null
   modelMappings.value = []
   modelRestrictionMode.value = 'whitelist'
   allowedModels.value = [...claudeModels] // Default fill related models
@@ -3482,6 +3499,7 @@ const handleImportAccessToken = async (accessTokenInput: string) => {
           extra: soraExtra,
           proxy_id: form.proxy_id,
           concurrency: form.concurrency,
+          load_factor: form.load_factor ?? undefined,
           priority: form.priority,
           rate_multiplier: form.rate_multiplier,
           group_ids: form.group_ids,
@@ -3532,15 +3550,21 @@ const createAccountAndFinish = async (
   if (!applyTempUnschedConfig(credentials)) {
     return
   }
+  // Inject quota_limit for apikey accounts
+  let finalExtra = extra
+  if (type === 'apikey' && editQuotaLimit.value != null && editQuotaLimit.value > 0) {
+    finalExtra = { ...(extra || {}), quota_limit: editQuotaLimit.value }
+  }
   await doCreateAccount({
     name: form.name,
     notes: form.notes,
     platform,
     type,
     credentials,
-    extra,
+    extra: finalExtra,
     proxy_id: form.proxy_id,
     concurrency: form.concurrency,
+    load_factor: form.load_factor ?? undefined,
     priority: form.priority,
     rate_multiplier: form.rate_multiplier,
     group_ids: form.group_ids,
@@ -3596,6 +3620,7 @@ const handleOpenAIExchange = async (authCode: string) => {
         extra,
         proxy_id: form.proxy_id,
         concurrency: form.concurrency,
+        load_factor: form.load_factor ?? undefined,
         priority: form.priority,
         rate_multiplier: form.rate_multiplier,
         group_ids: form.group_ids,
@@ -3625,6 +3650,7 @@ const handleOpenAIExchange = async (authCode: string) => {
         extra: soraExtra,
         proxy_id: form.proxy_id,
         concurrency: form.concurrency,
+        load_factor: form.load_factor ?? undefined,
         priority: form.priority,
         rate_multiplier: form.rate_multiplier,
         group_ids: form.group_ids,
@@ -3702,6 +3728,7 @@ const handleOpenAIValidateRT = async (refreshTokenInput: string) => {
             extra,
             proxy_id: form.proxy_id,
             concurrency: form.concurrency,
+            load_factor: form.load_factor ?? undefined,
             priority: form.priority,
             rate_multiplier: form.rate_multiplier,
             group_ids: form.group_ids,
@@ -3729,6 +3756,7 @@ const handleOpenAIValidateRT = async (refreshTokenInput: string) => {
             extra: soraExtra,
             proxy_id: form.proxy_id,
             concurrency: form.concurrency,
+            load_factor: form.load_factor ?? undefined,
             priority: form.priority,
             rate_multiplier: form.rate_multiplier,
             group_ids: form.group_ids,
@@ -3817,6 +3845,7 @@ const handleSoraValidateST = async (sessionTokenInput: string) => {
           extra: soraExtra,
           proxy_id: form.proxy_id,
           concurrency: form.concurrency,
+          load_factor: form.load_factor ?? undefined,
           priority: form.priority,
           rate_multiplier: form.rate_multiplier,
           group_ids: form.group_ids,
@@ -3905,6 +3934,7 @@ const handleAntigravityValidateRT = async (refreshTokenInput: string) => {
           extra: {},
           proxy_id: form.proxy_id,
           concurrency: form.concurrency,
+          load_factor: form.load_factor ?? undefined,
           priority: form.priority,
           rate_multiplier: form.rate_multiplier,
           group_ids: form.group_ids,
@@ -4063,8 +4093,11 @@ const handleAnthropicExchange = async (authCode: string) => {
     }
 
