perf(service): SSE Scanner buffer 改用 sync.Pool 复用，减少高并发 GC 压力

将流式响应中 bufio.Scanner 的 64KB buffer 从每次 make 分配改为
sync.Pool 复用，统一切片表达式为 [:0]、变量命名为 scanBuf，
并补充对应的单元测试。

Co-Authored-By: Claude Opus 4.6 <noreply@anthropic.com>

backend/internal/service/gateway_service_streaming_test.go

@@ -0,0 +1,52 @@
+package service
+
+import (
+	"context"
+	"io"
+	"net/http"
+	"net/http/httptest"
+	"testing"
+	"time"
+
+	"github.com/Wei-Shaw/sub2api/internal/config"
+	"github.com/gin-gonic/gin"
+	"github.com/stretchr/testify/require"
+)
+
+func TestGatewayService_StreamingReusesScannerBufferAndStillParsesUsage(t *testing.T) {
+	gin.SetMode(gin.TestMode)
+	cfg := &config.Config{
+		Gateway: config.GatewayConfig{
+			StreamDataIntervalTimeout: 0,
+			MaxLineSize:               defaultMaxLineSize,
+		},
+	}
+
+	svc := &GatewayService{
+		cfg:              cfg,
+		rateLimitService: &RateLimitService{},
+	}
+
+	rec := httptest.NewRecorder()
+	c, _ := gin.CreateTestContext(rec)
+	c.Request = httptest.NewRequest(http.MethodPost, "/v1/messages", nil)
+
+	pr, pw := io.Pipe()
+	resp := &http.Response{StatusCode: http.StatusOK, Header: http.Header{}, Body: pr}
+
+	go func() {
+		defer func() { _ = pw.Close() }()
+		// Minimal SSE event to trigger parseSSEUsage
+		_, _ = pw.Write([]byte("data: {\"type\":\"message_start\",\"message\":{\"usage\":{\"input_tokens\":3}}}\n\n"))
+		_, _ = pw.Write([]byte("data: {\"type\":\"message_delta\",\"usage\":{\"output_tokens\":7}}\n\n"))
+		_, _ = pw.Write([]byte("data: [DONE]\n\n"))
+	}()
+
+	result, err := svc.handleStreamingResponse(context.Background(), resp, c, &Account{ID: 1}, time.Now(), "model", "model", nil, false)
+	_ = pr.Close()
+	require.NoError(t, err)
+	require.NotNil(t, result)
+	require.NotNil(t, result.usage)
+	require.Equal(t, 3, result.usage.InputTokens)
+	require.Equal(t, 7, result.usage.OutputTokens)
+}