refactor(runtime): implement retry logic for Antigravity executor with improved error handling and capacity management

Add request_id to error logs and extract error messages

README.md

@@ -134,6 +134,10 @@ VSCode extension for quick switching between Claude Code models, featuring integ
 
 Windows desktop app built with Tauri + React for monitoring AI coding assistant quotas via CLIProxyAPI. Track usage across Gemini, Claude, OpenAI Codex, and Antigravity accounts with real-time dashboard, system tray integration, and one-click proxy control - no API keys needed.
 
+### [CPA-XXX Panel](https://github.com/ferretgeek/CPA-X)
+
+A lightweight web admin panel for CLIProxyAPI with health checks, resource monitoring, real-time logs, auto-update, request statistics and pricing display. Supports one-click installation and systemd service.
+
 > [!NOTE]  
 > If you developed a project based on CLIProxyAPI, please open a PR to add it to this list.
 

README_CN.md

@@ -133,6 +133,10 @@ CLI 封装器，用于通过 CLIProxyAPI OAuth 即时切换多个 Claude 账户
 
 Windows 桌面应用，基于 Tauri + React 构建，用于通过 CLIProxyAPI 监控 AI 编程助手配额。支持跨 Gemini、Claude、OpenAI Codex 和 Antigravity 账户的使用量追踪，提供实时仪表盘、系统托盘集成和一键代理控制，无需 API 密钥。
 
+### [CPA-XXX Panel](https://github.com/ferretgeek/CPA-X)
+
+面向 CLIProxyAPI 的 Web 管理面板，提供健康检查、资源监控、日志查看、自动更新、请求统计与定价展示，支持一键安装与 systemd 服务。
+
 > [!NOTE]  
 > 如果你开发了基于 CLIProxyAPI 的项目，请提交一个 PR（拉取请求）将其添加到此列表中。
 

internal/runtime/executor/antigravity_executor.go

@@ -148,87 +148,108 @@ func (e *AntigravityExecutor) Execute(ctx context.Context, auth *cliproxyauth.Au
 	baseURLs := antigravityBaseURLFallbackOrder(auth)
 	httpClient := newProxyAwareHTTPClient(ctx, e.cfg, auth, 0)
 
-	var lastStatus int
-	var lastBody []byte
-	var lastErr error
+	attempts := antigravityRetryAttempts(e.cfg)
 
-	for idx, baseURL := range baseURLs {
-		httpReq, errReq := e.buildRequest(ctx, auth, token, baseModel, translated, false, opts.Alt, baseURL)
-		if errReq != nil {
-			err = errReq
-			return resp, err
-		}
+attemptLoop:
+	for attempt := 0; attempt < attempts; attempt++ {
+		var lastStatus int
+		var lastBody []byte
+		var lastErr error
 
-		httpResp, errDo := httpClient.Do(httpReq)
-		if errDo != nil {
-			recordAPIResponseError(ctx, e.cfg, errDo)
-			if errors.Is(errDo, context.Canceled) || errors.Is(errDo, context.DeadlineExceeded) {
-				return resp, errDo
+		for idx, baseURL := range baseURLs {
+			httpReq, errReq := e.buildRequest(ctx, auth, token, baseModel, translated, false, opts.Alt, baseURL)
+			if errReq != nil {
+				err = errReq
+				return resp, err
 			}
-			lastStatus = 0
-			lastBody = nil
-			lastErr = errDo
-			if idx+1 < len(baseURLs) {
-				log.Debugf("antigravity executor: request error on base url %s, retrying with fallback base url: %s", baseURL, baseURLs[idx+1])
-				continue
+
+			httpResp, errDo := httpClient.Do(httpReq)
+			if errDo != nil {
+				recordAPIResponseError(ctx, e.cfg, errDo)
+				if errors.Is(errDo, context.Canceled) || errors.Is(errDo, context.DeadlineExceeded) {
+					return resp, errDo
+				}
+				lastStatus = 0
+				lastBody = nil
+				lastErr = errDo
+				if idx+1 < len(baseURLs) {
+					log.Debugf("antigravity executor: request error on base url %s, retrying with fallback base url: %s", baseURL, baseURLs[idx+1])
+					continue
+				}
+				err = errDo
+				return resp, err
 			}
-			err = errDo
-			return resp, err
+
+			recordAPIResponseMetadata(ctx, e.cfg, httpResp.StatusCode, httpResp.Header.Clone())
+			bodyBytes, errRead := io.ReadAll(httpResp.Body)
+			if errClose := httpResp.Body.Close(); errClose != nil {
+				log.Errorf("antigravity executor: close response body error: %v", errClose)
+			}
+			if errRead != nil {
+				recordAPIResponseError(ctx, e.cfg, errRead)
+				err = errRead
+				return resp, err
+			}
+			appendAPIResponseChunk(ctx, e.cfg, bodyBytes)
+
+			if httpResp.StatusCode < http.StatusOK || httpResp.StatusCode >= http.StatusMultipleChoices {
+				log.Debugf("antigravity executor: upstream error status: %d, body: %s", httpResp.StatusCode, summarizeErrorBody(httpResp.Header.Get("Content-Type"), bodyBytes))
+				lastStatus = httpResp.StatusCode
+				lastBody = append([]byte(nil), bodyBytes...)
+				lastErr = nil
+				if httpResp.StatusCode == http.StatusTooManyRequests && idx+1 < len(baseURLs) {
+					log.Debugf("antigravity executor: rate limited on base url %s, retrying with fallback base url: %s", baseURL, baseURLs[idx+1])
+					continue
+				}
+				if antigravityShouldRetryNoCapacity(httpResp.StatusCode, bodyBytes) {
+					if idx+1 < len(baseURLs) {
+						log.Debugf("antigravity executor: no capacity on base url %s, retrying with fallback base url: %s", baseURL, baseURLs[idx+1])
+						continue
+					}
+					if attempt+1 < attempts {
+						delay := antigravityNoCapacityRetryDelay(attempt)
+						log.Debugf("antigravity executor: no capacity for model %s, retrying in %s (attempt %d/%d)", baseModel, delay, attempt+1, attempts)
+						if errWait := antigravityWait(ctx, delay); errWait != nil {
+							return resp, errWait
+						}
+						continue attemptLoop
+					}
+				}
+				sErr := statusErr{code: httpResp.StatusCode, msg: string(bodyBytes)}
+				if httpResp.StatusCode == http.StatusTooManyRequests {
+					if retryAfter, parseErr := parseRetryDelay(bodyBytes); parseErr == nil && retryAfter != nil {
+						sErr.retryAfter = retryAfter
+					}
+				}
+				err = sErr
+				return resp, err
+			}
+
+			reporter.publish(ctx, parseAntigravityUsage(bodyBytes))
+			var param any
+			converted := sdktranslator.TranslateNonStream(ctx, to, from, req.Model, bytes.Clone(opts.OriginalRequest), translated, bodyBytes, &param)
+			resp = cliproxyexecutor.Response{Payload: []byte(converted)}
+			reporter.ensurePublished(ctx)
+			return resp, nil
 		}
 
-		recordAPIResponseMetadata(ctx, e.cfg, httpResp.StatusCode, httpResp.Header.Clone())
-		bodyBytes, errRead := io.ReadAll(httpResp.Body)
-		if errClose := httpResp.Body.Close(); errClose != nil {
-			log.Errorf("antigravity executor: close response body error: %v", errClose)
-		}
-		if errRead != nil {
-			recordAPIResponseError(ctx, e.cfg, errRead)
-			err = errRead
-			return resp, err
-		}
-		appendAPIResponseChunk(ctx, e.cfg, bodyBytes)
-
-		if httpResp.StatusCode < http.StatusOK || httpResp.StatusCode >= http.StatusMultipleChoices {
-			log.Debugf("antigravity executor: upstream error status: %d, body: %s", httpResp.StatusCode, summarizeErrorBody(httpResp.Header.Get("Content-Type"), bodyBytes))
-			lastStatus = httpResp.StatusCode
-			lastBody = append([]byte(nil), bodyBytes...)
-			lastErr = nil
-			if httpResp.StatusCode == http.StatusTooManyRequests && idx+1 < len(baseURLs) {
-				log.Debugf("antigravity executor: rate limited on base url %s, retrying with fallback base url: %s", baseURL, baseURLs[idx+1])
-				continue
-			}
-			sErr := statusErr{code: httpResp.StatusCode, msg: string(bodyBytes)}
-			if httpResp.StatusCode == http.StatusTooManyRequests {
-				if retryAfter, parseErr := parseRetryDelay(bodyBytes); parseErr == nil && retryAfter != nil {
+		switch {
+		case lastStatus != 0:
+			sErr := statusErr{code: lastStatus, msg: string(lastBody)}
+			if lastStatus == http.StatusTooManyRequests {
+				if retryAfter, parseErr := parseRetryDelay(lastBody); parseErr == nil && retryAfter != nil {
 					sErr.retryAfter = retryAfter
 				}
 			}
 			err = sErr
-			return resp, err
+		case lastErr != nil:
+			err = lastErr
+		default:
+			err = statusErr{code: http.StatusServiceUnavailable, msg: "antigravity executor: no base url available"}
 		}
-
-		reporter.publish(ctx, parseAntigravityUsage(bodyBytes))
-		var param any
-		converted := sdktranslator.TranslateNonStream(ctx, to, from, req.Model, bytes.Clone(opts.OriginalRequest), translated, bodyBytes, &param)
-		resp = cliproxyexecutor.Response{Payload: []byte(converted)}
-		reporter.ensurePublished(ctx)
-		return resp, nil
+		return resp, err
 	}
 
