Files
llmx/codex-rs/exec/tests/suite/output_schema.rs

68 lines
2.1 KiB
Rust
Raw Normal View History

#![cfg(not(target_os = "windows"))]
#![allow(clippy::expect_used, clippy::unwrap_used)]
use core_test_support::responses;
use core_test_support::test_codex_exec::test_codex_exec;
use serde_json::Value;
use wiremock::matchers::any;
#[tokio::test(flavor = "multi_thread", worker_threads = 2)]
async fn exec_includes_output_schema_in_request() -> anyhow::Result<()> {
let test = test_codex_exec();
let schema_contents = serde_json::json!({
"type": "object",
"properties": {
"answer": { "type": "string" }
},
"required": ["answer"],
"additionalProperties": false
});
let schema_path = test.cwd_path().join("schema.json");
std::fs::write(&schema_path, serde_json::to_vec_pretty(&schema_contents)?)?;
let expected_schema: Value = schema_contents;
let server = responses::start_mock_server().await;
let body = responses::sse(vec![
responses::ev_response_created("resp1"),
responses::ev_assistant_message("m1", "fixture hello"),
responses::ev_completed("resp1"),
]);
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(), body).await;
test.cmd_with_server(&server)
.arg("--skip-git-repo-check")
// keep using -C in the test to exercise the flag as well
.arg("-C")
.arg(test.cwd_path())
.arg("--output-schema")
.arg(&schema_path)
.arg("-m")
.arg("gpt-5")
.arg("tell me a joke")
.assert()
.success();
let requests = server
.received_requests()
.await
.expect("failed to capture requests");
assert_eq!(requests.len(), 1, "expected exactly one request");
let payload: Value = serde_json::from_slice(&requests[0].body)?;
let text = payload.get("text").expect("request missing text field");
let format = text
.get("format")
.expect("request missing text.format field");
assert_eq!(
format,
&serde_json::json!({
"name": "codex_output_schema",
"type": "json_schema",
"strict": true,
"schema": expected_schema,
})
);
Ok(())
}