Allow injecting the models manager into ThreadManager (#32911)

## Why

Embedding callers need to control whether model catalogs are persisted to disk.

## What changed

- Accept a shared models manager when constructing `ThreadManager` instead of always creating a cached manager internally.
- Add provider APIs for creating uncached model managers. OpenAI-compatible providers fetch on each `OnlineIfUncached` refresh without reading or writing `models_cache.json`.
- Keep existing app server, MCP server, sample, and test callers on the standard cached manager.

## Testing

- Verify an uncached manager fetches on every refresh.
- Verify an injected uncached manager controls thread refresh behavior and does not create `models_cache.json`.

GitOrigin-RevId: 8bb646054ecec4ccb865b2bf56249384916ea9db

codex-rs/model-provider/src/amazon_bedrock/mod.rs

@@ -172,6 +172,16 @@ impl ModelProvider for AmazonBedrockModelProvider {
             config_model_catalog.map_or_else(static_model_catalog, with_default_only_service_tier),
         ))
     }
+
+    fn models_manager_without_cache(
+        &self,
+        config_model_catalog: Option<ModelsResponse>,
+    ) -> SharedModelsManager {
+        Arc::new(StaticModelsManager::new(
+            /*auth_manager*/ None,
+            config_model_catalog.map_or_else(static_model_catalog, with_default_only_service_tier),
+        ))
+    }
 }
 
 #[cfg(test)]