Merge pull request #4625 from wucm667/fix/issue-4624-sticky-force-cache-billing

fix(handler): avoid cache billing on same-account retry

backend/internal/handler/failover_loop.go

@@ -83,8 +83,9 @@ func (s *FailoverState) HandleFailoverError(
 		return FailoverExhausted
 	}
 
-	// 缓存计费判断
-	if needForceCacheBilling(s.hasBoundSession, failoverErr) {
+	// 同账号重试不算切换账号，粘性会话仅在实际切换时强制缓存计费。
+	sameAccountRetry := failoverErr.RetryableOnSameAccount && s.SameAccountRetryCount[accountID] < retryLimit
+	if needForceCacheBilling(s.hasBoundSession, failoverErr, sameAccountRetry) {
 		s.ForceCacheBilling = true
 	}
 
@@ -174,9 +175,9 @@ func (s *FailoverState) HandleSelectionExhausted(ctx context.Context) FailoverAc
 }
 
 // needForceCacheBilling 判断 failover 时是否需要强制缓存计费。
-// 粘性会话切换账号、或上游明确标记时，将 input_tokens 转为 cache_read 计费。
-func needForceCacheBilling(hasBoundSession bool, failoverErr *service.UpstreamFailoverError) bool {
-	return hasBoundSession || (failoverErr != nil && failoverErr.ForceCacheBilling)
+// 粘性会话实际切换账号、或上游明确标记时，将 input_tokens 转为 cache_read 计费。
+func needForceCacheBilling(hasBoundSession bool, failoverErr *service.UpstreamFailoverError, sameAccountRetry bool) bool {
+	return (hasBoundSession && !sameAccountRetry) || (failoverErr != nil && failoverErr.ForceCacheBilling)
 }
 
 // failoverClientGone 判断下游客户端是否已断开（请求 context 已取消）。

backend/internal/handler/failover_loop_test.go

@@ -271,7 +271,7 @@ func TestHandleFailoverError_BasicSwitch(t *testing.T) {
 // ---------------------------------------------------------------------------
 
 func TestHandleFailoverError_CacheBilling(t *testing.T) {
-	t.Run("hasBoundSession为true时设置ForceCacheBilling", func(t *testing.T) {
+	t.Run("hasBoundSession为true且实际切换时设置ForceCacheBilling", func(t *testing.T) {
 		mock := &mockTempUnscheduler{}
 		fs := NewFailoverState(3, true) // hasBoundSession=true
 		err := newTestFailoverErr(500, false, false)
@@ -280,6 +280,32 @@ func TestHandleFailoverError_CacheBilling(t *testing.T) {
 		require.True(t, fs.ForceCacheBilling)
 	})
 
+	t.Run("同账号重试时仅凭hasBoundSession不设置ForceCacheBilling", func(t *testing.T) {
+		mock := &mockTempUnscheduler{}
+		fs := NewFailoverState(3, true)
+		err := newTestFailoverErr(400, true, false)
+
+		fs.HandleFailoverError(context.Background(), mock, 100, "openai", maxSameAccountRetries, err)
+
+		require.False(t, fs.ForceCacheBilling)
+		require.Zero(t, fs.SwitchCount)
+	})
+
+	t.Run("同账号重试耗尽并实际切换时设置ForceCacheBilling", func(t *testing.T) {
+		mock := &mockTempUnscheduler{}
+		fs := NewFailoverState(3, true)
+		err := newTestFailoverErr(400, true, false)
+
+		for i := 0; i < maxSameAccountRetries; i++ {
+			fs.HandleFailoverError(context.Background(), mock, 100, "openai", maxSameAccountRetries, err)
+			require.False(t, fs.ForceCacheBilling)
+		}
+		fs.HandleFailoverError(context.Background(), mock, 100, "openai", maxSameAccountRetries, err)
+
+		require.True(t, fs.ForceCacheBilling)
+		require.Equal(t, 1, fs.SwitchCount)
+	})
+
 	t.Run("failoverErr.ForceCacheBilling为true时设置", func(t *testing.T) {
 		mock := &mockTempUnscheduler{}
 		fs := NewFailoverState(3, false)
@@ -289,6 +315,17 @@ func TestHandleFailoverError_CacheBilling(t *testing.T) {
 		require.True(t, fs.ForceCacheBilling)
 	})
 
+	t.Run("同账号重试保留显式ForceCacheBilling", func(t *testing.T) {
+		mock := &mockTempUnscheduler{}
+		fs := NewFailoverState(3, true)
+		err := newTestFailoverErr(400, true, true)
+
+		fs.HandleFailoverError(context.Background(), mock, 100, "openai", maxSameAccountRetries, err)
+
+		require.True(t, fs.ForceCacheBilling)
+		require.Zero(t, fs.SwitchCount)
+	})
+
 	t.Run("两者均为false时不设置", func(t *testing.T) {
 		mock := &mockTempUnscheduler{}
 		fs := NewFailoverState(3, false)
@@ -633,13 +670,14 @@ func TestHandleFailoverError_IntegrationScenario(t *testing.T) {
 		for i := 0; i < maxSameAccountRetries; i++ {
 			action := fs.HandleFailoverError(context.Background(), mock, 100, "openai", maxSameAccountRetries, retryErr)
 			require.Equal(t, FailoverContinue, action)
+			require.False(t, fs.ForceCacheBilling, "同账号重试期间不应仅因绑定会话强制缓存计费")
 		}
-		require.True(t, fs.ForceCacheBilling, "hasBoundSession=true 应设置 ForceCacheBilling")
 
 		// 2. 账号 100 超过重试上限 → TempUnschedule + 切换
 		action := fs.HandleFailoverError(context.Background(), mock, 100, "openai", maxSameAccountRetries, retryErr)
 		require.Equal(t, FailoverContinue, action)
 		require.Equal(t, 1, fs.SwitchCount)
+		require.True(t, fs.ForceCacheBilling, "实际切换账号时应设置 ForceCacheBilling")
 		require.Len(t, mock.calls, 1)
 
 		// 3. 账号 200 遇到不可重试错误 → 直接切换