-	switch {
-	case lastStatus != 0:
-		sErr := statusErr{code: lastStatus, msg: string(lastBody)}
-		if lastStatus == http.StatusTooManyRequests {
-			if retryAfter, parseErr := parseRetryDelay(lastBody); parseErr == nil && retryAfter != nil {
-				sErr.retryAfter = retryAfter
-			}
-		}
-		err = sErr
-	case lastErr != nil:
-		err = lastErr
-	default:
-		err = statusErr{code: http.StatusServiceUnavailable, msg: "antigravity executor: no base url available"}
-	}
 	return resp, err
 }
 
@@ -268,150 +289,171 @@ func (e *AntigravityExecutor) executeClaudeNonStream(ctx context.Context, auth *
 	baseURLs := antigravityBaseURLFallbackOrder(auth)
 	httpClient := newProxyAwareHTTPClient(ctx, e.cfg, auth, 0)
 
-	var lastStatus int
-	var lastBody []byte
-	var lastErr error
+	attempts := antigravityRetryAttempts(e.cfg)
 
-	for idx, baseURL := range baseURLs {
-		httpReq, errReq := e.buildRequest(ctx, auth, token, baseModel, translated, true, opts.Alt, baseURL)
-		if errReq != nil {
-			err = errReq
-			return resp, err
-		}
+attemptLoop:
+	for attempt := 0; attempt < attempts; attempt++ {
+		var lastStatus int
+		var lastBody []byte
+		var lastErr error
 
-		httpResp, errDo := httpClient.Do(httpReq)
-		if errDo != nil {
-			recordAPIResponseError(ctx, e.cfg, errDo)
-			if errors.Is(errDo, context.Canceled) || errors.Is(errDo, context.DeadlineExceeded) {
-				return resp, errDo
+		for idx, baseURL := range baseURLs {
+			httpReq, errReq := e.buildRequest(ctx, auth, token, baseModel, translated, true, opts.Alt, baseURL)
+			if errReq != nil {
+				err = errReq
+				return resp, err
 			}
-			lastStatus = 0
-			lastBody = nil
-			lastErr = errDo
-			if idx+1 < len(baseURLs) {
-				log.Debugf("antigravity executor: request error on base url %s, retrying with fallback base url: %s", baseURL, baseURLs[idx+1])
-				continue
-			}
-			err = errDo
-			return resp, err
-		}
-		recordAPIResponseMetadata(ctx, e.cfg, httpResp.StatusCode, httpResp.Header.Clone())
-		if httpResp.StatusCode < http.StatusOK || httpResp.StatusCode >= http.StatusMultipleChoices {
-			bodyBytes, errRead := io.ReadAll(httpResp.Body)
-			if errClose := httpResp.Body.Close(); errClose != nil {
-				log.Errorf("antigravity executor: close response body error: %v", errClose)
-			}
-			if errRead != nil {
-				recordAPIResponseError(ctx, e.cfg, errRead)
-				if errors.Is(errRead, context.Canceled) || errors.Is(errRead, context.DeadlineExceeded) {
-					err = errRead
-					return resp, err
-				}
-				if errCtx := ctx.Err(); errCtx != nil {
-					err = errCtx
-					return resp, err
+
+			httpResp, errDo := httpClient.Do(httpReq)
+			if errDo != nil {
+				recordAPIResponseError(ctx, e.cfg, errDo)
+				if errors.Is(errDo, context.Canceled) || errors.Is(errDo, context.DeadlineExceeded) {
+					return resp, errDo
 				}
 				lastStatus = 0
 				lastBody = nil
-				lastErr = errRead
+				lastErr = errDo
 				if idx+1 < len(baseURLs) {
-					log.Debugf("antigravity executor: read error on base url %s, retrying with fallback base url: %s", baseURL, baseURLs[idx+1])
+					log.Debugf("antigravity executor: request error on base url %s, retrying with fallback base url: %s", baseURL, baseURLs[idx+1])
 					continue
 				}
-				err = errRead
+				err = errDo
 				return resp, err
 			}
-			appendAPIResponseChunk(ctx, e.cfg, bodyBytes)
-			lastStatus = httpResp.StatusCode
-			lastBody = append([]byte(nil), bodyBytes...)
-			lastErr = nil
-			if httpResp.StatusCode == http.StatusTooManyRequests && idx+1 < len(baseURLs) {
-				log.Debugf("antigravity executor: rate limited on base url %s, retrying with fallback base url: %s", baseURL, baseURLs[idx+1])
-				continue
+			recordAPIResponseMetadata(ctx, e.cfg, httpResp.StatusCode, httpResp.Header.Clone())
+			if httpResp.StatusCode < http.StatusOK || httpResp.StatusCode >= http.StatusMultipleChoices {
+				bodyBytes, errRead := io.ReadAll(httpResp.Body)
+				if errClose := httpResp.Body.Close(); errClose != nil {
+					log.Errorf("antigravity executor: close response body error: %v", errClose)
+				}
+				if errRead != nil {
+					recordAPIResponseError(ctx, e.cfg, errRead)
+					if errors.Is(errRead, context.Canceled) || errors.Is(errRead, context.DeadlineExceeded) {
+						err = errRead
+						return resp, err
+					}
+					if errCtx := ctx.Err(); errCtx != nil {
+						err = errCtx
+						return resp, err
+					}
+					lastStatus = 0
+					lastBody = nil
+					lastErr = errRead
+					if idx+1 < len(baseURLs) {
+						log.Debugf("antigravity executor: read error on base url %s, retrying with fallback base url: %s", baseURL, baseURLs[idx+1])
+						continue
+					}
+					err = errRead
+					return resp, err
+				}
+				appendAPIResponseChunk(ctx, e.cfg, bodyBytes)
+				lastStatus = httpResp.StatusCode
+				lastBody = append([]byte(nil), bodyBytes...)
+				lastErr = nil
+				if httpResp.StatusCode == http.StatusTooManyRequests && idx+1 < len(baseURLs) {
+					log.Debugf("antigravity executor: rate limited on base url %s, retrying with fallback base url: %s", baseURL, baseURLs[idx+1])
+					continue
+				}
+				if antigravityShouldRetryNoCapacity(httpResp.StatusCode, bodyBytes) {
+					if idx+1 < len(baseURLs) {
