Merge branch 'feature/claude-max-simulation-review' into release/custom-0.1.86

# Conflicts:
#	backend/cmd/server/VERSION

frontend/src/i18n/locales/en.ts

@@ -1191,6 +1191,14 @@ export default {
         enabled: 'Enabled',
         disabled: 'Disabled'
       },
+      claudeMaxSimulation: {
+        title: 'Claude Max Usage Simulation',
+        tooltip:
+          'When enabled, for Claude models without upstream cache-write usage, the system deterministically maps tokens to a small input plus 1h cache creation while keeping total tokens unchanged.',
+        enabled: 'Enabled (simulate 1h cache)',
+        disabled: 'Disabled',
+        hint: 'Only token categories in usage billing logs are adjusted. No per-request mapping state is persisted.'
+      },
       supportedScopes: {
         title: 'Supported Model Families',
         tooltip: 'Select the model families this group supports. Unchecked families will not be routed to this group.',

frontend/src/i18n/locales/zh.ts

@@ -1280,6 +1280,14 @@ export default {
         enabled: '已启用',
         disabled: '已禁用'
       },
+      claudeMaxSimulation: {
+        title: 'Claude Max 用量模拟',
+        tooltip:
+          '启用后，针对 Claude 模型且上游未返回写缓存时，系统会按确定性算法把输入 token 映射为少量 input，并将其余归入 1h cache creation，保持总 token 不变。',
+        enabled: '已启用（模拟 1h 缓存）',
+        disabled: '已禁用',
+        hint: '仅影响 usage 计费记录中的 token 分类，不保存请求级映射状态。'
+      },
       supportedScopes: {
         title: '支持的模型系列',
         tooltip: '选择此分组支持的模型系列。未勾选的系列将不会被路由到此分组。',