Skip to content

Fix Anthropic image content normalization #8

New issue

Have a question about this project? Sign up for a free GitHub account to open an issue and contact its maintainers and the community.

Sign up for GitHub

By clicking “Sign up for GitHub”, you agree to our terms of service and privacy statement. We’ll occasionally send you account related emails.

Already on GitHub? Sign in to your account

Merged
Futureppo merged 1 commit into from
Jul 13, 2026
Merged

Fix Anthropic image content normalization #8

Show file tree
Hide file tree
Changes from all commits
Commits
Show all changes
1 commit
Select commit
File filter

Filter by extension

Filter by extension
Conversations
Failed to load comments.
Loading
Jump to
Jump to file
Failed to load files.
Loading
Diff view
Diff view
38 changes: 38 additions & 0 deletions internal/openai/chat_prepare.go
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -467,13 +467,51 @@ func (p *chatPreparer) prepareMessageContent(raw any, path string, allowImages b
}
out = append(out, map[string]any{"type": "image_url", "image_url": image})
p.recordUnknownObjectFields(part, map[string]bool{"type": true, "image_url": true}, partPath)
case "image":
if !allowImages {
return nil, fmt.Errorf("%s.type image is only valid for user messages", partPath)
}
image, err := p.prepareAnthropicImage(part, partPath)
if err != nil {
return nil, err
}
out = append(out, map[string]any{"type": "image_url", "image_url": image})
p.recordUnknownObjectFields(part, map[string]bool{"type": true, "source": true}, partPath)
default:
return nil, fmt.Errorf("%s.type %q is not supported", partPath, kind)
}
}
return out, nil
}

func (p *chatPreparer) prepareAnthropicImage(block map[string]any, path string) (map[string]any, error) {
source, ok := block["source"].(map[string]any)
if !ok {
return nil, fmt.Errorf("%s.source must be an object", path)
}
var url string
switch sourceType, _ := source["type"].(string); sourceType {
case "url":
value, ok := source["url"].(string)
if !ok || strings.TrimSpace(value) == "" {
return nil, fmt.Errorf("%s.source.url must be a non-empty string", path)
}
url = value
case "base64":
mediaType, _ := source["media_type"].(string)
data, _ := source["data"].(string)
if strings.TrimSpace(mediaType) == "" || strings.TrimSpace(data) == "" {
return nil, fmt.Errorf("%s.source media_type and data are required for base64 images", path)
}
url = "data:" + mediaType + ";base64," + data
Comment on lines +501 to +506

@gemini-code-assist gemini-code-assist Bot Jul 13, 2026

Copy link
Copy Markdown

Choose a reason for hiding this comment

The reason will be displayed to describe this comment to others. Learn more.

medium

When constructing a data URL for base64-encoded images, any leading or trailing whitespace (such as newlines, which are very common in base64 payloads) in media_type or data can result in an invalid data URL. Trimming these values before validation and URL construction ensures robustness and compatibility with various client inputs.

Suggested change
mediaType, _ := source["media_type"].(string)
data, _ := source["data"].(string)
if strings.TrimSpace(mediaType) == "" || strings.TrimSpace(data) == "" {
return nil, fmt.Errorf("%s.source media_type and data are required for base64 images", path)
}
url = "data:" + mediaType + ";base64," + data
mediaType, _ := source["media_type"].(string)
data, _ := source["data"].(string)
mediaType = strings.TrimSpace(mediaType)
data = strings.TrimSpace(data)
if mediaType == "" || data == "" {
return nil, fmt.Errorf("%s.source media_type and data are required for base64 images", path)
}
url = "data:" + mediaType + ";base64," + data

default:
return nil, fmt.Errorf("%s.source.type %q is not supported", path, sourceType)
}
p.recordUnknownObjectFields(source, map[string]bool{"type": true, "url": true, "media_type": true, "data": true}, path+".source")
p.change(path, "rewritten", "Anthropic image block is normalized to OpenAI image_url content")
return map[string]any{"url": url}, nil
}

func (p *chatPreparer) prepareImageURL(raw any, path string) (map[string]any, error) {
if value, ok := raw.(string); ok && strings.TrimSpace(value) != "" {
p.change(path, "rewritten", "string image URL is normalized to an object")
Expand Down
7 changes: 6 additions & 1 deletion internal/openai/chat_prepare_test.go
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -66,6 +66,7 @@ func TestPrepareChatNormalizesMessagesAndToolHistory(t *testing.T) {
map[string]any{"role": "user", "content": []any{
map[string]any{"type": "text", "text": "inspect", "cache_control": true},
map[string]any{"type": "image_url", "image_url": map[string]any{"url": "data:image/png;base64,AA", "detail": "low", "vendor": true}},
map[string]any{"type": "image", "source": map[string]any{"type": "base64", "media_type": "image/png", "data": "BB", "vendor": true}, "cache_control": true},
}},
map[string]any{"role": "assistant", "content": nil, "reasoning_content": "need tool", "tool_calls": []any{
map[string]any{"id": "call-1", "type": "function", "function": map[string]any{"name": "lookup", "arguments": `{"id":1}`, "extra": true}},
Expand All @@ -82,11 +83,15 @@ func TestPrepareChatNormalizesMessagesAndToolHistory(t *testing.T) {
if parts[0].(map[string]any)["cache_control"] != nil || parts[1].(map[string]any)["image_url"].(map[string]any)["vendor"] != nil {
t.Fatalf("content metadata leaked: %#v", parts)
}
convertedImage := parts[2].(map[string]any)
if convertedImage["type"] != "image_url" || convertedImage["image_url"].(map[string]any)["url"] != "data:image/png;base64,BB" {
t.Fatalf("Anthropic image block was not normalized: %#v", convertedImage)
}
call := messages[2].(map[string]any)["tool_calls"].([]any)[0].(map[string]any)
if call["function"].(map[string]any)["extra"] != nil {
t.Fatalf("tool call metadata leaked: %#v", call)
}
for _, path := range []string{"messages[0].role", "messages[0].cache_control", "messages[1].content[0].cache_control", "messages[2].tool_calls[0].function.extra"} {
for _, path := range []string{"messages[0].role", "messages[0].cache_control", "messages[1].content[0].cache_control", "messages[1].content[2]", "messages[2].tool_calls[0].function.extra"} {
if !hasChatChange(prepared.Changes, path) {
t.Fatalf("missing change for %s", path)
}
Expand Down
Loading