+						log.Debugf("antigravity executor: no capacity on base url %s, retrying with fallback base url: %s", baseURL, baseURLs[idx+1])
+						continue
+					}
+					if attempt+1 < attempts {
+						delay := antigravityNoCapacityRetryDelay(attempt)
+						log.Debugf("antigravity executor: no capacity for model %s, retrying in %s (attempt %d/%d)", baseModel, delay, attempt+1, attempts)
+						if errWait := antigravityWait(ctx, delay); errWait != nil {
+							return resp, errWait
+						}
+						continue attemptLoop
+					}
+				}
+				sErr := statusErr{code: httpResp.StatusCode, msg: string(bodyBytes)}
+				if httpResp.StatusCode == http.StatusTooManyRequests {
+					if retryAfter, parseErr := parseRetryDelay(bodyBytes); parseErr == nil && retryAfter != nil {
+						sErr.retryAfter = retryAfter
+					}
+				}
+				err = sErr
+				return resp, err
 			}
-			sErr := statusErr{code: httpResp.StatusCode, msg: string(bodyBytes)}
-			if httpResp.StatusCode == http.StatusTooManyRequests {
-				if retryAfter, parseErr := parseRetryDelay(bodyBytes); parseErr == nil && retryAfter != nil {
+
+			out := make(chan cliproxyexecutor.StreamChunk)
+			go func(resp *http.Response) {
+				defer close(out)
+				defer func() {
+					if errClose := resp.Body.Close(); errClose != nil {
+						log.Errorf("antigravity executor: close response body error: %v", errClose)
+					}
+				}()
+				scanner := bufio.NewScanner(resp.Body)
+				scanner.Buffer(nil, streamScannerBuffer)
+				for scanner.Scan() {
+					line := scanner.Bytes()
+					appendAPIResponseChunk(ctx, e.cfg, line)
+
+					// Filter usage metadata for all models
+					// Only retain usage statistics in the terminal chunk
+					line = FilterSSEUsageMetadata(line)
+
+					payload := jsonPayload(line)
+					if payload == nil {
+						continue
+					}
+
+					if detail, ok := parseAntigravityStreamUsage(payload); ok {
+						reporter.publish(ctx, detail)
+					}
+
+					out <- cliproxyexecutor.StreamChunk{Payload: payload}
+				}
+				if errScan := scanner.Err(); errScan != nil {
+					recordAPIResponseError(ctx, e.cfg, errScan)
+					reporter.publishFailure(ctx)
+					out <- cliproxyexecutor.StreamChunk{Err: errScan}
+				} else {
+					reporter.ensurePublished(ctx)
+				}
+			}(httpResp)
+
+			var buffer bytes.Buffer
+			for chunk := range out {
+				if chunk.Err != nil {
+					return resp, chunk.Err
+				}
+				if len(chunk.Payload) > 0 {
+					_, _ = buffer.Write(chunk.Payload)
+					_, _ = buffer.Write([]byte("\n"))
+				}
+			}
+			resp = cliproxyexecutor.Response{Payload: e.convertStreamToNonStream(buffer.Bytes())}
+
+			reporter.publish(ctx, parseAntigravityUsage(resp.Payload))
+			var param any
+			converted := sdktranslator.TranslateNonStream(ctx, to, from, req.Model, bytes.Clone(opts.OriginalRequest), translated, resp.Payload, &param)
+			resp = cliproxyexecutor.Response{Payload: []byte(converted)}
+			reporter.ensurePublished(ctx)
+
+			return resp, nil
+		}
+
+		switch {
+		case lastStatus != 0:
+			sErr := statusErr{code: lastStatus, msg: string(lastBody)}
+			if lastStatus == http.StatusTooManyRequests {
+				if retryAfter, parseErr := parseRetryDelay(lastBody); parseErr == nil && retryAfter != nil {
 					sErr.retryAfter = retryAfter
 				}
 			}
 			err = sErr
-			return resp, err
+		case lastErr != nil:
+			err = lastErr
+		default:
+			err = statusErr{code: http.StatusServiceUnavailable, msg: "antigravity executor: no base url available"}
 		}
-
-		out := make(chan cliproxyexecutor.StreamChunk)
-		go func(resp *http.Response) {
-			defer close(out)
-			defer func() {
-				if errClose := resp.Body.Close(); errClose != nil {
-					log.Errorf("antigravity executor: close response body error: %v", errClose)
-				}
-			}()
-			scanner := bufio.NewScanner(resp.Body)
-			scanner.Buffer(nil, streamScannerBuffer)
-			for scanner.Scan() {
-				line := scanner.Bytes()
-				appendAPIResponseChunk(ctx, e.cfg, line)
-
-				// Filter usage metadata for all models
-				// Only retain usage statistics in the terminal chunk
-				line = FilterSSEUsageMetadata(line)
-
-				payload := jsonPayload(line)
-				if payload == nil {
-					continue
-				}
-
-				if detail, ok := parseAntigravityStreamUsage(payload); ok {
-					reporter.publish(ctx, detail)
-				}
-
-				out <- cliproxyexecutor.StreamChunk{Payload: payload}
-			}
-			if errScan := scanner.Err(); errScan != nil {
-				recordAPIResponseError(ctx, e.cfg, errScan)
-				reporter.publishFailure(ctx)
-				out <- cliproxyexecutor.StreamChunk{Err: errScan}
-			} else {
-				reporter.ensurePublished(ctx)
-			}
-		}(httpResp)
-
-		var buffer bytes.Buffer
-		for chunk := range out {
-			if chunk.Err != nil {
-				return resp, chunk.Err
-			}
-			if len(chunk.Payload) > 0 {
-				_, _ = buffer.Write(chunk.Payload)
-				_, _ = buffer.Write([]byte("\n"))
-			}
-		}
-		resp = cliproxyexecutor.Response{Payload: e.convertStreamToNonStream(buffer.Bytes())}
-
-		reporter.publish(ctx, parseAntigravityUsage(resp.Payload))
-		var param any
-		converted := sdktranslator.TranslateNonStream(ctx, to, from, req.Model, bytes.Clone(opts.OriginalRequest), translated, resp.Payload, &param)
-		resp = cliproxyexecutor.Response{Payload: []byte(converted)}
-		reporter.ensurePublished(ctx)
-
-		return resp, nil
+		return resp, err
 	}
 
