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
This commit is contained in:
Owen Lin authored and copyberry committed 2026-08-31 21:15:38 +00:00
1 parent a7913390f7
commit 5f79a92e39
67 files changed
+932 -162

No files matched your search

@@ -578,6 +578,7 @@ impl TurnContext {
let cwd = self.cwd.clone();
TurnContextItem {
turn_id: Some(self.sub_id.clone()),
root_turn_id: self.turn_metadata_state.root_turn_id(),
cwd,
workspace_roots: (!workspace_roots.is_empty()).then_some(workspace_roots),
current_date: self.current_date.clone(),