mirror of
https://github.com/openai/codex.git
synced 2026-11-18 22:20:48 +00:00
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:
@@ -1054,6 +1054,7 @@ impl Session {
|
||||
thread_extension_init.insert(codex_extension_api::ThreadOriginator(
|
||||
session_configuration.originator.clone(),
|
||||
));
|
||||
thread_extension_init.insert(Arc::clone(&models_manager));
|
||||
// Publish the already resolved model before extensions make startup decisions.
|
||||
// Turn construction refreshes this attachment when the selected model changes.
|
||||
thread_extension_init.insert(Arc::unwrap_or_clone(model_info.model));
|
||||
|
||||
Reference in New Issue
Block a user