mirror of
https://github.com/openai/codex.git
synced 2026-08-30 14:19:08 +00:00
b8b61bc692
## Why The thread inventory check compared state database rows only with plain `.jsonl` rollout files. Once a rollout was compressed to `.jsonl.zst`, the check could report its canonical database row as stale and omit the rollout from parity results. ## What changed - Scan completed compressed rollouts and match them to database rows using their canonical `.jsonl` paths. - Prefer a plain rollout when both plain and compressed siblings exist, and ignore compression temporary files. - Keep unreadable compressed rollouts in the set of existing paths so they produce scan errors without also producing misleading stale-row reports. - Use canonical paths when deriving legacy thread IDs and archived status. ## Testing Added coverage for active and archived compressed rollouts, plain/compressed siblings, metadata and legacy filename IDs, corrupt compressed data, and compression temporary files. GitOrigin-RevId: 2461376432194a4062beedbe875aa7002dd2049f