-	switch {
-	case lastStatus != 0:
-		sErr := statusErr{code: lastStatus, msg: string(lastBody)}
-		if lastStatus == http.StatusTooManyRequests {
-			if retryAfter, parseErr := parseRetryDelay(lastBody); parseErr == nil && retryAfter != nil {
-				sErr.retryAfter = retryAfter
-			}
-		}
-		err = sErr
-	case lastErr != nil:
-		err = lastErr
-	default:
-		err = statusErr{code: http.StatusServiceUnavailable, msg: "antigravity executor: no base url available"}
-	}
 	return resp, err
 }
 
@@ -635,139 +677,160 @@ func (e *AntigravityExecutor) ExecuteStream(ctx context.Context, auth *cliproxya
 	baseURLs := antigravityBaseURLFallbackOrder(auth)
 	httpClient := newProxyAwareHTTPClient(ctx, e.cfg, auth, 0)
 
-	var lastStatus int
-	var lastBody []byte
-	var lastErr error
+	attempts := antigravityRetryAttempts(e.cfg)
 
-	for idx, baseURL := range baseURLs {
-		httpReq, errReq := e.buildRequest(ctx, auth, token, baseModel, translated, true, opts.Alt, baseURL)
-		if errReq != nil {
-			err = errReq
-			return nil, err
-		}
-		httpResp, errDo := httpClient.Do(httpReq)
-		if errDo != nil {
-			recordAPIResponseError(ctx, e.cfg, errDo)
-			if errors.Is(errDo, context.Canceled) || errors.Is(errDo, context.DeadlineExceeded) {
-				return nil, errDo
+attemptLoop:
+	for attempt := 0; attempt < attempts; attempt++ {
+		var lastStatus int
+		var lastBody []byte
+		var lastErr error
+
+		for idx, baseURL := range baseURLs {
+			httpReq, errReq := e.buildRequest(ctx, auth, token, baseModel, translated, true, opts.Alt, baseURL)
+			if errReq != nil {
+				err = errReq
+				return nil, err
 			}
-			lastStatus = 0
-			lastBody = nil
-			lastErr = errDo
-			if idx+1 < len(baseURLs) {
-				log.Debugf("antigravity executor: request error on base url %s, retrying with fallback base url: %s", baseURL, baseURLs[idx+1])
-				continue
-			}
-			err = errDo
-			return nil, err
-		}
-		recordAPIResponseMetadata(ctx, e.cfg, httpResp.StatusCode, httpResp.Header.Clone())
-		if httpResp.StatusCode < http.StatusOK || httpResp.StatusCode >= http.StatusMultipleChoices {
-			bodyBytes, errRead := io.ReadAll(httpResp.Body)
-			if errClose := httpResp.Body.Close(); errClose != nil {
-				log.Errorf("antigravity executor: close response body error: %v", errClose)
-			}
-			if errRead != nil {
-				recordAPIResponseError(ctx, e.cfg, errRead)
-				if errors.Is(errRead, context.Canceled) || errors.Is(errRead, context.DeadlineExceeded) {
-					err = errRead
-					return nil, err
-				}
-				if errCtx := ctx.Err(); errCtx != nil {
-					err = errCtx
-					return nil, err
+			httpResp, errDo := httpClient.Do(httpReq)
+			if errDo != nil {
+				recordAPIResponseError(ctx, e.cfg, errDo)
+				if errors.Is(errDo, context.Canceled) || errors.Is(errDo, context.DeadlineExceeded) {
+					return nil, errDo
 				}
 				lastStatus = 0
 				lastBody = nil
-				lastErr = errRead
+				lastErr = errDo
 				if idx+1 < len(baseURLs) {
-					log.Debugf("antigravity executor: read error on base url %s, retrying with fallback base url: %s", baseURL, baseURLs[idx+1])
+					log.Debugf("antigravity executor: request error on base url %s, retrying with fallback base url: %s", baseURL, baseURLs[idx+1])
 					continue
 				}
-				err = errRead
+				err = errDo
 				return nil, err
 			}
-			appendAPIResponseChunk(ctx, e.cfg, bodyBytes)
-			lastStatus = httpResp.StatusCode
-			lastBody = append([]byte(nil), bodyBytes...)
-			lastErr = nil
-			if httpResp.StatusCode == http.StatusTooManyRequests && idx+1 < len(baseURLs) {
-				log.Debugf("antigravity executor: rate limited on base url %s, retrying with fallback base url: %s", baseURL, baseURLs[idx+1])
-				continue
+			recordAPIResponseMetadata(ctx, e.cfg, httpResp.StatusCode, httpResp.Header.Clone())
+			if httpResp.StatusCode < http.StatusOK || httpResp.StatusCode >= http.StatusMultipleChoices {
+				bodyBytes, errRead := io.ReadAll(httpResp.Body)
+				if errClose := httpResp.Body.Close(); errClose != nil {
+					log.Errorf("antigravity executor: close response body error: %v", errClose)
+				}
+				if errRead != nil {
+					recordAPIResponseError(ctx, e.cfg, errRead)
+					if errors.Is(errRead, context.Canceled) || errors.Is(errRead, context.DeadlineExceeded) {
+						err = errRead
+						return nil, err
+					}
+					if errCtx := ctx.Err(); errCtx != nil {
+						err = errCtx
+						return nil, err
+					}
+					lastStatus = 0
+					lastBody = nil
+					lastErr = errRead
+					if idx+1 < len(baseURLs) {
+						log.Debugf("antigravity executor: read error on base url %s, retrying with fallback base url: %s", baseURL, baseURLs[idx+1])
+						continue
+					}
+					err = errRead
+					return nil, err
+				}
+				appendAPIResponseChunk(ctx, e.cfg, bodyBytes)
+				lastStatus = httpResp.StatusCode
+				lastBody = append([]byte(nil), bodyBytes...)
+				lastErr = nil
+				if httpResp.StatusCode == http.StatusTooManyRequests && idx+1 < len(baseURLs) {
+					log.Debugf("antigravity executor: rate limited on base url %s, retrying with fallback base url: %s", baseURL, baseURLs[idx+1])
+					continue
+				}
+				if antigravityShouldRetryNoCapacity(httpResp.StatusCode, bodyBytes) {
+					if idx+1 < len(baseURLs) {
+						log.Debugf("antigravity executor: no capacity on base url %s, retrying with fallback base url: %s", baseURL, baseURLs[idx+1])
+						continue
+					}
+					if attempt+1 < attempts {
+						delay := antigravityNoCapacityRetryDelay(attempt)
+						log.Debugf("antigravity executor: no capacity for model %s, retrying in %s (attempt %d/%d)", baseModel, delay, attempt+1, attempts)
+						if errWait := antigravityWait(ctx, delay); errWait != nil {
+							return nil, errWait
+						}
+						continue attemptLoop
+					}
+				}
+				sErr := statusErr{code: httpResp.StatusCode, msg: string(bodyBytes)}
+				if httpResp.StatusCode == http.StatusTooManyRequests {
+					if retryAfter, parseErr := parseRetryDelay(bodyBytes); parseErr == nil && retryAfter != nil {
+						sErr.retryAfter = retryAfter
+					}
+				}
+				err = sErr
+				return nil, err
 			}
-			sErr := statusErr{code: httpResp.StatusCode, msg: string(bodyBytes)}
-			if httpResp.StatusCode == http.StatusTooManyRequests {
-				if retryAfter, parseErr := parseRetryDelay(bodyBytes); parseErr == nil && retryAfter != nil {
+
+			out := make(chan cliproxyexecutor.StreamChunk)
+			stream = out
+			go func(resp *http.Response) {
+				defer close(out)
+				defer func() {
+					if errClose := resp.Body.Close(); errClose != nil {
+						log.Errorf("antigravity executor: close response body error: %v", errClose)
+					}
+				}()
+				scanner := bufio.NewScanner(resp.Body)
+				scanner.Buffer(nil, streamScannerBuffer)
+				var param any
+				for scanner.Scan() {
+					line := scanner.Bytes()
+					appendAPIResponseChunk(ctx, e.cfg, line)
+
+					// Filter usage metadata for all models
+					// Only retain usage statistics in the terminal chunk
+					line = FilterSSEUsageMetadata(line)
+
+					payload := jsonPayload(line)
+					if payload == nil {
+						continue
+					}
+
+					if detail, ok := parseAntigravityStreamUsage(payload); ok {
+						reporter.publish(ctx, detail)
+					}
+
+					chunks := sdktranslator.TranslateStream(ctx, to, from, req.Model, bytes.Clone(opts.OriginalRequest), translated, bytes.Clone(payload), &param)
+					for i := range chunks {
+						out <- cliproxyexecutor.StreamChunk{Payload: []byte(chunks[i])}
+					}
+				}
+				tail := sdktranslator.TranslateStream(ctx, to, from, req.Model, bytes.Clone(opts.OriginalRequest), translated, []byte("[DONE]"), &param)
+				for i := range tail {
+					out <- cliproxyexecutor.StreamChunk{Payload: []byte(tail[i])}
+				}
+				if errScan := scanner.Err(); errScan != nil {
+					recordAPIResponseError(ctx, e.cfg, errScan)
+					reporter.publishFailure(ctx)
+					out <- cliproxyexecutor.StreamChunk{Err: errScan}
+				} else {
+					reporter.ensurePublished(ctx)
+				}
+			}(httpResp)
+			return stream, nil
+		}
+
+		switch {
+		case lastStatus != 0:
+			sErr := statusErr{code: lastStatus, msg: string(lastBody)}
+			if lastStatus == http.StatusTooManyRequests {
+				if retryAfter, parseErr := parseRetryDelay(lastBody); parseErr == nil && retryAfter != nil {
 					sErr.retryAfter = retryAfter
 				}
 			}
 			err = sErr
-			return nil, err
+		case lastErr != nil:
+			err = lastErr
+		default:
+			err = statusErr{code: http.StatusServiceUnavailable, msg: "antigravity executor: no base url available"}
 		}
-
-		out := make(chan cliproxyexecutor.StreamChunk)
-		stream = out
-		go func(resp *http.Response) {
-			defer close(out)
-			defer func() {
-				if errClose := resp.Body.Close(); errClose != nil {
-					log.Errorf("antigravity executor: close response body error: %v", errClose)
-				}
-			}()
-			scanner := bufio.NewScanner(resp.Body)
-			scanner.Buffer(nil, streamScannerBuffer)
-			var param any
-			for scanner.Scan() {
-				line := scanner.Bytes()
-				appendAPIResponseChunk(ctx, e.cfg, line)
-
-				// Filter usage metadata for all models
-				// Only retain usage statistics in the terminal chunk
-				line = FilterSSEUsageMetadata(line)
-
-				payload := jsonPayload(line)
-				if payload == nil {
-					continue
-				}
-
-				if detail, ok := parseAntigravityStreamUsage(payload); ok {
-					reporter.publish(ctx, detail)
-				}
-
-				chunks := sdktranslator.TranslateStream(ctx, to, from, req.Model, bytes.Clone(opts.OriginalRequest), translated, bytes.Clone(payload), &param)
-				for i := range chunks {
-					out <- cliproxyexecutor.StreamChunk{Payload: []byte(chunks[i])}
-				}
-			}
-			tail := sdktranslator.TranslateStream(ctx, to, from, req.Model, bytes.Clone(opts.OriginalRequest), translated, []byte("[DONE]"), &param)
-			for i := range tail {
-				out <- cliproxyexecutor.StreamChunk{Payload: []byte(tail[i])}
-			}
-			if errScan := scanner.Err(); errScan != nil {
-				recordAPIResponseError(ctx, e.cfg, errScan)
-				reporter.publishFailure(ctx)
-				out <- cliproxyexecutor.StreamChunk{Err: errScan}
-			} else {
-				reporter.ensurePublished(ctx)
-			}
-		}(httpResp)
-		return stream, nil
+		return nil, err
 	}
 