     // Add RPM limit settings
-    if (rpmLimitEnabled.value && baseRpm.value != null && baseRpm.value > 0) {
-      extra.base_rpm = baseRpm.value
+    if (rpmLimitEnabled.value) {
+      const DEFAULT_BASE_RPM = 15
+      extra.base_rpm = (baseRpm.value != null && baseRpm.value > 0)
+        ? baseRpm.value
+        : DEFAULT_BASE_RPM
       extra.rpm_strategy = rpmStrategy.value
       if (rpmStickyBuffer.value != null && rpmStickyBuffer.value > 0) {
         extra.rpm_sticky_buffer = rpmStickyBuffer.value
@@ -4175,8 +4208,11 @@ const handleCookieAuth = async (sessionKey: string) => {
         }
 
         // Add RPM limit settings
-        if (rpmLimitEnabled.value && baseRpm.value != null && baseRpm.value > 0) {
-          extra.base_rpm = baseRpm.value
+        if (rpmLimitEnabled.value) {
+          const DEFAULT_BASE_RPM = 15
+          extra.base_rpm = (baseRpm.value != null && baseRpm.value > 0)
+            ? baseRpm.value
+            : DEFAULT_BASE_RPM
           extra.rpm_strategy = rpmStrategy.value
           if (rpmStickyBuffer.value != null && rpmStickyBuffer.value > 0) {
             extra.rpm_sticky_buffer = rpmStickyBuffer.value
@@ -4222,6 +4258,7 @@ const handleCookieAuth = async (sessionKey: string) => {
           extra,
           proxy_id: form.proxy_id,
           concurrency: form.concurrency,
+          load_factor: form.load_factor ?? undefined,
           priority: form.priority,
           rate_multiplier: form.rate_multiplier,
           group_ids: form.group_ids,

frontend/src/components/account/EditAccountModal.vue

@@ -650,10 +650,18 @@
         <ProxySelector v-model="form.proxy_id" :proxies="proxies" />
       </div>
 
-      <div class="grid grid-cols-2 gap-4 lg:grid-cols-3">
+      <div class="grid grid-cols-2 gap-4 lg:grid-cols-4">
         <div>
           <label class="input-label">{{ t('admin.accounts.concurrency') }}</label>
-          <input v-model.number="form.concurrency" type="number" min="1" class="input" />
+          <input v-model.number="form.concurrency" type="number" min="1" class="input"
+            @input="form.concurrency = Math.max(1, form.concurrency || 1)" />
+        </div>
+        <div>
+          <label class="input-label">{{ t('admin.accounts.loadFactor') }}</label>
+          <input v-model.number="form.load_factor" type="number" min="1"
+            class="input" :placeholder="String(form.concurrency || 1)"
+            @input="form.load_factor = (form.load_factor &amp;&amp; form.load_factor >= 1) ? form.load_factor : null" />
+          <p class="input-hint">{{ t('admin.accounts.loadFactorHint') }}</p>
         </div>
         <div>
           <label class="input-label">{{ t('admin.accounts.priority') }}</label>
@@ -759,6 +767,9 @@
         </div>
       </div>
 
