2025-09-23 13:59:16 -07:00
|
|
|
|
#![cfg(not(target_os = "windows"))]
|
|
|
|
|
|
|
|
|
|
|
|
use codex_core::protocol::AskForApproval;
|
|
|
|
|
|
use codex_core::protocol::EventMsg;
|
|
|
|
|
|
use codex_core::protocol::InputItem;
|
|
|
|
|
|
use codex_core::protocol::Op;
|
|
|
|
|
|
use codex_core::protocol::SandboxPolicy;
|
|
|
|
|
|
use codex_protocol::config_types::ReasoningSummary;
|
|
|
|
|
|
use core_test_support::responses;
|
2025-09-25 13:11:14 -07:00
|
|
|
|
use core_test_support::skip_if_no_network;
|
2025-09-23 13:59:16 -07:00
|
|
|
|
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 responses::ev_assistant_message;
|
|
|
|
|
|
use responses::ev_completed;
|
|
|
|
|
|
use responses::sse;
|
|
|
|
|
|
use responses::start_mock_server;
|
|
|
|
|
|
|
|
|
|
|
|
const SCHEMA: &str = r#"
|
|
|
|
|
|
{
|
|
|
|
|
|
"type": "object",
|
|
|
|
|
|
"properties": {
|
|
|
|
|
|
"explanation": { "type": "string" },
|
|
|
|
|
|
"final_answer": { "type": "string" }
|
|
|
|
|
|
},
|
|
|
|
|
|
"required": ["explanation", "final_answer"],
|
|
|
|
|
|
"additionalProperties": false
|
|
|
|
|
|
}
|
|
|
|
|
|
"#;
|
|
|
|
|
|
|
|
|
|
|
|
#[tokio::test(flavor = "multi_thread", worker_threads = 2)]
|
2025-09-24 15:00:06 -07:00
|
|
|
|
async fn codex_returns_json_result_for_gpt5() -> anyhow::Result<()> {
|
|
|
|
|
|
codex_returns_json_result("gpt-5".to_string()).await
|
|
|
|
|
|
}
|
|
|
|
|
|
|
|
|
|
|
|
#[tokio::test(flavor = "multi_thread", worker_threads = 2)]
|
|
|
|
|
|
async fn codex_returns_json_result_for_gpt5_codex() -> anyhow::Result<()> {
|
|
|
|
|
|
codex_returns_json_result("gpt-5-codex".to_string()).await
|
|
|
|
|
|
}
|
|
|
|
|
|
|
|
|
|
|
|
async fn codex_returns_json_result(model: String) -> anyhow::Result<()> {
|
2025-09-25 13:11:14 -07:00
|
|
|
|
skip_if_no_network!(Ok(()));
|
2025-09-23 13:59:16 -07:00
|
|
|
|
|
|
|
|
|
|
let server = start_mock_server().await;
|
|
|
|
|
|
|
|
|
|
|
|
let sse1 = sse(vec![
|
|
|
|
|
|
ev_assistant_message(
|
|
|
|
|
|
"m2",
|
|
|
|
|
|
r#"{"explanation": "explanation", "final_answer": "final_answer"}"#,
|
|
|
|
|
|
),
|
|
|
|
|
|
ev_completed("r1"),
|
|
|
|
|
|
]);
|
|
|
|
|
|
|
|
|
|
|
|
let expected_schema: serde_json::Value = serde_json::from_str(SCHEMA)?;
|
|
|
|
|
|
let match_json_text_param = move |req: &wiremock::Request| {
|
|
|
|
|
|
let body: serde_json::Value = serde_json::from_slice(&req.body).unwrap_or_default();
|
|
|
|
|
|
let Some(text) = body.get("text") else {
|
|
|
|
|
|
return false;
|
|
|
|
|
|
};
|
|
|
|
|
|
let Some(format) = text.get("format") else {
|
|
|
|
|
|
return false;
|
|
|
|
|
|
};
|
|
|
|
|
|
|
|
|
|
|
|
format.get("name") == Some(&serde_json::Value::String("codex_output_schema".into()))
|
|
|
|
|
|
&& format.get("type") == Some(&serde_json::Value::String("json_schema".into()))
|
|
|
|
|
|
&& format.get("strict") == Some(&serde_json::Value::Bool(true))
|
|
|
|
|
|
&& format.get("schema") == Some(&expected_schema)
|
|
|
|
|
|
};
|
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, match_json_text_param, sse1).await;
|
2025-09-23 13:59:16 -07:00
|
|
|
|
|
|
|
|
|
|
let TestCodex { codex, cwd, .. } = test_codex().build(&server).await?;
|
|
|
|
|
|
|
|
|
|
|
|
// 1) Normal user input – should hit server once.
|
|
|
|
|
|
codex
|
|
|
|
|
|
.submit(Op::UserTurn {
|
|
|
|
|
|
items: vec![InputItem::Text {
|
|
|
|
|
|
text: "hello world".into(),
|
|
|
|
|
|
}],
|
|
|
|
|
|
final_output_json_schema: Some(serde_json::from_str(SCHEMA)?),
|
|
|
|
|
|
cwd: cwd.path().to_path_buf(),
|
|
|
|
|
|
approval_policy: AskForApproval::Never,
|
|
|
|
|
|
sandbox_policy: SandboxPolicy::DangerFullAccess,
|
2025-09-24 15:00:06 -07:00
|
|
|
|
model,
|
2025-09-23 13:59:16 -07:00
|
|
|
|
effort: None,
|
|
|
|
|
|
summary: ReasoningSummary::Auto,
|
|
|
|
|
|
})
|
|
|
|
|
|
.await?;
|
|
|
|
|
|
|
|
|
|
|
|
let message = wait_for_event(&codex, |ev| matches!(ev, EventMsg::AgentMessage(_))).await;
|
|
|
|
|
|
if let EventMsg::AgentMessage(message) = message {
|
|
|
|
|
|
let json: serde_json::Value = serde_json::from_str(&message.message)?;
|
|
|
|
|
|
assert_eq!(
|
|
|
|
|
|
json.get("explanation"),
|
|
|
|
|
|
Some(&serde_json::Value::String("explanation".into()))
|
|
|
|
|
|
);
|
|
|
|
|
|
assert_eq!(
|
|
|
|
|
|
json.get("final_answer"),
|
|
|
|
|
|
Some(&serde_json::Value::String("final_answer".into()))
|
|
|
|
|
|
);
|
|
|
|
|
|
} else {
|
|
|
|
|
|
anyhow::bail!("expected agent message event");
|
|
|
|
|
|
}
|
|
|
|
|
|
|
|
|
|
|
|
Ok(())
|
|
|
|
|
|
}
|