Stabilize skill catalogs across executor availability changes (#48353)

## Why

Changes in executor availability can alter cloud skill catalog rendering under a shared budget and repeat an unchanged executor catalog when it reconnects.

## What changed

- Cap cloud skills at three quarters of the metadata budget initially, leaving the remaining budget and unused cloud allowance for filesystem skills. Reduce the cloud cap only when doing so allows all skill entries to fit; description truncation alone does not trigger rebalancing.
- Persist the allocation across disconnects, compaction, and thread resume. Recompute it when the cloud inventory or total budget changes.
- Emit a short availability update when an unchanged selected-environment catalog returns and its full text remains in history. Reinject the full catalog when that text is missing.

## Testing

Add coverage for allocation stability, catalog and budget changes, omission handling, and full catalog reinjection after compaction and resume. Extend the selected capability stack test to verify reconnection avoids repeating the catalog.

GitOrigin-RevId: 839fe98024e00c4082a46e6a40675e15fd2c16c6
This commit is contained in:
vkg-oai
2026-09-26 04:19:46 +00:00
committed by copyberry
parent ca41ed337f
commit e72da2b538
17 changed files with 1173 additions and 233 deletions
+2 -1
View File
@@ -107,7 +107,8 @@ pub(crate) struct ContextManager {
/// also clear this when it trims a mixed initial-context developer bundle
/// whose non-diff fragments no longer exist in the surviving history.
reference_context_item: Option<TurnContextItem>,
/// World state most recently appended to model-visible history.
/// World-state comparison checkpoint. After compaction this may contain only
/// extension metadata, with model-visible context still awaiting reinjection.
world_state_baseline: Option<WorldStateSnapshot>,
}