+      <!-- API Key 账号配额限制 -->
+      <QuotaLimitCard v-if="account?.type === 'apikey'" v-model="editQuotaLimit" />
+
       <!-- OpenAI OAuth Codex 官方客户端限制开关 -->
       <div
         v-if="account?.platform === 'openai' && account?.type === 'oauth'"
@@ -1269,11 +1280,12 @@ import Icon from '@/components/icons/Icon.vue'
 import ProxySelector from '@/components/common/ProxySelector.vue'
 import GroupSelector from '@/components/common/GroupSelector.vue'
 import ModelWhitelistSelector from '@/components/account/ModelWhitelistSelector.vue'
+import QuotaLimitCard from '@/components/account/QuotaLimitCard.vue'
 import { applyInterceptWarmup } from '@/components/account/credentialsBuilder'
 import { formatDateTimeLocalInput, parseDateTimeLocalInput } from '@/utils/format'
 import { createStableObjectKeyResolver } from '@/utils/stableObjectKey'
 import {
-  OPENAI_WS_MODE_CTX_POOL,
+  // OPENAI_WS_MODE_CTX_POOL,
   OPENAI_WS_MODE_OFF,
   OPENAI_WS_MODE_PASSTHROUGH,
   isOpenAIWSModeEnabled,
@@ -1386,9 +1398,11 @@ const openaiOAuthResponsesWebSocketV2Mode = ref<OpenAIWSMode>(OPENAI_WS_MODE_OFF
 const openaiAPIKeyResponsesWebSocketV2Mode = ref<OpenAIWSMode>(OPENAI_WS_MODE_OFF)
 const codexCLIOnlyEnabled = ref(false)
 const anthropicPassthroughEnabled = ref(false)
+const editQuotaLimit = ref<number | null>(null)
 const openAIWSModeOptions = computed(() => [
   { value: OPENAI_WS_MODE_OFF, label: t('admin.accounts.openai.wsModeOff') },
-  { value: OPENAI_WS_MODE_CTX_POOL, label: t('admin.accounts.openai.wsModeCtxPool') },
+  // TODO: ctx_pool 选项暂时隐藏，待测试完成后恢复
+  // { value: OPENAI_WS_MODE_CTX_POOL, label: t('admin.accounts.openai.wsModeCtxPool') },
   { value: OPENAI_WS_MODE_PASSTHROUGH, label: t('admin.accounts.openai.wsModePassthrough') }
 ])
 const openaiResponsesWebSocketV2Mode = computed({
@@ -1464,6 +1478,7 @@ const form = reactive({
   notes: '',
   proxy_id: null as number | null,
   concurrency: 1,
+  load_factor: null as number | null,
   priority: 1,
   rate_multiplier: 1,
   status: 'active' as 'active' | 'inactive',
@@ -1497,9 +1512,12 @@ watch(
       form.notes = newAccount.notes || ''
       form.proxy_id = newAccount.proxy_id
       form.concurrency = newAccount.concurrency
+      form.load_factor = newAccount.load_factor ?? null
       form.priority = newAccount.priority
       form.rate_multiplier = newAccount.rate_multiplier ?? 1
-      form.status = newAccount.status as 'active' | 'inactive'
+      form.status = (newAccount.status === 'active' || newAccount.status === 'inactive')
+        ? newAccount.status
+        : 'active'
       form.group_ids = newAccount.group_ids || []
       form.expires_at = newAccount.expires_at ?? null
 
@@ -1540,6 +1558,14 @@ watch(
         anthropicPassthroughEnabled.value = extra?.anthropic_passthrough === true
       }
 
+      // Load quota limit for apikey accounts
+      if (newAccount.type === 'apikey') {
+        const quotaVal = extra?.quota_limit as number | undefined
+        editQuotaLimit.value = (quotaVal && quotaVal > 0) ? quotaVal : null
+      } else {
+        editQuotaLimit.value = null
+      }
+
       // Load antigravity model mapping (Antigravity 只支持映射模式)
       if (newAccount.platform === 'antigravity') {
         const credentials = newAccount.credentials as Record<string, unknown> | undefined
@@ -2039,6 +2065,11 @@ const handleSubmit = async () => {
   if (!props.account) return
   const accountID = props.account.id
 
+  if (form.status !== 'active' && form.status !== 'inactive') {
+    appStore.showError(t('admin.accounts.pleaseSelectStatus'))
+    return
+  }
+
   const updatePayload: Record<string, unknown> = { ...form }
   try {
     // 后端期望 proxy_id: 0 表示清除代理，而不是 null
@@ -2048,6 +2079,11 @@ const handleSubmit = async () => {
     if (form.expires_at === null) {
       updatePayload.expires_at = 0
     }
+    // load_factor: 空值/NaN/0/负数 时发送 0（后端约定 <= 0 = 清除）
+    const lf = form.load_factor
+    if (lf == null || Number.isNaN(lf) || lf <= 0) {
+      updatePayload.load_factor = 0
+    }
     updatePayload.auto_pause_on_expired = autoPauseOnExpired.value
 
