Always send reasoning parameters in Responses requests (#32206)

## What changed

- Build a reasoning payload for every Responses request and always include `reasoning.encrypted_content`.
- Remove `supports_reasoning_summaries` from model metadata and retire the `model_supports_reasoning_summaries` configuration override.
- Use configured or model-default reasoning effort without a capability gate, including for guardian reviews and tracing.

GitOrigin-RevId: 2c9f194a5d2d4d688a2235299e6358f82ab8e1ea

codex-rs/core/src/client.rs

@@ -804,25 +804,21 @@ impl ModelClient {
         model_info: &ModelInfo,
         effort: Option<ReasoningEffortConfig>,
         summary: ReasoningSummaryConfig,
-    ) -> Option<Reasoning> {
-        if model_info.supports_reasoning_summaries {
-            Some(Reasoning {
-                effort: effort
-                    .or_else(|| model_info.default_reasoning_level.clone())
-                    .map(reasoning_effort_for_request),
-                summary: if summary == ReasoningSummaryConfig::None {
-                    None
-                } else {
-                    Some(summary)
-                },
-                // When Responses Lite is disabled, omit context so Responses uses the default,
-                // which is currently `current_turn`.
-                context: model_info
-                    .use_responses_lite
-                    .then_some(ReasoningContext::AllTurns),
-            })
-        } else {
-            None
+    ) -> Reasoning {
+        Reasoning {
+            effort: effort
+                .or_else(|| model_info.default_reasoning_level.clone())
+                .map(reasoning_effort_for_request),
+            summary: if summary == ReasoningSummaryConfig::None {
+                None
+            } else {
+                Some(summary)
+            },
+            // When Responses Lite is disabled, omit context so Responses uses the default,
+            // which is currently `current_turn`.
+            context: model_info
+                .use_responses_lite
+                .then_some(ReasoningContext::AllTurns),
         }
     }
 
@@ -871,12 +867,8 @@ impl ModelClient {
             .then_some(StreamOptions {
                 reasoning_summary_delivery: codex_api::ReasoningSummaryDelivery::SequentialCutoff,
             });
-        let reasoning = Self::build_reasoning(model_info, effort, summary);
-        let include = if reasoning.is_some() {
-            vec!["reasoning.encrypted_content".to_string()]
-        } else {
-            Vec::new()
-        };
+        let reasoning = Some(Self::build_reasoning(model_info, effort, summary));
+        let include = vec!["reasoning.encrypted_content".to_string()];
         let verbosity = if model_info.support_verbosity {
             self.state.model_verbosity.or(model_info.default_verbosity)
         } else {