Enable reasoning for codex-prefixed models (#2275)

## Summary
- enable reasoning for any model slug starting with `codex-`
- provide default model info for `codex-*` slugs
- test that codex models are detected and support reasoning

## Testing
- `just fmt`
- `just fix` *(fails: E0658 `let` expressions in this position are
unstable)*
- `cargo test --all-features` *(fails: E0658 `let` expressions in this
position are unstable)*

------
https://chatgpt.com/codex/tasks/task_i_689d13f8705483208a6ed21c076868e1

codex-rs/core/src/model_family.rs

@@ -78,6 +78,11 @@ pub fn find_family_for_model(slug: &str) -> Option<ModelFamily> {
             supports_reasoning_summaries: true,
             uses_local_shell_tool: true,
         )
+    } else if slug.starts_with("codex-") {
+        model_family!(
+            slug, slug,
+            supports_reasoning_summaries: true,
+        )
     } else if slug.starts_with("gpt-4.1") {
         model_family!(
             slug, "gpt-4.1",

codex-rs/core/src/openai_model_info.rs

@@ -15,7 +15,8 @@ pub(crate) struct ModelInfo {
 }
 
 pub(crate) fn get_model_info(model_family: &ModelFamily) -> Option<ModelInfo> {
-    match model_family.slug.as_str() {
+    let slug = model_family.slug.as_str();
+    match slug {
         // OSS models have a 128k shared token pool.
         // Arbitrarily splitting it: 3/4 input context, 1/4 output.
         // https://openai.com/index/gpt-oss-model-card/
@@ -82,6 +83,11 @@ pub(crate) fn get_model_info(model_family: &ModelFamily) -> Option<ModelInfo> {
             max_output_tokens: 100_000,
         }),
 
+        _ if slug.starts_with("codex-") => Some(ModelInfo {
+            context_window: 200_000,
+            max_output_tokens: 100_000,
+        }),
+
         _ => None,
     }
 }