     // For apikey type, handle credentials update
@@ -2187,8 +2223,11 @@ const handleSubmit = async () => {
       }
 
       // RPM limit settings
-      if (rpmLimitEnabled.value && baseRpm.value != null && baseRpm.value > 0) {
-        newExtra.base_rpm = baseRpm.value
+      if (rpmLimitEnabled.value) {
+        const DEFAULT_BASE_RPM = 15
+        newExtra.base_rpm = (baseRpm.value != null && baseRpm.value > 0)
+          ? baseRpm.value
+          : DEFAULT_BASE_RPM
         newExtra.rpm_strategy = rpmStrategy.value
         if (rpmStickyBuffer.value != null && rpmStickyBuffer.value > 0) {
           newExtra.rpm_sticky_buffer = rpmStickyBuffer.value
@@ -2282,6 +2321,19 @@ const handleSubmit = async () => {
       updatePayload.extra = newExtra
     }
 
+    // For apikey accounts, handle quota_limit in extra
+    if (props.account.type === 'apikey') {
+      const currentExtra = (updatePayload.extra as Record<string, unknown>) ||
+        (props.account.extra as Record<string, unknown>) || {}
+      const newExtra: Record<string, unknown> = { ...currentExtra }
+      if (editQuotaLimit.value != null && editQuotaLimit.value > 0) {
+        newExtra.quota_limit = editQuotaLimit.value
+      } else {
+        delete newExtra.quota_limit
+      }
+      updatePayload.extra = newExtra
+    }
+
     const canContinue = await ensureAntigravityMixedChannelConfirmed(async () => {
       await submitUpdateAccount(accountID, updatePayload)
     })

frontend/src/components/account/QuotaLimitCard.vue

+<script setup lang="ts">
+import { ref, watch } from 'vue'
+import { useI18n } from 'vue-i18n'
+
+const { t } = useI18n()
+
+const props = defineProps<{
+  modelValue: number | null
+}>()
+
+const emit = defineEmits<{
+  'update:modelValue': [value: number | null]
+}>()
+
+const enabled = ref(props.modelValue != null && props.modelValue > 0)
+
+// Sync enabled state when modelValue changes externally (e.g. account load)
+watch(
+  () => props.modelValue,
+  (val) => {
+    enabled.value = val != null && val > 0
+  }
+)
+
+// When toggle is turned off, clear the value
+watch(enabled, (val) => {
+  if (!val) {
+    emit('update:modelValue', null)
+  }
+})
+
+const onInput = (e: Event) => {
+  const raw = (e.target as HTMLInputElement).valueAsNumber
+  emit('update:modelValue', Number.isNaN(raw) ? null : raw)
+}
+</script>
+
+<template>
+  <div class="border-t border-gray-200 pt-4 dark:border-dark-600 space-y-4">
+    <div class="mb-3">
+      <h3 class="input-label mb-0 text-base font-semibold">{{ t('admin.accounts.quotaLimit') }}</h3>
+      <p class="mt-1 text-xs text-gray-500 dark:text-gray-400">
+        {{ t('admin.accounts.quotaLimitHint') }}
+      </p>
+    </div>
+
+    <div class="rounded-lg border border-gray-200 p-4 dark:border-dark-600">
+      <div class="mb-3 flex items-center justify-between">
+        <div>
+          <label class="input-label mb-0">{{ t('admin.accounts.quotaLimitToggle') }}</label>
+          <p class="mt-1 text-xs text-gray-500 dark:text-gray-400">
+            {{ t('admin.accounts.quotaLimitToggleHint') }}
+          </p>
+        </div>
+        <button
+          type="button"
+          @click="enabled = !enabled"
+          :class="[
+            'relative inline-flex h-6 w-11 flex-shrink-0 cursor-pointer rounded-full border-2 border-transparent transition-colors duration-200 ease-in-out focus:outline-none focus:ring-2 focus:ring-primary-500 focus:ring-offset-2',
+            enabled ? 'bg-primary-600' : 'bg-gray-200 dark:bg-dark-600'
+          ]"
+        >
+          <span
+            :class="[
+              'pointer-events-none inline-block h-5 w-5 transform rounded-full bg-white shadow ring-0 transition duration-200 ease-in-out',
+              enabled ? 'translate-x-5' : 'translate-x-0'
+            ]"
+          />
+        </button>
+      </div>
+
+      <div v-if="enabled" class="space-y-3">
+        <div>
+          <label class="input-label">{{ t('admin.accounts.quotaLimitAmount') }}</label>
+          <div class="relative">
+            <span class="absolute left-3 top-1/2 -translate-y-1/2 text-gray-500 dark:text-gray-400">$</span>
+            <input
+              :value="modelValue"
+              @input="onInput"
+              type="number"
+              min="0"
+              step="0.01"
+              class="input pl-7"
+              :placeholder="t('admin.accounts.quotaLimitPlaceholder')"
+            />
+          </div>
+          <p class="input-hint">{{ t('admin.accounts.quotaLimitAmountHint') }}</p>
+        </div>
+      </div>
+    </div>
+  </div>
+</template>

