Commit Graph
8 Commits
Author SHA1 Message Date
felixxia-oai 5971d42847 Preserve verified answers across history compaction (#42293)
## Why

Compaction replaces the model history window, but host-verified user answers may
still be needed for the rest of the owning thread.

## What changed

- Add bounded, model-invisible retained context for verified
  `request_user_input` answers.
- Persist retained context in rollout events and compaction checkpoints, and
  restore it when a thread resumes.
- Remove answers when their source turns are rolled back, and prevent
  parent-local answers from being inherited by child forks.

## Testing

Add lifecycle coverage for deduplication and size limits, compaction and resume,
rollback, rollout migration, and child forks.

GitOrigin-RevId: c32900d3e8120a9899b71f0576683acd67a4b898
2026-09-02 15:07:11 +00:00
Owen Lin 5f79a92e39 Persist response token usage in rollout history (#41912)
## Why

Resumed threads need to continue per-turn and per-thread token totals without scanning arbitrarily far beyond the latest compaction checkpoint.

## What changed

- Add durable `TokenUsageRecord` rollout items with response, turn, thread, session, and root-turn attribution.
- Restore accumulated usage on resume and snapshot the latest record plus the compaction response ID in compaction checkpoints.
- Preserve root-turn lineage in persisted turn context, while ensuring forked child threads start with their own usage totals.

## Testing

- Cover usage accumulation across multiple responses and resumed turns.
- Cover local and remote compaction checkpoints, invalid remote compaction output, rollout reconstruction, and fork isolation.

GitOrigin-RevId: ef9e0c4a9102a08a2c382be4cdac68c84353c90a
2026-08-31 21:15:38 +00:00
Bryan Ashley f88ff940c0 Load bounded context after empty wake turns (#41901)
## Why

Paginated threads can accumulate wake turns with no user-message boundary. The
reverse context scan could not use those turns as a bounded replay cutoff, even
when a compaction and its resume state provided everything needed to reconstruct
the latest model context.

## What changed

Treat a full world-state snapshot that survives the latest compaction as a
durable baseline when it is paired with a compatible turn context. This lets the
scan stop at empty wake turns while still scanning further back for patches,
snapshots before compaction, or missing and mismatched turn contexts.

## Testing

Add coverage for repeated empty wake turns and verify that bounded replay
matches full rollout reconstruction across successive compaction windows.

GitOrigin-RevId: ae90c5f939c660ea539fbfc11128cc7259efaa9c
2026-08-31 19:30:05 +00:00
guinness-oai 41ca88e95c Persist realtime events in the thread timeline (#40508)
## Why

Clients need a bounded view of realtime conversations that preserves the order of speech, agent work, and turn lifecycle events without loading the full thread history.

## What changed

- Persist realtime session boundaries, transcript segments, and promoted agent items in paginated thread rollouts.
- Add the experimental `thread/timeline/list` API to page ordinary items, realtime items, and turn boundaries in canonical rollout order. Include `activeRealtimeSessionAtPageStart` so each page can be rendered independently.
- Emit typed `thread/realtime/item/started`, `thread/realtime/item/transcript/delta`, and `thread/realtime/item/completed` notifications around durable realtime items.
- Keep the existing `thread/items/list` response and legacy thread history behavior unchanged.

## Testing

- Cover mixed timeline pagination, realtime-session state at page boundaries, rollout replay, subagent history prefixes, transcript streaming, steering, and promoted agent artifacts.

GitOrigin-RevId: faa2c420192d63e060e8fb32446e3c797422656e
2026-08-25 01:03:20 +00:00
jif 72fa74fbc9 Persist security risk scores in rollout history (#38363)
## What changed

- Add a `SecurityRiskScore` rollout item containing a category and numeric score.
- Persist the item in both thread history modes while excluding it from model context, user-visible thread history, search text, forks, and reconstructed conversation history.
- Re-export the score type from the extension API.

## Testing

- Cover serialization, persistence and loading, thread history projection, session reconstruction, append planning, and memory filtering.

GitOrigin-RevId: 1926fe366aeaa75052708a6da589f45a38eefb52
2026-08-13 12:04:29 +00:00
rka-oai 3a6f747d77 Preserve harness metadata across conversation history (#38058)
## What changed

- Wrap response items with optional harness-owned metadata while keeping the persisted response payload shape backward compatible.
- Store compacted-history metadata in an aligned sidecar and reject malformed sidecars.
- Carry metadata through history normalization, compaction, resume, fork, truncation, migration, and rollout recording without sending it to model providers.

## Testing

- Cover legacy rollout compatibility, metadata serialization and validation, compaction retention, and resume/fork reconstruction.

GitOrigin-RevId: 17a6127c9048ff984cb4df4d97c0751a38c29f5f
2026-08-11 19:30:12 +00:00
Adam Perry @ OpenAI 63002bdb26 Extract persisted history types into a dedicated crate (#37871)
## What changed

- Add `codex-history` for model-history and persisted-rollout domain types, including `RolloutItem`, `RolloutLine`, `CompactedItem`, and initial/resumed history state.
- Re-export the persisted types from `codex-rollout` and update consumers to use the new crate boundary instead of `codex-protocol`.
- Preserve existing rollout serialization, including legacy numeric compacted-window IDs.

## Testing

- Add `codex-history` tests for rollout JSON round trips, compacted-history compatibility, persisted history modes, and multi-agent version selection.

GitOrigin-RevId: 944daa9297ddd231d3aebbdcb05fff4adf8b4e1b
2026-08-10 19:26:52 +00:00
Owen Lin 592467fb96 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
2026-07-13 23:29:59 +00:00