⚡ Bolt: Pool ResponseWriterWrapper buffers

.jules/bolt.md

@@ -219,3 +219,6 @@ go tool pprof mem.prof
 Remember: You're Bolt, making switchAILocal lightning fast. But speed without correctness is useless. Measure, optimize, verify.
 
 **If you can't find a clear performance win today, stop and do not create a PR.**
+## $(date +%Y-%m-%d) - Pooling Response Writer Buffers
+**Learning:** In the API gateway's hot path, `ResponseWriterWrapper` previously allocated a new `bytes.Buffer` for every HTTP response. This created unnecessary allocations and GC pressure, particularly for non-streaming requests. Using a `sync.Pool` to recycle these buffers provides measurable allocation savings.
+**Action:** Always consider `sync.Pool` for buffers created on a per-request basis in middleware, ensuring to cap the maximum buffer size returned to the pool to prevent memory bloat from occasional massive payloads.

internal/api/middleware/request_logging.go

@@ -51,6 +51,7 @@ func RequestLoggingMiddleware(logger logging.RequestLogger) gin.HandlerFunc {
 
 		// Create response writer wrapper
 		wrapper := NewResponseWriterWrapper(c.Writer, logger, requestInfo)
+		defer wrapper.Release()
 		if !logger.IsEnabled() {
 			wrapper.logOnErrorOnly = true
 		}

internal/api/middleware/response_writer.go

@@ -11,6 +11,7 @@ import (
 	"bytes"
 	"net/http"
 	"strings"
+	"sync"
 
 	"github.com/gin-gonic/gin"
 	"github.com/traylinx/switchAILocal/internal/interfaces"
@@ -28,6 +29,14 @@ type RequestInfo struct {
 
 // ResponseWriterWrapper wraps the standard gin.ResponseWriter to intercept and log response data.
 // It is designed to handle both standard and streaming responses, ensuring that logging operations do not block the client response.
+
+// bufferPool recycles bytes.Buffer to reduce allocations.
+var bufferPool = sync.Pool{
+	New: func() any {
+		return new(bytes.Buffer)
+	},
+}
+
 type ResponseWriterWrapper struct {
 	gin.ResponseWriter
 	body           *bytes.Buffer              // body is a buffer to store the response body for non-streaming responses.
@@ -55,7 +64,7 @@ type ResponseWriterWrapper struct {
 func NewResponseWriterWrapper(w gin.ResponseWriter, logger logging.RequestLogger, requestInfo *RequestInfo) *ResponseWriterWrapper {
 	return &ResponseWriterWrapper{
 		ResponseWriter: w,
-		body:           &bytes.Buffer{},
+		body:           bufferPool.Get().(*bytes.Buffer),
 		logger:         logger,
 		requestInfo:    requestInfo,
 		headers:        make(map[string][]string),
@@ -384,3 +393,14 @@ func (w *ResponseWriterWrapper) logRequest(statusCode int, headers map[string][]
 		w.requestInfo.RequestID,
 	)
 }
+
+// Release returns the internal buffer to the pool.
+func (w *ResponseWriterWrapper) Release() {
+	if w.body != nil {
+		if w.body.Cap() <= 128*1024 {
+			w.body.Reset()
+			bufferPool.Put(w.body)
+		}
+		w.body = nil
+	}
+}