feat: optimize connection pooling and improve Kiro executor reliability

## 中文说明

### 连接池优化
- 为 AMP 代理、SOCKS5 代理和 HTTP 代理配置优化的连接池参数
- MaxIdleConnsPerHost 从默认的 2 增加到 20,支持更多并发用户
- MaxConnsPerHost 设为 0(无限制),避免连接瓶颈
- 添加 IdleConnTimeout (90s) 和其他超时配置

### Kiro 执行器增强
- 添加 Event Stream 消息解析的边界保护,防止越界访问
- 实现实时使用量估算(每 5000 字符或 15 秒发送 ping 事件)
- 正确从上游事件中提取并传递 stop_reason
- 改进输入 token 计算,优先使用 Claude 格式解析
- 添加 max_tokens 截断警告日志

### Token 计算改进
- 添加 tokenizer 缓存(sync.Map)避免重复创建
- 为 Claude/Kiro/AmazonQ 模型添加 1.1 调整因子
- 新增 countClaudeChatTokens 函数支持 Claude API 格式
- 支持图像 token 估算(基于尺寸计算)

### 认证刷新优化
- RefreshLead 从 30 分钟改为 5 分钟,与 Antigravity 保持一致
- 修复 NextRefreshAfter 设置,防止频繁刷新检查
- refreshFailureBackoff 从 5 分钟改为 1 分钟,加快失败恢复

---

## English Description

### Connection Pool Optimization
- Configure optimized connection pool parameters for AMP proxy, SOCKS5 proxy, and HTTP proxy
- Increase MaxIdleConnsPerHost from default 2 to 20 to support more concurrent users
- Set MaxConnsPerHost to 0 (unlimited) to avoid connection bottlenecks
- Add IdleConnTimeout (90s) and other timeout configurations

### Kiro Executor Enhancements
- Add boundary protection for Event Stream message parsing to prevent out-of-bounds access
- Implement real-time usage estimation (send ping events every 5000 chars or 15 seconds)
- Correctly extract and pass stop_reason from upstream events
- Improve input token calculation, prioritize Claude format parsing
- Add max_tokens truncation warning logs

### Token Calculation Improvements
- Add tokenizer cache (sync.Map) to avoid repeated creation
- Add 1.1 adjustment factor for Claude/Kiro/AmazonQ models
- Add countClaudeChatTokens function to support Claude API format
- Support image token estimation (calculated based on dimensions)

### Authentication Refresh Optimization
- Change RefreshLead from 30 minutes to 5 minutes, consistent with Antigravity
- Fix NextRefreshAfter setting to prevent frequent refresh checks
- Change refreshFailureBackoff from 5 minutes to 1 minute for faster failure recovery
This commit is contained in:
Ravens2121
2025-12-13 10:19:53 +08:00
parent db80b20bc2
commit 58866b21cb
7 changed files with 840 additions and 164 deletions
+45 -5
View File
@@ -7,11 +7,13 @@ import (
"errors"
"fmt"
"io"
"net"
"net/http"
"net/http/httputil"
"net/url"
"strconv"
"strings"
"time"
"github.com/gin-gonic/gin"
log "github.com/sirupsen/logrus"
@@ -36,6 +38,22 @@ func createReverseProxy(upstreamURL string, secretSource SecretSource) (*httputi
}
proxy := httputil.NewSingleHostReverseProxy(parsed)
// Configure custom Transport with optimized connection pooling for high concurrency
proxy.Transport = &http.Transport{
MaxIdleConns: 100,
MaxIdleConnsPerHost: 20, // Increased from default 2 to support more concurrent users
MaxConnsPerHost: 0, // No limit on max concurrent connections per host
IdleConnTimeout: 90 * time.Second,
DialContext: (&net.Dialer{
Timeout: 30 * time.Second,
KeepAlive: 30 * time.Second,
}).DialContext,
TLSHandshakeTimeout: 10 * time.Second,
ResponseHeaderTimeout: 60 * time.Second,
ExpectContinueTimeout: 1 * time.Second,
}
originalDirector := proxy.Director
// Modify outgoing requests to inject API key and fix routing
@@ -64,7 +82,15 @@ func createReverseProxy(upstreamURL string, secretSource SecretSource) (*httputi
// Modify incoming responses to handle gzip without Content-Encoding
// This addresses the same issue as inline handler gzip handling, but at the proxy level
proxy.ModifyResponse = func(resp *http.Response) error {
// Only process successful responses
// Log upstream error responses for diagnostics (502, 503, etc.)
// These are NOT proxy connection errors - the upstream responded with an error status
if resp.StatusCode >= 500 {
log.Errorf("amp upstream responded with error [%d] for %s %s", resp.StatusCode, resp.Request.Method, resp.Request.URL.Path)
} else if resp.StatusCode >= 400 {
log.Warnf("amp upstream responded with client error [%d] for %s %s", resp.StatusCode, resp.Request.Method, resp.Request.URL.Path)
}
// Only process successful responses for gzip decompression
if resp.StatusCode < 200 || resp.StatusCode >= 300 {
return nil
}
@@ -148,15 +174,29 @@ func createReverseProxy(upstreamURL string, secretSource SecretSource) (*httputi
return nil
}
// Error handler for proxy failures
// Error handler for proxy failures with detailed error classification for diagnostics
proxy.ErrorHandler = func(rw http.ResponseWriter, req *http.Request, err error) {
// Check if this is a client-side cancellation (normal behavior)
// Classify the error type for better diagnostics
var errType string
if errors.Is(err, context.DeadlineExceeded) {
errType = "timeout"
} else if errors.Is(err, context.Canceled) {
errType = "canceled"
} else if netErr, ok := err.(net.Error); ok && netErr.Timeout() {
errType = "dial_timeout"
} else if _, ok := err.(net.Error); ok {
errType = "network_error"
} else {
errType = "connection_error"
}
// Don't log as error for context canceled - it's usually client closing connection
if errors.Is(err, context.Canceled) {
log.Debugf("amp upstream proxy: client canceled request for %s %s", req.Method, req.URL.Path)
log.Debugf("amp upstream proxy [%s]: client canceled request for %s %s", errType, req.Method, req.URL.Path)
} else {
log.Errorf("amp upstream proxy error for %s %s: %v", req.Method, req.URL.Path, err)
log.Errorf("amp upstream proxy error [%s] for %s %s: %v", errType, req.Method, req.URL.Path, err)
}
rw.Header().Set("Content-Type", "application/json")
rw.WriteHeader(http.StatusBadGateway)
_, _ = rw.Write([]byte(`{"error":"amp_upstream_proxy_error","message":"Failed to reach Amp upstream"}`))