feat: add Cache TTL Override per account + bump VERSION to 0.1.83

- Account-level cache TTL override: rewrite Anthropic cache_creation token classification (5m↔1h) in streaming/non-streaming responses - New DB field cache_ttl_overridden in usage_log for billing tracking - Migration 055_add_cache_ttl_overridden - Frontend: CacheTTL override toggle in account create/edit modals - Ent schema regenerated for new usage_log fields Co-Authored-By: Claude Opus 4.6 <noreply@anthropic.com>
2026-02-17 11:22:08 +03:00
parent a817cafe3d
commit 3d1f03c286
25 changed files with 533 additions and 19 deletions
--- a/frontend/src/components/account/CreateAccountModal.vue
+++ b/frontend/src/components/account/CreateAccountModal.vue
@@ -1527,6 +1527,46 @@
            </button>
          </div>
        </div>
+
+        <!-- Cache TTL Override -->
+        <div class="rounded-lg border border-gray-200 p-4 dark:border-dark-600">
+          <div class="flex items-center justify-between">
+            <div>
+              <label class="input-label mb-0">{{ t('admin.accounts.quotaControl.cacheTTLOverride.label') }}</label>
+              <p class="mt-1 text-xs text-gray-500 dark:text-gray-400">
+                {{ t('admin.accounts.quotaControl.cacheTTLOverride.hint') }}
+              </p>
+            </div>
+            <button
+              type="button"
+              @click="cacheTTLOverrideEnabled = !cacheTTLOverrideEnabled"
+              :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',
+                cacheTTLOverrideEnabled ? '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',
+                  cacheTTLOverrideEnabled ? 'translate-x-5' : 'translate-x-0'
+                ]"
+              />
+            </button>
+          </div>
+          <div v-if="cacheTTLOverrideEnabled" class="mt-3">
+            <label class="input-label text-xs">{{ t('admin.accounts.quotaControl.cacheTTLOverride.target') }}</label>
+            <select
+              v-model="cacheTTLOverrideTarget"
+              class="mt-1 block w-full rounded-md border border-gray-300 bg-white px-3 py-2 text-sm shadow-sm focus:border-primary-500 focus:outline-none focus:ring-1 focus:ring-primary-500 dark:border-dark-500 dark:bg-dark-700 dark:text-white"
+            >
+              <option value="5m">5m</option>
+              <option value="1h">1h</option>
+            </select>
+            <p class="mt-1 text-xs text-gray-500 dark:text-gray-400">
+              {{ t('admin.accounts.quotaControl.cacheTTLOverride.targetHint') }}
+            </p>
+          </div>
+        </div>
      </div>

      <div>
@@ -2146,6 +2186,8 @@ const maxSessions = ref<number | null>(null)
 const sessionIdleTimeout = ref<number | null>(null)
 const tlsFingerprintEnabled = ref(false)
 const sessionIdMaskingEnabled = ref(false)
+const cacheTTLOverrideEnabled = ref(false)
+const cacheTTLOverrideTarget = ref<string>('5m')

 // Gemini tier selection (used as fallback when auto-detection is unavailable/fails)
 const geminiTierGoogleOne = ref<'google_one_free' | 'google_ai_pro' | 'google_ai_ultra'>('google_one_free')
@@ -2597,6 +2639,8 @@ const resetForm = () => {
  sessionIdleTimeout.value = null
  tlsFingerprintEnabled.value = false
  sessionIdMaskingEnabled.value = false
+  cacheTTLOverrideEnabled.value = false
+  cacheTTLOverrideTarget.value = '5m'
  antigravityAccountType.value = 'oauth'
  upstreamBaseUrl.value = ''
  upstreamApiKey.value = ''
@@ -3174,6 +3218,12 @@ const handleAnthropicExchange = async (authCode: string) => {
      extra.session_id_masking_enabled = true
    }

+    // Add cache TTL override settings
+    if (cacheTTLOverrideEnabled.value) {
+      extra.cache_ttl_override_enabled = true
+      extra.cache_ttl_override_target = cacheTTLOverrideTarget.value
+    }
+
    const credentials = {
      ...tokenInfo,
      ...(interceptWarmupRequests.value ? { intercept_warmup_requests: true } : {})
@@ -3267,6 +3317,12 @@ const handleCookieAuth = async (sessionKey: string) => {
          extra.session_id_masking_enabled = true
        }