frontend/src/components/admin/account/AccountActionMenu.vue

@@ -41,6 +41,10 @@
               <Icon name="clock" size="sm" />
               {{ t('admin.accounts.clearRateLimit') }}
             </button>
+            <button v-if="hasQuotaLimit" @click="$emit('reset-quota', account); $emit('close')" class="flex w-full items-center gap-2 px-4 py-2 text-sm text-teal-600 hover:bg-gray-100 dark:hover:bg-dark-700">
+              <Icon name="refresh" size="sm" />
+              {{ t('admin.accounts.resetQuota') }}
+            </button>
           </template>
         </div>
       </div>
@@ -55,7 +59,7 @@ import { Icon } from '@/components/icons'
 import type { Account } from '@/types'
 
 const props = defineProps<{ show: boolean; account: Account | null; position: { top: number; left: number } | null }>()
-const emit = defineEmits(['close', 'test', 'stats', 'schedule', 'reauth', 'refresh-token', 'reset-status', 'clear-rate-limit'])
+const emit = defineEmits(['close', 'test', 'stats', 'schedule', 'reauth', 'refresh-token', 'reset-status', 'clear-rate-limit', 'reset-quota'])
 const { t } = useI18n()
 const isRateLimited = computed(() => {
   if (props.account?.rate_limit_reset_at && new Date(props.account.rate_limit_reset_at) > new Date()) {
@@ -71,6 +75,12 @@ const isRateLimited = computed(() => {
   return false
 })
 const isOverloaded = computed(() => props.account?.overload_until && new Date(props.account.overload_until) > new Date())
+const hasQuotaLimit = computed(() => {
+  return props.account?.type === 'apikey' &&
+    props.account?.quota_limit !== undefined &&
+    props.account?.quota_limit !== null &&
+    props.account?.quota_limit > 0
+})
 
 const handleKeydown = (event: KeyboardEvent) => {
   if (event.key === 'Escape') emit('close')

frontend/src/components/charts/TokenUsageTrend.vue

@@ -63,7 +63,8 @@ const chartColors = computed(() => ({
   grid: isDarkMode.value ? '#374151' : '#e5e7eb',
   input: '#3b82f6',
   output: '#10b981',
-  cache: '#f59e0b'
+  cacheCreation: '#f59e0b',
+  cacheRead: '#06b6d4'
 }))
 
