Files
llmx/codex-rs/core/tests/suite/user_notification.rs

80 lines
2.8 KiB
Rust
Raw Normal View History

#![cfg(not(target_os = "windows"))]
use std::os::unix::fs::PermissionsExt;
use codex_core::protocol::EventMsg;
use codex_core::protocol::Op;
use codex_protocol::user_input::UserInput;
use core_test_support::fs_wait;
use core_test_support::responses;
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 pretty_assertions::assert_eq;
use serde_json::Value;
use serde_json::json;
use tempfile::TempDir;
use wiremock::matchers::any;
use responses::ev_assistant_message;
use responses::ev_completed;
use responses::sse;
use responses::start_mock_server;
use std::time::Duration;
#[tokio::test(flavor = "multi_thread", worker_threads = 2)]
#[ignore = "flaky on ubuntu-24.04-arm - aarch64-unknown-linux-gnu"]
// The notify script gets far enough to create (and therefore surface) the file,
// but hasnt flushed the JSON yet. Reading an empty file produces EOF while parsing
// a value at line 1 column 0. May be caused by a slow runner.
async fn summarize_context_three_requests_and_instructions() -> anyhow::Result<()> {
skip_if_no_network!(Ok(()));
let server = start_mock_server().await;
let sse1 = sse(vec![ev_assistant_message("m1", "Done"), ev_completed("r1")]);
OpenTelemetry events (#2103) ### Title ## otel Codex can emit [OpenTelemetry](https://opentelemetry.io/) **log events** that describe each run: outbound API requests, streamed responses, user input, tool-approval decisions, and the result of every tool invocation. Export is **disabled by default** so local runs remain self-contained. Opt in by adding an `[otel]` table and choosing an exporter. ```toml [otel] environment = "staging" # defaults to "dev" exporter = "none" # defaults to "none"; set to otlp-http or otlp-grpc to send events log_user_prompt = false # defaults to false; redact prompt text unless explicitly enabled ``` Codex tags every exported event with `service.name = "codex-cli"`, the CLI version, and an `env` attribute so downstream collectors can distinguish dev/staging/prod traffic. Only telemetry produced inside the `codex_otel` crate—the events listed below—is forwarded to the exporter. ### Event catalog Every event shares a common set of metadata fields: `event.timestamp`, `conversation.id`, `app.version`, `auth_mode` (when available), `user.account_id` (when available), `terminal.type`, `model`, and `slug`. With OTEL enabled Codex emits the following event types (in addition to the metadata above): - `codex.api_request` - `cf_ray` (optional) - `attempt` - `duration_ms` - `http.response.status_code` (optional) - `error.message` (failures) - `codex.sse_event` - `event.kind` - `duration_ms` - `error.message` (failures) - `input_token_count` (completion only) - `output_token_count` (completion only) - `cached_token_count` (completion only, optional) - `reasoning_token_count` (completion only, optional) - `tool_token_count` (completion only) - `codex.user_prompt` - `prompt_length` - `prompt` (redacted unless `log_user_prompt = true`) - `codex.tool_decision` - `tool_name` - `call_id` - `decision` (`approved`, `approved_for_session`, `denied`, or `abort`) - `source` (`config` or `user`) - `codex.tool_result` - `tool_name` - `call_id` - `arguments` - `duration_ms` (execution time for the tool) - `success` (`"true"` or `"false"`) - `output` ### Choosing an exporter Set `otel.exporter` to control where events go: - `none` – leaves instrumentation active but skips exporting. This is the default. - `otlp-http` – posts OTLP log records to an OTLP/HTTP collector. Specify the endpoint, protocol, and headers your collector expects: ```toml [otel] exporter = { otlp-http = { endpoint = "https://otel.example.com/v1/logs", protocol = "binary", headers = { "x-otlp-api-key" = "${OTLP_TOKEN}" } }} ``` - `otlp-grpc` – streams OTLP log records over gRPC. Provide the endpoint and any metadata headers: ```toml [otel] exporter = { otlp-grpc = { endpoint = "https://otel.example.com:4317", headers = { "x-otlp-meta" = "abc123" } }} ``` If the exporter is `none` nothing is written anywhere; otherwise you must run or point to your own collector. All exporters run on a background batch worker that is flushed on shutdown. If you build Codex from source the OTEL crate is still behind an `otel` feature flag; the official prebuilt binaries ship with the feature enabled. When the feature is disabled the telemetry hooks become no-ops so the CLI continues to function without the extra dependencies. --------- Co-authored-by: Anton Panasenko <apanasenko@openai.com>
2025-09-29 19:30:55 +01:00
responses::mount_sse_once_match(&server, any(), sse1).await;
let notify_dir = TempDir::new()?;
// write a script to the notify that touches a file next to it
let notify_script = notify_dir.path().join("notify.sh");
std::fs::write(
&notify_script,
r#"#!/bin/bash
set -e
echo -n "${@: -1}" > $(dirname "${0}")/notify.txt"#,
)?;
std::fs::set_permissions(&notify_script, std::fs::Permissions::from_mode(0o755))?;
let notify_file = notify_dir.path().join("notify.txt");
let notify_script_str = notify_script.to_str().unwrap().to_string();
let TestCodex { codex, .. } = test_codex()
.with_config(move |cfg| cfg.notify = Some(vec![notify_script_str]))
.build(&server)
.await?;
// 1) Normal user input should hit server once.
codex
.submit(Op::UserInput {
items: vec![UserInput::Text {
text: "hello world".into(),
}],
})
.await?;
wait_for_event(&codex, |ev| matches!(ev, EventMsg::TaskComplete(_))).await;
// We fork the notify script, so we need to wait for it to write to the file.
fs_wait::wait_for_path_exists(&notify_file, Duration::from_secs(5)).await?;
let notify_payload_raw = tokio::fs::read_to_string(&notify_file).await?;
let payload: Value = serde_json::from_str(&notify_payload_raw)?;
assert_eq!(payload["type"], json!("agent-turn-complete"));
assert_eq!(payload["input-messages"], json!(["hello world"]));
assert_eq!(payload["last-assistant-message"], json!("Done"));
Ok(())
}