diff --git a/src/query.ts b/src/query.ts
index 1b1a6d574..280c63758 100644
--- a/src/query.ts
+++ b/src/query.ts
@@ -127,6 +127,12 @@ import {
   isLangfuseEnabled,
 } from './services/langfuse/index.js'
 import { getAPIProvider } from './utils/model/providers.js'
+import {
+  createCacheWarningMessage,
+  getCacheThreshold,
+  isCacheWarningEnabled,
+  shouldShowCacheWarning,
+} from './utils/cacheWarning.js'
 
 /* eslint-disable @typescript-eslint/no-require-imports */
 const snipModule = feature('HISTORY_SNIP')
@@ -1137,6 +1143,32 @@ async function* queryLoop(
       return { reason: 'model_error', error }
     }
 
+    // 检测缓存命中率并在需要时 yield 警告消息
+    // 必须在 executePostSamplingHooks 之前执行，确保警告消息在工具结果之前显示
+    if (
+      assistantMessages.length > 0 &&
+      !toolUseContext.options.isNonInteractiveSession
+    ) {
+      const lastAssistant = assistantMessages.at(-1)
+      const usage = lastAssistant?.message?.usage as
+        | {
+            input_tokens: number
+            cache_creation_input_tokens: number
+            cache_read_input_tokens: number
+          }
+        | undefined
+      if (usage && isCacheWarningEnabled()) {
+        const warningInfo = shouldShowCacheWarning(
+          usage,
+          querySource,
+          getCacheThreshold(),
+        )
+        if (warningInfo) {
+          yield createCacheWarningMessage(warningInfo)
+        }
+      }
+    }
+
     // Execute post-sampling hooks after model response is complete
     if (assistantMessages.length > 0) {
       void executePostSamplingHooks(
diff --git a/src/utils/cacheWarning.ts b/src/utils/cacheWarning.ts
index 294673f0c..04aab21c1 100644
--- a/src/utils/cacheWarning.ts
+++ b/src/utils/cacheWarning.ts
@@ -42,6 +42,14 @@ export function getCacheThreshold(): number {
     : DEFAULT_CACHE_THRESHOLD
 }
 
+/**
+ * 检查缓存警告是否启用。默认 true。
+ */
+export function isCacheWarningEnabled(): boolean {
+  const settings = getInitialSettings()
+  return settings.cacheWarningEnabled ?? true
+}
+
 /**
  * 计算缓存命中率
  * 返回值范围 0-100，null 表示无有效数据
diff --git a/src/utils/settings/types.ts b/src/utils/settings/types.ts
index 1c9dbf5e8..ba47bc142 100644
--- a/src/utils/settings/types.ts
+++ b/src/utils/settings/types.ts
@@ -1074,6 +1074,21 @@ export const SettingsSchema = lazySchema(() =>
             'Only applies to User, Project, and Local memory types (Managed/policy files cannot be excluded). ' +
             'Examples: "/home/user/monorepo/CLAUDE.md", "**/code/CLAUDE.md", "**/some-dir/.claude/rules/**"',
         ),
+      cacheThreshold: z
+        .number()
+        .int()
+        .min(0)
+        .max(100)
+        .optional()
+        .describe(
+          'Prompt cache hit rate threshold (0-100). Warnings shown when cache hit rate falls below this percentage. Default: 80.',
+        ),
+      cacheWarningEnabled: z
+        .boolean()
+        .optional()
+        .describe(
+          'Whether to show cache hit rate warnings in the message flow when the rate falls below cacheThreshold. Default: true.',
+        ),
       pluginTrustMessage: z
         .string()
         .optional()