Preserve image detail in app-server inputs (#20693)

## Summary

- Add optional image detail to user image inputs across core, app-server
v2, thread history/event mapping, and the generated app-server
schemas/types.
- Preserve requested detail when serializing Responses image inputs:
omitted detail stays on the existing `high` default, while explicit
`original` keeps local images on the original-resolution path.
- Support `high`/`original` consistently for tool image outputs,
including MCP `codex/imageDetail`, code-mode image helpers, and
`view_image`.
This commit is contained in:
Curtis 'Fjord' Hawthorne authored and GitHub committed 2026-05-15 15:04:04 -07:00
1 parent 249d50aafc
commit 8543e39885
81 files changed
+1302 -156

No files matched your search

+2 -1
View File
@@ -90,9 +90,10 @@ fn parse_user_message(message: &[ContentItem]) -> Option<UserMessageItem> {
text_elements: Vec::new(),
});
}
ContentItem::InputImage { image_url, .. } => {
ContentItem::InputImage { image_url, detail } => {
content.push(UserInput::Image {
image_url: image_url.clone(),
detail: *detail,
});
}
ContentItem::OutputText { text } => {