Use thread-scoped model catalogs for model lookups (#61421)

## Why

Model lookups through the startup catalog can use the wrong provider's capabilities or instructions after a default provider switch or when a thread has its own catalog.

## What changed

- Resolve model metadata for sampling, prediction forks, and memory writes through the owning thread's catalog.
- Make the thread's models manager available to extensions before startup callbacks and use it for guardian sampler configuration.
- Import external sessions using the destination provider and originator's catalog, loading its offline cache only when no refreshed catalog is available.

## Testing

Add regression coverage for sampling after a default provider switch, parent-specific prediction fork capabilities, thread-scoped model lookups, and imported sessions retaining destination provider instructions and originator.

GitOrigin-RevId: c86081b9e55c5e2b42a7f082966485d7fb5139d4
This commit is contained in:
Abhinav
2026-11-14 00:32:02 +00:00
committed by copyberry
parent 51f0b53d8b
commit 4598f33790
15 changed files with 215 additions and 36 deletions
+2 -3
View File
@@ -182,9 +182,8 @@ impl SampleTask {
})
.await
.map_err(|error| internal_error(error.to_string()))?;
let model = manager
.get_models_manager()
.get_model_info(
let model = parent
.model_info(
options.config.model.as_deref().unwrap_or(&snapshot.model),
&options.config.to_models_manager_config(),
)