 const chartData = computed(() => {
@@ -89,10 +90,18 @@ const chartData = computed(() => {
         tension: 0.3
       },
       {
-        label: 'Cache',
-        data: props.trendData.map((d) => d.cache_tokens),
-        borderColor: chartColors.value.cache,
-        backgroundColor: `${chartColors.value.cache}20`,
+        label: 'Cache Creation',
+        data: props.trendData.map((d) => d.cache_creation_tokens),
+        borderColor: chartColors.value.cacheCreation,
+        backgroundColor: `${chartColors.value.cacheCreation}20`,
+        fill: true,
+        tension: 0.3
+      },
+      {
+        label: 'Cache Read',
+        data: props.trendData.map((d) => d.cache_read_tokens),
+        borderColor: chartColors.value.cacheRead,
+        backgroundColor: `${chartColors.value.cacheRead}20`,
         fill: true,
         tension: 0.3
       }

frontend/src/components/keys/UseKeyModal.vue

@@ -443,7 +443,22 @@ $env:ANTHROPIC_AUTH_TOKEN="${apiKey}"`
       content = ''
   }
 
-  return [{ path, content }]
+  const vscodeSettingsPath = activeTab.value === 'unix'
+    ? '~/.claude/settings.json'
+    : '%userprofile%\\.claude\\settings.json'
+
+  const vscodeContent = `{
+  "env": {
+    "ANTHROPIC_BASE_URL": "${baseUrl}",
+    "ANTHROPIC_AUTH_TOKEN": "${apiKey}",
+    "CLAUDE_CODE_ATTRIBUTION_HEADER": "0"
+  }
+}`
+
+  return [
+    { path, content },
+    { path: vscodeSettingsPath, content: vscodeContent, hint: 'VSCode Claude Code' }
+  ]
 }
 
 function generateGeminiCliContent(baseUrl: string, apiKey: string): FileConfig {
@@ -496,16 +511,18 @@ function generateOpenAIFiles(baseUrl: string, apiKey: string): FileConfig[] {
   const configDir = isWindows ? '%userprofile%\\.codex' : '~/.codex'
 
   // config.toml content
-  const configContent = `model_provider = "sub2api"
-model = "gpt-5.3-codex"
-model_reasoning_effort = "high"
-network_access = "enabled"
+  const configContent = `model_provider = "OpenAI"
+model = "gpt-5.4"
+review_model = "gpt-5.4"
+model_reasoning_effort = "xhigh"
 disable_response_storage = true
+network_access = "enabled"
 windows_wsl_setup_acknowledged = true
-model_verbosity = "high"
+model_context_window = 1000000
+model_auto_compact_token_limit = 900000
 
-[model_providers.sub2api]
-name = "sub2api"
+[model_providers.OpenAI]
+name = "OpenAI"
 base_url = "${baseUrl}"
 wire_api = "responses"
 requires_openai_auth = true`
@@ -533,16 +550,18 @@ function generateOpenAIWsFiles(baseUrl: string, apiKey: string): FileConfig[] {
   const configDir = isWindows ? '%userprofile%\\.codex' : '~/.codex'
 
   // config.toml content with WebSocket v2
-  const configContent = `model_provider = "sub2api"
-model = "gpt-5.3-codex"
-model_reasoning_effort = "high"
-network_access = "enabled"
+  const configContent = `model_provider = "OpenAI"
+model = "gpt-5.4"
+review_model = "gpt-5.4"
+model_reasoning_effort = "xhigh"
 disable_response_storage = true
+network_access = "enabled"
 windows_wsl_setup_acknowledged = true
-model_verbosity = "high"
+model_context_window = 1000000
+model_auto_compact_token_limit = 900000
 
