feat(ops): 实现上游错误事件记录与查询功能

**新增功能**:
- 新建ops_upstream_error_events表存储上游服务错误详情
- 支持记录上游429/529/5xx错误的详细上下文信息
- 提供按时间范围查询上游错误事件的API

**后端改动**:
1. 模型层(ops_models.go, ops_port.go):
   - 新增UpstreamErrorEvent结构体
   - 扩展Repository接口支持上游错误事件CRUD

2. 仓储层(ops_repo.go):
   - 实现InsertUpstreamErrorEvent写入上游错误
   - 实现GetUpstreamErrorEvents按时间范围查询

3. 服务层(ops_service.go, ops_upstream_context.go):
   - ops_service: 新增GetUpstreamErrorEvents查询方法
   - ops_upstream_context: 封装上游错误上下文构建逻辑

4. Handler层(ops_error_logger.go):
   - 新增GetUpstreamErrorsHandler处理上游错误查询请求

5. Gateway层集成:
   - antigravity_gateway_service.go: 429/529错误时记录上游事件
   - gateway_service.go: OpenAI 429/5xx错误时记录
   - gemini_messages_compat_service.go: Gemini 429/5xx错误时记录
   - openai_gateway_service.go: OpenAI 429/5xx错误时记录
   - ratelimit_service.go: 429限流错误时记录

**数据记录字段**:
- request_id: 关联ops_logs主记录
- platform/model: 上游服务标识
- status_code/error_message: 错误详情
- request_headers/response_body: 调试信息(可选)
- created_at: 错误发生时间
This commit is contained in:
IanShaw027
2026-01-11 15:30:27 +08:00
parent c2962752eb
commit 7ebca553ef
11 changed files with 907 additions and 41 deletions

View File

@@ -511,7 +511,7 @@ func (s *OpenAIGatewayService) shouldFailoverUpstreamError(statusCode int) bool
}
func (s *OpenAIGatewayService) handleFailoverSideEffects(ctx context.Context, resp *http.Response, account *Account) {
body, _ := io.ReadAll(resp.Body)
body, _ := io.ReadAll(io.LimitReader(resp.Body, 2<<20))
s.rateLimitService.HandleUpstreamError(ctx, account, resp.StatusCode, resp.Header, body)
}
@@ -590,6 +590,13 @@ func (s *OpenAIGatewayService) Forward(ctx context.Context, c *gin.Context, acco
// Ensure the client receives an error response (handlers assume Forward writes on non-failover errors).
safeErr := sanitizeUpstreamErrorMessage(err.Error())
setOpsUpstreamError(c, 0, safeErr, "")
appendOpsUpstreamError(c, OpsUpstreamErrorEvent{
Platform: account.Platform,
AccountID: account.ID,
UpstreamStatusCode: 0,
Kind: "request_error",
Message: safeErr,
})
c.JSON(http.StatusBadGateway, gin.H{
"error": gin.H{
"type": "upstream_error",
@@ -603,6 +610,30 @@ func (s *OpenAIGatewayService) Forward(ctx context.Context, c *gin.Context, acco
// Handle error response
if resp.StatusCode >= 400 {
if s.shouldFailoverUpstreamError(resp.StatusCode) {
respBody, _ := io.ReadAll(io.LimitReader(resp.Body, 2<<20))
_ = resp.Body.Close()
resp.Body = io.NopCloser(bytes.NewReader(respBody))
upstreamMsg := strings.TrimSpace(extractUpstreamErrorMessage(respBody))
upstreamMsg = sanitizeUpstreamErrorMessage(upstreamMsg)
upstreamDetail := ""
if s.cfg != nil && s.cfg.Gateway.LogUpstreamErrorBody {
maxBytes := s.cfg.Gateway.LogUpstreamErrorBodyMaxBytes
if maxBytes <= 0 {
maxBytes = 2048
}
upstreamDetail = truncateString(string(respBody), maxBytes)
}
appendOpsUpstreamError(c, OpsUpstreamErrorEvent{
Platform: account.Platform,
AccountID: account.ID,
UpstreamStatusCode: resp.StatusCode,
UpstreamRequestID: resp.Header.Get("x-request-id"),
Kind: "failover",
Message: upstreamMsg,
Detail: upstreamDetail,
})
s.handleFailoverSideEffects(ctx, resp, account)
return nil, &UpstreamFailoverError{StatusCode: resp.StatusCode}
}
@@ -743,6 +774,15 @@ func (s *OpenAIGatewayService) handleErrorResponse(ctx context.Context, resp *ht
// Check custom error codes
if !account.ShouldHandleErrorCode(resp.StatusCode) {
appendOpsUpstreamError(c, OpsUpstreamErrorEvent{
Platform: account.Platform,
AccountID: account.ID,
UpstreamStatusCode: resp.StatusCode,
UpstreamRequestID: resp.Header.Get("x-request-id"),
Kind: "http_error",
Message: upstreamMsg,
Detail: upstreamDetail,
})
c.JSON(http.StatusInternalServerError, gin.H{
"error": gin.H{
"type": "upstream_error",
@@ -760,6 +800,19 @@ func (s *OpenAIGatewayService) handleErrorResponse(ctx context.Context, resp *ht
if s.rateLimitService != nil {
shouldDisable = s.rateLimitService.HandleUpstreamError(ctx, account, resp.StatusCode, resp.Header, body)
}
kind := "http_error"
if shouldDisable {
kind = "failover"
}
appendOpsUpstreamError(c, OpsUpstreamErrorEvent{
Platform: account.Platform,
AccountID: account.ID,
UpstreamStatusCode: resp.StatusCode,
UpstreamRequestID: resp.Header.Get("x-request-id"),
Kind: kind,
Message: upstreamMsg,
Detail: upstreamDetail,
})
if shouldDisable {
return nil, &UpstreamFailoverError{StatusCode: resp.StatusCode}
}