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/protocol/src/openai_models.rs

@@ -375,7 +375,6 @@ pub struct ModelInfo {
     pub model_messages: Option<ModelMessages>,
     #[serde(default)]
     pub include_skills_usage_instructions: bool,
-    pub supports_reasoning_summaries: bool,
     #[serde(default)]
     pub default_reasoning_summary: ReasoningSummary,
     pub support_verbosity: bool,
@@ -678,7 +677,6 @@ mod tests {
             base_instructions: "base".to_string(),
             model_messages: spec,
             include_skills_usage_instructions: false,
-            supports_reasoning_summaries: false,
             default_reasoning_summary: ReasoningSummary::Auto,
             support_verbosity: false,
             default_verbosity: None,
@@ -981,7 +979,6 @@ mod tests {
             "upgrade": null,
             "base_instructions": "base",
             "model_messages": null,
-            "supports_reasoning_summaries": false,
             "default_reasoning_summary": "auto",
             "support_verbosity": false,
             "default_verbosity": null,