Expose local image paths to models (#25944)

## Why

Local image attachments include image bytes, but the adjacent
model-visible label omits the source path. Exposing the path lets
model-selected workflows refer back to the intended local image
explicitly.

## What changed

- Include an escaped `path` attribute in model-visible local image
opening tags.
- Reuse the path-aware marker generator in rollout coverage.
- Update protocol, replay, and rollout coverage for the new request
shape.

## Validation

- `just fmt`
- `just test -p codex-protocol`
- `just test -p codex-core skips_local_image_label_text`
- `just test -p codex-core
copy_paste_local_image_persists_rollout_request_shape`
- `git diff --check`
This commit is contained in:
Won Park
2026-06-03 12:49:58 -07:00
committed by GitHub
Unverified
parent aeac226d16
commit 57ab4c89e0
4 changed files with 27 additions and 9 deletions
+1 -1
View File
@@ -67,7 +67,7 @@ fn parses_user_message_with_text_and_two_images() {
#[test]
fn skips_local_image_label_text() {
let image_url = "data:image/png;base64,abc".to_string();
let label = codex_protocol::models::local_image_open_tag_text(/*label_number*/ 1);
let label = r#"<image name=[Image #1] path="/tmp/local.png">"#.to_string();
let user_text = "Please review this image.".to_string();
let item = ResponseItem::Message {
+3 -1
View File
@@ -161,7 +161,9 @@ async fn copy_paste_local_image_persists_rollout_request_shape() -> anyhow::Resu
role: "user".to_string(),
content: vec![
ContentItem::InputText {
text: codex_protocol::models::local_image_open_tag_text(/*label_number*/ 1),
text: codex_protocol::models::local_image_open_tag_text_with_path(
/*label_number*/ 1, &abs_path,
),
},
ContentItem::InputImage {
image_url,
+20 -5
View File
@@ -1019,9 +1019,10 @@ pub fn local_image_label_text(label_number: usize) -> String {
format!("[Image #{label_number}]")
}
pub fn local_image_open_tag_text(label_number: usize) -> String {
pub fn local_image_open_tag_text_with_path(label_number: usize, path: &std::path::Path) -> String {
let label = local_image_label_text(label_number);
format!("{LOCAL_IMAGE_OPEN_TAG_PREFIX}{label}{LOCAL_IMAGE_OPEN_TAG_SUFFIX}")
let path = path.display();
format!("{LOCAL_IMAGE_OPEN_TAG_PREFIX}{label} path=\"{path}\"{LOCAL_IMAGE_OPEN_TAG_SUFFIX}")
}
pub fn is_local_image_open_tag_text(text: &str) -> bool {
@@ -1080,7 +1081,7 @@ pub fn local_image_content_items_with_label_number(
let mut items = Vec::with_capacity(3);
if let Some(label_number) = label_number {
items.push(ContentItem::InputText {
text: local_image_open_tag_text(label_number),
text: local_image_open_tag_text_with_path(label_number, path),
});
}
items.push(ContentItem::InputImage {
@@ -2866,7 +2867,7 @@ mod tests {
detail: None,
},
UserInput::LocalImage {
path: local_path,
path: local_path.clone(),
detail: None,
},
]);
@@ -2883,7 +2884,10 @@ mod tests {
assert_eq!(
content.get(1),
Some(&ContentItem::InputText {
text: local_image_open_tag_text(/*label_number*/ 2),
text: local_image_open_tag_text_with_path(
/*label_number*/ 2,
&local_path
),
})
);
assert!(matches!(
@@ -2903,6 +2907,17 @@ mod tests {
Ok(())
}
#[test]
fn local_image_open_tag_preserves_path() {
assert_eq!(
local_image_open_tag_text_with_path(
/*label_number*/ 1,
std::path::Path::new(r#"/tmp/a&"<b>.png"#),
),
r#"<image name=[Image #1] path="/tmp/a&"<b>.png">"#
);
}
#[test]
fn local_image_user_input_preserves_requested_detail() -> Result<()> {
let dir = tempdir()?;
+3 -2
View File
@@ -2190,8 +2190,9 @@ pub struct UserMessageEvent {
#[serde(default, skip_serializing_if = "Vec::is_empty")]
pub image_details: Vec<Option<ImageDetail>>,
/// Local file paths sourced from `UserInput::LocalImage`. These are kept so
/// the UI can reattach images when editing history, and should not be sent
/// to the model or treated as API-ready URLs.
/// the UI can reattach images when editing history. Local image prompts may
/// include a display form of the path, but these should not be treated as
/// API-ready URLs.
#[serde(default)]
pub local_images: Vec<std::path::PathBuf>,
/// Detail hints for `local_images`, indexed in parallel. Missing entries