From b6aa585dc0db0d81b3815895ef195361ba2d57be Mon Sep 17 00:00:00 2001
From: afjcjsbx <afjcjsbx@gmail.com>
Date: Fri, 3 Apr 2026 17:22:40 +0200
Subject: [PATCH] fix(mcp): preserve raw MCP payload in text artifacts

---
 pkg/tools/mcp_tool.go      | 33 +++++++++++++++++++----------
 pkg/tools/mcp_tool_test.go | 43 ++++++++++++++++++++++++++++++++++++++
 2 files changed, 65 insertions(+), 11 deletions(-)

diff --git a/pkg/tools/mcp_tool.go b/pkg/tools/mcp_tool.go
index 5e1c48d25..fa153226c 100644
--- a/pkg/tools/mcp_tool.go
+++ b/pkg/tools/mcp_tool.go
@@ -272,14 +272,19 @@ func extractContentText(content []mcp.Content) string {
 
 func (t *MCPTool) normalizeResultContent(ctx context.Context, content []mcp.Content) *ToolResult {
 	llmParts := make([]string, 0, len(content))
+	rawTextParts := make([]string, 0, len(content))
 	mediaRefs := make([]string, 0, len(content))
 
 	for _, c := range content {
 		switch v := c.(type) {
 		case *mcp.TextContent:
-			text := strings.TrimSpace(sanitizeToolLLMContent(v.Text))
-			if text != "" {
-				llmParts = append(llmParts, text)
+			rawText := strings.TrimSpace(v.Text)
+			if rawText != "" {
+				rawTextParts = append(rawTextParts, rawText)
+			}
+			safeText := strings.TrimSpace(sanitizeToolLLMContent(v.Text))
+			if safeText != "" {
+				llmParts = append(llmParts, safeText)
 			}
 		case *mcp.ImageContent:
 			ref, note := t.storeBinaryContent(
@@ -312,10 +317,13 @@ func (t *MCPTool) normalizeResultContent(ctx context.Context, content []mcp.Cont
 		case *mcp.ResourceLink:
 			llmParts = append(llmParts, summarizeResourceLink(v))
 		case *mcp.EmbeddedResource:
-			ref, note := t.storeEmbeddedResource(ctx, v)
+			ref, note, rawText := t.storeEmbeddedResource(ctx, v)
 			if ref != "" {
 				mediaRefs = append(mediaRefs, ref)
 			}
+			if rawText != "" {
+				rawTextParts = append(rawTextParts, rawText)
+			}
 			if note != "" {
 				llmParts = append(llmParts, note)
 			}
@@ -325,7 +333,8 @@ func (t *MCPTool) normalizeResultContent(ctx context.Context, content []mcp.Cont
 	}
 
 	forLLM := strings.Join(compactStrings(llmParts), "\n")
-	if artifactResult := t.persistLargeTextArtifact(forLLM); artifactResult != nil {
+	rawText := strings.Join(compactStrings(rawTextParts), "\n")
+	if artifactResult := t.persistLargeTextArtifact(rawText); artifactResult != nil {
 		artifactResult.Media = mediaRefs
 		return artifactResult
 	}
@@ -381,27 +390,29 @@ func (t *MCPTool) persistLargeTextArtifact(text string) *ToolResult {
 	}
 }
 
-func (t *MCPTool) storeEmbeddedResource(ctx context.Context, content *mcp.EmbeddedResource) (string, string) {
+func (t *MCPTool) storeEmbeddedResource(ctx context.Context, content *mcp.EmbeddedResource) (string, string, string) {
 	if content == nil || content.Resource == nil {
-		return "", "[MCP returned an embedded resource without data.]"
+		return "", "[MCP returned an embedded resource without data.]", ""
 	}
 
 	resource := content.Resource
 	if len(resource.Blob) > 0 {
-		return t.storeBinaryContent(
+		ref, note := t.storeBinaryContent(
 			ctx,
 			"resource",
 			normalizedMIMEType(resource.MIMEType),
 			resource.Blob,
 			content.Annotations,
 		)
+		return ref, note, ""
 	}
 
-	if strings.TrimSpace(resource.Text) != "" {
-		return "", sanitizeToolLLMContent(resource.Text)
+	rawText := strings.TrimSpace(resource.Text)
+	if rawText != "" {
+		return "", sanitizeToolLLMContent(resource.Text), rawText
 	}
 
-	return "", summarizeEmbeddedResource(content)
+	return "", summarizeEmbeddedResource(content), ""
 }
 
 func (t *MCPTool) storeBinaryContent(
diff --git a/pkg/tools/mcp_tool_test.go b/pkg/tools/mcp_tool_test.go
index e972f5add..816ac712a 100644
--- a/pkg/tools/mcp_tool_test.go
+++ b/pkg/tools/mcp_tool_test.go
@@ -635,6 +635,49 @@ func TestMCPTool_Execute_LargeBase64TextIsOmittedFromContext(t *testing.T) {
 	}
 }
 
+func TestMCPTool_Execute_LargeBase64TextArtifactPreservesRawPayload(t *testing.T) {
+	workspace := t.TempDir()
+	largeBase64 := strings.Repeat("QUJD", 400)
+	manager := &MockMCPManager{
+		callToolFunc: func(ctx context.Context, serverName, toolName string, arguments map[string]any) (*mcp.CallToolResult, error) {
+			return &mcp.CallToolResult{
+				Content: []mcp.Content{
+					&mcp.TextContent{Text: largeBase64},
+				},
+			}, nil
+		},
+	}
+
+	mcpTool := NewMCPTool(manager, "test_server", &mcp.Tool{Name: "dump_payload"})
+	mcpTool.SetWorkspace(workspace)
+	mcpTool.SetMaxInlineTextRunes(32)
+
+	result := mcpTool.Execute(context.Background(), nil)
+
+	if !strings.Contains(result.ForLLM, "saved as a local artifact") {
+		t.Fatalf("expected artifact note, got %q", result.ForLLM)
+	}
+	if result.ForLLM == largeBase64OmittedMessage {
+		t.Fatalf("expected artifact note instead of sanitized base64 placeholder")
+	}
+	if len(result.ArtifactTags) != 1 {
+		t.Fatalf("expected 1 artifact tag, got %d", len(result.ArtifactTags))
+	}
+	tag := result.ArtifactTags[0]
+	const prefix = "[file:"
+	if !strings.HasPrefix(tag, prefix) || !strings.HasSuffix(tag, "]") {
+		t.Fatalf("expected file artifact tag, got %q", tag)
+	}
+	path := strings.TrimSuffix(strings.TrimPrefix(tag, prefix), "]")
+	data, err := os.ReadFile(path)
+	if err != nil {
+		t.Fatalf("expected artifact file to be readable: %v", err)
+	}
+	if string(data) != largeBase64 {
+		t.Fatalf("expected artifact file contents to preserve raw MCP payload")
+	}
+}
+
 func TestMCPTool_Execute_LargeTextStoredAsArtifact(t *testing.T) {
 	workspace := t.TempDir()
 	largeText := strings.Repeat("This is a large MCP text payload.\n", 800)