feat: image resizing (#5446)

Add image resizing on the client side to reduce load on the API
This commit is contained in:
jif-oai
2025-10-27 16:58:10 +00:00
committed by GitHub
parent 775fbba6e0
commit aea7610c76
11 changed files with 684 additions and 28 deletions

View File

@@ -19,6 +19,10 @@ use core_test_support::skip_if_no_network;
use core_test_support::test_codex::TestCodex;
use core_test_support::test_codex::test_codex;
use core_test_support::wait_for_event;
use image::GenericImageView;
use image::ImageBuffer;
use image::Rgba;
use image::load_from_memory;
use serde_json::Value;
use wiremock::matchers::any;
@@ -49,6 +53,88 @@ fn extract_output_text(item: &Value) -> Option<&str> {
})
}
#[tokio::test(flavor = "multi_thread", worker_threads = 2)]
async fn user_turn_with_local_image_attaches_image() -> anyhow::Result<()> {
skip_if_no_network!(Ok(()));
let server = start_mock_server().await;
let TestCodex {
codex,
cwd,
session_configured,
..
} = test_codex().build(&server).await?;
let rel_path = "user-turn/example.png";
let abs_path = cwd.path().join(rel_path);
if let Some(parent) = abs_path.parent() {
std::fs::create_dir_all(parent)?;
}
let image = ImageBuffer::from_pixel(4096, 1024, Rgba([20u8, 40, 60, 255]));
image.save(&abs_path)?;
let response = sse(vec![
ev_response_created("resp-1"),
ev_assistant_message("msg-1", "done"),
ev_completed("resp-1"),
]);
let mock = responses::mount_sse_once_match(&server, any(), response).await;
let session_model = session_configured.model.clone();
codex
.submit(Op::UserTurn {
items: vec![UserInput::LocalImage {
path: abs_path.clone(),
}],
final_output_json_schema: None,
cwd: cwd.path().to_path_buf(),
approval_policy: AskForApproval::Never,
sandbox_policy: SandboxPolicy::DangerFullAccess,
model: session_model,
effort: None,
summary: ReasoningSummary::Auto,
})
.await?;
wait_for_event(&codex, |event| matches!(event, EventMsg::TaskComplete(_))).await;
let body = mock.single_request().body_json();
let image_message =
find_image_message(&body).expect("pending input image message not included in request");
let image_url = image_message
.get("content")
.and_then(Value::as_array)
.and_then(|content| {
content.iter().find_map(|span| {
if span.get("type").and_then(Value::as_str) == Some("input_image") {
span.get("image_url").and_then(Value::as_str)
} else {
None
}
})
})
.expect("image_url present");
let (prefix, encoded) = image_url
.split_once(',')
.expect("image url contains data prefix");
assert_eq!(prefix, "data:image/png;base64");
let decoded = BASE64_STANDARD
.decode(encoded)
.expect("image data decodes from base64 for request");
let resized = load_from_memory(&decoded).expect("load resized image");
let (width, height) = resized.dimensions();
assert!(width <= 2048);
assert!(height <= 768);
assert!(width < 4096);
assert!(height < 1024);
Ok(())
}
#[tokio::test(flavor = "multi_thread", worker_threads = 2)]
async fn view_image_tool_attaches_local_image() -> anyhow::Result<()> {
skip_if_no_network!(Ok(()));
@@ -67,8 +153,8 @@ async fn view_image_tool_attaches_local_image() -> anyhow::Result<()> {
if let Some(parent) = abs_path.parent() {
std::fs::create_dir_all(parent)?;
}
let image_bytes = b"fake_png_bytes".to_vec();
std::fs::write(&abs_path, &image_bytes)?;
let image = ImageBuffer::from_pixel(4096, 1024, Rgba([255u8, 0, 0, 255]));
image.save(&abs_path)?;
let call_id = "view-image-call";
let arguments = serde_json::json!({ "path": rel_path }).to_string();
@@ -143,11 +229,20 @@ async fn view_image_tool_attaches_local_image() -> anyhow::Result<()> {
})
.expect("image_url present");
let expected_image_url = format!(
"data:image/png;base64,{}",
BASE64_STANDARD.encode(&image_bytes)
);
assert_eq!(image_url, expected_image_url);
let (prefix, encoded) = image_url
.split_once(',')
.expect("image url contains data prefix");
assert_eq!(prefix, "data:image/png;base64");
let decoded = BASE64_STANDARD
.decode(encoded)
.expect("image data decodes from base64 for request");
let resized = load_from_memory(&decoded).expect("load resized image");
let (resized_width, resized_height) = resized.dimensions();
assert!(resized_width <= 2048);
assert!(resized_height <= 768);
assert!(resized_width < 4096);
assert!(resized_height < 1024);
Ok(())
}