+        // Add cache TTL override settings
+        if (cacheTTLOverrideEnabled.value) {
+          extra.cache_ttl_override_enabled = true
+          extra.cache_ttl_override_target = cacheTTLOverrideTarget.value
+        }
+
        const accountName = keys.length > 1 ? `${form.name} #${i + 1}` : form.name

        // Merge interceptWarmupRequests into credentials
--- a/frontend/src/components/account/EditAccountModal.vue
+++ b/frontend/src/components/account/EditAccountModal.vue
@@ -904,6 +904,46 @@
            </button>
          </div>
        </div>
+
+        <!-- Cache TTL Override -->
+        <div class="rounded-lg border border-gray-200 p-4 dark:border-dark-600">
+          <div class="flex items-center justify-between">
+            <div>
+              <label class="input-label mb-0">{{ t('admin.accounts.quotaControl.cacheTTLOverride.label') }}</label>
+              <p class="mt-1 text-xs text-gray-500 dark:text-gray-400">
+                {{ t('admin.accounts.quotaControl.cacheTTLOverride.hint') }}
+              </p>
+            </div>
+            <button
+              type="button"
+              @click="cacheTTLOverrideEnabled = !cacheTTLOverrideEnabled"
+              :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',
+                cacheTTLOverrideEnabled ? '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',
+                  cacheTTLOverrideEnabled ? 'translate-x-5' : 'translate-x-0'
+                ]"
+              />
+            </button>
+          </div>
+          <div v-if="cacheTTLOverrideEnabled" class="mt-3">
+            <label class="input-label text-xs">{{ t('admin.accounts.quotaControl.cacheTTLOverride.target') }}</label>
+            <select
+              v-model="cacheTTLOverrideTarget"
+              class="mt-1 block w-full rounded-md border border-gray-300 bg-white px-3 py-2 text-sm shadow-sm focus:border-primary-500 focus:outline-none focus:ring-1 focus:ring-primary-500 dark:border-dark-500 dark:bg-dark-700 dark:text-white"
+            >
+              <option value="5m">5m</option>
+              <option value="1h">1h</option>
+            </select>
+            <p class="mt-1 text-xs text-gray-500 dark:text-gray-400">
+              {{ t('admin.accounts.quotaControl.cacheTTLOverride.targetHint') }}
+            </p>
+          </div>
+        </div>
      </div>

      <div class="border-t border-gray-200 pt-4 dark:border-dark-600">
@@ -1102,6 +1142,8 @@ const maxSessions = ref<number | null>(null)
 const sessionIdleTimeout = ref<number | null>(null)
 const tlsFingerprintEnabled = ref(false)
 const sessionIdMaskingEnabled = ref(false)
+const cacheTTLOverrideEnabled = ref(false)
+const cacheTTLOverrideTarget = ref<string>('5m')

 // Computed: current preset mappings based on platform
 const presetMappings = computed(() => getPresetMappingsByPlatform(props.account?.platform || 'anthropic'))
@@ -1489,6 +1531,8 @@ function loadQuotaControlSettings(account: Account) {
  sessionIdleTimeout.value = null
  tlsFingerprintEnabled.value = false
  sessionIdMaskingEnabled.value = false
+  cacheTTLOverrideEnabled.value = false
+  cacheTTLOverrideTarget.value = '5m'

  // Only applies to Anthropic OAuth/SetupToken accounts
  if (account.platform !== 'anthropic' || (account.type !== 'oauth' && account.type !== 'setup-token')) {
@@ -1517,6 +1561,12 @@ function loadQuotaControlSettings(account: Account) {
  if (account.session_id_masking_enabled === true) {
    sessionIdMaskingEnabled.value = true
  }
+
+  // Load cache TTL override setting
+  if (account.cache_ttl_override_enabled === true) {
+    cacheTTLOverrideEnabled.value = true
+    cacheTTLOverrideTarget.value = account.cache_ttl_override_target || '5m'
+  }
 }

 function formatTempUnschedKeywords(value: unknown) {
@@ -1723,6 +1773,15 @@ const handleSubmit = async () => {
        delete newExtra.session_id_masking_enabled
      }

+      // Cache TTL override setting
+      if (cacheTTLOverrideEnabled.value) {
+        newExtra.cache_ttl_override_enabled = true
+        newExtra.cache_ttl_override_target = cacheTTLOverrideTarget.value
+      } else {
+        delete newExtra.cache_ttl_override_enabled
+        delete newExtra.cache_ttl_override_target
+      }
+
      updatePayload.extra = newExtra
    }

