Files
llmx/codex-rs/core/tests/common/responses.rs
vishnu-oai 04c1782e52 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 11:30:55 -07:00

218 lines
6.5 KiB
Rust

use serde_json::Value;
use wiremock::BodyPrintLimit;
use wiremock::Mock;
use wiremock::MockServer;
use wiremock::Respond;
use wiremock::ResponseTemplate;
use wiremock::matchers::method;
use wiremock::matchers::path;
/// Build an SSE stream body from a list of JSON events.
pub fn sse(events: Vec<Value>) -> String {
use std::fmt::Write as _;
let mut out = String::new();
for ev in events {
let kind = ev.get("type").and_then(|v| v.as_str()).unwrap();
writeln!(&mut out, "event: {kind}").unwrap();
if !ev.as_object().map(|o| o.len() == 1).unwrap_or(false) {
write!(&mut out, "data: {ev}\n\n").unwrap();
} else {
out.push('\n');
}
}
out
}
/// Convenience: SSE event for a completed response with a specific id.
pub fn ev_completed(id: &str) -> Value {
serde_json::json!({
"type": "response.completed",
"response": {
"id": id,
"usage": {"input_tokens":0,"input_tokens_details":null,"output_tokens":0,"output_tokens_details":null,"total_tokens":0}
}
})
}
pub fn ev_completed_with_tokens(id: &str, total_tokens: u64) -> Value {
serde_json::json!({
"type": "response.completed",
"response": {
"id": id,
"usage": {
"input_tokens": total_tokens,
"input_tokens_details": null,
"output_tokens": 0,
"output_tokens_details": null,
"total_tokens": total_tokens
}
}
})
}
/// Convenience: SSE event for a single assistant message output item.
pub fn ev_assistant_message(id: &str, text: &str) -> Value {
serde_json::json!({
"type": "response.output_item.done",
"item": {
"type": "message",
"role": "assistant",
"id": id,
"content": [{"type": "output_text", "text": text}]
}
})
}
pub fn ev_function_call(call_id: &str, name: &str, arguments: &str) -> Value {
serde_json::json!({
"type": "response.output_item.done",
"item": {
"type": "function_call",
"call_id": call_id,
"name": name,
"arguments": arguments
}
})
}
pub fn ev_custom_tool_call(call_id: &str, name: &str, input: &str) -> Value {
serde_json::json!({
"type": "response.output_item.done",
"item": {
"type": "custom_tool_call",
"call_id": call_id,
"name": name,
"input": input
}
})
}
pub fn ev_local_shell_call(call_id: &str, status: &str, command: Vec<&str>) -> Value {
serde_json::json!({
"type": "response.output_item.done",
"item": {
"type": "local_shell_call",
"call_id": call_id,
"status": status,
"action": {
"type": "exec",
"command": command,
}
}
})
}
/// Convenience: SSE event for an `apply_patch` custom tool call with raw patch
/// text. This mirrors the payload produced by the Responses API when the model
/// invokes `apply_patch` directly (before we convert it to a function call).
pub fn ev_apply_patch_custom_tool_call(call_id: &str, patch: &str) -> Value {
serde_json::json!({
"type": "response.output_item.done",
"item": {
"type": "custom_tool_call",
"name": "apply_patch",
"input": patch,
"call_id": call_id
}
})
}
/// Convenience: SSE event for an `apply_patch` function call. The Responses API
/// wraps the patch content in a JSON string under the `input` key; we recreate
/// the same structure so downstream code exercises the full parsing path.
pub fn ev_apply_patch_function_call(call_id: &str, patch: &str) -> Value {
let arguments = serde_json::json!({ "input": patch });
let arguments = serde_json::to_string(&arguments).expect("serialize apply_patch arguments");
serde_json::json!({
"type": "response.output_item.done",
"item": {
"type": "function_call",
"name": "apply_patch",
"arguments": arguments,
"call_id": call_id
}
})
}
pub fn sse_response(body: String) -> ResponseTemplate {
ResponseTemplate::new(200)
.insert_header("content-type", "text/event-stream")
.set_body_raw(body, "text/event-stream")
}
pub async fn mount_sse_once_match<M>(server: &MockServer, matcher: M, body: String)
where
M: wiremock::Match + Send + Sync + 'static,
{
Mock::given(method("POST"))
.and(path("/v1/responses"))
.and(matcher)
.respond_with(sse_response(body))
.up_to_n_times(1)
.mount(server)
.await;
}
pub async fn mount_sse_once(server: &MockServer, body: String) {
Mock::given(method("POST"))
.and(path("/v1/responses"))
.respond_with(sse_response(body))
.expect(1)
.mount(server)
.await;
}
pub async fn mount_sse(server: &MockServer, body: String) {
Mock::given(method("POST"))
.and(path("/v1/responses"))
.respond_with(sse_response(body))
.mount(server)
.await;
}
pub async fn start_mock_server() -> MockServer {
MockServer::builder()
.body_print_limit(BodyPrintLimit::Limited(80_000))
.start()
.await
}
/// Mounts a sequence of SSE response bodies and serves them in order for each
/// POST to `/v1/responses`. Panics if more requests are received than bodies
/// provided. Also asserts the exact number of expected calls.
pub async fn mount_sse_sequence(server: &MockServer, bodies: Vec<String>) {
use std::sync::atomic::AtomicUsize;
use std::sync::atomic::Ordering;
struct SeqResponder {
num_calls: AtomicUsize,
responses: Vec<String>,
}
impl Respond for SeqResponder {
fn respond(&self, _: &wiremock::Request) -> ResponseTemplate {
let call_num = self.num_calls.fetch_add(1, Ordering::SeqCst);
match self.responses.get(call_num) {
Some(body) => ResponseTemplate::new(200)
.insert_header("content-type", "text/event-stream")
.set_body_string(body.clone()),
None => panic!("no response for {call_num}"),
}
}
}
let num_calls = bodies.len();
let responder = SeqResponder {
num_calls: AtomicUsize::new(0),
responses: bodies,
};
Mock::given(method("POST"))
.and(path("/v1/responses"))
.respond_with(responder)
.expect(num_calls as u64)
.mount(server)
.await;
}