-[model_providers.sub2api]
-name = "sub2api"
+[model_providers.OpenAI]
+name = "OpenAI"
 base_url = "${baseUrl}"
 wire_api = "responses"
 supports_websockets = true
@@ -655,6 +674,22 @@ function generateOpenCodeConfig(platform: string, baseUrl: string, apiKey: strin
         xhigh: {}
       }
     },
+    'gpt-5.4': {
+      name: 'GPT-5.4',
+      limit: {
+        context: 1050000,
+        output: 128000
+      },
+      options: {
+        store: false
+      },
+      variants: {
+        low: {},
+        medium: {},
+        high: {},
+        xhigh: {}
+      }
+    },
     'gpt-5.3-codex-spark': {
       name: 'GPT-5.3 Codex Spark',
       limit: {

frontend/src/composables/__tests__/useModelWhitelist.spec.ts

@@ -2,6 +2,13 @@ import { describe, expect, it } from 'vitest'
 import { buildModelMappingObject, getModelsByPlatform } from '../useModelWhitelist'
 
 describe('useModelWhitelist', () => {
+  it('openai 模型列表包含 GPT-5.4 官方快照', () => {
+    const models = getModelsByPlatform('openai')
+
+    expect(models).toContain('gpt-5.4')
+    expect(models).toContain('gpt-5.4-2026-03-05')
+  })
+
   it('antigravity 模型列表包含图片模型兼容项', () => {
     const models = getModelsByPlatform('antigravity')
 
@@ -15,4 +22,12 @@ describe('useModelWhitelist', () => {
       'gemini-3.1-flash-image': 'gemini-3.1-flash-image'
     })
   })
+
+  it('whitelist 模式会保留 GPT-5.4 官方快照的精确映射', () => {
+    const mapping = buildModelMappingObject('whitelist', ['gpt-5.4-2026-03-05'], [])
+
+    expect(mapping).toEqual({
+      'gpt-5.4-2026-03-05': 'gpt-5.4-2026-03-05'
+    })
+  })
 })

frontend/src/composables/useModelWhitelist.ts

@@ -24,6 +24,8 @@ const openaiModels = [
   // GPT-5.2 系列
   'gpt-5.2', 'gpt-5.2-2025-12-11', 'gpt-5.2-chat-latest',
   'gpt-5.2-codex', 'gpt-5.2-pro', 'gpt-5.2-pro-2025-12-11',
+  // GPT-5.4 系列
+  'gpt-5.4', 'gpt-5.4-2026-03-05',
   // GPT-5.3 系列
   'gpt-5.3-codex', 'gpt-5.3-codex-spark',
   'chatgpt-4o-latest',
@@ -277,6 +279,7 @@ const openaiPresetMappings = [
   { label: 'GPT-5.3 Codex Spark', from: 'gpt-5.3-codex-spark', to: 'gpt-5.3-codex-spark', color: 'bg-teal-100 text-teal-700 hover:bg-teal-200 dark:bg-teal-900/30 dark:text-teal-400' },
   { label: 'GPT-5.1', from: 'gpt-5.1', to: 'gpt-5.1', color: 'bg-orange-100 text-orange-700 hover:bg-orange-200 dark:bg-orange-900/30 dark:text-orange-400' },
   { label: 'GPT-5.2', from: 'gpt-5.2', to: 'gpt-5.2', color: 'bg-red-100 text-red-700 hover:bg-red-200 dark:bg-red-900/30 dark:text-red-400' },
+  { label: 'GPT-5.4', from: 'gpt-5.4', to: 'gpt-5.4', color: 'bg-rose-100 text-rose-700 hover:bg-rose-200 dark:bg-rose-900/30 dark:text-rose-400' },
   { label: 'GPT-5.1 Codex', from: 'gpt-5.1-codex', to: 'gpt-5.1-codex', color: 'bg-cyan-100 text-cyan-700 hover:bg-cyan-200 dark:bg-cyan-900/30 dark:text-cyan-400' }
 ]
 

