mirror of
https://github.com/openai/codex.git
synced 2026-10-26 18:38:47 +00:00
## Why The generic `parent_compaction_error` classification metric does not distinguish serialization failures, oversized compactions, and unusable compactions. ## What changed Record separate `failure_reason` values for each case: `parent_compaction_serialization`, `parent_compaction_oversized`, and `parent_compaction_unusable`. ## Testing Extend parent-compaction reuse tests to cover unusable checkpoints in parent-context mode and assert specific failure reasons. Verify rejected compactions receive the maximum risk score, provide no cached approval, and do not reuse stale context. GitOrigin-RevId: 103c4173b2ebbdc33eb71bce7f8ecb56f73055f6