-	switch {
-	case lastStatus != 0:
-		sErr := statusErr{code: lastStatus, msg: string(lastBody)}
-		if lastStatus == http.StatusTooManyRequests {
-			if retryAfter, parseErr := parseRetryDelay(lastBody); parseErr == nil && retryAfter != nil {
-				sErr.retryAfter = retryAfter
-			}
-		}
-		err = sErr
-	case lastErr != nil:
-		err = lastErr
-	default:
-		err = statusErr{code: http.StatusServiceUnavailable, msg: "antigravity executor: no base url available"}
-	}
 	return nil, err
 }
 
@@ -1384,14 +1447,65 @@ func resolveUserAgent(auth *cliproxyauth.Auth) string {
 	return defaultAntigravityAgent
 }
 
+func antigravityRetryAttempts(cfg *config.Config) int {
+	if cfg == nil {
+		return 1
+	}
+	retry := cfg.RequestRetry
+	if retry < 0 {
+		retry = 0
+	}
+	attempts := retry + 1
+	if attempts < 1 {
+		return 1
+	}
+	return attempts
+}
+
+func antigravityShouldRetryNoCapacity(statusCode int, body []byte) bool {
+	if statusCode != http.StatusServiceUnavailable {
+		return false
+	}
+	if len(body) == 0 {
+		return false
+	}
+	msg := strings.ToLower(string(body))
+	return strings.Contains(msg, "no capacity available")
+}
+
+func antigravityNoCapacityRetryDelay(attempt int) time.Duration {
+	if attempt < 0 {
+		attempt = 0
+	}
+	delay := time.Duration(attempt+1) * 250 * time.Millisecond
+	if delay > 2*time.Second {
+		delay = 2 * time.Second
+	}
+	return delay
+}
+
+func antigravityWait(ctx context.Context, wait time.Duration) error {
+	if wait <= 0 {
+		return nil
+	}
+	timer := time.NewTimer(wait)
+	defer timer.Stop()
+	select {
+	case <-ctx.Done():
+		return ctx.Err()
+	case <-timer.C:
+		return nil
+	}
+}
+
 func antigravityBaseURLFallbackOrder(auth *cliproxyauth.Auth) []string {
 	if base := resolveCustomAntigravityBaseURL(auth); base != "" {
 		return []string{base}
 	}
 	return []string{
-		antigravitySandboxBaseURLDaily,
 		antigravityBaseURLDaily,
-		antigravityBaseURLProd,
+		antigravitySandboxBaseURLDaily,
+		// antigravityBaseURLProd,
 	}
 }
 

internal/runtime/executor/claude_executor.go

@@ -163,7 +163,7 @@ func (e *ClaudeExecutor) Execute(ctx context.Context, auth *cliproxyauth.Auth, r
 	if httpResp.StatusCode < 200 || httpResp.StatusCode >= 300 {
 		b, _ := io.ReadAll(httpResp.Body)
 		appendAPIResponseChunk(ctx, e.cfg, b)
-		log.Debugf("request error, error status: %d, error body: %s", httpResp.StatusCode, summarizeErrorBody(httpResp.Header.Get("Content-Type"), b))
+		logWithRequestID(ctx).Debugf("request error, error status: %d, error message: %s", httpResp.StatusCode, summarizeErrorBody(httpResp.Header.Get("Content-Type"), b))
 		err = statusErr{code: httpResp.StatusCode, msg: string(b)}
 		if errClose := httpResp.Body.Close(); errClose != nil {
 			log.Errorf("response body close error: %v", errClose)
@@ -295,7 +295,7 @@ func (e *ClaudeExecutor) ExecuteStream(ctx context.Context, auth *cliproxyauth.A
 	if httpResp.StatusCode < 200 || httpResp.StatusCode >= 300 {
 		b, _ := io.ReadAll(httpResp.Body)
 		appendAPIResponseChunk(ctx, e.cfg, b)
-		log.Debugf("request error, error status: %d, error body: %s", httpResp.StatusCode, summarizeErrorBody(httpResp.Header.Get("Content-Type"), b))
+		logWithRequestID(ctx).Debugf("request error, error status: %d, error message: %s", httpResp.StatusCode, summarizeErrorBody(httpResp.Header.Get("Content-Type"), b))
 		if errClose := httpResp.Body.Close(); errClose != nil {
 			log.Errorf("response body close error: %v", errClose)
 		}

internal/runtime/executor/codex_executor.go

@@ -150,7 +150,7 @@ func (e *CodexExecutor) Execute(ctx context.Context, auth *cliproxyauth.Auth, re
 	if httpResp.StatusCode < 200 || httpResp.StatusCode >= 300 {
 		b, _ := io.ReadAll(httpResp.Body)
 		appendAPIResponseChunk(ctx, e.cfg, b)
-		log.Debugf("request error, error status: %d, error body: %s", httpResp.StatusCode, summarizeErrorBody(httpResp.Header.Get("Content-Type"), b))
+		logWithRequestID(ctx).Debugf("request error, error status: %d, error message: %s", httpResp.StatusCode, summarizeErrorBody(httpResp.Header.Get("Content-Type"), b))
 		err = statusErr{code: httpResp.StatusCode, msg: string(b)}
 		return resp, err
 	}
@@ -265,7 +265,7 @@ func (e *CodexExecutor) ExecuteStream(ctx context.Context, auth *cliproxyauth.Au
 			return nil, readErr
 		}
 		appendAPIResponseChunk(ctx, e.cfg, data)
-		log.Debugf("request error, error status: %d, error body: %s", httpResp.StatusCode, summarizeErrorBody(httpResp.Header.Get("Content-Type"), data))
+		logWithRequestID(ctx).Debugf("request error, error status: %d, error message: %s", httpResp.StatusCode, summarizeErrorBody(httpResp.Header.Get("Content-Type"), data))
 		err = statusErr{code: httpResp.StatusCode, msg: string(data)}
 		return nil, err
 	}

internal/runtime/executor/gemini_cli_executor.go

@@ -227,7 +227,7 @@ func (e *GeminiCLIExecutor) Execute(ctx context.Context, auth *cliproxyauth.Auth
 
 		lastStatus = httpResp.StatusCode
 		lastBody = append([]byte(nil), data...)
-		log.Debugf("request error, error status: %d, error body: %s", httpResp.StatusCode, summarizeErrorBody(httpResp.Header.Get("Content-Type"), data))
+		logWithRequestID(ctx).Debugf("request error, error status: %d, error message: %s", httpResp.StatusCode, summarizeErrorBody(httpResp.Header.Get("Content-Type"), data))
 		if httpResp.StatusCode == 429 {
 			if idx+1 < len(models) {
 				log.Debugf("gemini cli executor: rate limited, retrying with next model: %s", models[idx+1])
@@ -360,7 +360,7 @@ func (e *GeminiCLIExecutor) ExecuteStream(ctx context.Context, auth *cliproxyaut
 			appendAPIResponseChunk(ctx, e.cfg, data)
 			lastStatus = httpResp.StatusCode
 			lastBody = append([]byte(nil), data...)
-			log.Debugf("request error, error status: %d, error body: %s", httpResp.StatusCode, summarizeErrorBody(httpResp.Header.Get("Content-Type"), data))
+			logWithRequestID(ctx).Debugf("request error, error status: %d, error message: %s", httpResp.StatusCode, summarizeErrorBody(httpResp.Header.Get("Content-Type"), data))
 			if httpResp.StatusCode == 429 {
 				if idx+1 < len(models) {
 					log.Debugf("gemini cli executor: rate limited, retrying with next model: %s", models[idx+1])

