Add collaboration modes test prompts (#9443)

# External (non-OpenAI) Pull Request Requirements

Before opening this Pull Request, please read the dedicated
"Contributing" markdown file or your PR may be closed:
https://github.com/openai/codex/blob/main/docs/contributing.md

If your PR conforms to our contribution guidelines, replace this text
with a detailed and high quality description of your changes.

Include a link to a bug report or enhancement request.
This commit is contained in:
Ahmed Ibrahim
2026-01-18 11:39:08 -08:00
committed by GitHub
parent 0a568a47fd
commit f72f87fbee
13 changed files with 251 additions and 36 deletions

View File

@@ -1,9 +1,11 @@
//! Validates that the collaboration mode list endpoint returns the expected default presets.
//!
//! The test drives the app server through the MCP harness and asserts that the list response
//! includes the plan, collaborate, and execute modes with their default model and reasoning
//! includes the plan, pair programming, and execute modes with their default model and reasoning
//! effort settings, which keeps the API contract visible in one place.
#![allow(clippy::unwrap_used)]
use std::time::Duration;
use anyhow::Result;
@@ -13,9 +15,8 @@ use codex_app_server_protocol::CollaborationModeListParams;
use codex_app_server_protocol::CollaborationModeListResponse;
use codex_app_server_protocol::JSONRPCResponse;
use codex_app_server_protocol::RequestId;
use codex_core::models_manager::test_builtin_collaboration_mode_presets;
use codex_protocol::config_types::CollaborationMode;
use codex_protocol::config_types::Settings;
use codex_protocol::openai_models::ReasoningEffort;
use pretty_assertions::assert_eq;
use tempfile::TempDir;
use tokio::time::timeout;
@@ -43,7 +44,7 @@ async fn list_collaboration_modes_returns_presets() -> Result<()> {
let CollaborationModeListResponse { data: items } =
to_response::<CollaborationModeListResponse>(response)?;
let expected = vec![plan_preset(), collaborate_preset(), execute_preset()];
let expected = vec![plan_preset(), pair_programming_preset(), execute_preset()];
assert_eq!(expected, items);
Ok(())
}
@@ -53,23 +54,23 @@ async fn list_collaboration_modes_returns_presets() -> Result<()> {
/// If the defaults change in the app server, this helper should be updated alongside the
/// contract, or the test will fail in ways that imply a regression in the API.
fn plan_preset() -> CollaborationMode {
CollaborationMode::Plan(Settings {
model: "gpt-5.2-codex".to_string(),
reasoning_effort: Some(ReasoningEffort::Medium),
developer_instructions: None,
})
let presets = test_builtin_collaboration_mode_presets();
presets
.into_iter()
.find(|p| matches!(p, CollaborationMode::Plan(_)))
.unwrap()
}
/// Builds the collaborate preset that the list response is expected to return.
/// Builds the pair programming preset that the list response is expected to return.
///
/// The helper keeps the expected model and reasoning defaults co-located with the test
/// so that mismatches point directly at the API contract being exercised.
fn collaborate_preset() -> CollaborationMode {
CollaborationMode::Collaborate(Settings {
model: "gpt-5.2-codex".to_string(),
reasoning_effort: Some(ReasoningEffort::Medium),
developer_instructions: None,
})
fn pair_programming_preset() -> CollaborationMode {
let presets = test_builtin_collaboration_mode_presets();
presets
.into_iter()
.find(|p| matches!(p, CollaborationMode::PairProgramming(_)))
.unwrap()
}
/// Builds the execute preset that the list response is expected to return.
@@ -77,9 +78,9 @@ fn collaborate_preset() -> CollaborationMode {
/// The execute preset uses a different reasoning effort to capture the higher-effort
/// execution contract the server currently exposes.
fn execute_preset() -> CollaborationMode {
CollaborationMode::Execute(Settings {
model: "gpt-5.2-codex".to_string(),
reasoning_effort: Some(ReasoningEffort::XHigh),
developer_instructions: None,
})
let presets = test_builtin_collaboration_mode_presets();
presets
.into_iter()
.find(|p| matches!(p, CollaborationMode::Execute(_)))
.unwrap()
}