codex

mirror of https://github.com/openai/codex.git synced 2026-10-23 18:08:45 +00:00

Files

T

Dmitriy Kovalenko 07cc649c65 Avoid double-counting retained reasoning in token usage (#55991 )

## Why

Responses Lite includes retained reasoning in its reported token usage even without an `X-Reasoning-Included` header. Adding a separate reasoning estimate can trigger automatic compaction prematurely. Locally recomputed usage also already includes retained reasoning.

## What changed

Initialize reasoning accounting from `use_responses_lite` before each sampling or compaction request, while allowing server events to override it. Mark locally recomputed token usage as including reasoning.

## Testing

Update the compaction regression test to verify that Responses Lite usage without the header stays below an 81-token limit at 80 tokens and triggers compaction at 81 tokens.

GitOrigin-RevId: 06f9272cb3c259e927941f1d2a1d7096310ffb2c

2026-10-21 21:23:01 +00:00

common

Drain WebSocket responses on mailbox preemption (#55969 )

2026-10-21 19:29:08 +00:00

remote_env_windows

Bind capability roots to environment selections (#51493 )

2026-10-06 22:39:32 +00:00

suite

Avoid double-counting retained reasoning in token usage (#55991 )

2026-10-21 21:23:01 +00:00

all.rs

[codex] Use expect in integration tests (#28441 )