--- a/frontend/src/components/admin/usage/UsageTable.vue
+++ b/frontend/src/components/admin/usage/UsageTable.vue
@@ -71,6 +71,7 @@
                  <svg class="h-3.5 w-3.5 text-amber-500" fill="none" stroke="currentColor" viewBox="0 0 24 24"><path stroke-linecap="round" stroke-linejoin="round" stroke-width="2" d="M11 5H6a2 2 0 00-2 2v11a2 2 0 002 2h11a2 2 0 002-2v-5m-1.414-9.414a2 2 0 112.828 2.828L11.828 15H9v-2.828l8.586-8.586z" /></svg>
                  <span class="font-medium text-amber-600 dark:text-amber-400">{{ formatCacheTokens(row.cache_creation_tokens) }}</span>
                  <span v-if="row.cache_creation_1h_tokens > 0" class="inline-flex items-center rounded px-1 py-px text-[10px] font-medium leading-tight bg-orange-100 text-orange-600 ring-1 ring-inset ring-orange-200 dark:bg-orange-500/20 dark:text-orange-400 dark:ring-orange-500/30">1h</span>
+                  <span v-if="row.cache_ttl_overridden" :title="t('usage.cacheTtlOverriddenHint')" class="inline-flex items-center rounded px-1 py-px text-[10px] font-medium leading-tight bg-rose-100 text-rose-600 ring-1 ring-inset ring-rose-200 dark:bg-rose-500/20 dark:text-rose-400 dark:ring-rose-500/30 cursor-help">R</span>
                </div>
              </div>
            </div>
@@ -182,6 +183,13 @@
                <span class="font-medium text-white">{{ tokenTooltipData.cache_creation_tokens.toLocaleString() }}</span>
              </div>
            </div>
+            <div v-if="tokenTooltipData && tokenTooltipData.cache_ttl_overridden" class="flex items-center justify-between gap-4">
+              <span class="text-gray-400 flex items-center gap-1.5">
+                {{ t('usage.cacheTtlOverriddenLabel') }}
+                <span class="inline-flex items-center rounded px-1 py-px text-[10px] font-medium leading-tight bg-rose-500/20 text-rose-400 ring-1 ring-inset ring-rose-500/30">R-{{ tokenTooltipData.cache_creation_1h_tokens > 0 ? '5m' : '1H' }}</span>
+              </span>
+              <span class="font-medium text-rose-400">{{ tokenTooltipData.cache_creation_1h_tokens > 0 ? t('usage.cacheTtlOverridden1h') : t('usage.cacheTtlOverridden5m') }}</span>
+            </div>
            <div v-if="tokenTooltipData && tokenTooltipData.cache_read_tokens > 0" class="flex items-center justify-between gap-4">
              <span class="text-gray-400">{{ t('admin.usage.cacheReadTokens') }}</span>
              <span class="font-medium text-white">{{ tokenTooltipData.cache_read_tokens.toLocaleString() }}</span>
--- a/frontend/src/i18n/locales/en.ts
+++ b/frontend/src/i18n/locales/en.ts
@@ -576,6 +576,10 @@ export default {
    description: 'View and analyze your API usage history',
    costDetails: 'Cost Breakdown',
    tokenDetails: 'Token Breakdown',
+    cacheTtlOverriddenHint: 'Cache TTL Override enabled',
+    cacheTtlOverriddenLabel: 'TTL Override',
+    cacheTtlOverridden5m: 'Billed as 5m',
+    cacheTtlOverridden1h: 'Billed as 1h',
    totalRequests: 'Total Requests',
    totalTokens: 'Total Tokens',
    totalCost: 'Total Cost',
@@ -1595,6 +1599,12 @@ export default {
        sessionIdMasking: {
          label: 'Session ID Masking',
          hint: 'When enabled, fixes the session ID in metadata.user_id for 15 minutes, making upstream think requests come from the same session'
+        },
+        cacheTTLOverride: {
+          label: 'Cache TTL Override',
+          hint: 'Force all cache creation tokens to be billed as the selected TTL tier (5m or 1h)',
+          target: 'Target TTL',
+          targetHint: 'Select the TTL tier for billing'
        }
      },
      expired: 'Expired',
--- a/frontend/src/i18n/locales/zh.ts
+++ b/frontend/src/i18n/locales/zh.ts
@@ -582,6 +582,10 @@ export default {
    description: '查看和分析您的 API 使用历史',
    costDetails: '成本明细',
    tokenDetails: 'Token 明细',
+    cacheTtlOverriddenHint: '缓存 TTL Override 已启用',
+    cacheTtlOverriddenLabel: 'TTL 替换',
+    cacheTtlOverridden5m: '按 5m 计费',
+    cacheTtlOverridden1h: '按 1h 计费',
    totalRequests: '总请求数',
    totalTokens: '总 Token',
    totalCost: '总消费',
@@ -1741,6 +1745,12 @@ export default {
        sessionIdMasking: {
          label: '会话 ID 伪装',
          hint: '启用后将在 15 分钟内固定 metadata.user_id 中的 session ID，使上游认为请求来自同一会话'
+        },
+        cacheTTLOverride: {
+          label: '缓存 TTL 强制替换',
+          hint: '将所有缓存创建 token 强制按指定的 TTL 类型（5分钟或1小时）计费',
+          target: '目标 TTL',
+          targetHint: '选择计费使用的 TTL 类型'
        }
      },
      expired: '已过期',
--- a/frontend/src/types/index.ts
+++ b/frontend/src/types/index.ts
@@ -614,6 +614,10 @@ export interface Account {
  // 启用后将在15分钟内固定 metadata.user_id 中的 session ID
  session_id_masking_enabled?: boolean | null

