Add files via upload

internal/multiagent/eino_single_runner.go

@@ -117,6 +117,7 @@ func RunEinoSingleChatModelAgent(
 		},
 	}
 	httpClient = openai.NewEinoHTTPClient(&appCfg.OpenAI, httpClient)
+	openai.AttachSummarizationDiagTransport(httpClient, logger)
 
 	baseModelCfg := &einoopenai.ChatModelConfig{
 		APIKey:     appCfg.OpenAI.APIKey,

internal/multiagent/eino_summarize.go

@@ -9,15 +9,19 @@ import (
 
 	"cyberstrike-ai/internal/agent"
 	"cyberstrike-ai/internal/config"
+	copenai "cyberstrike-ai/internal/openai"
 
 	"github.com/bytedance/sonic"
 	"github.com/cloudwego/eino/adk"
 	"github.com/cloudwego/eino/adk/middlewares/summarization"
 	"github.com/cloudwego/eino/components/model"
 	"github.com/cloudwego/eino/schema"
+	einoopenai "github.com/cloudwego/eino-ext/components/model/openai"
 	"go.uber.org/zap"
 )
 
+const defaultSummarizationRetryMax = 3
+
 // einoSummarizeUserInstruction：压缩历史时保留渗透测试关键信息。
 const einoSummarizeUserInstruction = `在保持所有关键安全测试信息完整的前提下压缩对话历史。
 
@@ -89,8 +93,32 @@ func newEinoSummarizationMiddleware(
 		}
 	}
 
+	retryMax := defaultSummarizationRetryMax
+	if mwCfg != nil && mwCfg.SummarizationRetryMaxAttempts > 0 {
+		retryMax = mwCfg.SummarizationRetryMaxAttempts
+	}
+
+	// ModelOptions apply only to summarization Generate (same ChatModel instance as the agent).
+	// Strip thinking/reasoning on this call path; mark requests for empty-choices diagnostics.
+	summaryModelOpts := []model.Option{
+		einoopenai.WithExtraHeader(map[string]string{
+			copenai.SummarizationRequestHeader: "1",
+		}),
+		einoopenai.WithRequestPayloadModifier(func(_ context.Context, in []*schema.Message, rawBody []byte) ([]byte, error) {
+			if logger != nil {
+				logger.Info("eino summarization generate request",
+					zap.Int("input_messages", len(in)),
+					zap.Int("payload_bytes", len(rawBody)),
+					zap.String("model", modelName),
+				)
+			}
+			return stripReasoningFromSummarizationPayload(rawBody)
+		}),
+	}
+
 	mw, err := summarization.New(ctx, &summarization.Config{
-		Model: summaryModel,
+		Model:        summaryModel,
+		ModelOptions: summaryModelOpts,
 		Trigger: &summarization.TriggerCondition{
 			ContextTokens: trigger,
 		},
@@ -102,6 +130,18 @@ func newEinoSummarizationMiddleware(
 			Enabled:   true,
 			MaxTokens: preserveMax,
 		},
+		Retry: &summarization.RetryConfig{
+			MaxRetries: &retryMax,
+			ShouldRetry: func(_ context.Context, _ adk.Message, err error) bool {
+				if err != nil && logger != nil {
+					logger.Warn("eino summarization generate attempt failed, will retry if attempts remain",
+						zap.Error(err),
+						zap.Int("max_retries", retryMax),
+					)
+				}
+				return err != nil
+			},
+		},
 		Finalize: func(ctx context.Context, originalMessages []adk.Message, summary adk.Message) ([]adk.Message, error) {
 			return summarizeFinalizeWithRecentAssistantToolTrail(ctx, originalMessages, summary, tokenCounter, recentTrailMax)
 		},

internal/multiagent/eino_summarize_payload.go

@@ -0,0 +1,35 @@
+package multiagent
+
+import (
+	"github.com/bytedance/sonic"
+)
+
+// stripReasoningFromSummarizationPayload removes thinking / reasoning fields from a
+// chat-completions JSON body. Applied only to summarization Generate calls via
+// model.ModelOptions on the shared ChatModel — main-agent requests are unchanged.
+func stripReasoningFromSummarizationPayload(rawBody []byte) ([]byte, error) {
+	var payload map[string]any
+	if err := sonic.Unmarshal(rawBody, &payload); err != nil {
+		return rawBody, nil
+	}
+	changed := false
+	for _, key := range []string{
+		"thinking",
+		"reasoning_effort",
+		"output_config",
+		"reasoning",
+	} {
+		if _, ok := payload[key]; ok {
+			delete(payload, key)
+			changed = true
+		}
+	}
+	if !changed {
+		return rawBody, nil
+	}
+	out, err := sonic.Marshal(payload)
+	if err != nil {
+		return rawBody, err
+	}
+	return out, nil
+}

internal/multiagent/eino_summarize_payload_test.go

@@ -0,0 +1,30 @@
+package multiagent
+
+import (
+	"strings"
+	"testing"
+)
+
+func TestStripReasoningFromSummarizationPayload(t *testing.T) {
+	in := []byte(`{"model":"deepseek-chat","messages":[],"thinking":{"type":"enabled"},"reasoning_effort":"high"}`)
+	out, err := stripReasoningFromSummarizationPayload(in)
+	if err != nil {
+		t.Fatal(err)
+	}
+	s := string(out)
+	if strings.Contains(s, "thinking") || strings.Contains(s, "reasoning_effort") {
+		t.Fatalf("expected reasoning fields stripped, got %s", s)
+	}
+	if !strings.Contains(s, `"model":"deepseek-chat"`) {
+		t.Fatalf("expected model preserved, got %s", s)
+	}
+
+	plain := []byte(`{"model":"gpt-4o","messages":[]}`)
+	out2, err := stripReasoningFromSummarizationPayload(plain)
+	if err != nil {
+		t.Fatal(err)
+	}
+	if string(out2) != string(plain) {
+		t.Fatalf("expected unchanged payload, got %s", out2)
+	}
+}

internal/multiagent/runner.go

@@ -161,6 +161,7 @@ func RunDeepAgent(
 
 	// 若配置为 Claude provider，注入自动桥接 transport，对 Eino 透明走 Anthropic Messages API
 	httpClient = openai.NewEinoHTTPClient(&appCfg.OpenAI, httpClient)
+	openai.AttachSummarizationDiagTransport(httpClient, logger)
 
 	baseModelCfg := &einoopenai.ChatModelConfig{
 		APIKey:     appCfg.OpenAI.APIKey,