mirror of
https://github.com/pchuan98/codex.git
synced 2026-07-01 00:31:56 +08:00
## Summary Stabilize `js_repl` runtime test setup in CI and move tool-facing `js_repl` behavior coverage into integration tests. This is a test/CI change only. No production `js_repl` behavior change is intended. ## Why - Bazel test sandboxes (especially on macOS) could resolve a different `node` than the one installed by `actions/setup-node`, which caused `js_repl` runtime/version failures. - `js_repl` runtime tests depend on platform-specific sandbox/test-harness behavior, so they need explicit gating in a base-stability commit. - Several tests in the `js_repl` unit test module were actually black-box/tool-level behavior tests and fit better in the integration suite. ## Changes - Add `actions/setup-node` to the Bazel and Rust `Tests` workflows, using the exact version pinned in the repo’s Node version file. - In Bazel (non-Windows), pass `CODEX_JS_REPL_NODE_PATH=$(which node)` into test env so `js_repl` uses the `actions/setup-node` runtime inside Bazel tests. - Add a new integration test suite for `js_repl` tool behavior and register it in the core integration test suite module. - Move black-box `js_repl` behavior tests into the integration suite (persistence/TLA, builtin tool invocation, recursive self-call rejection, `process` isolation, blocked builtin imports). - Keep white-box manager/kernel tests in the `js_repl` unit test module. - Gate `js_repl` runtime tests to run only on macOS and only when a usable Node runtime is available (skip on other platforms / missing Node in this commit). ## Impact - Reduces `js_repl` CI failures caused by Node resolution drift in Bazel. - Improves test organization by separating tool-facing behavior tests from white-box manager/kernel tests. - Keeps the base commit stable while expanding `js_repl` runtime coverage. #### [git stack](https://github.com/magus/git-stack-cli) - ✅ `1` https://github.com/openai/codex/pull/12372 - 👉 `2` https://github.com/openai/codex/pull/12407 - ⏳ `3` https://github.com/openai/codex/pull/12185 - ⏳ `4` https://github.com/openai/codex/pull/10673
138 lines
3.4 KiB
Rust
138 lines
3.4 KiB
Rust
// Aggregates all former standalone integration tests as modules.
|
|
use std::ffi::OsString;
|
|
|
|
use codex_arg0::Arg0PathEntryGuard;
|
|
use codex_arg0::arg0_dispatch;
|
|
use ctor::ctor;
|
|
use tempfile::TempDir;
|
|
|
|
struct TestCodexAliasesGuard {
|
|
_codex_home: TempDir,
|
|
_arg0: Arg0PathEntryGuard,
|
|
_previous_codex_home: Option<OsString>,
|
|
}
|
|
|
|
const CODEX_HOME_ENV_VAR: &str = "CODEX_HOME";
|
|
|
|
// This code runs before any other tests are run.
|
|
// It allows the test binary to behave like codex and dispatch to apply_patch and codex-linux-sandbox
|
|
// based on the arg0.
|
|
// NOTE: this doesn't work on ARM
|
|
#[ctor]
|
|
pub static CODEX_ALIASES_TEMP_DIR: TestCodexAliasesGuard = unsafe {
|
|
#[allow(clippy::unwrap_used)]
|
|
let codex_home = tempfile::Builder::new()
|
|
.prefix("codex-core-tests")
|
|
.tempdir()
|
|
.unwrap();
|
|
let previous_codex_home = std::env::var_os(CODEX_HOME_ENV_VAR);
|
|
// arg0_dispatch() creates helper links under CODEX_HOME/tmp. Point it at a
|
|
// test-owned temp dir so startup never mutates the developer's real ~/.codex.
|
|
//
|
|
// Safety: #[ctor] runs before tests start, so no test threads exist yet.
|
|
unsafe {
|
|
std::env::set_var(CODEX_HOME_ENV_VAR, codex_home.path());
|
|
}
|
|
|
|
#[allow(clippy::unwrap_used)]
|
|
let arg0 = arg0_dispatch().unwrap();
|
|
// Restore the process environment immediately so later tests observe the
|
|
// same CODEX_HOME state they started with.
|
|
match previous_codex_home.as_ref() {
|
|
Some(value) => unsafe {
|
|
std::env::set_var(CODEX_HOME_ENV_VAR, value);
|
|
},
|
|
None => unsafe {
|
|
std::env::remove_var(CODEX_HOME_ENV_VAR);
|
|
},
|
|
}
|
|
|
|
TestCodexAliasesGuard {
|
|
_codex_home: codex_home,
|
|
_arg0: arg0,
|
|
_previous_codex_home: previous_codex_home,
|
|
}
|
|
};
|
|
|
|
#[cfg(not(target_os = "windows"))]
|
|
mod abort_tasks;
|
|
mod agent_jobs;
|
|
mod agent_websocket;
|
|
mod apply_patch_cli;
|
|
#[cfg(not(target_os = "windows"))]
|
|
mod approvals;
|
|
mod auth_refresh;
|
|
mod cli_stream;
|
|
mod client;
|
|
mod client_websockets;
|
|
mod codex_delegate;
|
|
mod collaboration_instructions;
|
|
mod compact;
|
|
mod compact_remote;
|
|
mod compact_resume_fork;
|
|
mod deprecation_notice;
|
|
mod exec;
|
|
mod exec_policy;
|
|
mod fork_thread;
|
|
mod grep_files;
|
|
mod hierarchical_agents;
|
|
mod image_rollout;
|
|
mod items;
|
|
mod js_repl;
|
|
mod json_result;
|
|
mod list_dir;
|
|
mod live_cli;
|
|
mod live_reload;
|
|
mod model_info_overrides;
|
|
mod model_overrides;
|
|
mod model_switching;
|
|
mod model_tools;
|
|
mod model_visible_layout;
|
|
mod models_cache_ttl;
|
|
mod models_etag_responses;
|
|
mod otel;
|
|
mod pending_input;
|
|
mod permissions_messages;
|
|
mod personality;
|
|
mod personality_migration;
|
|
mod prompt_caching;
|
|
mod quota_exceeded;
|
|
mod read_file;
|
|
mod realtime_conversation;
|
|
mod remote_models;
|
|
mod request_compression;
|
|
#[cfg(not(target_os = "windows"))]
|
|
mod request_permissions;
|
|
mod request_user_input;
|
|
mod resume;
|
|
mod resume_warning;
|
|
mod review;
|
|
mod rmcp_client;
|
|
mod rollout_list_find;
|
|
mod safety_check_downgrade;
|
|
mod search_tool;
|
|
mod seatbelt;
|
|
mod shell_command;
|
|
mod shell_serialization;
|
|
mod shell_snapshot;
|
|
mod skill_approval;
|
|
mod skills;
|
|
mod sqlite_state;
|
|
mod stream_error_allows_next_turn;
|
|
mod stream_no_completed;
|
|
mod subagent_notifications;
|
|
mod text_encoding_fix;
|
|
mod tool_harness;
|
|
mod tool_parallelism;
|
|
mod tools;
|
|
mod truncation;
|
|
mod turn_state;
|
|
mod undo;
|
|
mod unified_exec;
|
|
mod unstable_features_warning;
|
|
mod user_notification;
|
|
mod user_shell_cmd;
|
|
mod view_image;
|
|
mod web_search;
|
|
mod websocket_fallback;
|