internal/runtime/executor/gemini_executor.go

@@ -188,7 +188,7 @@ func (e *GeminiExecutor) Execute(ctx context.Context, auth *cliproxyauth.Auth, r
 	if httpResp.StatusCode < 200 || httpResp.StatusCode >= 300 {
 		b, _ := io.ReadAll(httpResp.Body)
 		appendAPIResponseChunk(ctx, e.cfg, b)
-		log.Debugf("request error, error status: %d, error body: %s", httpResp.StatusCode, summarizeErrorBody(httpResp.Header.Get("Content-Type"), b))
+		logWithRequestID(ctx).Debugf("request error, error status: %d, error message: %s", httpResp.StatusCode, summarizeErrorBody(httpResp.Header.Get("Content-Type"), b))
 		err = statusErr{code: httpResp.StatusCode, msg: string(b)}
 		return resp, err
 	}
@@ -282,7 +282,7 @@ func (e *GeminiExecutor) ExecuteStream(ctx context.Context, auth *cliproxyauth.A
 	if httpResp.StatusCode < 200 || httpResp.StatusCode >= 300 {
 		b, _ := io.ReadAll(httpResp.Body)
 		appendAPIResponseChunk(ctx, e.cfg, b)
-		log.Debugf("request error, error status: %d, error body: %s", httpResp.StatusCode, summarizeErrorBody(httpResp.Header.Get("Content-Type"), b))
+		logWithRequestID(ctx).Debugf("request error, error status: %d, error message: %s", httpResp.StatusCode, summarizeErrorBody(httpResp.Header.Get("Content-Type"), b))
 		if errClose := httpResp.Body.Close(); errClose != nil {
 			log.Errorf("gemini executor: close response body error: %v", errClose)
 		}
@@ -402,7 +402,7 @@ func (e *GeminiExecutor) CountTokens(ctx context.Context, auth *cliproxyauth.Aut
 	}
 	appendAPIResponseChunk(ctx, e.cfg, data)
 	if resp.StatusCode < 200 || resp.StatusCode >= 300 {
-		log.Debugf("request error, error status: %d, error body: %s", resp.StatusCode, summarizeErrorBody(resp.Header.Get("Content-Type"), data))
+		logWithRequestID(ctx).Debugf("request error, error status: %d, error message: %s", resp.StatusCode, summarizeErrorBody(resp.Header.Get("Content-Type"), data))
 		return cliproxyexecutor.Response{}, statusErr{code: resp.StatusCode, msg: string(data)}
 	}
 

internal/runtime/executor/gemini_vertex_executor.go

@@ -389,7 +389,7 @@ func (e *GeminiVertexExecutor) executeWithServiceAccount(ctx context.Context, au
 	if httpResp.StatusCode < 200 || httpResp.StatusCode >= 300 {
 		b, _ := io.ReadAll(httpResp.Body)
 		appendAPIResponseChunk(ctx, e.cfg, b)
-		log.Debugf("request error, error status: %d, error body: %s", httpResp.StatusCode, summarizeErrorBody(httpResp.Header.Get("Content-Type"), b))
+		logWithRequestID(ctx).Debugf("request error, error status: %d, error message: %s", httpResp.StatusCode, summarizeErrorBody(httpResp.Header.Get("Content-Type"), b))
 		err = statusErr{code: httpResp.StatusCode, msg: string(b)}
 		return resp, err
 	}
@@ -503,7 +503,7 @@ func (e *GeminiVertexExecutor) executeWithAPIKey(ctx context.Context, auth *clip
 	if httpResp.StatusCode < 200 || httpResp.StatusCode >= 300 {
 		b, _ := io.ReadAll(httpResp.Body)
 		appendAPIResponseChunk(ctx, e.cfg, b)
-		log.Debugf("request error, error status: %d, error body: %s", httpResp.StatusCode, summarizeErrorBody(httpResp.Header.Get("Content-Type"), b))
+		logWithRequestID(ctx).Debugf("request error, error status: %d, error message: %s", httpResp.StatusCode, summarizeErrorBody(httpResp.Header.Get("Content-Type"), b))
 		err = statusErr{code: httpResp.StatusCode, msg: string(b)}
 		return resp, err
 	}
@@ -601,7 +601,7 @@ func (e *GeminiVertexExecutor) executeStreamWithServiceAccount(ctx context.Conte
 	if httpResp.StatusCode < 200 || httpResp.StatusCode >= 300 {
 		b, _ := io.ReadAll(httpResp.Body)
 		appendAPIResponseChunk(ctx, e.cfg, b)
-		log.Debugf("request error, error status: %d, error body: %s", httpResp.StatusCode, summarizeErrorBody(httpResp.Header.Get("Content-Type"), b))
+		logWithRequestID(ctx).Debugf("request error, error status: %d, error message: %s", httpResp.StatusCode, summarizeErrorBody(httpResp.Header.Get("Content-Type"), b))
 		if errClose := httpResp.Body.Close(); errClose != nil {
 			log.Errorf("vertex executor: close response body error: %v", errClose)
 		}
@@ -725,7 +725,7 @@ func (e *GeminiVertexExecutor) executeStreamWithAPIKey(ctx context.Context, auth
 	if httpResp.StatusCode < 200 || httpResp.StatusCode >= 300 {
 		b, _ := io.ReadAll(httpResp.Body)
 		appendAPIResponseChunk(ctx, e.cfg, b)
-		log.Debugf("request error, error status: %d, error body: %s", httpResp.StatusCode, summarizeErrorBody(httpResp.Header.Get("Content-Type"), b))
+		logWithRequestID(ctx).Debugf("request error, error status: %d, error message: %s", httpResp.StatusCode, summarizeErrorBody(httpResp.Header.Get("Content-Type"), b))
 		if errClose := httpResp.Body.Close(); errClose != nil {
 			log.Errorf("vertex executor: close response body error: %v", errClose)
 		}
@@ -838,7 +838,7 @@ func (e *GeminiVertexExecutor) countTokensWithServiceAccount(ctx context.Context
 	if httpResp.StatusCode < 200 || httpResp.StatusCode >= 300 {
 		b, _ := io.ReadAll(httpResp.Body)
 		appendAPIResponseChunk(ctx, e.cfg, b)
-		log.Debugf("request error, error status: %d, error body: %s", httpResp.StatusCode, summarizeErrorBody(httpResp.Header.Get("Content-Type"), b))
+		logWithRequestID(ctx).Debugf("request error, error status: %d, error message: %s", httpResp.StatusCode, summarizeErrorBody(httpResp.Header.Get("Content-Type"), b))
 		return cliproxyexecutor.Response{}, statusErr{code: httpResp.StatusCode, msg: string(b)}
 	}
 	data, errRead := io.ReadAll(httpResp.Body)
@@ -922,7 +922,7 @@ func (e *GeminiVertexExecutor) countTokensWithAPIKey(ctx context.Context, auth *
 	if httpResp.StatusCode < 200 || httpResp.StatusCode >= 300 {
 		b, _ := io.ReadAll(httpResp.Body)
 		appendAPIResponseChunk(ctx, e.cfg, b)
-		log.Debugf("request error, error status: %d, error body: %s", httpResp.StatusCode, summarizeErrorBody(httpResp.Header.Get("Content-Type"), b))
+		logWithRequestID(ctx).Debugf("request error, error status: %d, error message: %s", httpResp.StatusCode, summarizeErrorBody(httpResp.Header.Get("Content-Type"), b))
 		return cliproxyexecutor.Response{}, statusErr{code: httpResp.StatusCode, msg: string(b)}
 	}
 	data, errRead := io.ReadAll(httpResp.Body)

internal/runtime/executor/iflow_executor.go

@@ -142,7 +142,7 @@ func (e *IFlowExecutor) Execute(ctx context.Context, auth *cliproxyauth.Auth, re
 	if httpResp.StatusCode < 200 || httpResp.StatusCode >= 300 {
 		b, _ := io.ReadAll(httpResp.Body)
 		appendAPIResponseChunk(ctx, e.cfg, b)
-		log.Debugf("iflow request error: status %d body %s", httpResp.StatusCode, summarizeErrorBody(httpResp.Header.Get("Content-Type"), b))
+		logWithRequestID(ctx).Debugf("request error, error status: %d error message: %s", httpResp.StatusCode, summarizeErrorBody(httpResp.Header.Get("Content-Type"), b))
 		err = statusErr{code: httpResp.StatusCode, msg: string(b)}
 		return resp, err
 	}
@@ -244,7 +244,7 @@ func (e *IFlowExecutor) ExecuteStream(ctx context.Context, auth *cliproxyauth.Au
 			log.Errorf("iflow executor: close response body error: %v", errClose)
 		}
 		appendAPIResponseChunk(ctx, e.cfg, data)
-		log.Debugf("iflow streaming error: status %d body %s", httpResp.StatusCode, summarizeErrorBody(httpResp.Header.Get("Content-Type"), data))
+		logWithRequestID(ctx).Debugf("request error, error status: %d error message: %s", httpResp.StatusCode, summarizeErrorBody(httpResp.Header.Get("Content-Type"), data))
 		err = statusErr{code: httpResp.StatusCode, msg: string(data)}
 		return nil, err
 	}

internal/runtime/executor/logging_helpers.go

@@ -12,7 +12,10 @@ import (
 
 	"github.com/gin-gonic/gin"
 	"github.com/router-for-me/CLIProxyAPI/v6/internal/config"
+	"github.com/router-for-me/CLIProxyAPI/v6/internal/logging"
 	"github.com/router-for-me/CLIProxyAPI/v6/internal/util"
+	log "github.com/sirupsen/logrus"
+	"github.com/tidwall/gjson"
 )
 
 const (
@@ -332,6 +335,12 @@ func summarizeErrorBody(contentType string, body []byte) string {
 		}
 		return "[html body omitted]"
 	}
+
+	// Try to extract error message from JSON response
+	if message := extractJSONErrorMessage(body); message != "" {
+		return message
+	}
+
 	return string(body)
 }
 