frontend/src/i18n/locales/en.ts

@@ -133,6 +133,8 @@ export default {
     requests: 'Requests',
     inputTokens: 'Input Tokens',
     outputTokens: 'Output Tokens',
+    cacheCreationTokens: 'Cache Creation',
+    cacheReadTokens: 'Cache Read',
     totalTokens: 'Total Tokens',
     cost: 'Cost',
     // Status
@@ -155,11 +157,19 @@ export default {
     subscriptionExpires: 'Subscription Expires',
     // Usage stat cells
     todayRequests: 'Today Requests',
+    todayInputTokens: 'Today Input',
+    todayOutputTokens: 'Today Output',
     todayTokens: 'Today Tokens',
+    todayCacheCreation: 'Today Cache Creation',
+    todayCacheRead: 'Today Cache Read',
     todayCost: 'Today Cost',
     rpmTpm: 'RPM / TPM',
     totalRequests: 'Total Requests',
+    totalInputTokens: 'Total Input',
+    totalOutputTokens: 'Total Output',
     totalTokensLabel: 'Total Tokens',
+    totalCacheCreation: 'Total Cache Creation',
+    totalCacheRead: 'Total Cache Read',
     totalCost: 'Total Cost',
     avgDuration: 'Avg Duration',
     // Messages
@@ -1724,6 +1734,10 @@ export default {
           stickyExemptWarning: 'RPM limit (Sticky Exempt) - Approaching limit',
           stickyExemptOver: 'RPM limit (Sticky Exempt) - Over limit, sticky only'
         },
+        quota: {
+          exceeded: 'Quota exceeded, account paused',
+          normal: 'Quota normal'
+        },
       },
       tempUnschedulable: {
         title: 'Temp Unschedulable',
@@ -1769,6 +1783,14 @@ export default {
         }
       },
       clearRateLimit: 'Clear Rate Limit',
+      resetQuota: 'Reset Quota',
+      quotaLimit: 'Quota Limit',
+      quotaLimitPlaceholder: '0 means unlimited',
+      quotaLimitHint: 'Set max spending limit (USD). Account will be paused when reached. Changing limit won\'t reset usage.',
+      quotaLimitToggle: 'Enable Quota Limit',
+      quotaLimitToggleHint: 'When enabled, account will be paused when usage reaches the set limit',
+      quotaLimitAmount: 'Limit Amount',
+      quotaLimitAmountHint: 'Maximum spending limit (USD). Account will be auto-paused when reached. Changing limit won\'t reset usage.',
       testConnection: 'Test Connection',
       reAuthorize: 'Re-Authorize',
       refreshToken: 'Refresh Token',
@@ -1981,10 +2003,12 @@ export default {
       proxy: 'Proxy',
       noProxy: 'No Proxy',
       concurrency: 'Concurrency',
+      loadFactor: 'Load Factor',
+      loadFactorHint: 'Higher load factor increases scheduling frequency',
       priority: 'Priority',
       priorityHint: 'Lower value accounts are used first',
       billingRateMultiplier: 'Billing Rate Multiplier',
-      billingRateMultiplierHint: '>=0, 0 means free. Affects account billing only',
+      billingRateMultiplierHint: '0 = free, affects account billing only',
       expiresAt: 'Expires At',
       expiresAtHint: 'Leave empty for no expiration',
       higherPriorityFirst: 'Lower value means higher priority',
@@ -2000,6 +2024,7 @@ export default {
       accountUpdated: 'Account updated successfully',
       failedToCreate: 'Failed to create account',
       failedToUpdate: 'Failed to update account',
+      pleaseSelectStatus: 'Please select a valid account status',
       mixedChannelWarningTitle: 'Mixed Channel Warning',
       mixedChannelWarning: 'Warning: Group "{groupName}" contains both {currentPlatform} and {otherPlatform} accounts. Mixing different channels may cause thinking block signature validation issues, which will fallback to non-thinking mode. Are you sure you want to continue?',
       pleaseEnterAccountName: 'Please enter account name',