charley-openai a6599b8202 Add reasoning effort to turn tracing spans (#20060) ...

Why
#19432 added token usage to the turn and response spans. This follow-up
adds the configured reasoning effort so performance traces can be
filtered by model effort.

[example
trace](https://openai.datadoghq.com/apm/trace/1ff708a87159ff4898bdc8bd6091ec18?graphType=waterfall&shouldShowLegend=true&spanID=6596351544047485652&traceQuery=)
<img width="533" height="434" alt="Screenshot 2026-04-28 at 3 52 12 PM"
src="https://github.com/user-attachments/assets/77ef32fc-d7cd-4eec-87b4-26c6798f1af8"
/>


What Changed
- Adds `codex.turn.reasoning_effort` to the turn span.
- Adds `codex.request.reasoning_effort` to `handle_responses`.
- Extends the span test to cover explicit `high` effort with token
usage.

Testing
- `cargo test -p codex-core
turn_and_completed_response_spans_record_token_usage`
- `cargo test -p codex-otel`
- `just fmt`
- `just fix -p codex-core`
- `just fix -p codex-otel`

2026-05-04 12:57:05 -07:00

..

common

core: fix apply_patch request permissions test (#21060)

2026-05-04 12:48:59 -07:00

fixtures

Update tests to stop using sse_completed fixture (#10638)

2026-02-04 08:38:06 -08:00

suite

Add reasoning effort to turn tracing spans (#20060)

2026-05-04 12:57:05 -07:00

all.rs

remove temporary ownership re-exports (#16626)

2026-04-03 00:33:34 -07:00

cli_responses_fixture.sse

…

responses_headers.rs

Add turn start timestamp to turn metadata (#19473)

2026-04-28 16:36:59 +00:00