[codex] Support sequential cutoff reasoning summaries (#31306)

## Summary

When enabled for the OpenAI provider, Codex sends
`stream_options.reasoning_summary_delivery = "sequential_cutoff"` on
HTTP and
WebSocket requests, including prewarm, and renders completed summary
sections
from `reasoning_summary_text.done`. Flag-off and non-OpenAI behavior is
unchanged.

## Expected rollout

```text
reasoning 0 added
summary 0 done
summary 1 done
summary 2 starts
summary 2 cancelled / incomplete
reasoning 0 done  <-- cancel summary 2 work and mark it incomplete
message 1 added
message 1 text streams
message 1 completed
```

Depends on
[openai/openai#1096660](https://github.com/openai/openai/pull/1096660).

codex-rs/core/src/client_tests.rs

@@ -103,6 +103,7 @@ fn test_model_client_with_thread_id(
         /*include_timing_metrics*/ false,
         /*beta_features_header*/ None,
         /*item_ids_enabled*/ false,
+        /*concurrent_reasoning_summaries_enabled*/ false,
         /*attestation_provider*/ None,
     )
 }
@@ -147,6 +148,7 @@ async fn compact_uses_bearer_after_agent_identity_session_fallback() -> anyhow::
         /*include_timing_metrics*/ false,
         /*beta_features_header*/ None,
         /*item_ids_enabled*/ false,
+        /*concurrent_reasoning_summaries_enabled*/ false,
         /*attestation_provider*/ None,
     );
     let prompt = Prompt {
@@ -821,6 +823,7 @@ fn model_client_with_counting_attestation(
         /*include_timing_metrics*/ false,
         /*beta_features_header*/ None,
         /*item_ids_enabled*/ false,
+        /*concurrent_reasoning_summaries_enabled*/ false,
         Some(Arc::new(CountingAttestationProvider {
             calls: attestation_calls.clone(),
         })),