@@ -358,3 +367,25 @@ func extractHTMLTitle(body []byte) string {
 	}
 	return strings.Join(strings.Fields(title), " ")
 }
+
+// extractJSONErrorMessage attempts to extract error.message from JSON error responses
+func extractJSONErrorMessage(body []byte) string {
+	result := gjson.GetBytes(body, "error.message")
+	if result.Exists() && result.String() != "" {
+		return result.String()
+	}
+	return ""
+}
+
+// logWithRequestID returns a logrus Entry with request_id field populated from context.
+// If no request ID is found in context, it returns the standard logger.
+func logWithRequestID(ctx context.Context) *log.Entry {
+	if ctx == nil {
+		return log.NewEntry(log.StandardLogger())
+	}
+	requestID := logging.GetRequestID(ctx)
+	if requestID == "" {
+		return log.NewEntry(log.StandardLogger())
+	}
+	return log.WithField("request_id", requestID)
+}

internal/runtime/executor/openai_compat_executor.go

@@ -146,7 +146,7 @@ func (e *OpenAICompatExecutor) Execute(ctx context.Context, auth *cliproxyauth.A
 	if httpResp.StatusCode < 200 || httpResp.StatusCode >= 300 {
 		b, _ := io.ReadAll(httpResp.Body)
 		appendAPIResponseChunk(ctx, e.cfg, b)
-		log.Debugf("request error, error status: %d, error body: %s", httpResp.StatusCode, summarizeErrorBody(httpResp.Header.Get("Content-Type"), b))
+		logWithRequestID(ctx).Debugf("request error, error status: %d, error message: %s", httpResp.StatusCode, summarizeErrorBody(httpResp.Header.Get("Content-Type"), b))
 		err = statusErr{code: httpResp.StatusCode, msg: string(b)}
 		return resp, err
 	}
@@ -239,7 +239,7 @@ func (e *OpenAICompatExecutor) ExecuteStream(ctx context.Context, auth *cliproxy
 	if httpResp.StatusCode < 200 || httpResp.StatusCode >= 300 {
 		b, _ := io.ReadAll(httpResp.Body)
 		appendAPIResponseChunk(ctx, e.cfg, b)
-		log.Debugf("request error, error status: %d, error body: %s", httpResp.StatusCode, summarizeErrorBody(httpResp.Header.Get("Content-Type"), b))
+		logWithRequestID(ctx).Debugf("request error, error status: %d, error message: %s", httpResp.StatusCode, summarizeErrorBody(httpResp.Header.Get("Content-Type"), b))
 		if errClose := httpResp.Body.Close(); errClose != nil {
 			log.Errorf("openai compat executor: close response body error: %v", errClose)
 		}

internal/runtime/executor/qwen_executor.go

@@ -133,7 +133,7 @@ func (e *QwenExecutor) Execute(ctx context.Context, auth *cliproxyauth.Auth, req
 	if httpResp.StatusCode < 200 || httpResp.StatusCode >= 300 {
 		b, _ := io.ReadAll(httpResp.Body)
 		appendAPIResponseChunk(ctx, e.cfg, b)
-		log.Debugf("request error, error status: %d, error body: %s", httpResp.StatusCode, summarizeErrorBody(httpResp.Header.Get("Content-Type"), b))
+		logWithRequestID(ctx).Debugf("request error, error status: %d, error message: %s", httpResp.StatusCode, summarizeErrorBody(httpResp.Header.Get("Content-Type"), b))
 		err = statusErr{code: httpResp.StatusCode, msg: string(b)}
 		return resp, err
 	}
@@ -222,7 +222,7 @@ func (e *QwenExecutor) ExecuteStream(ctx context.Context, auth *cliproxyauth.Aut
 	if httpResp.StatusCode < 200 || httpResp.StatusCode >= 300 {
 		b, _ := io.ReadAll(httpResp.Body)
 		appendAPIResponseChunk(ctx, e.cfg, b)
-		log.Debugf("request error, error status: %d, error body: %s", httpResp.StatusCode, summarizeErrorBody(httpResp.Header.Get("Content-Type"), b))
+		logWithRequestID(ctx).Debugf("request error, error status: %d, error message: %s", httpResp.StatusCode, summarizeErrorBody(httpResp.Header.Get("Content-Type"), b))
 		if errClose := httpResp.Body.Close(); errClose != nil {
 			log.Errorf("qwen executor: close response body error: %v", errClose)
 		}

internal/translator/openai/claude/openai_claude_request_test.go

@@ -181,11 +181,11 @@ func TestConvertClaudeRequestToOpenAI_ThinkingToReasoningContent(t *testing.T) {
 			result := ConvertClaudeRequestToOpenAI("test-model", []byte(tt.inputJSON), false)
 			resultJSON := gjson.ParseBytes(result)
 
-			// Find the relevant message (skip system message at index 0)
+			// Find the relevant message
 			messages := resultJSON.Get("messages").Array()
-			if len(messages) < 2 {
+			if len(messages) < 1 {
 				if tt.wantHasReasoningContent || tt.wantHasContent {
-					t.Fatalf("Expected at least 2 messages (system + user/assistant), got %d", len(messages))
+					t.Fatalf("Expected at least 1 message, got %d", len(messages))
 				}
 				return
 			}
@@ -272,15 +272,15 @@ func TestConvertClaudeRequestToOpenAI_ThinkingOnlyMessagePreserved(t *testing.T)
 
 	messages := resultJSON.Get("messages").Array()
 
-	// Should have: system (auto-added) + user + assistant (thinking-only) + user = 4 messages
-	if len(messages) != 4 {
-		t.Fatalf("Expected 4 messages, got %d. Messages: %v", len(messages), resultJSON.Get("messages").Raw)
+	// Should have: user + assistant (thinking-only) + user = 3 messages
+	if len(messages) != 3 {
+		t.Fatalf("Expected 3 messages, got %d. Messages: %v", len(messages), resultJSON.Get("messages").Raw)
 	}
 
-	// Check the assistant message (index 2) has reasoning_content
-	assistantMsg := messages[2]
+	// Check the assistant message (index 1) has reasoning_content
+	assistantMsg := messages[1]
 	if assistantMsg.Get("role").String() != "assistant" {
-		t.Errorf("Expected message[2] to be assistant, got %s", assistantMsg.Get("role").String())
+		t.Errorf("Expected message[1] to be assistant, got %s", assistantMsg.Get("role").String())
 	}
 
 	if !assistantMsg.Get("reasoning_content").Exists() {
@@ -292,6 +292,104 @@ func TestConvertClaudeRequestToOpenAI_ThinkingOnlyMessagePreserved(t *testing.T)
 	}
 }
 
+func TestConvertClaudeRequestToOpenAI_SystemMessageScenarios(t *testing.T) {
+	tests := []struct {
+		name        string
+		inputJSON   string
+		wantHasSys  bool
+		wantSysText string
+	}{
+		{
+			name: "No system field",
+			inputJSON: `{
+				"model": "claude-3-opus",
+				"messages": [{"role": "user", "content": "hello"}]
+			}`,
+			wantHasSys: false,
+		},
+		{
+			name: "Empty string system field",
+			inputJSON: `{
+				"model": "claude-3-opus",
+				"system": "",
+				"messages": [{"role": "user", "content": "hello"}]
+			}`,
+			wantHasSys: false,
+		},
+		{
+			name: "String system field",
+			inputJSON: `{
+				"model": "claude-3-opus",
+				"system": "Be helpful",
+				"messages": [{"role": "user", "content": "hello"}]
+			}`,
+			wantHasSys:  true,
+			wantSysText: "Be helpful",
+		},
+		{
+			name: "Array system field with text",
+			inputJSON: `{
+				"model": "claude-3-opus",
+				"system": [{"type": "text", "text": "Array system"}],
+				"messages": [{"role": "user", "content": "hello"}]
+			}`,
+			wantHasSys:  true,
+			wantSysText: "Array system",
+		},
+		{
+			name: "Array system field with multiple text blocks",
+			inputJSON: `{
+				"model": "claude-3-opus",
+				"system": [
+					{"type": "text", "text": "Block 1"},
+					{"type": "text", "text": "Block 2"}
+				],
+				"messages": [{"role": "user", "content": "hello"}]
+			}`,
+			wantHasSys:  true,
+			wantSysText: "Block 2", // We will update the test logic to check all blocks or specifically the second one
+		},
+	}
+
+	for _, tt := range tests {
+		t.Run(tt.name, func(t *testing.T) {
+			result := ConvertClaudeRequestToOpenAI("test-model", []byte(tt.inputJSON), false)
+			resultJSON := gjson.ParseBytes(result)
+			messages := resultJSON.Get("messages").Array()
+
+			hasSys := false
+			var sysMsg gjson.Result
+			if len(messages) > 0 && messages[0].Get("role").String() == "system" {
+				hasSys = true
+				sysMsg = messages[0]
+			}
+
+			if hasSys != tt.wantHasSys {
+				t.Errorf("got hasSystem = %v, want %v", hasSys, tt.wantHasSys)
+			}
+
+			if tt.wantHasSys {
+				// Check content - it could be string or array in OpenAI
+				content := sysMsg.Get("content")
+				var gotText string
+				if content.IsArray() {
+					arr := content.Array()
+					if len(arr) > 0 {
+						// Get the last element's text for validation
+						gotText = arr[len(arr)-1].Get("text").String()
+					}
+				} else {
+					gotText = content.String()
+				}
+
+				if tt.wantSysText != "" && gotText != tt.wantSysText {
+					t.Errorf("got system text = %q, want %q", gotText, tt.wantSysText)
+				}
+			}
+		})
+	}
+}
+
 func TestConvertClaudeRequestToOpenAI_ToolResultOrderAndContent(t *testing.T) {
 	inputJSON := `{
 		"model": "claude-3-opus",
@@ -318,39 +416,35 @@ func TestConvertClaudeRequestToOpenAI_ToolResultOrderAndContent(t *testing.T) {
 	messages := resultJSON.Get("messages").Array()
 
