Merge ff99fae4e4 into sapling-pr-archive-bolinfest

This commit is contained in:
Michael Bolin
2025-07-14 09:39:50 -07:00
committed by GitHub
10 changed files with 333 additions and 16 deletions

View File

@@ -0,0 +1,9 @@
# npm releases
Run the following:
To build the 0.2.x or later version of the npm module, which runs the Rust version of the CLI, build it as follows:
```bash
./codex-cli/scripts/stage_rust_release.py --release-version 0.6.0
```

View File

@@ -4,10 +4,7 @@
# -----------------------------------------------------------------------------
# Stages an npm release for @openai/codex.
#
# The script used to accept a single optional positional argument that indicated
# the temporary directory in which to stage the package. We now support a
# flag-based interface so that we can extend the command with further options
# without breaking the call-site contract.
# Usage:
#
# --tmp <dir> : Use <dir> instead of a freshly created temp directory.
# --native : Bundle the pre-built Rust CLI binaries for Linux alongside
@@ -141,7 +138,8 @@ popd >/dev/null
echo "Staged version $VERSION for release in $TMPDIR"
if [[ "$INCLUDE_NATIVE" -eq 1 ]]; then
echo "Test Rust:"
echo "Verify the CLI:"
echo " node ${TMPDIR}/bin/codex.js --version"
echo " node ${TMPDIR}/bin/codex.js --help"
else
echo "Test Node:"

View File

@@ -391,3 +391,116 @@ async fn stream_from_fixture(path: impl AsRef<Path>) -> Result<ResponseStream> {
tokio::spawn(process_sse(stream, tx_event));
Ok(ResponseStream { rx_event })
}
#[cfg(test)]
mod tests {
#![allow(clippy::expect_used, clippy::unwrap_used)]
use super::*;
use serde_json::json;
async fn run_sse(events: Vec<serde_json::Value>) -> Vec<ResponseEvent> {
let mut body = String::new();
for e in events {
let kind = e
.get("type")
.and_then(|v| v.as_str())
.expect("fixture event missing type");
if e.as_object().map(|o| o.len() == 1).unwrap_or(false) {
body.push_str(&format!("event: {kind}\n\n"));
} else {
body.push_str(&format!("event: {kind}\ndata: {e}\n\n"));
}
}
let (tx, mut rx) = mpsc::channel::<Result<ResponseEvent>>(8);
let stream = ReaderStream::new(std::io::Cursor::new(body)).map_err(CodexErr::Io);
tokio::spawn(process_sse(stream, tx));
let mut out = Vec::new();
while let Some(ev) = rx.recv().await {
out.push(ev.expect("channel closed"));
}
out
}
/// Verifies that the SSE adapter emits the expected [`ResponseEvent`] for
/// a variety of `type` values from the Responses API. The test is written
/// table-driven style to keep additions for new event kinds trivial.
///
/// Each `Case` supplies an input event, a predicate that must match the
/// *first* `ResponseEvent` produced by the adapter, and the total number
/// of events expected after appending a synthetic `response.completed`
/// marker that terminates the stream.
#[tokio::test]
async fn table_driven_event_kinds() {
struct TestCase {
name: &'static str,
event: serde_json::Value,
expect_first: fn(&ResponseEvent) -> bool,
expected_len: usize,
}
fn is_created(ev: &ResponseEvent) -> bool {
matches!(ev, ResponseEvent::Created)
}
fn is_output(ev: &ResponseEvent) -> bool {
matches!(ev, ResponseEvent::OutputItemDone(_))
}
fn is_completed(ev: &ResponseEvent) -> bool {
matches!(ev, ResponseEvent::Completed { .. })
}
let completed = json!({
"type": "response.completed",
"response": {
"id": "c",
"usage": {
"input_tokens": 0,
"input_tokens_details": null,
"output_tokens": 0,
"output_tokens_details": null,
"total_tokens": 0
},
"output": []
}
});
let cases = vec![
TestCase {
name: "created",
event: json!({"type": "response.created", "response": {}}),
expect_first: is_created,
expected_len: 2,
},
TestCase {
name: "output_item.done",
event: json!({
"type": "response.output_item.done",
"item": {
"type": "message",
"role": "assistant",
"content": [
{"type": "output_text", "text": "hi"}
]
}
}),
expect_first: is_output,
expected_len: 2,
},
TestCase {
name: "unknown",
event: json!({"type": "response.new_tool_event"}),
expect_first: is_completed,
expected_len: 1,
},
];
for case in cases {
let mut evs = vec![case.event];
evs.push(completed.clone());
let out = run_sse(evs).await;
assert_eq!(out.len(), case.expected_len, "case {}", case.name);
assert!((case.expect_first)(&out[0]), "case {}", case.name);
}
}
}

