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>

codex-rs/core/src/chat_completions.rs

@@ -1,6 +1,19 @@
 use std::time::Duration;
 
+use crate::ModelProviderInfo;
+use crate::client_common::Prompt;
+use crate::client_common::ResponseEvent;
+use crate::client_common::ResponseStream;
+use crate::error::CodexErr;
+use crate::error::Result;
+use crate::model_family::ModelFamily;
+use crate::openai_tools::create_tools_json_for_chat_completions_api;
+use crate::util::backoff;
 use bytes::Bytes;
+use codex_otel::otel_event_manager::OtelEventManager;
+use codex_protocol::models::ContentItem;
+use codex_protocol::models::ReasoningItemContent;
+use codex_protocol::models::ResponseItem;
 use eventsource_stream::Eventsource;
 use futures::Stream;
 use futures::StreamExt;
@@ -15,25 +28,13 @@ use tokio::time::timeout;
 use tracing::debug;
 use tracing::trace;
 
-use crate::ModelProviderInfo;
-use crate::client_common::Prompt;
-use crate::client_common::ResponseEvent;
-use crate::client_common::ResponseStream;
-use crate::error::CodexErr;
-use crate::error::Result;
-use crate::model_family::ModelFamily;
-use crate::openai_tools::create_tools_json_for_chat_completions_api;
-use crate::util::backoff;
-use codex_protocol::models::ContentItem;
-use codex_protocol::models::ReasoningItemContent;
-use codex_protocol::models::ResponseItem;
-
 /// Implementation for the classic Chat Completions API.
 pub(crate) async fn stream_chat_completions(
     prompt: &Prompt,
     model_family: &ModelFamily,
     client: &reqwest::Client,
     provider: &ModelProviderInfo,
+    otel_event_manager: &OtelEventManager,
 ) -> Result<ResponseStream> {
     if prompt.output_schema.is_some() {
         return Err(CodexErr::UnsupportedOperation(
@@ -294,10 +295,13 @@ pub(crate) async fn stream_chat_completions(
 
         let req_builder = provider.create_request_builder(client, &None).await?;
 
-        let res = req_builder
-            .header(reqwest::header::ACCEPT, "text/event-stream")
-            .json(&payload)
-            .send()
+        let res = otel_event_manager
+            .log_request(attempt, || {
+                req_builder
+                    .header(reqwest::header::ACCEPT, "text/event-stream")
+                    .json(&payload)
+                    .send()
+            })
             .await;
 
         match res {
@@ -308,6 +312,7 @@ pub(crate) async fn stream_chat_completions(
                     stream,
                     tx_event,
                     provider.stream_idle_timeout(),
+                    otel_event_manager.clone(),
                 ));
                 return Ok(ResponseStream { rx_event });
             }
@@ -351,6 +356,7 @@ async fn process_chat_sse<S>(
     stream: S,
     tx_event: mpsc::Sender<Result<ResponseEvent>>,
     idle_timeout: Duration,
+    otel_event_manager: OtelEventManager,
 ) where
     S: Stream<Item = Result<Bytes>> + Unpin,
 {
@@ -374,7 +380,10 @@ async fn process_chat_sse<S>(
     let mut reasoning_text = String::new();
 
     loop {
-        let sse = match timeout(idle_timeout, stream.next()).await {
+        let sse = match otel_event_manager
+            .log_sse_event(|| timeout(idle_timeout, stream.next()))
+            .await
+        {
             Ok(Some(Ok(ev))) => ev,
             Ok(Some(Err(e))) => {
                 let _ = tx_event