[apply-patch] Clean up apply-patch tool definitions (#2539)
## Summary We've experienced a bit of drift in system prompting for `apply_patch`: - As pointed out in #2030 , our prettier formatting started altering prompt.md in a few ways - We introduced a separate markdown file for apply_patch instructions in #993, but currently duplicate them in the prompt.md file - We added a first-class apply_patch tool in #2303, which has yet another definition This PR starts to consolidate our logic in a few ways: - We now only use `apply_patch_tool_instructions.md](https://github.com/openai/codex/compare/dh--apply-patch-tool-definition?expand=1#diff-d4fffee5f85cb1975d3f66143a379e6c329de40c83ed5bf03ffd3829df985bea) for system instructions - We no longer include apply_patch system instructions if the tool is specified I'm leaving the definition in openai_tools.rs as duplicated text for now because we're going to be iterated on the first-class tool soon. ## Testing - [x] Added integration tests to verify prompt stability - [x] Tested locally with several different models (gpt-5, gpt-oss, o4-mini)
This commit is contained in:
Dylan
GitHub
@@ -25,6 +25,179 @@ fn sse_completed(id: &str) -> String {
|
||||
load_sse_fixture_with_id("tests/fixtures/completed_template.json", id)
|
||||
}
|
||||
|
||||
#[tokio::test(flavor = "multi_thread", worker_threads = 4)]
|
||||
async fn default_system_instructions_contain_apply_patch() {
|
||||
use pretty_assertions::assert_eq;
|
||||
|
||||
let server = MockServer::start().await;
|
||||
|
||||
let sse = sse_completed("resp");
|
||||
let template = ResponseTemplate::new(200)
|
||||
.insert_header("content-type", "text/event-stream")
|
||||
.set_body_raw(sse, "text/event-stream");
|
||||
|
||||
// Expect two POSTs to /v1/responses
|
||||
Mock::given(method("POST"))
|
||||
.and(path("/v1/responses"))
|
||||
.respond_with(template)
|
||||
.expect(2)
|
||||
.mount(&server)
|
||||
.await;
|
||||
|
||||
let model_provider = ModelProviderInfo {
|
||||
base_url: Some(format!("{}/v1", server.uri())),
|
||||
..built_in_model_providers()["openai"].clone()
|
||||
};
|
||||
|
||||
let cwd = TempDir::new().unwrap();
|
||||
let codex_home = TempDir::new().unwrap();
|
||||
let mut config = load_default_config_for_test(&codex_home);
|
||||
config.cwd = cwd.path().to_path_buf();
|
||||
config.model_provider = model_provider;
|
||||
config.user_instructions = Some("be consistent and helpful".to_string());
|
||||
|
||||
let conversation_manager = ConversationManager::default();
|
||||
let codex = conversation_manager
|
||||
.new_conversation_with_auth(config, Some(CodexAuth::from_api_key("Test API Key")))
|
||||
.await
|
||||
.expect("create new conversation")
|
||||
.conversation;
|
||||
|
||||
codex
|
||||
.submit(Op::UserInput {
|
||||
items: vec![InputItem::Text {
|
||||
text: "hello 1".into(),
|
||||
}],
|
||||
})
|
||||
.await
|
||||
.unwrap();
|
||||
wait_for_event(&codex, |ev| matches!(ev, EventMsg::TaskComplete(_))).await;
|
||||
|
||||
codex
|
||||
.submit(Op::UserInput {
|
||||
items: vec![InputItem::Text {
|
||||
text: "hello 2".into(),
|
||||
}],
|
||||
})
|
||||
.await
|
||||
.unwrap();
|
||||
wait_for_event(&codex, |ev| matches!(ev, EventMsg::TaskComplete(_))).await;
|
||||
|
||||
let requests = server.received_requests().await.unwrap();
|
||||
assert_eq!(requests.len(), 2, "expected two POST requests");
|
||||
|
||||
let expected_instructions = [
|
||||
include_str!("../prompt.md"),
|
||||
include_str!("../../apply-patch/apply_patch_tool_instructions.md"),
|
||||
]
|
||||
.join("\n");
|
||||
|
||||
let body0 = requests[0].body_json::<serde_json::Value>().unwrap();
|
||||
assert_eq!(
|
||||
body0["instructions"],
|
||||
serde_json::json!(expected_instructions),
|