View File

@@ -0,0 +1,8 @@
event: response.created
data: {"type":"response.created","response":{"id":"resp1"}}
event: response.output_item.done
data: {"type":"response.output_item.done","item":{"type":"message","role":"assistant","content":[{"type":"output_text","text":"fixture hello"}]}}
event: response.completed
data: {"type":"response.completed","response":{"id":"resp1","output":[]}}

View File

@@ -0,0 +1,119 @@
#![expect(clippy::unwrap_used)]
use assert_cmd::Command as AssertCommand;
use codex_core::exec::CODEX_SANDBOX_NETWORK_DISABLED_ENV_VAR;
use tempfile::TempDir;
use wiremock::Mock;
use wiremock::MockServer;
use wiremock::ResponseTemplate;
use wiremock::matchers::method;
use wiremock::matchers::path;
/// Tests streaming chat completions through the CLI using a mock server.
/// This test:
/// 1. Sets up a mock server that simulates OpenAI's chat completions API
/// 2. Configures codex to use this mock server via a custom provider
/// 3. Sends a simple "hello?" prompt and verifies the streamed response
/// 4. Ensures the response is received exactly once and contains "hi"
#[tokio::test(flavor = "multi_thread", worker_threads = 2)]
async fn chat_mode_stream_cli() {
if std::env::var(CODEX_SANDBOX_NETWORK_DISABLED_ENV_VAR).is_ok() {
println!(
"Skipping test because it cannot execute when network is disabled in a Codex sandbox."
);
return;
}
let server = MockServer::start().await;
let sse = concat!(
"data: {\"choices\":[{\"delta\":{\"content\":\"hi\"}}]}\n\n",
"data: {\"choices\":[{\"delta\":{}}]}\n\n",
"data: [DONE]\n\n"
);
Mock::given(method("POST"))
.and(path("/v1/chat/completions"))
.respond_with(
ResponseTemplate::new(200)
.insert_header("content-type", "text/event-stream")
.set_body_raw(sse, "text/event-stream"),
)
.expect(1)
.mount(&server)
.await;
let home = TempDir::new().unwrap();
let provider_override = format!(
"model_providers.mock={{ name = \"mock\", base_url = \"{}/v1\", env_key = \"PATH\", wire_api = \"chat\" }}",
server.uri()
);
let mut cmd = AssertCommand::new("cargo");
cmd.arg("run")
.arg("-p")
.arg("codex-cli")
.arg("--quiet")
.arg("--")
.arg("exec")
.arg("--skip-git-repo-check")
.arg("-c")
.arg(&provider_override)
.arg("-c")
.arg("model_provider=\"mock\"")
.arg("-C")
.arg(env!("CARGO_MANIFEST_DIR"))
.arg("hello?");
cmd.env("CODEX_HOME", home.path())
.env("OPENAI_API_KEY", "dummy")
.env("OPENAI_BASE_URL", format!("{}/v1", server.uri()));
let output = cmd.output().unwrap();
println!("Status: {}", output.status);
println!("Stdout:\n{}", String::from_utf8_lossy(&output.stdout));
println!("Stderr:\n{}", String::from_utf8_lossy(&output.stderr));
assert!(output.status.success());
let stdout = String::from_utf8_lossy(&output.stdout);
assert!(stdout.contains("hi"));
assert_eq!(stdout.matches("hi").count(), 1);
server.verify().await;
}
/// Tests streaming responses through the CLI using a local SSE fixture file.
/// This test:
/// 1. Uses a pre-recorded SSE response fixture instead of a live server
/// 2. Configures codex to read from this fixture via CODEX_RS_SSE_FIXTURE env var
/// 3. Sends a "hello?" prompt and verifies the response
/// 4. Ensures the fixture content is correctly streamed through the CLI
#[tokio::test(flavor = "multi_thread", worker_threads = 2)]
async fn responses_api_stream_cli() {
if std::env::var(CODEX_SANDBOX_NETWORK_DISABLED_ENV_VAR).is_ok() {
println!(
"Skipping test because it cannot execute when network is disabled in a Codex sandbox."
);
return;
}
let fixture =
std::path::Path::new(env!("CARGO_MANIFEST_DIR")).join("tests/cli_responses_fixture.sse");
let home = TempDir::new().unwrap();
let mut cmd = AssertCommand::new("cargo");
cmd.arg("run")
.arg("-p")
.arg("codex-cli")
.arg("--quiet")
.arg("--")
.arg("exec")
.arg("--skip-git-repo-check")
.arg("-C")
.arg(env!("CARGO_MANIFEST_DIR"))
.arg("hello?");
cmd.env("CODEX_HOME", home.path())
.env("OPENAI_API_KEY", "dummy")
.env("CODEX_RS_SSE_FIXTURE", fixture)
.env("OPENAI_BASE_URL", "http://unused.local");
let output = cmd.output().unwrap();
assert!(output.status.success());
let stdout = String::from_utf8_lossy(&output.stdout);
assert!(stdout.contains("fixture hello"));
}

