mirror of
https://github.com/openai/codex.git
synced 2026-05-06 06:12:59 +03:00
we were not respecting turn's `truncation_policy` to clamp output tokens for `unified_exec` and `write_stdin`. this meant truncation was only being applied by `ContextManager` before the output was stored in-memory (so it _was_ being truncated from model-visible context), but the full output was persisted to rollout on disk. now we respect that `truncation_policy` and `ContextManager`-level truncation remains a backup. ### Tests added tests, tested locally.