+  // 缓存 TTL 强制替换（仅 Anthropic OAuth/SetupToken 账号有效）
+  cache_ttl_override_enabled?: boolean | null
+  cache_ttl_override_target?: string | null
+
  // 运行时状态（仅当启用对应限制时返回）
  current_window_cost?: number | null // 当前窗口费用
  active_sessions?: number | null // 当前活跃会话数
@@ -827,6 +831,9 @@ export interface UsageLog {
  // User-Agent
  user_agent: string | null

+  // Cache TTL Override
+  cache_ttl_overridden: boolean
+
  created_at: string

  user?: User
--- a/frontend/src/views/user/UsageView.vue
+++ b/frontend/src/views/user/UsageView.vue
@@ -234,6 +234,7 @@
                      formatCacheTokens(row.cache_creation_tokens)
                    }}</span>
                    <span v-if="row.cache_creation_1h_tokens > 0" class="inline-flex items-center rounded px-1 py-px text-[10px] font-medium leading-tight bg-orange-100 text-orange-600 ring-1 ring-inset ring-orange-200 dark:bg-orange-500/20 dark:text-orange-400 dark:ring-orange-500/30">1h</span>
+                    <span v-if="row.cache_ttl_overridden" :title="t('usage.cacheTtlOverriddenHint')" class="inline-flex items-center rounded px-1 py-px text-[10px] font-medium leading-tight bg-rose-100 text-rose-600 ring-1 ring-inset ring-rose-200 dark:bg-rose-500/20 dark:text-rose-400 dark:ring-rose-500/30 cursor-help">R</span>
                  </div>
                </div>
              </div>
@@ -375,6 +376,13 @@
                <span class="font-medium text-white">{{ tokenTooltipData.cache_creation_tokens.toLocaleString() }}</span>
              </div>
            </div>
+            <div v-if="tokenTooltipData && tokenTooltipData.cache_ttl_overridden" class="flex items-center justify-between gap-4">
+              <span class="text-gray-400 flex items-center gap-1.5">
+                {{ t('usage.cacheTtlOverriddenLabel') }}
+                <span class="inline-flex items-center rounded px-1 py-px text-[10px] font-medium leading-tight bg-rose-500/20 text-rose-400 ring-1 ring-inset ring-rose-500/30">R-{{ tokenTooltipData.cache_creation_1h_tokens > 0 ? '5m' : '1H' }}</span>
+              </span>
+              <span class="font-medium text-rose-400">{{ tokenTooltipData.cache_creation_1h_tokens > 0 ? t('usage.cacheTtlOverridden1h') : t('usage.cacheTtlOverridden5m') }}</span>
+            </div>
            <div v-if="tokenTooltipData && tokenTooltipData.cache_read_tokens > 0" class="flex items-center justify-between gap-4">
              <span class="text-gray-400">{{ t('admin.usage.cacheReadTokens') }}</span>
              <span class="font-medium text-white">{{ tokenTooltipData.cache_read_tokens.toLocaleString() }}</span>