View File

@@ -0,0 +1,16 @@
[
{
"type": "response.completed",
"response": {
"id": "__ID__",
"usage": {
"input_tokens": 0,
"input_tokens_details": null,
"output_tokens": 0,
"output_tokens_details": null,
"total_tokens": 0
},
"output": []
}
}
]

View File

@@ -0,0 +1,3 @@
[
{"type": "response.output_item.done"}
]

View File

@@ -11,6 +11,7 @@ mod test_support;
use serde_json::Value;
use tempfile::TempDir;
use test_support::load_default_config_for_test;
use test_support::load_sse_fixture_with_id;
use tokio::time::timeout;
use wiremock::Match;
use wiremock::Mock;
@@ -42,12 +43,9 @@ impl Match for HasPrevId {
}
}
/// Build minimal SSE stream with completed marker.
/// Build minimal SSE stream with completed marker using the JSON fixture.
fn sse_completed(id: &str) -> String {
format!(
"event: response.completed\n\
data: {{\"type\":\"response.completed\",\"response\":{{\"id\":\"{id}\",\"output\":[]}}}}\n\n\n"
)
load_sse_fixture_with_id("tests/fixtures/completed_template.json", id)
}
#[tokio::test(flavor = "multi_thread", worker_threads = 2)]

View File

@@ -12,6 +12,8 @@ use codex_core::protocol::Op;
mod test_support;
use tempfile::TempDir;
use test_support::load_default_config_for_test;
use test_support::load_sse_fixture;
use test_support::load_sse_fixture_with_id;
use tokio::time::timeout;
use wiremock::Mock;
use wiremock::MockServer;
@@ -22,15 +24,11 @@ use wiremock::matchers::method;
use wiremock::matchers::path;
fn sse_incomplete() -> String {
// Only a single line; missing the completed event.
"event: response.output_item.done\n\n".to_string()
load_sse_fixture("tests/fixtures/incomplete_sse.json")
}
fn sse_completed(id: &str) -> String {
format!(
"event: response.completed\n\
data: {{\"type\":\"response.completed\",\"response\":{{\"id\":\"{id}\",\"output\":[]}}}}\n\n\n"
)
load_sse_fixture_with_id("tests/fixtures/completed_template.json", id)
}
#[tokio::test(flavor = "multi_thread", worker_threads = 2)]

View File

@@ -21,3 +21,58 @@ pub fn load_default_config_for_test(codex_home: &TempDir) -> Config {
)
.expect("defaults for test should always succeed")
}
/// Builds an SSE stream body from a JSON fixture.
///
/// The fixture must contain an array of objects where each object represents a
/// single SSE event with at least a `type` field matching the `event:` value.
/// Additional fields become the JSON payload for the `data:` line. An object
/// with only a `type` field results in an event with no `data:` section. This
/// makes it trivial to extend the fixtures as OpenAI adds new event kinds or
/// fields.
#[allow(dead_code)]
pub fn load_sse_fixture(path: impl AsRef<std::path::Path>) -> String {
let events: Vec<serde_json::Value> =
serde_json::from_reader(std::fs::File::open(path).expect("read fixture"))
.expect("parse JSON fixture");
events
.into_iter()
.map(|e| {
let kind = e
.get("type")
.and_then(|v| v.as_str())
.expect("fixture event missing type");
if e.as_object().map(|o| o.len() == 1).unwrap_or(false) {
format!("event: {kind}\n\n")
} else {
format!("event: {kind}\ndata: {e}\n\n")
}
})
.collect()
}
/// Same as [`load_sse_fixture`], but replaces the placeholder `__ID__` in the
/// fixture template with the supplied identifier before parsing. This lets a
/// single JSON template be reused by multiple tests that each need a unique
/// `response_id`.
#[allow(dead_code)]
pub fn load_sse_fixture_with_id(path: impl AsRef<std::path::Path>, id: &str) -> String {
let raw = std::fs::read_to_string(path).expect("read fixture template");
let replaced = raw.replace("__ID__", id);
let events: Vec<serde_json::Value> =
serde_json::from_str(&replaced).expect("parse JSON fixture");
events
.into_iter()
.map(|e| {
let kind = e
.get("type")
.and_then(|v| v.as_str())
.expect("fixture event missing type");
if e.as_object().map(|o| o.len() == 1).unwrap_or(false) {
format!("event: {kind}\n\n")
} else {
format!("event: {kind}\ndata: {e}\n\n")
}
})
.collect()
}