Skip to content

refactor: optimize agent list payload and improve multimodal detection logic #12942

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
KevinHuSh merged 2 commits into from
Feb 2, 2026
Merged

refactor: optimize agent list payload and improve multimodal detection logic #12942

Changes from 1 commit
Commits
Show all changes
2 commits
Select commit Hold shift + click to select a range
8f92519
fix(web): detect multimodal capability via tags instead of model_type
eviaaaaa Feb 2, 2026
ffa09cf
perf(api): remove dsl field from canvas list to reduce payload size
eviaaaaa Feb 2, 2026
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
Next Next commit
fix(web): detect multimodal capability via tags instead of model_type 
Since model_type only represents the primary category (e.g., 'chat'),
it cannot capture auxiliary capabilities. Switching to 'IMAGE2TEXT' tag
detection allows multimodal support for versatile models like gpt-5.2-pro.
  • Loading branch information
@eviaaaaa
eviaaaaa committed Feb 2, 2026
commit 8f9251969481a78a98a2d2929cd6ec8fbdeaf505
2 changes: 1 addition & 1 deletion web/src/pages/agent/form/agent-form/index.tsx
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -162,7 +162,7 @@ function AgentForm({ node }: INextOperatorForm) {
<FormWrapper>
{isSubAgent && <DescriptionField></DescriptionField>}
<LargeModelFormField showSpeech2TextModel></LargeModelFormField>
{findLlmByUuid(llmId)?.model_type === LlmModelType.Image2text && (
{findLlmByUuid(llmId)?.tags?.includes('IMAGE2TEXT') && (
<QueryVariable
name="visual_files_var"
label="Visual Input File"
Expand Down