mirror of
https://github.com/openai/codex.git
synced 2026-11-13 14:46:14 +00:00
Load model context from a bounded rollout suffix (#32896)
## Why Reconstructing the latest model-visible context does not require replaying an entire paginated rollout when a usable compaction checkpoint and the associated completed-turn metadata are available. ## What changed - Add `ThreadStore::load_latest_model_context` and `StoredModelContext` for loading replay-ready model context independently of full thread history. - Reverse-scan plain paginated JSONL rollouts until the newest safe bounded suffix is found, while preserving canonical session metadata and chronological replay order. - Fall back to complete history for legacy or compressed rollouts and whenever compaction or rollback records make a bounded cutoff unsafe. ## Testing - Cover checkpoint selection, turn-metadata boundaries, agent messages, contextual user fragments, and full-history fallbacks. GitOrigin-RevId: 3572f4ecc7aa4099a6d9f0d3e72d0ef432cd9497
This commit is contained in:
1 parent
7fdf2f254b
commit
592467fb96
13 files changed
+812
-17
No files matched your search
@@ -39,6 +39,7 @@ pub use types::ReadThreadParams;
|
||||
pub use types::ResumeThreadParams;
|
||||
pub use types::SearchThreadsParams;
|
||||
pub use types::SortDirection;
|
||||
pub use types::StoredModelContext;
|
||||
pub use types::StoredThread;
|
||||
pub use types::StoredThreadHistory;
|
||||
pub use types::StoredThreadItem;
|
||||
|
||||
Reference in new issue
Block a user