||||
);
|
||||
let body1 = requests[1].body_json::<serde_json::Value>().unwrap();
|
||||
assert_eq!(
|
||||
body1["instructions"],
|
||||
serde_json::json!(expected_instructions),
|
||||
);
|
||||
}
|
||||
|
||||
#[tokio::test(flavor = "multi_thread", worker_threads = 4)]
|
||||
async fn prompt_tools_are_consistent_across_requests() {
|
||||
use pretty_assertions::assert_eq;
|
||||
|
||||
let server = MockServer::start().await;
|
||||
|
||||
let sse = sse_completed("resp");
|
||||
let template = ResponseTemplate::new(200)
|
||||
.insert_header("content-type", "text/event-stream")
|
||||
.set_body_raw(sse, "text/event-stream");
|
||||
|
||||
// Expect two POSTs to /v1/responses
|
||||
Mock::given(method("POST"))
|
||||
.and(path("/v1/responses"))
|
||||
.respond_with(template)
|
||||
.expect(2)
|
||||
.mount(&server)
|
||||
.await;
|
||||
|
||||
let model_provider = ModelProviderInfo {
|
||||
base_url: Some(format!("{}/v1", server.uri())),
|
||||
..built_in_model_providers()["openai"].clone()
|
||||
};
|
||||
|
||||
let cwd = TempDir::new().unwrap();
|
||||
let codex_home = TempDir::new().unwrap();
|
||||
let mut config = load_default_config_for_test(&codex_home);
|
||||
config.cwd = cwd.path().to_path_buf();
|
||||
config.model_provider = model_provider;
|
||||
config.user_instructions = Some("be consistent and helpful".to_string());
|
||||
config.include_apply_patch_tool = true;
|
||||
config.include_plan_tool = true;
|
||||
|
||||
let conversation_manager = ConversationManager::default();
|
||||
let codex = conversation_manager
|
||||
.new_conversation_with_auth(config, Some(CodexAuth::from_api_key("Test API Key")))
|
||||
.await
|
||||
.expect("create new conversation")
|
||||
.conversation;
|
||||
|
||||
codex
|
||||
.submit(Op::UserInput {
|
||||
items: vec![InputItem::Text {
|
||||
text: "hello 1".into(),
|
||||
}],
|
||||
})
|
||||
.await
|
||||
.unwrap();
|
||||
wait_for_event(&codex, |ev| matches!(ev, EventMsg::TaskComplete(_))).await;
|
||||
|
||||
codex
|
||||
.submit(Op::UserInput {
|
||||
items: vec![InputItem::Text {
|
||||
text: "hello 2".into(),
|
||||
}],
|
||||
})
|
||||
.await
|
||||
.unwrap();
|
||||
wait_for_event(&codex, |ev| matches!(ev, EventMsg::TaskComplete(_))).await;
|
||||
|
||||
let requests = server.received_requests().await.unwrap();
|
||||
assert_eq!(requests.len(), 2, "expected two POST requests");
|
||||
|
||||
let expected_instructions: &str = include_str!("../prompt.md");
|
||||
// our internal implementation is responsible for keeping tools in sync
|
||||
// with the OpenAI schema, so we just verify the tool presence here
|
||||
let expected_tools_names: &[&str] = &["shell", "update_plan", "apply_patch"];
|
||||
fn assert_tool_names(body: &serde_json::Value, expected_names: &[&str]) {
|
||||
assert_eq!(
|
||||
body["tools"]
|
||||
.as_array()
|
||||
.unwrap()
|
||||
.iter()
|
||||
.map(|t| t["name"].as_str().unwrap().to_string())
|
||||
.collect::<Vec<_>>(),
|
||||
expected_names
|
||||
);
|
||||
}
|
||||
|
||||
let body0 = requests[0].body_json::<serde_json::Value>().unwrap();
|
||||
assert_eq!(
|
||||
body0["instructions"],
|
||||
serde_json::json!(expected_instructions),
|
||||
);
|
||||
assert_tool_names(&body0, expected_tools_names);
|
||||
|
||||
let body1 = requests[1].body_json::<serde_json::Value>().unwrap();
|
||||
assert_eq!(
|
||||
body1["instructions"],
|
||||
serde_json::json!(expected_instructions),
|
||||
);
|
||||
assert_tool_names(&body1, expected_tools_names);
|
||||
}
|
||||
|
||||
#[tokio::test(flavor = "multi_thread", worker_threads = 2)]
|
||||
async fn prefixes_context_and_instructions_once_and_consistently_across_requests() {
|
||||
use pretty_assertions::assert_eq;
|
||||
|
||||
Reference in New Issue
Block a user