feat: use provider defaults for memory models (#27129)

## Why

Memory startup used hardcoded OpenAI model slugs for extraction and
consolidation. That works for the default OpenAI-compatible path, but
provider-specific backends can require different model identifiers. In
particular, Amazon Bedrock should use its Bedrock model ID for these
background memory requests instead of the OpenAI `gpt-5.4-mini` /
`gpt-5.4` slugs.

## What Changed

- Added provider-owned preferred memory model methods alongside
`approval_review_preferred_model`.
- Updated memory extraction and consolidation to resolve their default
model through the active `ModelProvider`.
- Added Amazon Bedrock overrides so both memory stages use
`openai.gpt-5.4` through Bedrock’s provider-specific model ID.
- Kept explicit `memories.extract_model` and
`memories.consolidation_model` config overrides taking precedence.
- Added startup coverage for default OpenAI and Bedrock memory model
selection.

#closes #26288

codex-rs/memories/write/src/phase1.rs

@@ -190,11 +190,12 @@ async fn build_request_context(
     context: &MemoryStartupContext,
     config: &Config,
 ) -> StageOneRequestContext {
-    let model_name = config
-        .memories
-        .extract_model
-        .clone()
-        .unwrap_or(crate::stage_one::MODEL.to_string());
+    let model_name = config.memories.extract_model.clone().unwrap_or_else(|| {
+        context
+            .provider()
+            .memory_extraction_preferred_model()
+            .to_string()
+    });
     context
         .stage_one_request_context(config, &model_name, crate::stage_one::REASONING_EFFORT)
         .await