 	// OpenAI requires: tool messages MUST immediately follow assistant(tool_calls).
-	// Correct order: system + assistant(tool_calls) + tool(result) + user(before+after)
-	if len(messages) != 4 {
-		t.Fatalf("Expected 4 messages, got %d. Messages: %s", len(messages), resultJSON.Get("messages").Raw)
+	// Correct order: assistant(tool_calls) + tool(result) + user(before+after)
+	if len(messages) != 3 {
+		t.Fatalf("Expected 3 messages, got %d. Messages: %s", len(messages), resultJSON.Get("messages").Raw)
 	}
 
-	if messages[0].Get("role").String() != "system" {
-		t.Fatalf("Expected messages[0] to be system, got %s", messages[0].Get("role").String())
-	}
-
-	if messages[1].Get("role").String() != "assistant" || !messages[1].Get("tool_calls").Exists() {
-		t.Fatalf("Expected messages[1] to be assistant tool_calls, got %s: %s", messages[1].Get("role").String(), messages[1].Raw)
+	if messages[0].Get("role").String() != "assistant" || !messages[0].Get("tool_calls").Exists() {
+		t.Fatalf("Expected messages[0] to be assistant tool_calls, got %s: %s", messages[0].Get("role").String(), messages[0].Raw)
 	}
 
 	// tool message MUST immediately follow assistant(tool_calls) per OpenAI spec
-	if messages[2].Get("role").String() != "tool" {
-		t.Fatalf("Expected messages[2] to be tool (must follow tool_calls), got %s", messages[2].Get("role").String())
+	if messages[1].Get("role").String() != "tool" {
+		t.Fatalf("Expected messages[1] to be tool (must follow tool_calls), got %s", messages[1].Get("role").String())
 	}
-	if got := messages[2].Get("tool_call_id").String(); got != "call_1" {
+	if got := messages[1].Get("tool_call_id").String(); got != "call_1" {
 		t.Fatalf("Expected tool_call_id %q, got %q", "call_1", got)
 	}
-	if got := messages[2].Get("content").String(); got != "tool ok" {
+	if got := messages[1].Get("content").String(); got != "tool ok" {
 		t.Fatalf("Expected tool content %q, got %q", "tool ok", got)
 	}
 
 	// User message comes after tool message
-	if messages[3].Get("role").String() != "user" {
-		t.Fatalf("Expected messages[3] to be user, got %s", messages[3].Get("role").String())
+	if messages[2].Get("role").String() != "user" {
+		t.Fatalf("Expected messages[2] to be user, got %s", messages[2].Get("role").String())
 	}
 	// User message should contain both "before" and "after" text
-	if got := messages[3].Get("content.0.text").String(); got != "before" {
+	if got := messages[2].Get("content.0.text").String(); got != "before" {
 		t.Fatalf("Expected user text[0] %q, got %q", "before", got)
 	}
-	if got := messages[3].Get("content.1.text").String(); got != "after" {
+	if got := messages[2].Get("content.1.text").String(); got != "after" {
 		t.Fatalf("Expected user text[1] %q, got %q", "after", got)
 	}
 }
@@ -378,16 +472,16 @@ func TestConvertClaudeRequestToOpenAI_ToolResultObjectContent(t *testing.T) {
 	resultJSON := gjson.ParseBytes(result)
 	messages := resultJSON.Get("messages").Array()
 
-	// system + assistant(tool_calls) + tool(result)
-	if len(messages) != 3 {
-		t.Fatalf("Expected 3 messages, got %d. Messages: %s", len(messages), resultJSON.Get("messages").Raw)
+	// assistant(tool_calls) + tool(result)
+	if len(messages) != 2 {
+		t.Fatalf("Expected 2 messages, got %d. Messages: %s", len(messages), resultJSON.Get("messages").Raw)
 	}
 
-	if messages[2].Get("role").String() != "tool" {
-		t.Fatalf("Expected messages[2] to be tool, got %s", messages[2].Get("role").String())
+	if messages[1].Get("role").String() != "tool" {
+		t.Fatalf("Expected messages[1] to be tool, got %s", messages[1].Get("role").String())
 	}
 
-	toolContent := messages[2].Get("content").String()
+	toolContent := messages[1].Get("content").String()
 	parsed := gjson.Parse(toolContent)
 	if parsed.Get("foo").String() != "bar" {
 		t.Fatalf("Expected tool content JSON foo=bar, got %q", toolContent)
@@ -414,18 +508,14 @@ func TestConvertClaudeRequestToOpenAI_AssistantTextToolUseTextOrder(t *testing.T
 	messages := resultJSON.Get("messages").Array()
 
 	// New behavior: content + tool_calls unified in single assistant message
-	// Expect: system + assistant(content[pre,post] + tool_calls)
-	if len(messages) != 2 {
-		t.Fatalf("Expected 2 messages, got %d. Messages: %s", len(messages), resultJSON.Get("messages").Raw)
+	// Expect: assistant(content[pre,post] + tool_calls)
+	if len(messages) != 1 {
+		t.Fatalf("Expected 1 message, got %d. Messages: %s", len(messages), resultJSON.Get("messages").Raw)
 	}
 
-	if messages[0].Get("role").String() != "system" {
-		t.Fatalf("Expected messages[0] to be system, got %s", messages[0].Get("role").String())
-	}
-
-	assistantMsg := messages[1]
+	assistantMsg := messages[0]
 	if assistantMsg.Get("role").String() != "assistant" {
-		t.Fatalf("Expected messages[1] to be assistant, got %s", assistantMsg.Get("role").String())
+		t.Fatalf("Expected messages[0] to be assistant, got %s", assistantMsg.Get("role").String())
 	}
 
 	// Should have both content and tool_calls in same message
@@ -470,14 +560,14 @@ func TestConvertClaudeRequestToOpenAI_AssistantThinkingToolUseThinkingSplit(t *t
 	messages := resultJSON.Get("messages").Array()
 
 	// New behavior: all content, thinking, and tool_calls unified in single assistant message
-	// Expect: system + assistant(content[pre,post] + tool_calls + reasoning_content[t1+t2])
-	if len(messages) != 2 {
-		t.Fatalf("Expected 2 messages, got %d. Messages: %s", len(messages), resultJSON.Get("messages").Raw)
+	// Expect: assistant(content[pre,post] + tool_calls + reasoning_content[t1+t2])
+	if len(messages) != 1 {
+		t.Fatalf("Expected 1 message, got %d. Messages: %s", len(messages), resultJSON.Get("messages").Raw)
 	}
 
-	assistantMsg := messages[1]
+	assistantMsg := messages[0]
 	if assistantMsg.Get("role").String() != "assistant" {
-		t.Fatalf("Expected messages[1] to be assistant, got %s", assistantMsg.Get("role").String())
+		t.Fatalf("Expected messages[0] to be assistant, got %s", assistantMsg.Get("role").String())
 	}
 
 	// Should have content with both pre and post